From 73370f38a53926d7b9d6373dbb57cb1a772cbb14 Mon Sep 17 00:00:00 2001 From: Tarzelf Date: Sat, 10 Oct 2026 07:52:51 -0400 Subject: [PATCH] Publish DVIDIA Observation Lab engineering pilot and open-source links --- README.md | 2 + .../reports/DVIDIA Observation Lab pilot.md | 44 ++++++++++ .../runs/2026-10-10-observation-lab/README.md | 29 +++++++ .../episode-summary.json | 80 +++++++++++++++++++ .../hardened-protocol.json | 1 + .../hardened-run.json | 1 + .../initial-protocol.json | 1 + .../initial-run.json | 1 + .../ui-validation.json | 22 +++++ docs/feed.xml | 2 +- docs/index.html | 2 +- .../index.html | 2 +- docs/papers/dvidia-observation-lab/index.html | 24 ++++++ .../index.html | 2 +- .../from-skillspace-to-robot-skill/index.html | 2 +- .../grok-robotics-research-on-x/index.html | 2 +- .../index.html | 2 +- .../physical-skill-research-agenda/index.html | 2 +- .../robotics-research-pipeline/index.html | 2 +- .../skill-capsule-acquisition/index.html | 2 +- .../skillspace-arm-benchmarks/index.html | 2 +- .../skillspace-arm-installation/index.html | 2 +- .../skillspace-footage-training/index.html | 2 +- .../index.html | 2 +- docs/publications.json | 14 ++++ docs/sitemap.xml | 2 +- docs/topics/capture-quality/index.html | 2 +- docs/topics/evaluation-provenance/index.html | 2 +- docs/topics/physical-grounding/index.html | 2 +- docs/topics/skill-relations/index.html | 2 +- publications.json | 14 ++++ reports/DVIDIA Observation Lab pilot.md | 44 ++++++++++ .../runs/2026-10-10-observation-lab/README.md | 29 +++++++ .../episode-summary.json | 80 +++++++++++++++++++ .../hardened-protocol.json | 1 + .../hardened-run.json | 1 + .../initial-protocol.json | 1 + .../initial-run.json | 1 + .../ui-validation.json | 22 +++++ 39 files changed, 431 insertions(+), 19 deletions(-) create mode 100644 docs/downloads/reports/DVIDIA Observation Lab pilot.md create mode 100644 docs/downloads/topics/evaluation-provenance/runs/2026-10-10-observation-lab/README.md create mode 100644 docs/downloads/topics/evaluation-provenance/runs/2026-10-10-observation-lab/episode-summary.json create mode 100644 docs/downloads/topics/evaluation-provenance/runs/2026-10-10-observation-lab/hardened-protocol.json create mode 100644 docs/downloads/topics/evaluation-provenance/runs/2026-10-10-observation-lab/hardened-run.json create mode 100644 docs/downloads/topics/evaluation-provenance/runs/2026-10-10-observation-lab/initial-protocol.json create mode 100644 docs/downloads/topics/evaluation-provenance/runs/2026-10-10-observation-lab/initial-run.json create mode 100644 docs/downloads/topics/evaluation-provenance/runs/2026-10-10-observation-lab/ui-validation.json create mode 100644 docs/papers/dvidia-observation-lab/index.html create mode 100644 reports/DVIDIA Observation Lab pilot.md create mode 100644 topics/evaluation-provenance/runs/2026-10-10-observation-lab/README.md create mode 100644 topics/evaluation-provenance/runs/2026-10-10-observation-lab/episode-summary.json create mode 100644 topics/evaluation-provenance/runs/2026-10-10-observation-lab/hardened-protocol.json create mode 100644 topics/evaluation-provenance/runs/2026-10-10-observation-lab/hardened-run.json create mode 100644 topics/evaluation-provenance/runs/2026-10-10-observation-lab/initial-protocol.json create mode 100644 topics/evaluation-provenance/runs/2026-10-10-observation-lab/initial-run.json create mode 100644 topics/evaluation-provenance/runs/2026-10-10-observation-lab/ui-validation.json diff --git a/README.md b/README.md index 007973d..1883a45 100644 --- a/README.md +++ b/README.md @@ -26,6 +26,8 @@ All four covers are **AI-generated editorial illustrations**, not footage, measu ## Latest studies +[DVIDIA Observation Lab pilot](reports/DVIDIA%20Observation%20Lab%20pilot.md) publishes our local video detection and review workflow: sampled object/palm proposals, editable timeline revisions and JSON export. Each recorded engineering run completed six public excerpts (19 seconds and 38 sampled frames); independent annotation accuracy remains unmeasured. [Read the paper](https://research.dvidia.org/papers/dvidia-observation-lab/), [install the versioned open-source release](https://github.com/Dvidia-Inference/dvidia-training/releases/tag/observation-lab-v0.1.0), or [try the synthetic browser review demo](https://huggingface.co/spaces/Dvidia/observation-lab). The hosted demo uses authored clips and boxes; real detection runs locally with separately provisioned upstream models. No action captions, validated depth or robot skill are established. + [Robotics research pipeline](reports/Robotics%20research%20pipeline.md) maps the path from Skillspace originals and synchronized robot measurements to reviewed episodes, local training, frozen simulation evaluation and compatible skill installation. The diagram distinguishes implemented simulation components from proposed automatic labeling and a learned task supervisor. A new annotation-labor pilot and feedback-supervisor experiment are specified; neither has been run, and physical robot qualification remains open. [Read the public architecture](https://research.dvidia.org/papers/robotics-research-pipeline/). [Skillspace footage training pipeline](reports/Skillspace%20footage%20training%20pipeline.md) introduces the standalone [DVIDIA Training repository](https://github.com/Dvidia-Inference/dvidia-training): audit actual footage, freeze connected source groups, fit visual weights locally and export inspectable results. Its optional movement branch requires aligned numerical actions and a supported simulation adapter. The separate [frozen sample-count benchmark](https://github.com/Dvidia-Inference/dvidia-training/blob/main/benchmarks/sample-count-19047/README.md) compares two, four and seven training groups on the same twelve layouts: nominal completion is 8/8, 7/8 and 8/8; actuator-stress completion is 3/4 for each, and all 36 matched open-jaw controls fail. This single composition-order pilot establishes no sufficient video count, human-video action bridge or hardware skill. [Inspect the protocol, outcomes and recorded evidence release](https://github.com/Dvidia-Inference/dvidia-training/releases/tag/benchmark-2026-10-08). diff --git a/docs/downloads/reports/DVIDIA Observation Lab pilot.md b/docs/downloads/reports/DVIDIA Observation Lab pilot.md new file mode 100644 index 0000000..efc7d68 --- /dev/null +++ b/docs/downloads/reports/DVIDIA Observation Lab pilot.md @@ -0,0 +1,44 @@ +# DVIDIA Observation Lab pilot + +**Engineering integration passed on six public excerpts; annotation accuracy remains unmeasured.** On 10 October 2026, we ran a local observation pipeline that decodes video, proposes sampled object and palm boxes, associates nearby detections and opens an editable review timeline. Review changes persist as revisions and export with their source identity. This establishes a working research tool, not reliable automatic task labeling, a cup-placement benchmark or a trained robot skill. The published implementation is anchored to [DVIDIA Training commit d355a4a](https://github.com/Dvidia-Inference/dvidia-training/tree/d355a4a284cf9bcc4f48dd375ca072d2da188dad). + +[Install the Observation Lab release](https://github.com/Dvidia-Inference/dvidia-training/blob/observation-lab-v0.1.0/docs/observations.md) · [GitHub release and downloads](https://github.com/Dvidia-Inference/dvidia-training/releases/tag/observation-lab-v0.1.0) · [Try the synthetic review demo](https://huggingface.co/spaces/Dvidia/observation-lab) · [Frozen engineering receipts](https://research.dvidia.org/downloads/topics/evaluation-provenance/runs/2026-10-10-observation-lab/README.md) + +## The pilot produces reviewable 2D evidence + +The local adapter uses the pinned OpenCV Zoo YOLOX COCO object detector and MediaPipe palm detector. It samples at two frames per second, up to 120 frames and a 640-pixel maximum image side per clip. Proposals retain decoded presentation timestamps, frame and source hashes, raw labels and scores. Same-class image overlap associates detections; palm/object overlap proposes 2D proximity. Neither association establishes physical identity nor overlap proves touching. Palm rectangles are not full-hand segmentation. No optical flow, depth reconstruction, natural-language action captioner or language model participates in this pilot. ([Observation contract](https://github.com/Dvidia-Inference/dvidia-training/blob/d355a4a284cf9bcc4f48dd375ca072d2da188dad/docs/observations.md), [frozen model and recipe](https://research.dvidia.org/downloads/topics/evaluation-provenance/runs/2026-10-10-observation-lab/hardened-protocol.json)) + +The review interface shares one clock between the original video and timeline. It displays a box only within 0.25 seconds of its sampled timestamp, leaving gaps visible. Reviewers can correct labels and boundaries, approve or reject proposals and add missed events. Raw model labels remain separate from the accepted draft. Outcomes default to `unknown`; `visible_completion` and `incomplete` describe the operator's visual assessment. They are not robot-success measurements. ([Review interface contract](https://github.com/Dvidia-Inference/dvidia-training/blob/d355a4a284cf9bcc4f48dd375ca072d2da188dad/docs/observation-ui.md)) + +Saving appends a revision with conflict detection against the current base revision. A stale tab cannot silently replace newer edits. Every event needs a decision before review completion; unsaved changes trigger navigation protection, and export is disabled until saving. Downloads contain the last saved review, episode ID and original source hash. These checks make corrections inspectable. They do not authenticate the operator or turn agreement into independent ground truth. The loopback server performs no uploads and checks the local origin for writes. ([Local workflow](https://github.com/Dvidia-Inference/dvidia-training/blob/d355a4a284cf9bcc4f48dd375ca072d2da188dad/docs/observations.md)) + +## Six excerpts establish integration, not accuracy + +The fixed input order was shirt, stir, pack, onion, melon and jeans, selected before examining model output. Five excerpts come from EgoAnnotate, credited to Taher Panbiharwala and Zainab Barwaniwala; the stir excerpt comes from CoMind, with its full author credit retained in the protocol. The records identify CC BY 4.0 terms and upstream source links. We hash-verified the exact excerpts; full upstream originals were not downloaded or hash-verified for this run. This publication distributes sanitized receipts rather than footage or sampled frames. ([Input protocol and credits](https://research.dvidia.org/downloads/topics/evaluation-provenance/runs/2026-10-10-observation-lab/initial-protocol.json)) + +The six excerpts total **19 seconds, 2,753,287 bytes and 38 sampled frames**. They are neither independent complete attempts nor the intended cup-placement cohort. Unknown session provenance remains one conservative shared group. There was no training split, learning run or physical evaluation. Publisher titles were display metadata and were not fed to the detector. ([Episode summary](https://research.dvidia.org/downloads/topics/evaluation-provenance/runs/2026-10-10-observation-lab/episode-summary.json), [run and grouping](https://research.dvidia.org/downloads/topics/evaluation-provenance/runs/2026-10-10-observation-lab/hardened-run.json)) + +| Recipe attempt | Completed / attempted excerpts | Processing time | Recorded failures | +| --- | ---: | ---: | ---: | +| Initial v1 | 6/6 | 4.835 seconds | 0 | +| Hardened v1.1 | 6/6 | 4.635 seconds | 0 | + +These are two single runs on the same inputs and a warm macOS ARM64 machine. Timing includes intake, copy/hash, decoding, detection, association and per-episode writes. It excludes model provisioning/loading, final receipt writing, UI startup and human review. The difference is not a controlled speedup. Peak RAM, energy, cost, p95 latency, minimum hardware and production throughput were not measured. No paid inference API was called. The runtime used Python 3.12.9, OpenCV 5.0.0.93 and NumPy 2.5.3. Execution requested four CPU threads and one inference worker, while frozen OpenCV metadata records ten threads; an enforced thread cap was not independently verified. No GPU path was requested or measured. ([Initial receipt](https://research.dvidia.org/downloads/topics/evaluation-provenance/runs/2026-10-10-observation-lab/initial-run.json), [hardened receipt](https://research.dvidia.org/downloads/topics/evaluation-provenance/runs/2026-10-10-observation-lab/hardened-run.json), [full frozen protocols](https://research.dvidia.org/downloads/topics/evaluation-provenance/runs/2026-10-10-observation-lab/README.md), [original benchmark description](https://github.com/Dvidia-Inference/dvidia-training/blob/d355a4a284cf9bcc4f48dd375ca072d2da188dad/benchmarks/observation-20261010/README.md)) + +## Workflow checks preserve failures and revisions + +Review after the initial run identified a possible browser-clock mismatch for nonzero-start videos. Recipe v1.1 rejects nonzero container, video or decoded starts rather than silently moving boxes against an unchanged original. All six inputs have zero starts and were accepted in both runs. Initial artifacts remain alongside the hardened attempt. Same-size media replacement, malformed review IDs and oversized metadata also received workflow checks. These changes do not establish improved detector quality. ([Original and revised recipes](https://research.dvidia.org/downloads/topics/evaluation-provenance/runs/2026-10-10-observation-lab/README.md)) + +The implementation records 307 passing repository tests followed by 24 focused observation tests, including four additional detector-admission/suppression checks. Fifteen browser checks exercised playback, sampled overlays, correction save/reload, manual events, export, unsaved edits and completion validation on an isolated copy. The 390px and 320px layouts had no horizontal overflow; no browser console or page errors were recorded. These are interface and software checks, not physical-phone, Safari or annotation-accuracy qualification. Test edits do not count as independent human references. ([Test scope](https://github.com/Dvidia-Inference/dvidia-training/blob/d355a4a284cf9bcc4f48dd375ca072d2da188dad/benchmarks/observation-20261010/README.md), [browser receipt](https://research.dvidia.org/downloads/topics/evaluation-provenance/runs/2026-10-10-observation-lab/ui-validation.json)) + +Qualitative inspection found a saucepan labeled cup, storage jars labeled cups and missed palms in the preliminary stir check. These observations are not a scored accuracy estimate. COCO categories omit task-specific objects; overlap association can fragment or switch identities; two samples per second can miss brief actions. Model scores remain uncalibrated and all automatic outcomes remain unknown. Without independent references, inspection reports `accuracy: null` and `accuracy_status: not_assessed`. ([Recorded limitations](https://github.com/Dvidia-Inference/dvidia-training/blob/d355a4a284cf9bcc4f48dd375ca072d2da188dad/benchmarks/observation-20261010/README.md)) + +## The release keeps ownership and missing evidence explicit + +DVIDIA owns the orchestration, intake, timing, proposal association, review contract and workflow. Original DVIDIA Training code remains MIT. Detector preprocessing/postprocessing adapted from OpenCV Zoo retains Apache-2.0 attribution, and the pinned detector artifacts retain their separate upstream licenses and credits. The two ONNX files total about 40 MB and are provisioned explicitly with size/hash verification; inference does not download weights. Model terms do not grant rights to input footage. No new foundation model, SpatialLM, MANO or depth-model weights are claimed. ([Exact artifacts and notices](https://github.com/Dvidia-Inference/dvidia-training/blob/d355a4a284cf9bcc4f48dd375ca072d2da188dad/docs/observation-models.md)) + +This lab is upstream of robot learning. Image rectangles supply no calibrated XYZ, contact forces, joint actions, gripper commands or robot policy. No automatic physical action is produced, and the existing visual predictor and movement head gain no new skill from this release. The next proposed study collects 30–50 complete permission-cleared cup-placement attempts with explicit session/person grouping, failures, occlusion and recovery. Independent blinded references should precede comparisons of detector-only, temporal-caption, combined and manual annotation at matched quality, correction time and full cost. Depth, a supervised action bridge and closed-loop qualification require separate experiments. ([Uncollected cohort and gates](https://github.com/Dvidia-Inference/dvidia-training/blob/d355a4a284cf9bcc4f48dd375ca072d2da188dad/docs/observation-pilot-plan.md)) + +The public [Hugging Face Observation Lab Space](https://huggingface.co/spaces/Dvidia/observation-lab) reuses our review interface with two authored geometric videos and authored image boxes. It is a synthetic workflow demonstration: no detector, VLM or robot policy runs in the hosted page. Revisions stay in each visitor's browser, with a visible temporary-memory fallback if browser storage or cross-tab locking is unavailable. Visitors can edit, save and export their own review without server writes. The actual detector pipeline is installed and run locally on permitted footage. All sixteen hosted files were read anonymously at [Space commit 8547b78](https://huggingface.co/spaces/Dvidia/observation-lab/tree/8547b78f312e39d9a0b299ebe055c401f8135848) and compared with the staged hashes. The public runtime was observed running with its synthetic scope labels visible. + +Publication preparation reran 311 repository tests and separately checked 22 publisher tests, six synthetic preparation/privacy/media tests and browser-local revision/conflict behavior. Both pinned ONNX detectors loaded and ran on a neutral image in the local CPU runtime; that smoke test measures neither detection accuracy nor task understanding. [Release source](https://github.com/Dvidia-Inference/dvidia-training/tree/3cc4a3b03ca6d61479c9f6a86cebf7ccc77fd117) preserves the original pilot receipts and clarifies the requested-versus-reported thread discrepancy. Original code uses MIT and the detector adapter retains its Apache-2.0 notices. Production uploads, accounts, storage and application analysis remain separate from this research release. diff --git a/docs/downloads/topics/evaluation-provenance/runs/2026-10-10-observation-lab/README.md b/docs/downloads/topics/evaluation-provenance/runs/2026-10-10-observation-lab/README.md new file mode 100644 index 0000000..8726c50 --- /dev/null +++ b/docs/downloads/topics/evaluation-provenance/runs/2026-10-10-observation-lab/README.md @@ -0,0 +1,29 @@ +# DVIDIA Observation Lab public evidence + +Six public excerpts completed two local detector/review engineering attempts on +10 October 2026. Accuracy was not assessed, all automatic outcomes remain unknown, +and no robot skill was trained or qualified. + +The six JSON documents here are byte-for-byte copies of the public benchmark +records in [DVIDIA Training commit d355a4a](https://github.com/Dvidia-Inference/dvidia-training/tree/d355a4a284cf9bcc4f48dd375ca072d2da188dad/benchmarks/observation-20261010). +They retain model/source credits, license declarations, hashes, timing scope, +grouping, complete attempted-run denominators and interface-check scope. + +[Read the paper](../../../../reports/DVIDIA%20Observation%20Lab%20pilot.md) · +[Original benchmark description](https://github.com/Dvidia-Inference/dvidia-training/blob/d355a4a284cf9bcc4f48dd375ca072d2da188dad/benchmarks/observation-20261010/README.md) + +| Evidence | Scope | +| --- | --- | +| [Initial protocol](initial-protocol.json) | First frozen source order, excerpt identities, model recipe and declared limits | +| [Initial run](initial-run.json) | Six attempted/completed excerpts, no failures, timing and source grouping | +| [Hardened protocol](hardened-protocol.json) | Revised zero-start admission recipe and model/license provenance | +| [Hardened run](hardened-run.json) | Separate second-attempt receipt on the same six inputs | +| [Episode summary](episode-summary.json) | Per-excerpt duration, proposal count, processing time and source hash | +| [Browser checks](ui-validation.json) | Isolated review-copy behavior; no model-accuracy inference | + +Raw media, sampled frames, weights, private metadata and test review edits are not +redistributed in this evidence folder. A receipt hash binds a retained artifact; +it does not establish authenticity, semantic truth or reproduction without the +permitted inputs. Full upstream-original hashes were not independently verified. +The six excerpts share one conservative unknown-session group and cannot be +counted as six independent complete cup-placement attempts. diff --git a/docs/downloads/topics/evaluation-provenance/runs/2026-10-10-observation-lab/episode-summary.json b/docs/downloads/topics/evaluation-provenance/runs/2026-10-10-observation-lab/episode-summary.json new file mode 100644 index 0000000..a6cf4a6 --- /dev/null +++ b/docs/downloads/topics/evaluation-provenance/runs/2026-10-10-observation-lab/episode-summary.json @@ -0,0 +1,80 @@ +[ + { + "id": "shirt", + "duration_seconds": 3.0, + "metrics": { + "accuracy_status": "not_assessed", + "detected_frames": 6, + "elapsed_seconds": 0.6693273328710347, + "frames": 6, + "inference_seconds": 0.46699687489308417 + }, + "proposals": 7, + "source_sha256": "8392c62f4e9590a15745311746114c2b6355e24c60fa87fef68e834f20762113" + }, + { + "id": "stir", + "duration_seconds": 4.0, + "metrics": { + "accuracy_status": "not_assessed", + "detected_frames": 8, + "elapsed_seconds": 1.1173061658628285, + "frames": 8, + "inference_seconds": 0.6056890829931945 + }, + "proposals": 25, + "source_sha256": "4ffe78850d4e6475546a521e0eb425f7a34c632679183cf112aacb70ec1b0861" + }, + { + "id": "pack", + "duration_seconds": 3.0, + "metrics": { + "accuracy_status": "not_assessed", + "detected_frames": 6, + "elapsed_seconds": 0.6751292911358178, + "frames": 6, + "inference_seconds": 0.4420628750231117 + }, + "proposals": 7, + "source_sha256": "87a67e5b10f124a65df7d669086d4a9b2cb7ae25a5d758594b9b3aa7b0938f4c" + }, + { + "id": "onion", + "duration_seconds": 3.0, + "metrics": { + "accuracy_status": "not_assessed", + "detected_frames": 6, + "elapsed_seconds": 0.7398202081676573, + "frames": 6, + "inference_seconds": 0.43661770783364773 + }, + "proposals": 10, + "source_sha256": "100e25698ee99e99dc648c41d9864144e312f0fce7c07dc9a7b06b487b9a2a5f" + }, + { + "id": "melon", + "duration_seconds": 3.0, + "metrics": { + "accuracy_status": "not_assessed", + "detected_frames": 6, + "elapsed_seconds": 0.7281540830153972, + "frames": 6, + "inference_seconds": 0.4237409171182662 + }, + "proposals": 14, + "source_sha256": "f32cf75d28602d169b4f302830ba633a351ac890596887c54c8e928efcf2650e" + }, + { + "id": "jeans", + "duration_seconds": 3.0, + "metrics": { + "accuracy_status": "not_assessed", + "detected_frames": 6, + "elapsed_seconds": 0.6997090000659227, + "frames": 6, + "inference_seconds": 0.4299595837946981 + }, + "proposals": 9, + "source_sha256": "95845362951b3f78b7b731691df6d472bf176ced4b07ecef4d99d0b8a21da3e2" + } +] diff --git a/docs/downloads/topics/evaluation-provenance/runs/2026-10-10-observation-lab/hardened-protocol.json b/docs/downloads/topics/evaluation-provenance/runs/2026-10-10-observation-lab/hardened-protocol.json new file mode 100644 index 0000000..f424e21 --- /dev/null +++ b/docs/downloads/topics/evaluation-provenance/runs/2026-10-10-observation-lab/hardened-protocol.json @@ -0,0 +1 @@ +{"created_at":"2026-10-10T11:22:03.270961+00:00","execution":"local_offline","hardware":{"machine":"arm64","platform":"Darwin"},"kind":"dvidia.observation-protocol.v1","limits":{"cpu_threads":4,"workers":1},"manifest_sha256":"6e4e3a0b1b12eeb32cafcba0668d2614c80b022a91eafc7740018be880eddb29","model":{"backend":"opencv","coordinates":"normalized_image_xyxy","cpu_threads":10,"device":"cpu","hand_box_semantics":"Palm detector rectangle; not full hand segmentation or observed contact.","hand_detector_enabled":true,"hand_threshold":0.5,"implementation_sha256":"e1c6939779ab39a32497e00c35892a98eef59c3dd512135f1ac6cd4f897d1a22","implementation_version":1,"kind":"opencv-zoo-yolox-palm","limitations":["COCO labels can be wrong or absent, especially for small and occluded objects.","Palm boxes do not establish finger contact, grasp, force, depth, task success or robot actions.","Object identity and temporal relationships require a separate tracking stage."],"max_detections":30,"max_nms_candidates":1000,"models":[{"bytes":35858002,"directory":"object_detection_yolox","download_url":"https://media.githubusercontent.com/media/opencv/opencv_zoo/47534e27c9851bb1128ccc0102f1145e27f23f98/models/object_detection_yolox/object_detection_yolox_2022nov.onnx","license":"Apache-2.0","license_bytes":11371,"license_sha256":"0ec3668d3274bcf29e8a29e9576d5a2cd96fc78d3c5bec4387355a796e5d9088","license_url":"https://raw.githubusercontent.com/opencv/opencv_zoo/47534e27c9851bb1128ccc0102f1145e27f23f98/models/object_detection_yolox/LICENSE","name":"object_detection_yolox_2022nov.onnx","revision":"47534e27c9851bb1128ccc0102f1145e27f23f98","role":"objects","sha256":"c5c2d13e59ae883e6af3b45daea64af4833a4951c92d116ec270d9ddbe998063","source":"https://github.com/opencv/opencv_zoo/blob/47534e27c9851bb1128ccc0102f1145e27f23f98/models/object_detection_yolox/object_detection_yolox_2022nov.onnx"},{"bytes":3905734,"directory":"palm_detection_mediapipe","download_url":"https://media.githubusercontent.com/media/opencv/opencv_zoo/47534e27c9851bb1128ccc0102f1145e27f23f98/models/palm_detection_mediapipe/palm_detection_mediapipe_2023feb.onnx","license":"Apache-2.0","license_bytes":11358,"license_sha256":"cfc7749b96f63bd31c3c42b5c471bf756814053e847c10f3eb003417bc523d30","license_url":"https://raw.githubusercontent.com/opencv/opencv_zoo/47534e27c9851bb1128ccc0102f1145e27f23f98/models/palm_detection_mediapipe/LICENSE","name":"palm_detection_mediapipe_2023feb.onnx","revision":"47534e27c9851bb1128ccc0102f1145e27f23f98","role":"palms","sha256":"78ff51c38496b7fc8b8ebdb6cc8c1abb02fa6c38427c6848254cdaba57fcce7c","source":"https://github.com/opencv/opencv_zoo/blob/47534e27c9851bb1128ccc0102f1145e27f23f98/models/palm_detection_mediapipe/palm_detection_mediapipe_2023feb.onnx"}],"nms_iou":{"objects":0.5,"palms":0.3},"runtime":{"numpy":"2.5.3","opencv":"5.0.0"},"score_kind":"uncalibrated_model_evidence","threshold":0.35},"recipe":{"automatic_outcome":"unknown","claim_scope":"sampled_2d_observations","id":"dvidia-observations-v1.1","max_duration_seconds":60,"max_frames":120,"max_image_side":640,"max_track_gap_seconds":0.8,"minimum_association_iou":0.2,"samples_per_second":2,"timebase":"zero-origin video and container; nonzero starts rejected"},"sources":[{"credit":"Taher Panbiharwala and Zainab Barwaniwala; EgoAnnotate v1; excerpt starts 0s, original full hash not verified","id":"shirt","kind":"public","license":"CC BY 4.0","permission":"local_analysis","session_id":"unknown-shared-publisher-session","sha256":"8392c62f4e9590a15745311746114c2b6355e24c60fa87fef68e834f20762113","source_recording_id":"https://huggingface.co/datasets/TaherPanbiharwala/EgoAnnotate/blob/156d13adaee4110cf63e54fa940ec16ff199d12f/videos/GX010079.mp4","source_url":"https://huggingface.co/datasets/TaherPanbiharwala/EgoAnnotate/blob/156d13adaee4110cf63e54fa940ec16ff199d12f/videos/GX010079.mp4","title":"Starting to fold a white shirt"},{"credit":"Alexey Gavryushin, Dingxi Zhang, Zhao Huang, Alexandros Delitzas, Jiaqi Chen, Ben Ellis, Cedric Z\u00f6llner, Manthan Patel, Manuel Kaufmann, Marc Pollefeys, and Xi Wang; CoMind (2026); excerpt starts 1s, original full hash not verified","id":"stir","kind":"public","license":"CC BY 4.0","permission":"local_analysis","session_id":"unknown-shared-publisher-session","sha256":"4ffe78850d4e6475546a521e0eb425f7a34c632679183cf112aacb70ec1b0861","source_recording_id":"https://comind.ethz.ch/","source_url":"https://comind.ethz.ch/","title":"Stirring vegetables in a pan"},{"credit":"Taher Panbiharwala and Zainab Barwaniwala; EgoAnnotate v1; excerpt starts 0s, original full hash not verified","id":"pack","kind":"public","license":"CC BY 4.0","permission":"local_analysis","session_id":"unknown-shared-publisher-session","sha256":"87a67e5b10f124a65df7d669086d4a9b2cb7ae25a5d758594b9b3aa7b0938f4c","source_recording_id":"https://huggingface.co/datasets/TaherPanbiharwala/EgoAnnotate/blob/156d13adaee4110cf63e54fa940ec16ff199d12f/videos/GX010087.mp4","source_url":"https://huggingface.co/datasets/TaherPanbiharwala/EgoAnnotate/blob/156d13adaee4110cf63e54fa940ec16ff199d12f/videos/GX010087.mp4","title":"Moving food from a tray toward a container"},{"credit":"Taher Panbiharwala and Zainab Barwaniwala; EgoAnnotate v1; excerpt starts 0s, original full hash not verified","id":"onion","kind":"public","license":"CC BY 4.0","permission":"local_analysis","session_id":"unknown-shared-publisher-session","sha256":"100e25698ee99e99dc648c41d9864144e312f0fce7c07dc9a7b06b487b9a2a5f","source_recording_id":"https://huggingface.co/datasets/TaherPanbiharwala/EgoAnnotate/blob/156d13adaee4110cf63e54fa940ec16ff199d12f/videos/GX010072.mp4","source_url":"https://huggingface.co/datasets/TaherPanbiharwala/EgoAnnotate/blob/156d13adaee4110cf63e54fa940ec16ff199d12f/videos/GX010072.mp4","title":"Slicing an onion on a pink plate"},{"credit":"Taher Panbiharwala and Zainab Barwaniwala; EgoAnnotate v1; excerpt starts 0s, original full hash not verified","id":"melon","kind":"public","license":"CC BY 4.0","permission":"local_analysis","session_id":"unknown-shared-publisher-session","sha256":"f32cf75d28602d169b4f302830ba633a351ac890596887c54c8e928efcf2650e","source_recording_id":"https://huggingface.co/datasets/TaherPanbiharwala/EgoAnnotate/blob/156d13adaee4110cf63e54fa940ec16ff199d12f/videos/GX010076.mp4","source_url":"https://huggingface.co/datasets/TaherPanbiharwala/EgoAnnotate/blob/156d13adaee4110cf63e54fa940ec16ff199d12f/videos/GX010076.mp4","title":"Cutting a watermelon wedge"},{"credit":"Taher Panbiharwala and Zainab Barwaniwala; EgoAnnotate v1; excerpt starts 0s, original full hash not verified","id":"jeans","kind":"public","license":"CC BY 4.0","permission":"local_analysis","session_id":"unknown-shared-publisher-session","sha256":"95845362951b3f78b7b731691df6d472bf176ced4b07ecef4d99d0b8a21da3e2","source_recording_id":"https://huggingface.co/datasets/TaherPanbiharwala/EgoAnnotate/blob/156d13adaee4110cf63e54fa940ec16ff199d12f/videos/GX010081.mp4","source_url":"https://huggingface.co/datasets/TaherPanbiharwala/EgoAnnotate/blob/156d13adaee4110cf63e54fa940ec16ff199d12f/videos/GX010081.mp4","title":"Folding grey jeans"}]} \ No newline at end of file diff --git a/docs/downloads/topics/evaluation-provenance/runs/2026-10-10-observation-lab/hardened-run.json b/docs/downloads/topics/evaluation-provenance/runs/2026-10-10-observation-lab/hardened-run.json new file mode 100644 index 0000000..30e5c2a --- /dev/null +++ b/docs/downloads/topics/evaluation-provenance/runs/2026-10-10-observation-lab/hardened-run.json @@ -0,0 +1 @@ +{"accuracy_status":"not_assessed","attempted":6,"completed":6,"elapsed_seconds":4.635012916056439,"episodes":[{"episode_sha256":"26b67bb490a0853482817f840715a17ae827830f32898b5fed60ccbcd51fd1a0","id":"shirt"},{"episode_sha256":"8b18fbda42aa44fa008fd763c865a045a416947b00464126b2e31b1c2c1c5ac8","id":"stir"},{"episode_sha256":"bb76a1996112fcb0bed37b988a4698676788b068d77e33ac4bc8cd080f6042da","id":"pack"},{"episode_sha256":"b94f9d15c4ecfc8c843d6c2d0e22568dbe32337cfe03091b7ef1bb529e1ee449","id":"onion"},{"episode_sha256":"7be44932308e08032322cfff7d9ee264335c016266c36015b0a991fb3cef9dab","id":"melon"},{"episode_sha256":"dee34f090cd5697889a6f904e30be6669085bf4db79273c56af3e4959151168e","id":"jeans"}],"failures":[],"geometry":"image_coordinates_only","kind":"dvidia.observation-run.v1","protocol_sha256":"3cd74c261157101b459563ff2b449c847194055fa024e60a6ed56aed94cf1b9c","robot_skill_qualified":false,"sessions":{"unknown-shared-publisher-session":["shirt","stir","pack","onion","melon","jeans"]},"timing_scope":"intake, decode, inference, association and per-episode writes; excludes model setup and final receipt"} \ No newline at end of file diff --git a/docs/downloads/topics/evaluation-provenance/runs/2026-10-10-observation-lab/initial-protocol.json b/docs/downloads/topics/evaluation-provenance/runs/2026-10-10-observation-lab/initial-protocol.json new file mode 100644 index 0000000..4425dd8 --- /dev/null +++ b/docs/downloads/topics/evaluation-provenance/runs/2026-10-10-observation-lab/initial-protocol.json @@ -0,0 +1 @@ +{"created_at":"2026-10-10T11:14:17.377906+00:00","execution":"local_offline","hardware":{"machine":"arm64","platform":"Darwin"},"kind":"dvidia.observation-protocol.v1","limits":{"cpu_threads":4,"workers":1},"manifest_sha256":"6e4e3a0b1b12eeb32cafcba0668d2614c80b022a91eafc7740018be880eddb29","model":{"backend":"opencv","coordinates":"normalized_image_xyxy","cpu_threads":10,"device":"cpu","hand_box_semantics":"Palm detector rectangle; not full hand segmentation or observed contact.","hand_detector_enabled":true,"hand_threshold":0.5,"implementation_sha256":"89cf6a3058661ec03acf78e3eaeab1182f235b0c2fe0d03b406fbaaafb29c2a4","implementation_version":1,"kind":"opencv-zoo-yolox-palm","limitations":["COCO labels can be wrong or absent, especially for small and occluded objects.","Palm boxes do not establish finger contact, grasp, force, depth, task success or robot actions.","Object identity and temporal relationships require a separate tracking stage."],"max_detections":30,"max_nms_candidates":1000,"models":[{"bytes":35858002,"directory":"object_detection_yolox","download_url":"https://media.githubusercontent.com/media/opencv/opencv_zoo/47534e27c9851bb1128ccc0102f1145e27f23f98/models/object_detection_yolox/object_detection_yolox_2022nov.onnx","license":"Apache-2.0","license_url":"https://raw.githubusercontent.com/opencv/opencv_zoo/47534e27c9851bb1128ccc0102f1145e27f23f98/models/object_detection_yolox/LICENSE","name":"object_detection_yolox_2022nov.onnx","revision":"47534e27c9851bb1128ccc0102f1145e27f23f98","role":"objects","sha256":"c5c2d13e59ae883e6af3b45daea64af4833a4951c92d116ec270d9ddbe998063","source":"https://github.com/opencv/opencv_zoo/blob/47534e27c9851bb1128ccc0102f1145e27f23f98/models/object_detection_yolox/object_detection_yolox_2022nov.onnx"},{"bytes":3905734,"directory":"palm_detection_mediapipe","download_url":"https://media.githubusercontent.com/media/opencv/opencv_zoo/47534e27c9851bb1128ccc0102f1145e27f23f98/models/palm_detection_mediapipe/palm_detection_mediapipe_2023feb.onnx","license":"Apache-2.0","license_url":"https://raw.githubusercontent.com/opencv/opencv_zoo/47534e27c9851bb1128ccc0102f1145e27f23f98/models/palm_detection_mediapipe/LICENSE","name":"palm_detection_mediapipe_2023feb.onnx","revision":"47534e27c9851bb1128ccc0102f1145e27f23f98","role":"palms","sha256":"78ff51c38496b7fc8b8ebdb6cc8c1abb02fa6c38427c6848254cdaba57fcce7c","source":"https://github.com/opencv/opencv_zoo/blob/47534e27c9851bb1128ccc0102f1145e27f23f98/models/palm_detection_mediapipe/palm_detection_mediapipe_2023feb.onnx"}],"nms_iou":{"objects":0.5,"palms":0.3},"runtime":{"numpy":"2.5.3","opencv":"5.0.0"},"score_kind":"uncalibrated_model_evidence","threshold":0.35},"recipe":{"automatic_outcome":"unknown","claim_scope":"sampled_2d_observations","id":"dvidia-observations-v1","max_duration_seconds":60,"max_frames":120,"max_image_side":640,"max_track_gap_seconds":0.8,"minimum_association_iou":0.2,"samples_per_second":2},"sources":[{"credit":"Taher Panbiharwala and Zainab Barwaniwala; EgoAnnotate v1; excerpt starts 0s, original full hash not verified","id":"shirt","kind":"public","license":"CC BY 4.0","permission":"local_analysis","session_id":"unknown-shared-publisher-session","sha256":"8392c62f4e9590a15745311746114c2b6355e24c60fa87fef68e834f20762113","source_recording_id":"https://huggingface.co/datasets/TaherPanbiharwala/EgoAnnotate/blob/156d13adaee4110cf63e54fa940ec16ff199d12f/videos/GX010079.mp4","source_url":"https://huggingface.co/datasets/TaherPanbiharwala/EgoAnnotate/blob/156d13adaee4110cf63e54fa940ec16ff199d12f/videos/GX010079.mp4","title":"Starting to fold a white shirt"},{"credit":"Alexey Gavryushin, Dingxi Zhang, Zhao Huang, Alexandros Delitzas, Jiaqi Chen, Ben Ellis, Cedric Z\u00f6llner, Manthan Patel, Manuel Kaufmann, Marc Pollefeys, and Xi Wang; CoMind (2026); excerpt starts 1s, original full hash not verified","id":"stir","kind":"public","license":"CC BY 4.0","permission":"local_analysis","session_id":"unknown-shared-publisher-session","sha256":"4ffe78850d4e6475546a521e0eb425f7a34c632679183cf112aacb70ec1b0861","source_recording_id":"https://comind.ethz.ch/","source_url":"https://comind.ethz.ch/","title":"Stirring vegetables in a pan"},{"credit":"Taher Panbiharwala and Zainab Barwaniwala; EgoAnnotate v1; excerpt starts 0s, original full hash not verified","id":"pack","kind":"public","license":"CC BY 4.0","permission":"local_analysis","session_id":"unknown-shared-publisher-session","sha256":"87a67e5b10f124a65df7d669086d4a9b2cb7ae25a5d758594b9b3aa7b0938f4c","source_recording_id":"https://huggingface.co/datasets/TaherPanbiharwala/EgoAnnotate/blob/156d13adaee4110cf63e54fa940ec16ff199d12f/videos/GX010087.mp4","source_url":"https://huggingface.co/datasets/TaherPanbiharwala/EgoAnnotate/blob/156d13adaee4110cf63e54fa940ec16ff199d12f/videos/GX010087.mp4","title":"Moving food from a tray toward a container"},{"credit":"Taher Panbiharwala and Zainab Barwaniwala; EgoAnnotate v1; excerpt starts 0s, original full hash not verified","id":"onion","kind":"public","license":"CC BY 4.0","permission":"local_analysis","session_id":"unknown-shared-publisher-session","sha256":"100e25698ee99e99dc648c41d9864144e312f0fce7c07dc9a7b06b487b9a2a5f","source_recording_id":"https://huggingface.co/datasets/TaherPanbiharwala/EgoAnnotate/blob/156d13adaee4110cf63e54fa940ec16ff199d12f/videos/GX010072.mp4","source_url":"https://huggingface.co/datasets/TaherPanbiharwala/EgoAnnotate/blob/156d13adaee4110cf63e54fa940ec16ff199d12f/videos/GX010072.mp4","title":"Slicing an onion on a pink plate"},{"credit":"Taher Panbiharwala and Zainab Barwaniwala; EgoAnnotate v1; excerpt starts 0s, original full hash not verified","id":"melon","kind":"public","license":"CC BY 4.0","permission":"local_analysis","session_id":"unknown-shared-publisher-session","sha256":"f32cf75d28602d169b4f302830ba633a351ac890596887c54c8e928efcf2650e","source_recording_id":"https://huggingface.co/datasets/TaherPanbiharwala/EgoAnnotate/blob/156d13adaee4110cf63e54fa940ec16ff199d12f/videos/GX010076.mp4","source_url":"https://huggingface.co/datasets/TaherPanbiharwala/EgoAnnotate/blob/156d13adaee4110cf63e54fa940ec16ff199d12f/videos/GX010076.mp4","title":"Cutting a watermelon wedge"},{"credit":"Taher Panbiharwala and Zainab Barwaniwala; EgoAnnotate v1; excerpt starts 0s, original full hash not verified","id":"jeans","kind":"public","license":"CC BY 4.0","permission":"local_analysis","session_id":"unknown-shared-publisher-session","sha256":"95845362951b3f78b7b731691df6d472bf176ced4b07ecef4d99d0b8a21da3e2","source_recording_id":"https://huggingface.co/datasets/TaherPanbiharwala/EgoAnnotate/blob/156d13adaee4110cf63e54fa940ec16ff199d12f/videos/GX010081.mp4","source_url":"https://huggingface.co/datasets/TaherPanbiharwala/EgoAnnotate/blob/156d13adaee4110cf63e54fa940ec16ff199d12f/videos/GX010081.mp4","title":"Folding grey jeans"}]} \ No newline at end of file diff --git a/docs/downloads/topics/evaluation-provenance/runs/2026-10-10-observation-lab/initial-run.json b/docs/downloads/topics/evaluation-provenance/runs/2026-10-10-observation-lab/initial-run.json new file mode 100644 index 0000000..5a57c5e --- /dev/null +++ b/docs/downloads/topics/evaluation-provenance/runs/2026-10-10-observation-lab/initial-run.json @@ -0,0 +1 @@ +{"accuracy_status":"not_assessed","attempted":6,"completed":6,"elapsed_seconds":4.835139082977548,"episodes":[{"episode_sha256":"e5225fd8209e6a27f1b906d02cd642f52d4b21693a5d1ec671146aacaa7282b7","id":"shirt"},{"episode_sha256":"a4b1323797769802f7b945185748814038c1ef391fb0f94cf77a84cf5748a24e","id":"stir"},{"episode_sha256":"4ab53292050295dbd3fa3615b499b42a61013c7751fd992ba725266b241cec7b","id":"pack"},{"episode_sha256":"a4a4cf5b23ae679a712f79a522824b347560d5f0c1a6dcc246316244af6f900e","id":"onion"},{"episode_sha256":"a5cc8dd002f65cde1639771952fa0099415e22a2103e44cd1bfba7147e8e62ca","id":"melon"},{"episode_sha256":"dc0ace7b027e2260e791b278d9241c8b42f2e9243ce7d0ab9e47a00a25db734d","id":"jeans"}],"failures":[],"geometry":"image_coordinates_only","kind":"dvidia.observation-run.v1","protocol_sha256":"71629e04edd72e1daccb968e011f68db07ae87cf9fa083976cb1a73744a32926","robot_skill_qualified":false,"sessions":{"unknown-shared-publisher-session":["shirt","stir","pack","onion","melon","jeans"]},"timing_scope":"intake, decode, inference, association and per-episode writes; excludes model setup and final receipt"} \ No newline at end of file diff --git a/docs/downloads/topics/evaluation-provenance/runs/2026-10-10-observation-lab/ui-validation.json b/docs/downloads/topics/evaluation-provenance/runs/2026-10-10-observation-lab/ui-validation.json new file mode 100644 index 0000000..e39c612 --- /dev/null +++ b/docs/downloads/topics/evaluation-provenance/runs/2026-10-10-observation-lab/ui-validation.json @@ -0,0 +1,22 @@ +{ + "scope": "Local isolated UI QA copy; not model accuracy", + "checks": [ + "Desktop loads real episode and unknown outcome without horizontal overflow", + "Video plays, sampled overlays render, and box visibility toggles", + "Corrected approval persists after reload while raw label and unknown outcome remain unchanged", + "A new blank manual event can be removed; a labeled manual event can be approved and saved", + "Downloaded review matches persisted revision and original source hash", + "Episode navigation protects unsaved changes, preserves Keep reviewing, and honors explicit discard", + "Structured model and source provenance render as readable text", + "390px phone layout has no horizontal overflow and visible controls have 44px targets", + "320px phone layout has no horizontal overflow and visible controls have 44px targets", + "No browser console or page errors", + "Accepted events preserve decimal timing, including 0.25s\u20130.50s", + "Overlay counts match timestamp-bounded real evidence at 12 sample and gap boundaries", + "Pending events block completion without writing an invalid revision", + "390px: event selection reveals editor, provenance follows review, no overflow, 44px controls", + "320px: event selection reveals editor, provenance follows review, no overflow, 44px controls" + ], + "console_errors": [], + "screenshots": "Kept locally with ignored QA run; no source frames redistributed" +} diff --git a/docs/feed.xml b/docs/feed.xml index d6d6a3f..c1e3ee0 100644 --- a/docs/feed.xml +++ b/docs/feed.xml @@ -1,2 +1,2 @@ -DVIDIA Researchhttps://research.dvidia.org/Research footprints on demonstrations, calibrated simulation and robot skills.enRobotics research pipelinehttps://research.dvidia.org/papers/robotics-research-pipeline/https://research.dvidia.org/papers/robotics-research-pipeline/Fri, 09 Oct 2026 12:00:00 GMTArchitecture proposal · current simulation alpha · hardware unqualified. An updated architecture connects immutable Skillspace recordings, reviewed task-label proposals and synchronized measured telemetry to grouped datasets, separate visual and motor learners, and a proposed local state supervisor. The implemented CPU baseline retains authored phases, gripper decisions and recovery around its learned joint-delta head. New annotation and supervisor pilots, fresh frozen confirmation, physics calibration and compatible skill-installation gates define the next milestones. Automatic labeling, learned supervision, human-video action recovery and physical arm qualification remain unestablished; this publication adds no new training or hardware result.Skillspace footage training pipelinehttps://research.dvidia.org/papers/skillspace-footage-training/https://research.dvidia.org/papers/skillspace-footage-training/Thu, 08 Oct 2026 12:00:00 GMTPublic CPU package · one native scene qualified · simulation-only. The public Dvidia-Inference/dvidia-training repository provides a standalone CPU pipeline that audits Skillspace media, freezes grouped splits and exports inspectable artifacts. Ten synthetic six-second clips train a visual predictor with a 0.5106-second median pipeline time across three repeats on one macOS host. Aligned native simulator telemetry supplies 4,029 training labels for a learned joint-delta head, evaluated on one held-out recording. Its capsule passes native placement qualification in that recording's exact scene; identical joint targets with open jaws fail. Installation and hardware guides accompany the package. Human-video action recovery, shoe organization, demonstration sufficiency, independent scene generalization and physical robot competence remain unestablished.Skill capsule acquisition and optimizationhttps://research.dvidia.org/papers/skill-capsule-acquisition/https://research.dvidia.org/papers/skill-capsule-acquisition/Wed, 07 Oct 2026 12:00:00 GMTSimulation-only · teacher/student 7/8 · no overall speedup. A compact learned CPU movement head replaces joint-target computation inside an authored placement supervisor. Teacher and student both pass 7/8 in a new frozen evaluation, while episode wall time increases from 6.273 to 6.360 seconds. A 39,845-byte JSON capsule imports into the local lab, checks its exact runtime and qualifies the current scene through native placement and a recorded-arm/open-jaw control. Scene changes require a fresh test. One known scene and repeat pass native network denial; perception, complete task learning, other embodiments and hardware remain unqualified.Skillspace arm benchmarks and evolutionhttps://research.dvidia.org/papers/skillspace-arm-benchmarks/https://research.dvidia.org/papers/skillspace-arm-benchmarks/Wed, 07 Oct 2026 12:00:00 GMTMixed held-out result · 30/32 baseline, 29/32 updated. Two controller revisions improve development completion from 14/20 to 17/20, but the frozen paired test declines from 30/32 to 29/32: both pass all 24 normal-strength cases while actuator-stress completion falls from 6/8 to 5/8. Instrumented CPU throughput also declines. We publish the regression, unchanged contact and success rules, exact controller snapshots, richer physical inputs, runtime-bound installation and a proposed staged Skillspace contract. Contact forces and penetration remain uncalibrated; learned perception and physical qualification are open.Installing a Skillspace on a simulated armhttps://research.dvidia.org/papers/skillspace-arm-installation/https://research.dvidia.org/papers/skillspace-arm-installation/Wed, 07 Oct 2026 12:00:00 GMTPublic skill link to authored adapter · 6/6 scene placements. The first link-to-arm product path installs an existing DVIDIA placement envelope, binds a local authored controller to one simulated arm, and reuses it in independently grounded scenes. Native jaw contacts carry a free box; six layouts complete, while no-motion and identical joint commands with open jaws each complete zero of six. Installed execution passes process-level offline checks. Task metadata contains no learned policy; perception, cup geometry, full arm collisions and physical qualification remain open.Offline cable training environmenthttps://research.dvidia.org/papers/offline-cable-training-environment/https://research.dvidia.org/papers/offline-cable-training-environment/Wed, 07 Oct 2026 12:00:00 GMTCPU simulation-only · Controller search and frozen evaluation executed. The first runnable product loop combines an anchored cable environment, local controller-parameter search, frozen evaluation, offline replay and a manifest-backed skill pack. The selected controller and a fixed feedback baseline both completed 10/10 held-out simulated episodes; zero-force and release controls completed 0/10. A native macOS network-denial run completed 3/3 additional episodes. Ideal endpoint attachment and privileged state bound the result; physical rope calibration, gripping, sensors and GPU throughput remain untested.Fast accurate robot training simulationhttps://research.dvidia.org/papers/fast-accurate-robot-training-simulation/https://research.dvidia.org/papers/fast-accurate-robot-training-simulation/Wed, 07 Oct 2026 12:00:00 GMT54 CPU fixture trials · GPU and physical transfer untested. A design for an offline, self-hosted training environment that turns demonstrations into calibrated practice and qualified robot skills. We examine contact, deformation, sensor feedback and the performance–accuracy tradeoff, then report 54 deterministic native MuJoCo CPU fixture trials. Fine endpoint agreement did not establish accurate contact transients, and coarse timesteps missed collisions. Minimum GPU memory, rope accuracy and physical transfer remain unmeasured.Grok robotics research on Xhttps://research.dvidia.org/papers/grok-robotics-research-on-x/https://research.dvidia.org/papers/grok-robotics-research-on-x/Wed, 07 Oct 2026 12:00:00 GMTPrimary sources checked · Experiments proposed. Three Grok 4.7 research passes surface observation-to-action, synthetic-practice and reusable-repair ideas. Independent primary-source checks compare those findings with our thesis: observation supplies goals and state, language retrieves a skill, spatial expectations guide attention, and executable feedback with evaluation establishes competence. X posts remain discovery leads. No universal demonstration count or arbitrary-robot transfer follows from the reviewed results.Spatially grounded downloadable robot skillshttps://research.dvidia.org/papers/spatially-grounded-downloadable-robot-skills/https://research.dvidia.org/papers/spatially-grounded-downloadable-robot-skills/Wed, 07 Oct 2026 12:00:00 GMTSource review · DVIDIA experiments not run. A synthesis of learning from human demonstrations, language-conditioned spatial attention, simulation expansion and robot-specific skill delivery. Spatial priors can accelerate inspection but do not determine contact state or control. The proposed downloadable skill packages a controller, initiation and termination conditions, compatible sensing and hardware, recovery behavior and measured evidence. Separate experiments would test attention, data coverage, feedback and transfer.Clef and grounded video observationshttps://research.dvidia.org/papers/clef-and-grounded-video-observations/https://research.dvidia.org/papers/clef-and-grounded-video-observations/Tue, 06 Oct 2026 12:00:00 GMTFive licensed excerpts · Accuracy evaluation outstanding. A preregistered image-API feasibility run processed five licensed three-second POV excerpts using four timestamped frames, a Gemma caption and a Clef-flash check. All five completed at a price-derived inference estimate of $0.00140634. Post-run inspection found an object error accepted by the checker and omitted state changes. API and schema compatibility were demonstrated; annotation accuracy and whole-task success were not.From Skillspace to robot skillhttps://research.dvidia.org/papers/from-skillspace-to-robot-skill/https://research.dvidia.org/papers/from-skillspace-to-robot-skill/Tue, 06 Oct 2026 12:00:00 GMTGraduation and robot training not run. An Argus review and a proposal to connect original recordings, reviewed episodes, immutable datasets, training runs, held-out evaluation and robot-tested releases. The review separates video annotation from action supervision and defines compatibility beyond a robot’s degree-of-freedom count. A proposed 40-episode annotation pilot and evidence-based graduation criteria remain unrun.Turn physical footage into testable evidencehttps://research.dvidia.org/papers/physical-skill-research-agenda/https://research.dvidia.org/papers/physical-skill-research-agenda/Tue, 06 Oct 2026 12:00:00 GMTFour baseline protocols proposed. A research agenda covering visible capture evidence, relations over time, evaluation provenance and physical grounding. Each question has a bounded protocol and a failure condition. The aim is to measure whether structure and physical signals improve a defined task before scaling collection. Strategic opinions, author-reported results and our untested proposals are kept distinct. +DVIDIA Researchhttps://research.dvidia.org/Research footprints on demonstrations, calibrated simulation and robot skills.enDVIDIA Observation Lab pilothttps://research.dvidia.org/papers/dvidia-observation-lab/https://research.dvidia.org/papers/dvidia-observation-lab/Sat, 10 Oct 2026 12:00:00 GMTSix public excerpts processed · accuracy not assessed · no robot actions. DVIDIA Observation Lab supplies a local detector and palm-observation workflow with sampled timestamps, source/model provenance, editable timeline revisions and saved-review export. Two engineering attempts each process the same six public excerpts: 19 seconds and 38 sampled frames. Processing takes 4.835 and 4.635 seconds on one warm macOS ARM64 machine, excluding model setup, UI and human review. Software and browser checks establish integration; independent annotation accuracy, correction time, complete cup-placement coverage, depth, action learning and hardware competence remain unmeasured.Robotics research pipelinehttps://research.dvidia.org/papers/robotics-research-pipeline/https://research.dvidia.org/papers/robotics-research-pipeline/Fri, 09 Oct 2026 12:00:00 GMTArchitecture proposal · current simulation alpha · hardware unqualified. An updated architecture connects immutable Skillspace recordings, reviewed task-label proposals and synchronized measured telemetry to grouped datasets, separate visual and motor learners, and a proposed local state supervisor. The implemented CPU baseline retains authored phases, gripper decisions and recovery around its learned joint-delta head. New annotation and supervisor pilots, fresh frozen confirmation, physics calibration and compatible skill-installation gates define the next milestones. Automatic labeling, learned supervision, human-video action recovery and physical arm qualification remain unestablished; this publication adds no new training or hardware result.Skillspace footage training pipelinehttps://research.dvidia.org/papers/skillspace-footage-training/https://research.dvidia.org/papers/skillspace-footage-training/Thu, 08 Oct 2026 12:00:00 GMTPublic CPU package · one native scene qualified · simulation-only. The public Dvidia-Inference/dvidia-training repository provides a standalone CPU pipeline that audits Skillspace media, freezes grouped splits and exports inspectable artifacts. Ten synthetic six-second clips train a visual predictor with a 0.5106-second median pipeline time across three repeats on one macOS host. Aligned native simulator telemetry supplies 4,029 training labels for a learned joint-delta head, evaluated on one held-out recording. Its capsule passes native placement qualification in that recording's exact scene; identical joint targets with open jaws fail. Installation and hardware guides accompany the package. Human-video action recovery, shoe organization, demonstration sufficiency, independent scene generalization and physical robot competence remain unestablished.Skill capsule acquisition and optimizationhttps://research.dvidia.org/papers/skill-capsule-acquisition/https://research.dvidia.org/papers/skill-capsule-acquisition/Wed, 07 Oct 2026 12:00:00 GMTSimulation-only · teacher/student 7/8 · no overall speedup. A compact learned CPU movement head replaces joint-target computation inside an authored placement supervisor. Teacher and student both pass 7/8 in a new frozen evaluation, while episode wall time increases from 6.273 to 6.360 seconds. A 39,845-byte JSON capsule imports into the local lab, checks its exact runtime and qualifies the current scene through native placement and a recorded-arm/open-jaw control. Scene changes require a fresh test. One known scene and repeat pass native network denial; perception, complete task learning, other embodiments and hardware remain unqualified.Skillspace arm benchmarks and evolutionhttps://research.dvidia.org/papers/skillspace-arm-benchmarks/https://research.dvidia.org/papers/skillspace-arm-benchmarks/Wed, 07 Oct 2026 12:00:00 GMTMixed held-out result · 30/32 baseline, 29/32 updated. Two controller revisions improve development completion from 14/20 to 17/20, but the frozen paired test declines from 30/32 to 29/32: both pass all 24 normal-strength cases while actuator-stress completion falls from 6/8 to 5/8. Instrumented CPU throughput also declines. We publish the regression, unchanged contact and success rules, exact controller snapshots, richer physical inputs, runtime-bound installation and a proposed staged Skillspace contract. Contact forces and penetration remain uncalibrated; learned perception and physical qualification are open.Installing a Skillspace on a simulated armhttps://research.dvidia.org/papers/skillspace-arm-installation/https://research.dvidia.org/papers/skillspace-arm-installation/Wed, 07 Oct 2026 12:00:00 GMTPublic skill link to authored adapter · 6/6 scene placements. The first link-to-arm product path installs an existing DVIDIA placement envelope, binds a local authored controller to one simulated arm, and reuses it in independently grounded scenes. Native jaw contacts carry a free box; six layouts complete, while no-motion and identical joint commands with open jaws each complete zero of six. Installed execution passes process-level offline checks. Task metadata contains no learned policy; perception, cup geometry, full arm collisions and physical qualification remain open.Offline cable training environmenthttps://research.dvidia.org/papers/offline-cable-training-environment/https://research.dvidia.org/papers/offline-cable-training-environment/Wed, 07 Oct 2026 12:00:00 GMTCPU simulation-only · Controller search and frozen evaluation executed. The first runnable product loop combines an anchored cable environment, local controller-parameter search, frozen evaluation, offline replay and a manifest-backed skill pack. The selected controller and a fixed feedback baseline both completed 10/10 held-out simulated episodes; zero-force and release controls completed 0/10. A native macOS network-denial run completed 3/3 additional episodes. Ideal endpoint attachment and privileged state bound the result; physical rope calibration, gripping, sensors and GPU throughput remain untested.Fast accurate robot training simulationhttps://research.dvidia.org/papers/fast-accurate-robot-training-simulation/https://research.dvidia.org/papers/fast-accurate-robot-training-simulation/Wed, 07 Oct 2026 12:00:00 GMT54 CPU fixture trials · GPU and physical transfer untested. A design for an offline, self-hosted training environment that turns demonstrations into calibrated practice and qualified robot skills. We examine contact, deformation, sensor feedback and the performance–accuracy tradeoff, then report 54 deterministic native MuJoCo CPU fixture trials. Fine endpoint agreement did not establish accurate contact transients, and coarse timesteps missed collisions. Minimum GPU memory, rope accuracy and physical transfer remain unmeasured.Grok robotics research on Xhttps://research.dvidia.org/papers/grok-robotics-research-on-x/https://research.dvidia.org/papers/grok-robotics-research-on-x/Wed, 07 Oct 2026 12:00:00 GMTPrimary sources checked · Experiments proposed. Three Grok 4.7 research passes surface observation-to-action, synthetic-practice and reusable-repair ideas. Independent primary-source checks compare those findings with our thesis: observation supplies goals and state, language retrieves a skill, spatial expectations guide attention, and executable feedback with evaluation establishes competence. X posts remain discovery leads. No universal demonstration count or arbitrary-robot transfer follows from the reviewed results.Spatially grounded downloadable robot skillshttps://research.dvidia.org/papers/spatially-grounded-downloadable-robot-skills/https://research.dvidia.org/papers/spatially-grounded-downloadable-robot-skills/Wed, 07 Oct 2026 12:00:00 GMTSource review · DVIDIA experiments not run. A synthesis of learning from human demonstrations, language-conditioned spatial attention, simulation expansion and robot-specific skill delivery. Spatial priors can accelerate inspection but do not determine contact state or control. The proposed downloadable skill packages a controller, initiation and termination conditions, compatible sensing and hardware, recovery behavior and measured evidence. Separate experiments would test attention, data coverage, feedback and transfer.Clef and grounded video observationshttps://research.dvidia.org/papers/clef-and-grounded-video-observations/https://research.dvidia.org/papers/clef-and-grounded-video-observations/Tue, 06 Oct 2026 12:00:00 GMTFive licensed excerpts · Accuracy evaluation outstanding. A preregistered image-API feasibility run processed five licensed three-second POV excerpts using four timestamped frames, a Gemma caption and a Clef-flash check. All five completed at a price-derived inference estimate of $0.00140634. Post-run inspection found an object error accepted by the checker and omitted state changes. API and schema compatibility were demonstrated; annotation accuracy and whole-task success were not.From Skillspace to robot skillhttps://research.dvidia.org/papers/from-skillspace-to-robot-skill/https://research.dvidia.org/papers/from-skillspace-to-robot-skill/Tue, 06 Oct 2026 12:00:00 GMTGraduation and robot training not run. An Argus review and a proposal to connect original recordings, reviewed episodes, immutable datasets, training runs, held-out evaluation and robot-tested releases. The review separates video annotation from action supervision and defines compatibility beyond a robot’s degree-of-freedom count. A proposed 40-episode annotation pilot and evidence-based graduation criteria remain unrun.Turn physical footage into testable evidencehttps://research.dvidia.org/papers/physical-skill-research-agenda/https://research.dvidia.org/papers/physical-skill-research-agenda/Tue, 06 Oct 2026 12:00:00 GMTFour baseline protocols proposed. A research agenda covering visible capture evidence, relations over time, evaluation provenance and physical grounding. Each question has a bounded protocol and a failure condition. The aim is to measure whether structure and physical signals improve a defined task before scaling collection. Strategic opinions, author-reported results and our untested proposals are kept distinct. diff --git a/docs/index.html b/docs/index.html index 8b6dfc2..1e88fbb 100644 --- a/docs/index.html +++ b/docs/index.html @@ -1,4 +1,4 @@ Research journal · DVIDIA Research -

An open research notebook

From observation
to physical skill.

We study how demonstrations become usable evidence, how simulation becomes useful practice, and when a robot skill earns a release.

Published by DVIDIA · hello@dvidia.org

Publications

12 papers and working notes

· Architecture proposal and staged validation roadmap

Robotics research pipeline

An updated architecture connects immutable Skillspace recordings, reviewed task-label proposals and synchronized measured telemetry to grouped datasets, separate visual and motor learners, and a proposed local state supervisor. The implemented CPU baseline retains authored phases, gripper decisions and recovery around its learned joint-delta head. New annotation and supervisor pilots, fresh frozen confirmation, physics calibration and compatible skill-installation gates define the next milestones. Automatic labeling, learned supervision, human-video action recovery and physical arm qualification remain unestablished; this publication adds no new training or hardware result.

Architecture proposal · current simulation alpha · hardware unqualified

· Product implementation and measured synthetic pilot

Skillspace footage training pipeline

The public Dvidia-Inference/dvidia-training repository provides a standalone CPU pipeline that audits Skillspace media, freezes grouped splits and exports inspectable artifacts. Ten synthetic six-second clips train a visual predictor with a 0.5106-second median pipeline time across three repeats on one macOS host. Aligned native simulator telemetry supplies 4,029 training labels for a learned joint-delta head, evaluated on one held-out recording. Its capsule passes native placement qualification in that recording's exact scene; identical joint targets with open jaws fail. Installation and hardware guides accompany the package. Human-video action recovery, shoe organization, demonstration sufficiency, independent scene generalization and physical robot competence remain unestablished.

Public CPU package · one native scene qualified · simulation-only

· Learned movement artifact and installation prototype

Skill capsule acquisition and optimization

A compact learned CPU movement head replaces joint-target computation inside an authored placement supervisor. Teacher and student both pass 7/8 in a new frozen evaluation, while episode wall time increases from 6.273 to 6.360 seconds. A 39,845-byte JSON capsule imports into the local lab, checks its exact runtime and qualifies the current scene through native placement and a recorded-arm/open-jaw control. Scene changes require a fresh test. One known scene and repeat pass native network denial; perception, complete task learning, other embodiments and hardware remain unqualified.

Simulation-only · teacher/student 7/8 · no overall speedup

· Paired simulation benchmark and product assessment

Skillspace arm benchmarks and evolution

Two controller revisions improve development completion from 14/20 to 17/20, but the frozen paired test declines from 30/32 to 29/32: both pass all 24 normal-strength cases while actuator-stress completion falls from 6/8 to 5/8. Instrumented CPU throughput also declines. We publish the regression, unchanged contact and success rules, exact controller snapshots, richer physical inputs, runtime-bound installation and a proposed staged Skillspace contract. Contact forces and penetration remain uncalibrated; learned perception and physical qualification are open.

Mixed held-out result · 30/32 baseline, 29/32 updated

· Product prototype and native contact qualification

Installing a Skillspace on a simulated arm

The first link-to-arm product path installs an existing DVIDIA placement envelope, binds a local authored controller to one simulated arm, and reuses it in independently grounded scenes. Native jaw contacts carry a free box; six layouts complete, while no-motion and identical joint commands with open jaws each complete zero of six. Installed execution passes process-level offline checks. Task metadata contains no learned policy; perception, cup geometry, full arm collisions and physical qualification remain open.

Public skill link to authored adapter · 6/6 scene placements

· Product prototype and local qualification

Offline cable training environment

The first runnable product loop combines an anchored cable environment, local controller-parameter search, frozen evaluation, offline replay and a manifest-backed skill pack. The selected controller and a fixed feedback baseline both completed 10/10 held-out simulated episodes; zero-force and release controls completed 0/10. A native macOS network-denial run completed 3/3 additional episodes. Ideal endpoint attachment and privileged state bound the result; physical rope calibration, gripping, sensors and GPU throughput remain untested.

CPU simulation-only · Controller search and frozen evaluation executed

· Decision report and local experiment

Fast accurate robot training simulation

A design for an offline, self-hosted training environment that turns demonstrations into calibrated practice and qualified robot skills. We examine contact, deformation, sensor feedback and the performance–accuracy tradeoff, then report 54 deterministic native MuJoCo CPU fixture trials. Fine endpoint agreement did not establish accurate contact transients, and coarse timesteps missed collisions. Minimum GPU memory, rope accuracy and physical transfer remain unmeasured.

54 CPU fixture trials · GPU and physical transfer untested

· Source review and thesis comparison

Grok robotics research on X

Three Grok 4.7 research passes surface observation-to-action, synthetic-practice and reusable-repair ideas. Independent primary-source checks compare those findings with our thesis: observation supplies goals and state, language retrieves a skill, spatial expectations guide attention, and executable feedback with evaluation establishes competence. X posts remain discovery leads. No universal demonstration count or arbitrary-robot transfer follows from the reviewed results.

Primary sources checked · Experiments proposed

· Research synthesis and proposed experiments

Spatially grounded downloadable robot skills

A synthesis of learning from human demonstrations, language-conditioned spatial attention, simulation expansion and robot-specific skill delivery. Spatial priors can accelerate inspection but do not determine contact state or control. The proposed downloadable skill packages a controller, initiation and termination conditions, compatible sensing and hardware, recovery behavior and measured evidence. Separate experiments would test attention, data coverage, feedback and transfer.

Source review · DVIDIA experiments not run

· Engineering feasibility pilot

Clef and grounded video observations

A preregistered image-API feasibility run processed five licensed three-second POV excerpts using four timestamped frames, a Gemma caption and a Clef-flash check. All five completed at a price-derived inference estimate of $0.00140634. Post-run inspection found an object error accepted by the checker and omitted state changes. API and schema compatibility were demonstrated; annotation accuracy and whole-task success were not.

Five licensed excerpts · Accuracy evaluation outstanding

· Source review and implementation proposal

From Skillspace to robot skill

An Argus review and a proposal to connect original recordings, reviewed episodes, immutable datasets, training runs, held-out evaluation and robot-tested releases. The review separates video annotation from action supervision and defines compatibility beyond a robot’s degree-of-freedom count. A proposed 40-episode annotation pilot and evidence-based graduation criteria remain unrun.

Graduation and robot training not run

· Research agenda

Turn physical footage into testable evidence

A research agenda covering visible capture evidence, relations over time, evaluation provenance and physical grounding. Each question has a bounded protocol and a failure condition. The aim is to measure whether structure and physical signals improve a defined task before scaling collection. Strategic opinions, author-reported results and our untested proposals are kept distinct.

Four baseline protocols proposed

Research footprints

  1. Publish the robotics research pipeline

    A diagram connects footage review, measured robot state, local training, frozen simulation evaluation and compatible skill installation. Automatic annotation and a learned task supervisor are proposed; their companion validation studies and physical robot qualification remain unrun.

    Read the architecture and validation gates
  2. A public skill link reaches a simulated arm

    One-click local installation binds a DVIDIA placement envelope to an authored contact controller. Six scene layouts pass; identical joint commands with open jaws and no-motion controls each pass 0/6. Physical transfer and learned policies remain open.

    Read the installation contract and arm replay
  3. The offline cable environment is runnable

    A local controller-training loop and simulation-only skill pack now run on CPU. Trained and baseline feedback each pass 10/10 simulated seeds; zero force and early release each pass 0/10. Real gripping, calibration and GPU qualification remain open.

    Read the first product build and replay
  4. Contact accuracy meets runtime

    54 deterministic CPU fixture trials recorded. Endpoint agreement coexists with unqualified force transients; coarse wall tests expose missed contact. No GPU or physical-transfer claim.

    Read the measurements
  5. Compare the observation-to-skill thesis with prior work

    Spatial attention, demonstration coverage, executable simulation and reusable repairs are reviewed separately. Three parallel Grok 4.7 searches support discovery; primary sources support the claims.

    Read the comparison
  6. Five licensed POV excerpts processed

    Ten image calls completed. A checker accepted an object error and captions omitted visible state changes. The separate accuracy pilot remains unrun.

    Read the feasibility run
  7. Define the evidence and release questions

    Four baseline protocols and a Skillspace graduation proposal establish the questions to test. A proposed protocol is distinct from an executed experiment.

    Read the agenda

Open questions

  • Capture quality — Test whether hands, relevant objects and state changes are actually observable in a POV demonstration.
  • Skill relations — Calibrate hand–object relations, then test temporal event graphs whose claims point back to video intervals.
  • Evaluation and provenance — Test episode readback, original-to-derivative lineage and split integrity using small, auditable fixtures.
  • Physical grounding — Measure whether state/contact evidence and controlled synthetic augmentation improve a defined physical-skill task.

Follow new publications through RSS or inspect the source and revisions on GitHub.

+

An open research notebook

From observation
to physical skill.

We study how demonstrations become usable evidence, how simulation becomes useful practice, and when a robot skill earns a release.

Published by DVIDIA · hello@dvidia.org

Publications

13 papers and working notes

· Local observation workflow and engineering feasibility pilot

DVIDIA Observation Lab pilot

DVIDIA Observation Lab supplies a local detector and palm-observation workflow with sampled timestamps, source/model provenance, editable timeline revisions and saved-review export. Two engineering attempts each process the same six public excerpts: 19 seconds and 38 sampled frames. Processing takes 4.835 and 4.635 seconds on one warm macOS ARM64 machine, excluding model setup, UI and human review. Software and browser checks establish integration; independent annotation accuracy, correction time, complete cup-placement coverage, depth, action learning and hardware competence remain unmeasured.

Six public excerpts processed · accuracy not assessed · no robot actions

· Architecture proposal and staged validation roadmap

Robotics research pipeline

An updated architecture connects immutable Skillspace recordings, reviewed task-label proposals and synchronized measured telemetry to grouped datasets, separate visual and motor learners, and a proposed local state supervisor. The implemented CPU baseline retains authored phases, gripper decisions and recovery around its learned joint-delta head. New annotation and supervisor pilots, fresh frozen confirmation, physics calibration and compatible skill-installation gates define the next milestones. Automatic labeling, learned supervision, human-video action recovery and physical arm qualification remain unestablished; this publication adds no new training or hardware result.

Architecture proposal · current simulation alpha · hardware unqualified

· Product implementation and measured synthetic pilot

Skillspace footage training pipeline

The public Dvidia-Inference/dvidia-training repository provides a standalone CPU pipeline that audits Skillspace media, freezes grouped splits and exports inspectable artifacts. Ten synthetic six-second clips train a visual predictor with a 0.5106-second median pipeline time across three repeats on one macOS host. Aligned native simulator telemetry supplies 4,029 training labels for a learned joint-delta head, evaluated on one held-out recording. Its capsule passes native placement qualification in that recording's exact scene; identical joint targets with open jaws fail. Installation and hardware guides accompany the package. Human-video action recovery, shoe organization, demonstration sufficiency, independent scene generalization and physical robot competence remain unestablished.

Public CPU package · one native scene qualified · simulation-only

· Learned movement artifact and installation prototype

Skill capsule acquisition and optimization

A compact learned CPU movement head replaces joint-target computation inside an authored placement supervisor. Teacher and student both pass 7/8 in a new frozen evaluation, while episode wall time increases from 6.273 to 6.360 seconds. A 39,845-byte JSON capsule imports into the local lab, checks its exact runtime and qualifies the current scene through native placement and a recorded-arm/open-jaw control. Scene changes require a fresh test. One known scene and repeat pass native network denial; perception, complete task learning, other embodiments and hardware remain unqualified.

Simulation-only · teacher/student 7/8 · no overall speedup

· Paired simulation benchmark and product assessment

Skillspace arm benchmarks and evolution

Two controller revisions improve development completion from 14/20 to 17/20, but the frozen paired test declines from 30/32 to 29/32: both pass all 24 normal-strength cases while actuator-stress completion falls from 6/8 to 5/8. Instrumented CPU throughput also declines. We publish the regression, unchanged contact and success rules, exact controller snapshots, richer physical inputs, runtime-bound installation and a proposed staged Skillspace contract. Contact forces and penetration remain uncalibrated; learned perception and physical qualification are open.

Mixed held-out result · 30/32 baseline, 29/32 updated

· Product prototype and native contact qualification

Installing a Skillspace on a simulated arm

The first link-to-arm product path installs an existing DVIDIA placement envelope, binds a local authored controller to one simulated arm, and reuses it in independently grounded scenes. Native jaw contacts carry a free box; six layouts complete, while no-motion and identical joint commands with open jaws each complete zero of six. Installed execution passes process-level offline checks. Task metadata contains no learned policy; perception, cup geometry, full arm collisions and physical qualification remain open.

Public skill link to authored adapter · 6/6 scene placements

· Product prototype and local qualification

Offline cable training environment

The first runnable product loop combines an anchored cable environment, local controller-parameter search, frozen evaluation, offline replay and a manifest-backed skill pack. The selected controller and a fixed feedback baseline both completed 10/10 held-out simulated episodes; zero-force and release controls completed 0/10. A native macOS network-denial run completed 3/3 additional episodes. Ideal endpoint attachment and privileged state bound the result; physical rope calibration, gripping, sensors and GPU throughput remain untested.

CPU simulation-only · Controller search and frozen evaluation executed

· Decision report and local experiment

Fast accurate robot training simulation

A design for an offline, self-hosted training environment that turns demonstrations into calibrated practice and qualified robot skills. We examine contact, deformation, sensor feedback and the performance–accuracy tradeoff, then report 54 deterministic native MuJoCo CPU fixture trials. Fine endpoint agreement did not establish accurate contact transients, and coarse timesteps missed collisions. Minimum GPU memory, rope accuracy and physical transfer remain unmeasured.

54 CPU fixture trials · GPU and physical transfer untested

· Source review and thesis comparison

Grok robotics research on X

Three Grok 4.7 research passes surface observation-to-action, synthetic-practice and reusable-repair ideas. Independent primary-source checks compare those findings with our thesis: observation supplies goals and state, language retrieves a skill, spatial expectations guide attention, and executable feedback with evaluation establishes competence. X posts remain discovery leads. No universal demonstration count or arbitrary-robot transfer follows from the reviewed results.

Primary sources checked · Experiments proposed

· Research synthesis and proposed experiments

Spatially grounded downloadable robot skills

A synthesis of learning from human demonstrations, language-conditioned spatial attention, simulation expansion and robot-specific skill delivery. Spatial priors can accelerate inspection but do not determine contact state or control. The proposed downloadable skill packages a controller, initiation and termination conditions, compatible sensing and hardware, recovery behavior and measured evidence. Separate experiments would test attention, data coverage, feedback and transfer.

Source review · DVIDIA experiments not run

· Engineering feasibility pilot

Clef and grounded video observations

A preregistered image-API feasibility run processed five licensed three-second POV excerpts using four timestamped frames, a Gemma caption and a Clef-flash check. All five completed at a price-derived inference estimate of $0.00140634. Post-run inspection found an object error accepted by the checker and omitted state changes. API and schema compatibility were demonstrated; annotation accuracy and whole-task success were not.

Five licensed excerpts · Accuracy evaluation outstanding

· Source review and implementation proposal

From Skillspace to robot skill

An Argus review and a proposal to connect original recordings, reviewed episodes, immutable datasets, training runs, held-out evaluation and robot-tested releases. The review separates video annotation from action supervision and defines compatibility beyond a robot’s degree-of-freedom count. A proposed 40-episode annotation pilot and evidence-based graduation criteria remain unrun.

Graduation and robot training not run

· Research agenda

Turn physical footage into testable evidence

A research agenda covering visible capture evidence, relations over time, evaluation provenance and physical grounding. Each question has a bounded protocol and a failure condition. The aim is to measure whether structure and physical signals improve a defined task before scaling collection. Strategic opinions, author-reported results and our untested proposals are kept distinct.

Four baseline protocols proposed

Research footprints

  1. Publish the robotics research pipeline

    A diagram connects footage review, measured robot state, local training, frozen simulation evaluation and compatible skill installation. Automatic annotation and a learned task supervisor are proposed; their companion validation studies and physical robot qualification remain unrun.

    Read the architecture and validation gates
  2. A public skill link reaches a simulated arm

    One-click local installation binds a DVIDIA placement envelope to an authored contact controller. Six scene layouts pass; identical joint commands with open jaws and no-motion controls each pass 0/6. Physical transfer and learned policies remain open.

    Read the installation contract and arm replay
  3. The offline cable environment is runnable

    A local controller-training loop and simulation-only skill pack now run on CPU. Trained and baseline feedback each pass 10/10 simulated seeds; zero force and early release each pass 0/10. Real gripping, calibration and GPU qualification remain open.

    Read the first product build and replay
  4. Contact accuracy meets runtime

    54 deterministic CPU fixture trials recorded. Endpoint agreement coexists with unqualified force transients; coarse wall tests expose missed contact. No GPU or physical-transfer claim.

    Read the measurements
  5. Compare the observation-to-skill thesis with prior work

    Spatial attention, demonstration coverage, executable simulation and reusable repairs are reviewed separately. Three parallel Grok 4.7 searches support discovery; primary sources support the claims.

    Read the comparison
  6. Five licensed POV excerpts processed

    Ten image calls completed. A checker accepted an object error and captions omitted visible state changes. The separate accuracy pilot remains unrun.

    Read the feasibility run
  7. Define the evidence and release questions

    Four baseline protocols and a Skillspace graduation proposal establish the questions to test. A proposed protocol is distinct from an executed experiment.

    Read the agenda

Open questions

  • Capture quality — Test whether hands, relevant objects and state changes are actually observable in a POV demonstration.
  • Skill relations — Calibrate hand–object relations, then test temporal event graphs whose claims point back to video intervals.
  • Evaluation and provenance — Test episode readback, original-to-derivative lineage and split integrity using small, auditable fixtures.
  • Physical grounding — Measure whether state/contact evidence and controlled synthetic augmentation improve a defined physical-skill task.

Follow new publications through RSS or inspect the source and revisions on GitHub.

diff --git a/docs/papers/clef-and-grounded-video-observations/index.html b/docs/papers/clef-and-grounded-video-observations/index.html index 13d2413..2d63bcf 100644 --- a/docs/papers/clef-and-grounded-video-observations/index.html +++ b/docs/papers/clef-and-grounded-video-observations/index.html @@ -1,7 +1,7 @@ Clef and grounded video observations · DVIDIA Research -

Engineering feasibility pilot

Clef and grounded video observations

· DVIDIA

Five licensed excerpts · Accuracy evaluation outstanding

Source & history · Download Markdown

Abstract

A preregistered image-API feasibility run processed five licensed three-second POV excerpts using four timestamped frames, a Gemma caption and a Clef-flash check. All five completed at a price-derived inference estimate of $0.00140634. Post-run inspection found an object error accepted by the checker and omitted state changes. API and schema compatibility were demonstrated; annotation accuracy and whole-task success were not.

In this paper

Engineering pilot executed · 6 October 2026 · Accuracy evaluation outstanding

+

Engineering feasibility pilot

Clef and grounded video observations

· DVIDIA

Five licensed excerpts · Accuracy evaluation outstanding

Source & history · Download Markdown

Abstract

A preregistered image-API feasibility run processed five licensed three-second POV excerpts using four timestamped frames, a Gemma caption and a Clef-flash check. All five completed at a price-derived inference estimate of $0.00140634. Post-run inspection found an object error accepted by the checker and omitted state changes. API and schema compatibility were demonstrated; annotation accuracy and whole-task success were not.

In this paper

Engineering pilot executed · 6 October 2026 · Accuracy evaluation outstanding

We executed a small, preregistered feasibility run: five existing public, licensed three-second POV excerpts, four original-timestamped frames per excerpt, one Gemma caption call and one Clef-flash check per excerpt. All five completed. The estimated inference cost was $0.00140634. This establishes that the image APIs and bounded data contract work; it does not establish that the annotations are accurate.

The useful finding was a failure: a caption called a pink plate a cutting board, and the second model agreed. Several descriptions listed objects or hand positions while missing visible folding or transfer. Model agreement must not become a “verified” badge. The observations below come from AI-assisted inspection of the exact input frames after outputs were frozen, not independent human annotations.

Preregistration · Complete sanitized results and source/frame hashes · Prompts and request recipes · Next evaluation protocol

diff --git a/docs/papers/dvidia-observation-lab/index.html b/docs/papers/dvidia-observation-lab/index.html new file mode 100644 index 0000000..cdb0509 --- /dev/null +++ b/docs/papers/dvidia-observation-lab/index.html @@ -0,0 +1,24 @@ + + +DVIDIA Observation Lab pilot · DVIDIA Research +

Local observation workflow and engineering feasibility pilot

DVIDIA Observation Lab pilot

· DVIDIA

Six public excerpts processed · accuracy not assessed · no robot actions

Source & history · Download Markdown

Abstract

DVIDIA Observation Lab supplies a local detector and palm-observation workflow with sampled timestamps, source/model provenance, editable timeline revisions and saved-review export. Two engineering attempts each process the same six public excerpts: 19 seconds and 38 sampled frames. Processing takes 4.835 and 4.635 seconds on one warm macOS ARM64 machine, excluding model setup, UI and human review. Software and browser checks establish integration; independent annotation accuracy, correction time, complete cup-placement coverage, depth, action learning and hardware competence remain unmeasured.

In this paper

Engineering integration passed on six public excerpts; annotation accuracy remains unmeasured. On 10 October 2026, we ran a local observation pipeline that decodes video, proposes sampled object and palm boxes, associates nearby detections and opens an editable review timeline. Review changes persist as revisions and export with their source identity. This establishes a working research tool, not reliable automatic task labeling, a cup-placement benchmark or a trained robot skill. The published implementation is anchored to DVIDIA Training commit d355a4a.

+

Install the Observation Lab release · GitHub release and downloads · Try the synthetic review demo · Frozen engineering receipts

+

The pilot produces reviewable 2D evidence

+

The local adapter uses the pinned OpenCV Zoo YOLOX COCO object detector and MediaPipe palm detector. It samples at two frames per second, up to 120 frames and a 640-pixel maximum image side per clip. Proposals retain decoded presentation timestamps, frame and source hashes, raw labels and scores. Same-class image overlap associates detections; palm/object overlap proposes 2D proximity. Neither association establishes physical identity nor overlap proves touching. Palm rectangles are not full-hand segmentation. No optical flow, depth reconstruction, natural-language action captioner or language model participates in this pilot. (Observation contract, frozen model and recipe)

+

The review interface shares one clock between the original video and timeline. It displays a box only within 0.25 seconds of its sampled timestamp, leaving gaps visible. Reviewers can correct labels and boundaries, approve or reject proposals and add missed events. Raw model labels remain separate from the accepted draft. Outcomes default to unknown; visible_completion and incomplete describe the operator's visual assessment. They are not robot-success measurements. (Review interface contract)

+

Saving appends a revision with conflict detection against the current base revision. A stale tab cannot silently replace newer edits. Every event needs a decision before review completion; unsaved changes trigger navigation protection, and export is disabled until saving. Downloads contain the last saved review, episode ID and original source hash. These checks make corrections inspectable. They do not authenticate the operator or turn agreement into independent ground truth. The loopback server performs no uploads and checks the local origin for writes. (Local workflow)

+

Six excerpts establish integration, not accuracy

+

The fixed input order was shirt, stir, pack, onion, melon and jeans, selected before examining model output. Five excerpts come from EgoAnnotate, credited to Taher Panbiharwala and Zainab Barwaniwala; the stir excerpt comes from CoMind, with its full author credit retained in the protocol. The records identify CC BY 4.0 terms and upstream source links. We hash-verified the exact excerpts; full upstream originals were not downloaded or hash-verified for this run. This publication distributes sanitized receipts rather than footage or sampled frames. (Input protocol and credits)

+

The six excerpts total 19 seconds, 2,753,287 bytes and 38 sampled frames. They are neither independent complete attempts nor the intended cup-placement cohort. Unknown session provenance remains one conservative shared group. There was no training split, learning run or physical evaluation. Publisher titles were display metadata and were not fed to the detector. (Episode summary, run and grouping)

+
Recipe attemptCompleted / attempted excerptsProcessing timeRecorded failures
Initial v16/64.835 seconds0
Hardened v1.16/64.635 seconds0
+

These are two single runs on the same inputs and a warm macOS ARM64 machine. Timing includes intake, copy/hash, decoding, detection, association and per-episode writes. It excludes model provisioning/loading, final receipt writing, UI startup and human review. The difference is not a controlled speedup. Peak RAM, energy, cost, p95 latency, minimum hardware and production throughput were not measured. No paid inference API was called. The runtime used Python 3.12.9, OpenCV 5.0.0.93 and NumPy 2.5.3. Execution requested four CPU threads and one inference worker, while frozen OpenCV metadata records ten threads; an enforced thread cap was not independently verified. No GPU path was requested or measured. (Initial receipt, hardened receipt, full frozen protocols, original benchmark description)

+

Workflow checks preserve failures and revisions

+

Review after the initial run identified a possible browser-clock mismatch for nonzero-start videos. Recipe v1.1 rejects nonzero container, video or decoded starts rather than silently moving boxes against an unchanged original. All six inputs have zero starts and were accepted in both runs. Initial artifacts remain alongside the hardened attempt. Same-size media replacement, malformed review IDs and oversized metadata also received workflow checks. These changes do not establish improved detector quality. (Original and revised recipes)

+

The implementation records 307 passing repository tests followed by 24 focused observation tests, including four additional detector-admission/suppression checks. Fifteen browser checks exercised playback, sampled overlays, correction save/reload, manual events, export, unsaved edits and completion validation on an isolated copy. The 390px and 320px layouts had no horizontal overflow; no browser console or page errors were recorded. These are interface and software checks, not physical-phone, Safari or annotation-accuracy qualification. Test edits do not count as independent human references. (Test scope, browser receipt)

+

Qualitative inspection found a saucepan labeled cup, storage jars labeled cups and missed palms in the preliminary stir check. These observations are not a scored accuracy estimate. COCO categories omit task-specific objects; overlap association can fragment or switch identities; two samples per second can miss brief actions. Model scores remain uncalibrated and all automatic outcomes remain unknown. Without independent references, inspection reports accuracy: null and accuracy_status: not_assessed. (Recorded limitations)

+

The release keeps ownership and missing evidence explicit

+

DVIDIA owns the orchestration, intake, timing, proposal association, review contract and workflow. Original DVIDIA Training code remains MIT. Detector preprocessing/postprocessing adapted from OpenCV Zoo retains Apache-2.0 attribution, and the pinned detector artifacts retain their separate upstream licenses and credits. The two ONNX files total about 40 MB and are provisioned explicitly with size/hash verification; inference does not download weights. Model terms do not grant rights to input footage. No new foundation model, SpatialLM, MANO or depth-model weights are claimed. (Exact artifacts and notices)

+

This lab is upstream of robot learning. Image rectangles supply no calibrated XYZ, contact forces, joint actions, gripper commands or robot policy. No automatic physical action is produced, and the existing visual predictor and movement head gain no new skill from this release. The next proposed study collects 30–50 complete permission-cleared cup-placement attempts with explicit session/person grouping, failures, occlusion and recovery. Independent blinded references should precede comparisons of detector-only, temporal-caption, combined and manual annotation at matched quality, correction time and full cost. Depth, a supervised action bridge and closed-loop qualification require separate experiments. (Uncollected cohort and gates)

+

The public Hugging Face Observation Lab Space reuses our review interface with two authored geometric videos and authored image boxes. It is a synthetic workflow demonstration: no detector, VLM or robot policy runs in the hosted page. Revisions stay in each visitor's browser, with a visible temporary-memory fallback if browser storage or cross-tab locking is unavailable. Visitors can edit, save and export their own review without server writes. The actual detector pipeline is installed and run locally on permitted footage. All sixteen hosted files were read anonymously at Space commit 8547b78 and compared with the staged hashes. The public runtime was observed running with its synthetic scope labels visible.

+

Publication preparation reran 311 repository tests and separately checked 22 publisher tests, six synthetic preparation/privacy/media tests and browser-local revision/conflict behavior. Both pinned ONNX detectors loaded and ran on a neutral image in the local CPU runtime; that smoke test measures neither detection accuracy nor task understanding. Release source preserves the original pilot receipts and clarifies the requested-versus-reported thread discrepancy. Original code uses MIT and the detector adapter retains its Apache-2.0 notices. Production uploads, accounts, storage and application analysis remain separate from this research release.

+
diff --git a/docs/papers/fast-accurate-robot-training-simulation/index.html b/docs/papers/fast-accurate-robot-training-simulation/index.html index 10f772c..39e8d84 100644 --- a/docs/papers/fast-accurate-robot-training-simulation/index.html +++ b/docs/papers/fast-accurate-robot-training-simulation/index.html @@ -1,7 +1,7 @@ Fast accurate robot training simulation · DVIDIA Research -

Decision report and local experiment

Fast accurate robot training simulation

· DVIDIA

54 CPU fixture trials · GPU and physical transfer untested

Source & history · Download Markdown

Abstract

A design for an offline, self-hosted training environment that turns demonstrations into calibrated practice and qualified robot skills. We examine contact, deformation, sensor feedback and the performance–accuracy tradeoff, then report 54 deterministic native MuJoCo CPU fixture trials. Fine endpoint agreement did not establish accurate contact transients, and coarse timesteps missed collisions. Minimum GPU memory, rope accuracy and physical transfer remain unmeasured.

In this paper

Decision report · 7 October 2026 · Grok 4.7 research plus primary-source verification · 54 local CPU fixture trials; no GPU training or physical robot tests

+

Decision report and local experiment

Fast accurate robot training simulation

· DVIDIA

54 CPU fixture trials · GPU and physical transfer untested

Source & history · Download Markdown

Abstract

A design for an offline, self-hosted training environment that turns demonstrations into calibrated practice and qualified robot skills. We examine contact, deformation, sensor feedback and the performance–accuracy tradeoff, then report 54 deterministic native MuJoCo CPU fixture trials. Fine endpoint agreement did not establish accurate contact transients, and coarse timesteps missed collisions. Minimum GPU memory, rope accuracy and physical transfer remain unmeasured.

In this paper

Decision report · 7 October 2026 · Grok 4.7 research plus primary-source verification · 54 local CPU fixture trials; no GPU training or physical robot tests

Build an offline, self-hosted environment that converts demonstrations into calibrated practice and qualified robot skills. Start with existing physics engines and concentrate the product on task construction, uncertainty, failure/recovery coverage, efficient scheduling and qualification. Use native MuJoCo for local numerical checks, test MuJoCo Warp for batched rigid contact, and qualify Newton rods or another deformable backend against the actual rope task before selecting it. The microscopic intuition explains why objects resist and deform; the useful simulation interface is the resulting force, motion, friction and sensor response at robot scale. The first product vertical should be bounded rope grasping, pulling, threading and regrasping, with bow tying a later capability. One owned GPU is the starting design target; minimum useful VRAM and an “ultrafast” training rate remain unmeasured. Adding GPUs or servers should scale independent practice worlds, while a released skill retains a declared hardware profile and physical evidence.

Reproduce the response that changes the robot's decision

When a fingertip presses a table, resistance ultimately comes from electromagnetic interactions and quantum constraints on matter. “Electrons reject each other” is a useful intuition but incomplete: atoms also attract and bond, and Pauli exclusion restricts allowed electron states rather than adding a separate classical repulsive force. Molecular structure and collective interactions produce elasticity. We do not need to track electrons to calculate whether a gripper holds a lace; we need the effective mechanical behavior at the force, length and time scales the task uses. (Feynman on forces and elasticity, exclusion and matter)

diff --git a/docs/papers/from-skillspace-to-robot-skill/index.html b/docs/papers/from-skillspace-to-robot-skill/index.html index bd5056d..f21e960 100644 --- a/docs/papers/from-skillspace-to-robot-skill/index.html +++ b/docs/papers/from-skillspace-to-robot-skill/index.html @@ -1,7 +1,7 @@ From Skillspace to robot skill · DVIDIA Research -

Source review and implementation proposal

From Skillspace to robot skill

· DVIDIA

Graduation and robot training not run

Source & history · Download Markdown

Abstract

An Argus review and a proposal to connect original recordings, reviewed episodes, immutable datasets, training runs, held-out evaluation and robot-tested releases. The review separates video annotation from action supervision and defines compatibility beyond a robot’s degree-of-freedom count. A proposed 40-episode annotation pilot and evidence-based graduation criteria remain unrun.

In this paper

Source review and proposal · 6 October 2026 · Graduation experiment not run

+

Source review and implementation proposal

From Skillspace to robot skill

· DVIDIA

Graduation and robot training not run

Source & history · Download Markdown

Abstract

An Argus review and a proposal to connect original recordings, reviewed episodes, immutable datasets, training runs, held-out evaluation and robot-tested releases. The review separates video annotation from action supervision and defines compatibility beyond a robot’s degree-of-freedom count. A proposed 40-episode annotation pilot and evidence-based graduation criteria remain unrun.

In this paper

Source review and proposal · 6 October 2026 · Graduation experiment not run

Follow-up: the Clef image feasibility pilot has now run on five public excerpts. It does not complete the 40-episode accuracy protocol below.

A Skillspace can become the home for a skill's learning history. More uploaded videos do not, by themselves, establish a better policy. We need evidence that new demonstrations add useful coverage, survive quality checks, and improve held-out performance on a specified robot.

This review follows Varun Nair's pipeline post, its linked Argus article, selected upstream source files, and an audit of the DVIDIA website. The design below is our proposal, not an implemented training service. No user footage was sent to any model, no training was run, and no robot was operated for this review.

diff --git a/docs/papers/grok-robotics-research-on-x/index.html b/docs/papers/grok-robotics-research-on-x/index.html index 9b61436..3f6bee8 100644 --- a/docs/papers/grok-robotics-research-on-x/index.html +++ b/docs/papers/grok-robotics-research-on-x/index.html @@ -1,7 +1,7 @@ Grok robotics research on X · DVIDIA Research -

Source review and thesis comparison

Grok robotics research on X

· DVIDIA

Primary sources checked · Experiments proposed

Source & history · Download Markdown

Abstract

Three Grok 4.7 research passes surface observation-to-action, synthetic-practice and reusable-repair ideas. Independent primary-source checks compare those findings with our thesis: observation supplies goals and state, language retrieves a skill, spatial expectations guide attention, and executable feedback with evaluation establishes competence. X posts remain discovery leads. No universal demonstration count or arbitrary-robot transfer follows from the reviewed results.

In this paper

Research snapshot: 7 October 2026 · Grok 4.7 used through Pi CLI · No training, simulation or hardware experiment was run

+

Source review and thesis comparison

Grok robotics research on X

· DVIDIA

Primary sources checked · Experiments proposed

Source & history · Download Markdown

Abstract

Three Grok 4.7 research passes surface observation-to-action, synthetic-practice and reusable-repair ideas. Independent primary-source checks compare those findings with our thesis: observation supplies goals and state, language retrieves a skill, spatial expectations guide attention, and executable feedback with evaluation establishes competence. X posts remain discovery leads. No universal demonstration count or arbitrary-robot transfer follows from the reviewed results.

In this paper

Research snapshot: 7 October 2026 · Grok 4.7 used through Pi CLI · No training, simulation or hardware experiment was run

Your initial thesis has substantial support when expressed as observation-derived goals and task state, language-based retrieval, contextual spatial attention, and simulation-assisted learning of a feedback skill. The evidence does not establish that a fixed quantity of video covers every variant, that XYZ determines what to do, or that a simulated policy downloads unchanged onto arbitrary robots. The strongest interpretation of your small-sample idea is adaptation: existing models supply reusable manipulation knowledge, while new demonstrations specify a task, object or operating region. Recent work makes that interpretation more credible, and also exposes its dependencies. Robots can learn through trial and error and retain useful repairs; execution still needs observable outcomes and compatible actions. A fast virtual training environment is consequently a plausible product hypothesis, but the research first needs to establish which observed information makes training more efficient and which simulated improvements survive physical transfer.

The observation-to-skill thesis matches the evidence when each skill has a tested operating region

The following mapping preserves the sequence you described. “Supported” means a component has demonstrated precedents, not that the complete proposed architecture has been demonstrated.

diff --git a/docs/papers/offline-cable-training-environment/index.html b/docs/papers/offline-cable-training-environment/index.html index f5ec0a4..557100b 100644 --- a/docs/papers/offline-cable-training-environment/index.html +++ b/docs/papers/offline-cable-training-environment/index.html @@ -1,7 +1,7 @@ Offline cable training environment · DVIDIA Research -

Product prototype and local qualification

Offline cable training environment

· DVIDIA

CPU simulation-only · Controller search and frozen evaluation executed

Source & history · Download Markdown

Abstract

The first runnable product loop combines an anchored cable environment, local controller-parameter search, frozen evaluation, offline replay and a manifest-backed skill pack. The selected controller and a fixed feedback baseline both completed 10/10 held-out simulated episodes; zero-force and release controls completed 0/10. A native macOS network-denial run completed 3/3 additional episodes. Ideal endpoint attachment and privileged state bound the result; physical rope calibration, gripping, sensors and GPU throughput remain untested.

In this paper

Product prototype and local qualification · 7 October 2026 · Native CPU simulation only

+

Product prototype and local qualification

Offline cable training environment

· DVIDIA

CPU simulation-only · Controller search and frozen evaluation executed

Source & history · Download Markdown

Abstract

The first runnable product loop combines an anchored cable environment, local controller-parameter search, frozen evaluation, offline replay and a manifest-backed skill pack. The selected controller and a fixed feedback baseline both completed 10/10 held-out simulated episodes; zero-force and release controls completed 0/10. A native macOS network-denial run completed 3/3 additional episodes. Ideal endpoint attachment and privileged state bound the result; physical rope calibration, gripping, sensors and GPU throughput remain untested.

In this paper

Product prototype and local qualification · 7 October 2026 · Native CPU simulation only

The first runnable product loop now connects an authored environment → local practice → a frozen controller → evaluation → an inspectable skill pack. CableEndReach-v0 bends an anchored cable using bounded forces at its terminal site. The selected controller completed 10/10 held-out simulated episodes, but a fixed feedback baseline also completed 10/10 and finished faster. The result establishes an executable research and packaging foundation, with explicit failure controls. It does not establish physical rope accuracy, shoe tying, realistic grasping or a performance advantage over existing simulators.

Runnable source and instructions · Open the recorded replay · Download the skill pack · Complete qualification

The task has an explicit operating envelope

diff --git a/docs/papers/physical-skill-research-agenda/index.html b/docs/papers/physical-skill-research-agenda/index.html index d470711..dda40d2 100644 --- a/docs/papers/physical-skill-research-agenda/index.html +++ b/docs/papers/physical-skill-research-agenda/index.html @@ -1,7 +1,7 @@ Turn physical footage into testable evidence · DVIDIA Research -

Research agenda

Turn physical footage into testable evidence

· DVIDIA

Four baseline protocols proposed

Source & history · Download Markdown

Abstract

A research agenda covering visible capture evidence, relations over time, evaluation provenance and physical grounding. Each question has a bounded protocol and a failure condition. The aim is to measure whether structure and physical signals improve a defined task before scaling collection. Strategic opinions, author-reported results and our untested proposals are kept distinct.

In this paper

DVIDIA should test the usefulness of its evidence before expanding collection volume. The immediate opportunity is to make demonstrations easier to inspect, compare and reproduce, then measure whether added structure or physical signals help a defined task. Sam Padilla's 5 October essay provides a strategic prompt; the technical sources support narrower, testable questions. The four baseline protocols proposed in this agenda have not run, and neither customer demand nor robot transfer has been established. Four contributor-sized studies cover capture quality, relations over time, provenance and physical grounding.

+

Research agenda

Turn physical footage into testable evidence

· DVIDIA

Four baseline protocols proposed

Source & history · Download Markdown

Abstract

A research agenda covering visible capture evidence, relations over time, evaluation provenance and physical grounding. Each question has a bounded protocol and a failure condition. The aim is to measure whether structure and physical signals improve a defined task before scaling collection. Strategic opinions, author-reported results and our untested proposals are kept distinct.

In this paper

DVIDIA should test the usefulness of its evidence before expanding collection volume. The immediate opportunity is to make demonstrations easier to inspect, compare and reproduce, then measure whether added structure or physical signals help a defined task. Sam Padilla's 5 October essay provides a strategic prompt; the technical sources support narrower, testable questions. The four baseline protocols proposed in this agenda have not run, and neither customer demand nor robot transfer has been established. Four contributor-sized studies cover capture quality, relations over time, provenance and physical grounding.

The essay motivates a hypothesis, not a market forecast

In Robotics Data: Bet Hard Or Get Out, Sam Padilla, 5 October 2026, argues for exceptional collection scale, distinctive physical information or synthetic generation. He warns that buyers can internalize embodiment-specific collection and points to opportunities beyond raw data supply. His conversations and volume anecdote are not independently verified demand evidence. (Original essay).

Our inference is a practical test: does an attributable demonstration with observable state changes improve a specific evaluation more than a clip with coarse tags? This would establish a useful property of a research artifact. It would not establish willingness to pay, a durable business model or an executable robot skill. The first deliverable should therefore be a small benchmark with a clear failure condition, rather than a volume target.

diff --git a/docs/papers/robotics-research-pipeline/index.html b/docs/papers/robotics-research-pipeline/index.html index 78707ee..ac7f6dc 100644 --- a/docs/papers/robotics-research-pipeline/index.html +++ b/docs/papers/robotics-research-pipeline/index.html @@ -1,7 +1,7 @@ Robotics research pipeline · DVIDIA Research -

Architecture proposal and staged validation roadmap

Robotics research pipeline

· DVIDIA

Architecture proposal · current simulation alpha · hardware unqualified

Source & history · Download Markdown

Abstract

An updated architecture connects immutable Skillspace recordings, reviewed task-label proposals and synchronized measured telemetry to grouped datasets, separate visual and motor learners, and a proposed local state supervisor. The implemented CPU baseline retains authored phases, gripper decisions and recovery around its learned joint-delta head. New annotation and supervisor pilots, fresh frozen confirmation, physics calibration and compatible skill-installation gates define the next milestones. Automatic labeling, learned supervision, human-video action recovery and physical arm qualification remain unestablished; this publication adds no new training or hardware result.

In this paper

DVIDIA's product goal is a local training environment that converts Skillspace evidence into a versioned skill a compatible robot can install, test and execute with feedback. The next architectural step couples reviewed task descriptions to measured robot state, allowing a skill to decide whether a grasp worked, whether progress stopped and whether to retry or abstain. This paper specifies that pipeline and its validation gates. It adds no trained supervisor, human-video action bridge or hardware qualification. The implemented foundation remains a CPU research alpha with bounded simulation evidence. (Public training package, Published measurements)

+

Architecture proposal and staged validation roadmap

Robotics research pipeline

· DVIDIA

Architecture proposal · current simulation alpha · hardware unqualified

Source & history · Download Markdown

Abstract

An updated architecture connects immutable Skillspace recordings, reviewed task-label proposals and synchronized measured telemetry to grouped datasets, separate visual and motor learners, and a proposed local state supervisor. The implemented CPU baseline retains authored phases, gripper decisions and recovery around its learned joint-delta head. New annotation and supervisor pilots, fresh frozen confirmation, physics calibration and compatible skill-installation gates define the next milestones. Automatic labeling, learned supervision, human-video action recovery and physical arm qualification remain unestablished; this publication adds no new training or hardware result.

In this paper

DVIDIA's product goal is a local training environment that converts Skillspace evidence into a versioned skill a compatible robot can install, test and execute with feedback. The next architectural step couples reviewed task descriptions to measured robot state, allowing a skill to decide whether a grasp worked, whether progress stopped and whether to retry or abstain. This paper specifies that pipeline and its validation gates. It adds no trained supervisor, human-video action bridge or hardware qualification. The implemented foundation remains a CPU research alpha with bounded simulation evidence. (Public training package, Published measurements)

Pipeline at a glance

DVIDIA robotics pipeline: source evidence branches into reviewed label proposals and synchronized numerical telemetry; grouped datasets feed separate visual and motor learners, a proposed state supervisor, frozen simulation evaluation and compatible skill installation. Runtime observations return to bounded decisions and future reviewed recordings.
DVIDIA robotics pipeline: source evidence branches into reviewed label proposals and synchronized numerical telemetry; grouped datasets feed separate visual and motor learners, a proposed state supervisor, frozen simulation evaluation and compatible skill installation. Runtime observations return to bounded decisions and future reviewed recordings.

Figure 1. Solid elements represent implemented components within the bounded simulation pipeline; dashed elements represent proposed integrations. Physical robot execution remains unqualified. A visual model, reviewed label and executable motor policy have different evidence requirements. The diagram describes a target architecture, not a newly completed end-to-end system.

diff --git a/docs/papers/skill-capsule-acquisition/index.html b/docs/papers/skill-capsule-acquisition/index.html index e2a9244..b7a3253 100644 --- a/docs/papers/skill-capsule-acquisition/index.html +++ b/docs/papers/skill-capsule-acquisition/index.html @@ -1,7 +1,7 @@ Skill capsule acquisition and optimization · DVIDIA Research -

Learned movement artifact and installation prototype

Skill capsule acquisition and optimization

· DVIDIA

Simulation-only · teacher/student 7/8 · no overall speedup

Source & history · Download Markdown

Abstract

A compact learned CPU movement head replaces joint-target computation inside an authored placement supervisor. Teacher and student both pass 7/8 in a new frozen evaluation, while episode wall time increases from 6.273 to 6.360 seconds. A 39,845-byte JSON capsule imports into the local lab, checks its exact runtime and qualifies the current scene through native placement and a recorded-arm/open-jaw control. Scene changes require a fresh test. One known scene and repeat pass native network denial; perception, complete task learning, other embodiments and hardware remain unqualified.

In this paper

Measured prototype and proposed next steps · 7 October 2026 · Simulation-only

+

Learned movement artifact and installation prototype

Skill capsule acquisition and optimization

· DVIDIA

Simulation-only · teacher/student 7/8 · no overall speedup

Source & history · Download Markdown

Abstract

A compact learned CPU movement head replaces joint-target computation inside an authored placement supervisor. Teacher and student both pass 7/8 in a new frozen evaluation, while episode wall time increases from 6.273 to 6.360 seconds. A 39,845-byte JSON capsule imports into the local lab, checks its exact runtime and qualifies the current scene through native placement and a recorded-arm/open-jaw control. Scene changes require a fresh test. One known scene and repeat pass native network denial; perception, complete task learning, other embodiments and hardware remain unqualified.

In this paper

Measured prototype and proposed next steps · 7 October 2026 · Simulation-only

DVIDIA now has a compact learned movement artifact that can be packaged for a compatible simulated arm. A normalized RBF head replaces the teacher's joint-target computation; task phases, waypoints, gripper/contact supervision, and bounded recovery remain authored. The frozen head contains 34,171 canonical JSON bytes, and the compiled candidate capsule contains 39,845 bytes. In a new eight-scene evaluation, teacher and student both completed 7/8, without teacher fallback, while total episode wall time increased from 6.273 to 6.360 seconds. This establishes a bounded teacher-to-student acquisition step, with neither reliability improvement nor overall acceleration demonstrated. The useful product path is import → compatibility check → actual local execution and negative control → scene-specific qualification → execution. Human-video learning, calibrated perception/contact, and physical-arm competence remain separate future capabilities. (Training receipt, profiling, candidate capsule).

The acquired behavior is movement inside an authored task

The experiment declares 16 training scenes, four separate development-selection scenes, and eight evaluation scenes with disjoint scene digests. Historical v0.3 held-out cases were excluded and their earlier results remain unchanged. The teacher completed 16/16 collection scenes, generating 6,344 supervised rows: 3,172 sampled native teacher calls and 3,172 extra teacher queries with perturbed Cartesian goals at the same physical states. Augmentation adds movement labels, not another 3,172 physical attempts. The full canonical dataset occupies 3,814,171 bytes. (Protocol, collection).

diff --git a/docs/papers/skillspace-arm-benchmarks/index.html b/docs/papers/skillspace-arm-benchmarks/index.html index d54671a..64520d0 100644 --- a/docs/papers/skillspace-arm-benchmarks/index.html +++ b/docs/papers/skillspace-arm-benchmarks/index.html @@ -1,7 +1,7 @@ Skillspace arm benchmarks and evolution · DVIDIA Research -

Paired simulation benchmark and product assessment

Skillspace arm benchmarks and evolution

· DVIDIA

Mixed held-out result · 30/32 baseline, 29/32 updated

Source & history · Download Markdown

Abstract

Two controller revisions improve development completion from 14/20 to 17/20, but the frozen paired test declines from 30/32 to 29/32: both pass all 24 normal-strength cases while actuator-stress completion falls from 6/8 to 5/8. Instrumented CPU throughput also declines. We publish the regression, unchanged contact and success rules, exact controller snapshots, richer physical inputs, runtime-bound installation and a proposed staged Skillspace contract. Contact forces and penetration remain uncalibrated; learned perception and physical qualification are open.

In this paper

Research and implementation assessment · 7 October 2026 · Simulation-only evidence

+

Paired simulation benchmark and product assessment

Skillspace arm benchmarks and evolution

· DVIDIA

Mixed held-out result · 30/32 baseline, 29/32 updated

Source & history · Download Markdown

Abstract

Two controller revisions improve development completion from 14/20 to 17/20, but the frozen paired test declines from 30/32 to 29/32: both pass all 24 normal-strength cases while actuator-stress completion falls from 6/8 to 5/8. Instrumented CPU throughput also declines. We publish the regression, unchanged contact and success rules, exact controller snapshots, richer physical inputs, runtime-bound installation and a proposed staged Skillspace contract. Contact forces and penetration remain uncalibrated; learned perception and physical qualification are open.

In this paper

Research and implementation assessment · 7 October 2026 · Simulation-only evidence

Skillspace → install → simulated arm makes sense as a grounded, compatible execution workflow. The present implementation imports task metadata, binds an explicitly authored adapter, supplies a metric scene, executes native contact dynamics, and checks completion. Two engineering rounds increased development success from 14/20 to 16/20 to 17/20, but the frozen held-out comparison declined from 30/32 to 29/32: both controllers passed all 24 nominal cases, while actuator-stress success fell from 6/8 to 5/8. There were zero held-out improvements and one regression. Observed instrumented CPU throughput also declined from 12.283× to 11.388× simulated seconds per wall second. The result establishes an auditable simulation workflow and useful failure diagnostics; it establishes neither improved held-out reliability nor calibrated physical accuracy. Skillspaces should evolve toward immutable releases that bind task, embodiment, observations, controller, and independently evaluated evidence. (Frozen assessment).

Installation supplies an explicit execution bridge

The public place_cup envelope contains a task label, robot identifier, recording format, and demonstration count. It does not contain learned weights, actions, object dimensions, metric target coordinates, or camera calibration. The local bridge supplies a declared rigid-box proxy and contact-pick-place-box-v0 adapter for dvidia-authored-6dof-parallel-jaw-v0. Thus installation selects existing authored behavior; it does not infer cup manipulation from the referenced demonstrations. This distinction preserves the useful architecture: language identifies the goal, grounding supplies the state and physical assumptions, a compatible controller acts, and a verifier judges the result. (Public metadata, execution guide).

diff --git a/docs/papers/skillspace-arm-installation/index.html b/docs/papers/skillspace-arm-installation/index.html index 721005f..f05a183 100644 --- a/docs/papers/skillspace-arm-installation/index.html +++ b/docs/papers/skillspace-arm-installation/index.html @@ -1,7 +1,7 @@ Installing a Skillspace on a simulated arm · DVIDIA Research -

Product prototype and native contact qualification

Installing a Skillspace on a simulated arm

· DVIDIA

Public skill link to authored adapter · 6/6 scene placements

Source & history · Download Markdown

Abstract

The first link-to-arm product path installs an existing DVIDIA placement envelope, binds a local authored controller to one simulated arm, and reuses it in independently grounded scenes. Native jaw contacts carry a free box; six layouts complete, while no-motion and identical joint commands with open jaws each complete zero of six. Installed execution passes process-level offline checks. Task metadata contains no learned policy; perception, cup geometry, full arm collisions and physical qualification remain open.

In this paper

Research note, 7 October 2026. The current bridge makes a narrow part of the proposed skill workflow executable: import a DVIDIA skill envelope, install an explicitly authored local simulation adapter, create a scene, and run an articulated arm. It provides a concrete place to investigate observation-to-simulation-to-skill packaging. It does not yet infer an executable policy, object geometry, material properties, or robot calibration from human video.

+

Product prototype and native contact qualification

Installing a Skillspace on a simulated arm

· DVIDIA

Public skill link to authored adapter · 6/6 scene placements

Source & history · Download Markdown

Abstract

The first link-to-arm product path installs an existing DVIDIA placement envelope, binds a local authored controller to one simulated arm, and reuses it in independently grounded scenes. Native jaw contacts carry a free box; six layouts complete, while no-motion and identical joint commands with open jaws each complete zero of six. Installed execution passes process-level offline checks. Task metadata contains no learned policy; perception, cup geometry, full arm collisions and physical qualification remain open.

In this paper

Research note, 7 October 2026. The current bridge makes a narrow part of the proposed skill workflow executable: import a DVIDIA skill envelope, install an explicitly authored local simulation adapter, create a scene, and run an articulated arm. It provides a concrete place to investigate observation-to-simulation-to-skill packaging. It does not yet infer an executable policy, object geometry, material properties, or robot calibration from human video.

The public example is DVIDIA place_cup, whose metadata is served at place_cup/skill.json. The recorded 360-byte source is vdia:0, version 0.3.0, with task “Set a cup on the mark.” Its exact-byte SHA-256 is 16b4e1ef0f3799345c1d18ce9f1da83b072863ab00ce30a83424080fb467d4ec. The envelope declares a demonstration count, recording format and robot identifier; these declarations do not supply trajectories, observations, trained weights, or an evaluated controller. The installation receipt preserves the source bytes, URL, source hash, separate grounding hash, adapter identity and physical_robot_ready: false. A later download may differ; its receipt must identify its own bytes.

In the local studio, one click installs the compatible public envelope and binds contact-pick-place-box-v0 to dvidia-authored-6dof-parallel-jaw-v0. A bundled envelope supports installation without fetching the public site. JSON upload/drop accepts the supported DVIDIA formats. Missing grounding is supplied through a visible, locally authored adapter; inline grounding remains separately validated. Installation downloads metadata and executes the already installed local controller. Object and target coordinates belong to the scene and can change between executions. The browser displays recorded native simulation poses rather than inventing an object trajectory. Execution and replay are designed to work with installed dependencies and local assets; the broader product's air-gapped deployment remains a separate validation task.

The embodiment is an original six-hinge arm with two actuated sliding jaws. Native MuJoCo 3.15.0 simulates a free rigid box, gravity and jaw/object/table contact. The default proxy is a 40 mm cube weighing 40 g on a table at 0.29 m. No weld, mocap attachment, or object-state update carries the object during execution. Arm controls use bounded position servos, model-based bias compensation and current-state damped Jacobian control. The declared limits are 40 N·m per arm actuator and 15 N per jaw. Physics uses a 1 ms timestep, implicitfast integration, Newton solving and an elliptic Coulomb friction cone. These choices describe an authored fixture, not measured hardware or calibrated material fidelity.

diff --git a/docs/papers/skillspace-footage-training/index.html b/docs/papers/skillspace-footage-training/index.html index 96c6ddb..167fab1 100644 --- a/docs/papers/skillspace-footage-training/index.html +++ b/docs/papers/skillspace-footage-training/index.html @@ -1,7 +1,7 @@ Skillspace footage training pipeline · DVIDIA Research -

Product implementation and measured synthetic pilot

Skillspace footage training pipeline

· DVIDIA

Public CPU package · one native scene qualified · simulation-only

Source & history · Download Markdown

Abstract

The public Dvidia-Inference/dvidia-training repository provides a standalone CPU pipeline that audits Skillspace media, freezes grouped splits and exports inspectable artifacts. Ten synthetic six-second clips train a visual predictor with a 0.5106-second median pipeline time across three repeats on one macOS host. Aligned native simulator telemetry supplies 4,029 training labels for a learned joint-delta head, evaluated on one held-out recording. Its capsule passes native placement qualification in that recording's exact scene; identical joint targets with open jaws fail. Installation and hardware guides accompany the package. Human-video action recovery, shoe organization, demonstration sufficiency, independent scene generalization and physical robot competence remain unestablished.

In this paper

Research pipeline evolution — 9 October 2026. The Robotics research pipeline adds the proposed annotation-review and measured-state task-supervisor layers around this implemented training path. It includes an architecture diagram, data contracts and separate validation gates. Those additions are proposals; the recorded pilots and frozen sample-count results below retain their original scope.

+

Product implementation and measured synthetic pilot

Skillspace footage training pipeline

· DVIDIA

Public CPU package · one native scene qualified · simulation-only

Source & history · Download Markdown

Abstract

The public Dvidia-Inference/dvidia-training repository provides a standalone CPU pipeline that audits Skillspace media, freezes grouped splits and exports inspectable artifacts. Ten synthetic six-second clips train a visual predictor with a 0.5106-second median pipeline time across three repeats on one macOS host. Aligned native simulator telemetry supplies 4,029 training labels for a learned joint-delta head, evaluated on one held-out recording. Its capsule passes native placement qualification in that recording's exact scene; identical joint targets with open jaws fail. Installation and hardware guides accompany the package. Human-video action recovery, shoe organization, demonstration sufficiency, independent scene generalization and physical robot competence remain unestablished.

In this paper

Research pipeline evolution — 9 October 2026. The Robotics research pipeline adds the proposed annotation-review and measured-state task-supervisor layers around this implemented training path. It includes an architecture diagram, data contracts and separate validation gates. Those additions are proposals; the recorded pilots and frozen sample-count results below retain their original scope.

The public, standalone DVIDIA training repository provides a local CPU pipeline that turns actual Skillspace media into a fitted visual model and, when aligned numeric actions are supplied, a learned movement head. The useful advance is a reproducible path from source files through provenance checks, grouped splits, measured fitting and portable artifacts. Video prediction and robot movement remain separate claims. Ten synthetic six-second clips demonstrate visual fitting; simulator telemetry supplies the movement pilot's action labels. Its exported capsule installs and passes native qualification in one exact scene, while identical joint targets with open jaws fail. Neither experiment learns shoe organization or reconstructs robot actions from human footage. This report documents the implemented path and its limited measured evidence, rather than establishing a sufficient demonstration count or hardware competence. (Standalone source archive, Qualification receipt)

Published artifacts on Hugging Face

The DVIDIA organization on Hugging Face mirrors the measured pilot for inspection and local reproduction:

diff --git a/docs/papers/spatially-grounded-downloadable-robot-skills/index.html b/docs/papers/spatially-grounded-downloadable-robot-skills/index.html index 903bd95..2aadf38 100644 --- a/docs/papers/spatially-grounded-downloadable-robot-skills/index.html +++ b/docs/papers/spatially-grounded-downloadable-robot-skills/index.html @@ -1,7 +1,7 @@ Spatially grounded downloadable robot skills · DVIDIA Research -

Research synthesis and proposed experiments

Spatially grounded downloadable robot skills

· DVIDIA

Source review · DVIDIA experiments not run

Source & history · Download Markdown

Abstract

A synthesis of learning from human demonstrations, language-conditioned spatial attention, simulation expansion and robot-specific skill delivery. Spatial priors can accelerate inspection but do not determine contact state or control. The proposed downloadable skill packages a controller, initiation and termination conditions, compatible sensing and hardware, recovery behavior and measured evidence. Separate experiments would test attention, data coverage, feedback and transfer.

In this paper

Research synthesis and proposed experiments · 7 October 2026 · No DVIDIA experiment in this report has run

+

Research synthesis and proposed experiments

Spatially grounded downloadable robot skills

· DVIDIA

Source review · DVIDIA experiments not run

Source & history · Download Markdown

Abstract

A synthesis of learning from human demonstrations, language-conditioned spatial attention, simulation expansion and robot-specific skill delivery. Spatial priors can accelerate inspection but do not determine contact state or control. The proposed downloadable skill packages a controller, initiation and termination conditions, compatible sensing and hardware, recovery behavior and measured evidence. Separate experiments would test attention, data coverage, feedback and transfer.

In this paper

Research synthesis and proposed experiments · 7 October 2026 · No DVIDIA experiment in this report has run

My judgment is that the thesis identifies a useful architecture, but its strongest version needs a measurable operating boundary. Human demonstrations can teach what a task means, which state changes matter, and where to inspect; turning those observations into robot control needs an action and embodiment bridge. A command-conditioned spatial prior could accelerate target discovery, provided observation corrects it when a shoe is on a table or the person changes posture. Simulation can expand grounded experience, but generated volume cannot establish coverage of every material, contact, damaged object, or recovery. Fifty examples could adapt a substantial pretrained physical skill model; they are not an established threshold for acquiring all of shoe tying. The falsifiable research claim is: for a fixed pretrained model and robot, task-state annotations, spatially directed inspection, and targeted real/simulated recovery data improve held-out physical success per unit of collection cost, while preserving performance on unusual placements. A downloadable skill is the resulting tested controller, its compatibility and task contract, and evidence of where it works.

This synthesis combines three parallel primary-source research tracks with the existing DVIDIA research context. Grok 4.7 was inaccessible and was not used: the inspected browser was signed out, the exact model could not be verified, and no prompt or response exists. Recent 2026 results below include author-reported preprints; none was independently reproduced here. Architecture, experiments, budgets, and release criteria are proposals.

Demonstrations teach meaning before they supply motor control

diff --git a/docs/publications.json b/docs/publications.json index 88b8a61..bff679c 100644 --- a/docs/publications.json +++ b/docs/publications.json @@ -5,6 +5,20 @@ "follow": "https://x.com/iammrriver", "contributor": null, "publications": [ + { + "slug": "dvidia-observation-lab", + "title": "DVIDIA Observation Lab pilot", + "source": "reports/DVIDIA Observation Lab pilot.md", + "date": "2026-10-10", + "type": "Local observation workflow and engineering feasibility pilot", + "status": "Six public excerpts processed · accuracy not assessed · no robot actions", + "topics": [ + "capture-quality", + "evaluation-provenance", + "physical-grounding" + ], + "abstract": "DVIDIA Observation Lab supplies a local detector and palm-observation workflow with sampled timestamps, source/model provenance, editable timeline revisions and saved-review export. Two engineering attempts each process the same six public excerpts: 19 seconds and 38 sampled frames. Processing takes 4.835 and 4.635 seconds on one warm macOS ARM64 machine, excluding model setup, UI and human review. Software and browser checks establish integration; independent annotation accuracy, correction time, complete cup-placement coverage, depth, action learning and hardware competence remain unmeasured." + }, { "slug": "robotics-research-pipeline", "title": "Robotics research pipeline", diff --git a/docs/sitemap.xml b/docs/sitemap.xml index 5fbf80e..e5c753b 100644 --- a/docs/sitemap.xml +++ b/docs/sitemap.xml @@ -1,2 +1,2 @@ -https://research.dvidia.org/2026-10-09https://research.dvidia.org/papers/robotics-research-pipeline/2026-10-09https://research.dvidia.org/papers/skillspace-footage-training/2026-10-08https://research.dvidia.org/papers/skill-capsule-acquisition/2026-10-07https://research.dvidia.org/papers/skillspace-arm-benchmarks/2026-10-07https://research.dvidia.org/papers/skillspace-arm-installation/2026-10-07https://research.dvidia.org/papers/offline-cable-training-environment/2026-10-07https://research.dvidia.org/papers/fast-accurate-robot-training-simulation/2026-10-07https://research.dvidia.org/papers/grok-robotics-research-on-x/2026-10-07https://research.dvidia.org/papers/spatially-grounded-downloadable-robot-skills/2026-10-07https://research.dvidia.org/papers/clef-and-grounded-video-observations/2026-10-06https://research.dvidia.org/papers/from-skillspace-to-robot-skill/2026-10-06https://research.dvidia.org/papers/physical-skill-research-agenda/2026-10-06https://research.dvidia.org/topics/capture-quality/2026-10-09https://research.dvidia.org/topics/skill-relations/2026-10-09https://research.dvidia.org/topics/evaluation-provenance/2026-10-09https://research.dvidia.org/topics/physical-grounding/2026-10-09 +https://research.dvidia.org/2026-10-10https://research.dvidia.org/papers/dvidia-observation-lab/2026-10-10https://research.dvidia.org/papers/robotics-research-pipeline/2026-10-09https://research.dvidia.org/papers/skillspace-footage-training/2026-10-08https://research.dvidia.org/papers/skill-capsule-acquisition/2026-10-07https://research.dvidia.org/papers/skillspace-arm-benchmarks/2026-10-07https://research.dvidia.org/papers/skillspace-arm-installation/2026-10-07https://research.dvidia.org/papers/offline-cable-training-environment/2026-10-07https://research.dvidia.org/papers/fast-accurate-robot-training-simulation/2026-10-07https://research.dvidia.org/papers/grok-robotics-research-on-x/2026-10-07https://research.dvidia.org/papers/spatially-grounded-downloadable-robot-skills/2026-10-07https://research.dvidia.org/papers/clef-and-grounded-video-observations/2026-10-06https://research.dvidia.org/papers/from-skillspace-to-robot-skill/2026-10-06https://research.dvidia.org/papers/physical-skill-research-agenda/2026-10-06https://research.dvidia.org/topics/capture-quality/2026-10-10https://research.dvidia.org/topics/skill-relations/2026-10-09https://research.dvidia.org/topics/evaluation-provenance/2026-10-10https://research.dvidia.org/topics/physical-grounding/2026-10-10 diff --git a/docs/topics/capture-quality/index.html b/docs/topics/capture-quality/index.html index 430974f..70c22a1 100644 --- a/docs/topics/capture-quality/index.html +++ b/docs/topics/capture-quality/index.html @@ -1,7 +1,7 @@ Capture quality · DVIDIA Research -

Research question

Capture quality

DVIDIA · Visible evidence

Protocols and progress are scoped below

Question

Test whether hands, relevant objects and state changes are actually observable in a POV demonstration.

Question: Test whether hands, relevant objects and state changes are actually observable in a POV demonstration.

+

Research question

Capture quality

DVIDIA · Visible evidence

Protocols and progress are scoped below

Question

Test whether hands, relevant objects and state changes are actually observable in a POV demonstration.

Question: Test whether hands, relevant objects and state changes are actually observable in a POV demonstration.

Status: scoping · Updated 6 October 2026 · Results: not run

Open a research question · Baseline protocol · Bibliography

Primary sources

diff --git a/docs/topics/evaluation-provenance/index.html b/docs/topics/evaluation-provenance/index.html index 4322f95..1023cd3 100644 --- a/docs/topics/evaluation-provenance/index.html +++ b/docs/topics/evaluation-provenance/index.html @@ -1,7 +1,7 @@ Evaluation and provenance · DVIDIA Research -

Research question

Evaluation and provenance

DVIDIA · Reproducible evidence

Protocols and progress are scoped below

Question

Test episode readback, original-to-derivative lineage and split integrity using small, auditable fixtures.

Question: Test episode readback, original-to-derivative lineage and split integrity using small, auditable fixtures.

+

Research question

Evaluation and provenance

DVIDIA · Reproducible evidence

Protocols and progress are scoped below

Question

Test episode readback, original-to-derivative lineage and split integrity using small, auditable fixtures.

Question: Test episode readback, original-to-derivative lineage and split integrity using small, auditable fixtures.

Status: evaluating · Updated 6 October 2026 · Results: image feasibility run complete; reference accuracy and provenance baselines not run

Open a research question · Baseline protocol · Bibliography

Primary sources

diff --git a/docs/topics/physical-grounding/index.html b/docs/topics/physical-grounding/index.html index ec409b4..6f5c84c 100644 --- a/docs/topics/physical-grounding/index.html +++ b/docs/topics/physical-grounding/index.html @@ -1,7 +1,7 @@ Physical grounding · DVIDIA Research -

Research question

Physical grounding

DVIDIA · Signals beyond appearance

Protocols and progress are scoped below

Question

Measure whether state/contact evidence and controlled synthetic augmentation improve a defined physical-skill task.

Robotics research pipeline — 9 October 2026

+

Research question

Physical grounding

DVIDIA · Signals beyond appearance

Protocols and progress are scoped below

Question

Measure whether state/contact evidence and controlled synthetic augmentation improve a defined physical-skill task.

Robotics research pipeline — 9 October 2026

Robotics research pipeline connects footage review, synchronized measured state, separate visual and movement training, frozen simulation evaluation and versioned skill installation. Its diagram identifies current simulation components, proposed automatic labeling and learned task decisions, and the outstanding physical qualification gate. The proposed supervisor consumes recent joint, gripper and contact evidence; it does not equate a close command with a successful grasp. The new annotation-labor pilot is a companion to the existing graduation proposal. Both new experiments are not run. Existing recorded benchmarks retain their original protocols and claims.

Skillspace footage training pipeline introduces the separate public DVIDIA Training diff --git a/docs/topics/skill-relations/index.html b/docs/topics/skill-relations/index.html index 32db2ff..e6b99cf 100644 --- a/docs/topics/skill-relations/index.html +++ b/docs/topics/skill-relations/index.html @@ -1,7 +1,7 @@ Skill relations · DVIDIA Research -

Research question

Skill relations

DVIDIA · Events with evidence

Protocols and progress are scoped below

Question

Calibrate hand–object relations, then test temporal event graphs whose claims point back to video intervals.

Question: Calibrate hand–object relations, then test temporal event graphs whose claims point back to video intervals.

+

Research question

Skill relations

DVIDIA · Events with evidence

Protocols and progress are scoped below

Question

Calibrate hand–object relations, then test temporal event graphs whose claims point back to video intervals.

Question: Calibrate hand–object relations, then test temporal event graphs whose claims point back to video intervals.

Status: scoping · Updated 6 October 2026 · Results: not run

Open a research question · Baseline protocol · Bibliography

Primary sources

diff --git a/publications.json b/publications.json index fa0f897..25bf587 100644 --- a/publications.json +++ b/publications.json @@ -5,6 +5,20 @@ "follow": "https://x.com/iammrriver", "contributor": null, "publications": [ + { + "slug": "dvidia-observation-lab", + "title": "DVIDIA Observation Lab pilot", + "source": "reports/DVIDIA Observation Lab pilot.md", + "date": "2026-10-10", + "type": "Local observation workflow and engineering feasibility pilot", + "status": "Six public excerpts processed \u00b7 accuracy not assessed \u00b7 no robot actions", + "topics": [ + "capture-quality", + "evaluation-provenance", + "physical-grounding" + ], + "abstract": "DVIDIA Observation Lab supplies a local detector and palm-observation workflow with sampled timestamps, source/model provenance, editable timeline revisions and saved-review export. Two engineering attempts each process the same six public excerpts: 19 seconds and 38 sampled frames. Processing takes 4.835 and 4.635 seconds on one warm macOS ARM64 machine, excluding model setup, UI and human review. Software and browser checks establish integration; independent annotation accuracy, correction time, complete cup-placement coverage, depth, action learning and hardware competence remain unmeasured." + }, { "slug": "robotics-research-pipeline", "title": "Robotics research pipeline", diff --git a/reports/DVIDIA Observation Lab pilot.md b/reports/DVIDIA Observation Lab pilot.md new file mode 100644 index 0000000..3a1ed35 --- /dev/null +++ b/reports/DVIDIA Observation Lab pilot.md @@ -0,0 +1,44 @@ +# DVIDIA Observation Lab pilot + +**Engineering integration passed on six public excerpts; annotation accuracy remains unmeasured.** On 10 October 2026, we ran a local observation pipeline that decodes video, proposes sampled object and palm boxes, associates nearby detections and opens an editable review timeline. Review changes persist as revisions and export with their source identity. This establishes a working research tool, not reliable automatic task labeling, a cup-placement benchmark or a trained robot skill. The published implementation is anchored to [DVIDIA Training commit d355a4a](https://github.com/Dvidia-Inference/dvidia-training/tree/d355a4a284cf9bcc4f48dd375ca072d2da188dad). + +[Install the Observation Lab release](https://github.com/Dvidia-Inference/dvidia-training/blob/observation-lab-v0.1.0/docs/observations.md) · [GitHub release and downloads](https://github.com/Dvidia-Inference/dvidia-training/releases/tag/observation-lab-v0.1.0) · [Try the synthetic review demo](https://huggingface.co/spaces/Dvidia/observation-lab) · [Frozen engineering receipts](../topics/evaluation-provenance/runs/2026-10-10-observation-lab/README.md) + +## The pilot produces reviewable 2D evidence + +The local adapter uses the pinned OpenCV Zoo YOLOX COCO object detector and MediaPipe palm detector. It samples at two frames per second, up to 120 frames and a 640-pixel maximum image side per clip. Proposals retain decoded presentation timestamps, frame and source hashes, raw labels and scores. Same-class image overlap associates detections; palm/object overlap proposes 2D proximity. Neither association establishes physical identity nor overlap proves touching. Palm rectangles are not full-hand segmentation. No optical flow, depth reconstruction, natural-language action captioner or language model participates in this pilot. ([Observation contract](https://github.com/Dvidia-Inference/dvidia-training/blob/d355a4a284cf9bcc4f48dd375ca072d2da188dad/docs/observations.md), [frozen model and recipe](../topics/evaluation-provenance/runs/2026-10-10-observation-lab/hardened-protocol.json)) + +The review interface shares one clock between the original video and timeline. It displays a box only within 0.25 seconds of its sampled timestamp, leaving gaps visible. Reviewers can correct labels and boundaries, approve or reject proposals and add missed events. Raw model labels remain separate from the accepted draft. Outcomes default to `unknown`; `visible_completion` and `incomplete` describe the operator's visual assessment. They are not robot-success measurements. ([Review interface contract](https://github.com/Dvidia-Inference/dvidia-training/blob/d355a4a284cf9bcc4f48dd375ca072d2da188dad/docs/observation-ui.md)) + +Saving appends a revision with conflict detection against the current base revision. A stale tab cannot silently replace newer edits. Every event needs a decision before review completion; unsaved changes trigger navigation protection, and export is disabled until saving. Downloads contain the last saved review, episode ID and original source hash. These checks make corrections inspectable. They do not authenticate the operator or turn agreement into independent ground truth. The loopback server performs no uploads and checks the local origin for writes. ([Local workflow](https://github.com/Dvidia-Inference/dvidia-training/blob/d355a4a284cf9bcc4f48dd375ca072d2da188dad/docs/observations.md)) + +## Six excerpts establish integration, not accuracy + +The fixed input order was shirt, stir, pack, onion, melon and jeans, selected before examining model output. Five excerpts come from EgoAnnotate, credited to Taher Panbiharwala and Zainab Barwaniwala; the stir excerpt comes from CoMind, with its full author credit retained in the protocol. The records identify CC BY 4.0 terms and upstream source links. We hash-verified the exact excerpts; full upstream originals were not downloaded or hash-verified for this run. This publication distributes sanitized receipts rather than footage or sampled frames. ([Input protocol and credits](../topics/evaluation-provenance/runs/2026-10-10-observation-lab/initial-protocol.json)) + +The six excerpts total **19 seconds, 2,753,287 bytes and 38 sampled frames**. They are neither independent complete attempts nor the intended cup-placement cohort. Unknown session provenance remains one conservative shared group. There was no training split, learning run or physical evaluation. Publisher titles were display metadata and were not fed to the detector. ([Episode summary](../topics/evaluation-provenance/runs/2026-10-10-observation-lab/episode-summary.json), [run and grouping](../topics/evaluation-provenance/runs/2026-10-10-observation-lab/hardened-run.json)) + +| Recipe attempt | Completed / attempted excerpts | Processing time | Recorded failures | +| --- | ---: | ---: | ---: | +| Initial v1 | 6/6 | 4.835 seconds | 0 | +| Hardened v1.1 | 6/6 | 4.635 seconds | 0 | + +These are two single runs on the same inputs and a warm macOS ARM64 machine. Timing includes intake, copy/hash, decoding, detection, association and per-episode writes. It excludes model provisioning/loading, final receipt writing, UI startup and human review. The difference is not a controlled speedup. Peak RAM, energy, cost, p95 latency, minimum hardware and production throughput were not measured. No paid inference API was called. The runtime used Python 3.12.9, OpenCV 5.0.0.93 and NumPy 2.5.3. Execution requested four CPU threads and one inference worker, while frozen OpenCV metadata records ten threads; an enforced thread cap was not independently verified. No GPU path was requested or measured. ([Initial receipt](../topics/evaluation-provenance/runs/2026-10-10-observation-lab/initial-run.json), [hardened receipt](../topics/evaluation-provenance/runs/2026-10-10-observation-lab/hardened-run.json), [full frozen protocols](../topics/evaluation-provenance/runs/2026-10-10-observation-lab/README.md), [original benchmark description](https://github.com/Dvidia-Inference/dvidia-training/blob/d355a4a284cf9bcc4f48dd375ca072d2da188dad/benchmarks/observation-20261010/README.md)) + +## Workflow checks preserve failures and revisions + +Review after the initial run identified a possible browser-clock mismatch for nonzero-start videos. Recipe v1.1 rejects nonzero container, video or decoded starts rather than silently moving boxes against an unchanged original. All six inputs have zero starts and were accepted in both runs. Initial artifacts remain alongside the hardened attempt. Same-size media replacement, malformed review IDs and oversized metadata also received workflow checks. These changes do not establish improved detector quality. ([Original and revised recipes](../topics/evaluation-provenance/runs/2026-10-10-observation-lab/README.md)) + +The implementation records 307 passing repository tests followed by 24 focused observation tests, including four additional detector-admission/suppression checks. Fifteen browser checks exercised playback, sampled overlays, correction save/reload, manual events, export, unsaved edits and completion validation on an isolated copy. The 390px and 320px layouts had no horizontal overflow; no browser console or page errors were recorded. These are interface and software checks, not physical-phone, Safari or annotation-accuracy qualification. Test edits do not count as independent human references. ([Test scope](https://github.com/Dvidia-Inference/dvidia-training/blob/d355a4a284cf9bcc4f48dd375ca072d2da188dad/benchmarks/observation-20261010/README.md), [browser receipt](../topics/evaluation-provenance/runs/2026-10-10-observation-lab/ui-validation.json)) + +Qualitative inspection found a saucepan labeled cup, storage jars labeled cups and missed palms in the preliminary stir check. These observations are not a scored accuracy estimate. COCO categories omit task-specific objects; overlap association can fragment or switch identities; two samples per second can miss brief actions. Model scores remain uncalibrated and all automatic outcomes remain unknown. Without independent references, inspection reports `accuracy: null` and `accuracy_status: not_assessed`. ([Recorded limitations](https://github.com/Dvidia-Inference/dvidia-training/blob/d355a4a284cf9bcc4f48dd375ca072d2da188dad/benchmarks/observation-20261010/README.md)) + +## The release keeps ownership and missing evidence explicit + +DVIDIA owns the orchestration, intake, timing, proposal association, review contract and workflow. Original DVIDIA Training code remains MIT. Detector preprocessing/postprocessing adapted from OpenCV Zoo retains Apache-2.0 attribution, and the pinned detector artifacts retain their separate upstream licenses and credits. The two ONNX files total about 40 MB and are provisioned explicitly with size/hash verification; inference does not download weights. Model terms do not grant rights to input footage. No new foundation model, SpatialLM, MANO or depth-model weights are claimed. ([Exact artifacts and notices](https://github.com/Dvidia-Inference/dvidia-training/blob/d355a4a284cf9bcc4f48dd375ca072d2da188dad/docs/observation-models.md)) + +This lab is upstream of robot learning. Image rectangles supply no calibrated XYZ, contact forces, joint actions, gripper commands or robot policy. No automatic physical action is produced, and the existing visual predictor and movement head gain no new skill from this release. The next proposed study collects 30–50 complete permission-cleared cup-placement attempts with explicit session/person grouping, failures, occlusion and recovery. Independent blinded references should precede comparisons of detector-only, temporal-caption, combined and manual annotation at matched quality, correction time and full cost. Depth, a supervised action bridge and closed-loop qualification require separate experiments. ([Uncollected cohort and gates](https://github.com/Dvidia-Inference/dvidia-training/blob/d355a4a284cf9bcc4f48dd375ca072d2da188dad/docs/observation-pilot-plan.md)) + +The public [Hugging Face Observation Lab Space](https://huggingface.co/spaces/Dvidia/observation-lab) reuses our review interface with two authored geometric videos and authored image boxes. It is a synthetic workflow demonstration: no detector, VLM or robot policy runs in the hosted page. Revisions stay in each visitor's browser, with a visible temporary-memory fallback if browser storage or cross-tab locking is unavailable. Visitors can edit, save and export their own review without server writes. The actual detector pipeline is installed and run locally on permitted footage. All sixteen hosted files were read anonymously at [Space commit 8547b78](https://huggingface.co/spaces/Dvidia/observation-lab/tree/8547b78f312e39d9a0b299ebe055c401f8135848) and compared with the staged hashes. The public runtime was observed running with its synthetic scope labels visible. + +Publication preparation reran 311 repository tests and separately checked 22 publisher tests, six synthetic preparation/privacy/media tests and browser-local revision/conflict behavior. Both pinned ONNX detectors loaded and ran on a neutral image in the local CPU runtime; that smoke test measures neither detection accuracy nor task understanding. [Release source](https://github.com/Dvidia-Inference/dvidia-training/tree/3cc4a3b03ca6d61479c9f6a86cebf7ccc77fd117) preserves the original pilot receipts and clarifies the requested-versus-reported thread discrepancy. Original code uses MIT and the detector adapter retains its Apache-2.0 notices. Production uploads, accounts, storage and application analysis remain separate from this research release. diff --git a/topics/evaluation-provenance/runs/2026-10-10-observation-lab/README.md b/topics/evaluation-provenance/runs/2026-10-10-observation-lab/README.md new file mode 100644 index 0000000..8726c50 --- /dev/null +++ b/topics/evaluation-provenance/runs/2026-10-10-observation-lab/README.md @@ -0,0 +1,29 @@ +# DVIDIA Observation Lab public evidence + +Six public excerpts completed two local detector/review engineering attempts on +10 October 2026. Accuracy was not assessed, all automatic outcomes remain unknown, +and no robot skill was trained or qualified. + +The six JSON documents here are byte-for-byte copies of the public benchmark +records in [DVIDIA Training commit d355a4a](https://github.com/Dvidia-Inference/dvidia-training/tree/d355a4a284cf9bcc4f48dd375ca072d2da188dad/benchmarks/observation-20261010). +They retain model/source credits, license declarations, hashes, timing scope, +grouping, complete attempted-run denominators and interface-check scope. + +[Read the paper](../../../../reports/DVIDIA%20Observation%20Lab%20pilot.md) · +[Original benchmark description](https://github.com/Dvidia-Inference/dvidia-training/blob/d355a4a284cf9bcc4f48dd375ca072d2da188dad/benchmarks/observation-20261010/README.md) + +| Evidence | Scope | +| --- | --- | +| [Initial protocol](initial-protocol.json) | First frozen source order, excerpt identities, model recipe and declared limits | +| [Initial run](initial-run.json) | Six attempted/completed excerpts, no failures, timing and source grouping | +| [Hardened protocol](hardened-protocol.json) | Revised zero-start admission recipe and model/license provenance | +| [Hardened run](hardened-run.json) | Separate second-attempt receipt on the same six inputs | +| [Episode summary](episode-summary.json) | Per-excerpt duration, proposal count, processing time and source hash | +| [Browser checks](ui-validation.json) | Isolated review-copy behavior; no model-accuracy inference | + +Raw media, sampled frames, weights, private metadata and test review edits are not +redistributed in this evidence folder. A receipt hash binds a retained artifact; +it does not establish authenticity, semantic truth or reproduction without the +permitted inputs. Full upstream-original hashes were not independently verified. +The six excerpts share one conservative unknown-session group and cannot be +counted as six independent complete cup-placement attempts. diff --git a/topics/evaluation-provenance/runs/2026-10-10-observation-lab/episode-summary.json b/topics/evaluation-provenance/runs/2026-10-10-observation-lab/episode-summary.json new file mode 100644 index 0000000..a6cf4a6 --- /dev/null +++ b/topics/evaluation-provenance/runs/2026-10-10-observation-lab/episode-summary.json @@ -0,0 +1,80 @@ +[ + { + "id": "shirt", + "duration_seconds": 3.0, + "metrics": { + "accuracy_status": "not_assessed", + "detected_frames": 6, + "elapsed_seconds": 0.6693273328710347, + "frames": 6, + "inference_seconds": 0.46699687489308417 + }, + "proposals": 7, + "source_sha256": "8392c62f4e9590a15745311746114c2b6355e24c60fa87fef68e834f20762113" + }, + { + "id": "stir", + "duration_seconds": 4.0, + "metrics": { + "accuracy_status": "not_assessed", + "detected_frames": 8, + "elapsed_seconds": 1.1173061658628285, + "frames": 8, + "inference_seconds": 0.6056890829931945 + }, + "proposals": 25, + "source_sha256": "4ffe78850d4e6475546a521e0eb425f7a34c632679183cf112aacb70ec1b0861" + }, + { + "id": "pack", + "duration_seconds": 3.0, + "metrics": { + "accuracy_status": "not_assessed", + "detected_frames": 6, + "elapsed_seconds": 0.6751292911358178, + "frames": 6, + "inference_seconds": 0.4420628750231117 + }, + "proposals": 7, + "source_sha256": "87a67e5b10f124a65df7d669086d4a9b2cb7ae25a5d758594b9b3aa7b0938f4c" + }, + { + "id": "onion", + "duration_seconds": 3.0, + "metrics": { + "accuracy_status": "not_assessed", + "detected_frames": 6, + "elapsed_seconds": 0.7398202081676573, + "frames": 6, + "inference_seconds": 0.43661770783364773 + }, + "proposals": 10, + "source_sha256": "100e25698ee99e99dc648c41d9864144e312f0fce7c07dc9a7b06b487b9a2a5f" + }, + { + "id": "melon", + "duration_seconds": 3.0, + "metrics": { + "accuracy_status": "not_assessed", + "detected_frames": 6, + "elapsed_seconds": 0.7281540830153972, + "frames": 6, + "inference_seconds": 0.4237409171182662 + }, + "proposals": 14, + "source_sha256": "f32cf75d28602d169b4f302830ba633a351ac890596887c54c8e928efcf2650e" + }, + { + "id": "jeans", + "duration_seconds": 3.0, + "metrics": { + "accuracy_status": "not_assessed", + "detected_frames": 6, + "elapsed_seconds": 0.6997090000659227, + "frames": 6, + "inference_seconds": 0.4299595837946981 + }, + "proposals": 9, + "source_sha256": "95845362951b3f78b7b731691df6d472bf176ced4b07ecef4d99d0b8a21da3e2" + } +] diff --git a/topics/evaluation-provenance/runs/2026-10-10-observation-lab/hardened-protocol.json b/topics/evaluation-provenance/runs/2026-10-10-observation-lab/hardened-protocol.json new file mode 100644 index 0000000..f424e21 --- /dev/null +++ b/topics/evaluation-provenance/runs/2026-10-10-observation-lab/hardened-protocol.json @@ -0,0 +1 @@ +{"created_at":"2026-10-10T11:22:03.270961+00:00","execution":"local_offline","hardware":{"machine":"arm64","platform":"Darwin"},"kind":"dvidia.observation-protocol.v1","limits":{"cpu_threads":4,"workers":1},"manifest_sha256":"6e4e3a0b1b12eeb32cafcba0668d2614c80b022a91eafc7740018be880eddb29","model":{"backend":"opencv","coordinates":"normalized_image_xyxy","cpu_threads":10,"device":"cpu","hand_box_semantics":"Palm detector rectangle; not full hand segmentation or observed contact.","hand_detector_enabled":true,"hand_threshold":0.5,"implementation_sha256":"e1c6939779ab39a32497e00c35892a98eef59c3dd512135f1ac6cd4f897d1a22","implementation_version":1,"kind":"opencv-zoo-yolox-palm","limitations":["COCO labels can be wrong or absent, especially for small and occluded objects.","Palm boxes do not establish finger contact, grasp, force, depth, task success or robot actions.","Object identity and temporal relationships require a separate tracking stage."],"max_detections":30,"max_nms_candidates":1000,"models":[{"bytes":35858002,"directory":"object_detection_yolox","download_url":"https://media.githubusercontent.com/media/opencv/opencv_zoo/47534e27c9851bb1128ccc0102f1145e27f23f98/models/object_detection_yolox/object_detection_yolox_2022nov.onnx","license":"Apache-2.0","license_bytes":11371,"license_sha256":"0ec3668d3274bcf29e8a29e9576d5a2cd96fc78d3c5bec4387355a796e5d9088","license_url":"https://raw.githubusercontent.com/opencv/opencv_zoo/47534e27c9851bb1128ccc0102f1145e27f23f98/models/object_detection_yolox/LICENSE","name":"object_detection_yolox_2022nov.onnx","revision":"47534e27c9851bb1128ccc0102f1145e27f23f98","role":"objects","sha256":"c5c2d13e59ae883e6af3b45daea64af4833a4951c92d116ec270d9ddbe998063","source":"https://github.com/opencv/opencv_zoo/blob/47534e27c9851bb1128ccc0102f1145e27f23f98/models/object_detection_yolox/object_detection_yolox_2022nov.onnx"},{"bytes":3905734,"directory":"palm_detection_mediapipe","download_url":"https://media.githubusercontent.com/media/opencv/opencv_zoo/47534e27c9851bb1128ccc0102f1145e27f23f98/models/palm_detection_mediapipe/palm_detection_mediapipe_2023feb.onnx","license":"Apache-2.0","license_bytes":11358,"license_sha256":"cfc7749b96f63bd31c3c42b5c471bf756814053e847c10f3eb003417bc523d30","license_url":"https://raw.githubusercontent.com/opencv/opencv_zoo/47534e27c9851bb1128ccc0102f1145e27f23f98/models/palm_detection_mediapipe/LICENSE","name":"palm_detection_mediapipe_2023feb.onnx","revision":"47534e27c9851bb1128ccc0102f1145e27f23f98","role":"palms","sha256":"78ff51c38496b7fc8b8ebdb6cc8c1abb02fa6c38427c6848254cdaba57fcce7c","source":"https://github.com/opencv/opencv_zoo/blob/47534e27c9851bb1128ccc0102f1145e27f23f98/models/palm_detection_mediapipe/palm_detection_mediapipe_2023feb.onnx"}],"nms_iou":{"objects":0.5,"palms":0.3},"runtime":{"numpy":"2.5.3","opencv":"5.0.0"},"score_kind":"uncalibrated_model_evidence","threshold":0.35},"recipe":{"automatic_outcome":"unknown","claim_scope":"sampled_2d_observations","id":"dvidia-observations-v1.1","max_duration_seconds":60,"max_frames":120,"max_image_side":640,"max_track_gap_seconds":0.8,"minimum_association_iou":0.2,"samples_per_second":2,"timebase":"zero-origin video and container; nonzero starts rejected"},"sources":[{"credit":"Taher Panbiharwala and Zainab Barwaniwala; EgoAnnotate v1; excerpt starts 0s, original full hash not verified","id":"shirt","kind":"public","license":"CC BY 4.0","permission":"local_analysis","session_id":"unknown-shared-publisher-session","sha256":"8392c62f4e9590a15745311746114c2b6355e24c60fa87fef68e834f20762113","source_recording_id":"https://huggingface.co/datasets/TaherPanbiharwala/EgoAnnotate/blob/156d13adaee4110cf63e54fa940ec16ff199d12f/videos/GX010079.mp4","source_url":"https://huggingface.co/datasets/TaherPanbiharwala/EgoAnnotate/blob/156d13adaee4110cf63e54fa940ec16ff199d12f/videos/GX010079.mp4","title":"Starting to fold a white shirt"},{"credit":"Alexey Gavryushin, Dingxi Zhang, Zhao Huang, Alexandros Delitzas, Jiaqi Chen, Ben Ellis, Cedric Z\u00f6llner, Manthan Patel, Manuel Kaufmann, Marc Pollefeys, and Xi Wang; CoMind (2026); excerpt starts 1s, original full hash not verified","id":"stir","kind":"public","license":"CC BY 4.0","permission":"local_analysis","session_id":"unknown-shared-publisher-session","sha256":"4ffe78850d4e6475546a521e0eb425f7a34c632679183cf112aacb70ec1b0861","source_recording_id":"https://comind.ethz.ch/","source_url":"https://comind.ethz.ch/","title":"Stirring vegetables in a pan"},{"credit":"Taher Panbiharwala and Zainab Barwaniwala; EgoAnnotate v1; excerpt starts 0s, original full hash not verified","id":"pack","kind":"public","license":"CC BY 4.0","permission":"local_analysis","session_id":"unknown-shared-publisher-session","sha256":"87a67e5b10f124a65df7d669086d4a9b2cb7ae25a5d758594b9b3aa7b0938f4c","source_recording_id":"https://huggingface.co/datasets/TaherPanbiharwala/EgoAnnotate/blob/156d13adaee4110cf63e54fa940ec16ff199d12f/videos/GX010087.mp4","source_url":"https://huggingface.co/datasets/TaherPanbiharwala/EgoAnnotate/blob/156d13adaee4110cf63e54fa940ec16ff199d12f/videos/GX010087.mp4","title":"Moving food from a tray toward a container"},{"credit":"Taher Panbiharwala and Zainab Barwaniwala; EgoAnnotate v1; excerpt starts 0s, original full hash not verified","id":"onion","kind":"public","license":"CC BY 4.0","permission":"local_analysis","session_id":"unknown-shared-publisher-session","sha256":"100e25698ee99e99dc648c41d9864144e312f0fce7c07dc9a7b06b487b9a2a5f","source_recording_id":"https://huggingface.co/datasets/TaherPanbiharwala/EgoAnnotate/blob/156d13adaee4110cf63e54fa940ec16ff199d12f/videos/GX010072.mp4","source_url":"https://huggingface.co/datasets/TaherPanbiharwala/EgoAnnotate/blob/156d13adaee4110cf63e54fa940ec16ff199d12f/videos/GX010072.mp4","title":"Slicing an onion on a pink plate"},{"credit":"Taher Panbiharwala and Zainab Barwaniwala; EgoAnnotate v1; excerpt starts 0s, original full hash not verified","id":"melon","kind":"public","license":"CC BY 4.0","permission":"local_analysis","session_id":"unknown-shared-publisher-session","sha256":"f32cf75d28602d169b4f302830ba633a351ac890596887c54c8e928efcf2650e","source_recording_id":"https://huggingface.co/datasets/TaherPanbiharwala/EgoAnnotate/blob/156d13adaee4110cf63e54fa940ec16ff199d12f/videos/GX010076.mp4","source_url":"https://huggingface.co/datasets/TaherPanbiharwala/EgoAnnotate/blob/156d13adaee4110cf63e54fa940ec16ff199d12f/videos/GX010076.mp4","title":"Cutting a watermelon wedge"},{"credit":"Taher Panbiharwala and Zainab Barwaniwala; EgoAnnotate v1; excerpt starts 0s, original full hash not verified","id":"jeans","kind":"public","license":"CC BY 4.0","permission":"local_analysis","session_id":"unknown-shared-publisher-session","sha256":"95845362951b3f78b7b731691df6d472bf176ced4b07ecef4d99d0b8a21da3e2","source_recording_id":"https://huggingface.co/datasets/TaherPanbiharwala/EgoAnnotate/blob/156d13adaee4110cf63e54fa940ec16ff199d12f/videos/GX010081.mp4","source_url":"https://huggingface.co/datasets/TaherPanbiharwala/EgoAnnotate/blob/156d13adaee4110cf63e54fa940ec16ff199d12f/videos/GX010081.mp4","title":"Folding grey jeans"}]} \ No newline at end of file diff --git a/topics/evaluation-provenance/runs/2026-10-10-observation-lab/hardened-run.json b/topics/evaluation-provenance/runs/2026-10-10-observation-lab/hardened-run.json new file mode 100644 index 0000000..30e5c2a --- /dev/null +++ b/topics/evaluation-provenance/runs/2026-10-10-observation-lab/hardened-run.json @@ -0,0 +1 @@ +{"accuracy_status":"not_assessed","attempted":6,"completed":6,"elapsed_seconds":4.635012916056439,"episodes":[{"episode_sha256":"26b67bb490a0853482817f840715a17ae827830f32898b5fed60ccbcd51fd1a0","id":"shirt"},{"episode_sha256":"8b18fbda42aa44fa008fd763c865a045a416947b00464126b2e31b1c2c1c5ac8","id":"stir"},{"episode_sha256":"bb76a1996112fcb0bed37b988a4698676788b068d77e33ac4bc8cd080f6042da","id":"pack"},{"episode_sha256":"b94f9d15c4ecfc8c843d6c2d0e22568dbe32337cfe03091b7ef1bb529e1ee449","id":"onion"},{"episode_sha256":"7be44932308e08032322cfff7d9ee264335c016266c36015b0a991fb3cef9dab","id":"melon"},{"episode_sha256":"dee34f090cd5697889a6f904e30be6669085bf4db79273c56af3e4959151168e","id":"jeans"}],"failures":[],"geometry":"image_coordinates_only","kind":"dvidia.observation-run.v1","protocol_sha256":"3cd74c261157101b459563ff2b449c847194055fa024e60a6ed56aed94cf1b9c","robot_skill_qualified":false,"sessions":{"unknown-shared-publisher-session":["shirt","stir","pack","onion","melon","jeans"]},"timing_scope":"intake, decode, inference, association and per-episode writes; excludes model setup and final receipt"} \ No newline at end of file diff --git a/topics/evaluation-provenance/runs/2026-10-10-observation-lab/initial-protocol.json b/topics/evaluation-provenance/runs/2026-10-10-observation-lab/initial-protocol.json new file mode 100644 index 0000000..4425dd8 --- /dev/null +++ b/topics/evaluation-provenance/runs/2026-10-10-observation-lab/initial-protocol.json @@ -0,0 +1 @@ +{"created_at":"2026-10-10T11:14:17.377906+00:00","execution":"local_offline","hardware":{"machine":"arm64","platform":"Darwin"},"kind":"dvidia.observation-protocol.v1","limits":{"cpu_threads":4,"workers":1},"manifest_sha256":"6e4e3a0b1b12eeb32cafcba0668d2614c80b022a91eafc7740018be880eddb29","model":{"backend":"opencv","coordinates":"normalized_image_xyxy","cpu_threads":10,"device":"cpu","hand_box_semantics":"Palm detector rectangle; not full hand segmentation or observed contact.","hand_detector_enabled":true,"hand_threshold":0.5,"implementation_sha256":"89cf6a3058661ec03acf78e3eaeab1182f235b0c2fe0d03b406fbaaafb29c2a4","implementation_version":1,"kind":"opencv-zoo-yolox-palm","limitations":["COCO labels can be wrong or absent, especially for small and occluded objects.","Palm boxes do not establish finger contact, grasp, force, depth, task success or robot actions.","Object identity and temporal relationships require a separate tracking stage."],"max_detections":30,"max_nms_candidates":1000,"models":[{"bytes":35858002,"directory":"object_detection_yolox","download_url":"https://media.githubusercontent.com/media/opencv/opencv_zoo/47534e27c9851bb1128ccc0102f1145e27f23f98/models/object_detection_yolox/object_detection_yolox_2022nov.onnx","license":"Apache-2.0","license_url":"https://raw.githubusercontent.com/opencv/opencv_zoo/47534e27c9851bb1128ccc0102f1145e27f23f98/models/object_detection_yolox/LICENSE","name":"object_detection_yolox_2022nov.onnx","revision":"47534e27c9851bb1128ccc0102f1145e27f23f98","role":"objects","sha256":"c5c2d13e59ae883e6af3b45daea64af4833a4951c92d116ec270d9ddbe998063","source":"https://github.com/opencv/opencv_zoo/blob/47534e27c9851bb1128ccc0102f1145e27f23f98/models/object_detection_yolox/object_detection_yolox_2022nov.onnx"},{"bytes":3905734,"directory":"palm_detection_mediapipe","download_url":"https://media.githubusercontent.com/media/opencv/opencv_zoo/47534e27c9851bb1128ccc0102f1145e27f23f98/models/palm_detection_mediapipe/palm_detection_mediapipe_2023feb.onnx","license":"Apache-2.0","license_url":"https://raw.githubusercontent.com/opencv/opencv_zoo/47534e27c9851bb1128ccc0102f1145e27f23f98/models/palm_detection_mediapipe/LICENSE","name":"palm_detection_mediapipe_2023feb.onnx","revision":"47534e27c9851bb1128ccc0102f1145e27f23f98","role":"palms","sha256":"78ff51c38496b7fc8b8ebdb6cc8c1abb02fa6c38427c6848254cdaba57fcce7c","source":"https://github.com/opencv/opencv_zoo/blob/47534e27c9851bb1128ccc0102f1145e27f23f98/models/palm_detection_mediapipe/palm_detection_mediapipe_2023feb.onnx"}],"nms_iou":{"objects":0.5,"palms":0.3},"runtime":{"numpy":"2.5.3","opencv":"5.0.0"},"score_kind":"uncalibrated_model_evidence","threshold":0.35},"recipe":{"automatic_outcome":"unknown","claim_scope":"sampled_2d_observations","id":"dvidia-observations-v1","max_duration_seconds":60,"max_frames":120,"max_image_side":640,"max_track_gap_seconds":0.8,"minimum_association_iou":0.2,"samples_per_second":2},"sources":[{"credit":"Taher Panbiharwala and Zainab Barwaniwala; EgoAnnotate v1; excerpt starts 0s, original full hash not verified","id":"shirt","kind":"public","license":"CC BY 4.0","permission":"local_analysis","session_id":"unknown-shared-publisher-session","sha256":"8392c62f4e9590a15745311746114c2b6355e24c60fa87fef68e834f20762113","source_recording_id":"https://huggingface.co/datasets/TaherPanbiharwala/EgoAnnotate/blob/156d13adaee4110cf63e54fa940ec16ff199d12f/videos/GX010079.mp4","source_url":"https://huggingface.co/datasets/TaherPanbiharwala/EgoAnnotate/blob/156d13adaee4110cf63e54fa940ec16ff199d12f/videos/GX010079.mp4","title":"Starting to fold a white shirt"},{"credit":"Alexey Gavryushin, Dingxi Zhang, Zhao Huang, Alexandros Delitzas, Jiaqi Chen, Ben Ellis, Cedric Z\u00f6llner, Manthan Patel, Manuel Kaufmann, Marc Pollefeys, and Xi Wang; CoMind (2026); excerpt starts 1s, original full hash not verified","id":"stir","kind":"public","license":"CC BY 4.0","permission":"local_analysis","session_id":"unknown-shared-publisher-session","sha256":"4ffe78850d4e6475546a521e0eb425f7a34c632679183cf112aacb70ec1b0861","source_recording_id":"https://comind.ethz.ch/","source_url":"https://comind.ethz.ch/","title":"Stirring vegetables in a pan"},{"credit":"Taher Panbiharwala and Zainab Barwaniwala; EgoAnnotate v1; excerpt starts 0s, original full hash not verified","id":"pack","kind":"public","license":"CC BY 4.0","permission":"local_analysis","session_id":"unknown-shared-publisher-session","sha256":"87a67e5b10f124a65df7d669086d4a9b2cb7ae25a5d758594b9b3aa7b0938f4c","source_recording_id":"https://huggingface.co/datasets/TaherPanbiharwala/EgoAnnotate/blob/156d13adaee4110cf63e54fa940ec16ff199d12f/videos/GX010087.mp4","source_url":"https://huggingface.co/datasets/TaherPanbiharwala/EgoAnnotate/blob/156d13adaee4110cf63e54fa940ec16ff199d12f/videos/GX010087.mp4","title":"Moving food from a tray toward a container"},{"credit":"Taher Panbiharwala and Zainab Barwaniwala; EgoAnnotate v1; excerpt starts 0s, original full hash not verified","id":"onion","kind":"public","license":"CC BY 4.0","permission":"local_analysis","session_id":"unknown-shared-publisher-session","sha256":"100e25698ee99e99dc648c41d9864144e312f0fce7c07dc9a7b06b487b9a2a5f","source_recording_id":"https://huggingface.co/datasets/TaherPanbiharwala/EgoAnnotate/blob/156d13adaee4110cf63e54fa940ec16ff199d12f/videos/GX010072.mp4","source_url":"https://huggingface.co/datasets/TaherPanbiharwala/EgoAnnotate/blob/156d13adaee4110cf63e54fa940ec16ff199d12f/videos/GX010072.mp4","title":"Slicing an onion on a pink plate"},{"credit":"Taher Panbiharwala and Zainab Barwaniwala; EgoAnnotate v1; excerpt starts 0s, original full hash not verified","id":"melon","kind":"public","license":"CC BY 4.0","permission":"local_analysis","session_id":"unknown-shared-publisher-session","sha256":"f32cf75d28602d169b4f302830ba633a351ac890596887c54c8e928efcf2650e","source_recording_id":"https://huggingface.co/datasets/TaherPanbiharwala/EgoAnnotate/blob/156d13adaee4110cf63e54fa940ec16ff199d12f/videos/GX010076.mp4","source_url":"https://huggingface.co/datasets/TaherPanbiharwala/EgoAnnotate/blob/156d13adaee4110cf63e54fa940ec16ff199d12f/videos/GX010076.mp4","title":"Cutting a watermelon wedge"},{"credit":"Taher Panbiharwala and Zainab Barwaniwala; EgoAnnotate v1; excerpt starts 0s, original full hash not verified","id":"jeans","kind":"public","license":"CC BY 4.0","permission":"local_analysis","session_id":"unknown-shared-publisher-session","sha256":"95845362951b3f78b7b731691df6d472bf176ced4b07ecef4d99d0b8a21da3e2","source_recording_id":"https://huggingface.co/datasets/TaherPanbiharwala/EgoAnnotate/blob/156d13adaee4110cf63e54fa940ec16ff199d12f/videos/GX010081.mp4","source_url":"https://huggingface.co/datasets/TaherPanbiharwala/EgoAnnotate/blob/156d13adaee4110cf63e54fa940ec16ff199d12f/videos/GX010081.mp4","title":"Folding grey jeans"}]} \ No newline at end of file diff --git a/topics/evaluation-provenance/runs/2026-10-10-observation-lab/initial-run.json b/topics/evaluation-provenance/runs/2026-10-10-observation-lab/initial-run.json new file mode 100644 index 0000000..5a57c5e --- /dev/null +++ b/topics/evaluation-provenance/runs/2026-10-10-observation-lab/initial-run.json @@ -0,0 +1 @@ +{"accuracy_status":"not_assessed","attempted":6,"completed":6,"elapsed_seconds":4.835139082977548,"episodes":[{"episode_sha256":"e5225fd8209e6a27f1b906d02cd642f52d4b21693a5d1ec671146aacaa7282b7","id":"shirt"},{"episode_sha256":"a4b1323797769802f7b945185748814038c1ef391fb0f94cf77a84cf5748a24e","id":"stir"},{"episode_sha256":"4ab53292050295dbd3fa3615b499b42a61013c7751fd992ba725266b241cec7b","id":"pack"},{"episode_sha256":"a4a4cf5b23ae679a712f79a522824b347560d5f0c1a6dcc246316244af6f900e","id":"onion"},{"episode_sha256":"a5cc8dd002f65cde1639771952fa0099415e22a2103e44cd1bfba7147e8e62ca","id":"melon"},{"episode_sha256":"dc0ace7b027e2260e791b278d9241c8b42f2e9243ce7d0ab9e47a00a25db734d","id":"jeans"}],"failures":[],"geometry":"image_coordinates_only","kind":"dvidia.observation-run.v1","protocol_sha256":"71629e04edd72e1daccb968e011f68db07ae87cf9fa083976cb1a73744a32926","robot_skill_qualified":false,"sessions":{"unknown-shared-publisher-session":["shirt","stir","pack","onion","melon","jeans"]},"timing_scope":"intake, decode, inference, association and per-episode writes; excludes model setup and final receipt"} \ No newline at end of file diff --git a/topics/evaluation-provenance/runs/2026-10-10-observation-lab/ui-validation.json b/topics/evaluation-provenance/runs/2026-10-10-observation-lab/ui-validation.json new file mode 100644 index 0000000..e39c612 --- /dev/null +++ b/topics/evaluation-provenance/runs/2026-10-10-observation-lab/ui-validation.json @@ -0,0 +1,22 @@ +{ + "scope": "Local isolated UI QA copy; not model accuracy", + "checks": [ + "Desktop loads real episode and unknown outcome without horizontal overflow", + "Video plays, sampled overlays render, and box visibility toggles", + "Corrected approval persists after reload while raw label and unknown outcome remain unchanged", + "A new blank manual event can be removed; a labeled manual event can be approved and saved", + "Downloaded review matches persisted revision and original source hash", + "Episode navigation protects unsaved changes, preserves Keep reviewing, and honors explicit discard", + "Structured model and source provenance render as readable text", + "390px phone layout has no horizontal overflow and visible controls have 44px targets", + "320px phone layout has no horizontal overflow and visible controls have 44px targets", + "No browser console or page errors", + "Accepted events preserve decimal timing, including 0.25s\u20130.50s", + "Overlay counts match timestamp-bounded real evidence at 12 sample and gap boundaries", + "Pending events block completion without writing an invalid revision", + "390px: event selection reveals editor, provenance follows review, no overflow, 44px controls", + "320px: event selection reveals editor, provenance follows review, no overflow, 44px controls" + ], + "console_errors": [], + "screenshots": "Kept locally with ignored QA run; no source frames redistributed" +}