From 97956d9e4d2193675bc53eef75cd48f1c7bfa2ce Mon Sep 17 00:00:00 2001 From: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> Date: Sat, 7 Nov 2026 10:31:33 +0800 Subject: [PATCH] docs(research): link retained benchmark trajectories Signed-off-by: LoopX Agent <337587101+loopx-agent@users.noreply.github.com> --- .../edgebench-ad-20261023-history.json | 6 ++++ ...ench-grid-context-on-20261103-history.json | 6 ++++ .../edgebench-schema-20261025-history.json | 6 ++++ .../research-history.md | 30 +++++++++++++++++++ 4 files changed, 48 insertions(+) diff --git a/apps/presentation/dashboard/src/data/fixtures/edgebench-ad-20261023-history.json b/apps/presentation/dashboard/src/data/fixtures/edgebench-ad-20261023-history.json index e411881ddd..7c2117859b 100644 --- a/apps/presentation/dashboard/src/data/fixtures/edgebench-ad-20261023-history.json +++ b/apps/presentation/dashboard/src/data/fixtures/edgebench-ad-20261023-history.json @@ -22,6 +22,12 @@ "Native and local measurement scopes remain distinct. Cancelled or invalid runs do not qualify a scientific comparison." ], "redactions": [], + "trajectory_archive": { + "url": "https://huggingface.co/datasets/huangrt01/loopx-edgebench-research-checkpoints-20261015/resolve/a97e88f951deb6827d7051a59927860e9e4c4476/20261107-real-benchmark-trajectories/ad_placement_optimization.zip", + "sha256": "45ce26e44a59587b5a086d3aabde9bba9899b184abd6a21029f75c8b6695a44b", + "manifest_url": "https://huggingface.co/datasets/huangrt01/loopx-edgebench-research-checkpoints-20261015/blob/a97e88f951deb6827d7051a59927860e9e4c4476/20261107-real-benchmark-trajectories/manifest.json", + "redactions_url": "https://huggingface.co/datasets/huangrt01/loopx-edgebench-research-checkpoints-20261015/blob/a97e88f951deb6827d7051a59927860e9e4c4476/20261107-real-benchmark-trajectories/redactions.json" + }, "boundary": "Display-state events only. No authority or credential store, raw session transcript, hidden evaluator, workspace or model weights are included." }, "source_counts": { diff --git a/apps/presentation/dashboard/src/data/fixtures/edgebench-grid-context-on-20261103-history.json b/apps/presentation/dashboard/src/data/fixtures/edgebench-grid-context-on-20261103-history.json index dc64720394..93b4599ac6 100644 --- a/apps/presentation/dashboard/src/data/fixtures/edgebench-grid-context-on-20261103-history.json +++ b/apps/presentation/dashboard/src/data/fixtures/edgebench-grid-context-on-20261103-history.json @@ -21,6 +21,12 @@ "These runs include operational interventions and are not a qualified causal comparison. Local and native measurements retain separate scopes." ], "redactions": [], + "trajectory_archive": { + "url": "https://huggingface.co/datasets/huangrt01/loopx-edgebench-research-checkpoints-20261015/resolve/a97e88f951deb6827d7051a59927860e9e4c4476/20261107-real-benchmark-trajectories/grid_turing_robot.zip", + "sha256": "ea147c9ae7173e3f1ce9ca6e0bbda5e0103e2be035b8e6d0658dd35a2d282c8d", + "manifest_url": "https://huggingface.co/datasets/huangrt01/loopx-edgebench-research-checkpoints-20261015/blob/a97e88f951deb6827d7051a59927860e9e4c4476/20261107-real-benchmark-trajectories/manifest.json", + "redactions_url": "https://huggingface.co/datasets/huangrt01/loopx-edgebench-research-checkpoints-20261015/blob/a97e88f951deb6827d7051a59927860e9e4c4476/20261107-real-benchmark-trajectories/redactions.json" + }, "boundary": "Display-state events only. No execution/authority store, credentials, raw session transcript, hidden evaluator, workspace or model weights are included." }, "source_counts": { diff --git a/apps/presentation/dashboard/src/data/fixtures/edgebench-schema-20261025-history.json b/apps/presentation/dashboard/src/data/fixtures/edgebench-schema-20261025-history.json index c4b3f81750..060a2356aa 100644 --- a/apps/presentation/dashboard/src/data/fixtures/edgebench-schema-20261025-history.json +++ b/apps/presentation/dashboard/src/data/fixtures/edgebench-schema-20261025-history.json @@ -22,6 +22,12 @@ "Native and local measurement scopes remain distinct. Cancelled or invalid runs do not qualify a scientific comparison." ], "redactions": [], + "trajectory_archive": { + "url": "https://huggingface.co/datasets/huangrt01/loopx-edgebench-research-checkpoints-20261015/resolve/a97e88f951deb6827d7051a59927860e9e4c4476/20261107-real-benchmark-trajectories/schemathesis_config_modernization.zip", + "sha256": "e892d3b9569d84c7fff8ce80c2a0ae9f9a801d5f745eb980bfc918835327b2ea", + "manifest_url": "https://huggingface.co/datasets/huangrt01/loopx-edgebench-research-checkpoints-20261015/blob/a97e88f951deb6827d7051a59927860e9e4c4476/20261107-real-benchmark-trajectories/manifest.json", + "redactions_url": "https://huggingface.co/datasets/huangrt01/loopx-edgebench-research-checkpoints-20261015/blob/a97e88f951deb6827d7051a59927860e9e4c4476/20261107-real-benchmark-trajectories/redactions.json" + }, "boundary": "Display-state events only. No authority or credential store, raw session transcript, hidden evaluator, workspace or model weights are included." }, "source_counts": { diff --git a/examples/personal-workspace-browser/research-history.md b/examples/personal-workspace-browser/research-history.md index 6454cb1211..4152f3172c 100644 --- a/examples/personal-workspace-browser/research-history.md +++ b/examples/personal-workspace-browser/research-history.md @@ -92,6 +92,36 @@ the same preview's `--fixture` option; their original Goal IDs stay intact. These display captures do not include their complete session trajectories or qualify installed App adoption, paid analysis or a scientific comparison. +## Captured session archives + +The [fixed capture set](https://huggingface.co/datasets/huangrt01/loopx-edgebench-research-checkpoints-20261015/tree/a97e88f951deb6827d7051a59927860e9e4c4476/20261107-real-benchmark-trajectories) links the three real display +fixtures above to all four retained solver-session files: + +| Display fixture | Captured session archive | +| --- | --- | +| Grid context on | [Grid ZIP](https://huggingface.co/datasets/huangrt01/loopx-edgebench-research-checkpoints-20261015/resolve/a97e88f951deb6827d7051a59927860e9e4c4476/20261107-real-benchmark-trajectories/grid_turing_robot.zip) | +| Ad placement | [Ad ZIP](https://huggingface.co/datasets/huangrt01/loopx-edgebench-research-checkpoints-20261015/resolve/a97e88f951deb6827d7051a59927860e9e4c4476/20261107-real-benchmark-trajectories/ad_placement_optimization.zip) | +| Schemathesis | [Schema ZIP](https://huggingface.co/datasets/huangrt01/loopx-edgebench-research-checkpoints-20261015/resolve/a97e88f951deb6827d7051a59927860e9e4c4476/20261107-real-benchmark-trajectories/schemathesis_config_modernization.zip) | + +Each fixture's `provenance.trajectory_archive` pins the archive and its SHA-256. +The [manifest](https://huggingface.co/datasets/huangrt01/loopx-edgebench-research-checkpoints-20261015/blob/a97e88f951deb6827d7051a59927860e9e4c4476/20261107-real-benchmark-trajectories/manifest.json) binds native session IDs, +original/published/compressed hashes, record counts and capture variants; the +[redaction audit](https://huggingface.co/datasets/huangrt01/loopx-edgebench-research-checkpoints-20261015/blob/a97e88f951deb6827d7051a59927860e9e4c4476/20261107-real-benchmark-trajectories/redactions.json) identifies every +removed opaque encrypted field. All plaintext values and unchanged JSONL lines +were compared with the source, and all seven published files were read back by +SHA-256. The 382 Explore records remain byte-identical. + +The Schema receiver's alternate runtime capture is a strict prefix missing +56 tail records; the longer worker-session file is retained. Earlier Schema +session history keeps its original identity. Complete captured files do not +establish whole-run coverage or active duration. Invalid/cancelled statuses, +unknown adoption/cost and unqualified scientific comparisons remain explicit. +The earlier checkpoint release below remains available at its original version. + +中文：三例现有真实展示样例现在关联到同一固定 HF 版本的完整已捕获会话，保留 +原文、身份、取消/无效状态及未知覆盖。Schema 较短副本缺少的 56 条尾部记录已 +由较长原文件保留；清单和逐字段脱敏审计可查，不据此推断科学收益或完整运行覆盖。 + ## Earlier research checkpoints ### Saved analysis reference