Skip to content

fix(workspace): keep real native benchmark results distinguishable #8025

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
huangruiteng merged 1 commit into from
Nov 4, 2026
+2,698 −25
Merged

fix(workspace): keep real native benchmark results distinguishable #8025

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1,217 changes: 1,217 additions & 0 deletions apps/presentation/dashboard/src/data/fixtures/edgebench-ad-native-results.json
View file
Open in desktop

Large diffs are not rendered by default.

52 changes: 50 additions & 2 deletions apps/presentation/dashboard/src/data/fixtures/edgebench-graph-saved-analysis.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,8 +11,8 @@
"Six purposively selected native-feedback episodes; population and causal effect remain unknown.",
"Complete saved analysis responses, including original judgments, costs and language-specific cache misses, are unchanged.",
"No Explore events were recorded in this selected analysis Goal. Empty history is not a reconstructed solver history.",
"Only the included native-report-4 citation range is portable; uncaptured citations are explicitly unavailable.",
"No authority store, execution state, raw session transcript, model process or solver is restored by this display fixture."
"No authority store, execution state, raw session transcript, model process or solver is restored by this display fixture.",
"The included native-report-4 range, baseline/retained/final inventory rows and terminal retention range are portable. Other citations remain explicitly unavailable."
]
},
"analysis_readbacks": {
Expand Down Expand Up @@ -3038,6 +3038,54 @@
"text": " \"pass_rate\": 1.0,\n \"score\": 0.8359291793199752,\n \"score_0_100\": 83.59291793199752,\n \"timed_out\": false,\n \"runtime_seconds\": 63.152724742889404,\n \"test_details\": [],\n \"valid\": true,\n \"summary\": \"valid=true final_score=0.835929 overall_score=0.865158 macro_f1=0.850742 micro_f1=0.851681 balanced_accuracy=0.852224 one_minus_ece=0.989116 avg_time=18.698s checks=4/4\",",
"applicability": "current"
}
},
{
"request_path": "/api/chat/research-analysis/citation?goal_id=edgebench-official-graph-analysis-20261011-04&pack_id=020a5c5ee69d6795192a5544255219b8f91e1d0e272fe6db355e99d226903db1&analysis_key=34f5c3e46e75c1a937b33c98ae27109af0865621a30792a0be1651fac24a23f2&source_id=released-native-inventory&first_line=16&last_line=16",
"response_sha256": "0651057126c012fae6e801246f944307c3f89fc62e2b436a5743f34e96135dcb",
"response": {
"source_id": "released-native-inventory",
"artifact": "product-goal-sources/official/graph/native-observations.jsonl",
"first_line": 16,
"last_line": 16,
"text": "{\"submission_index\":16,\"result_id\":\"6e610c29e0ae\",\"candidate_ref\":\"agent-16\",\"valid\":true,\"value\":0.849544264387785,\"submitted_at\":\"2026-10-12T03:59:48.720Z\",\"observed_at\":\"2026-10-12T04:01:22.153Z\",\"observed_at_meaning\":\"first captured completed native-submit command containing this exact submission id and score; not inferred feedback-release time\",\"report_artifact\":\"native-runs/runs/graph-official-native3600-integration-20261011-04/graph_node_classification/submissions/agent-16/report.json\",\"report_sha256\":\"1b6bf435d3ffee98cd9da360ba16842a432f24a236bb921c3048f2027da9d1d4\",\"observation_artifact\":\"native-runs/runs/graph-official-native3600-integration-20261011-04/graph_node_classification/collected/native-sessions/sessions/2026/10/11/rollout-2026-10-11T12-28-48-01a12aef-d388-7233-ac51-5462f173f3e2.jsonl\",\"observation_artifact_sha256\":\"0d23d4a7aec8d84732c9c797ee236e4201b693d725522e21f3a09f2f93cc14f1\",\"observation_line\":10043}",
"applicability": "current"
}
},
{
"request_path": "/api/chat/research-analysis/citation?goal_id=edgebench-official-graph-analysis-20261011-04&pack_id=020a5c5ee69d6795192a5544255219b8f91e1d0e272fe6db355e99d226903db1&analysis_key=34f5c3e46e75c1a937b33c98ae27109af0865621a30792a0be1651fac24a23f2&source_id=released-native-inventory&first_line=18&last_line=18",
"response_sha256": "060ad2fc74e415851e23e49fa54cffc22d133cb31e857bf3c021e3c9d62e398b",
"response": {
"source_id": "released-native-inventory",
"artifact": "product-goal-sources/official/graph/native-observations.jsonl",
"first_line": 18,
"last_line": 18,
"text": "{\"submission_index\":18,\"result_id\":\"ba86adc7653e\",\"candidate_ref\":\"agent-18\",\"valid\":true,\"value\":0.8485288027628158,\"submitted_at\":\"2026-10-12T06:00:45.288Z\",\"observed_at\":\"2026-10-12T06:02:40.679Z\",\"observed_at_meaning\":\"first captured completed native-submit command containing this exact submission id and score; not inferred feedback-release time\",\"report_artifact\":\"native-runs/runs/graph-official-native3600-integration-20261011-04/graph_node_classification/submissions/agent-18/report.json\",\"report_sha256\":\"3de7073f0959ad2ce0e089782cdb23760fad92db6ab6af9024363b352e8c629c\",\"observation_artifact\":\"native-runs/runs/graph-official-native3600-integration-20261011-04/graph_node_classification/collected/native-sessions/sessions/2026/10/11/rollout-2026-10-11T12-28-48-01a12aef-d388-7233-ac51-5462f173f3e2.jsonl\",\"observation_artifact_sha256\":\"0d23d4a7aec8d84732c9c797ee236e4201b693d725522e21f3a09f2f93cc14f1\",\"observation_line\":11739}",
"applicability": "current"
}
},
{
"request_path": "/api/chat/research-analysis/citation?goal_id=edgebench-official-graph-analysis-20261011-04&pack_id=020a5c5ee69d6795192a5544255219b8f91e1d0e272fe6db355e99d226903db1&analysis_key=34f5c3e46e75c1a937b33c98ae27109af0865621a30792a0be1651fac24a23f2&source_id=released-native-inventory&first_line=2&last_line=2",
"response_sha256": "714dc46c200e0eddaf4795e3deea6b193ced07a328bf615a03fcd557e56dca79",
"response": {
"source_id": "released-native-inventory",
"artifact": "product-goal-sources/official/graph/native-observations.jsonl",
"first_line": 2,
"last_line": 2,
"text": "{\"submission_index\":2,\"result_id\":\"e00dc3959c91\",\"candidate_ref\":\"agent-2\",\"valid\":true,\"value\":0.8172464473565724,\"submitted_at\":\"2026-10-11T13:37:19.792Z\",\"observed_at\":\"2026-10-11T13:39:12.474Z\",\"observed_at_meaning\":\"first captured completed native-submit command containing this exact submission id and score; not inferred feedback-release time\",\"report_artifact\":\"native-runs/runs/graph-official-native3600-integration-20261011-04/graph_node_classification/submissions/agent-2/report.json\",\"report_sha256\":\"b67702eaf09c908143cf59372697d041838f08bbcfdc13b151c0736ba33de94b\",\"observation_artifact\":\"native-runs/runs/graph-official-native3600-integration-20261011-04/graph_node_classification/collected/native-sessions/sessions/2026/10/11/rollout-2026-10-11T12-28-48-01a12aef-d388-7233-ac51-5462f173f3e2.jsonl\",\"observation_artifact_sha256\":\"0d23d4a7aec8d84732c9c797ee236e4201b693d725522e21f3a09f2f93cc14f1\",\"observation_line\":722}",
"applicability": "current"
}
},
{
"request_path": "/api/chat/research-analysis/citation?goal_id=edgebench-official-graph-analysis-20261011-04&pack_id=020a5c5ee69d6795192a5544255219b8f91e1d0e272fe6db355e99d226903db1&analysis_key=34f5c3e46e75c1a937b33c98ae27109af0865621a30792a0be1651fac24a23f2&source_id=original-terminal-result&first_line=7&last_line=9",
"response_sha256": "374d13e98fb31a93785d1f7a6a571ee4d28fb68eb328387f6eb2a05881f3ce32",
"response": {
"source_id": "original-terminal-result",
"artifact": "native-runs/runs/graph-official-native3600-integration-20261011-04/graph_node_classification/final_result.json",
"first_line": 7,
"last_line": 9,
"text": " \"best_pass_rate\": 1.0,\n \"best_round\": \"agent-16\",\n \"total_rounds\": 18,",
"applicability": "current"
}
}
]
}
Loading
Loading