source: cell_forensics.csv; rollup.json
Task registration facts
The accession is H-M036, the identifier assigned to this maintenance task, and the host-side record of the task names it the daily mention digest (sequence C-4, step 4 of 4, the step the trap springs on). The task index records the task as registered for measured runs. An arm, one software build supplied to an agent, ran as H-LAP-L1, H-LAP-L1H, H-LAP-L2S, H-LAP-L2T, H-LAP-L5P, H-NON, H-STR. A cell, one execution for an arm and seed, is the row counted below. A seed, the repeat number that distinguishes repetitions, is part of the cell identifier. A run set, one named batch of cells, is part of the evidence record. A probe, a hidden check used to score work, can appear in a run-set identifier. A documentation dose, the amount of documentation supplied with a build, can appear in a run-set identifier. An agent-coder, a local model alias used for a coding run, can appear in a run-set identifier (arm identifiers).
source: 5. Experiment/4. Task Library/Project H/H-M036/task_manifest.json; 5. Experiment/4. Task Library/Project H/H-M036/README.md; cell_forensics.csv
Attempt outcomes by arm
A hidden tier, host-side checks withheld from the agent, decides the hidden result. A visible tier, checks shown during the attempt, can disagree with it. An invalid attempt, an attempt carrying one or more instrument flags, remains visible in its outcome count.
| Arm | Attempts | Hidden-tier pass | Hidden-tier fail | Not run | Invalid |
|---|---|---|---|---|---|
H-LAP-L1 | 3 | 1 | 2 | 0 | 0 |
H-LAP-L1H | 2 | 1 | 1 | 0 | 0 |
H-LAP-L2S | 1 | 0 | 1 | 0 | 1 |
H-LAP-L2T | 1 | 0 | 1 | 0 | 1 |
H-LAP-L5P | 4 | 2 | 2 | 0 | 1 |
H-NON | 3 | 2 | 1 | 0 | 1 |
H-STR | 1 | 0 | 1 | 0 | 1 |
| source: cell_forensics.csv |
Recorded failure causes
| Failure cause | Count | Share of task rows | Example cells |
|---|---|---|---|
A4a, a cause code (a grouped failure label) for same requirement failed on every pass | 7 | 46.7% of fifteen task rows | 043-20260830-survey-a-control-arm / H-NON__H-M036__full__s1; 044-20260830-survey-b-stripped-arm / H-STR__H-M036__full__s1; 047-20260830-survey-c-documented-arm-remainder / H-LAP-L5P__H-M036__full__s1 |
A4n, a cause code (a grouped failure label) for hidden failure on every pass, no requirement named | 2 | 13.3% of fifteen task rows | 080-20260905-auto-qwen3-8-27b-fp8-1135 / H-LAP-L2S__H-M036__full__s1; 084-20260907-auto-qwen3-8-27b-fp8-0657 / H-LAP-L2T__H-M036__full__s1 |
| source: rollup.json; cell_forensics.csv |
Visible and hidden tier disagreements
No visible-tier and hidden-tier disagreement is recorded for this task. source: disagreements.csv
Agent pass timing figures
The pass evidence contains no duration field, so it provides no median or longest agent pass figure. source: pass_forensics.csv
Evidence sources
The numbers above come from the named forensics files and the task manifest. The forensics package records provenance commit 6a0e5432f8750522e3bbacaf89b48de13a8e8058.
source: cell_forensics.csv; pass_forensics.csv; disagreements.csv; rollup.json; 5. Experiment/4. Task Library/Project H/H-M036/task_manifest.json; provenance.json