source: cell_forensics.csv; rollup.json
Task registration facts
The accession is H-M033, the identifier assigned to this maintenance task, and the host-side record of the task names it the mention notification list (sequence C-4, step 1 of 4). 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-L2C, H-LAP-L2S, H-LAP-L2T, H-LAP-L3B, H-LAP-L4P, 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-M033/task_manifest.json; 5. Experiment/4. Task Library/Project H/H-M033/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 | 13 | 7 | 4 | 2 | 6 |
H-LAP-L1H | 12 | 6 | 6 | 0 | 5 |
H-LAP-L2C | 1 | 1 | 0 | 0 | 0 |
H-LAP-L2S | 2 | 1 | 0 | 1 | 1 |
H-LAP-L2T | 1 | 1 | 0 | 0 | 0 |
H-LAP-L3B | 1 | 0 | 1 | 0 | 1 |
H-LAP-L4P | 1 | 0 | 1 | 0 | 1 |
H-LAP-L5P | 9 | 7 | 2 | 0 | 1 |
H-NON | 9 | 8 | 1 | 0 | 1 |
H-STR | 9 | 4 | 5 | 0 | 2 |
| source: cell_forensics.csv |
Recorded failure causes
| Failure cause | Count | Share of task rows | Example cells |
|---|---|---|---|
A11, a cause code (a grouped failure label) for no success, visible verdict varied between passes | 1 | 1.7% of 58 task rows | 065-20260902-experiment-1348 / H-LAP-L1H__H-M033__full__s1 |
A2, a cause code (a grouped failure label) for success after a hidden-failure retry | 7 | 12.1% of 58 task rows | 055-20260901-experiment-1102 / H-LAP-L1H__H-M033__full__s1; 055-20260901-experiment-1102 / H-LAP-L1__H-M033__full__s1; 056-20260901-experiment-1538 / H-LAP-L1H__H-M033__full__s1 |
A4a, a cause code (a grouped failure label) for same requirement failed on every pass | 8 | 13.8% of 58 task rows | 044-20260830-survey-b-stripped-arm / H-STR__H-M033__full__s1; 047-20260830-survey-c-documented-arm-remainder / H-LAP-L5P__H-M033__full__s1; 050-20260830-survey-discriminating-ladder / H-LAP-L1H__H-M033__full__s1 |
A4b, a cause code (a grouped failure label) for failed requirements changed between passes | 1 | 1.7% of 58 task rows | 066-20260902-experiment-1640 / H-LAP-L1H__H-M033__full__s1 |
A5, a cause code (a grouped failure label) for no edit made | 8 | 13.8% of 58 task rows | 107-20260910-auto-igx-thor-qwen3-4b-fp8-1204 / H-LAP-L1__H-M033__full__s3; 108-20260910-auto-dgx-qwen3-4b-fp8-1204 / H-LAP-L5P__H-M033__full__s3; 112-20260910-auto-dgx-qwen3-4b-fp8-1530 / H-STR__H-M033__full__s3 |
A7, a cause code (a grouped failure label) for visible failure on every pass | 1 | 1.7% of 58 task rows | 065-20260902-experiment-1348 / H-LAP-L1__H-M033__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-M033/task_manifest.json; provenance.json