source: cell_forensics.csv; rollup.json
Task registration facts
The accession is H-M024, the identifier assigned to this maintenance task, and the host-side record of the task names it logged time reported in hours as well as minutes. 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-M024/task_manifest.json; 5. Experiment/4. Task Library/Project H/H-M024/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 | 10 | 6 | 4 | 0 | 1 |
H-LAP-L1H | 9 | 5 | 4 | 0 | 2 |
H-LAP-L2C | 1 | 1 | 0 | 0 | 0 |
H-LAP-L2S | 1 | 1 | 0 | 0 | 1 |
H-LAP-L2T | 1 | 1 | 0 | 0 | 0 |
H-LAP-L3B | 1 | 1 | 0 | 0 | 1 |
H-LAP-L4P | 1 | 0 | 1 | 0 | 1 |
H-LAP-L5P | 17 | 7 | 6 | 4 | 8 |
H-NON | 9 | 7 | 2 | 0 | 1 |
H-STR | 11 | 8 | 3 | 0 | 5 |
| source: cell_forensics.csv |
Recorded failure causes
| Failure cause | Count | Share of task rows | Example cells |
|---|---|---|---|
A2, a cause code (a grouped failure label) for success after a hidden-failure retry | 7 | 11.5% of 61 task rows | 045-20260830-survey-c-documented-arm / H-LAP-L5P__H-M024__full__s1; 060-20260902-nd-haiku-hint-off / H-LAP-L5P__H-M024__full__s1; 064-20260902-nd-local-hint-off-seed2 / H-STR__H-M024__full__s2 |
A4a, a cause code (a grouped failure label) for same requirement failed on every pass | 6 | 9.8% of 61 task rows | 053-20260831-survey-qwen3coder-throughput / H-LAP-L5P__H-M024__full__s1; 076-20260905-auto-qwen3-coder-30b-a3b-instruct-awq-02 / H-LAP-L1__H-M024__full__s1; 077-20260905-auto-qwen3-coder-30b-a3b-instruct-awq-02 / H-LAP-L1__H-M024__full__s1 |
A4n, a cause code (a grouped failure label) for hidden failure on every pass, no requirement named | 1 | 1.6% of 61 task rows | 082-20260906-auto-qwen3-8-27b-fp8-0956 / H-LAP-L4P__H-M024__full__s1 |
A5, a cause code (a grouped failure label) for no edit made | 7 | 11.5% of 61 task rows | 114-20260910-auto-igx-thor-qwen3-4b-fp8-1535 / H-LAP-L1H__H-M024__full__s4; 166-20260911-auto-dgx-qwen3-4b-fp8-1022 / H-NON__H-M024__full__s5; 174-20260911-auto-dgx-qwen3-4b-fp8-1626 / H-LAP-L5P__H-M024__full__s5 |
| source: rollup.json; cell_forensics.csv |
Visible and hidden tier disagreements
| Run set | Cell | Field | Expected record | Observed record |
|---|---|---|---|---|
091-20260909-auto-igx-thor-agent-coder-1859 | H-LAP-L1H__H-M024__full__s2 | population_key | register | missing_from_forensics (record comparison) |
168-20260911-auto-dgx-agent-coder-1157 | H-LAP-L5P__H-M024__full__s4 | population_key | register | missing_from_forensics (record comparison) |
203-20260912-auto-igx-thor-agent-coder-1053 | H-LAP-L1H__H-M024__full__s9 | population_key | register | missing_from_forensics (record comparison) |
203-20260912-auto-igx-thor-agent-coder-1053 | H-LAP-L5P__H-M024__full__s6 | population_key | register | missing_from_forensics (record comparison) |
203-20260912-auto-igx-thor-agent-coder-1053 | H-STR__H-M024__full__s8 | population_key | register | missing_from_forensics (record comparison) |
| 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-M024/task_manifest.json; provenance.json