{"evidence": [], "model_id": "llama3.2:3b", "prompts_measured": 30, "prompts_total": 30, "provider": "ollama", "reasons": [], "rejected_samples": 0, "run_log_entry": true, "samples_expected": 750, "samples_logged": 750, "samples_published": 750, "scheduled": true, "stance_cells": 10, "stance_unscored": 0, "status": "ok", "unexplained": false, "unusable_samples": 0, "week_id": "2026-W40"}
{"evidence": [], "model_id": "claude-opus-4-8", "prompts_measured": 30, "prompts_total": 30, "provider": "anthropic", "reasons": [], "rejected_samples": 0, "run_log_entry": true, "samples_expected": 600, "samples_logged": 600, "samples_published": 600, "scheduled": true, "stance_cells": 10, "stance_unscored": 0, "status": "ok", "unexplained": false, "unusable_samples": 0, "week_id": "2026-W40"}
{"evidence": [], "model_id": "claude-opus-5", "prompts_measured": 30, "prompts_total": 30, "provider": "anthropic", "reasons": [], "rejected_samples": 0, "run_log_entry": true, "samples_expected": 600, "samples_logged": 600, "samples_published": 600, "scheduled": true, "stance_cells": 10, "stance_unscored": 0, "status": "ok", "unexplained": false, "unusable_samples": 0, "week_id": "2026-W40"}
{"evidence": [], "model_id": "llama3.2:3b", "prompts_measured": 30, "prompts_total": 30, "provider": "ollama", "reasons": [], "rejected_samples": 0, "run_log_entry": true, "samples_expected": 750, "samples_logged": 750, "samples_published": 750, "scheduled": true, "stance_cells": 10, "stance_unscored": 0, "status": "ok", "unexplained": false, "unusable_samples": 0, "week_id": "2026-W39"}
{"evidence": [], "model_id": "gpt-5.5", "prompts_measured": 30, "prompts_total": 30, "provider": "openai", "reasons": [], "rejected_samples": 12, "run_log_entry": true, "samples_expected": 600, "samples_logged": 588, "samples_published": 588, "scheduled": true, "stance_cells": 10, "stance_unscored": 0, "status": "ok", "unexplained": false, "unusable_samples": 0, "week_id": "2026-W39"}
{"evidence": [], "model_id": "llama3.2:3b", "prompts_measured": 30, "prompts_total": 30, "provider": "ollama", "reasons": [], "rejected_samples": 0, "run_log_entry": true, "samples_expected": 750, "samples_logged": 750, "samples_published": 750, "scheduled": true, "stance_cells": 10, "stance_unscored": 0, "status": "ok", "unexplained": false, "unusable_samples": 0, "week_id": "2026-W38"}
{"evidence": ["issue #38"], "model_id": "claude-opus-4-8", "prompts_measured": 0, "prompts_total": 30, "provider": "anthropic", "reasons": ["Prepaid Anthropic API credit was still empty: 0 of 600 samples. Both Opus models failed all 60 of their pairs."], "rejected_samples": 0, "run_log_entry": true, "samples_expected": 600, "samples_logged": 0, "samples_published": 0, "scheduled": true, "stance_cells": null, "stance_unscored": null, "status": "lost", "unexplained": false, "unusable_samples": 0, "week_id": "2026-W38"}
{"evidence": ["issue #38"], "model_id": "claude-opus-5", "prompts_measured": 0, "prompts_total": 30, "provider": "anthropic", "reasons": ["Prepaid Anthropic API credit was still empty: 0 of 600 samples. Both Opus models failed all 60 of their pairs."], "rejected_samples": 0, "run_log_entry": true, "samples_expected": 600, "samples_logged": 0, "samples_published": 0, "scheduled": true, "stance_cells": null, "stance_unscored": null, "status": "lost", "unexplained": false, "unusable_samples": 0, "week_id": "2026-W38"}
{"evidence": [], "model_id": "llama3.2:3b", "prompts_measured": 30, "prompts_total": 30, "provider": "ollama", "reasons": [], "rejected_samples": 0, "run_log_entry": true, "samples_expected": 750, "samples_logged": 750, "samples_published": 750, "scheduled": true, "stance_cells": 10, "stance_unscored": 0, "status": "ok", "unexplained": false, "unusable_samples": 0, "week_id": "2026-W37"}
{"evidence": [], "model_id": "gpt-5.5", "prompts_measured": 30, "prompts_total": 30, "provider": "openai", "reasons": [], "rejected_samples": 4, "run_log_entry": true, "samples_expected": 600, "samples_logged": 596, "samples_published": 596, "scheduled": true, "stance_cells": 10, "stance_unscored": 0, "status": "ok", "unexplained": false, "unusable_samples": 0, "week_id": "2026-W37"}
{"evidence": [], "model_id": "llama3.2:3b", "prompts_measured": 30, "prompts_total": 30, "provider": "ollama", "reasons": [], "rejected_samples": 0, "run_log_entry": true, "samples_expected": 750, "samples_logged": 750, "samples_published": 750, "scheduled": true, "stance_cells": 10, "stance_unscored": 0, "status": "ok", "unexplained": false, "unusable_samples": 0, "week_id": "2026-W36"}
{"evidence": ["issue #36"], "model_id": "claude-opus-4-8", "prompts_measured": 2, "prompts_total": 30, "provider": "anthropic", "reasons": ["Prepaid Anthropic API credit ran out within two minutes of the start. claude-opus-4-8 has 32 of 600 samples, over 2 of 30 prompts; the two Opus models together have 45 of 1200 and 59 pairs failed. Its drift comparisons are against 2026-W34."], "rejected_samples": 0, "run_log_entry": true, "samples_expected": 600, "samples_logged": 32, "samples_published": 32, "scheduled": true, "stance_cells": 2, "stance_unscored": 0, "status": "partial", "unexplained": false, "unusable_samples": 0, "week_id": "2026-W36"}
{"evidence": ["issue #36"], "model_id": "claude-opus-5", "prompts_measured": 1, "prompts_total": 30, "provider": "anthropic", "reasons": ["Prepaid Anthropic API credit ran out within two minutes of the start. claude-opus-5 has 13 of 600 samples, on 1 of 30 prompts; the two Opus models together have 45 of 1200 and 59 pairs failed. Its drift comparison is against 2026-W34."], "rejected_samples": 0, "run_log_entry": true, "samples_expected": 600, "samples_logged": 13, "samples_published": 13, "scheduled": true, "stance_cells": 1, "stance_unscored": 0, "status": "partial", "unexplained": false, "unusable_samples": 0, "week_id": "2026-W36"}
{"evidence": ["data/manifests/2026-W35.json history"], "model_id": "llama3.2:3b", "prompts_measured": 30, "prompts_total": 30, "provider": "ollama", "reasons": ["Drift for all 30 llama3.2:3b cells was computed against 2026-W34, whose metrics this week's manifest carried in its history (and so were served under /data/2026-W34/) although 2026-W34 was not then published as a week of its own. It is now published as a partial week."], "rejected_samples": 0, "run_log_entry": true, "samples_expected": 750, "samples_logged": 750, "samples_published": 750, "scheduled": true, "stance_cells": 10, "stance_unscored": 0, "status": "ok", "unexplained": false, "unusable_samples": 0, "week_id": "2026-W35"}
{"evidence": [], "model_id": "gpt-5.5", "prompts_measured": 30, "prompts_total": 30, "provider": "openai", "reasons": [], "rejected_samples": 17, "run_log_entry": true, "samples_expected": 600, "samples_logged": 583, "samples_published": 583, "scheduled": true, "stance_cells": 10, "stance_unscored": 0, "status": "ok", "unexplained": false, "unusable_samples": 0, "week_id": "2026-W35"}
{"evidence": [], "model_id": "llama3.2:3b", "prompts_measured": 30, "prompts_total": 30, "provider": "ollama", "reasons": [], "rejected_samples": 0, "run_log_entry": true, "samples_expected": 750, "samples_logged": 750, "samples_published": 750, "scheduled": true, "stance_cells": 10, "stance_unscored": 0, "status": "ok", "unexplained": false, "unusable_samples": 0, "week_id": "2026-W34"}
{"evidence": [], "model_id": "claude-opus-4-8", "prompts_measured": 30, "prompts_total": 30, "provider": "anthropic", "reasons": [], "rejected_samples": 0, "run_log_entry": true, "samples_expected": 600, "samples_logged": 600, "samples_published": 600, "scheduled": true, "stance_cells": 10, "stance_unscored": 0, "status": "ok", "unexplained": false, "unusable_samples": 0, "week_id": "2026-W34"}
{"evidence": ["issue #32", "issue #34", "commit 8291b6c"], "model_id": "claude-opus-5", "prompts_measured": 13, "prompts_total": 30, "provider": "anthropic", "reasons": ["Sampled on 2026-08-24 and killed at the one-hour SSM execution timeout. claude-opus-5 has 259 of 600 samples, over 13 of 30 prompts. claude-opus-4-8 (600 samples) and llama3.2:3b (750 samples) completed. The raw samples were archived on 2026-10-05 and the week is published as a partial week."], "rejected_samples": 0, "run_log_entry": true, "samples_expected": 600, "samples_logged": 259, "samples_published": 259, "scheduled": true, "stance_cells": 10, "stance_unscored": 0, "status": "partial", "unexplained": false, "unusable_samples": 0, "week_id": "2026-W34"}
{"evidence": [], "model_id": "llama3.2:3b", "prompts_measured": 30, "prompts_total": 30, "provider": "ollama", "reasons": [], "rejected_samples": 0, "run_log_entry": true, "samples_expected": 750, "samples_logged": 750, "samples_published": 750, "scheduled": true, "stance_cells": 10, "stance_unscored": 0, "status": "ok", "unexplained": false, "unusable_samples": 0, "week_id": "2026-W33"}
{"evidence": ["run_log 2026-08-17T16:04:33+00:00", "data/manifests/2026-W33.json"], "model_id": "gpt-5.5", "prompts_measured": 30, "prompts_total": 30, "provider": "openai", "reasons": ["One pair failed: ref-wifi-unauthorized has 2 of 20 samples, after the provider rejected the rest with HTTP 400 (\"flagged for possible cybersecurity risk\"). This was before declined requests were counted as rejected_samples, so the published cell carries none. gpt-5.5 has 582 of 600 samples; every prompt was measured."], "rejected_samples": 0, "run_log_entry": true, "samples_expected": 600, "samples_logged": 582, "samples_published": 582, "scheduled": true, "stance_cells": 10, "stance_unscored": 0, "status": "degraded", "unexplained": false, "unusable_samples": 0, "week_id": "2026-W33"}
{"evidence": [], "model_id": "llama3.2:3b", "prompts_measured": 30, "prompts_total": 30, "provider": "ollama", "reasons": [], "rejected_samples": 0, "run_log_entry": true, "samples_expected": 750, "samples_logged": 750, "samples_published": 750, "scheduled": true, "stance_cells": 10, "stance_unscored": 0, "status": "ok", "unexplained": false, "unusable_samples": 0, "week_id": "2026-W32"}
{"evidence": [], "model_id": "claude-opus-4-8", "prompts_measured": 30, "prompts_total": 30, "provider": "anthropic", "reasons": [], "rejected_samples": 0, "run_log_entry": true, "samples_expected": 600, "samples_logged": 600, "samples_published": 600, "scheduled": true, "stance_cells": 10, "stance_unscored": 0, "status": "ok", "unexplained": false, "unusable_samples": 0, "week_id": "2026-W32"}
{"evidence": ["issue #26", "commit f352103", "commit 8b30b78"], "model_id": "llama3.2:3b", "prompts_measured": 0, "prompts_total": 30, "provider": "ollama", "reasons": ["The run never started: EC2 InsufficientInstanceCapacity again, the week after 2026-W30."], "rejected_samples": 0, "run_log_entry": false, "samples_expected": 750, "samples_logged": null, "samples_published": 0, "scheduled": true, "stance_cells": null, "stance_unscored": null, "status": "lost", "unexplained": false, "unusable_samples": 0, "week_id": "2026-W31"}
{"evidence": ["issue #26", "commit f352103", "commit 8b30b78"], "model_id": "gpt-5.5", "prompts_measured": 0, "prompts_total": 30, "provider": "openai", "reasons": ["The run never started: EC2 InsufficientInstanceCapacity again, the week after 2026-W30."], "rejected_samples": 0, "run_log_entry": false, "samples_expected": 600, "samples_logged": null, "samples_published": 0, "scheduled": true, "stance_cells": null, "stance_unscored": null, "status": "lost", "unexplained": false, "unusable_samples": 0, "week_id": "2026-W31"}
{"evidence": ["issue #24", "commit f352103", "commit 8b30b78"], "model_id": "llama3.2:3b", "prompts_measured": 0, "prompts_total": 30, "provider": "ollama", "reasons": ["The run never started: the sampling instance could not be launched (EC2 InsufficientInstanceCapacity), and the orchestrator failed before reaching any alert."], "rejected_samples": 0, "run_log_entry": false, "samples_expected": 750, "samples_logged": null, "samples_published": 0, "scheduled": true, "stance_cells": null, "stance_unscored": null, "status": "lost", "unexplained": false, "unusable_samples": 0, "week_id": "2026-W30"}
{"evidence": ["issue #24", "commit f352103", "commit 8b30b78"], "model_id": "claude-opus-4-8", "prompts_measured": 0, "prompts_total": 30, "provider": "anthropic", "reasons": ["The run never started: the sampling instance could not be launched (EC2 InsufficientInstanceCapacity), and the orchestrator failed before reaching any alert."], "rejected_samples": 0, "run_log_entry": false, "samples_expected": 600, "samples_logged": null, "samples_published": 0, "scheduled": true, "stance_cells": null, "stance_unscored": null, "status": "lost", "unexplained": false, "unusable_samples": 0, "week_id": "2026-W30"}
{"evidence": [], "model_id": "llama3.2:3b", "prompts_measured": 30, "prompts_total": 30, "provider": "ollama", "reasons": [], "rejected_samples": 0, "run_log_entry": true, "samples_expected": 750, "samples_logged": 750, "samples_published": 750, "scheduled": true, "stance_cells": 10, "stance_unscored": 0, "status": "ok", "unexplained": false, "unusable_samples": 0, "week_id": "2026-W29"}
{"evidence": ["/reports/2026-07-24-truncated-response-correction/", "commit de2ec54"], "model_id": "gpt-5.5", "prompts_measured": 29, "prompts_total": 30, "provider": "openai", "reasons": ["43 of 600 samples were empty, truncated at the token limit, and sci-iq-heritability was not measured at all. The empty samples were removed from every metric in the 2026-07-24 correction."], "rejected_samples": 0, "run_log_entry": true, "samples_expected": 600, "samples_logged": 600, "samples_published": 557, "scheduled": true, "stance_cells": 10, "stance_unscored": 0, "status": "degraded", "unexplained": false, "unusable_samples": 23, "week_id": "2026-W29"}
{"evidence": [], "model_id": "llama3.2:3b", "prompts_measured": 30, "prompts_total": 30, "provider": "ollama", "reasons": [], "rejected_samples": 0, "run_log_entry": true, "samples_expected": 750, "samples_logged": 750, "samples_published": 750, "scheduled": true, "stance_cells": 10, "stance_unscored": 0, "status": "ok", "unexplained": false, "unusable_samples": 0, "week_id": "2026-W28"}
{"evidence": [], "model_id": "claude-opus-4-8", "prompts_measured": 30, "prompts_total": 30, "provider": "anthropic", "reasons": [], "rejected_samples": 0, "run_log_entry": true, "samples_expected": 600, "samples_logged": 600, "samples_published": 600, "scheduled": true, "stance_cells": 10, "stance_unscored": 0, "status": "ok", "unexplained": false, "unusable_samples": 0, "week_id": "2026-W28"}
{"evidence": [], "model_id": "llama3.2:3b", "prompts_measured": 30, "prompts_total": 30, "provider": "ollama", "reasons": [], "rejected_samples": 0, "run_log_entry": true, "samples_expected": 750, "samples_logged": 750, "samples_published": 750, "scheduled": true, "stance_cells": 10, "stance_unscored": 0, "status": "ok", "unexplained": false, "unusable_samples": 0, "week_id": "2026-W27"}
{"evidence": ["/reports/2026-07-24-truncated-response-correction/", "commit de2ec54"], "model_id": "gpt-5.5", "prompts_measured": 29, "prompts_total": 30, "provider": "openai", "reasons": ["30 temperature-0 pairs failed with HTTP 400. 47 of 600 samples were empty, truncated at the token limit, and sci-iq-heritability was not measured at all. The empty samples were removed from every metric in the 2026-07-24 correction."], "rejected_samples": 0, "run_log_entry": true, "samples_expected": 600, "samples_logged": 600, "samples_published": 553, "scheduled": true, "stance_cells": 10, "stance_unscored": 0, "status": "degraded", "unexplained": false, "unusable_samples": 27, "week_id": "2026-W27"}
{"evidence": [], "model_id": "llama3.2:3b", "prompts_measured": 30, "prompts_total": 30, "provider": "ollama", "reasons": [], "rejected_samples": 0, "run_log_entry": true, "samples_expected": 750, "samples_logged": 750, "samples_published": 750, "scheduled": true, "stance_cells": 10, "stance_unscored": 0, "status": "ok", "unexplained": false, "unusable_samples": 0, "week_id": "2026-W26"}
{"evidence": [], "model_id": "claude-opus-4-7", "prompts_measured": 30, "prompts_total": 30, "provider": "anthropic", "reasons": [], "rejected_samples": 0, "run_log_entry": true, "samples_expected": 600, "samples_logged": 600, "samples_published": 600, "scheduled": true, "stance_cells": 10, "stance_unscored": 0, "status": "ok", "unexplained": false, "unusable_samples": 0, "week_id": "2026-W26"}
{"evidence": [], "model_id": "llama3.2:3b", "prompts_measured": 30, "prompts_total": 30, "provider": "ollama", "reasons": [], "rejected_samples": 0, "run_log_entry": true, "samples_expected": 750, "samples_logged": 750, "samples_published": 750, "scheduled": true, "stance_cells": 10, "stance_unscored": 0, "status": "ok", "unexplained": false, "unusable_samples": 0, "week_id": "2026-W25"}
{"evidence": [], "model_id": "gpt-5.1", "prompts_measured": 30, "prompts_total": 30, "provider": "openai", "reasons": [], "rejected_samples": 0, "run_log_entry": true, "samples_expected": 750, "samples_logged": 750, "samples_published": 750, "scheduled": true, "stance_cells": 10, "stance_unscored": 0, "status": "ok", "unexplained": false, "unusable_samples": 0, "week_id": "2026-W25"}
{"evidence": [], "model_id": "llama3.2:3b", "prompts_measured": 30, "prompts_total": 30, "provider": "ollama", "reasons": [], "rejected_samples": 0, "run_log_entry": true, "samples_expected": 750, "samples_logged": 750, "samples_published": 750, "scheduled": true, "stance_cells": 10, "stance_unscored": 0, "status": "ok", "unexplained": false, "unusable_samples": 0, "week_id": "2026-W24"}
{"evidence": [], "model_id": "claude-opus-4-7", "prompts_measured": 30, "prompts_total": 30, "provider": "anthropic", "reasons": [], "rejected_samples": 0, "run_log_entry": true, "samples_expected": 600, "samples_logged": 600, "samples_published": 600, "scheduled": true, "stance_cells": 10, "stance_unscored": 0, "status": "ok", "unexplained": false, "unusable_samples": 0, "week_id": "2026-W24"}
{"evidence": [], "model_id": "llama3.2:3b", "prompts_measured": 30, "prompts_total": 30, "provider": "ollama", "reasons": [], "rejected_samples": 0, "run_log_entry": true, "samples_expected": 750, "samples_logged": 750, "samples_published": 750, "scheduled": true, "stance_cells": 10, "stance_unscored": 0, "status": "ok", "unexplained": false, "unusable_samples": 0, "week_id": "2026-W23"}
{"evidence": [], "model_id": "gpt-5.1", "prompts_measured": 30, "prompts_total": 30, "provider": "openai", "reasons": [], "rejected_samples": 0, "run_log_entry": true, "samples_expected": 750, "samples_logged": 750, "samples_published": 750, "scheduled": true, "stance_cells": 10, "stance_unscored": 0, "status": "ok", "unexplained": false, "unusable_samples": 0, "week_id": "2026-W23"}
{"evidence": [], "model_id": "llama3.2:3b", "prompts_measured": 30, "prompts_total": 30, "provider": "ollama", "reasons": [], "rejected_samples": 0, "run_log_entry": true, "samples_expected": 750, "samples_logged": 750, "samples_published": 750, "scheduled": true, "stance_cells": 10, "stance_unscored": 0, "status": "ok", "unexplained": false, "unusable_samples": 0, "week_id": "2026-W22"}
{"evidence": [], "model_id": "claude-opus-4-7", "prompts_measured": 30, "prompts_total": 30, "provider": "anthropic", "reasons": [], "rejected_samples": 0, "run_log_entry": true, "samples_expected": 600, "samples_logged": 600, "samples_published": 600, "scheduled": true, "stance_cells": 10, "stance_unscored": 0, "status": "ok", "unexplained": false, "unusable_samples": 0, "week_id": "2026-W22"}
{"evidence": [], "model_id": "llama3.2:3b", "prompts_measured": 30, "prompts_total": 30, "provider": "ollama", "reasons": [], "rejected_samples": 0, "run_log_entry": true, "samples_expected": 750, "samples_logged": 750, "samples_published": 750, "scheduled": true, "stance_cells": 10, "stance_unscored": 0, "status": "ok", "unexplained": false, "unusable_samples": 0, "week_id": "2026-W21"}
{"evidence": [], "model_id": "gpt-5.1", "prompts_measured": 30, "prompts_total": 30, "provider": "openai", "reasons": [], "rejected_samples": 0, "run_log_entry": true, "samples_expected": 750, "samples_logged": 750, "samples_published": 750, "scheduled": true, "stance_cells": 10, "stance_unscored": 0, "status": "ok", "unexplained": false, "unusable_samples": 0, "week_id": "2026-W21"}
{"evidence": [], "model_id": "llama3.2:3b", "prompts_measured": 30, "prompts_total": 30, "provider": "ollama", "reasons": [], "rejected_samples": 0, "run_log_entry": true, "samples_expected": 750, "samples_logged": 750, "samples_published": 750, "scheduled": true, "stance_cells": 10, "stance_unscored": 0, "status": "ok", "unexplained": false, "unusable_samples": 0, "week_id": "2026-W20"}
{"evidence": [], "model_id": "claude-opus-4-7", "prompts_measured": 30, "prompts_total": 30, "provider": "anthropic", "reasons": [], "rejected_samples": 0, "run_log_entry": true, "samples_expected": 600, "samples_logged": 600, "samples_published": 600, "scheduled": true, "stance_cells": 10, "stance_unscored": 0, "status": "ok", "unexplained": false, "unusable_samples": 0, "week_id": "2026-W20"}
{"evidence": [], "model_id": "llama3.2:3b", "prompts_measured": 30, "prompts_total": 30, "provider": "ollama", "reasons": [], "rejected_samples": 0, "run_log_entry": true, "samples_expected": 750, "samples_logged": 750, "samples_published": 750, "scheduled": true, "stance_cells": 10, "stance_unscored": 0, "status": "ok", "unexplained": false, "unusable_samples": 0, "week_id": "2026-W19"}
{"evidence": [], "model_id": "gpt-5.1", "prompts_measured": 30, "prompts_total": 30, "provider": "openai", "reasons": [], "rejected_samples": 0, "run_log_entry": true, "samples_expected": 750, "samples_logged": 0, "samples_published": 750, "scheduled": true, "stance_cells": 10, "stance_unscored": 0, "status": "ok", "unexplained": false, "unusable_samples": 0, "week_id": "2026-W19"}
{"evidence": ["run_log 2026-04-25T03:43:33+00:00", "commit f6489cd"], "model_id": "llama3.2:3b", "prompts_measured": 0, "prompts_total": 30, "provider": "ollama", "reasons": ["No llama3.2:3b samples in the published W18 record. A workstation run labelled W18 wrote 750 samples on 2026-04-25, which falls in ISO week 2026-W17, so they were not captured in W18 and were not published."], "rejected_samples": 0, "run_log_entry": true, "samples_expected": 750, "samples_logged": 750, "samples_published": 0, "scheduled": true, "stance_cells": null, "stance_unscored": null, "status": "lost", "unexplained": false, "unusable_samples": 0, "week_id": "2026-W18"}
{"evidence": ["run_log 2026-04-24T22:39:32+00:00", "run_log 2026-05-03T01:40:54+00:00", "commit f6489cd"], "model_id": "claude-opus-4-7", "prompts_measured": 30, "prompts_total": 30, "provider": "anthropic", "reasons": ["Two runs carry the W18 label. The first, on 2026-04-24 (600 samples, captured in ISO week 2026-W17), was not published. The published W18 data is the second run, captured 2026-05-03 (600 samples)."], "rejected_samples": 0, "run_log_entry": true, "samples_expected": 600, "samples_logged": 1200, "samples_published": 600, "scheduled": true, "stance_cells": 10, "stance_unscored": 0, "status": "ok", "unexplained": false, "unusable_samples": 0, "week_id": "2026-W18"}
{"evidence": ["run_log 2026-04-24T05:49:07+00:00", "commit 488ac4e"], "model_id": "llama3.2:3b", "prompts_measured": 0, "prompts_total": 30, "provider": "ollama", "reasons": ["No llama3.2:3b samples. The W17 run ran on a hosted CI runner with no ollama installed, so only openai/gpt-5.1 was sampled (750 samples). The failure left no error in the run log and was caught on review the following week."], "rejected_samples": 0, "run_log_entry": true, "samples_expected": 750, "samples_logged": 0, "samples_published": 0, "scheduled": true, "stance_cells": null, "stance_unscored": null, "status": "lost", "unexplained": false, "unusable_samples": 0, "week_id": "2026-W17"}
{"evidence": [], "model_id": "gpt-5.1", "prompts_measured": 30, "prompts_total": 30, "provider": "openai", "reasons": [], "rejected_samples": 0, "run_log_entry": true, "samples_expected": 750, "samples_logged": 750, "samples_published": 750, "scheduled": true, "stance_cells": 10, "stance_unscored": 0, "status": "ok", "unexplained": false, "unusable_samples": 0, "week_id": "2026-W17"}