The JI-v1.2 fix was tested against the same three models that had just produced 0 / 15 schema compliance. This time every one of the thirty responses parsed on the first try, with the full seven-key schema and no renamed keys.
chatgpt is absent: it ran a single pilot block. On this day the three models tied on the graded metric (30/30 schema), which is why the index chart ranks them level and this chart shows strictness instead.JI-v1.2 is the whole intervention. The Day-7 pilot had shown that an abstract one-line schema was not a contract: fifteen models each invented their own verdict vocabulary. JI-v1.2 replaced the schema with a literal object to copy, and put the enum values directly against the field names.
Each model saw each of the ten drafts exactly once. The drafts were stratified by failure type rather than taken as the first ten: unmeasured post-state, resolution claimed with no fix described, a tooling policy that hides errors, a crash on degenerate input, measurement validity, nondeterminism, silent netlist corruption, a repair that took 40000 seconds on one endpoint, a misattributed root cause, and a bug closed without reproduction.
Show the Day 8 sweep: the schema given as a literal object to copy, and three models parsing cleanly on all thirty responses.
Day 7's prose schema got zero of fifteen. Giving the object to copy is what changed.
**OUTPUT FORMAT (binding, read first):** your entire response must be exactly one JSON object matching the schema at the end of this brief. The first character of your reply must be `{` and the last must be `}`. No markdown, no headings, no commentary before or after, no code fences, no explanations — the JSON object only.
**Your review, as a single bare JSON object:** {"verdict": one of SOUND | SOUND-WITH-RESERVATIONS | SUSPECT | IMPLAUSIBLE-FOR-THIS-RECORD, "objections": [{"claim_attacked", "objection", "severity", "confidence"}], "mechanism_check", "evidence_check", "attribution_check", "missing_from_story", "most_defensible_part"}
**Hard rules:** attack the NUMBERS, the causal chain, and whether the intervention explains the outcome — not the writing. The pasted record is the WHOLE evidence base: do not browse the web or fetch any page. Do not invent thread content, commits, PRs, participants, or tool behaviour that is not in it. If the record does not settle a question, write “not-determinable-from-this-record” rather than guessing — a field-level escape beats a guessed objection. A claimed resolution with no measured post-state is an EVIDENCE defect, not a mechanism defect; classify it under `evidence_check`. If a claim is sound, say so — inventing objections is as bad as missing real ones. Fewer sharp objections beat a padded list. This review is a PRE-SCREEN for expert review, not a verdict on the underlying bug — flag, don’t convict.
kimi, sonnet, deepseek. Chosen for clean records on the earlier truth-anchored instruments: arithmetic exact on 9 / 9 values, format conformance 4 / 4 on the reference canonicalizer, correct on the citation-anchor and measured browser-behaviour probes. chatgpt ran block 01 as a format pilot and was schema-compliant, but was not extended to the other nine blocks.digest/_verify/flash_d6_harvest.py → d6run/d6harvest.json, staged tally in redteam/TALLY-34.md.digest/wave1-report.mdSOUND on a draft known to be imperfect would be the same miscalibration defect the tally codebook had produced earlier.redteam/TALLY-34.mddigest/wave1-report.md, “What the review debt looks like”| Model | Files | 7-key schema | Objections | Major / minor | SUSPECT | S-W-RES | Bare SOUND |
|---|---|---|---|---|---|---|---|
| deepseek | 10 / 10 | 30 / 30 | 26 | 20 / 6 | 9 | 1 | 0 |
| kimi | 10 / 10 | 30 / 30 | 23 | 16 / 7 | 2 | 8 | 0 |
| sonnet | 10 / 10 | 30 / 30 | 22 | 8 / 14 | 4 | 6 | 0 |
| chatgpt | 1 (pilot) | block 01 only | n/a | n/a | n/a | n/a | 0 |
| Block | Draft under review | deepseek | kimi | sonnet | Reading |
|---|---|---|---|---|---|
| red1-01 | BoomTile/Megaboom: 20k congestion DRCs at 0.24 density | SUSPECT | S-W-RES | S-W-RES | deepseek strictest |
| red1-02 | GPL-0314: getFillerGCell index out of bounds | SUSPECT | SUSPECT | SUSPECT | unanimous |
| red1-03 | RUDY and global-route congestion maps disagree (ICCAD04 risc2) | SUSPECT | SUSPECT | S-W-RES | strong concern |
| red1-04 | GRT DRC cap (10000) hides hotspots and macro overlaps | SUSPECT | S-W-RES | SUSPECT | split |
| red1-05 | repair_timing ODB-1200 with Liberty Q→QN arcs | SUSPECT | S-W-RES | S-W-RES | |
| red1-06 | TritonCTS segfault when Liberty has no max_capacitance | SUSPECT | S-W-RES | SUSPECT | split |
| red1-07 | CTS NDRs on heavily gated clocks (level definition) | SUSPECT | S-W-RES | SUSPECT | split |
| red1-08 | asap7 cva6 hier-synth GRT report references a nonexistent net | SUSPECT | S-W-RES | S-W-RES | |
| red1-09 | STA false hold/setup: ideal top clock mixed with propagated macro clock | S-W-RES | S-W-RES | S-W-RES | unanimous; strongest record |
| red1-10 | GPL regression: too-early non-virtual TD iteration makes design unroutable | SUSPECT | S-W-RES | S-W-RES | deepseek strictest |
SUSPECT, 15 SOUND-WITH-RESERVATIONS. No SOUND, no IMPLAUSIBLE. Zero fatal objections across all thirty reviews. deepseek flagged SUSPECT on nine of ten blocks; kimi and sonnet leaned SOUND-WITH-RESERVATIONS. The models agree on which records are strong and which are thin.deepseeksonnetnot-determinable-from-this-record was available, and every model treated the pasted record as its whole evidence base.SUSPECT and IMPLAUSIBLE-FOR-THIS-RECORD. The second was never used by any of the three models on any of the ten blocks. Every draft carries a known defect by construction, since the set was stratified by failure type, and no model escalated past SUSPECT. The enum is wider than the models’ willingness to convict.SUSPECT from all three models. Block 09, the STA false hold and setup record, is the best evidenced in the set and drew SOUND-WITH-RESERVATIONS from all three. Where the three agree on which records are thin, a human reviewer can start there.SOUND-WITH-RESERVATIONS into SOUND and manufactures a clean verdict. Across all thirty files no model emitted a bare SOUND, so no grader had to collapse a reserved verdict to reach one. deepseek reached SUSPECT on 9 of the 10 blocks.deepseek, kimi and sonnet share training biases we cannot see. Thirty reviews of ten drafts describe how those three read incident drafts. Three models from one generation cannot stand for the web field. The drafts are first-generation mining with no expert review yet, and if that review changes them these verdicts describe the old versions.Web Model Tasks/Day 8/ (30 files, deepseek · kimi · sonnet × red1-01..10)digest/wave1-report.md (the Day-8 report)prompts/J-ISSUE-REDTEAM-V1.md (JI-v1.2)prompts/_paste/redteam/red1-01.paste.md … red1-10.paste.mdprompts/_paste/redteam/MANIFEST-PASTE-RT.sha256digest/_verify/flash_d6_harvest.py → d6run/d6harvest.jsonredteam/TALLY-34.md (staged tally)RUNSHEET-34.md (the 34-draft sheet)