Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
139 changes: 139 additions & 0 deletions docs/audits/quorum-PMAT-3524-pr3523.json
Original file line number Diff line number Diff line change
@@ -0,0 +1,139 @@
{
"ticket": "PMAT-3524",
"base": "main",
"base_resolved": "origin/main",
"base_note": "local main differs from origin/main by 101 commit(s); judged against origin/main",
"head": "4e0d1c69339e73cde472fe26d5770d91cefe2abd",
"diff_sha256": "a2856fc0604d0912503b77c2e7c5ecd1ba295bb27d41e9c5d03d092144f18ced",
"width": 3,
"executor": "agy",
"prompt_mode": "inline",
"prompt_bytes": 10505,
"author": {
"model": "claude-fable-5-1",
"family": "claude",
"source": "flag"
},
"agreed": true,
"lanes": [
{
"lane": 1,
"status": "SUCCESS",
"verdict": "PASS",
"summary": "The diff perfectly aligns with PMAT-3524. It strictly replaces the `gx10.json` and `lambda.json` files with the new model ladder receipts generated at `a6f54e84c`. Exactly 8 rungs are present in both files, all have `present: true`, `sha_ok: true`, and the measured `sha256` field added. Furthermore, the receipts correctly reflect the red-by-construction state on main for Qwen3.5 models (with CUDA fallbacks indicated, and 4b/9b/27b exiting with code 101). No other files are touched.",
"findings": [],
"raw_bytes": 2222,
"err_bytes": 0,
"envelope_status": "SUCCESS",
"verdict_source": "structured_output",
"grounding_check": "parity",
"model": "gemini-3.1-pro-high",
"model_measured": "gemini-3.1-pro-high",
"model_source": "measured",
"family": "gemini"
},
{
"lane": 2,
"status": "SUCCESS",
"verdict": "PASS",
"summary": "Diff strictly adheres to PMAT-3524: touches only evidence/dogfood/models/0.68.1/{gx10,lambda}.json to update model ladder receipts for commit a6f54e84c with all 8 rungs present, sha_ok=true, measured sha256 hashes recorded, and Qwen3.5 rungs red-by-construction as expected on main. No gates or forbidden files were modified.",
"findings": [
{
"claim": "gx10.json updated to main a6f54e84c with 8 rungs, sha_ok=true, measured sha256 digests, and red Qwen3.5 rungs",
"file": "evidence/dogfood/models/0.68.1/gx10.json",
"fix": "None needed",
"grounding": "cited",
"line": 5
},
{
"claim": "lambda.json updated to main a6f54e84c with 8 rungs, sha_ok=true, measured sha256 digests, and red Qwen3.5 rungs",
"file": "evidence/dogfood/models/0.68.1/lambda.json",
"fix": "None needed",
"grounding": "cited",
"line": 5
}
],
"raw_bytes": 2855,
"err_bytes": 0,
"envelope_status": "SUCCESS",
"verdict_source": "structured_output",
"grounding_check": "parity",
"model": "gemini-3.8-flash-high",
"model_measured": "gemini-3.8-flash-high",
"model_source": "measured",
"family": "gemini"
},
{
"lane": 3,
"status": "SUCCESS",
"verdict": "PASS",
"summary": "PR touches only evidence/dogfood/models/0.68.1/{gx10,lambda}.json, updating both model ladder receipts to main a6f54e84c with 8 rungs, sha_ok=true, measured sha256 hashes, and red Qwen3.5 rungs as mandated by PMAT-3524. No gates or forbidden files were touched.",
"findings": [
{
"claim": "gx10.json receipt updated for commit a6f54e84c with 8 rungs, sha256 digests, and expected red statuses for Qwen3.5 rungs",
"file": "evidence/dogfood/models/0.68.1/gx10.json",
"fix": "None needed",
"grounding": "cited",
"line": 5
},
{
"claim": "lambda.json receipt updated for commit a6f54e84c with 8 rungs, sha256 digests, and expected red statuses for Qwen3.5 rungs",
"file": "evidence/dogfood/models/0.68.1/lambda.json",
"fix": "None needed",
"grounding": "cited",
"line": 5
}
],
"raw_bytes": 2765,
"err_bytes": 0,
"envelope_status": "SUCCESS",
"verdict_source": "structured_output",
"grounding_check": "parity",
"model": "gemini-3.7-flash-high",
"model_measured": "gemini-3.7-flash-high",
"model_source": "measured",
"family": "gemini"
}
],
"dissent": [],
"dedup": [
{
"file": "evidence/dogfood/models/0.68.1/gx10.json",
"line": 5,
"lanes_agreeing": [
2,
3
],
"claims": [
"gx10.json receipt updated for commit a6f54e84c with 8 rungs, sha256 digests, and expected red statuses for Qwen3.5 rungs",
"gx10.json updated to main a6f54e84c with 8 rungs, sha_ok=true, measured sha256 digests, and red Qwen3.5 rungs"
]
},
{
"file": "evidence/dogfood/models/0.68.1/lambda.json",
"line": 5,
"lanes_agreeing": [
2,
3
],
"claims": [
"lambda.json receipt updated for commit a6f54e84c with 8 rungs, sha256 digests, and expected red statuses for Qwen3.5 rungs",
"lambda.json updated to main a6f54e84c with 8 rungs, sha_ok=true, measured sha256 digests, and red Qwen3.5 rungs"
]
}
],
"uncovered": [],
"coverage_source": "lanes",
"partial": false,
"partial_reasons": [],
"auto_merge": {
"checked": true,
"was_armed": false,
"disarmed": false,
"note": "auto-merge not armed"
},
"lint": {
"ok": true,
"output": "receipt complete: kind=artifact lanes=3 author=claude-fable-5-1/claude"
}
}
121 changes: 115 additions & 6 deletions evidence/dogfood/models/0.68.1/gx10.json
Original file line number Diff line number Diff line change
Expand Up @@ -2,19 +2,20 @@
"schema": "apr-model-ladder-receipt/v1",
"host": "gx10",
"version": "0.68.1",
"sha": "927587272",
"sha": "a6f54e84c",
"isa": "aarch64",
"gpu": "NVIDIA GB10",
"cc": "12.1",
"date": "2026-09-18T14:36Z",
"apr_version": "apr 0.68.1 (927587272)",
"executed": 4,
"red": 0,
"date": "2026-09-19T09:40Z",
"apr_version": "apr 0.68.1 (a6f54e84c)",
"executed": 8,
"red": 5,
"rungs": [
{
"id": "qwen2-1.5b-q4km",
"present": true,
"sha_ok": true,
"sha256": "6a1a2eb6d15622bf3c96857206351ba97e1af16c30d7a74ee38970e434e9407e",
"required": true,
"qa_rc": 0,
"capability_match": {
Expand Down Expand Up @@ -45,6 +46,7 @@
"id": "qwen3-1.7b-q4km",
"present": true,
"sha_ok": true,
"sha256": "b139949c5bd74937ad8ed8c8cf3d9ffb1e99c866c823204dc42c0d91fa181897",
"required": true,
"qa_rc": 0,
"capability_match": {
Expand Down Expand Up @@ -75,6 +77,7 @@
"id": "qwen3-8b-q4km",
"present": true,
"sha_ok": true,
"sha256": "d98cdcbd03e17ce47681435b5150e34c1417f50b5c0019dd560e4882c5745785",
"required": false,
"qa_rc": 0,
"capability_match": {
Expand Down Expand Up @@ -105,6 +108,7 @@
"id": "qwen35-0.8b-q4km",
"present": true,
"sha_ok": true,
"sha256": "bd258782e35f7f458f8aced1adc053e6e92e89bc735ba3be89d38a06121dc517",
"required": true,
"qa_rc": 0,
"capability_match": {
Expand All @@ -122,9 +126,114 @@
"ran": true,
"fallback": false,
"rc": 0
},
"cuda": {
"ran": true,
"fallback": true,
"rc": 0
}
},
"green": true
"green": false
},
{
"id": "qwen35-2b-q4km",
"present": true,
"sha_ok": true,
"sha256": "aaf42c8b7c3cab2bf3d69c355048d4a0ee9973d48f16c731c0520ee914699223",
"required": true,
"qa_rc": 5,
"capability_match": {
"passed": true,
"skipped": false,
"message": "Architecture 'qwen35': CPU-only \u2014 Gated DeltaNet runs on the CPU (#3091); the GPU backend has no SSM kernels (#3090), GPU gates skipped"
},
"golden_output": {
"passed": false,
"skipped": false,
"message": "golden_output_cpu: Empty output"
},
"backends": {
"cpu": {
"ran": true,
"fallback": false,
"rc": 0
},
"cuda": {
"ran": true,
"fallback": true,
"rc": 0
}
},
"green": false
},
{
"id": "qwen35-4b-q4km",
"present": true,
"sha_ok": true,
"sha256": "00fe7986ff5f6b463e62455821146049db6f9313603938a70800d1fb69ef11a4",
"required": true,
"qa_rc": 101,
"capability_match": null,
"golden_output": null,
"backends": {
"cpu": {
"ran": false,
"fallback": false,
"rc": 101
},
"cuda": {
"ran": false,
"fallback": true,
"rc": 101
}
},
"green": false
},
{
"id": "qwen35-9b-q4km",
"present": true,
"sha_ok": true,
"sha256": "03b74727a860a56338e042c4420bb3f04b2fec5734175f4cb9fa853daf52b7e8",
"required": true,
"qa_rc": 101,
"capability_match": null,
"golden_output": null,
"backends": {
"cpu": {
"ran": false,
"fallback": false,
"rc": 101
},
"cuda": {
"ran": false,
"fallback": true,
"rc": 101
}
},
"green": false
},
{
"id": "qwen35-27b-q4km",
"present": true,
"sha_ok": true,
"sha256": "84b5f7f112156d63836a01a69dc3f11a6ba63b10a23b8ca7a7efaf52d5a2d806",
"required": true,
"qa_rc": 101,
"capability_match": null,
"golden_output": null,
"backends": {
"cpu": {
"ran": false,
"fallback": false,
"rc": 101
},
"cuda": {
"ran": false,
"fallback": true,
"rc": 101
}
},
"green": false
}
]
}
Loading
Loading