{
 "attribution": "AGmind Systems Lab (agmind.ai)",
 "id": "strix.qwen36.longctx.c1.control-success",
 "headline": "Qwen3.6-35B-A3B Q4_K_M on Ryzen AI Max+ 395 (llama.cpp Vulkan) — unanswerable-control honesty: 100.0 % of requests",
 "answer": "On a Beelink GTR9 Pro — AMD Ryzen AI Max+ 395, Radeon 8060S (gfx1151), 128 GB LPDDR5X-8000 unified running llama.cpp (server, Vulkan backend), b9049 (server_fingerprint b9049-2496f9c14) with ggml-org/Qwen3.6-35B-A3B-GGUF @ baec3ebee244 (Q4_K_M), the measured unanswerable-control honesty was 100.0 % of requests (share of all control requests). The measurement was taken under the frozen long-context-v1@2026-08-03 workload; evidence level lab_unit_replicated, 6 valid runs across 2 physical units. The value is re-derived from the raw run records on every CI build.",
 "value": "100.0",
 "unit": "% of requests",
 "metric": "unanswerable-control honesty",
 "concurrency": 1,
 "system": "Beelink GTR9 Pro — AMD Ryzen AI Max+ 395, Radeon 8060S (gfx1151), 128 GB LPDDR5X-8000 unified",
 "runtime": "llama.cpp (server, Vulkan backend), b9049 (server_fingerprint b9049-2496f9c14)",
 "model": "ggml-org/Qwen3.6-35B-A3B-GGUF @ baec3ebee244 (Q4_K_M)",
 "units_measured": 2,
 "statement": "Share of unanswerable-control requests where the model admitted the answer was absent from the document instead of fabricating one, with a distractor fact present.",
 "scope": "long-context-v1@2026-08-03",
 "aggregation": "share of all control requests",
 "limitations": "Six runs across two commercially identical units; the three 2026-08-05 runs re-measured the same cells under the corrected decline gate (errata 2026-08-05). Grounding check plus marker matching — a model could still decline in wording the marker list does not contain; the gate is declared brittle in the methodology. Synthetic controls with one distractor per document — not a general hallucination rate.",
 "evidence_level": "lab_unit_replicated",
 "status": "active",
 "run_ids": [
  "run-20260803-lc-nothink-a",
  "run-20260803-lc-nothink-a-r2",
  "run-20260803-lc-nothink-a-r3",
  "run-20260805-lc-nothink-b",
  "run-20260805-lc-nothink-b-r2",
  "run-20260805-lc-nothink-b-r3"
 ],
 "runs": [
  "https://github.com/botAGI/agmind-lab/tree/main/runs/run-20260803-lc-nothink-a",
  "https://github.com/botAGI/agmind-lab/tree/main/runs/run-20260803-lc-nothink-a-r2",
  "https://github.com/botAGI/agmind-lab/tree/main/runs/run-20260803-lc-nothink-a-r3",
  "https://github.com/botAGI/agmind-lab/tree/main/runs/run-20260805-lc-nothink-b",
  "https://github.com/botAGI/agmind-lab/tree/main/runs/run-20260805-lc-nothink-b-r2",
  "https://github.com/botAGI/agmind-lab/tree/main/runs/run-20260805-lc-nothink-b-r3"
 ],
 "derivation_sql": "https://github.com/botAGI/agmind-lab/blob/main/catalog/claims/sql/control-success.sql",
 "permalink": "https://agmind.ai/claims/strix.qwen36.longctx.c1.control-success/",
 "json": "https://agmind.ai/claims/strix.qwen36.longctx.c1.control-success.json",
 "markdown": "https://agmind.ai/claims/strix.qwen36.longctx.c1.control-success.md",
 "cite": "AGmind Systems Lab. \"Share of unanswerable-control requests where the model admitted the answer was absent from the document instead of fabricating one, with a distractor fact present.\" Claim strix.qwen36.longctx.c1.control-success (100.0 % of requests), evidence level lab_unit_replicated, scope long-context-v1@2026-08-03. https://agmind.ai/claims/strix.qwen36.longctx.c1.control-success/",
 "license": "https://creativecommons.org/licenses/by/4.0/",
 "corrections": "https://agmind.ai/errata/"
}