Step 20: tool results

{
  "context": "Noise injection is a baseline in a paper advancing a different elicitation method. The comparison table gives 0 to 3 percent of the hidden capability recovered by noise on each of eleven fine-tuned password locks, as single integers with no spread. Nowhere in the paper, appendix included, is the noise protocol described: where the noise was applied, over what range, with how many seeds, or whether the figure is a best or a mean. The denial is of the effect in fine-tuned password locks, not in prompted sandbagging.",
  "claim_id": "e0abe646-c78f-417c-813f-b8e2c15d775c",
  "reasoning": "The earlier context said 'the sections read do not describe the noise protocol'. The whole TeX source (main.tex, all 59,815 characters, including the Datasets and Hyperparameters appendix) has now been read and contains no description of the noise baseline at all, so the context is corrected from a limit of the reading to a fact about the paper.",
  "confidence": 0.55,
  "instance_id": "5a778012-43f9-4f4f-899e-49d2149eb122"
}

{
  "note": "The paper reports that noise recovered 0 to 3 percent of the locked capability on each of eleven password-locked models but never says how the noise was applied, over what range, with how many seeds, or by what statistic. The locks sit well below chance on a four-option test scored by forced choice, so a model scrambled by heavy noise would recover several percent to over twenty percent of the gap by answering at random. The reported figures are lower than that on ten of the eleven models, which indicates the baseline was not the original method's best score over a sweep running to collapse. The result shows that noise at the settings tried did nothing, not that a full sweep finds nothing. The authors say code and per-model outputs are released; no one else is known to have examined them.",
  "support": "evidence_not_shown",
  "deployment": "Noise injection appears as a failing baseline column beside the paper's own activation-grafting method, to show the new method beats an existing one.",
  "instance_id": "5a778012-43f9-4f4f-899e-49d2149eb122",
  "source_kind": "preprint",
  "source_read": true,
  "worth_reading": false
}

{
  "party": "Le, Tan and Williams-King (Lida Safety)",
  "scope": "claim",
  "stake": "The paper introduces reference-grafting and presents noise injection as a competing elicitation method that it beats. A weak showing by the noise baseline favors the authors' own method.",
  "claim_id": "e0abe646-c78f-417c-813f-b8e2c15d775c",
  "source_id": "ac0b51d9-e596-4989-a8cf-bfc47909eb9f"
}