{"id":"W6910741973","doi":"10.48660/25050047","title":"Self testing in General Probabilistic Theories","year":2025,"lang":"en","type":"other","venue":"PIRSA","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Perimeter Institute","funders":"","keywords":"Probabilistic logic; Statistical hypothesis testing; Probabilistic relevance model; Test (biology); Bayesian probability","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00388455,0.0007639749,0.0009776489,0.002184029,0.001869005,0.003890042,0.001750327,0.001915806,0.03756998],"category_scores_gemma":[0.02122505,0.0006299336,0.00169759,0.002041738,0.003383801,0.008213317,0.002979793,0.002810115,0.006200951],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002056061,"about_ca_system_score_gemma":0.001490936,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003221633,"about_ca_topic_score_gemma":0.003087866,"domain_scores_codex":[0.9961768,0.001881733,0.000138069,0.0004903625,0.001085811,0.0002272163],"domain_scores_gemma":[0.9863646,0.009571237,0.0003737376,0.002097545,0.001318586,0.0002742861],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00003997974,0.00003292686,0.0004601405,0.00006045558,0.00001696754,0.00004076314,0.00008863161,0.001956841,0.0001198667,0.9593295,0.01492331,0.02293058],"study_design_scores_gemma":[0.00001003355,0.000004214839,0.0001179217,0.00001894365,0.000008216265,0.0000349035,0.00002662616,0.01495547,0.0003241649,0.9760795,0.008412982,0.000007039221],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"other","genre_gemma":"methods","genre_scores_codex":[0.04583262,0.001768064,0.3964529,0.01196419,0.0007568615,0.0001097874,0.001881376,0.003865156,0.537369],"genre_scores_gemma":[0.7731777,0.001151557,0.09103732,0.001621946,0.001189203,0.0001545137,0.003206993,0.002117387,0.1263434],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.03756998,"threshold_uncertainty_score":0.1256841,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01687693288147233,"score_gpt":0.2605379581309396,"score_spread":0.2436610252494673,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}