{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0002717627,0.0003140956,0.0003811934,0.0004240242,0.00002602741,0.00004503476,0.0002931415,0.0002262472,0.0009721885],"category_scores_gemma":[0.001164351,0.0002964663,0.00004481283,0.000640122,0.00007983833,0.0000225249,0.0001276459,0.0002845738,0.003159553],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002280977,"about_ca_system_score_gemma":0.0003438601,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009784824,"about_ca_topic_score_gemma":0.001213956,"domain_scores_codex":[0.9986449,0.0001271311,0.0002301415,0.0004394046,0.0001994613,0.000358985],"domain_scores_gemma":[0.9991284,0.0001859762,0.0001520504,0.0004484234,0.00004441749,0.00004076011],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002734194,0.0004286401,0.02411266,0.002274179,0.0002224445,0.0001875422,0.0007863746,0.0001631771,0.0001764416,0.243346,0.723471,0.00480422],"study_design_scores_gemma":[0.0004832287,0.00002533887,0.001515933,0.00111447,0.00009671003,0.000006508056,0.00001779913,0.0007675186,0.00001254752,0.02266216,0.9726832,0.000614579],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.0001776873,0.0007620802,0.00002167081,0.00002209089,0.0002755646,0.0006091828,0.0001877077,0.001201419,0.9967426],"genre_scores_gemma":[0.002193454,0.000007594273,0.01745739,0.00006084063,0.0006647227,0.0001408647,0.00005552677,0.001069538,0.97835],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.2492122,"threshold_uncertainty_score":0.9999487,"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."}}