{"id":"W4409183528","doi":"10.1007/978-981-96-4656-2_5","title":"Testing and Design of Uniform CNF Samplers: A Virtuous Cycle Enabled by Distribution Testing","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Formal Methods in Verification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Distribution (mathematics); Mathematics","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"],"consensus_categories":[],"category_scores_codex":[0.002055714,0.0004071537,0.0004795323,0.000406493,0.0002992765,0.0003292218,0.001915162,0.0002667283,0.000001757208],"category_scores_gemma":[0.002728707,0.0003964005,0.00004465805,0.001346908,0.0006310365,0.0007044735,0.001070916,0.00053868,0.00000196417],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003160847,"about_ca_system_score_gemma":0.0005709635,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000951972,"about_ca_topic_score_gemma":0.00000338883,"domain_scores_codex":[0.9969686,0.0000864192,0.0006505615,0.001133261,0.0006408871,0.0005202224],"domain_scores_gemma":[0.9952293,0.002709793,0.0005261195,0.0009490566,0.0004736698,0.0001120463],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006743448,0.00002267959,0.0001181024,0.0001074704,0.000007922058,0.000007070203,0.000196332,0.03153686,0.002271208,0.01382702,0.00001931723,0.9518793],"study_design_scores_gemma":[0.0001754367,0.0002299746,0.0002121773,0.0006326407,0.00001011044,0.00003679571,2.35661e-7,0.9072746,0.005360645,0.08559161,0.0001047039,0.0003710783],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001106751,0.0002539009,0.9974219,0.00007908159,0.0004815532,0.0005081263,0.00002349728,0.0001503978,0.0009708401],"genre_scores_gemma":[0.02784739,0.0000127279,0.9718248,0.0001657688,0.00006820372,0.00001101793,0.000008111226,0.00001476159,0.00004728272],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9515082,"threshold_uncertainty_score":0.9998488,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0400573742236029,"score_gpt":0.2695620406360729,"score_spread":0.22950466641247,"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."}}