{"id":"W4225474367","doi":"10.1007/978-3-030-99527-0_35","title":"Ultimate GemCutter and the Axes of Generalization","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Formal Methods in Verification","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Generalization; Correctness; Computer science; Counterexample; Spurious relationship; Concurrency; Interpolation (computer graphics); Theoretical computer science; Algorithm; Programming language; Artificial intelligence; Discrete mathematics; Mathematics; Machine learning; Image (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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003936979,0.0005953846,0.0007444357,0.001022256,0.0007898585,0.001743967,0.001676246,0.0009448747,0.003619836],"category_scores_gemma":[0.00526645,0.0006010824,0.001213566,0.0007747437,0.004718067,0.004358981,0.004184868,0.004001142,0.0005566934],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001124199,"about_ca_system_score_gemma":0.00107316,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001204973,"about_ca_topic_score_gemma":0.001329765,"domain_scores_codex":[0.9965129,0.0009098571,0.0001579479,0.0007986351,0.001249549,0.0003710475],"domain_scores_gemma":[0.9960104,0.001562818,0.000149772,0.001498724,0.0006372881,0.0001410211],"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":[0.0002125548,0.00005932715,0.001001656,0.0001107384,0.00002051692,0.0002299637,0.0003795142,0.01646899,0.00854195,0.903881,0.001751271,0.06734245],"study_design_scores_gemma":[0.00003964443,0.0002602477,0.0005454945,0.00008236929,0.00003587093,0.0004096728,0.0001469578,0.1099953,0.02107693,0.8365239,0.03083204,0.00005161027],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09014214,0.0008388463,0.8533604,0.0009677148,0.0002078348,0.0001002933,0.00008822147,0.003157606,0.05113703],"genre_scores_gemma":[0.800504,0.0004802629,0.1845273,0.0007993515,0.000125237,0.00009394383,0.0001712822,0.0005697734,0.01272886],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003936979,"threshold_uncertainty_score":0.02082098,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02093376002383395,"score_gpt":0.2666484394688838,"score_spread":0.2457146794450499,"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."}}