{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001902095,0.0002471248,0.0003368936,0.0003832303,0.0002502628,0.0001990676,0.002195576,0.0001084384,0.0000280632],"category_scores_gemma":[0.0001224678,0.0001786524,0.00006787138,0.0004396839,0.001162037,0.000509686,0.001418278,0.0003972945,0.000002615188],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009784062,"about_ca_system_score_gemma":0.0001350078,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002994679,"about_ca_topic_score_gemma":0.000006984335,"domain_scores_codex":[0.9977575,0.0001147291,0.0004333096,0.0007201079,0.0007135984,0.0002607376],"domain_scores_gemma":[0.9980182,0.0003695723,0.0003729464,0.001060512,0.0001341517,0.00004460234],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001220857,0.000008709105,0.00002686336,0.00003831495,0.000008056117,0.000004217844,0.001570405,0.02488478,0.0001490437,0.6174965,0.000009090757,0.3557918],"study_design_scores_gemma":[0.0003181333,0.0000607507,0.0001687055,0.00005559433,0.000007648408,0.00004027013,1.461623e-7,0.8189701,0.001488825,0.1768394,0.001810107,0.0002402666],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00009173863,0.0004640471,0.9953138,0.0008199597,0.001009881,0.0003413769,0.00000355687,0.00004999041,0.00190562],"genre_scores_gemma":[0.02595661,0.0001798452,0.9723434,0.001201375,0.0001295604,0.00001817458,0.0000047631,0.00001869917,0.0001475267],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7940854,"threshold_uncertainty_score":0.7285234,"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."}}