{"id":"W2028045996","doi":"10.1007/s10009-007-0047-9","title":"A framework for counterexample generation and exploration","year":2007,"lang":"en","type":"article","venue":"International Journal on Software Tools for Technology Transfer","topic":"Formal Methods in Verification","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Counterexample; Debugging; Mathematical proof; Computer science; Property (philosophy); Programming language; Theoretical computer science; Model checking; Algorithm; Mathematics; Discrete 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":[0.001021614,0.0001424813,0.000141698,0.0004675232,0.0002060541,0.0003486574,0.0007173965,0.0002596911,0.000005183776],"category_scores_gemma":[0.00116746,0.0001350749,0.0000856541,0.0001772989,0.00006669459,0.001417004,0.00002753549,0.0002767797,0.000004044753],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001279474,"about_ca_system_score_gemma":0.00004198514,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":5.195879e-7,"about_ca_topic_score_gemma":0.0000037536,"domain_scores_codex":[0.9987307,0.00002036754,0.0004174435,0.0002963257,0.0002934184,0.000241784],"domain_scores_gemma":[0.9985827,0.0004306261,0.00009268582,0.0002161177,0.0006202236,0.00005767488],"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":[0.0001005306,0.00004327491,0.0000684621,0.000004318033,0.00004060657,0.000003171865,0.0001528694,0.00004253035,0.001633756,0.6751723,0.0001359626,0.3226022],"study_design_scores_gemma":[0.002613334,0.001694986,0.0008119663,0.0001466813,0.00003392067,0.0004818481,0.0001472233,0.01716223,0.1291459,0.7588444,0.08836135,0.0005562326],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0224307,0.00006265346,0.9708614,0.004186642,0.001778055,0.0004105464,0.00002669921,0.0002301061,0.00001322012],"genre_scores_gemma":[0.1740339,0.0000595839,0.8245085,0.0008824763,0.0003598753,0.0001037478,0.00001843106,0.00001606669,0.00001738263],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.322046,"threshold_uncertainty_score":0.5508193,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1044817341754693,"score_gpt":0.368031216693099,"score_spread":0.2635494825176297,"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."}}