{"id":"W3097577547","doi":"10.1109/modre51215.2020.00009","title":"ALDB: Debugging Alloy Models of Behavioural Requirements","year":2020,"lang":"en","type":"article","venue":"","topic":"Model-Driven Software Engineering Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Debugger; Debugging; Computer science; Programming language; Model checking; Constraint (computer-aided design); Transition system; User interface; Software engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.002785033,0.001225616,0.0005299586,0.001215231,0.0004465475,0.001372166,0.001843069,0.001298273,0.006266929],"category_scores_gemma":[0.01067993,0.0009765299,0.0007929323,0.0005178064,0.0006689079,0.002566919,0.001836457,0.001487565,0.001332771],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006452368,"about_ca_system_score_gemma":0.001094976,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002931386,"about_ca_topic_score_gemma":0.004060863,"domain_scores_codex":[0.9977568,0.000935702,0.0001594058,0.0002378317,0.0008017371,0.0001085679],"domain_scores_gemma":[0.9961544,0.002186985,0.0002760105,0.0007751759,0.0004899512,0.0001175556],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001736824,0.0004889418,0.01152778,0.001798885,0.0002387288,0.001764552,0.003324495,0.3380459,0.08656853,0.1901028,0.04561509,0.3187875],"study_design_scores_gemma":[0.0001975932,0.0001836821,0.0006241075,0.0001281431,0.00004720219,0.0004296413,0.0001734711,0.8784847,0.03965778,0.03596957,0.04404002,0.0000641733],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02170608,0.0001409571,0.9400796,0.0002389016,0.00006856288,0.00009662261,0.0009388851,0.03384594,0.002884417],"genre_scores_gemma":[0.2311483,0.0002542488,0.7579354,0.0002125662,0.00002320008,0.0002370535,0.002443164,0.00383439,0.003911648],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006266929,"threshold_uncertainty_score":0.02096492,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1092132603220452,"score_gpt":0.26354340444075,"score_spread":0.1543301441187049,"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."}}