{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009305758,0.0001079216,0.0001455147,0.00004559023,0.00002137347,0.00002837701,0.0007988318,0.00003947838,0.00001304089],"category_scores_gemma":[0.00000351427,0.0001040452,0.00005579567,0.0001820258,0.00001515015,0.0005684852,0.0003568354,0.00007888831,0.000006129951],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002175666,"about_ca_system_score_gemma":0.00002414524,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004956206,"about_ca_topic_score_gemma":0.000001074477,"domain_scores_codex":[0.999068,0.00001482342,0.0002222751,0.0002538172,0.0002591813,0.0001818946],"domain_scores_gemma":[0.9994238,0.00001108773,0.00005228015,0.0003529954,0.00005811493,0.0001017075],"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":[0.000006929879,0.00008885332,0.003071456,0.0000663146,0.00004911808,0.00003083172,0.002424886,0.02770658,0.0179106,0.8857891,0.005363853,0.05749147],"study_design_scores_gemma":[0.0001123724,0.00006600802,0.0001731347,0.00001829263,0.000004748057,0.000002219535,0.000001108962,0.9756051,0.02147813,0.001622847,0.0007726763,0.0001433989],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005573687,0.00002263371,0.9917805,0.0006565499,0.00004952518,0.0001084611,0.000001240348,0.001367269,0.0004401637],"genre_scores_gemma":[0.5164255,0.000002224602,0.4833243,0.0002055543,0.000006971247,0.000005612093,7.322538e-7,0.000006481025,0.00002256844],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9478985,"threshold_uncertainty_score":0.424284,"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."}}