{"id":"W2953059566","doi":"10.48550/arxiv.1906.05881","title":"Astra Version 1.0: Evaluating Translations from Alloy to SMT-LIB","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Logic, programming, and type systems","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Translation (biology); Set (abstract data type); Representation (politics); Interface (matter); Solver; Programming language; Parallel computing","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003969009,0.0003181201,0.0003627513,0.0002347983,0.0001942591,0.0002264552,0.001879472,0.000322749,0.00008303249],"category_scores_gemma":[0.0000325406,0.0003557617,0.0002529136,0.000511456,0.00003796433,0.0003578194,0.001063845,0.0004618067,0.001173098],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001826206,"about_ca_system_score_gemma":0.0002573034,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009329399,"about_ca_topic_score_gemma":0.000111426,"domain_scores_codex":[0.9976421,0.000219332,0.0002503551,0.001284372,0.0002091546,0.0003946621],"domain_scores_gemma":[0.9978693,0.0001533715,0.0002209126,0.00135261,0.0001808238,0.0002229424],"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":[0.00007537844,0.0002313104,0.01410837,0.0001507934,0.000343368,0.000206455,0.004083633,0.6943743,0.0007944296,0.2727683,0.001461926,0.01140178],"study_design_scores_gemma":[0.001410739,0.0003328263,0.006567729,0.000108905,0.0002060006,0.000003395088,0.0003252025,0.9018712,0.0002446208,0.07521317,0.01248392,0.001232282],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2069328,0.00005601089,0.7856948,0.0001403916,0.001553182,0.0006248245,0.00001685388,0.0003130807,0.004668016],"genre_scores_gemma":[0.9921337,0.00001441738,0.005515131,0.00008659069,0.0001432073,0.000001843064,0.00005911087,0.00002010964,0.002025843],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.785201,"threshold_uncertainty_score":0.9998894,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.121175624579681,"score_gpt":0.2287895984531023,"score_spread":0.1076139738734213,"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."}}