{"id":"W3088768572","doi":"10.4204/eptcs.327.7","title":"Proceedings of the Sixteenth International Workshop on the ACL2 Theorem Prover and its Applications","year":2020,"lang":"en","type":"article","venue":"Electronic Proceedings in Theoretical Computer Science","topic":"Formal Methods in Verification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Automated theorem proving; Calculus (dental); Programming language; Computer science; Gas meter prover; Software engineering; Mathematics; Mathematical proof; Medicine","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":[0.002059421,0.0001845092,0.0001596266,0.000106365,0.0002920043,0.0003534778,0.004475684,0.00006215717,0.00000849812],"category_scores_gemma":[0.0008637128,0.0001100423,0.00005100949,0.002198639,0.001372657,0.0008055228,0.001320143,0.0005892872,0.000006596346],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001364524,"about_ca_system_score_gemma":0.0001346927,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":2.23121e-7,"about_ca_topic_score_gemma":6.478278e-8,"domain_scores_codex":[0.9975826,0.00002188127,0.0003423196,0.0007210977,0.0008136033,0.0005184605],"domain_scores_gemma":[0.9988904,0.0002274214,0.0002093993,0.0002136262,0.000350121,0.0001090334],"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":[0.00001625623,0.00003806179,0.0000979809,0.00001369806,0.000004235269,5.714997e-8,0.001040837,0.00001050351,0.003706605,0.9839928,0.00003660706,0.01104243],"study_design_scores_gemma":[0.0002129027,0.0001964617,0.000974738,0.00008104769,0.000005267329,0.00001569156,0.00007612933,0.6464033,0.06916091,0.281765,0.0009029299,0.0002057284],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2631764,0.000166615,0.6460003,0.05946266,0.0004939971,0.003066777,0.000002933018,0.0002921571,0.02733808],"genre_scores_gemma":[0.9773964,0.00002620444,0.02080215,0.001532099,0.0001186235,0.0001072728,9.149648e-8,0.000009044429,0.000008121692],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7142199,"threshold_uncertainty_score":0.8317009,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0128813813626887,"score_gpt":0.2568102535012909,"score_spread":0.2439288721386022,"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."}}