{"id":"W4394987214","doi":"10.4204/eptcs.402.10","title":"CHC-COMP 2023: Competition Report","year":2024,"lang":"en","type":"article","venue":"Electronic Proceedings in Theoretical Computer Science","topic":"Formal Methods in Verification","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Competition (biology); French horn; Class (philosophy); Computer science; Operations research; Engineering; Sociology; Artificial intelligence","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.005416739,0.0002499045,0.0002399771,0.0006299296,0.0002573658,0.001209462,0.002716271,0.0000974635,0.00003336165],"category_scores_gemma":[0.0002684277,0.0002264334,0.00007788172,0.004124702,0.001388677,0.002304049,0.0007605042,0.0007362615,0.0001198254],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006793249,"about_ca_system_score_gemma":0.000528986,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004400724,"about_ca_topic_score_gemma":8.763806e-7,"domain_scores_codex":[0.9959771,0.00004086886,0.0005371296,0.001349232,0.0009511526,0.001144513],"domain_scores_gemma":[0.9988815,0.0001201357,0.0000887315,0.0005022562,0.0002299221,0.000177494],"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":[0.000004425795,0.00003719134,0.00003563533,0.00003193117,0.000003395653,0.00004263132,0.0003344217,0.00002146006,0.001298947,0.9750249,0.00006812618,0.02309697],"study_design_scores_gemma":[0.00007793094,0.0001656563,0.0003061036,0.000100394,0.000002558632,0.0006728234,0.000006225117,0.6161463,0.006054076,0.3745488,0.00169743,0.0002216465],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01976401,0.0002526059,0.9605352,0.001300816,0.001276594,0.0002838933,4.365615e-7,0.0006222476,0.01596425],"genre_scores_gemma":[0.74966,0.00002184563,0.2498852,0.0001752258,0.0001814392,0.00003346464,0.000001002747,0.00001183565,0.0000299846],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.729896,"threshold_uncertainty_score":0.9998274,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007252410397899102,"score_gpt":0.276505250815857,"score_spread":0.2692528404179579,"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."}}