{"id":"W2610208837","doi":"10.1017/s0960129517000093","title":"Benchmarks for reasoning with syntax trees containing binders and contexts of assumptions","year":2017,"lang":"en","type":"article","venue":"Mathematical Structures in Computer Science","topic":"Logic, programming, and type systems","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; University of Ottawa","funders":"","keywords":"Variety (cybernetics); Computer science; Syntax; Context (archaeology); Programming language; Logical framework; Qualitative reasoning; Artificial intelligence; Management science","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":[0.0008106399,0.0001450572,0.0002933211,0.0001185481,0.0005177766,0.0006928985,0.001404339,0.00004533451,0.000003695186],"category_scores_gemma":[0.0002218993,0.00009899912,0.00003604565,0.0001422883,0.0008919079,0.0005904679,0.0004431924,0.00009514373,4.595635e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002928886,"about_ca_system_score_gemma":0.00007821772,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003809599,"about_ca_topic_score_gemma":0.00005393642,"domain_scores_codex":[0.9985501,0.00002487075,0.000273652,0.0004576094,0.0003480314,0.0003457529],"domain_scores_gemma":[0.9986122,0.0002437422,0.0002510591,0.0006760941,0.0001080798,0.0001088666],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000007889304,0.00002037442,0.008578308,0.00006179349,0.000007773811,0.000006607719,0.001125086,0.00009043149,0.00007231638,0.926264,0.000008115674,0.06375734],"study_design_scores_gemma":[0.001030389,0.0003883388,0.08468232,0.0001449813,0.0000109288,0.0001375541,0.00009017134,0.3932343,0.0007884696,0.5190665,0.00008504698,0.0003410139],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07095097,0.00004623311,0.9276599,0.0001358308,0.0001899731,0.0003227236,7.051085e-7,0.00002749356,0.0006661946],"genre_scores_gemma":[0.790283,9.32782e-7,0.2096356,0.0000262961,0.00002934472,0.00001590182,3.213787e-7,0.00000376673,0.000004799541],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.719332,"threshold_uncertainty_score":0.6681637,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02386510311144906,"score_gpt":0.2888497279891201,"score_spread":0.264984624877671,"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."}}