{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01726605,0.001227101,0.001391437,0.004288546,0.002729696,0.007883566,0.00547475,0.002242617,0.005828652],"category_scores_gemma":[0.07822418,0.001141586,0.002103639,0.005394961,0.004311741,0.01651424,0.004869092,0.004221706,0.0009281098],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004441741,"about_ca_system_score_gemma":0.004954651,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005479602,"about_ca_topic_score_gemma":0.005397643,"domain_scores_codex":[0.9791613,0.008815242,0.002743404,0.001474864,0.006590656,0.001214549],"domain_scores_gemma":[0.9413133,0.03940079,0.003403446,0.009371901,0.005362858,0.001147641],"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":[0.0002218693,0.0002434938,0.003115969,0.0007202892,0.0000781902,0.0002013564,0.00160126,0.03609468,0.003403738,0.9033156,0.004290828,0.04671272],"study_design_scores_gemma":[0.000113493,0.0002086061,0.001225027,0.0004767008,0.0001195551,0.0002443933,0.001056963,0.2195698,0.02125206,0.7219604,0.03363506,0.000137891],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05071967,0.0006074677,0.9225407,0.001152599,0.0001484274,0.0003981299,0.001346233,0.006861707,0.01622513],"genre_scores_gemma":[0.35981,0.0005787057,0.6319946,0.0002715603,0.00006999859,0.0005989127,0.002721199,0.001948423,0.002006559],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01726605,"threshold_uncertainty_score":0.09131271,"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."}}