{"id":"W1551936078","doi":"10.1007/s10817-015-9327-3","title":"The Next 700 Challenge Problems for Reasoning with Higher-Order Abstract Syntax Representations","year":2015,"lang":"en","type":"article","venue":"Journal of Automated Reasoning","topic":"Logic, programming, and type systems","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University; University of Ottawa","funders":"","keywords":"Syntax; Computer science; Variety (cybernetics); Context (archaeology); Automated reasoning; Order (exchange); Reasoning system; Abstract syntax; Programming language; Artificial intelligence; Natural language processing","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":[0.001737898,0.0001853611,0.0002894728,0.0001061146,0.00044061,0.0007614433,0.0007744856,0.00009402956,0.000002799],"category_scores_gemma":[0.0003206534,0.0001063859,0.0001090499,0.0004253547,0.00006977512,0.0009790743,0.00007892673,0.0002871736,0.00000982928],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001042746,"about_ca_system_score_gemma":0.0003563644,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008591863,"about_ca_topic_score_gemma":0.00003067193,"domain_scores_codex":[0.9980955,0.0001024588,0.0005733751,0.0002432051,0.0005639549,0.000421483],"domain_scores_gemma":[0.9971253,0.0003349197,0.0009923795,0.0003902358,0.0009329852,0.0002241776],"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":[0.0005135267,0.0009605933,0.005731069,0.0003893026,0.002165247,0.0008548481,0.02908712,0.03660154,0.001068639,0.7272596,0.03711289,0.1582557],"study_design_scores_gemma":[0.01032442,0.005538289,0.01950684,0.001645938,0.0003853669,0.005966263,0.008779748,0.538832,0.001079282,0.0289054,0.3770705,0.001965989],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05541998,0.01895453,0.8559459,0.01609241,0.007177722,0.002857544,0.000003596307,0.002852927,0.04069534],"genre_scores_gemma":[0.9575792,0.00007427404,0.04146432,0.00003070071,0.0003414001,0.00003148507,0.00000163433,0.00002607684,0.0004509361],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9021592,"threshold_uncertainty_score":0.7342616,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05308342773294895,"score_gpt":0.2990921808630375,"score_spread":0.2460087531300885,"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."}}