{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00784856,0.0009493922,0.001683896,0.002247369,0.00515234,0.01155629,0.003632828,0.007179047,0.02649532],"category_scores_gemma":[0.03408926,0.001502545,0.00339568,0.003306815,0.008071473,0.0416242,0.006595603,0.01193853,0.004666279],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003296579,"about_ca_system_score_gemma":0.00305816,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004794828,"about_ca_topic_score_gemma":0.005304866,"domain_scores_codex":[0.9942864,0.002207373,0.0004572796,0.00114081,0.001394083,0.0005140881],"domain_scores_gemma":[0.977964,0.01466407,0.0007266674,0.003220926,0.002330223,0.001094067],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001900447,0.0001007618,0.001254839,0.0002578905,0.000042752,0.0002149005,0.0007782043,0.003190117,0.000422534,0.891574,0.04071327,0.06126059],"study_design_scores_gemma":[0.00001799022,0.000008736492,0.0001566147,0.00007546401,0.00001461571,0.0001263889,0.0003421156,0.007275029,0.0002785893,0.9689357,0.02274656,0.00002230816],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09366484,0.0105781,0.6796348,0.102913,0.002905053,0.0002984081,0.003128103,0.002856362,0.1040214],"genre_scores_gemma":[0.4570725,0.006405939,0.4663572,0.00817317,0.004056138,0.0004936807,0.007009943,0.002239445,0.04819203],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02649532,"threshold_uncertainty_score":0.08863562,"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."}}