{"id":"W2952268267","doi":"10.48550/arxiv.1810.01375","title":"A Knowledge Hunting Framework for Common Sense Reasoning","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Schema (genetic algorithms); Computer science; Inference; Task (project management); Common sense; Commonsense reasoning; Inference engine; Artificial intelligence; Machine learning; Epistemology; Engineering","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005051398,0.000324799,0.0003966177,0.0002204279,0.000317577,0.0002066742,0.001620379,0.0004738625,0.00001051854],"category_scores_gemma":[0.000189757,0.0004038766,0.0002638431,0.0003936263,0.00008499745,0.000277892,0.003027285,0.0006908475,0.00007346514],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002091069,"about_ca_system_score_gemma":0.0001930628,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001001657,"about_ca_topic_score_gemma":0.00005189514,"domain_scores_codex":[0.9977132,0.0001288986,0.000245008,0.001338881,0.00007108136,0.0005029205],"domain_scores_gemma":[0.9971234,0.0004056003,0.0003104036,0.001749811,0.0002523356,0.0001585185],"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":[0.0000226756,0.00006771139,0.002425205,0.0001910722,0.00008624495,0.00009644994,0.001229607,0.03457417,0.00001010107,0.9580312,0.0002680379,0.002997471],"study_design_scores_gemma":[0.0002036861,0.00002964094,0.0001406142,0.0004122594,0.0000398163,0.00000457769,0.00004950262,0.7778276,0.00008800581,0.2198725,0.0009598104,0.0003719495],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1856893,0.0000734339,0.8089437,0.0000591766,0.001135651,0.0003207633,0.000005883706,0.0003541013,0.003418023],"genre_scores_gemma":[0.8408966,0.00001973056,0.1578889,0.00008616654,0.0004141239,0.00000189842,0.000005811441,0.00002548969,0.0006613205],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7432534,"threshold_uncertainty_score":0.9998413,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1032434531671333,"score_gpt":0.2338531365749794,"score_spread":0.1306096834078461,"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."}}