{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007865506,0.001673401,0.00147004,0.007944485,0.00218008,0.005185439,0.006373304,0.002584706,0.009453135],"category_scores_gemma":[0.02251426,0.001202799,0.003726817,0.004300797,0.002952162,0.01187656,0.007523309,0.004761516,0.004277201],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001554082,"about_ca_system_score_gemma":0.002470702,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006227805,"about_ca_topic_score_gemma":0.008700919,"domain_scores_codex":[0.9928715,0.002235641,0.0005998768,0.001958676,0.002059917,0.0002744584],"domain_scores_gemma":[0.9896685,0.005449838,0.0005161946,0.002967983,0.001042773,0.0003547053],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002573195,0.0005178315,0.002788752,0.0009494868,0.0003704045,0.0005923812,0.002984479,0.02362715,0.01221344,0.2536662,0.03934664,0.662686],"study_design_scores_gemma":[0.00005399153,0.00006124604,0.0006222646,0.0001585883,0.00008922846,0.0005158898,0.0004753576,0.4922535,0.009381227,0.4508141,0.04548886,0.00008567198],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002053759,0.0003000417,0.9894288,0.0005498538,0.00005862964,0.000171434,0.0004287729,0.00514943,0.001859338],"genre_scores_gemma":[0.05936823,0.0002352403,0.9355474,0.0003747138,0.0001148485,0.000264194,0.001859874,0.0004351416,0.00180036],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009453135,"threshold_uncertainty_score":0.04159725,"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."}}