{"id":"W6976738005","doi":"10.60692/10q1k-4bd19","title":"Can a Gorilla Ride a Camel? Learning Semantic Plausibility from Text","year":2019,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Usability and User Interface Design","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; McGill University","funders":"","keywords":"Natural language understanding; Language model; Set (abstract data type); Commonsense knowledge; Language understanding; Commonsense reasoning; Natural language; Testbed","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006170648,0.0002155197,0.0003127389,0.0001521723,0.0001389326,0.0005364519,0.0006557168,0.0001252053,0.00005481791],"category_scores_gemma":[0.00004703242,0.000183196,0.0001002394,0.0003000118,0.00002343824,0.001367303,0.0002203344,0.0002187947,0.004934568],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000217566,"about_ca_system_score_gemma":0.00007741374,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003062442,"about_ca_topic_score_gemma":0.000004706663,"domain_scores_codex":[0.9980643,0.0001917863,0.0006478673,0.0003458418,0.0004180352,0.00033215],"domain_scores_gemma":[0.9984114,0.00004150721,0.0002989912,0.0009501404,0.0001788112,0.0001191624],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005331542,0.000005094553,0.7123752,0.0004157194,0.00007209964,0.000004663122,0.2825578,0.002173345,0.00003219102,0.001126898,0.0001148788,0.001068796],"study_design_scores_gemma":[0.002741187,0.0003401987,0.3402567,0.0006542049,0.00004580449,0.00008277221,0.02958778,0.6176374,0.004542878,0.0000947455,0.002763066,0.001253295],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8416541,0.000002045434,0.1548193,0.0001207792,0.0006729929,0.0004022072,0.00003207572,0.0004252423,0.001871233],"genre_scores_gemma":[0.9982539,3.860402e-8,0.001210599,0.0001580274,0.00004357586,0.00002389038,0.00001009586,0.00000717678,0.0002927037],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6154641,"threshold_uncertainty_score":0.9958402,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02524745682790789,"score_gpt":0.202151425145915,"score_spread":0.1769039683180071,"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."}}