{"id":"W4389519026","doi":"10.18653/v1/2023.emnlp-main.496","title":"GD-COMET: A Geo-Diverse Commonsense Inference Model","year":2023,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Comet; Commonsense knowledge; Inference; Task (project management); Computer science; Commonsense reasoning; Range (aeronautics); Natural language processing; Artificial intelligence; Data science; Knowledge-based systems; Astronomy; Physics; Engineering; Systems engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002393858,0.0001129828,0.0001135847,0.0001910434,0.0001879903,0.0001109982,0.0009419835,0.00004610623,0.00004125693],"category_scores_gemma":[0.0001207522,0.0001041686,0.00004875504,0.001004547,0.00003878384,0.0002090433,0.000617356,0.0001907776,0.003328624],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002256218,"about_ca_system_score_gemma":0.00005860705,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008492836,"about_ca_topic_score_gemma":0.00004739739,"domain_scores_codex":[0.9989556,0.00004697307,0.0001522445,0.0003456857,0.0002252654,0.0002742273],"domain_scores_gemma":[0.9986537,0.0002672789,0.00004729549,0.0008553503,0.00006297279,0.0001133924],"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":[0.00000403131,0.0001066559,0.01226047,0.00001450812,0.00002047884,0.00002019348,0.001956016,0.2825129,0.002398328,0.6438255,0.01179153,0.04508941],"study_design_scores_gemma":[0.0001339625,0.00001130569,0.02462138,0.000003160257,0.000002090072,0.000002622587,0.0000197961,0.9650005,0.00008732372,0.009336124,0.0006509504,0.000130777],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2181918,0.0000032897,0.7633341,0.004812294,0.00005689657,0.0001511181,0.000004760103,0.00168375,0.01176201],"genre_scores_gemma":[0.9059949,0.000004644825,0.0914844,0.0005248067,0.00001353205,0.0000369189,0.00000573939,0.000008108053,0.001926934],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6878031,"threshold_uncertainty_score":0.9974474,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05572125529200657,"score_gpt":0.3378330340009139,"score_spread":0.2821117787089074,"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."}}