{"id":"W6910332889","doi":"10.48448/3yrc-8z07","title":"What Motivates You? Benchmarking Automatic Detection of Basic Needs from Short Posts","year":2021,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Benchmarking; Task (project management); Benchmark (surveying); Autonomy; Everyday life; Basic needs; Automation; Binary number","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001122462,0.0006071623,0.0008022186,0.002782467,0.0002322927,0.0005544146,0.001241249,0.0003910435,0.00384213],"category_scores_gemma":[0.0003892678,0.0005898788,0.0001607303,0.004685732,0.001429984,0.0008968025,0.0004868362,0.000463514,0.0002980505],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000557773,"about_ca_system_score_gemma":0.0008170197,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001655811,"about_ca_topic_score_gemma":0.002198069,"domain_scores_codex":[0.995312,0.0001535973,0.0007311936,0.001115619,0.001908374,0.0007792265],"domain_scores_gemma":[0.9973478,0.0002048917,0.0006170234,0.001243982,0.0003365223,0.0002497734],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001445314,0.0004220228,0.00274599,0.0003299657,0.0002927535,0.00004478546,0.001802349,0.0003100575,0.7493222,0.0001649452,0.005009755,0.2395408],"study_design_scores_gemma":[0.002369458,0.001080536,0.02672747,0.02761459,0.00130062,0.0001870767,0.02154742,0.4651205,0.402289,0.00269742,0.04266555,0.006400309],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7833292,0.01551565,0.00706044,0.0003149191,0.02115704,0.003608488,0.0008471779,0.0034854,0.1646817],"genre_scores_gemma":[0.9694391,0.0002328822,0.008742427,0.00009654291,0.0009239439,0.00002913698,0.0005026062,0.0009340142,0.01909927],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4648105,"threshold_uncertainty_score":0.9996552,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02211603283015955,"score_gpt":0.2782460860923982,"score_spread":0.2561300532622386,"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."}}