{"id":"W4400651304","doi":"10.2139/ssrn.4894680","title":"Will User-Contributed AI Training Data Eat its Own Tail?","year":2024,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Mobile Crowdsensing and Crowdsourcing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Training (meteorology); Computer science; Artificial intelligence; Geography","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":[0.03314893,0.000821103,0.001112904,0.001635534,0.001861539,0.006880153,0.00295278,0.004282604,0.01492979],"category_scores_gemma":[0.1596217,0.0006836564,0.0005896448,0.002282206,0.003216071,0.01373383,0.003940996,0.005817185,0.01268384],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001830554,"about_ca_system_score_gemma":0.002911341,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009624149,"about_ca_topic_score_gemma":0.01130893,"domain_scores_codex":[0.986707,0.007543244,0.0003575581,0.001434984,0.003397012,0.0005602072],"domain_scores_gemma":[0.8529418,0.07649024,0.003466811,0.03709722,0.0264919,0.00351201],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001583272,0.000492083,0.06234494,0.0005580947,0.000360431,0.0001906206,0.001953175,0.01343159,0.005210928,0.09989135,0.3937625,0.420221],"study_design_scores_gemma":[0.0001978516,0.0004562565,0.02943643,0.0007689045,0.0001898555,0.0005547494,0.00531824,0.1651175,0.01540856,0.3453504,0.4369172,0.0002840219],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.1144569,0.004093282,0.2793561,0.3941287,0.01716205,0.0006493118,0.01829753,0.01017559,0.1616803],"genre_scores_gemma":[0.7951002,0.002143171,0.07666187,0.04761948,0.007550253,0.0004440974,0.01128848,0.00236992,0.05682253],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03314893,"threshold_uncertainty_score":0.1753104,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02161098288901193,"score_gpt":0.2681092890640046,"score_spread":0.2464983061749926,"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."}}