{"id":"W4401267042","doi":"10.2139/ssrn.4885662","title":"Will User-Contributed AI Training Data Eat Its Own Tail?","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Training (meteorology); Computer science; 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":[0.03937671,0.0007753012,0.000999357,0.002145782,0.001184423,0.00576818,0.003087215,0.002974328,0.01929927],"category_scores_gemma":[0.202145,0.0007236107,0.0005893015,0.002921742,0.002465008,0.01214852,0.00388214,0.005442036,0.01326653],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001563675,"about_ca_system_score_gemma":0.002138066,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004168279,"about_ca_topic_score_gemma":0.004800124,"domain_scores_codex":[0.9828032,0.01085562,0.0006026832,0.001334712,0.003955444,0.0004483723],"domain_scores_gemma":[0.7595558,0.1181779,0.003667836,0.08441319,0.03130145,0.002883941],"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":[0.001792131,0.0004618712,0.05136514,0.0005990982,0.0003660067,0.0002059163,0.002405359,0.01218955,0.007744775,0.07849318,0.2925246,0.5518523],"study_design_scores_gemma":[0.0002392916,0.0004514721,0.0247526,0.000803861,0.0001997717,0.0007237616,0.003000836,0.1829132,0.0398312,0.2652975,0.4815188,0.0002676856],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1659528,0.002834249,0.4629369,0.1701667,0.0084111,0.000612618,0.02233515,0.02805247,0.1386979],"genre_scores_gemma":[0.7384484,0.00132498,0.1630247,0.02044999,0.002378324,0.0005020624,0.01848794,0.007186876,0.04819672],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03937671,"threshold_uncertainty_score":0.2082465,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05195564040774149,"score_gpt":0.3158387788508273,"score_spread":0.2638831384430858,"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."}}