{"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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.003399088,0.0002637744,0.0002815621,0.000234752,0.0004526283,0.001369164,0.002065823,0.0001175437,0.00002014585],"category_scores_gemma":[0.0001729058,0.0002239864,0.000129308,0.0006772502,0.00003885753,0.002742013,0.000409018,0.002857781,0.0001023801],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005598295,"about_ca_system_score_gemma":0.003412238,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001678193,"about_ca_topic_score_gemma":0.0001838264,"domain_scores_codex":[0.9953107,0.0001518392,0.0004161157,0.0006868333,0.0004782383,0.002956326],"domain_scores_gemma":[0.9984945,0.0001431741,0.0001027318,0.0009434764,0.0001263356,0.0001897663],"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":[0.00001993022,0.00004306448,0.00006830828,0.00002761393,0.0003941286,0.00027093,0.001437536,0.0004180757,0.003038696,0.5714497,0.004249945,0.4185821],"study_design_scores_gemma":[0.001472575,0.000631163,0.00007022359,0.0006058441,0.0001583318,0.0134985,0.001513379,0.4317178,0.0009358088,0.1849487,0.3632678,0.001179861],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0354898,0.02181544,0.9318272,0.008040789,0.001621936,0.0001546059,0.00001480689,0.0005775317,0.0004578744],"genre_scores_gemma":[0.9937668,0.001326817,0.001023866,0.0004484921,0.0009169067,0.000002773657,0.00001694691,0.00003961026,0.002457794],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.958277,"threshold_uncertainty_score":0.9996675,"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."}}