{"id":"W4403432465","doi":"10.1002/pra2.1009","title":"Mining, Scraping, Training, Generating: Copyright Implications of Generative <scp>AI</scp>","year":2024,"lang":"en","type":"article","venue":"Proceedings of the Association for Information Science and Technology","topic":"Open Source Software Innovations","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"College of Veterinary Medicine, Cornell University; University of Oxford; University of Cambridge; Harvard University","keywords":"Generative grammar; Training (meteorology); Computer science; Generative model; 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":[],"consensus_categories":[],"category_scores_codex":[0.001859795,0.0001069232,0.0001699336,0.0009781388,0.0005113891,0.0004729736,0.001152192,0.0001382968,6.423805e-7],"category_scores_gemma":[0.004083341,0.0000852516,0.00004752773,0.005434713,0.0003648865,0.004113656,0.0003182239,0.0001457201,0.000002722049],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001661556,"about_ca_system_score_gemma":0.0004349315,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000256772,"about_ca_topic_score_gemma":0.000001112932,"domain_scores_codex":[0.9984508,0.000003821967,0.0005491195,0.0002222777,0.0005118695,0.0002621369],"domain_scores_gemma":[0.9952334,0.0001915173,0.0007571748,0.0001692037,0.003615118,0.00003363725],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[2.275577e-7,0.00000933993,0.005300656,0.00003914153,0.00002191317,5.20588e-9,0.00663386,0.000008227545,0.01599212,0.9525476,0.008461371,0.01098556],"study_design_scores_gemma":[0.000780805,0.0003464973,0.008517076,0.0002384398,0.00007324106,0.00003467519,0.006134856,0.1035364,0.4507091,0.1559973,0.2733282,0.0003033977],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6484407,0.0002695562,0.2443791,0.06317014,0.00144379,0.002616896,0.0001324823,0.001296883,0.03825052],"genre_scores_gemma":[0.951541,0.00001047987,0.04748676,0.000454264,0.0000269535,0.0001265871,0.000003207373,0.000005592902,0.0003451371],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7965503,"threshold_uncertainty_score":0.4888436,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01669452258420467,"score_gpt":0.2706071367164153,"score_spread":0.2539126141322106,"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."}}