{"id":"W4400522920","doi":"10.1162/dint_a_00255","title":"FAIR Enough: Develop and Assess a FAIR-Compliant Dataset for Large Language Model Training?","year":2024,"lang":"en","type":"article","venue":"Data Intelligence","topic":"Research Data Management Practices","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University; Toronto Metropolitan University; Vector Institute","funders":"Government of Canada; Canadian Institute for Advanced Research","keywords":"Stewardship (theology); Computer science; Context (archaeology); Interoperability; Frame (networking); Process (computing); Work (physics); Engineering ethics; Knowledge management; Process management; Accreditation; Checklist; Data science; Risk analysis (engineering); Political science; Business; Engineering; Psychology; World Wide Web; Medical education; Medicine","routes":{"ca_aff":true,"ca_fund":true,"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","open_science"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.00269819,0.0002052829,0.0001878785,0.0001562742,0.000180138,0.004148574,0.006409768,0.000049338,0.00001993199],"category_scores_gemma":[0.001224741,0.0001822166,0.0000197869,0.0006260299,0.00006392137,0.02551872,0.005568637,0.000263095,0.000108036],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003186255,"about_ca_system_score_gemma":0.0002529285,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000757524,"about_ca_topic_score_gemma":0.0001289749,"domain_scores_codex":[0.9972439,0.00007975441,0.0003179701,0.001306568,0.000460068,0.0005917808],"domain_scores_gemma":[0.9961771,0.0007432081,0.00006632492,0.002793728,0.00006557247,0.0001540747],"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":[0.00001469289,0.00008869802,0.00001089966,0.0004503621,0.0001062552,0.0002261223,0.002427848,0.00009579117,0.0002428567,0.7147921,0.1145727,0.1669717],"study_design_scores_gemma":[0.00003771304,0.00002775039,0.000009180864,0.00004941401,0.00001073402,0.00001699268,0.000521019,0.6087494,0.000216032,0.001386255,0.3888081,0.0001673479],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001305821,0.0008504866,0.9582657,0.00201164,0.0001810255,0.0004458553,0.03762138,0.0001686807,0.000324657],"genre_scores_gemma":[0.157155,0.001880926,0.7866951,0.001313735,0.0001756158,0.0001988503,0.0514195,0.00005579933,0.001105479],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7134058,"threshold_uncertainty_score":0.998966,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3962006214895893,"score_gpt":0.4654284737358328,"score_spread":0.0692278522462435,"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."}}