{"id":"W4396786982","doi":"10.1145/3630106.3658955","title":"Machine learning data practices through a data curation lens: An evaluation framework","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Data curation; Rubric; Computer science; Data science; Transparency (behavior); Documentation; Best practice; Machine learning; Artificial intelligence; Knowledge management","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5199912,0.002229158,0.002285956,0.01609989,0.00685792,0.01348016,0.004578287,0.003914454,0.003657067],"category_scores_gemma":[0.5934619,0.001106044,0.003129178,0.01923763,0.01427586,0.01618837,0.01378437,0.004467027,0.0009818643],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.02520348,"about_ca_system_score_gemma":0.02076573,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01030721,"about_ca_topic_score_gemma":0.008832995,"domain_scores_codex":[0.3063923,0.5764674,0.03293145,0.009059348,0.06999759,0.005152042],"domain_scores_gemma":[0.2875161,0.4688128,0.04494875,0.05662307,0.1376123,0.004486939],"domain_codex":"methods","domain_gemma":"methods","domain_candidate":"methods","domain_consensus":"methods","study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.006601645,0.00800412,0.124104,0.01411325,0.002512239,0.0004827588,0.09411533,0.02242008,0.00689869,0.3017962,0.01891362,0.4000382],"study_design_scores_gemma":[0.007592836,0.02598684,0.1307431,0.02848134,0.005096538,0.001040073,0.1099262,0.149493,0.07228758,0.2302103,0.2378345,0.001307678],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.456891,0.006045166,0.3513132,0.01591768,0.0004752248,0.05989846,0.005726664,0.001081415,0.1026512],"genre_scores_gemma":[0.667115,0.0006867211,0.2697217,0.001538593,0.00009084216,0.05642394,0.001822497,0.0003860536,0.002214659],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4800088,"threshold_uncertainty_score":0.5919363,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.498315670419755,"score_gpt":0.4884108769035415,"score_spread":0.00990479351621354,"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."}}