{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.006258138,0.0003832755,0.000319047,0.0001641203,0.0003096284,0.003229015,0.009856921,0.0004083749,0.000285642],"category_scores_gemma":[0.007470533,0.000354882,0.00004112502,0.0006119084,0.00006008376,0.01351654,0.02743065,0.002361153,0.0007965073],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001458753,"about_ca_system_score_gemma":0.0009032907,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004557972,"about_ca_topic_score_gemma":0.001843215,"domain_scores_codex":[0.9936841,0.0009761782,0.0006925885,0.002910121,0.001335338,0.0004017475],"domain_scores_gemma":[0.9877489,0.0006844898,0.0009228157,0.01012957,0.0004379505,0.00007624987],"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":[0.00002612898,0.0003504429,0.0001463162,0.0004327542,0.0002425079,0.00006286088,0.00952951,0.04531603,0.0002011695,0.632741,0.00674104,0.3042103],"study_design_scores_gemma":[0.00001862682,0.00004765346,0.000005659471,0.0001887979,0.00009013442,0.000008467176,0.000307977,0.7113247,0.000247897,0.2648053,0.02265826,0.0002965892],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0006041442,0.003802638,0.9739664,0.008931396,0.002547112,0.0009344231,0.00009899514,0.0008732797,0.008241594],"genre_scores_gemma":[0.2897741,0.001719276,0.6967415,0.0008779202,0.001335011,0.0001053034,0.008777655,0.00007662673,0.0005926479],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6660087,"threshold_uncertainty_score":0.9999815,"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."}}