{"id":"W4312338894","doi":"10.1177/20539517221139785","title":"Politics of data reuse in machine learning systems: Theorizing reuse entanglements","year":2022,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Research Data Management Practices","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Danmarks Frie Forskningsfond; Simon Fraser University; Concordia University; Copenhagen Business School","keywords":"Reuse; Politics; Sociology; Epistemology; Computer science; Data science; Political science; Engineering; Law","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.007923241,0.0001538548,0.0002282273,0.0001137585,0.0004188566,0.000831003,0.0419517,0.00003051408,0.00001712056],"category_scores_gemma":[0.003110813,0.0001583679,0.00003678504,0.0009799665,0.00007015096,0.01719452,0.1516998,0.0006401626,0.000007277554],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001936783,"about_ca_system_score_gemma":0.0001860043,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002677413,"about_ca_topic_score_gemma":0.0000563431,"domain_scores_codex":[0.9957705,0.00092836,0.0005110101,0.001029208,0.001238394,0.000522565],"domain_scores_gemma":[0.9808636,0.000507585,0.0003676415,0.01812744,0.0000452701,0.00008846092],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00008740062,0.002556006,0.0680794,0.001748467,0.001400171,0.0004726579,0.01629672,0.002072089,0.003209356,0.2637014,0.611672,0.0287043],"study_design_scores_gemma":[0.0007281138,0.00008986551,0.0005299768,0.00004690794,0.00002535906,0.000009382713,0.00405652,0.225628,0.00002372653,0.0004587111,0.7681661,0.0002372838],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1624706,0.02880307,0.6720283,0.04753925,0.00807116,0.007946533,0.06411637,0.001757287,0.00726745],"genre_scores_gemma":[0.7973664,0.01011011,0.1639896,0.000947223,0.0004633428,0.000110091,0.02466997,0.00008903984,0.002254278],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6348958,"threshold_uncertainty_score":0.9965515,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3213972372293789,"score_gpt":0.3922255520914198,"score_spread":0.07082831486204094,"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."}}