{"id":"W4308789076","doi":"10.1145/3555623","title":"Documenting Data Production Processes","year":2022,"lang":"en","type":"article","venue":"Proceedings of the ACM on Human-Computer Interaction","topic":"Ethics and Social Impacts of AI","field":"Social Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Bundesministerium für Bildung und Forschung; International Development Research Centre","keywords":"Documentation; Computer science; Boundary object; Data science; Production (economics); Knowledge management; Object (grammar); Citizen journalism; Data curation; Data collection; Field (mathematics); Process management; World Wide Web; Artificial intelligence; Engineering; Geography","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.001690751,0.0001032457,0.0001298542,0.00009977203,0.002375694,0.000307021,0.002636587,0.00004489172,0.00009380116],"category_scores_gemma":[0.002840409,0.00009012248,0.00005503456,0.0004334651,0.0001317171,0.001550587,0.001964554,0.0005111609,0.000004430549],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001978926,"about_ca_system_score_gemma":0.00009591963,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005909281,"about_ca_topic_score_gemma":0.0001124102,"domain_scores_codex":[0.9983668,0.00004800165,0.0002556219,0.0003554195,0.0007534467,0.0002207576],"domain_scores_gemma":[0.9983978,0.0001205237,0.0004768511,0.0004312932,0.0005328725,0.00004061066],"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":[0.0003428073,0.002035812,0.01138381,0.0009037193,0.0004079039,0.000001725745,0.2800591,0.0005614373,0.03046774,0.1213703,0.5006496,0.05181606],"study_design_scores_gemma":[0.0009385208,0.001022763,0.005385516,0.0008577457,0.0002153057,0.00002384046,0.06876702,0.0005879534,0.03167672,0.2224694,0.6669021,0.001153122],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.940241,0.00002095537,0.00000596679,0.0338162,0.002804982,0.0004594604,0.000007351233,0.0001171158,0.02252696],"genre_scores_gemma":[0.9960164,0.00002075217,0.0004834741,0.000485066,0.001371604,0.00002148474,0.000006718009,0.0000146839,0.0015798],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.211292,"threshold_uncertainty_score":0.9989231,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2017090878449614,"score_gpt":0.438637902456563,"score_spread":0.2369288146116015,"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."}}