{"id":"W4402759470","doi":"10.1177/10506519241280587","title":"Technical Communication's Fight Against Extractive Large Language Modeling by Applying FAIR and CARE Principles of Data","year":2024,"lang":"en","type":"article","venue":"Journal of Business and Technical Communication","topic":"Research Data Management Practices","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Technical communication; Technical writing; Engineering ethics; Computer science; Management science; Sociology; Linguistics; Engineering; Political science; Higher education; Law; Philosophy","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002344061,0.0001233077,0.0002489691,0.0002269375,0.0002050164,0.000884651,0.003766568,0.00009177894,0.00000176464],"category_scores_gemma":[0.0006401041,0.0001010347,0.00003293519,0.0005635156,0.0001259801,0.01290743,0.005118043,0.000667576,4.455733e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005320507,"about_ca_system_score_gemma":0.00009047853,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004758648,"about_ca_topic_score_gemma":0.00005176548,"domain_scores_codex":[0.9983218,0.0002475976,0.0005704192,0.0002675989,0.0004355772,0.0001570046],"domain_scores_gemma":[0.9962286,0.000686063,0.000372489,0.002256962,0.0003838275,0.00007209118],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001850874,0.001229762,0.000667771,0.002201981,0.0003374507,0.00009366778,0.002278442,0.0009654713,0.0563839,0.3992894,0.004341343,0.5320257],"study_design_scores_gemma":[0.00186182,0.0002540997,0.005947531,0.004513965,0.0002874878,0.0004297089,0.004657055,0.694983,0.0008810464,0.003159889,0.2821123,0.0009120868],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008656034,0.06260367,0.9194964,0.006713889,0.0000276594,0.0003824669,0.00008347222,0.00009926584,0.001937199],"genre_scores_gemma":[0.8818849,0.03143629,0.08645759,0.00004175169,0.00001437711,0.00001340443,0.000125912,0.00001101389,0.00001479491],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8732288,"threshold_uncertainty_score":0.9357576,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1012070423202426,"score_gpt":0.3740162401333412,"score_spread":0.2728091978130986,"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."}}