{"id":"W3133718336","doi":"10.22148/001c.21374","title":"Images of the arXiv: Reconfiguring large scientific image datasets","year":2021,"lang":"en","type":"article","venue":"Journal of Cultural Analytics","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Metadata; Data science; Set (abstract data type); Representation (politics); Point (geometry); Range (aeronautics); Information retrieval; Scientific literature; World Wide Web","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.003793437,0.0007398337,0.0005906352,0.009147221,0.001029835,0.00477488,0.002002007,0.001148698,0.005013487],"category_scores_gemma":[0.02669528,0.0005226476,0.001203983,0.008337064,0.001396411,0.006795729,0.005070837,0.001966302,0.003863009],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001244053,"about_ca_system_score_gemma":0.001219526,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00569175,"about_ca_topic_score_gemma":0.01288819,"domain_scores_codex":[0.997656,0.000760769,0.0002119178,0.000580609,0.0006078639,0.0001828757],"domain_scores_gemma":[0.9875136,0.003896684,0.0008510986,0.004765045,0.002123102,0.000850439],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0009079184,0.0005634354,0.03944862,0.002210993,0.0003531448,0.000840084,0.008394603,0.01278759,0.01355851,0.04580446,0.4356865,0.4394441],"study_design_scores_gemma":[0.00017826,0.0002286966,0.039747,0.0004855548,0.0001269819,0.0008313045,0.008848199,0.09443574,0.02267116,0.1061299,0.7260272,0.0002900808],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2415447,0.006299646,0.3016061,0.01306571,0.003660903,0.001844972,0.281285,0.1076119,0.04308096],"genre_scores_gemma":[0.3109386,0.001879529,0.4670368,0.001043758,0.0007057901,0.0009178029,0.2038986,0.009587163,0.003991888],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9908528,"threshold_uncertainty_score":0.02006185,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03356266331921172,"score_gpt":0.3070275559818708,"score_spread":0.2734648926626591,"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."}}