{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006087896,0.00009609632,0.0002176823,0.00007588467,0.000175508,0.0005388761,0.001072502,0.00002970433,0.00006437677],"category_scores_gemma":[0.0004373808,0.00005589065,0.000204381,0.0008827537,0.0001057085,0.001073045,0.0003312405,0.0001762333,0.00001017785],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002706541,"about_ca_system_score_gemma":0.0001802447,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001181055,"about_ca_topic_score_gemma":0.000006390927,"domain_scores_codex":[0.9985614,0.00008671716,0.0005453725,0.0001560594,0.0004765443,0.000173857],"domain_scores_gemma":[0.9978196,0.00004180009,0.0005880053,0.0005028255,0.0009596376,0.0000881228],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001760665,0.001108591,0.005141062,0.0003148212,0.0006325783,0.0005252406,0.002643671,0.001508091,0.1679516,0.08605418,0.7267988,0.007303729],"study_design_scores_gemma":[0.001800688,0.0001084595,0.006403073,0.0006405114,0.0003594449,0.001027307,0.002267494,0.1157267,0.5734975,0.004500981,0.2930499,0.0006179816],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2444709,0.0035221,0.7189158,0.01963106,0.006799665,0.000244771,0.00151217,0.00008245497,0.004821013],"genre_scores_gemma":[0.9797845,0.0002161037,0.0155529,0.000560828,0.0002076172,1.847257e-7,0.00007253112,0.000009207582,0.003596146],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7353135,"threshold_uncertainty_score":0.5196394,"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."}}