{"id":"W3190588453","doi":"10.3390/data6080084","title":"The Automatic Detection of Dataset Names in Scientific Articles","year":2021,"lang":"en","type":"article","venue":"Data","topic":"Topic Modeling","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Canadian Institute of Steel Construction","keywords":"Computer science; Named-entity recognition; Annotation; Task (project management); Natural language processing; Sentence; Feature (linguistics); Set (abstract data type); Artificial intelligence; Code (set theory); Information retrieval; Baseline (sea); Linguistics; Programming language","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":[],"consensus_categories":[],"category_scores_codex":[0.0005563392,0.0000269095,0.00004038633,0.0000262374,0.00007893956,0.0001792805,0.001102236,0.000009695138,0.000003720235],"category_scores_gemma":[0.0002138499,0.00002028507,0.000005094779,0.0002862189,0.00003647146,0.0003933952,0.0009262192,0.00003872473,0.000013431],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000072935,"about_ca_system_score_gemma":0.00005115886,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003983095,"about_ca_topic_score_gemma":0.0006182794,"domain_scores_codex":[0.9993723,0.00004966146,0.0001319215,0.0002182492,0.0001384005,0.00008947693],"domain_scores_gemma":[0.9979287,0.00008212581,0.0000318154,0.001924616,0.00001900294,0.0000137472],"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":[9.935897e-7,0.00005669532,0.0006867381,0.00003048663,0.000008232072,0.00001796789,0.0004939306,0.0001704856,0.02690547,0.005320536,0.005499923,0.9608085],"study_design_scores_gemma":[0.00005955939,0.000002528211,0.001474649,0.0000123745,0.000001453152,0.000005396482,0.00005770931,0.9718564,0.01319066,0.001722929,0.01158581,0.0000305702],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5463612,0.0007260242,0.449773,0.001462804,0.0007693234,0.00009879962,0.0007165414,0.00005478185,0.00003753227],"genre_scores_gemma":[0.988172,0.000005528274,0.01147107,0.00002752609,0.000009658516,0.000001576348,0.0002920402,0.00000136224,0.00001922465],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9716859,"threshold_uncertainty_score":0.2048248,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06923547144482206,"score_gpt":0.2931762461491873,"score_spread":0.2239407747043652,"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."}}