{"id":"W6891414117","doi":"10.3929/ethz-a-010137112","title":"Comparing ICP variants on real-world data sets: Open-source library and experimental protocol","year":2013,"lang":"en","type":"article","venue":"reroDoc Digital Library","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Protocol (science); Data collection; Identification (biology); Matching (statistics); Feature (linguistics)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01149,0.002145017,0.00144592,0.004683401,0.001898313,0.001815505,0.004687674,0.002151536,0.0180127],"category_scores_gemma":[0.02856893,0.00121327,0.001045447,0.005972268,0.002155282,0.002909008,0.005282925,0.002015366,0.009969069],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001400305,"about_ca_system_score_gemma":0.00345881,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003311848,"about_ca_topic_score_gemma":0.003850819,"domain_scores_codex":[0.9883279,0.00312567,0.001784634,0.00179574,0.00435762,0.0006085181],"domain_scores_gemma":[0.9759854,0.006449934,0.0009985666,0.007267606,0.008777014,0.0005214346],"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":[0.006692003,0.006908645,0.009908133,0.00646064,0.0007140213,0.001323047,0.002265017,0.07611382,0.08521169,0.0180426,0.1616088,0.6247516],"study_design_scores_gemma":[0.002724049,0.004398015,0.03866719,0.001003683,0.0004396731,0.002887344,0.003021851,0.2106934,0.3537602,0.03342737,0.3476138,0.001363465],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07687175,0.0005063416,0.7816457,0.0005365824,0.0004324992,0.02761449,0.04931238,0.04860641,0.01447384],"genre_scores_gemma":[0.07440972,0.000466584,0.7296787,0.000347743,0.00008384368,0.09133737,0.09240329,0.006331902,0.004940952],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0180127,"threshold_uncertainty_score":0.06076568,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04447859576449631,"score_gpt":0.3107546281914985,"score_spread":0.2662760324270022,"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."}}