{"id":"W4385436799","doi":"10.48550/arxiv.2307.15508","title":"The Road to Quality is Paved with Good Revisions: A Detailed Evaluation Methodology for Revision Policies in Incremental Sequence Labelling","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Atomic Energy of Canada Limited","keywords":"Computer science; Prefix; Sequence (biology); Labelling; Encoder; Quality (philosophy); Transformer; Engineering","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":[0.007240255,0.0002763602,0.0004710071,0.0003151015,0.000308746,0.0001769273,0.001553763,0.0002138607,0.000004280865],"category_scores_gemma":[0.0009346413,0.0002238452,0.0001493257,0.001110961,0.00007607327,0.0002270811,0.001149295,0.0003075026,0.00004499577],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004917808,"about_ca_system_score_gemma":0.0004118122,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003168618,"about_ca_topic_score_gemma":0.002356724,"domain_scores_codex":[0.9959925,0.00170178,0.000463814,0.001131819,0.0002599029,0.0004501393],"domain_scores_gemma":[0.996351,0.001376557,0.0004198668,0.001292864,0.0004253811,0.0001343507],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002256877,0.0003617122,0.05089939,0.001424427,0.0007955156,0.0002198934,0.01700389,0.2766908,0.006421833,0.577292,0.001117967,0.06551573],"study_design_scores_gemma":[0.004424752,0.0008605271,0.03285499,0.002635898,0.0002887755,0.00001204131,0.00315157,0.8323341,0.002967873,0.1161932,0.002408038,0.001868235],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3463849,0.0002145173,0.6489249,0.0007292575,0.0005492067,0.002739024,0.00003978199,0.000164047,0.0002542934],"genre_scores_gemma":[0.9786142,0.0002805273,0.02001991,0.0002488776,0.00008137474,0.00003030806,0.00003262601,0.00002113519,0.0006710006],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6322293,"threshold_uncertainty_score":0.9128142,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4732101525060852,"score_gpt":0.3479648132122058,"score_spread":0.1252453392938793,"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."}}