{"id":"W4401042513","doi":"10.18653/v1/2024.naacl-demo.7","title":"jp-evalb: Robust Alignment-based PARSEVAL Measures","year":2024,"lang":"en","type":"article","venue":"","topic":"Fuzzy Logic and Control Systems","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"University of British Columbia","keywords":"Parseval's theorem; Computer science; Mathematics; Fourier transform; Fourier analysis","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":[0.0004802785,0.0001367685,0.0001475262,0.00007313895,0.00007250381,0.0004484289,0.0006348081,0.00005611968,0.00004293023],"category_scores_gemma":[0.00001776418,0.00009701309,0.0001141212,0.0002616666,0.00002550796,0.0002360453,0.00007803919,0.00008435442,0.0006951212],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005468543,"about_ca_system_score_gemma":0.0001334769,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001028185,"about_ca_topic_score_gemma":0.00001223051,"domain_scores_codex":[0.9985375,0.00008975236,0.000194514,0.0004168964,0.0004723369,0.0002889971],"domain_scores_gemma":[0.9992905,0.0001054869,0.00002062938,0.0004442825,0.00003840575,0.0001007098],"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":[0.00001102652,0.00008292745,0.0002083196,0.00007804176,0.00009677232,0.0001915449,0.0002483173,0.007554111,0.002388524,0.8205239,0.09458634,0.07403021],"study_design_scores_gemma":[0.0007455344,0.0001969778,0.0002701687,0.0001031473,0.00002839054,0.00003709641,0.00007482835,0.8125163,0.002201628,0.0145728,0.1687084,0.0005447147],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0003630589,0.001977942,0.8666975,0.005516702,0.001518284,0.0002017153,0.000001882445,0.0009449246,0.1227779],"genre_scores_gemma":[0.9883068,0.000005276716,0.006462272,0.001282168,0.0001833973,0.00003655872,0.000001259934,0.000009338426,0.0037129],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9879438,"threshold_uncertainty_score":0.8934608,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03207759730768253,"score_gpt":0.2273532539965208,"score_spread":0.1952756566888383,"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."}}