{"id":"W2121448658","doi":"10.1109/icdar.2009.247","title":"Issues in Performance Evaluation: A Case Study of Math Recognition","year":2009,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada; Xerox Foundation","keywords":"Computer science; Context (archaeology); Range (aeronautics); Machine learning; Artificial intelligence; Engineering","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06830505,0.00146427,0.001540065,0.003987664,0.002591445,0.007069195,0.002594864,0.003785465,0.002426897],"category_scores_gemma":[0.2185434,0.0004117537,0.0009884406,0.006731608,0.003873829,0.006542515,0.002920795,0.003035509,0.001171575],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004818047,"about_ca_system_score_gemma":0.002446692,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005836393,"about_ca_topic_score_gemma":0.004473454,"domain_scores_codex":[0.8746058,0.08830684,0.005938667,0.004708174,0.02432253,0.002117842],"domain_scores_gemma":[0.6466637,0.2943509,0.00945678,0.01348313,0.0331545,0.002891062],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001369579,0.00130363,0.0399131,0.003087133,0.0004062935,0.001771028,0.01294537,0.05231098,0.00957501,0.06982031,0.02845303,0.7790444],"study_design_scores_gemma":[0.0006775627,0.00761469,0.11561,0.003660357,0.0007405718,0.01125795,0.02015975,0.3619401,0.07872199,0.216865,0.1817808,0.0009712087],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3711282,0.0275302,0.4802269,0.03176539,0.000655389,0.001225018,0.0007271027,0.003401299,0.08334045],"genre_scores_gemma":[0.8935893,0.00249829,0.0986251,0.0009423899,0.0003541028,0.0002462699,0.0003290558,0.0005394752,0.002876027],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.06830505,"threshold_uncertainty_score":0.3612359,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0537565135134561,"score_gpt":0.3329474294971629,"score_spread":0.2791909159837068,"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."}}