{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008175296,0.00007909186,0.0001280589,0.0002195638,0.00003485151,0.00003951658,0.0002027267,0.00003408049,0.00006140421],"category_scores_gemma":[0.00002977747,0.00007140356,0.00001836476,0.0004640711,0.00000906878,0.00061947,0.00003576713,0.00007088274,0.00002645551],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003192347,"about_ca_system_score_gemma":0.00003070845,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002034743,"about_ca_topic_score_gemma":0.0001263174,"domain_scores_codex":[0.9989665,0.0001138714,0.000286977,0.0002182047,0.0003026337,0.0001117832],"domain_scores_gemma":[0.999356,0.00002614395,0.00007264345,0.0002847885,0.0002339479,0.00002645463],"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":[0.00000345839,0.0005835199,0.0008414785,0.000004634567,0.000002606569,0.000120658,0.002472472,0.000004126991,0.0001114704,0.0001507017,0.00008780558,0.9956171],"study_design_scores_gemma":[0.007670147,0.0133686,0.08216692,0.0004675484,0.00007147641,0.005220878,0.01265782,0.7258071,0.116297,0.03464694,0.0001966618,0.001428893],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9877099,0.00002802988,0.008112025,0.0001794535,0.00002857543,0.0005780723,3.543683e-7,0.0001657149,0.003197847],"genre_scores_gemma":[0.9742307,0.00001705763,0.02553461,0.000105368,0.00001384702,0.00004945465,0.000001342234,0.000002322983,0.00004530906],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9941882,"threshold_uncertainty_score":0.2911752,"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."}}