{"id":"W4231515836","doi":"10.1109/jcdl.2017.7991565","title":"A Text Extraction Software Benchmark Based on a Synthesized Dataset","year":2017,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Vienna Science and Technology Fund","keywords":"Computer science; Ground truth; Correctness; Workflow; Information retrieval; Data mining; Benchmark (surveying); Scalability; Quality (philosophy); Process (computing); Snippet; Artificial intelligence; Database; Algorithm; Programming language","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":[0.0004434673,0.0001443291,0.0001372022,0.00009927408,0.0005596271,0.0005962047,0.001464159,0.0000678568,0.00007338652],"category_scores_gemma":[0.00256087,0.0001197976,0.00004913063,0.00006485039,0.00005018797,0.0005287549,0.0002024554,0.0001342114,0.0001240471],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000327074,"about_ca_system_score_gemma":0.00006217565,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002483352,"about_ca_topic_score_gemma":0.000009099151,"domain_scores_codex":[0.99889,0.00004799974,0.0001430393,0.000427051,0.0002691594,0.0002227857],"domain_scores_gemma":[0.9965471,0.0007928166,0.0001541431,0.002375728,0.00004496428,0.00008527312],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003264909,0.0002251297,0.005505756,0.00002195091,0.000009753746,0.00008499458,0.0000308057,0.0000375302,0.000123543,0.00202502,0.6657451,0.3261577],"study_design_scores_gemma":[0.001665901,0.0007730069,0.07043976,0.0006711196,0.00003679467,0.0001115972,0.000003499381,0.7580779,0.01165442,0.068082,0.08683537,0.001648661],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003993617,0.000006696727,0.9855735,0.001392193,0.0002270452,0.0001419062,0.000046895,0.008440681,0.003771679],"genre_scores_gemma":[0.3975645,0.00000122726,0.6010851,0.001078539,0.00004483622,0.00003150157,0.00004449356,0.000009695892,0.0001400507],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7580404,"threshold_uncertainty_score":0.5749216,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03252267041055522,"score_gpt":0.315905866224399,"score_spread":0.2833831958138438,"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."}}