{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002790733,0.001267057,0.0005177315,0.002892171,0.0007855308,0.001252134,0.002121509,0.001621817,0.001805662],"category_scores_gemma":[0.01090468,0.0003251788,0.001228672,0.002779584,0.0007311595,0.00142694,0.001291363,0.001132819,0.00121123],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001517425,"about_ca_system_score_gemma":0.001354197,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004492149,"about_ca_topic_score_gemma":0.006396173,"domain_scores_codex":[0.9970706,0.0008796686,0.00043534,0.0007270491,0.0007454423,0.0001418448],"domain_scores_gemma":[0.991405,0.00359151,0.0005254441,0.00171194,0.002526224,0.0002398261],"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":[0.002052996,0.004721568,0.03219249,0.00686598,0.0006903075,0.002797775,0.001411851,0.2308778,0.08005082,0.01861655,0.2109765,0.4087454],"study_design_scores_gemma":[0.001209145,0.002642853,0.04090546,0.0007086412,0.0003403932,0.002473261,0.001424895,0.5931824,0.148073,0.01680985,0.1919292,0.0003009967],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4540379,0.002490315,0.3190277,0.001936654,0.000780927,0.005463921,0.1635479,0.03778136,0.01493336],"genre_scores_gemma":[0.2790783,0.000796911,0.354875,0.0005381948,0.00009465767,0.004302068,0.3554243,0.001282154,0.003608281],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004492149,"threshold_uncertainty_score":0.014759,"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."}}