{"id":"W2557589170","doi":"10.1145/3015022.3015024","title":"A Position-Based Method for the Extraction of Financial Information in PDF Documents","year":2016,"lang":"en","type":"article","venue":"","topic":"Mathematics, Computing, and Information Processing","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Computer science; Heuristics; Table (database); Context (archaeology); Restructuring; Process (computing); Information extraction; Information retrieval; Position (finance); Order (exchange); General partnership; Benchmark (surveying); Data mining; Data science; Finance","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006873923,0.00005233615,0.00007235109,0.000110128,0.00007326976,0.00007222582,0.0002406655,0.00002968455,0.00005538805],"category_scores_gemma":[0.0002146517,0.00002888021,0.00003516476,0.0001448683,0.00001088537,0.002004643,0.00002660154,0.00002596021,0.00003594493],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003146184,"about_ca_system_score_gemma":0.00009092842,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000134508,"about_ca_topic_score_gemma":0.000004100136,"domain_scores_codex":[0.9993144,0.00001864602,0.0003698034,0.00005450134,0.0001460848,0.0000965373],"domain_scores_gemma":[0.9989838,0.000460517,0.0002536394,0.000148584,0.0001389805,0.00001445707],"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":[0.00004299788,0.00008586612,0.0002056059,0.0002758754,0.000007840827,1.047793e-7,0.002787145,0.002537298,0.0009680829,0.2505276,0.003918533,0.7386431],"study_design_scores_gemma":[0.0006664434,0.00003738958,0.001073625,0.00007527565,0.000002396203,0.00000195071,0.00002779235,0.9683422,0.0110261,0.01567492,0.003004651,0.00006723677],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000932514,0.000002846941,0.9947301,0.000844398,0.0001386643,0.0002018562,8.744716e-7,0.0000273314,0.003121399],"genre_scores_gemma":[0.4275663,0.000002232124,0.5710614,0.001050464,0.00002529707,0.00004121961,0.000001930841,0.000001978241,0.0002491841],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9658049,"threshold_uncertainty_score":0.1453318,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01136375061371595,"score_gpt":0.2916578617110134,"score_spread":0.2802941110972974,"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."}}