{"id":"W4385607400","doi":"10.1145/3608114","title":"Robust OCR Pipeline for Automated Digitization of Mother and Child Protection Cards in India","year":2023,"lang":"en","type":"article","venue":"ACM Journal on Computing and Sustainable Societies","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Biotechnology Industry Research Assistance Council; Ministry of Electronics and Information technology; Indian Institute of Technology Delhi; Bill and Melinda Gates Foundation","keywords":"Computer science; Digitization; Pipeline (software); Artificial intelligence; Optical character recognition; Computer vision; Computer security; Image (mathematics)","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0008902643,0.0001000357,0.0001694628,0.0002125305,0.0003403817,0.0001672734,0.000177136,0.00006469493,2.400658e-7],"category_scores_gemma":[0.0004142556,0.00008766183,0.00004020137,0.0005481728,0.00004992615,0.0003573337,0.0001871724,0.0001868507,1.23438e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005234526,"about_ca_system_score_gemma":0.000045963,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006139316,"about_ca_topic_score_gemma":1.224224e-7,"domain_scores_codex":[0.9991157,0.00005573798,0.0002383742,0.0001674941,0.000145413,0.0002772691],"domain_scores_gemma":[0.9993436,0.0001354919,0.0001553194,0.0001238761,0.0002038281,0.00003787638],"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":[0.0004158989,0.0004653325,0.01126226,0.003941,0.0002070882,0.0002504191,0.0315247,0.1032228,0.0006710525,0.08013805,0.04258916,0.7253122],"study_design_scores_gemma":[0.001386396,0.0006163876,0.01151359,0.0004864534,0.000007921319,0.00008571454,0.005213387,0.9200352,0.003729182,0.05438423,0.002243922,0.0002976256],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04595863,0.0003812168,0.9510443,0.001268864,0.00006390295,0.000660094,0.000001222653,0.0004193908,0.0002023878],"genre_scores_gemma":[0.981079,0.0003608617,0.01777788,0.0001426882,0.00009097569,0.00001818697,0.000001910391,0.00001682605,0.0005116112],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9351205,"threshold_uncertainty_score":0.3574746,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01844732457606583,"score_gpt":0.2838287740640956,"score_spread":0.2653814494880297,"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."}}