{"id":"W3146762582","doi":"10.18653/v1/2022.nlpcss-1.19","title":"OLALA: Object-Level Active Learning for Efficient Document Layout Annotation","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Harvard Data Science Initiative, Harvard University; Harvard Catalyst; National Science Foundation","keywords":"Annotation; Computer science; Automatic image annotation; Artificial intelligence; Object (grammar); Information retrieval; Process (computing); Active learning (machine learning); Image retrieval; Machine learning; Image (mathematics); Pattern recognition (psychology)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002530247,0.001591063,0.001428215,0.001301645,0.0005672773,0.002224604,0.004532042,0.002703807,0.004801693],"category_scores_gemma":[0.006612937,0.0008878705,0.001084808,0.001374184,0.001229408,0.002780219,0.002848066,0.003561683,0.004011554],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009105079,"about_ca_system_score_gemma":0.0008915616,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002557938,"about_ca_topic_score_gemma":0.005021572,"domain_scores_codex":[0.9986089,0.0004326298,0.00007892175,0.0003442701,0.0004302873,0.0001049374],"domain_scores_gemma":[0.9968315,0.00181176,0.0002146388,0.0005086631,0.0005047503,0.0001287272],"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":[0.0004370397,0.0003090343,0.0007120438,0.0003382409,0.0001354361,0.0001608773,0.0002549118,0.20938,0.02725879,0.01099521,0.01491166,0.7351067],"study_design_scores_gemma":[0.00001571745,0.00002518864,0.00007457506,0.000008713334,0.000006178779,0.00002630165,0.00001404115,0.986388,0.005906613,0.005764286,0.0017607,0.000009703153],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002071602,0.0001482359,0.9925417,0.00009099174,0.00003342394,0.00004040411,0.0001134773,0.00449126,0.000468895],"genre_scores_gemma":[0.1538926,0.0003717981,0.8334287,0.000578957,0.0001419811,0.0005181376,0.001888811,0.001478284,0.007700696],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004801693,"threshold_uncertainty_score":0.01606327,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0334919703407659,"score_gpt":0.3054129292682622,"score_spread":0.2719209589274963,"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."}}