{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":43,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":43,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12","author_layer_release":"2026-06-26"},"query_hash":"cea167b9e56d","filters":{"venue":"International Journal on Document Analysis and Recognition (IJDAR)"}},"results":[{"id":"W2031071334","doi":"10.1007/s10032-011-0174-4","title":"Recognition and retrieval of mathematical expressions","year":2011,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":287,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Search engine indexing; Information retrieval; Relevance (law); Human–computer information retrieval; Image retrieval; Normalization (sociology); Document retrieval; Key (lock); Optical character recognition; Graphics; Relevance feedback; Notation; Artificial intelligence; Pattern recognition (psychology); Search engine; Image (mathematics); Mathematics","authors":[{"name":"Richard Zanibbi","is_ca":false},{"name":"Dorothea Blostein","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04133708286574984,"gpt":0.2874709149178449,"spread":0.246133832052095,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007521482,0.000175839,0.0003150802,0.001075836,0.0001201377,0.0002685564,0.0003812852,0.0001009534,0.001457274],"category_scores_gemma":[0.0001485314,0.0001417623,0.0002288896,0.0004244372,0.00009670984,0.0007992024,0.0001513341,0.0002545156,0.00005661203],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004250039,"about_ca_system_score_gemma":0.00002840716,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000140593,"about_ca_topic_score_gemma":0.000002553724,"domain_scores_codex":[0.9980052,0.0001539113,0.000685522,0.0003206846,0.0006672787,0.0001673642],"domain_scores_gemma":[0.9983554,0.0001544795,0.0004835896,0.0001675765,0.0006474913,0.0001914094],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0005052387,0.001291863,0.002543117,0.00004777978,0.00434081,0.000207075,0.003531263,0.000001652355,0.006637692,0.007426254,0.0006401884,0.9728271],"study_design_scores_gemma":[0.001945627,0.0008834123,0.01032626,0.0007325073,0.0009675898,0.0006619008,0.0003554267,0.001427643,0.1692885,0.8122157,0.0004858614,0.0007095958],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.634381,0.0001234062,0.3581386,0.0007649934,0.0003582237,0.0002156329,0.0000561357,0.0001140133,0.00584805],"genre_scores_gemma":[0.9480997,0.001330654,0.04992367,0.000321139,0.00011802,0.00001102489,0.00004414204,0.00001075758,0.0001409165],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9721175,"threshold_uncertainty_score":0.9994555,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2092772700","doi":"10.1007/s10032-004-0120-9","title":"A survey of table recognition","year":2004,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":282,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"","keywords":"Table (database); Computer science; Decision table; Feature (linguistics); Presentation (obstetrics); Data mining; Artificial intelligence; Machine learning","authors":[{"name":"Richard Zanibbi","is_ca":true},{"name":"Dorothea Blostein","is_ca":true},{"name":"JamesR. Cordy","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0307860651868092,"gpt":0.2944813659463421,"spread":0.2636953007595328,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009475324,0.0001279919,0.0002276496,0.0007844839,0.0001040542,0.0003938553,0.0004278944,0.00006178195,0.0002626562],"category_scores_gemma":[0.0001345045,0.0001050916,0.0001714424,0.0009054731,0.00004685831,0.000705357,0.00006789594,0.0001775697,0.00004229663],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001107954,"about_ca_system_score_gemma":0.00007872116,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000238434,"about_ca_topic_score_gemma":0.00003807862,"domain_scores_codex":[0.9982841,0.0001225086,0.0005382645,0.0002532766,0.0006662561,0.0001356171],"domain_scores_gemma":[0.9979508,0.00008920679,0.0004839656,0.0001459502,0.001227687,0.0001024101],"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":[0.0001926753,0.0007495169,0.006094517,0.00001249773,0.00268201,0.0000548949,0.000327774,0.00008615047,0.002691629,0.003435523,0.0003249549,0.9833478],"study_design_scores_gemma":[0.005968244,0.001565753,0.3218808,0.000658408,0.001049673,0.0003671465,0.0001778941,0.00456313,0.3749903,0.2839038,0.00339264,0.001482213],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1625601,0.0001728805,0.8330472,0.002162812,0.0004880828,0.000130959,0.00007189776,0.00007271497,0.001293397],"genre_scores_gemma":[0.9900427,0.00122073,0.007988664,0.0003499113,0.0000811511,0.000007209939,0.000140637,0.000005916825,0.0001630581],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9818656,"threshold_uncertainty_score":0.428551,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2098345386","doi":"10.1007/s10032-006-0020-2","title":"A survey of document image classification: problem statement, classifier architecture and performance evaluation","year":2006,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":174,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"Xerox Foundation","keywords":"Computer science; Classifier (UML); Document classification; Contextual image classification; Artificial intelligence; Pattern recognition (psychology); Problem statement; Ambiguity; Information retrieval; Machine learning; Data mining; Image (mathematics)","authors":[{"name":"Nawei Chen","is_ca":true},{"name":"Dorothea Blostein","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02727027337698614,"gpt":0.3066844968063903,"spread":0.2794142234294041,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002610092,0.0002138797,0.0002987199,0.001076402,0.0001648205,0.0007244788,0.0003797886,0.00007766073,0.0003577771],"category_scores_gemma":[0.00005773034,0.0001759364,0.000141063,0.0006210809,0.00009395547,0.0009583492,0.000106911,0.0002526276,0.00001362313],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001690418,"about_ca_system_score_gemma":0.00008876112,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001638734,"about_ca_topic_score_gemma":0.0001310962,"domain_scores_codex":[0.9967981,0.00041323,0.0009287193,0.0004224125,0.001241011,0.0001965485],"domain_scores_gemma":[0.9970593,0.0001447507,0.0008287504,0.0001952438,0.00166441,0.000107586],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001452085,0.0003145308,0.03312308,0.00002414911,0.001262804,0.00001128509,0.00022661,0.000110431,0.001262075,0.001153215,0.0009167804,0.9614499],"study_design_scores_gemma":[0.00273554,0.0007365838,0.8932781,0.0003155858,0.0006942907,0.0001237344,0.00007572821,0.02849116,0.01416995,0.05713075,0.001566541,0.000682054],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7562963,0.0002298146,0.2370886,0.0025974,0.0002655585,0.0005007182,0.00006072151,0.00007015313,0.002890733],"genre_scores_gemma":[0.9795442,0.0009252122,0.01871325,0.000162928,0.0001051626,0.00005317228,0.0002841387,0.000009714541,0.0002022721],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9607678,"threshold_uncertainty_score":0.7174479,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2150428256","doi":"10.1007/s10032-011-0180-6","title":"Multi-feature extraction and selection in writer-independent off-line signature verification","year":2011,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":98,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Computer science; Pattern recognition (psychology); Feature selection; Feature extraction; Artificial intelligence; Signature (topology); Data mining; Feature (linguistics); Boosting (machine learning); Feature vector; Mathematics","authors":[{"name":"Dominique Rivard","is_ca":true},{"name":"Éric Granger","is_ca":true},{"name":"Robert Sabourin","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02541672727111226,"gpt":0.2942723971238677,"spread":0.2688556698527554,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007547585,0.0002121949,0.000243762,0.001608479,0.0001415997,0.0005397794,0.0003196892,0.0001909035,0.0003053468],"category_scores_gemma":[0.0000564632,0.00018734,0.0001549807,0.000633006,0.0000346758,0.001343739,0.00006782774,0.0005917721,0.00002117329],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001764871,"about_ca_system_score_gemma":0.00003185084,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005975685,"about_ca_topic_score_gemma":0.0001516326,"domain_scores_codex":[0.998065,0.0001854421,0.0005074029,0.0004710873,0.0005808507,0.0001901976],"domain_scores_gemma":[0.9987674,0.00005863259,0.0004167268,0.0001030705,0.0005144267,0.0001397875],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0002722325,0.0008329403,0.01102168,0.00001215577,0.001160114,0.000147644,0.001186774,0.00003396205,0.01236586,0.0007558391,0.0003263041,0.9718845],"study_design_scores_gemma":[0.007325678,0.001585023,0.738387,0.0007271666,0.001059544,0.001906107,0.0006138367,0.08070202,0.1203266,0.0398138,0.00562202,0.001931143],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4860411,0.0004636849,0.5096648,0.002006303,0.0005843989,0.000366829,0.00002190044,0.0001710737,0.0006798239],"genre_scores_gemma":[0.9506407,0.00249472,0.04586954,0.0004255404,0.0001722556,0.00002807442,0.00005203605,0.00001121615,0.0003058584],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9699534,"threshold_uncertainty_score":0.7639504,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1978799108","doi":"10.1007/s10032-012-0184-x","title":"A new approach for recognizing handwritten mathematics using relational grammars and fuzzy sets","year":2012,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":96,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Parsing; Computer science; Artificial intelligence; Set (abstract data type); Natural language processing; Rule-based machine translation; Ambiguity; S-attributed grammar; Similarity (geometry); Fuzzy logic; Interpretation (philosophy); Programming language; Image (mathematics)","authors":[{"name":"Scott MacLean","is_ca":true},{"name":"George Labahn","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0435284099296081,"gpt":0.3182998786613794,"spread":0.2747714687317713,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009027748,0.0001641909,0.0002255424,0.000674525,0.000220124,0.0007032399,0.0002819804,0.00008673446,0.00004918009],"category_scores_gemma":[0.0001182363,0.0001324545,0.0001680422,0.0003137473,0.00002523701,0.001229435,0.0001121811,0.0002177339,0.000003536442],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001047851,"about_ca_system_score_gemma":0.00004080544,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001773134,"about_ca_topic_score_gemma":0.000002021278,"domain_scores_codex":[0.998537,0.00005421435,0.0004180503,0.0002532441,0.0005203552,0.000217131],"domain_scores_gemma":[0.9988362,0.0001520836,0.0003871911,0.0001030278,0.0003264358,0.0001950316],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001438733,0.0004347127,0.00684798,0.00006754966,0.003974101,0.00002059862,0.002588431,0.0001461011,0.001433158,0.04981213,0.00155705,0.9329743],"study_design_scores_gemma":[0.003142258,0.0002358092,0.001610125,0.0005339147,0.001981594,0.001609375,0.0004148673,0.1489361,0.004776367,0.8333358,0.002142276,0.001281617],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01483705,0.0007962741,0.9829776,0.000740334,0.0002400298,0.0001341236,0.00001110728,0.00005138874,0.0002121141],"genre_scores_gemma":[0.1229388,0.0001731633,0.8759962,0.000281511,0.0003437827,0.000007853337,0.00006442109,0.00001025368,0.0001839194],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9316927,"threshold_uncertainty_score":0.6781358,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1965285802","doi":"10.1007/s10032-008-0076-2","title":"Low quality document image modeling and enhancement","year":2009,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":75,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"École de Technologie Supérieure","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Computer science; Degradation (telecommunications); Shadow (psychology); Diffusion; Image restoration; Image enhancement; Computer vision; Artificial intelligence; Process (computing); Image (mathematics); Image processing; Physics","authors":[{"name":"Reza Farrahi Moghaddam","is_ca":true},{"name":"Mohamed Cheriet","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01485540075618043,"gpt":0.2952721653155663,"spread":0.2804167645593859,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007732154,0.0001808504,0.0002531139,0.000639223,0.0001407484,0.001477492,0.0002993817,0.00004693684,0.0001197618],"category_scores_gemma":[0.00006815047,0.0001501522,0.000187455,0.0003065568,0.00003354307,0.00144688,0.00008654938,0.0001993057,0.00003508867],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001567764,"about_ca_system_score_gemma":0.00002574236,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002350124,"about_ca_topic_score_gemma":0.00001107997,"domain_scores_codex":[0.9977928,0.00008798148,0.0006131858,0.0003807801,0.0009246952,0.0002005347],"domain_scores_gemma":[0.9988834,0.00005075967,0.0003130138,0.0001563548,0.000400982,0.0001955423],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00008954907,0.0002220126,0.0001461723,0.000004626619,0.0009239389,0.00005156055,0.000331154,0.0004070768,0.001021793,0.002870098,0.0001535562,0.9937785],"study_design_scores_gemma":[0.006639283,0.002693911,0.009217881,0.0007083993,0.001064501,0.0005414179,0.0005042894,0.2417656,0.055567,0.676715,0.002506517,0.002076171],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5549504,0.00008447279,0.43853,0.00387128,0.0007529883,0.0001000593,0.000003804848,0.00004036312,0.001666627],"genre_scores_gemma":[0.9906313,0.0007871632,0.00715433,0.000962134,0.0002225096,0.000005918643,0.00002214489,0.000004579233,0.0002098656],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9917023,"threshold_uncertainty_score":0.999559,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2795776870","doi":"10.1007/s10032-018-0301-6","title":"Fixed-sized representation learning from offline handwritten signatures of different sizes","year":2018,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":66,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"École de Technologie Supérieure","funders":"Fonds de recherche du Québec – Nature et technologies; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Signature (topology); Feature (linguistics); Convolutional neural network; Feature learning; Pyramid (geometry); Representation (politics); Pattern recognition (psychology); Constraint (computer-aided design)","authors":[],"retraction":null,"screen_n_in":null,"score":{"opus":0.01616332556073162,"gpt":0.2904750571368058,"spread":0.2743117315760741,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004729771,0.0002188221,0.0004175995,0.001037432,0.0001990957,0.000588419,0.0005660299,0.0001107094,0.001292129],"category_scores_gemma":[0.0002287839,0.000172444,0.0003588441,0.0005049712,0.0001071486,0.0006823466,0.000167048,0.0003580536,0.00003658086],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000765126,"about_ca_system_score_gemma":0.00003063058,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009861599,"about_ca_topic_score_gemma":0.00005075985,"domain_scores_codex":[0.9973561,0.0002980607,0.0007622541,0.0004320775,0.0009642543,0.000187317],"domain_scores_gemma":[0.9974634,0.0003527215,0.0007348121,0.0001974411,0.001111015,0.0001405963],"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":[0.0006538403,0.0007249606,0.01949545,0.00001172848,0.007414434,0.00009149003,0.001611087,0.0001077725,0.02941622,0.001672077,0.001896436,0.9369045],"study_design_scores_gemma":[0.006221712,0.002125654,0.08920935,0.0008012642,0.001765755,0.00009035716,0.0005110591,0.03219854,0.6790616,0.1836071,0.003120504,0.001287112],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6953447,0.0001427626,0.3003482,0.002108641,0.0006479166,0.0001600339,0.00002683529,0.0001219769,0.001098909],"genre_scores_gemma":[0.9886348,0.0009012459,0.008956488,0.0004068644,0.0005823358,0.0000132145,0.0001757049,0.00001120136,0.0003181658],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9356174,"threshold_uncertainty_score":0.9996209,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2120888827","doi":"10.1007/s10032-011-0166-4","title":"Writer verification using texture-based features","year":2011,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":64,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"École de Technologie Supérieure","funders":"Conselho Nacional de Desenvolvimento Científico e Tecnológico","keywords":"Computer science; Classifier (UML); Word error rate; Artificial intelligence; Pattern recognition (psychology); Texture (cosmology); Segmentation; Representation (politics); Writing style; Set (abstract data type); Image (mathematics)","authors":[{"name":"Regiane Kowalek Hanusiak","is_ca":false},{"name":"Luiz S. Oliveira","is_ca":false},{"name":"Edson Justino","is_ca":false},{"name":"Robert Sabourin","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03427482938487292,"gpt":0.2878837232854027,"spread":0.2536088939005298,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005762335,0.0002059458,0.0002345456,0.001377039,0.0001990901,0.000799962,0.0006193857,0.0001077889,0.0009355406],"category_scores_gemma":[0.0000472561,0.0001712707,0.0003122467,0.0005489969,0.00005400622,0.000901935,0.00007060834,0.000303831,0.00005598965],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001321927,"about_ca_system_score_gemma":0.0000527575,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005626146,"about_ca_topic_score_gemma":0.00001393633,"domain_scores_codex":[0.9980339,0.000160043,0.0005021849,0.0003884329,0.0007148439,0.0002006137],"domain_scores_gemma":[0.9984385,0.00006190425,0.000425028,0.0002350991,0.0006765689,0.0001628872],"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":[0.0002688821,0.0007797376,0.005864519,0.00001294456,0.003237613,0.0002404552,0.001049545,0.00007527752,0.00296804,0.005307234,0.001334501,0.9788613],"study_design_scores_gemma":[0.008683669,0.002167348,0.1784246,0.001299327,0.004085522,0.001903395,0.0005373861,0.07787878,0.4130346,0.2882066,0.01944849,0.004330218],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1071933,0.0001329038,0.887013,0.001249031,0.0007176076,0.0001808018,0.00002223539,0.0001671647,0.003324055],"genre_scores_gemma":[0.9371278,0.000223783,0.0605906,0.001563726,0.0002364651,0.00001443286,0.00006175961,0.00001225429,0.0001691782],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9745311,"threshold_uncertainty_score":0.9999778,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2107835247","doi":"10.1007/s10032-011-0157-5","title":"A local linear level set method for the binarization of degraded historical document images","year":2011,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":59,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"École de Technologie Supérieure","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Active contour model; Historical document; Set (abstract data type); Segmentation; Curvature; Computer vision; Probabilistic logic; Image (mathematics); Pattern recognition (psychology); Pixel; Image segmentation; Level set (data structures); Mathematics","authors":[{"name":"David Rivest‐Hénault","is_ca":true},{"name":"Reza Farrahi Moghaddam","is_ca":true},{"name":"Mohamed Cheriet","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0645111069674379,"gpt":0.3269907466057523,"spread":0.2624796396383144,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001295014,0.0001845009,0.0002940833,0.0008156978,0.000186396,0.0002175266,0.000653044,0.00008417325,0.0002086796],"category_scores_gemma":[0.0001157797,0.00012698,0.0004114312,0.0004832958,0.00005772819,0.0004600523,0.000116342,0.00020655,0.000008653644],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000240059,"about_ca_system_score_gemma":0.00005665453,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001580659,"about_ca_topic_score_gemma":0.00001891089,"domain_scores_codex":[0.9979055,0.000198746,0.0006978569,0.0003235927,0.0006972343,0.0001770528],"domain_scores_gemma":[0.9978723,0.0002598038,0.0005844597,0.0001968241,0.0009738021,0.0001128079],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003271741,0.0004267794,0.0007689941,0.00001762955,0.003748052,0.00002710056,0.001401946,0.000117145,0.0007634278,0.005301673,0.002342326,0.9847578],"study_design_scores_gemma":[0.008404355,0.00447353,0.01957409,0.0006918701,0.005467342,0.0008042253,0.001066531,0.1112003,0.4069467,0.4079522,0.03124209,0.002176812],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00246502,0.0001374541,0.9943182,0.002220592,0.0004156373,0.0002185435,0.0000302119,0.00003905779,0.0001552459],"genre_scores_gemma":[0.6910412,0.001036284,0.3063052,0.0007029576,0.0002362222,0.00008666755,0.00006568118,0.00001648228,0.0005092889],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.982581,"threshold_uncertainty_score":0.5178093,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2050738804","doi":"10.1007/s10032-009-0107-7","title":"Distance-based classification of handwritten symbols","year":2010,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"Convex hull; Mathematics; Dimension (graph theory); Pattern recognition (psychology); k-nearest neighbors algorithm; Euclidean distance; Distance measures; Support vector machine; Matching (statistics); Regular polygon; Algorithm; Computer science; Artificial intelligence; Combinatorics; Geometry; Statistics","authors":[{"name":"Oleg Golubitsky","is_ca":true},{"name":"Stephen M. Watt","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01473643662366251,"gpt":0.2819775161814186,"spread":0.2672410795577561,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005740627,0.0001261263,0.0002028925,0.0007068557,0.0001143608,0.000451657,0.0005498212,0.00007439801,0.0002913999],"category_scores_gemma":[0.00007687239,0.00009950405,0.0002385181,0.0005212924,0.00007775392,0.0004892791,0.00004077048,0.0002797298,0.000017891],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004624419,"about_ca_system_score_gemma":0.0000562815,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001046241,"about_ca_topic_score_gemma":0.00001086451,"domain_scores_codex":[0.9983491,0.00006894509,0.0005122108,0.0002562921,0.0006933308,0.0001201183],"domain_scores_gemma":[0.9982654,0.0000996841,0.0005148352,0.0002179237,0.0007953742,0.0001067473],"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":[0.0001810743,0.0006938067,0.01670936,0.00001772962,0.001583496,0.00002896749,0.0002201068,0.00001604676,0.07410654,0.06130179,0.0005625148,0.8445786],"study_design_scores_gemma":[0.003578209,0.0007119065,0.2678179,0.000317215,0.001018544,0.0001288134,0.0001859527,0.06278481,0.5262715,0.1095676,0.0264051,0.001212469],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1082586,0.00003810253,0.8845618,0.005084309,0.0005457238,0.0001027293,0.00001610691,0.00006005219,0.001332596],"genre_scores_gemma":[0.9892564,0.0001830044,0.009859289,0.0002857599,0.0001425101,0.00001114365,0.00004609358,0.000005339984,0.0002104987],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8809977,"threshold_uncertainty_score":0.4355339,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2122160657","doi":"10.1007/s10032-005-0013-6","title":"Feature selection for ensembles applied to handwriting recognition","year":2006,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Artificial intelligence; Random subspace method; Computer science; Feature selection; Pattern recognition (psychology); Boosting (machine learning); Perceptron; Machine learning; Robustness (evolution); Cascading classifiers; Feature (linguistics); Artificial neural network; Hidden Markov model; Classifier (UML)","authors":[{"name":"Luiz S. Oliveira","is_ca":false},{"name":"Marisa Morita","is_ca":true},{"name":"Robert Sabourin","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01284765546056195,"gpt":0.2665302875074339,"spread":0.253682632046872,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003461179,0.0001575735,0.0001908274,0.0006124402,0.0003572481,0.0009661322,0.0002741584,0.00006702277,0.0000555016],"category_scores_gemma":[0.00001853039,0.0001366257,0.0002106257,0.0006193311,0.00001364622,0.0003486935,0.00004795803,0.0001729101,0.00003177794],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008801618,"about_ca_system_score_gemma":0.00001847649,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002337576,"about_ca_topic_score_gemma":0.00007395938,"domain_scores_codex":[0.9986486,0.0000368868,0.0003331574,0.000365598,0.0004115197,0.0002042017],"domain_scores_gemma":[0.9989246,0.0001253964,0.0002630386,0.00008974129,0.0004838877,0.000113334],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001868035,0.0002707618,0.0009506741,0.000008696067,0.001053931,0.000008746588,0.00009812791,0.003815573,0.007474333,0.01175284,0.01839929,0.9559802],"study_design_scores_gemma":[0.00848492,0.001438066,0.02773948,0.0006351945,0.002447605,0.0006777909,0.000341174,0.1008721,0.1078853,0.5571783,0.1891536,0.003146529],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1907028,0.00005204637,0.7923219,0.01464875,0.0004428521,0.0003780577,0.00003701053,0.00008857426,0.001328064],"genre_scores_gemma":[0.9579191,0.0001375664,0.0379536,0.001524732,0.001391725,0.0001146583,0.0002467581,0.00001254912,0.0006993163],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9528337,"threshold_uncertainty_score":0.9316435,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1970571079","doi":"10.1007/s10032-002-0085-5","title":"The recognition of handwritten numeral strings using a two-stage HMM-based method","year":2003,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University; École de Technologie Supérieure; Hôpital Notre-Dame; Université du Québec à Montréal","funders":"","keywords":"Segmentation; Numeral system; Pattern recognition (psychology); Computer science; Digit recognition; Artificial intelligence; Speech recognition; Classifier (UML); Intelligent word recognition; Hidden Markov model; Speech segmentation; String (physics); Intelligent character recognition; Mathematics; Character recognition; Artificial neural network","authors":[{"name":"Alceu de Souza Britto","is_ca":false},{"name":"Robert Sabourin","is_ca":true},{"name":"Flávio Bortolozzi","is_ca":false},{"name":"Ching Y. Suen","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02642962544933657,"gpt":0.3273302003287046,"spread":0.3009005748793681,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002397192,0.000259615,0.0003751431,0.001124185,0.0004182208,0.001016578,0.0006166101,0.00009318754,0.0004376038],"category_scores_gemma":[0.0002401341,0.0001935216,0.0004920447,0.0008534028,0.00008969552,0.0007867902,0.0000767481,0.0003872435,0.00001952229],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001713978,"about_ca_system_score_gemma":0.0001258157,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009321869,"about_ca_topic_score_gemma":0.00003119259,"domain_scores_codex":[0.9966697,0.000627075,0.0009289163,0.0004220691,0.001052031,0.0003001887],"domain_scores_gemma":[0.9970107,0.0004751619,0.0009070365,0.0002556808,0.001175178,0.0001762385],"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":[0.0002719,0.000535102,0.002558812,0.00002181244,0.004232529,0.0001180211,0.0003472778,0.0008152342,0.004921615,0.007416404,0.000293163,0.9784681],"study_design_scores_gemma":[0.01067929,0.0013985,0.002596983,0.001094403,0.002732142,0.0008561045,0.0007407789,0.141128,0.5740144,0.2447503,0.0177584,0.002250673],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1296175,0.0001285256,0.8672192,0.001044187,0.0004885789,0.0002143549,0.00004131033,0.00007006288,0.001176309],"genre_scores_gemma":[0.8251649,0.000578528,0.1727367,0.000915552,0.0001903421,0.00003092281,0.00006321827,0.00002300123,0.0002968388],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9762174,"threshold_uncertainty_score":0.9802887,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1977202248","doi":"10.1007/s10032-010-0118-4","title":"Grammar-based techniques for creating ground-truthed sketch corpora","year":2010,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Sketch; Computer science; Natural language processing; Template; Artificial intelligence; Grammar; Sketch recognition; Annotation; Domain (mathematical analysis); Matching (statistics); Ground truth; Programming language; Linguistics; Algorithm","authors":[{"name":"Scott MacLean","is_ca":true},{"name":"George Labahn","is_ca":true},{"name":"Edward Lank","is_ca":true},{"name":"Mirette Marzouk","is_ca":true},{"name":"David Tausky","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01460440879270711,"gpt":0.2906842237893361,"spread":0.276079814996629,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001362532,0.0002664071,0.0003555993,0.001427286,0.0003554518,0.001605385,0.0007801151,0.0001562864,0.000462079],"category_scores_gemma":[0.0002210262,0.0002251745,0.000504142,0.0005419625,0.00007950753,0.0008468218,0.00009352712,0.0004950054,0.00002324856],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009840934,"about_ca_system_score_gemma":0.00008266779,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005147489,"about_ca_topic_score_gemma":0.00006198321,"domain_scores_codex":[0.9976018,0.0001132324,0.000727572,0.0004845441,0.000791952,0.0002808654],"domain_scores_gemma":[0.9972453,0.0003778436,0.0006797228,0.0002598284,0.001223465,0.0002138227],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000136319,0.0003672923,0.002113721,0.00001285335,0.001378153,0.00005384174,0.0001530131,0.000006757163,0.005572138,0.008426438,0.0007035965,0.9810759],"study_design_scores_gemma":[0.00514888,0.001932615,0.009715371,0.0005506297,0.001722387,0.0006270172,0.000201329,0.03710374,0.3406563,0.5677398,0.03229599,0.002305891],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1375898,0.00001972081,0.8563049,0.003095828,0.0007885814,0.0003658862,0.00004322981,0.0003089543,0.001483019],"genre_scores_gemma":[0.8092663,0.0001211161,0.1881485,0.001318472,0.0005750312,0.0001258148,0.0001668903,0.00002047084,0.0002573234],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.97877,"threshold_uncertainty_score":0.9994311,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2009946426","doi":"10.1007/s10032-003-0113-0","title":"Lexicon-driven HMM decoding for large vocabulary handwriting recognition with multiple character models","year":2003,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University; École de Technologie Supérieure","funders":"Conselho Nacional de Desenvolvimento Científico e Tecnológico","keywords":"Computer science; Bigram; Lexicon; Hidden Markov model; Speech recognition; Vocabulary; Artificial intelligence; Word recognition; Handwriting recognition; Natural language processing; Word (group theory); Segmentation; Optical character recognition; Tree (set theory); Decoding methods; Handwriting; Pattern recognition (psychology); Feature extraction; Linguistics; Mathematics; Algorithm","authors":[{"name":"Alessandro L. Koerich","is_ca":false},{"name":"Robert Sabourin","is_ca":true},{"name":"Ching Y. Suen","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02501651241459563,"gpt":0.2759748070783409,"spread":0.2509582946637453,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001176099,0.0003189747,0.0004156873,0.001267094,0.0004532217,0.001288791,0.0004408445,0.0001324331,0.0003047548],"category_scores_gemma":[0.0001584213,0.0002680748,0.0003949512,0.0004923626,0.00003761649,0.002087288,0.00007275981,0.0003554187,0.00003611584],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001673799,"about_ca_system_score_gemma":0.00008444432,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001059983,"about_ca_topic_score_gemma":0.00004519608,"domain_scores_codex":[0.9972438,0.0002132972,0.0007478267,0.0006025215,0.0007715062,0.0004210166],"domain_scores_gemma":[0.9974425,0.0003266168,0.0006145889,0.0002029297,0.001177291,0.0002360045],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0007757914,0.001574928,0.01318333,0.00007363849,0.009349973,0.0003504897,0.001708252,0.0004594961,0.002696313,0.01988896,0.00117479,0.948764],"study_design_scores_gemma":[0.02172159,0.002779191,0.003724408,0.002570496,0.003120809,0.002256643,0.001295576,0.3908651,0.1344539,0.4205827,0.01246253,0.004167031],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1342117,0.00007282832,0.8628758,0.000909699,0.0003424365,0.0003572784,0.00009182437,0.0001275857,0.001010915],"genre_scores_gemma":[0.8853437,0.0006228443,0.1118416,0.001265231,0.0002960353,0.0001267096,0.0003113504,0.00002851395,0.0001639616],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.944597,"threshold_uncertainty_score":0.9999772,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1899315810","doi":"10.1007/s10032-015-0246-y","title":"Machine-assisted authentication of paper currency: an experiment on Indian banknotes","year":2015,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Currency Recognition and Detection","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Currency; Authentication (law); Computer science; Banknote; Computer security; Artificial intelligence; Economics; Monetary economics","authors":[{"name":"Ankush Roy","is_ca":true},{"name":"Biswajit Halder","is_ca":false},{"name":"Utpal Garain","is_ca":false},{"name":"David Doermann","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0396712521175821,"gpt":0.3219999670659646,"spread":0.2823287149483825,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006318645,0.0001813253,0.0002381382,0.001180471,0.0001173319,0.0004429769,0.0003802742,0.00007078551,0.0004889267],"category_scores_gemma":[0.00008618997,0.0001484155,0.0002223775,0.0005166551,0.00004043561,0.0009326651,0.00005710812,0.0002172432,0.0000691577],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001370354,"about_ca_system_score_gemma":0.00006560797,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005207237,"about_ca_topic_score_gemma":0.00002670753,"domain_scores_codex":[0.9977459,0.0002071106,0.0005909274,0.0003460723,0.0009580979,0.0001518519],"domain_scores_gemma":[0.9982672,0.00006927031,0.0004810671,0.0002092862,0.0006996115,0.0002735941],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002499079,0.0009845007,0.001903921,0.000006274236,0.001223762,0.00002992238,0.002165629,0.0001436299,0.001171298,0.003670823,0.0002728038,0.9881775],"study_design_scores_gemma":[0.02910131,0.01359471,0.2110827,0.001900192,0.003845121,0.001646337,0.00439001,0.1409441,0.1732363,0.3741472,0.04063135,0.005480635],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9200472,0.0003728723,0.06790106,0.003944889,0.003460987,0.0002834461,0.00006683973,0.000122022,0.00380072],"genre_scores_gemma":[0.9968782,0.0002501681,0.002050553,0.0003644648,0.0001974383,0.00001460793,0.0001390489,0.000007340713,0.00009818237],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9826969,"threshold_uncertainty_score":0.6052207,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1971709796","doi":"10.1007/s100320100056","title":"A generic method of cleaning and enhancing handwritten data from business forms","year":2001,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Montréal; École de Technologie Supérieure; Concordia University","funders":"","keywords":"Computer science; Handwriting; Thresholding; Artificial intelligence; Task (project management); Workload; Automation; Natural language processing; Image (mathematics)","authors":[{"name":"Xiangyun Ye","is_ca":true},{"name":"Mohamed Cheriet","is_ca":true},{"name":"Ching Y. Suen","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03368209746036197,"gpt":0.3181661943383481,"spread":0.2844840968779861,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001042484,0.0001875325,0.0003716398,0.0009540659,0.0001488584,0.000683229,0.000818025,0.00007745756,0.0003529322],"category_scores_gemma":[0.0001225707,0.0001518134,0.0001250837,0.0007396849,0.00004316598,0.001477266,0.0004265173,0.0002130005,0.00001212989],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005487302,"about_ca_system_score_gemma":0.00004093974,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001823909,"about_ca_topic_score_gemma":0.00009082353,"domain_scores_codex":[0.9978382,0.0001416492,0.0006829214,0.0004801575,0.0006753022,0.0001817825],"domain_scores_gemma":[0.9981058,0.0002256692,0.0005496759,0.00031519,0.0006645017,0.0001391281],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00008111388,0.0001381364,0.004224346,0.00000724807,0.001945075,0.00009606651,0.0003200741,0.00002481132,0.003745805,0.0002989729,0.0002228093,0.9888955],"study_design_scores_gemma":[0.01168577,0.001387558,0.2001925,0.003020129,0.006004191,0.004096183,0.002058103,0.2126752,0.160039,0.3759048,0.01897824,0.003958259],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1803822,0.0001928796,0.8175414,0.001031774,0.0001888503,0.00007467571,0.00004427888,0.00004468496,0.0004993466],"genre_scores_gemma":[0.8208362,0.004756052,0.1729186,0.000732114,0.0003182806,0.000008919226,0.0002934042,0.00001424296,0.0001222284],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9849373,"threshold_uncertainty_score":0.6588393,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2617973426","doi":"10.1007/s10032-017-0287-5","title":"A sigma-lognormal model-based approach to generating large synthetic online handwriting sample databases","year":2017,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Handwriting; Artificial intelligence; Set (abstract data type); Speech recognition; Scripting language; Sample (material); Test set; Natural language processing; Pattern recognition (psychology)","authors":[{"name":"Ujjwal Bhattacharya","is_ca":false},{"name":"Réjean Plamondon","is_ca":true},{"name":"Souvik Chowdhury","is_ca":false},{"name":"Pankaj Goyal","is_ca":false},{"name":"Swapan K. Parui","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04040810030770019,"gpt":0.3229824232304629,"spread":0.2825743229227627,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001231268,0.0002712814,0.000370191,0.00109636,0.001037586,0.002694173,0.001183919,0.0000688812,0.0001513939],"category_scores_gemma":[0.0005787194,0.0002357268,0.0003242427,0.0002532175,0.00005610547,0.001333773,0.0003882868,0.0003515624,0.00001023558],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001159172,"about_ca_system_score_gemma":0.00008359702,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008087722,"about_ca_topic_score_gemma":0.00008427817,"domain_scores_codex":[0.9972646,0.0001459691,0.0006805405,0.0006040022,0.0009380853,0.000366784],"domain_scores_gemma":[0.9976798,0.0001963752,0.0006344196,0.0004821604,0.0007070524,0.0003002041],"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":[0.0002025661,0.002424629,0.006387239,0.00004074901,0.002874963,0.0001716923,0.0006776872,0.03422096,0.001544264,0.007522837,0.001117594,0.9428148],"study_design_scores_gemma":[0.001153195,0.0001409724,0.0006585914,0.0002517973,0.0002899797,0.00007548901,0.00008532857,0.9849494,0.006434918,0.004456826,0.001004221,0.0004993102],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0598067,0.00003359517,0.937019,0.001698952,0.0002123874,0.0001606393,0.0002931628,0.00009163236,0.0006839494],"genre_scores_gemma":[0.7201712,0.0001048207,0.2772807,0.001682092,0.0003277072,0.00003212833,0.0003102653,0.00001366559,0.00007749445],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9507284,"threshold_uncertainty_score":0.9983411,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1977304445","doi":"10.1007/s10032-003-0114-z","title":"Segmentation and recognition of handwritten dates: an HMM-MLP hybrid approach","year":2003,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Hidden Markov model; Segmentation; Computer science; Artificial intelligence; Pattern recognition (psychology); Lexicon; Speech recognition; Market segmentation; Process (computing); DECIPHER","authors":[{"name":"Marisa Morita","is_ca":true},{"name":"Robert Sabourin","is_ca":true},{"name":"Flávio Bortolozzi","is_ca":false},{"name":"Ching Y. Suen","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02017753980924637,"gpt":0.2806059995565203,"spread":0.260428459747274,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001304892,0.0002606674,0.0003844112,0.001383833,0.0002004272,0.0008135538,0.0003932641,0.00009022578,0.0003606643],"category_scores_gemma":[0.0001039414,0.0002304168,0.0002169148,0.0005203728,0.00009253286,0.001835884,0.00007805687,0.0002880611,0.00001908651],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009318299,"about_ca_system_score_gemma":0.00004910335,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003641141,"about_ca_topic_score_gemma":0.000008797032,"domain_scores_codex":[0.9971769,0.0004036654,0.000807194,0.0005376553,0.0008449189,0.0002296314],"domain_scores_gemma":[0.9979575,0.0001174207,0.0006486931,0.0002181263,0.0008239168,0.0002343366],"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":[0.0001343842,0.0009181129,0.003207602,0.00003381486,0.002497446,0.00006078772,0.0008764735,0.00004136415,0.003324392,0.001967698,0.0004283852,0.9865096],"study_design_scores_gemma":[0.01082165,0.003505865,0.01217231,0.0008867252,0.00335784,0.003284947,0.002630965,0.02621519,0.498644,0.4313875,0.003983937,0.003109056],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5366094,0.000170798,0.4598084,0.0004046988,0.0003250287,0.0002790588,0.00007112967,0.00009580157,0.002235629],"genre_scores_gemma":[0.9252828,0.001878935,0.0715169,0.0005537316,0.000144146,0.00003909974,0.0004389989,0.00001732326,0.0001280856],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9834005,"threshold_uncertainty_score":0.9396125,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4205487349","doi":"10.1007/s10032-021-00391-3","title":"Segmentation for document layout analysis: not dead yet","year":2022,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Saskatchewan","funders":"Mitacs","keywords":"Computer science; Segmentation; Bounding overwatch; Minimum bounding box; Task (project management); Benchmarking; Annotation; Artificial intelligence; Object (grammar); Image segmentation; Document layout analysis; Pattern recognition (psychology); Image (mathematics); Information retrieval; Machine learning; Data mining","authors":[{"name":"Logan Markewich","is_ca":true},{"name":"Hao Zhang","is_ca":true},{"name":"Yubin Xing","is_ca":true},{"name":"Navid Shirzad","is_ca":false},{"name":"Zhexin Jiang","is_ca":false},{"name":"Roy Ka-Wei Lee","is_ca":true},{"name":"Zhi Li","is_ca":true},{"name":"Seok‐Bum Ko","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01885778479085148,"gpt":0.3029762366451839,"spread":0.2841184518543324,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001572632,0.0002572738,0.0004270423,0.002771539,0.000613853,0.001189525,0.0008317276,0.00005841007,0.001779847],"category_scores_gemma":[0.00005965875,0.0002396256,0.0007994199,0.001466151,0.00003548527,0.0009104192,0.0002748781,0.00034057,0.00003037957],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004371133,"about_ca_system_score_gemma":0.00006794308,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004918234,"about_ca_topic_score_gemma":0.00003341724,"domain_scores_codex":[0.9964991,0.0003064619,0.0008614767,0.0005857575,0.001451249,0.000296008],"domain_scores_gemma":[0.9979314,0.000239287,0.0007274674,0.0002486277,0.0006606943,0.0001925784],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0007542802,0.001150402,0.006437073,0.00002228038,0.04104742,0.0001991524,0.002045864,0.00512145,0.001674933,0.01193844,0.007084363,0.9225243],"study_design_scores_gemma":[0.02217669,0.007601108,0.03549435,0.0003422185,0.03746251,0.001209807,0.004706799,0.1527132,0.1252222,0.502728,0.1038195,0.006523584],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1507654,0.000118763,0.839635,0.00669837,0.001167648,0.0005506334,0.0002381944,0.000184382,0.0006415565],"genre_scores_gemma":[0.9646047,0.000369024,0.02953639,0.003227868,0.0002389123,0.0003691747,0.0007247151,0.00001760142,0.0009116535],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9160008,"threshold_uncertainty_score":0.9998474,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2060595667","doi":"10.1007/s10032-003-0119-7","title":"Color segmentation for text extraction","year":2003,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Artificial intelligence; Color histogram; Computer science; Color space; Color normalization; Computer vision; Pattern recognition (psychology); Segmentation; Histogram equalization; Cluster analysis; Histogram; HSL and HSV; Color image; Color balance; Character (mathematics); Image (mathematics); Mathematics; Image processing","authors":[{"name":"Hiroyuki Hase","is_ca":false},{"name":"Masaaki Yoneda","is_ca":false},{"name":"Shogo Tokai","is_ca":false},{"name":"Jien Kato","is_ca":false},{"name":"Ching Y. Suen","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02124378365571252,"gpt":0.3209451094401309,"spread":0.2997013257844184,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006423299,0.0001207172,0.0001484727,0.0005946447,0.0002028072,0.0007122993,0.0002359532,0.00005621625,0.0002975569],"category_scores_gemma":[0.00009649148,0.00009973376,0.0002178274,0.0003734192,0.00002348446,0.000808102,0.00001843274,0.0001232514,0.00002954048],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001386683,"about_ca_system_score_gemma":0.00003827747,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004408563,"about_ca_topic_score_gemma":0.000002798786,"domain_scores_codex":[0.9986458,0.00009770585,0.0003950904,0.0002560234,0.0004740614,0.0001313331],"domain_scores_gemma":[0.9987333,0.0001260129,0.0003586655,0.0001030723,0.0005877672,0.00009121084],"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":[0.0001844857,0.0005071752,0.001281416,0.00001133194,0.002349176,0.00002370176,0.0003430754,0.00005936885,0.01521514,0.05233397,0.0017439,0.9259472],"study_design_scores_gemma":[0.005000937,0.00137614,0.01191093,0.0001525836,0.00134167,0.0004981912,0.0006259129,0.02099109,0.6323516,0.2079805,0.1164929,0.001277591],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02266401,0.00006242796,0.9732518,0.002034844,0.000570393,0.0001770467,0.000009481803,0.00005330136,0.001176664],"genre_scores_gemma":[0.9432087,0.0009432451,0.05311655,0.0009069301,0.0002032543,0.00006461084,0.00007555602,0.000009340752,0.001471825],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9246697,"threshold_uncertainty_score":0.6868718,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2080016965","doi":"10.1007/s10032-005-0005-6","title":"Genetic engineering of hierarchical fuzzy regional representations for handwritten character recognition","year":2006,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Pattern recognition (psychology); Artificial intelligence; Fuzzy logic; Genetic programming; Classifier (UML); Feature selection; Minimum bounding box; Feature (linguistics)","authors":[{"name":"Christian Gagné","is_ca":true},{"name":"Marc Parizeau","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01771191284402642,"gpt":0.2722801801429247,"spread":0.2545682672988983,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003402487,0.0001303496,0.0002066678,0.0008326176,0.0001116863,0.0003321452,0.0003085005,0.00006553394,0.00008977477],"category_scores_gemma":[0.00005628692,0.0001153677,0.0003043014,0.000393818,0.00004083056,0.0004545383,0.00004299171,0.0001545804,0.000009018536],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006176568,"about_ca_system_score_gemma":0.00003208111,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002548566,"about_ca_topic_score_gemma":0.000003834222,"domain_scores_codex":[0.9983896,0.00005617135,0.0005984447,0.0002791341,0.0005307214,0.0001459376],"domain_scores_gemma":[0.9985135,0.0001689577,0.0003832767,0.0001318256,0.0007255724,0.00007685234],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004946385,0.001241318,0.007588212,0.00006332262,0.004078382,0.00006914757,0.0004195351,0.0004131866,0.03158588,0.02840109,0.003311047,0.9223343],"study_design_scores_gemma":[0.005307406,0.001007925,0.3529182,0.000549117,0.001598922,0.0005784348,0.0001085672,0.06064284,0.1278524,0.4307961,0.01711084,0.001529326],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1123091,0.00009043318,0.8824124,0.0042053,0.0003047667,0.0001973577,0.00005076089,0.00005956333,0.0003703603],"genre_scores_gemma":[0.9309561,0.0005722107,0.06669713,0.0003618344,0.0006688736,0.0000603697,0.0003001395,0.00001266073,0.0003707023],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9208049,"threshold_uncertainty_score":0.4704559,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2079125047","doi":"10.1007/s10032-014-0217-8","title":"Texture sparseness for pixel classification of business document images","year":2014,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Constraint (computer-aided design); Artificial intelligence; Feature (linguistics); Document layout analysis; Pattern recognition (psychology); Segmentation; Filter (signal processing); Pixel; Feature vector; Image (mathematics); Graphics; Basis (linear algebra); Texture (cosmology); Data mining; Computer vision; Mathematics; Computer graphics (images)","authors":[{"name":"Melissa Cote","is_ca":true},{"name":"Alexandra Branzan Albu","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01999021022263243,"gpt":0.2875741722566527,"spread":0.2675839620340203,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008846102,0.0001686615,0.0002858914,0.0007462084,0.0001479161,0.0005399585,0.0005656034,0.00007836185,0.00009879738],"category_scores_gemma":[0.0001414854,0.0001315013,0.0002560413,0.0006053763,0.00006227238,0.0006775691,0.00006841087,0.0001345141,0.00001075459],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008488823,"about_ca_system_score_gemma":0.00004354204,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001078604,"about_ca_topic_score_gemma":0.000003082475,"domain_scores_codex":[0.9981232,0.0001126973,0.0006137873,0.0003352004,0.0006603695,0.0001547218],"domain_scores_gemma":[0.9972206,0.0001709822,0.0006838008,0.0002188574,0.001608997,0.00009677656],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001385046,0.0002750041,0.001220397,0.0000297233,0.001122487,0.000002914811,0.0001276454,0.0000424317,0.01245778,0.0286225,0.0006828689,0.9552777],"study_design_scores_gemma":[0.005917628,0.001224732,0.2096059,0.0006949254,0.002069118,0.0002059146,0.0003263254,0.05376979,0.2684861,0.3543813,0.101483,0.001835293],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01241016,0.00006523952,0.9810378,0.005244447,0.000411131,0.0001577518,0.00001796161,0.00004499304,0.0006105173],"genre_scores_gemma":[0.982771,0.0006997115,0.01526949,0.0003576131,0.0002772672,0.00003316235,0.00009145814,0.000009085325,0.0004912333],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9703608,"threshold_uncertainty_score":0.5362466,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2119140562","doi":"10.1007/s10032-007-0060-2","title":"Genre as noise: noise in genre","year":2007,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Noise (video); Perspective (graphical); Hierarchy; Feature (linguistics); Word error rate; Natural language processing; Artificial intelligence; Emphasis (telecommunications); Speech recognition; Selection (genetic algorithm); Pattern recognition (psychology); Linguistics","authors":[{"name":"Andrea Stubbe","is_ca":false},{"name":"Christoph Ringlstetter","is_ca":true},{"name":"Klaus U. Schulz","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02048356387265479,"gpt":0.317666999386885,"spread":0.2971834355142302,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001893853,0.000174775,0.0002342474,0.001375255,0.0001640828,0.0005850069,0.0005228295,0.0001015651,0.000676151],"category_scores_gemma":[0.0001036044,0.0001491242,0.000254129,0.0008399211,0.00003054987,0.0006595626,0.0001129938,0.000411899,0.0001970449],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001982498,"about_ca_system_score_gemma":0.00005374489,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006036781,"about_ca_topic_score_gemma":0.00006776847,"domain_scores_codex":[0.997752,0.0001250738,0.0006543931,0.0003481379,0.0008372884,0.0002830891],"domain_scores_gemma":[0.9987441,0.0001436138,0.0003308768,0.0001500186,0.0003988502,0.000232578],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0005302676,0.000638478,0.09753013,0.00001326795,0.002851851,0.001587889,0.002168062,0.0009108754,0.002091705,0.02460363,0.0006022611,0.8664716],"study_design_scores_gemma":[0.009411152,0.001034442,0.7406067,0.0006664636,0.001060225,0.001720765,0.001709514,0.02540914,0.04034439,0.1440464,0.03126677,0.002723983],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7320476,0.0002571719,0.2585337,0.004357609,0.001117268,0.0001140931,0.00001022206,0.00004839269,0.00351395],"genre_scores_gemma":[0.9931297,0.0004812803,0.003487832,0.001619392,0.0003282775,0.000003878053,0.00005294586,0.000007230431,0.0008894525],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8637476,"threshold_uncertainty_score":0.740338,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4400055411","doi":"10.1007/s10032-024-00487-6","title":"Automatic floor plan analysis using a boundary attention-based deep network","year":2024,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"3D Surveying and Cultural Heritage","field":"Earth and Planetary Sciences","cited_by":14,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Plan (archaeology); Artificial intelligence; Boundary (topology); Pattern recognition (psychology); Geology","authors":[{"name":"Zhongguo Xu","is_ca":true},{"name":"Cheng Yang","is_ca":true},{"name":"Salah Alheejawi","is_ca":true},{"name":"Naresh Jha","is_ca":true},{"name":"Syed Mehadi","is_ca":false},{"name":"Mrinal Mandal","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0212746797109204,"gpt":0.264864999975496,"spread":0.2435903202645756,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008469895,0.0001968656,0.0003157975,0.001194191,0.0003820131,0.001636914,0.0001894615,0.00007216789,0.01400893],"category_scores_gemma":[0.0000265413,0.000142134,0.0006077333,0.001653314,0.00005342186,0.0004098315,0.000009952185,0.0002707685,0.0001990853],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004238965,"about_ca_system_score_gemma":0.00005721517,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000299815,"about_ca_topic_score_gemma":0.001162605,"domain_scores_codex":[0.9979444,0.0002198139,0.0005203752,0.0003209511,0.0007440701,0.0002504606],"domain_scores_gemma":[0.9991979,0.0001664767,0.0001862944,0.00008876774,0.000176244,0.0001843347],"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":[0.0001362748,0.00007516941,0.3836281,0.00003126276,0.02132849,0.0004852249,0.0002567505,0.1524423,0.00002406646,0.00002677165,0.0003668616,0.4411987],"study_design_scores_gemma":[0.0002969835,0.00008856038,0.1922296,0.0001614906,0.003828579,0.00005858543,0.0001440352,0.8004053,0.000007961597,0.001436429,0.00106888,0.0002735615],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9875001,0.001295604,0.008718793,0.0004845165,0.001115093,0.00006978551,0.0001360175,0.00006658845,0.0006134597],"genre_scores_gemma":[0.9956482,0.000227402,0.001559997,0.0003951632,0.0005774613,0.000001326948,0.001299496,0.000005396584,0.0002855372],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.647963,"threshold_uncertainty_score":0.9993995,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4318465586","doi":"10.1007/s10032-023-00427-w","title":"Large-scale genealogical information extraction from handwritten Quebec parish records","year":2023,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"Université du Québec à Chicoutimi","funders":"Association Nationale de la Recherche et de la Technologie","keywords":"Computer science; Workflow; Consistency (knowledge bases); Scale (ratio); Sample (material); Information extraction; Population; Artificial intelligence; Natural language processing; Information retrieval; Data mining; Database; Geography; Medicine; Cartography","authors":[{"name":"Solène Tarride","is_ca":false},{"name":"Martin Maarand","is_ca":false},{"name":"Mélodie Boillet","is_ca":false},{"name":"James McGrath","is_ca":true},{"name":"Eugénie Capel","is_ca":true},{"name":"Hélène Vézina","is_ca":true},{"name":"Christopher Kermorvant","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01208182651710639,"gpt":0.2916883980205446,"spread":0.2796065715034383,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006666536,0.000154919,0.0002079509,0.001020606,0.0002249963,0.001602959,0.0004888465,0.0001175167,0.0003692618],"category_scores_gemma":[0.00008879191,0.0001228037,0.0002076481,0.0007564221,0.00002251183,0.00242849,0.0001505126,0.0003456644,0.0001664868],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001571578,"about_ca_system_score_gemma":0.00003906472,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004981934,"about_ca_topic_score_gemma":0.0005345686,"domain_scores_codex":[0.9981197,0.0001054578,0.0005220373,0.0002596851,0.0007901908,0.0002029184],"domain_scores_gemma":[0.9987554,0.0001113996,0.0004081313,0.0001469387,0.0004547853,0.0001233756],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001183902,0.0001477795,0.004409354,0.000005822922,0.001249194,0.0001184789,0.001608756,0.00009945362,0.0005317415,0.001204816,0.008225637,0.9822806],"study_design_scores_gemma":[0.005453192,0.0007361511,0.1387794,0.0006550938,0.001496473,0.0003890081,0.001984913,0.1622871,0.02707503,0.5588711,0.09988011,0.002392362],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2954084,0.0001988706,0.6965792,0.005582562,0.001196784,0.0001184966,0.00006573413,0.000404079,0.0004459352],"genre_scores_gemma":[0.9294596,0.001643642,0.06415938,0.002070535,0.0007624999,0.00002833557,0.001073634,0.00001132139,0.0007909949],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9798882,"threshold_uncertainty_score":0.9994335,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2140217726","doi":"10.1007/s10032-005-0147-6","title":"Retrieving poorly degraded OCR documents","year":2005,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"École de Technologie Supérieure; Université de Montréal; Concordia University","funders":"","keywords":"Computer science; Information retrieval; Precision and recall; Query expansion; Relevance (law); Software; Vector space model; Optical character recognition; Artificial intelligence; Pattern recognition (psychology); Selection (genetic algorithm); Error detection and correction; Document retrieval; Data mining; Natural language processing; Image (mathematics); Algorithm","authors":[{"name":"Y. Fataicha","is_ca":true},{"name":"Mohamed Cheriet","is_ca":true},{"name":"Jian‐Yun Nie","is_ca":true},{"name":"C.Y. Suen","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01535983961365943,"gpt":0.3048018974636144,"spread":0.2894420578499549,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.000601451,0.0002126049,0.000273966,0.001020964,0.0002205644,0.001167988,0.0007086835,0.0000715174,0.0004352556],"category_scores_gemma":[0.0001138506,0.0001735172,0.0003173701,0.0007236225,0.00003925742,0.0021613,0.0001622794,0.0003471916,0.0000930623],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002100702,"about_ca_system_score_gemma":0.00003341382,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001278751,"about_ca_topic_score_gemma":0.000006687064,"domain_scores_codex":[0.9977096,0.0001004095,0.0005994131,0.000394975,0.0009401027,0.0002554686],"domain_scores_gemma":[0.9985753,0.0001046637,0.000421614,0.0002071429,0.0004931237,0.0001981703],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006926824,0.0001521324,0.002164913,0.000002371499,0.001288109,0.00009033875,0.000153925,0.00004407565,0.000520501,0.002167451,0.001293104,0.9920538],"study_design_scores_gemma":[0.00901345,0.002205273,0.04328684,0.0009954526,0.002316491,0.001597432,0.0003199102,0.01823979,0.2697621,0.3018901,0.346726,0.003647167],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08441254,0.0005547092,0.9027068,0.008389378,0.0006252944,0.0001615058,0.00001133361,0.0001777759,0.002960652],"genre_scores_gemma":[0.9435344,0.003321337,0.04855217,0.002600612,0.0006041347,0.000008228227,0.0000339642,0.00001287357,0.001332215],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9884067,"threshold_uncertainty_score":0.9998689,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2031691644","doi":"10.1007/s10032-002-0081-9","title":"Iterative model-based binarization algorithm for cheque images","year":2002,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Cheque; Computer science; Artificial intelligence; Handwriting; Pattern recognition (psychology); Histogram; Noise (video); Image (mathematics); Computer vision; Wavelet; Grayscale; Algorithm","authors":[{"name":"Amer Dawoud","is_ca":true},{"name":"Mohamed S. Kamel","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02316602904311791,"gpt":0.2844399393836243,"spread":0.2612739103405063,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003648245,0.0001559394,0.000188686,0.0007657083,0.000215173,0.0009353423,0.0003768918,0.00006445188,0.0002000614],"category_scores_gemma":[0.00004737906,0.000126931,0.0002595999,0.0004499014,0.00003959737,0.0008100018,0.00003730979,0.0001476595,0.00001873923],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000116236,"about_ca_system_score_gemma":0.0000251415,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002876882,"about_ca_topic_score_gemma":6.31709e-7,"domain_scores_codex":[0.9985542,0.00007020024,0.0004091951,0.0003072152,0.0005096061,0.0001495429],"domain_scores_gemma":[0.9984527,0.00007600019,0.0003354987,0.0001294134,0.0009048181,0.000101621],"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":[0.00002291308,0.0002577254,0.00008314396,0.000004467474,0.0006724519,0.00001243741,0.0002165821,0.0003695332,0.000789905,0.002505329,0.000645668,0.9944199],"study_design_scores_gemma":[0.0006974758,0.0001729334,0.0001558887,0.00004469694,0.0001501238,0.00001576663,0.00001427666,0.9531544,0.02434364,0.01972955,0.001310531,0.0002107239],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0007418558,0.00009555017,0.9939329,0.004421634,0.0001941734,0.000142531,0.00003675346,0.00006593214,0.0003686867],"genre_scores_gemma":[0.7099068,0.001070399,0.2844027,0.002152192,0.0003515618,0.00008523581,0.0001717938,0.00001734248,0.00184194],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9942091,"threshold_uncertainty_score":0.9019527,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1979902991","doi":"10.1007/s10032-011-0154-8","title":"Rejection measurement based on linear discriminant analysis for document recognition","year":2011,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; National Institute of Standards and Technology","keywords":"Linear discriminant analysis; Numeral system; Classifier (UML); Computer science; Pattern recognition (psychology); NIST; Artificial intelligence; Word error rate; Reliability (semiconductor); Discriminant; Data mining; Speech recognition","authors":[{"name":"Chun Lei He","is_ca":true},{"name":"Louisa Lam","is_ca":true},{"name":"Ching Y. Suen","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06057137742983903,"gpt":0.2951684649659072,"spread":0.2345970875360681,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002348358,0.0003909441,0.0005407242,0.003644137,0.0003779548,0.0007047917,0.0006409095,0.0001500832,0.0008840347],"category_scores_gemma":[0.0001982922,0.0003240305,0.001064199,0.001395717,0.00005744015,0.0009341728,0.00008288056,0.0003495202,0.00007946668],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005051079,"about_ca_system_score_gemma":0.00008529895,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001094559,"about_ca_topic_score_gemma":0.0001016382,"domain_scores_codex":[0.9957199,0.0003102286,0.001054184,0.0007895563,0.001749659,0.0003764909],"domain_scores_gemma":[0.9963782,0.0001625725,0.0008282248,0.0003690495,0.001976224,0.0002857574],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001427426,0.002062261,0.003399379,0.0000369866,0.01758467,0.000118239,0.0009206844,0.000569939,0.000652603,0.001568786,0.001143748,0.9705153],"study_design_scores_gemma":[0.01674937,0.01245249,0.0872886,0.00208471,0.03407396,0.0002797051,0.0009401297,0.2163157,0.2770931,0.3328956,0.01386661,0.005960019],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02500197,0.00003946639,0.9697905,0.001822668,0.0008389498,0.0005054013,0.00007002372,0.0001741944,0.001756792],"genre_scores_gemma":[0.9405219,0.0004697889,0.05640527,0.00150707,0.0003691086,0.0002187156,0.0003260111,0.00002505022,0.000157109],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9645553,"threshold_uncertainty_score":0.9999212,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4386544129","doi":"10.1007/s10032-023-00453-8","title":"TableStrRec: framework for table structure recognition in data sheet images","year":2023,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Gnowit (Canada); University of Ottawa","funders":"Mitacs","keywords":"Row; Row and column spaces; Computer science; Table (database); Set (abstract data type); Column (typography); Pattern recognition (psychology); Artificial intelligence; Inference; Test data; Test set; Data mining; Database","authors":[{"name":"Johan Fernandes","is_ca":true},{"name":"Bin Xiao","is_ca":true},{"name":"Murat Şimşek","is_ca":true},{"name":"Burak Kantarcı","is_ca":true},{"name":"Shahzad Khan","is_ca":true},{"name":"Ala Abu Alkheir","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03503051319368615,"gpt":0.3313850425348655,"spread":0.2963545293411793,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001331559,0.0002613511,0.0003939142,0.002181785,0.0002144533,0.001407442,0.001278542,0.0001754168,0.000622471],"category_scores_gemma":[0.0004738497,0.0002340233,0.0001854854,0.001752709,0.00004756284,0.00195152,0.0003551645,0.0004711386,0.00006658815],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001351415,"about_ca_system_score_gemma":0.00007973612,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004570279,"about_ca_topic_score_gemma":0.0000755626,"domain_scores_codex":[0.9972078,0.0001627534,0.000757089,0.0007096453,0.0007851748,0.000377549],"domain_scores_gemma":[0.9978314,0.0004801565,0.0004560259,0.0004237386,0.000642326,0.0001663651],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000132237,0.0002018062,0.001948157,0.00002132009,0.00149976,0.0001363549,0.0002229258,0.0001783145,0.0004727474,0.00139997,0.01163938,0.982147],"study_design_scores_gemma":[0.002269277,0.0003312908,0.00604308,0.0007312872,0.0005522802,0.0001934867,0.0002859024,0.03027204,0.0157894,0.9324067,0.01011336,0.001011882],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09615261,0.0001854914,0.8901154,0.008455439,0.00179759,0.0006334542,0.001750294,0.0003971315,0.000512554],"genre_scores_gemma":[0.750836,0.006126206,0.2311041,0.002371767,0.001406817,0.0001581506,0.007236121,0.00006034732,0.0007005567],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9811351,"threshold_uncertainty_score":0.9996292,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2130604705","doi":"10.1007/s10032-011-0171-7","title":"A robust probabilistic Braille recognition system","year":2011,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Tactile and Sensory Interactions","field":"Neuroscience","cited_by":7,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Braille; Computer science; Skewness; Probabilistic logic; Line (geometry); Artificial intelligence; Optical character recognition; Speech recognition; Pattern recognition (psychology); Mathematics; Statistics","authors":[{"name":"Mehdi Yousefi","is_ca":false},{"name":"Mahmoud Famouri","is_ca":false},{"name":"Behrooz Nasihatkon","is_ca":false},{"name":"Zohreh Azimifar","is_ca":false},{"name":"Paul Fieguth","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0912653964310988,"gpt":0.2830081094912913,"spread":0.1917427130601925,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002086071,0.0002073404,0.0002622024,0.0009841319,0.0003130261,0.0004200252,0.0002406418,0.0000808334,0.003647515],"category_scores_gemma":[0.0002906321,0.0001700144,0.0003479934,0.0004272641,0.00006806007,0.0006725476,0.00004169574,0.0003624074,0.0005567238],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002034291,"about_ca_system_score_gemma":0.00003037296,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007390393,"about_ca_topic_score_gemma":0.00004445036,"domain_scores_codex":[0.9978677,0.0002277255,0.0006100158,0.0004237441,0.0006469418,0.0002238595],"domain_scores_gemma":[0.9985937,0.0002091914,0.0004665267,0.0001387815,0.0003978959,0.0001938431],"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":[0.006789332,0.006941601,0.008764402,0.0002038187,0.01528494,0.004754606,0.0102834,0.002093968,0.05495325,0.01616239,0.008098892,0.8656694],"study_design_scores_gemma":[0.01549759,0.004698388,0.03282673,0.003168211,0.01353978,0.01688341,0.01294175,0.02340096,0.7405763,0.09071562,0.03964643,0.006104793],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9584851,0.00001228165,0.002185957,0.0006276609,0.001921942,0.0002235863,0.0001104482,0.000106923,0.03632614],"genre_scores_gemma":[0.9970658,0.0002532038,0.0004163727,0.0006768159,0.0003944668,0.00002578395,0.00005104952,0.00001690961,0.001099545],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8595646,"threshold_uncertainty_score":0.9972633,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4313201936","doi":"10.1007/s10032-022-00422-7","title":"Refocus attention span networks for handwriting line recognition","year":2022,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"","keywords":"Computer science; Handwriting; Transformer; Artificial intelligence; Speech recognition; Encoder; Robustness (evolution); Lexicon; Natural language processing; Benchmark (surveying); Pattern recognition (psychology)","authors":[{"name":"Mohammed Hamdan","is_ca":true},{"name":"Himanshu Chaudhary","is_ca":false},{"name":"Ahmed Bali","is_ca":true},{"name":"Mohamed Cheriet","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02054236969264456,"gpt":0.2856094053117104,"spread":0.2650670356190658,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001833745,0.0002592695,0.00035864,0.001536889,0.0008534792,0.001083818,0.0006719006,0.00008689681,0.0008414431],"category_scores_gemma":[0.0001072649,0.000251176,0.0005616695,0.0008110849,0.00004020517,0.0009257261,0.000277807,0.0005413669,0.0000243553],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003277574,"about_ca_system_score_gemma":0.00004665384,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000283425,"about_ca_topic_score_gemma":0.00001683154,"domain_scores_codex":[0.9968929,0.0003136936,0.0008747788,0.0005798468,0.0009969366,0.0003418206],"domain_scores_gemma":[0.9977266,0.0002351917,0.0007449065,0.0002070187,0.0008975998,0.0001887188],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001857981,0.0002962142,0.0005634888,0.000006945524,0.001459404,0.0000593203,0.0001088567,0.0005269838,0.0002927803,0.0006192375,0.001123653,0.9947573],"study_design_scores_gemma":[0.01767744,0.007615735,0.008345911,0.001030432,0.004769905,0.00330249,0.00174973,0.4185463,0.02255429,0.443772,0.06582633,0.004809438],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06501989,0.0001703719,0.9285123,0.003739685,0.001219438,0.0003911724,0.0001124684,0.0001909554,0.0006436731],"genre_scores_gemma":[0.970692,0.0009932509,0.02349178,0.001838942,0.001016866,0.0003113369,0.00102238,0.00002976958,0.0006037148],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9899479,"threshold_uncertainty_score":0.999994,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4295128257","doi":"10.1007/s10032-022-00411-w","title":"Domain adaptation for staff-region retrieval of music score images","year":2022,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Music and Audio Processing","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"Fonds de Recherche du Québec-Société et Culture; Agencia Estatal de Investigación; Generalitat Valenciana; American Concrete Institute Foundation","keywords":"Computer science; Classifier (UML); Domain adaptation; Artificial intelligence; Workflow; Inference; Domain (mathematical analysis); Artificial neural network; Machine learning; Annotation; Documentation; Process (computing); Information retrieval; Database","authors":[{"name":"Francisco J. Castellanos","is_ca":false},{"name":"Antonio‐Javier Gallego","is_ca":false},{"name":"Jorge Calvo-Zaragoza","is_ca":false},{"name":"Ichiro Fujinaga","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03474842508047755,"gpt":0.2758689477789538,"spread":0.2411205226984763,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006740384,0.0001123111,0.000200679,0.000732857,0.0003274353,0.000317295,0.0003887508,0.00002540189,0.0002365444],"category_scores_gemma":[0.00003210645,0.00009862395,0.0002505445,0.0005061039,0.00003407985,0.0005340271,0.0001178947,0.0001658871,0.000001832751],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001114356,"about_ca_system_score_gemma":0.00006892836,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001233782,"about_ca_topic_score_gemma":0.000004400053,"domain_scores_codex":[0.998285,0.0001067002,0.0004491521,0.0002541266,0.0007732554,0.0001317577],"domain_scores_gemma":[0.9986771,0.0001033353,0.0006053888,0.0000988339,0.0004468143,0.00006856256],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001359931,0.0009621651,0.003549751,0.00005555897,0.004730248,0.0001680784,0.005411598,0.007650931,0.004293446,0.01434101,0.004796509,0.9526808],"study_design_scores_gemma":[0.01843202,0.006199696,0.03008845,0.0008525107,0.00327705,0.001413994,0.009478924,0.1223607,0.04128952,0.7004039,0.06338447,0.002818745],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3010729,0.0001199123,0.6952046,0.002625276,0.0005769355,0.0001051089,0.00002525659,0.0000162392,0.0002538068],"genre_scores_gemma":[0.9862624,0.0001283123,0.01246577,0.0005955793,0.0001976549,0.00001255527,0.00007131408,0.000006791464,0.0002595783],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.949862,"threshold_uncertainty_score":0.4021768,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2511810441","doi":"10.1007/s10032-016-0271-5","title":"Document segmentation and classification into musical scores and text","year":2016,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Music and Audio Processing","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria","funders":"","keywords":"Musical; Segmentation; Natural language processing; Artificial intelligence; Computer science; Pattern recognition (psychology); Psychology; Speech recognition; Art; Literature","authors":[{"name":"Fabrizio Pedersoli","is_ca":true},{"name":"George Tzanetakis","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01930539014656912,"gpt":0.2900539760564974,"spread":0.2707485859099282,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004699861,0.0001452482,0.0001740466,0.0005345527,0.0002247174,0.0009971967,0.0001956447,0.00004986249,0.0001880897],"category_scores_gemma":[0.00004755648,0.00009402844,0.00007932923,0.000216107,0.00008511227,0.001160985,0.0001099436,0.0001067003,0.00002038768],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009673138,"about_ca_system_score_gemma":0.00002792173,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001602069,"about_ca_topic_score_gemma":0.00001614387,"domain_scores_codex":[0.9984738,0.00008837178,0.0003896956,0.0003666421,0.0005457802,0.000135714],"domain_scores_gemma":[0.9990643,0.0001234333,0.0003160049,0.00009754487,0.0002446311,0.0001541176],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00003476393,0.00004242348,0.00421874,0.0000051304,0.0004095584,0.00001167107,0.0004127405,0.000002595542,0.003706276,0.002906011,0.0002641456,0.987986],"study_design_scores_gemma":[0.0115282,0.001330628,0.4394359,0.001716306,0.001864073,0.0008625968,0.001028646,0.02070247,0.02815129,0.4695461,0.02155889,0.002274951],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6804919,0.0002111201,0.3010518,0.01741874,0.0003546536,0.00008840262,0.000003639161,0.00002901134,0.0003507409],"genre_scores_gemma":[0.9877425,0.00189155,0.008751402,0.001119171,0.0002095683,0.000009821993,0.00001180275,0.000005502275,0.0002586678],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.985711,"threshold_uncertainty_score":0.9615991,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2029526043","doi":"10.1007/s10032-011-0156-6","title":"Error handling approach using characterization and correction steps for handwritten document analysis","year":2011,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"École de Technologie Supérieure","funders":"H2020 European Research Council","keywords":"Computer science; Phrase; Word (group theory); Artificial intelligence; Speech recognition; Natural language processing; Sentence; Intelligent word recognition; Posterior probability; Handwriting; Error detection and correction; Pattern recognition (psychology); Intelligent character recognition; Algorithm; Bayesian probability; Linguistics","authors":[{"name":"Solen Quiniou","is_ca":true},{"name":"Mohamed Cheriet","is_ca":true},{"name":"Éric Anquetil","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04020382215980793,"gpt":0.2903658157744112,"spread":0.2501619936146032,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001287567,0.0002852731,0.0004788308,0.002441421,0.0003953869,0.001142993,0.000387594,0.0001417547,0.0002155999],"category_scores_gemma":[0.00006956796,0.0002510056,0.0004199731,0.00104451,0.00005898539,0.001447323,0.000120246,0.0002583918,0.000005876123],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001705983,"about_ca_system_score_gemma":0.00003974867,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008322152,"about_ca_topic_score_gemma":0.00002234655,"domain_scores_codex":[0.9974627,0.0002144421,0.0007888861,0.0006055647,0.0006541448,0.0002742544],"domain_scores_gemma":[0.9979549,0.0001153798,0.0007276752,0.0001969181,0.0007964099,0.0002087337],"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":[0.000551429,0.0008498394,0.01545648,0.00004180122,0.02186344,0.00004807355,0.003204946,0.0003884406,0.004405777,0.001490316,0.0001642279,0.9515352],"study_design_scores_gemma":[0.005432598,0.001323768,0.0618462,0.0004457251,0.01550457,0.0006443892,0.001022411,0.8436058,0.04408654,0.02124298,0.002502173,0.002342843],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1833344,0.00004757466,0.81527,0.0001884279,0.0005479118,0.0002653955,0.00003013406,0.0000791952,0.0002369122],"genre_scores_gemma":[0.9302816,0.00070307,0.06726377,0.0004490924,0.000323091,0.0000717066,0.000482145,0.00002047288,0.0004049799],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9491924,"threshold_uncertainty_score":0.9999942,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4389941462","doi":"10.1007/s10032-023-00456-5","title":"Improving accuracy and explainability of online handwritten character recognition","year":2023,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo; National Research Council Canada","funders":"","keywords":"Computer science; Artificial intelligence; Handwriting; Robustness (evolution); Pattern recognition (psychology); Handwriting recognition; Machine learning; Task (project management); Deep learning; Alphabet; Speech recognition; Feature extraction","authors":[{"name":"Hilda Azimi","is_ca":true},{"name":"Steven Chang","is_ca":true},{"name":"Jonathan Gold","is_ca":true},{"name":"Koray Karabina","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02193815844080075,"gpt":0.2769692219164192,"spread":0.2550310634756184,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009404945,0.0001686115,0.0003326251,0.001076827,0.000194032,0.0005577914,0.000318891,0.00006367111,0.0002215584],"category_scores_gemma":[0.0002614808,0.0001365856,0.0002801428,0.0008322989,0.00005639981,0.001068405,0.0002080416,0.0002202092,0.00001936639],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005533707,"about_ca_system_score_gemma":0.00003049101,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007575301,"about_ca_topic_score_gemma":0.00003472724,"domain_scores_codex":[0.9980459,0.0001109482,0.0006870687,0.0003727351,0.0005802111,0.0002031145],"domain_scores_gemma":[0.9982071,0.0002299262,0.0006424779,0.0001608505,0.0006252703,0.0001343884],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00007042774,0.000128318,0.006037605,0.0000158017,0.001252978,0.00003907484,0.0004060748,0.00004927519,0.0009504187,0.0001978371,0.00007994211,0.9907722],"study_design_scores_gemma":[0.006605598,0.001491957,0.5405193,0.0009560467,0.003509109,0.0005773957,0.003109926,0.3380943,0.01328843,0.08480094,0.004794212,0.002252825],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9793159,0.000061997,0.01743888,0.002569107,0.0003055721,0.00008539737,0.00005607918,0.00004593639,0.000121081],"genre_scores_gemma":[0.9945189,0.001047034,0.003533585,0.0002461283,0.000280448,0.00000686046,0.0002138175,0.000008352406,0.0001448828],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9885194,"threshold_uncertainty_score":0.5569798,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4403102908","doi":"10.1007/s10032-024-00499-2","title":"Unpaired document image denoising for OCR using BiLSTM enhanced CycleGAN","year":2024,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Computer science; Pattern recognition (psychology); Image (mathematics); Noise reduction; Computer vision","authors":[{"name":"Katyani Singh","is_ca":true},{"name":"Ganesh Tata","is_ca":true},{"name":"Eric Van Oeveren","is_ca":false},{"name":"Nilanjan Ray","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02578919183659872,"gpt":0.3390521256032745,"spread":0.3132629337666758,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00145718,0.0002469519,0.0003237545,0.001372803,0.0003184533,0.003848292,0.0005163404,0.00007390088,0.0002111678],"category_scores_gemma":[0.00009003589,0.0002011615,0.0005356576,0.0006579788,0.00004890889,0.001635473,0.0001151526,0.0002671535,0.00002886613],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000274052,"about_ca_system_score_gemma":0.00009733673,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003179956,"about_ca_topic_score_gemma":0.000005891835,"domain_scores_codex":[0.9975051,0.0002082291,0.0006575077,0.0005271803,0.0007950551,0.0003069259],"domain_scores_gemma":[0.9985569,0.0003174462,0.0002535239,0.0001808645,0.000517746,0.0001735173],"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":[0.0003390327,0.0002149016,0.00008660534,0.00005861455,0.006784728,0.0005482606,0.001372249,0.001353529,0.08863408,0.004635962,0.0009802766,0.8949918],"study_design_scores_gemma":[0.005260757,0.0008543258,0.0008163401,0.001663811,0.003380727,0.0009170812,0.0003408089,0.3335301,0.3325384,0.3057003,0.01313383,0.001863506],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1231826,0.0003932663,0.8723394,0.001892325,0.001598636,0.0001431,0.00001232111,0.00007687199,0.0003615379],"genre_scores_gemma":[0.8498691,0.0004599954,0.1470335,0.0008291395,0.0009414623,0.00001611321,0.00004606017,0.00002606133,0.0007786396],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8931283,"threshold_uncertainty_score":0.9971858,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4384524000","doi":"10.1007/s10032-023-00447-6","title":"Attribute-based document image retrieval","year":2023,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Information retrieval; Image retrieval; Convolutional neural network; Set (abstract data type); Document retrieval; Visual Word; Image (mathematics); Scalability; Table (database); Data mining; Artificial intelligence; Database","authors":[{"name":"Melissa Cote","is_ca":true},{"name":"Alexandra Branzan Albu","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01781958009846585,"gpt":0.2975130757065387,"spread":0.2796934956080728,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001522717,0.0002688454,0.0003539186,0.002352088,0.0002827815,0.001758553,0.0008379093,0.000110128,0.001118058],"category_scores_gemma":[0.000162438,0.0002303356,0.0004970539,0.001762434,0.00006966511,0.001091941,0.0002030955,0.000388228,0.0006646835],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002365392,"about_ca_system_score_gemma":0.00008664417,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001876945,"about_ca_topic_score_gemma":0.000006926574,"domain_scores_codex":[0.996691,0.0002242799,0.0007464107,0.0005287103,0.001447282,0.0003622595],"domain_scores_gemma":[0.9978296,0.0002463988,0.000453594,0.0002776618,0.0009177316,0.0002749936],"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":[0.000825865,0.001204089,0.009150404,0.00005927582,0.01216031,0.003056395,0.0009316491,0.000362259,0.01001438,0.007476591,0.03802072,0.916738],"study_design_scores_gemma":[0.01381845,0.003020969,0.06674486,0.001243435,0.002902552,0.0008496717,0.000532879,0.04184613,0.4548008,0.3458964,0.06392308,0.004420761],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3156206,0.0001071689,0.6542106,0.02467105,0.00199237,0.0004452776,0.0001135553,0.0009806076,0.001858773],"genre_scores_gemma":[0.970197,0.001590612,0.02296183,0.002842041,0.0006274741,0.00003953399,0.0004915664,0.00002999225,0.001219959],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9123173,"threshold_uncertainty_score":0.9997951,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4410636570","doi":"10.1007/s10032-025-00527-9","title":"Revisiting Table Detection Datasets for Visually Rich Documents","year":2025,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Defence Research and Development Canada; University of Ottawa","funders":"Mitacs","keywords":"Table (database); Information retrieval; Computer science; Data mining","authors":[{"name":"Bin Xiao","is_ca":true},{"name":"Murat Şimşek","is_ca":true},{"name":"Burak Kantarcı","is_ca":true},{"name":"Ala Abu Alkheir","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01224472622766342,"gpt":0.3188094202265064,"spread":0.306564693998843,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001174564,0.0002110827,0.000303608,0.001595565,0.0003750279,0.001539182,0.0006269617,0.00009180177,0.0002044],"category_scores_gemma":[0.0002012133,0.0001892199,0.000256576,0.0009100451,0.00002896664,0.001271312,0.0001737874,0.0002494538,0.00002886403],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002054577,"about_ca_system_score_gemma":0.00006020232,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002359866,"about_ca_topic_score_gemma":0.00001323942,"domain_scores_codex":[0.997826,0.0001379995,0.0006997041,0.0004780691,0.0006053358,0.0002529117],"domain_scores_gemma":[0.9981875,0.0002289545,0.000455608,0.0002117745,0.0007965381,0.0001195768],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001024041,0.0001432601,0.0009831645,0.00002001282,0.002377592,0.00002409408,0.00005397723,0.00002553768,0.001251073,0.002235489,0.002381221,0.9904022],"study_design_scores_gemma":[0.01076615,0.001483161,0.01355762,0.002338195,0.004422061,0.0004534999,0.0003494421,0.04718193,0.3167491,0.4216775,0.1783355,0.002685717],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02985997,0.0001383673,0.9648899,0.00233519,0.0008253967,0.0003076635,0.0001052892,0.0001269085,0.001411322],"genre_scores_gemma":[0.9606711,0.001485908,0.03209068,0.003152651,0.0005717847,0.0001390467,0.0006336328,0.00001760184,0.001237633],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9877164,"threshold_uncertainty_score":0.9994973,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2010145024","doi":"10.1007/s10032-007-0038-0","title":"Special issue on graphics recognition","year":2007,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"","keywords":"Graphics; Computer science; Computer graphics (images)","authors":[{"name":"Josep Lladós","is_ca":false},{"name":"Dorothea Blostein","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0185579322519571,"gpt":0.2713835459913483,"spread":0.2528256137393912,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001055446,0.0002103717,0.0002666026,0.001664662,0.0001743737,0.0003786731,0.0001186693,0.0001743366,0.002462759],"category_scores_gemma":[0.00006110995,0.0001812492,0.0003352547,0.0005593708,0.00002534464,0.0002802883,0.0000142539,0.0004775551,0.0003877346],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001912951,"about_ca_system_score_gemma":0.00001015785,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002578617,"about_ca_topic_score_gemma":0.00005205299,"domain_scores_codex":[0.9980364,0.0000654013,0.0006635678,0.0002218679,0.0007897799,0.0002230279],"domain_scores_gemma":[0.9990464,0.0001303975,0.0002081527,0.00009274877,0.0003480758,0.0001742295],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004686086,0.0001168698,0.0005341999,0.000007150918,0.002363487,0.0001279329,0.0001790961,0.0007968772,0.0002790208,0.0001210613,0.01401225,0.9809934],"study_design_scores_gemma":[0.007831357,0.001989518,0.02341339,0.0008915353,0.002195126,0.0006648671,0.001150208,0.003418697,0.04086235,0.01508413,0.9003491,0.002149766],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9267631,0.00006867883,0.008092875,0.00046591,0.01379936,0.0002641204,0.000073982,0.0001678117,0.05030416],"genre_scores_gemma":[0.9711828,0.0008501027,0.0001518025,0.0004694777,0.02660785,0.000006705503,0.0001462766,0.00002908366,0.0005559228],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9788437,"threshold_uncertainty_score":0.9984491,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4414929823","doi":"10.1007/s10032-025-00559-1","title":"CalliNet: a triplet network for chinese calligraphy style classification","year":2025,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Color perception and design","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"Natural Science Foundation of Jiangxi Province; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Calligraphy; Discriminative model; Robustness (evolution); Style (visual arts); Feature extraction; Pattern recognition (psychology); Pooling; Feature (linguistics)","authors":[{"name":"Hui Ma","is_ca":false},{"name":"Li Liu","is_ca":false},{"name":"Yue Lu","is_ca":false},{"name":"Ching Y. Suen","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02888770512613196,"gpt":0.3700693358111449,"spread":0.3411816306850129,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006855343,0.0001807759,0.0002891377,0.0009836142,0.0002179574,0.0003026522,0.0002049552,0.0001207212,0.004596058],"category_scores_gemma":[0.00006266651,0.0001444382,0.0004743277,0.0006466256,0.00004473297,0.0001292543,0.00002014684,0.0002260012,0.00008995185],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009774775,"about_ca_system_score_gemma":0.00003173186,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004348996,"about_ca_topic_score_gemma":0.0001048624,"domain_scores_codex":[0.9983482,0.0001624617,0.0006102929,0.0003339711,0.0003382427,0.0002068521],"domain_scores_gemma":[0.9987035,0.00024957,0.000311899,0.0001365386,0.000483833,0.0001146821],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.006719443,0.00183167,0.1121032,0.00002520152,0.02427762,0.00006737115,0.001804003,0.001010812,0.0007410871,0.03036696,0.1598918,0.6611608],"study_design_scores_gemma":[0.007816596,0.0006633647,0.7366803,0.0001551219,0.002441294,0.00004895809,0.0007724312,0.007234667,0.00003831122,0.06329805,0.180165,0.0006858783],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7084631,0.0007729457,0.2516694,0.01367612,0.005463488,0.0008100863,0.000200544,0.0001071884,0.01883707],"genre_scores_gemma":[0.9875935,0.0005164069,0.001145127,0.002846804,0.0009559187,0.0001128533,0.0004103148,0.00001166148,0.006407356],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.660475,"threshold_uncertainty_score":0.9963139,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4414059432","doi":"10.1007/s10032-025-00555-5","title":"Optimizing identity documents classification in online systems: A comparative analysis","year":2025,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"International Medias Data Services (Canada)","funders":"","keywords":"Convolutional neural network; Context (archaeology); Identity (music); Process (computing); A priori and a posteriori; Identity management; Strengths and weaknesses","authors":[{"name":"Joris Voerman","is_ca":false},{"name":"Musab Ghadi","is_ca":false},{"name":"Nicolas Sidère","is_ca":false},{"name":"Mickaël Coustaty","is_ca":false},{"name":"Olivier Lessard","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04133032381567437,"gpt":0.3529996195214886,"spread":0.3116692957058143,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007891015,0.0002300755,0.0005071515,0.005117055,0.0001984985,0.001902936,0.00101238,0.0001137092,0.0001085218],"category_scores_gemma":[0.00007313528,0.000200234,0.0003486486,0.003886376,0.0000696127,0.001954602,0.0002113713,0.000362847,0.00002677306],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004180499,"about_ca_system_score_gemma":0.0000615162,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001260417,"about_ca_topic_score_gemma":0.0002424077,"domain_scores_codex":[0.9972163,0.0002234028,0.0009704658,0.0005427836,0.0008154057,0.0002315897],"domain_scores_gemma":[0.9982194,0.0001649574,0.0006425821,0.0003311552,0.0005520002,0.00008996086],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.0004786295,0.003582609,0.2421876,0.00005811837,0.05607975,0.0001959297,0.003310184,0.02718066,0.001138734,0.4208621,0.002890938,0.2420348],"study_design_scores_gemma":[0.005146771,0.0003015055,0.5337169,0.0005609625,0.005315244,0.00003257298,0.006428702,0.3551406,0.001571392,0.0813398,0.009083667,0.001361876],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3681466,0.0006720263,0.6194502,0.007474282,0.0010664,0.000314145,0.00003402764,0.0001654896,0.002676882],"genre_scores_gemma":[0.992269,0.001303655,0.005081592,0.0003818027,0.00005509639,0.00003664067,0.0001557509,0.00000354933,0.0007129302],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6241224,"threshold_uncertainty_score":0.9991332,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2043851063","doi":"10.1007/s10032-011-0169-1","title":"Editorial preface","year":2011,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"History and advancements in chemistry","field":"Chemistry","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"","keywords":"Philosophy","authors":[{"name":"Josep Lladós","is_ca":false},{"name":"Apostolos Antonacopoulos","is_ca":false},{"name":"Mohamed Cheriet","is_ca":true},{"name":"Umapada Pal","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01975482709631475,"gpt":0.2702978268210915,"spread":0.2505429997247767,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002168806,0.0001608142,0.0001847364,0.0002015114,0.0001567781,0.0001304812,0.0002574761,0.0001011652,0.01978415],"category_scores_gemma":[0.00005662033,0.000139029,0.0002320559,0.0001117416,0.00005663597,0.0002902084,0.00004538487,0.0003411459,0.00008489078],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001513989,"about_ca_system_score_gemma":0.00003491612,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001179893,"about_ca_topic_score_gemma":0.000004439919,"domain_scores_codex":[0.9985182,0.00002057162,0.0004005378,0.0002503561,0.0006550544,0.0001552628],"domain_scores_gemma":[0.9991019,0.00004014453,0.0003057444,0.000117068,0.0002835957,0.0001515311],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.005917219,0.005033519,0.03923455,0.00017652,0.04663926,0.0008461443,0.006017073,0.0002948256,0.1027092,0.001937703,0.192313,0.598881],"study_design_scores_gemma":[0.003776175,0.0001626589,0.0005775803,0.0002846049,0.001929757,0.0001247641,0.0006213022,0.000082293,0.202141,0.02273861,0.7666066,0.0009546898],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7702852,0.00027199,0.001760923,0.0004031577,0.04913994,0.00007626935,0.0001477698,0.0001077375,0.177807],"genre_scores_gemma":[0.9480537,0.001035771,0.001524363,0.0002983097,0.0390666,0.00001536169,0.0002041599,0.00002275033,0.009779055],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5979263,"threshold_uncertainty_score":0.9811119,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4406984947","doi":"10.1007/s10032-025-00513-1","title":"Redacted text detection using neural image segmentation methods","year":2025,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Canadian Institute of Steel Construction","keywords":"Artificial intelligence; Segmentation; Image segmentation; Computer vision; Pattern recognition (psychology); Computer science; Image (mathematics); Artificial neural network","authors":[{"name":"Ruben van Heusden","is_ca":false},{"name":"M. Marx","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01943269196242409,"gpt":0.3641712029352362,"spread":0.3447385109728122,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001039755,0.0002126143,0.000279547,0.002219865,0.0003030952,0.001434238,0.0004482771,0.00009971359,0.0003147288],"category_scores_gemma":[0.000134249,0.0001896284,0.0003178103,0.001191872,0.00005049815,0.001451624,0.0001366416,0.0003440133,0.00001579467],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003023419,"about_ca_system_score_gemma":0.00005067248,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005514354,"about_ca_topic_score_gemma":0.00001507698,"domain_scores_codex":[0.9976845,0.0004481201,0.0006763095,0.0004203353,0.000563951,0.0002067164],"domain_scores_gemma":[0.9982021,0.0001764563,0.0004607002,0.0001807138,0.0008642381,0.0001157327],"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":[0.00005675526,0.00009989215,0.0003498661,0.000005190584,0.001293882,0.0000268582,0.00008924199,0.00006417256,0.02470229,0.0002747805,0.0001011592,0.9729359],"study_design_scores_gemma":[0.002863259,0.0004187748,0.01175568,0.0003398349,0.001760485,0.0004355421,0.0003237779,0.2686657,0.6225231,0.08744588,0.002503042,0.0009649789],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1538625,0.00006096737,0.8428622,0.001265264,0.0008063902,0.0001433856,0.000008731518,0.0001155186,0.0008750123],"genre_scores_gemma":[0.7650407,0.0004412217,0.2325869,0.001289373,0.000219655,0.00002652941,0.000056915,0.00001201815,0.0003266656],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9719709,"threshold_uncertainty_score":0.9996024,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}