{"meta":{"query_hash":"cea167b9e56d","filters":{"venue":"International Journal on Document Analysis and Recognition (IJDAR)"},"cohort_total":43,"direct_labels_cover":0,"predictions_cover":43,"exported":43,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/cea167b9e56d","api":"https://metacan.xera.ac/api/v1/cohort?venue=International+Journal+on+Document+Analysis+and+Recognition+%28IJDAR%29"},"results":[{"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Currency; Authentication (law); Computer science; Banknote; Computer security; Artificial intelligence; Economics; Monetary economics","score_opus":0.0396712521175821,"score_gpt":0.3219999670659646,"score_spread":0.2823287149483825,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1899315810","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9923415,0.00014514897,0.0051841848,0.00006480114,0.00013936375,0.000058913152,0.00014346573,0.00046853008,0.001454161],"genre_scores_gemma":[0.99303085,0.00009566628,0.004259353,0.000035501154,0.00002454386,0.000013863964,0.00022521545,0.000028013588,0.002287119],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990619,0.00027563758,0.00009105552,0.00016997107,0.0002487192,0.00015269156],"domain_scores_gemma":[0.9974274,0.0011299282,0.00015682547,0.00053469214,0.0005372802,0.00021380377],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009745669,0.0005572644,0.0008568791,0.0005768682,0.00065075356,0.0009981722,0.0007245699,0.0009514322,0.003992906],"category_scores_gemma":[0.0032314307,0.000187472,0.0003783144,0.00059029536,0.00059476076,0.0012965909,0.00076159614,0.00053355243,0.0018060361],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.023178803,0.005375336,0.029712176,0.0016353085,0.00041022315,0.004074842,0.0027800165,0.017254362,0.52624977,0.0033051423,0.0078026103,0.37822136],"study_design_scores_gemma":[0.0008947535,0.01910506,0.08857061,0.0001259408,0.0007940113,0.0045645,0.0031605838,0.2898942,0.57763714,0.0018611744,0.013116382,0.00027565274],"about_ca_topic_score_codex":0.0016976302,"about_ca_topic_score_gemma":0.0009555257,"teacher_disagreement_score":0.003992906,"about_ca_system_score_codex":0.00023270014,"about_ca_system_score_gemma":0.00029429872,"threshold_uncertainty_score":0.013357639},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.014855400756180434,"score_gpt":0.2952721653155663,"score_spread":0.2804167645593859,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1965285802","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0322791,0.00057827885,0.9629594,0.00014532362,0.000058464164,0.00005400393,0.00011937648,0.0008704151,0.0029356598],"genre_scores_gemma":[0.5282771,0.0019927833,0.44637966,0.00014373993,0.00008425137,0.000086977714,0.0006301309,0.0004481114,0.021957168],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9997532,0.000027645256,0.000013335532,0.000047877034,0.00013483677,0.000023174487],"domain_scores_gemma":[0.9994838,0.00010410524,0.00005359098,0.00011344648,0.00022612557,0.000018885597],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036680928,0.00058725715,0.00037877852,0.0005705416,0.00018986905,0.0011357355,0.0006009028,0.0006403313,0.0029759267],"category_scores_gemma":[0.0010894892,0.0003180896,0.0005560727,0.00043652285,0.00027540434,0.0009772875,0.00039489716,0.00059822557,0.0016231432],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042749668,0.00018073207,0.0018759336,0.00039312162,0.000064339234,0.0002793875,0.00013196595,0.13349469,0.41628027,0.0069933124,0.0033086673,0.4365701],"study_design_scores_gemma":[0.000012030439,0.00010884483,0.0016428058,0.000019582738,0.00005783782,0.0004675003,0.000030786123,0.7721009,0.21704137,0.0013497401,0.0071459427,0.000022656963],"about_ca_topic_score_codex":0.0013609204,"about_ca_topic_score_gemma":0.0013530118,"teacher_disagreement_score":0.0029759267,"about_ca_system_score_codex":0.0003279377,"about_ca_system_score_gemma":0.00032885504,"threshold_uncertainty_score":0.009955525},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.026429625449336573,"score_gpt":0.32733020032870463,"score_spread":0.30090057487936805,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1970571079","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0286707,0.0003959155,0.96546924,0.0000977599,0.00017750158,0.000089951274,0.00024777438,0.0029285194,0.001922528],"genre_scores_gemma":[0.38137054,0.00077203603,0.6022474,0.00016852922,0.00009314747,0.00024039813,0.0009626528,0.00019604509,0.01394917],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995666,0.00006982039,0.000037946716,0.0001225947,0.00014384658,0.00005924246],"domain_scores_gemma":[0.9992748,0.00032961273,0.000039192993,0.00009155231,0.00022173344,0.000043207172],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047118583,0.0005145744,0.00079971313,0.00061824627,0.0003680719,0.0007088627,0.00078403176,0.0010004343,0.0024543435],"category_scores_gemma":[0.0012444059,0.00043951705,0.00063844374,0.0006963547,0.00024688285,0.00084170344,0.0004190345,0.00083518296,0.0021571817],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00074790034,0.00022361262,0.0024644611,0.0003098177,0.00011665505,0.00020007265,0.00014730233,0.012348509,0.26309648,0.0018543735,0.0030227806,0.71546805],"study_design_scores_gemma":[0.00007287662,0.00043838582,0.015701707,0.000068047964,0.00019398914,0.00070824084,0.000085386535,0.77790725,0.19458733,0.0017636714,0.008330538,0.00014262916],"about_ca_topic_score_codex":0.0035985457,"about_ca_topic_score_gemma":0.0054805144,"teacher_disagreement_score":0.0035985457,"about_ca_system_score_codex":0.00027128623,"about_ca_system_score_gemma":0.0006798594,"threshold_uncertainty_score":0.008210599},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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)","score_opus":0.03368209746036197,"score_gpt":0.31816619433834814,"score_spread":0.28448409687798615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1971709796","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004131644,0.0002667759,0.98713326,0.000053991786,0.000116268006,0.0001364739,0.0003200383,0.007196259,0.0006452146],"genre_scores_gemma":[0.01917891,0.00032858062,0.9725609,0.00008562836,0.000067435,0.00012058686,0.0011665004,0.0006739909,0.0058175777],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99839467,0.00010430516,0.00014285378,0.00042371472,0.00079306203,0.00014147926],"domain_scores_gemma":[0.9976816,0.0002733844,0.00020057101,0.00094479794,0.0008158614,0.00008377949],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010597006,0.0014478444,0.0016693615,0.0027961258,0.0007874239,0.0020995801,0.002068343,0.0018016025,0.0046002874],"category_scores_gemma":[0.0024643547,0.0007193431,0.0019604277,0.00256967,0.00081354723,0.0016838937,0.0019203146,0.0013684871,0.007726496],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014910298,0.00012419847,0.00088187103,0.00048800482,0.00011737297,0.00020010381,0.00013927648,0.0024605491,0.19110587,0.0017061257,0.006816606,0.7958109],"study_design_scores_gemma":[0.0000709722,0.00036515543,0.009925902,0.000098725526,0.00031776336,0.003600226,0.0002235107,0.16729335,0.7279857,0.0043558767,0.085574195,0.0001886082],"about_ca_topic_score_codex":0.0015402714,"about_ca_topic_score_gemma":0.0031716228,"teacher_disagreement_score":0.0046002874,"about_ca_system_score_codex":0.00038957802,"about_ca_system_score_gemma":0.0011279898,"threshold_uncertainty_score":0.015389502},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.014604408792707106,"score_gpt":0.2906842237893361,"score_spread":0.27607981499662904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1977202248","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013488947,0.00043284002,0.9394773,0.00019269761,0.00024682857,0.0006504088,0.007850831,0.03302616,0.0046339543],"genre_scores_gemma":[0.07027875,0.0003765993,0.87818503,0.0001018996,0.00010282072,0.0009050324,0.04155602,0.0052009104,0.0032929236],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9959002,0.00085035915,0.000628454,0.0013472677,0.0010821733,0.00019145374],"domain_scores_gemma":[0.98228735,0.00796724,0.0008118307,0.0047753756,0.003907377,0.00025094586],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035072078,0.0022871515,0.001763391,0.0072944066,0.0017384455,0.0044584596,0.0040755337,0.0024152522,0.030312274],"category_scores_gemma":[0.022079581,0.0018634896,0.0022446604,0.00506553,0.0016083585,0.0053213416,0.004006347,0.0039681536,0.013641828],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028484515,0.00025629913,0.0025098678,0.0019186485,0.00020418364,0.0010135266,0.0011404295,0.0378093,0.050473113,0.028960085,0.043967683,0.83146214],"study_design_scores_gemma":[0.00027768998,0.0003703806,0.0048307753,0.00044471578,0.0003098024,0.0024239821,0.0012823857,0.71191937,0.08543219,0.06740991,0.12504719,0.0002516443],"about_ca_topic_score_codex":0.003274394,"about_ca_topic_score_gemma":0.0073716114,"teacher_disagreement_score":0.030312274,"about_ca_system_score_codex":0.0012833629,"about_ca_system_score_gemma":0.002354125,"threshold_uncertainty_score":0.10140467},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.020177539809246366,"score_gpt":0.2806059995565203,"score_spread":0.26042845974727397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1977304445","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06859697,0.0013332083,0.92231816,0.0001279152,0.00017822177,0.000059970713,0.0004250497,0.0036220248,0.003338556],"genre_scores_gemma":[0.48210287,0.0015978544,0.49820727,0.000107282896,0.00016255782,0.00013240798,0.0011679822,0.0003509928,0.016170798],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997278,0.000033871005,0.000021403614,0.000086761305,0.00007761525,0.000052589377],"domain_scores_gemma":[0.9996191,0.0001729448,0.000027226166,0.000043705448,0.00010957328,0.000027440201],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039914862,0.000486118,0.0007877883,0.0008947763,0.00036802416,0.0009068244,0.00066365814,0.0010355124,0.002391317],"category_scores_gemma":[0.0008029756,0.0005130299,0.00068607694,0.0008980155,0.00019892292,0.0009309292,0.0003729858,0.0007460034,0.0016486202],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00072498625,0.00014031483,0.0025345928,0.00023802575,0.00014608592,0.00021873509,0.00011828909,0.04458442,0.18334366,0.0011013749,0.0023406649,0.7645087],"study_design_scores_gemma":[0.000029808662,0.00013522606,0.011521008,0.00004613757,0.00021031768,0.00026706335,0.00008530805,0.8972564,0.08370703,0.0016745368,0.005010704,0.000056470686],"about_ca_topic_score_codex":0.005229861,"about_ca_topic_score_gemma":0.0073127686,"teacher_disagreement_score":0.005229861,"about_ca_system_score_codex":0.0003065162,"about_ca_system_score_gemma":0.00047880522,"threshold_uncertainty_score":0.010398865},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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)","score_opus":0.043528409929608096,"score_gpt":0.3182998786613794,"score_spread":0.2747714687317713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1978799108","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011230424,0.0002687554,0.98498154,0.00008887056,0.00006266083,0.0000777025,0.00015012184,0.0012715932,0.001868326],"genre_scores_gemma":[0.08782488,0.00033652308,0.908295,0.00007261696,0.000036378337,0.00008001833,0.0003037978,0.000110178626,0.0029406939],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99945265,0.000043844357,0.000047930753,0.00020223642,0.00022043056,0.000032991844],"domain_scores_gemma":[0.9996226,0.00012163773,0.000028618884,0.0000775695,0.00012481085,0.00002487896],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040011227,0.0005687526,0.00077875843,0.0016561358,0.00062824937,0.0015613404,0.0013275777,0.00072604907,0.0029798665],"category_scores_gemma":[0.0010277682,0.0003929576,0.0012468932,0.0010989221,0.00080459984,0.0025073444,0.001115883,0.0010681481,0.0011368283],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012179937,0.00015498194,0.0019151809,0.00035841187,0.00017157425,0.0005866801,0.00093711785,0.024241382,0.11678146,0.093489125,0.0033227867,0.7579195],"study_design_scores_gemma":[0.000047225585,0.0001780705,0.0026842472,0.00014252706,0.00027284346,0.0012459039,0.0006653479,0.78648585,0.05954703,0.11160574,0.036987726,0.00013741312],"about_ca_topic_score_codex":0.005790562,"about_ca_topic_score_gemma":0.007975962,"teacher_disagreement_score":0.005790562,"about_ca_system_score_codex":0.00061070785,"about_ca_system_score_gemma":0.0010528148,"threshold_uncertainty_score":0.01151371},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.06057137742983903,"score_gpt":0.29516846496590715,"score_spread":0.23459708753606812,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1979902991","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019284891,0.0004071683,0.978827,0.00006535383,0.000078145225,0.000022679247,0.000020685422,0.0006004562,0.000693627],"genre_scores_gemma":[0.4510942,0.0007776639,0.54181856,0.00013501476,0.0001866453,0.00012503065,0.0003110774,0.00023833603,0.0053135017],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986865,0.00041767786,0.000061864586,0.00022797432,0.00051848503,0.000087499946],"domain_scores_gemma":[0.9985366,0.000562251,0.000114108996,0.00018314576,0.0005608543,0.000042927517],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012238054,0.00069521356,0.000980776,0.0009998555,0.0004310119,0.0007949046,0.0007897681,0.0006458428,0.0023017216],"category_scores_gemma":[0.0025421518,0.00021808481,0.0007050393,0.00101987,0.00046099178,0.0009363596,0.0005301413,0.0010578189,0.0017797422],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000737886,0.00025461146,0.0012484377,0.00023366178,0.00010519071,0.00006987114,0.00007470487,0.017516738,0.14887868,0.006466854,0.002135883,0.8222774],"study_design_scores_gemma":[0.00004214881,0.00042131272,0.0036833985,0.00002507391,0.00012198153,0.0003071049,0.00004140681,0.89214593,0.09544427,0.002795505,0.004916189,0.000055783603],"about_ca_topic_score_codex":0.0007870957,"about_ca_topic_score_gemma":0.00071025535,"teacher_disagreement_score":0.0023017216,"about_ca_system_score_codex":0.00028152738,"about_ca_system_score_gemma":0.00042286183,"threshold_uncertainty_score":0.007700026},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.025016512414595626,"score_gpt":0.2759748070783409,"score_spread":0.25095829466374525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2009946426","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0109257875,0.00037444136,0.97185946,0.000120619596,0.0001573146,0.000082504535,0.0006501614,0.014321603,0.001508136],"genre_scores_gemma":[0.27872017,0.00053929,0.6976155,0.00036844966,0.00016752456,0.00041789553,0.0058387476,0.002762141,0.013570305],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99910057,0.00025996947,0.00009839935,0.00021101513,0.00020681536,0.0001233476],"domain_scores_gemma":[0.9973562,0.0015563675,0.00009193516,0.00029061703,0.00062531565,0.00007969456],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00083944865,0.0011430325,0.0013902487,0.0009875924,0.0007328301,0.0014938277,0.0014980822,0.0016963377,0.010469828],"category_scores_gemma":[0.004764719,0.0009927152,0.0009003261,0.0012085456,0.00035209671,0.0015256084,0.0013823096,0.0019598177,0.011332475],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006490962,0.00015616968,0.0007085494,0.00024052456,0.00012730042,0.00035676075,0.00014738349,0.05523019,0.046383947,0.004176949,0.009633396,0.8821898],"study_design_scores_gemma":[0.000041498697,0.00006286581,0.0004997113,0.000027172277,0.000041893316,0.00013243298,0.000054195574,0.9637096,0.026472174,0.005930892,0.002992218,0.000035395216],"about_ca_topic_score_codex":0.010587623,"about_ca_topic_score_gemma":0.022582553,"teacher_disagreement_score":0.010587623,"about_ca_system_score_codex":0.000622863,"about_ca_system_score_gemma":0.0018510275,"threshold_uncertainty_score":0.03502506},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Graphics; Computer science; Computer graphics (images)","score_opus":0.018557932251957097,"score_gpt":0.27138354599134834,"score_spread":0.2528256137393912,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2010145024","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028553146,0.07598247,0.055547215,0.013545227,0.5631354,0.00050358527,0.0016204312,0.0054183905,0.281392],"genre_scores_gemma":[0.00814542,0.025626896,0.01087703,0.0035433262,0.12521186,0.0001988881,0.0032103416,0.0017367319,0.82144946],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99875534,0.0001289122,0.00010787496,0.00032254294,0.0005639478,0.000121308716],"domain_scores_gemma":[0.9962656,0.0004159955,0.00012233676,0.0005515759,0.0020462372,0.000598341],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011822591,0.002245831,0.002727595,0.0054386044,0.001380028,0.0054600798,0.002238656,0.002618138,0.21251297],"category_scores_gemma":[0.002576675,0.0006372325,0.001310494,0.0037287413,0.000756404,0.0035655233,0.0021931285,0.0020646143,0.13262543],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000060891656,0.000073356176,0.00017377149,0.00036262983,0.00002902252,0.00010542377,0.00001762971,0.00024678296,0.0021324712,0.0024258948,0.7712793,0.22309278],"study_design_scores_gemma":[0.000011149708,0.00008631869,0.0005155074,0.0001055683,0.000027156198,0.00032995836,0.000021757138,0.0008831092,0.001080028,0.0020053969,0.99491787,0.000016350652],"about_ca_topic_score_codex":0.001123298,"about_ca_topic_score_gemma":0.0025296551,"teacher_disagreement_score":0.21251297,"about_ca_system_score_codex":0.00091570977,"about_ca_system_score_gemma":0.0013355605,"threshold_uncertainty_score":0.7109267},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.04020382215980793,"score_gpt":0.2903658157744112,"score_spread":0.25016199361460323,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2029526043","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03099354,0.00032137916,0.9625005,0.000085501626,0.00012203913,0.00010603398,0.00007939541,0.0050380244,0.0007534914],"genre_scores_gemma":[0.19796619,0.00031596393,0.7935607,0.00011294269,0.000057193192,0.000096597345,0.0005279938,0.00067469437,0.0066877576],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9980622,0.00019146941,0.00024273837,0.0004471308,0.0008780605,0.00017837265],"domain_scores_gemma":[0.9938923,0.0010538816,0.0006247776,0.0011388116,0.0031378649,0.00015242913],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010599662,0.0012684538,0.00094627653,0.0023609048,0.001209289,0.0019677521,0.0019561648,0.001215949,0.0035627275],"category_scores_gemma":[0.0040406403,0.00046210532,0.00079364365,0.0015864854,0.00049762503,0.0014221214,0.0010562722,0.0014693268,0.0018559572],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045287053,0.00018426812,0.0028054654,0.0002311035,0.0000897837,0.0005049007,0.00034084893,0.006173949,0.14597507,0.0013311055,0.0025164462,0.83939415],"study_design_scores_gemma":[0.00003861161,0.00043748118,0.006944356,0.000074155185,0.0002562047,0.0025082491,0.00039156814,0.3777846,0.5923817,0.0020219176,0.017049469,0.000111665264],"about_ca_topic_score_codex":0.0033652547,"about_ca_topic_score_gemma":0.0036917531,"teacher_disagreement_score":0.0035627275,"about_ca_system_score_codex":0.00041577985,"about_ca_system_score_gemma":0.0016477196,"threshold_uncertainty_score":0.011918485},"labels":[],"label_agreement":null},{"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.04133708286574984,"score_gpt":0.2874709149178449,"score_spread":0.24613383205209505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2031071334","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14982636,0.0058355387,0.8087582,0.00081994245,0.00057197193,0.0002488766,0.0019371441,0.0072560757,0.024745932],"genre_scores_gemma":[0.45050514,0.005696739,0.49826172,0.0003098201,0.00039368198,0.0002239884,0.005776577,0.00083037384,0.038001936],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99944586,0.0000787696,0.000071117756,0.00012334024,0.00021657623,0.00006434072],"domain_scores_gemma":[0.99927384,0.00017758037,0.00008768176,0.0001736412,0.00025426663,0.0000331187],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047236943,0.0006830465,0.0010519716,0.0024623042,0.00041255774,0.0022686548,0.0008870837,0.0006253222,0.008760522],"category_scores_gemma":[0.0029478623,0.00026057547,0.0007303488,0.0020800678,0.00043963315,0.0025631273,0.00089962385,0.0006130803,0.008744781],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003721586,0.0000936623,0.0007517438,0.00048363968,0.00004816827,0.00046725158,0.00038981397,0.0027950413,0.13637087,0.028039273,0.013034514,0.8171539],"study_design_scores_gemma":[0.0001963501,0.0007533673,0.0077573555,0.00032786696,0.0003932123,0.0060928147,0.0011381448,0.3485678,0.42457542,0.044063676,0.16592684,0.00020715932],"about_ca_topic_score_codex":0.0008704512,"about_ca_topic_score_gemma":0.00068522914,"teacher_disagreement_score":0.008760522,"about_ca_system_score_codex":0.00055303104,"about_ca_system_score_gemma":0.0007133975,"threshold_uncertainty_score":0.029306829},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.023166029043117906,"score_gpt":0.2844399393836243,"score_spread":0.26127391034050634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2031691644","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0074854684,0.00017693981,0.9904812,0.00005745753,0.000036066725,0.00004161299,0.00003817483,0.0010109951,0.0006721433],"genre_scores_gemma":[0.09073756,0.00027687367,0.9039994,0.00008844521,0.000028543014,0.00012278136,0.00037201185,0.00027348832,0.0041009327],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994881,0.00008124229,0.000027094933,0.00010451015,0.0002297506,0.00006935721],"domain_scores_gemma":[0.9992447,0.00013664046,0.00004809104,0.00011784694,0.00042646934,0.000026334106],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007112382,0.000694063,0.00096206955,0.0013464065,0.0007527776,0.0010562616,0.0015243544,0.0010826797,0.004044774],"category_scores_gemma":[0.0016337282,0.00045239908,0.0008443447,0.0012985076,0.00047589853,0.0012137012,0.0010223726,0.001373743,0.0024295498],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003673306,0.00012400854,0.00074880215,0.00012219431,0.00011031653,0.00005359576,0.00013441141,0.046400525,0.0818105,0.006228683,0.004514195,0.85938543],"study_design_scores_gemma":[0.000028240001,0.00008266262,0.0010598792,0.000010958096,0.00005200823,0.00018433295,0.000044911438,0.9496716,0.041270174,0.00257306,0.004989042,0.000033102893],"about_ca_topic_score_codex":0.009141272,"about_ca_topic_score_gemma":0.012202067,"teacher_disagreement_score":0.009141272,"about_ca_system_score_codex":0.00073194824,"about_ca_system_score_gemma":0.0014947093,"threshold_uncertainty_score":0.018176138},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"","keywords":"Philosophy","score_opus":0.019754827096314754,"score_gpt":0.2702978268210915,"score_spread":0.2505429997247767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2043851063","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000074920106,0.0022360838,0.00015826408,0.026732065,0.9589999,0.00004351598,0.00019372141,0.00010508471,0.011456453],"genre_scores_gemma":[0.0019622478,0.003412328,0.00034172734,0.02847433,0.83619165,0.000077559234,0.00039633276,0.00024788413,0.12889597],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99766207,0.00027551636,0.00019041954,0.00037786778,0.0012808113,0.00021337083],"domain_scores_gemma":[0.9809192,0.00331793,0.00095989165,0.0009277103,0.010772105,0.0031031715],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031387021,0.0012840506,0.001012904,0.0034744365,0.0024054558,0.0048975074,0.001349102,0.0042729,0.11287044],"category_scores_gemma":[0.02447585,0.00050775125,0.0009809863,0.0010945888,0.0009318845,0.0020921144,0.0016439385,0.0070847324,0.061187476],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016040458,0.000004169692,0.000019181207,0.000054512573,0.0000026243004,0.00004341767,0.000007017268,0.000007545688,0.000052630116,0.00022545907,0.9934644,0.0061030113],"study_design_scores_gemma":[0.000012410196,0.000010355261,0.0001565204,0.000100021934,0.0000065531117,0.00008922841,0.000023514976,0.000025812633,0.00009572262,0.00053266773,0.99894124,0.0000060145626],"about_ca_topic_score_codex":0.0021264036,"about_ca_topic_score_gemma":0.0046655103,"teacher_disagreement_score":0.11287044,"about_ca_system_score_codex":0.0019793343,"about_ca_system_score_gemma":0.0027988965,"threshold_uncertainty_score":0.37758923},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.014736436623662514,"score_gpt":0.28197751618141864,"score_spread":0.2672410795577561,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2050738804","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48947096,0.0045081526,0.48698333,0.0002598866,0.0007789917,0.0002839039,0.001625525,0.004363678,0.0117256185],"genre_scores_gemma":[0.77767533,0.00123516,0.19952041,0.00009383962,0.00015089536,0.00009390506,0.0030987181,0.00022466216,0.017906995],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99918014,0.00008243757,0.000079073085,0.00015348318,0.0004112212,0.00009361253],"domain_scores_gemma":[0.9980951,0.00047409322,0.0001588224,0.00017735231,0.0010128748,0.000081753824],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004650752,0.0004754324,0.00094832265,0.003105893,0.00035290848,0.0012828778,0.00089152897,0.0006795472,0.0050688353],"category_scores_gemma":[0.0021175374,0.00013749301,0.0004640956,0.002135274,0.00031178715,0.00097305235,0.00052623474,0.0005296322,0.0030688972],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00082051876,0.00014797032,0.0028158745,0.00022731895,0.00006348461,0.000089003166,0.000069971065,0.0053425846,0.07097971,0.00083166506,0.0028923824,0.9157195],"study_design_scores_gemma":[0.00009087117,0.000922292,0.036141146,0.00011029461,0.00018973093,0.0014920819,0.00030695694,0.7920259,0.15171967,0.0024815,0.014419799,0.00009965047],"about_ca_topic_score_codex":0.004140646,"about_ca_topic_score_gemma":0.0042971005,"teacher_disagreement_score":0.0050688353,"about_ca_system_score_codex":0.0005348213,"about_ca_system_score_gemma":0.0006985462,"threshold_uncertainty_score":0.016956925},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.021243783655712518,"score_gpt":0.32094510944013094,"score_spread":0.29970132578441844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2060595667","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07378591,0.0031822647,0.85395443,0.0004915405,0.000784216,0.00066365587,0.004002796,0.03564485,0.02749044],"genre_scores_gemma":[0.24254695,0.0023514233,0.70420873,0.00034225665,0.00026272438,0.00035780438,0.007366588,0.002978953,0.03958453],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996356,0.00002619809,0.000025869078,0.00009736446,0.00011454965,0.000100500074],"domain_scores_gemma":[0.99944586,0.0000740709,0.000034971665,0.00009729149,0.00030399696,0.000043692206],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024676166,0.0011279661,0.00083511183,0.003970182,0.00091834273,0.0014961455,0.00071254314,0.00072937505,0.019727996],"category_scores_gemma":[0.0006903119,0.00040885183,0.00086679374,0.0027864194,0.0003595354,0.0012547827,0.0005765906,0.0007438042,0.014175184],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033842627,0.00007122637,0.00058254175,0.00027120838,0.000031674197,0.0001364617,0.0000600579,0.0009901114,0.4233122,0.0015990281,0.008742783,0.5638643],"study_design_scores_gemma":[0.00004315679,0.00022393561,0.009144783,0.00006472364,0.00017258503,0.000982378,0.00019748078,0.070856996,0.8450336,0.002774797,0.0704397,0.00006593741],"about_ca_topic_score_codex":0.003925539,"about_ca_topic_score_gemma":0.0071889223,"teacher_disagreement_score":0.019727996,"about_ca_system_score_codex":0.0005721491,"about_ca_system_score_gemma":0.0008595192,"threshold_uncertainty_score":0.065996766},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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)","score_opus":0.019990210222632428,"score_gpt":0.2875741722566527,"score_spread":0.2675839620340203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2079125047","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38890916,0.0009347467,0.6061595,0.0003569759,0.000062580184,0.00008005777,0.0008305925,0.0009046913,0.0017616473],"genre_scores_gemma":[0.8938023,0.00075673376,0.1023057,0.000059686736,0.0001100331,0.000051118146,0.0014032337,0.000060400605,0.0014507591],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997948,0.000029367931,0.000012539772,0.000035961075,0.00009016744,0.00003711187],"domain_scores_gemma":[0.999363,0.00022535038,0.00008905071,0.00008313486,0.00019710521,0.000042434738],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034161244,0.00021022657,0.0004752342,0.0015925037,0.00018242818,0.00052502006,0.000325722,0.00037483152,0.0011910395],"category_scores_gemma":[0.0014250149,0.00014146273,0.00037178767,0.0011280903,0.00025059737,0.00048593292,0.0003384949,0.00050458405,0.0004042103],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001366874,0.00024931773,0.008171117,0.00026286536,0.00006185105,0.00014975588,0.000109135966,0.050382968,0.16187069,0.0033431377,0.004079249,0.7699531],"study_design_scores_gemma":[0.000020591337,0.00011953725,0.011794051,0.000014155769,0.000032899155,0.00016062793,0.00006575468,0.96959555,0.01553257,0.0017041817,0.00094710535,0.000012950976],"about_ca_topic_score_codex":0.0031565123,"about_ca_topic_score_gemma":0.0032581107,"teacher_disagreement_score":0.0031565123,"about_ca_system_score_codex":0.00027686445,"about_ca_system_score_gemma":0.00036929818,"threshold_uncertainty_score":0.0062763095},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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)","score_opus":0.017711912844026425,"score_gpt":0.2722801801429247,"score_spread":0.2545682672988983,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2080016965","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11471487,0.00012272848,0.8810783,0.00009117762,0.00003628013,0.00004605804,0.000047166563,0.00041481425,0.0034486575],"genre_scores_gemma":[0.7156501,0.00009747022,0.2809927,0.000039516515,0.000013406356,0.00005968848,0.000085465224,0.00008464629,0.0029769433],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9999058,0.0000184349,0.000004497304,0.000028844694,0.000025840933,0.00001649598],"domain_scores_gemma":[0.9997762,0.00008801293,0.000028478073,0.000023769737,0.00007115905,0.000012402884],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027529197,0.0002331523,0.00037128298,0.00046325644,0.00029001897,0.0004326519,0.0005539406,0.00045441752,0.0015086728],"category_scores_gemma":[0.0008597735,0.00021697723,0.00053029746,0.00038255367,0.000263152,0.00035808998,0.00027970917,0.00043770685,0.00020603983],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007578431,0.00009958563,0.0005748503,0.000049668626,0.000035363406,0.000093416435,0.00009552555,0.7991659,0.049252626,0.022357866,0.0005983512,0.12760106],"study_design_scores_gemma":[0.000005252338,0.000024628944,0.00015237743,0.0000029927774,0.000008986381,0.000017181888,0.000010854002,0.9936917,0.0029757943,0.002841675,0.0002636982,0.0000048683223],"about_ca_topic_score_codex":0.006479887,"about_ca_topic_score_gemma":0.0073660975,"teacher_disagreement_score":0.006479887,"about_ca_system_score_codex":0.0007344763,"about_ca_system_score_gemma":0.00054947945,"threshold_uncertainty_score":0.012884319},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.030786065186809198,"score_gpt":0.29448136594634206,"score_spread":0.26369530075953285,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2092772700","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019431075,0.48018867,0.41650194,0.0032638097,0.0029580232,0.0006478393,0.0036580013,0.005017478,0.06833321],"genre_scores_gemma":[0.09784291,0.38080287,0.43587664,0.0025846588,0.0028258502,0.0003321147,0.012818837,0.00077937247,0.06613683],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982412,0.00020583184,0.00020194736,0.0005259518,0.0007140086,0.00011110426],"domain_scores_gemma":[0.9980573,0.00052182935,0.00011045473,0.00039780865,0.00082251895,0.00009011932],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010809895,0.0008759959,0.0015458475,0.005759725,0.00079465576,0.0029848916,0.0026856433,0.00097410835,0.01804785],"category_scores_gemma":[0.0035049124,0.0007528455,0.0011708261,0.010949121,0.0005305667,0.0049093035,0.0010228573,0.0009142207,0.009993939],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006931249,0.00010949903,0.0011275903,0.0011233571,0.00003513611,0.00003889031,0.000041574065,0.0018111911,0.0021192785,0.0057789087,0.022431,0.9653144],"study_design_scores_gemma":[0.000038982285,0.00047204638,0.006118206,0.0009973837,0.00015461199,0.0028354416,0.00044704197,0.051576685,0.01794459,0.018168896,0.90108144,0.0001646585],"about_ca_topic_score_codex":0.005691668,"about_ca_topic_score_gemma":0.0070829513,"teacher_disagreement_score":0.01804785,"about_ca_system_score_codex":0.00093082455,"about_ca_system_score_gemma":0.0019055452,"threshold_uncertainty_score":0.060376048},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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)","score_opus":0.027270273376986138,"score_gpt":0.30668449680639026,"score_spread":0.27941422342940414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2098345386","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06427073,0.32154948,0.59867007,0.002675424,0.0007385037,0.0004338848,0.0011711014,0.002961402,0.007529376],"genre_scores_gemma":[0.22658704,0.22136475,0.52921677,0.0014235227,0.002899596,0.0005866138,0.005379091,0.0004909603,0.012051635],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9970958,0.00045201925,0.0003520037,0.0007316673,0.0012311366,0.00013734052],"domain_scores_gemma":[0.99386287,0.0026935118,0.0003624112,0.00046192622,0.0024596332,0.00015973597],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037310717,0.0012181161,0.0027942224,0.0039646965,0.00075907,0.003185854,0.0024520608,0.0019676173,0.0014349861],"category_scores_gemma":[0.008718997,0.0007173229,0.00096530194,0.0062391246,0.00041973474,0.0036155651,0.0006418457,0.0012422245,0.0017127588],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015934266,0.00025394012,0.004536844,0.0011340362,0.000094673014,0.000025460591,0.000054040633,0.0050326777,0.0040211733,0.001621063,0.007957368,0.97510934],"study_design_scores_gemma":[0.00012194636,0.0029267771,0.03261197,0.0018506895,0.00092065043,0.0027443378,0.00079098035,0.70522994,0.06805705,0.0206951,0.16373806,0.0003125297],"about_ca_topic_score_codex":0.003638311,"about_ca_topic_score_gemma":0.0038627246,"teacher_disagreement_score":0.0039646965,"about_ca_system_score_codex":0.0010089778,"about_ca_system_score_gemma":0.0017485622,"threshold_uncertainty_score":0.019732058},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.0645111069674379,"score_gpt":0.3269907466057523,"score_spread":0.2624796396383144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107835247","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033592437,0.00019852888,0.9953117,0.000038411927,0.000020391082,0.000030336445,0.000049716877,0.000681858,0.00030994887],"genre_scores_gemma":[0.06199988,0.0004179039,0.93318605,0.0000766848,0.000038504822,0.00011935288,0.00039711173,0.00029380427,0.003470736],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999479,0.000086685635,0.00003526851,0.00008086588,0.00027637056,0.00004174537],"domain_scores_gemma":[0.9995289,0.00014269876,0.000038755064,0.00007750588,0.00018081116,0.000031442265],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006694554,0.00052734645,0.00081525533,0.0014965906,0.00041448954,0.0011588996,0.0011909135,0.00067350396,0.00455119],"category_scores_gemma":[0.0011385899,0.00046156888,0.0010832915,0.0012200583,0.00037467346,0.00096706284,0.0008124003,0.0014079089,0.0021343457],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017365982,0.00010943254,0.00037023233,0.00019659534,0.00009530667,0.000042101576,0.0000782082,0.032631688,0.069764525,0.003331786,0.0026007034,0.8906057],"study_design_scores_gemma":[0.000019470182,0.00011841568,0.0015439744,0.000024847279,0.000070696755,0.00013763721,0.00003115709,0.95325893,0.037793886,0.0016049979,0.0053556617,0.000040403647],"about_ca_topic_score_codex":0.004231859,"about_ca_topic_score_gemma":0.0064739063,"teacher_disagreement_score":0.00455119,"about_ca_system_score_codex":0.0005889168,"about_ca_system_score_gemma":0.0009764489,"threshold_uncertainty_score":0.015225291},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.020483563872654792,"score_gpt":0.31766699938688503,"score_spread":0.2971834355142302,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119140562","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7148488,0.0064564664,0.2371968,0.0042812275,0.0013510721,0.00016473245,0.0018355226,0.00087183365,0.03299347],"genre_scores_gemma":[0.98308384,0.00055831484,0.012404573,0.00017832406,0.00050135993,0.00004399843,0.00042363978,0.0001356076,0.002670407],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9961378,0.0013637269,0.00032520734,0.00076513283,0.0011312941,0.00027673578],"domain_scores_gemma":[0.9653045,0.024176018,0.0028692023,0.0031674737,0.0028238534,0.001658897],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037725058,0.0005028419,0.00087921956,0.0038610685,0.0013578455,0.007157531,0.0006359284,0.0009855335,0.0047258004],"category_scores_gemma":[0.035882115,0.00033358872,0.00050157384,0.0040916083,0.0021619217,0.0059456583,0.0026290931,0.001862126,0.0008613692],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002365535,0.0005775017,0.22017327,0.00064233266,0.00023635842,0.00071689987,0.008353383,0.008914478,0.022321058,0.095168404,0.011657593,0.62887317],"study_design_scores_gemma":[0.000116584786,0.0006824649,0.27768672,0.00069871766,0.0006184805,0.0036202255,0.01255278,0.2893348,0.017241433,0.35284638,0.044269953,0.00033142685],"about_ca_topic_score_codex":0.001149518,"about_ca_topic_score_gemma":0.0010568928,"teacher_disagreement_score":0.007157531,"about_ca_system_score_codex":0.0007977855,"about_ca_system_score_gemma":0.00070617575,"threshold_uncertainty_score":0.019951165},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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)","score_opus":0.03427482938487292,"score_gpt":0.2878837232854027,"score_spread":0.25360889390052976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120888827","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.52493286,0.0013067022,0.46104276,0.00019012384,0.0004067695,0.00011210671,0.00072247296,0.003276693,0.0080095],"genre_scores_gemma":[0.90496045,0.0005308581,0.087241,0.00004622138,0.00009295554,0.000027191536,0.0006432763,0.00022602345,0.006232021],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995665,0.000038468195,0.000029942696,0.00010480481,0.0001731192,0.000087208005],"domain_scores_gemma":[0.9987394,0.0002857107,0.00021213312,0.0002565257,0.0004328766,0.00007329034],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003741853,0.00051884865,0.0008279565,0.0014839288,0.0004670359,0.0011059153,0.00040422246,0.0006617602,0.0036493596],"category_scores_gemma":[0.0015634163,0.00026947918,0.0004388211,0.00085678644,0.0002272942,0.0008803324,0.0004847569,0.0005889303,0.0024435844],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018303812,0.000119491655,0.006583173,0.00017569095,0.000057330097,0.00040021277,0.00006471709,0.0032716324,0.54201,0.00044826258,0.0014115744,0.44362757],"study_design_scores_gemma":[0.000113988455,0.0005947077,0.0347706,0.000050697206,0.00022021525,0.0022884856,0.00022551687,0.33005968,0.6251548,0.0006630699,0.0057879672,0.00007031847],"about_ca_topic_score_codex":0.0009291353,"about_ca_topic_score_gemma":0.001423986,"teacher_disagreement_score":0.0036493596,"about_ca_system_score_codex":0.00016592548,"about_ca_system_score_gemma":0.00042253145,"threshold_uncertainty_score":0.012208283},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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)","score_opus":0.01284765546056195,"score_gpt":0.2665302875074339,"score_spread":0.25368263204687197,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122160657","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.059659686,0.0008336931,0.93725085,0.00012261006,0.00017088579,0.00007558809,0.00015473974,0.0010565642,0.0006753748],"genre_scores_gemma":[0.71788317,0.0005438796,0.27587774,0.00009719721,0.00020737678,0.00025100226,0.00090063707,0.00023268507,0.0040062587],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99924767,0.0002540123,0.00008360092,0.00013744792,0.00019343097,0.00008387587],"domain_scores_gemma":[0.9977908,0.0011022239,0.00010261381,0.00025758884,0.0006593676,0.00008737555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019787995,0.0007636899,0.0016156851,0.0009129412,0.0006004188,0.0007659358,0.0009000547,0.00065992336,0.0016588705],"category_scores_gemma":[0.0037571264,0.00041107048,0.0010867418,0.0010633644,0.00025317568,0.0008212356,0.0009932446,0.001126802,0.00063561514],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003503788,0.0001941943,0.0025244553,0.00008942215,0.00026689374,0.00008995665,0.00007840437,0.17192435,0.01479146,0.001897092,0.0031869707,0.80460656],"study_design_scores_gemma":[0.000009417725,0.00007484534,0.0011360922,0.00000812043,0.000038372626,0.000035418685,0.000012580575,0.9927301,0.0037004268,0.0015795106,0.0006669623,0.000008147719],"about_ca_topic_score_codex":0.0030690623,"about_ca_topic_score_gemma":0.0038059964,"teacher_disagreement_score":0.0030690623,"about_ca_system_score_codex":0.0003345346,"about_ca_system_score_gemma":0.00065768184,"threshold_uncertainty_score":0.010465026},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.0912653964310988,"score_gpt":0.2830081094912913,"score_spread":0.1917427130601925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130604705","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00945413,0.00045888041,0.9731818,0.00013060069,0.00014024202,0.000104792496,0.00027944293,0.014420702,0.0018293539],"genre_scores_gemma":[0.27491248,0.00047830402,0.7080863,0.00075904024,0.00018587284,0.00037444432,0.0014310263,0.0010766523,0.012695825],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989134,0.00011627192,0.0000664798,0.00033583713,0.00048290813,0.00008515352],"domain_scores_gemma":[0.99907136,0.00027605658,0.000076703196,0.00020685882,0.00031338044,0.000055600904],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010848297,0.0009751502,0.0017463771,0.0008329969,0.00061165995,0.0010655847,0.0024148342,0.0019278546,0.009595797],"category_scores_gemma":[0.0020121415,0.00072660076,0.00075412856,0.0005911275,0.00041218958,0.0017861811,0.0015678343,0.0010872383,0.0066292235],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007572141,0.00017106936,0.00054028403,0.00027949712,0.000102101585,0.00022121494,0.00003956868,0.010747214,0.29861692,0.0024293717,0.007322165,0.67877346],"study_design_scores_gemma":[0.00013283631,0.00041966263,0.0029567783,0.00005313014,0.00020085517,0.0012663302,0.000024615149,0.78869283,0.18494561,0.00419385,0.016926683,0.00018676341],"about_ca_topic_score_codex":0.0021100633,"about_ca_topic_score_gemma":0.0032876704,"teacher_disagreement_score":0.009595797,"about_ca_system_score_codex":0.00037452916,"about_ca_system_score_gemma":0.0008287734,"threshold_uncertainty_score":0.032101214},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.015359839613659432,"score_gpt":0.30480189746361436,"score_spread":0.2894420578499549,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140217726","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76479864,0.013254227,0.16796455,0.0016592325,0.0018227908,0.0008705674,0.006833723,0.01967346,0.02312295],"genre_scores_gemma":[0.7256222,0.0053697135,0.20976052,0.0009609122,0.0011279676,0.00017523844,0.015038895,0.0020926653,0.03985192],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99890864,0.00009180759,0.00010929696,0.00016521948,0.0005782543,0.00014675625],"domain_scores_gemma":[0.9974585,0.0005581348,0.0002006392,0.0005270564,0.0011089817,0.0001466682],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006145021,0.0024063727,0.0018916766,0.0038905074,0.0010341071,0.002114205,0.00075865485,0.0020781127,0.011284467],"category_scores_gemma":[0.0042396924,0.0004781543,0.0009214867,0.0021995876,0.0004579694,0.0017031651,0.00089820375,0.0010276958,0.009462752],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002554022,0.00027408978,0.0019468351,0.0010307359,0.00015414404,0.00208104,0.00014793045,0.0050422368,0.5464801,0.0004149548,0.01706991,0.42280388],"study_design_scores_gemma":[0.0001569093,0.0010244987,0.015867596,0.00018198983,0.0007033783,0.009102704,0.00069423625,0.15013577,0.7797054,0.0014141904,0.040866863,0.0001465992],"about_ca_topic_score_codex":0.004339493,"about_ca_topic_score_gemma":0.0048916987,"teacher_disagreement_score":0.011284467,"about_ca_system_score_codex":0.0006847548,"about_ca_system_score_gemma":0.00082302064,"threshold_uncertainty_score":0.037750304},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.025416727271112265,"score_gpt":0.29427239712386766,"score_spread":0.2688556698527554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2150428256","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23070063,0.0010055081,0.7636613,0.000110342866,0.00015187709,0.00011044163,0.00024396871,0.001693712,0.002322246],"genre_scores_gemma":[0.7710483,0.00047022963,0.21937095,0.0000776423,0.00008767377,0.00007734055,0.0006328222,0.00019085572,0.008044206],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99920696,0.00012864081,0.00007060452,0.00012423689,0.00035949543,0.00011004994],"domain_scores_gemma":[0.9991021,0.00023648526,0.000112857444,0.00016012827,0.0003428874,0.000045449575],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005274704,0.0004918646,0.00096527155,0.0010794923,0.0004821897,0.0006961063,0.00070315035,0.00046985285,0.0021725872],"category_scores_gemma":[0.0011186145,0.0002548346,0.0004905933,0.0008039894,0.0002025421,0.0008992459,0.00059879746,0.0004474246,0.0015104976],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009172906,0.00021833448,0.0024888834,0.00008724035,0.000045591187,0.00016664925,0.000050766823,0.0029216674,0.31870496,0.00041483843,0.0012515364,0.67273223],"study_design_scores_gemma":[0.00005964032,0.00066568464,0.024338713,0.000021700347,0.00016959236,0.001547318,0.00012047502,0.3541994,0.61254877,0.000606503,0.0056655845,0.000056546232],"about_ca_topic_score_codex":0.00076249224,"about_ca_topic_score_gemma":0.001317976,"teacher_disagreement_score":0.0021725872,"about_ca_system_score_codex":0.00015316931,"about_ca_system_score_gemma":0.00048795852,"threshold_uncertainty_score":0.0072680116},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.019305390146569124,"score_gpt":0.29005397605649735,"score_spread":0.27074858590992823,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2511810441","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38553122,0.0063890163,0.5139353,0.0012934933,0.0016700221,0.0021349096,0.023021445,0.023510892,0.04251362],"genre_scores_gemma":[0.44882888,0.00218323,0.4657864,0.00027219037,0.0010852524,0.00063419197,0.03272032,0.0008556209,0.047633946],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99886453,0.000065519926,0.00016261234,0.00030712044,0.0003988747,0.00020132078],"domain_scores_gemma":[0.99808997,0.0003123956,0.00016728301,0.0002233943,0.0010319152,0.00017501441],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005891942,0.0011416363,0.0012331476,0.0076664076,0.0011030813,0.0026853816,0.0007603782,0.0010147971,0.010523663],"category_scores_gemma":[0.0018238227,0.00024913036,0.0013116796,0.0049708253,0.0005454724,0.0011003294,0.00073124864,0.00074056705,0.014533564],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00067088904,0.00027240475,0.0058137714,0.00033461335,0.000057746867,0.00023641152,0.00019234918,0.0006307726,0.17503864,0.0008966539,0.010931886,0.80492383],"study_design_scores_gemma":[0.00019429256,0.0021490492,0.16056287,0.0003208271,0.00085927994,0.0039935485,0.002513676,0.14728498,0.56123066,0.0061894353,0.11448654,0.00021482467],"about_ca_topic_score_codex":0.0040740073,"about_ca_topic_score_gemma":0.006207831,"teacher_disagreement_score":0.010523663,"about_ca_system_score_codex":0.0006199843,"about_ca_system_score_gemma":0.0012988329,"threshold_uncertainty_score":0.035205185},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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)","score_opus":0.040408100307700194,"score_gpt":0.3229824232304629,"score_spread":0.2825743229227627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2617973426","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03779874,0.00015973033,0.9589485,0.0000980714,0.00002807639,0.00010865313,0.0003387821,0.0019426752,0.00057674677],"genre_scores_gemma":[0.50338525,0.00021851942,0.49133,0.00013209843,0.000031928397,0.00026891218,0.0019592224,0.00019165958,0.0024824792],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99936265,0.00014713666,0.000057350913,0.00016595433,0.00021591582,0.00005104419],"domain_scores_gemma":[0.9969029,0.0016129861,0.00019729376,0.00036937516,0.0008318039,0.000085682324],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010967238,0.0005689055,0.0006454591,0.0013220268,0.0003785863,0.0007844136,0.0013063095,0.0009924797,0.0018269932],"category_scores_gemma":[0.004559575,0.00051689416,0.0007718785,0.001468605,0.00036339933,0.0007940188,0.00076029554,0.0009728196,0.00080816064],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000374216,0.00023351582,0.004473373,0.000119750315,0.00009396684,0.00026577106,0.00011995845,0.7027947,0.011694357,0.0042660967,0.0024224778,0.27314186],"study_design_scores_gemma":[0.000004010969,0.000021231406,0.00018541148,0.0000021867406,0.0000036829827,0.000030795563,0.000008180925,0.9975424,0.001458229,0.00058209844,0.00015800315,0.0000037158636],"about_ca_topic_score_codex":0.010537316,"about_ca_topic_score_gemma":0.014278262,"teacher_disagreement_score":0.010537316,"about_ca_system_score_codex":0.00073765067,"about_ca_system_score_gemma":0.0010139786,"threshold_uncertainty_score":0.020951986},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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)","score_opus":0.016163325560731617,"score_gpt":0.29047505713680577,"score_spread":0.27431173157607414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2795776870","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21081424,0.0021863529,0.7725985,0.0004958912,0.0006102248,0.00017272349,0.001109306,0.008011308,0.004001532],"genre_scores_gemma":[0.72428656,0.0012372212,0.2587429,0.00037056502,0.00025027385,0.00017649517,0.0036590868,0.0005184863,0.010758465],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99915755,0.000095425035,0.00006260443,0.00030534496,0.0002251404,0.00015389406],"domain_scores_gemma":[0.99837095,0.00045770773,0.00013685678,0.00046686275,0.0004924896,0.00007512382],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006176246,0.0013188168,0.0012132989,0.0009468181,0.00038144572,0.0010380755,0.0010586678,0.0012115723,0.0036365327],"category_scores_gemma":[0.0030550647,0.00032995167,0.0008562661,0.0014119517,0.00046382824,0.0019734644,0.0011426498,0.0015528159,0.0033605255],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00067010307,0.00031859305,0.0011743578,0.00014637073,0.00007025611,0.00013996461,0.000045543413,0.016683176,0.06945097,0.00068751426,0.0050433534,0.90556985],"study_design_scores_gemma":[0.000073168405,0.0007948103,0.0044935276,0.00005694113,0.00015681834,0.0008326729,0.00017637329,0.881492,0.10291733,0.00366411,0.0052855853,0.000056506255],"about_ca_topic_score_codex":0.0015246426,"about_ca_topic_score_gemma":0.0021255508,"teacher_disagreement_score":0.0036365327,"about_ca_system_score_codex":0.00042190315,"about_ca_system_score_gemma":0.0010029471,"threshold_uncertainty_score":0.012165427},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.018857784790851477,"score_gpt":0.30297623664518386,"score_spread":0.2841184518543324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205487349","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012466774,0.05083363,0.892892,0.0037933085,0.0021566162,0.00026961404,0.0021940728,0.025851248,0.009542749],"genre_scores_gemma":[0.08164151,0.02430005,0.86097634,0.0017381643,0.001716242,0.00025374588,0.004877002,0.0035444081,0.020952562],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99829644,0.00035098247,0.00010361016,0.00051275175,0.000582937,0.00015327345],"domain_scores_gemma":[0.9962322,0.0010424498,0.00018897772,0.00087970466,0.0014420911,0.00021453778],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013437541,0.0018125345,0.002162649,0.002851219,0.0007864843,0.0038816694,0.0026395093,0.0024159485,0.013363559],"category_scores_gemma":[0.0029102655,0.0010417957,0.0012670332,0.0034292568,0.0011530212,0.0043513076,0.0012373067,0.0016980118,0.01733792],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000183488,0.00007089247,0.00064468075,0.000759302,0.000099551224,0.00004966681,0.00011889681,0.0015633947,0.04087686,0.0025760266,0.027161956,0.92589533],"study_design_scores_gemma":[0.00016513567,0.0008839645,0.009831396,0.0012575176,0.0005750432,0.0016037142,0.0012359642,0.20096633,0.2426459,0.054417226,0.48597845,0.0004394996],"about_ca_topic_score_codex":0.003026665,"about_ca_topic_score_gemma":0.0041673565,"teacher_disagreement_score":0.013363559,"about_ca_system_score_codex":0.00071832887,"about_ca_system_score_gemma":0.0013266684,"threshold_uncertainty_score":0.04470557},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.03474842508047755,"score_gpt":0.2758689477789538,"score_spread":0.24112052269847628,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4295128257","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3105428,0.0019379458,0.6714935,0.0004365105,0.00044639886,0.00031406508,0.0007588414,0.008523987,0.0055460157],"genre_scores_gemma":[0.79772323,0.00047436726,0.19340134,0.00024846097,0.00013384635,0.00007437185,0.0019149554,0.0001930084,0.0058364505],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999321,0.000209819,0.000035370642,0.00019346803,0.00015618662,0.00008417275],"domain_scores_gemma":[0.9989766,0.00037708884,0.00008114575,0.00025062103,0.00025246,0.000062144616],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013968805,0.00073732313,0.0008114951,0.0008274348,0.0002292821,0.000623596,0.0009386534,0.0008786258,0.001646335],"category_scores_gemma":[0.0026172143,0.00015276717,0.00063152896,0.0006702898,0.0003923564,0.00080182106,0.00079886994,0.0008653764,0.0015994459],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015276109,0.0004967758,0.0019430082,0.00033341072,0.00014064672,0.000367021,0.00017304198,0.1873859,0.099908076,0.0017034134,0.012187228,0.6938338],"study_design_scores_gemma":[0.000020475854,0.00013039056,0.000942082,0.000008403939,0.00001949009,0.00011235749,0.000048704856,0.97460324,0.021778105,0.00076168467,0.001559075,0.0000159658],"about_ca_topic_score_codex":0.002779217,"about_ca_topic_score_gemma":0.001818542,"teacher_disagreement_score":0.002779217,"about_ca_system_score_codex":0.0004012666,"about_ca_system_score_gemma":0.00044105446,"threshold_uncertainty_score":0.007387519},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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)","score_opus":0.02054236969264456,"score_gpt":0.28560940531171036,"score_spread":0.2650670356190658,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313201936","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12097199,0.00361919,0.86194694,0.00038882197,0.00037860396,0.00012522536,0.0005690509,0.0058337147,0.0061664656],"genre_scores_gemma":[0.8497379,0.0009930496,0.13247326,0.00039685308,0.00023702672,0.00010817652,0.001073416,0.00018955086,0.014790871],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99979943,0.00003332742,0.000010432891,0.00007005044,0.000043240165,0.000043443237],"domain_scores_gemma":[0.9995808,0.00016449975,0.000033867254,0.00005408391,0.00013174221,0.000034983193],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042932836,0.00080245745,0.00060808955,0.0006637606,0.00033005644,0.0005818667,0.0010968188,0.0008186342,0.0065919193],"category_scores_gemma":[0.001033587,0.00025226994,0.00035772883,0.0007137014,0.00019089032,0.0010980269,0.0007388488,0.0010393814,0.0015925248],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039132545,0.00020773093,0.000625375,0.00009377464,0.00006303974,0.00010240356,0.00006525021,0.064913064,0.024626741,0.0020715187,0.00670004,0.9001397],"study_design_scores_gemma":[0.000013212538,0.0001847442,0.0006855683,0.000012610859,0.00003147402,0.00004867257,0.000023416758,0.9816335,0.012253887,0.0032762466,0.0018258821,0.000010788995],"about_ca_topic_score_codex":0.008543046,"about_ca_topic_score_gemma":0.00998571,"teacher_disagreement_score":0.008543046,"about_ca_system_score_codex":0.00059256336,"about_ca_system_score_gemma":0.0006665991,"threshold_uncertainty_score":0.022052169},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.012081826517106386,"score_gpt":0.29168839802054464,"score_spread":0.27960657150343826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318465586","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.72820264,0.0045982026,0.04237662,0.00082825485,0.00022904044,0.0006873042,0.19073896,0.0068289894,0.02551006],"genre_scores_gemma":[0.7460549,0.0014165135,0.06518684,0.00011382943,0.00010714866,0.00024247047,0.16006298,0.00033881256,0.026476564],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99975544,0.000014022102,0.000016634325,0.00006584187,0.00009088822,0.000057106517],"domain_scores_gemma":[0.99885094,0.0001992776,0.00010491933,0.00012426393,0.0006522605,0.000068351],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016544537,0.0004757779,0.00039769392,0.010188202,0.0012525634,0.0010144158,0.0007713487,0.0005526625,0.004731523],"category_scores_gemma":[0.0012512713,0.00021366986,0.00034991498,0.009637579,0.0002928137,0.0004428312,0.00035273642,0.00041407152,0.0020568664],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038113847,0.0002023995,0.11139287,0.0009723843,0.00025170017,0.0033416164,0.0018255118,0.019422784,0.04472473,0.0024188163,0.09632257,0.71874356],"study_design_scores_gemma":[0.00005820305,0.000121372344,0.55873233,0.0003811162,0.00029948325,0.0015596783,0.0043293717,0.17968415,0.027815055,0.0018164116,0.22505592,0.00014699786],"about_ca_topic_score_codex":0.7610443,"about_ca_topic_score_gemma":0.88046783,"teacher_disagreement_score":0.23895568,"about_ca_system_score_codex":0.0028657399,"about_ca_system_score_gemma":0.004257022,"threshold_uncertainty_score":0.48072582},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.017819580098465848,"score_gpt":0.2975130757065387,"score_spread":0.27969349560807283,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384524000","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1571522,0.009745743,0.8144928,0.0003698846,0.0007673519,0.00031274816,0.0021286588,0.0069302553,0.008100366],"genre_scores_gemma":[0.6820728,0.0039663133,0.29210368,0.0002505027,0.00043978516,0.00014594062,0.0059428755,0.00021946196,0.014858654],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99905413,0.00009406893,0.000112481444,0.00015673885,0.00048953743,0.00009310617],"domain_scores_gemma":[0.999338,0.00011305625,0.000052105188,0.00017219385,0.0002878149,0.000036845362],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052507233,0.00043089275,0.0015517761,0.0029759987,0.0004355446,0.0011301796,0.00086115504,0.0005031008,0.0038417461],"category_scores_gemma":[0.0011049123,0.0001683833,0.0007773852,0.0035356614,0.00028952913,0.0012715535,0.0006405734,0.0005218556,0.003240522],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00052955665,0.0003009908,0.0014263587,0.00022366819,0.000104406245,0.00011132073,0.000040232928,0.0043433686,0.110843465,0.0021762135,0.007283828,0.8726166],"study_design_scores_gemma":[0.00013694652,0.0010051182,0.017130753,0.00006445655,0.000480058,0.0031676365,0.0002541223,0.6223,0.3114266,0.0068539744,0.03702237,0.0001579438],"about_ca_topic_score_codex":0.0017624737,"about_ca_topic_score_gemma":0.001630104,"teacher_disagreement_score":0.0038417461,"about_ca_system_score_codex":0.0003864112,"about_ca_system_score_gemma":0.0005420871,"threshold_uncertainty_score":0.0128519535},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.03503051319368615,"score_gpt":0.3313850425348655,"score_spread":0.29635452934117934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386544129","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028896034,0.00038127095,0.89916176,0.00007678097,0.00010234763,0.00016542891,0.0030985447,0.09213175,0.001992589],"genre_scores_gemma":[0.058265846,0.0005788896,0.9088434,0.00027766105,0.00010627804,0.00045265406,0.016077308,0.00654545,0.008852561],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99923766,0.00007221804,0.00006534661,0.00017747574,0.00035748834,0.000089834204],"domain_scores_gemma":[0.9994604,0.00011413366,0.000046867706,0.00016884664,0.00017206506,0.000037734684],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000684965,0.0013769973,0.0010170416,0.0019957533,0.000391604,0.0022227175,0.0029685027,0.0010528308,0.022030693],"category_scores_gemma":[0.002109449,0.0007014895,0.0017776205,0.0016505664,0.0004339617,0.0017888015,0.0013380125,0.0012295288,0.013648983],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000742236,0.00019652765,0.0013604902,0.0007815585,0.00018049308,0.00038273132,0.00020165725,0.016201025,0.041937582,0.01595265,0.109055094,0.81300795],"study_design_scores_gemma":[0.00015127091,0.00037111744,0.002067661,0.00023129732,0.00012091717,0.001052866,0.00021744252,0.6227633,0.15511829,0.026859198,0.19087924,0.00016747104],"about_ca_topic_score_codex":0.004976467,"about_ca_topic_score_gemma":0.007831309,"teacher_disagreement_score":0.022030693,"about_ca_system_score_codex":0.0006023504,"about_ca_system_score_gemma":0.0010680732,"threshold_uncertainty_score":0.07369995},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.02193815844080075,"score_gpt":0.27696922191641915,"score_spread":0.2550310634756184,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389941462","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83748615,0.001038628,0.15686423,0.00035080203,0.00013500305,0.000027643706,0.00040291325,0.0019477397,0.001746937],"genre_scores_gemma":[0.9883681,0.00011888238,0.010111982,0.00002208468,0.000053730786,0.0000054409034,0.0003900621,0.000045864243,0.00088389416],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990314,0.0002468524,0.00006793725,0.00031765288,0.0002129298,0.00012325864],"domain_scores_gemma":[0.9901355,0.0073105018,0.00066589034,0.0008762903,0.0008842663,0.00012752909],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011322432,0.00062909955,0.0005942604,0.0011440188,0.0002604309,0.0010059644,0.00047483595,0.00092489965,0.0018294958],"category_scores_gemma":[0.008809535,0.00017393527,0.00059576216,0.00055700657,0.00021868176,0.0012113331,0.00056540314,0.00087454345,0.0006696012],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014896644,0.0004731122,0.04122421,0.00012871473,0.00024663657,0.00039370725,0.00018991066,0.14261147,0.034383785,0.0014156995,0.002289001,0.7751541],"study_design_scores_gemma":[0.000011750714,0.00010384413,0.016619595,0.000006610389,0.00005337074,0.00008271797,0.000033423566,0.9698864,0.012051032,0.0007865746,0.00035294564,0.000011705439],"about_ca_topic_score_codex":0.0058732405,"about_ca_topic_score_gemma":0.0036298458,"teacher_disagreement_score":0.0058732405,"about_ca_system_score_codex":0.0004549163,"about_ca_system_score_gemma":0.0004655533,"threshold_uncertainty_score":0.0116781},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.0212746797109204,"score_gpt":0.26486499997549595,"score_spread":0.24359032026457555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400055411","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09887345,0.00069520756,0.8828651,0.00033155366,0.0002633554,0.00013201537,0.0017390444,0.008528978,0.0065712333],"genre_scores_gemma":[0.7107,0.00047607883,0.27062708,0.00034850743,0.00015061164,0.00013572749,0.005859325,0.0005448337,0.01115778],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99970824,0.000017485845,0.000009476403,0.00010505174,0.00007004999,0.000089634275],"domain_scores_gemma":[0.99976045,0.00005268205,0.0000239551,0.000041362688,0.000093311246,0.000028233277],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002109639,0.0011588582,0.0011461759,0.0018660325,0.0004535498,0.00076639757,0.0015974316,0.0009170269,0.0047976957],"category_scores_gemma":[0.0005004305,0.00065693987,0.0009915654,0.0013759028,0.00036407934,0.0009809877,0.0013898151,0.0011907229,0.0021324728],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004280787,0.00038087618,0.00420369,0.00013027493,0.00010978055,0.00023359468,0.0000754374,0.10807706,0.04253741,0.0021540686,0.013729089,0.8279406],"study_design_scores_gemma":[0.000008293005,0.000032868862,0.0013505096,0.000011725521,0.000023703535,0.000044653116,0.000024498218,0.99135333,0.0047425,0.001403728,0.0009931857,0.000010940661],"about_ca_topic_score_codex":0.015497651,"about_ca_topic_score_gemma":0.031896964,"teacher_disagreement_score":0.015497651,"about_ca_system_score_codex":0.0005505447,"about_ca_system_score_gemma":0.0010842625,"threshold_uncertainty_score":0.030814886},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.02578919183659872,"score_gpt":0.3390521256032745,"score_spread":0.3132629337666758,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403102908","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10202113,0.0017437984,0.8792474,0.00036530482,0.00038860118,0.00016548358,0.00071105285,0.0057002995,0.00965689],"genre_scores_gemma":[0.39674184,0.0013156489,0.5729058,0.0003582097,0.00011731496,0.00017216362,0.0025828055,0.00071695447,0.025089288],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999721,0.000024856556,0.000015522735,0.0000677102,0.00011913954,0.00005170852],"domain_scores_gemma":[0.999653,0.000052610925,0.000020795515,0.00007333241,0.00018239047,0.000017794371],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043310208,0.0008216289,0.0005293205,0.00082794816,0.00032085637,0.00061985437,0.00051227864,0.0006783314,0.0055019846],"category_scores_gemma":[0.0008693707,0.00022357449,0.00054203975,0.000560876,0.00026018047,0.00064160285,0.00068181375,0.0009938268,0.0030519902],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043155788,0.000118788936,0.0010000413,0.00027696934,0.000058985985,0.00012675757,0.00008816135,0.006869481,0.3026885,0.0020131692,0.0040719626,0.6822556],"study_design_scores_gemma":[0.000028430513,0.00044561707,0.006793453,0.00007885181,0.00016959345,0.00070493686,0.00011497493,0.44234863,0.521585,0.0023835767,0.025290387,0.0000565177],"about_ca_topic_score_codex":0.0020104425,"about_ca_topic_score_gemma":0.0054584127,"teacher_disagreement_score":0.0055019846,"about_ca_system_score_codex":0.0003018271,"about_ca_system_score_gemma":0.00076585147,"threshold_uncertainty_score":0.018405974},"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,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.019432691962424094,"score_gpt":0.36417120293523625,"score_spread":0.34473851097281216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406984947","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24519542,0.003834371,0.7097066,0.0006299676,0.000587205,0.00049208174,0.0013294724,0.024495741,0.013729138],"genre_scores_gemma":[0.6227892,0.0011390427,0.35585728,0.00037193525,0.00019723234,0.00017670689,0.0025415416,0.00047603966,0.016450938],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992514,0.0000667473,0.00006826217,0.0003002164,0.0002196009,0.00009371041],"domain_scores_gemma":[0.99856937,0.0003725817,0.00029101243,0.00019849754,0.00050120195,0.000067323504],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00066255504,0.0012559496,0.000895146,0.0029756608,0.0003477878,0.0016499488,0.0014732898,0.0013960353,0.0031305517],"category_scores_gemma":[0.0021457982,0.0004199042,0.0008162576,0.0015872538,0.00054143305,0.0014176179,0.00052890676,0.00074230414,0.0026527555],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004972499,0.00015602153,0.0020850562,0.00021698144,0.00008479137,0.00021281489,0.00009758794,0.03379408,0.06812037,0.00096015073,0.004785747,0.8889892],"study_design_scores_gemma":[0.000022125902,0.00015213329,0.0037015276,0.000039159877,0.00006147555,0.00024887605,0.00007106936,0.922444,0.06796122,0.0012548304,0.004013983,0.000029586305],"about_ca_topic_score_codex":0.0067803813,"about_ca_topic_score_gemma":0.008041788,"teacher_disagreement_score":0.0067803813,"about_ca_system_score_codex":0.0012224044,"about_ca_system_score_gemma":0.00071774214,"threshold_uncertainty_score":0.013481855},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Defence Research and Development Canada; University of Ottawa","funders":"Mitacs","keywords":"Table (database); Information retrieval; Computer science; Data mining","score_opus":0.012244726227663415,"score_gpt":0.31880942022650643,"score_spread":0.306564693998843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410636570","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32344726,0.010465425,0.0893218,0.00247474,0.0023575057,0.0017738515,0.47087213,0.08554813,0.013739124],"genre_scores_gemma":[0.16296,0.0013286732,0.12266344,0.00043452182,0.00019352308,0.00044727235,0.7024119,0.0011219879,0.00843865],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99719894,0.00023619669,0.00028658842,0.0007039094,0.0012752172,0.0002991116],"domain_scores_gemma":[0.9952827,0.0011787978,0.00028317238,0.0013082324,0.0017090318,0.00023801904],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016206523,0.0019671267,0.0014152378,0.0071922825,0.0011766292,0.0028118307,0.002634662,0.0022843122,0.0047049974],"category_scores_gemma":[0.008114233,0.0005513405,0.0018660333,0.00485123,0.00046507097,0.0020863237,0.0016769376,0.0016215591,0.007843979],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013489868,0.0014423161,0.018015666,0.002436648,0.0005666448,0.0011486541,0.0003025806,0.015648864,0.041373543,0.0020614997,0.37193605,0.5437185],"study_design_scores_gemma":[0.00066580664,0.0010773921,0.074573755,0.0009724765,0.00055689417,0.003605035,0.0020073166,0.3683945,0.12835771,0.00953975,0.40992787,0.00032145865],"about_ca_topic_score_codex":0.024161695,"about_ca_topic_score_gemma":0.04411023,"teacher_disagreement_score":0.024161695,"about_ca_system_score_codex":0.0013415758,"about_ca_system_score_gemma":0.0019802444,"threshold_uncertainty_score":0.04804212},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.04133032381567437,"score_gpt":0.3529996195214886,"score_spread":0.31166929570581425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414059432","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7729157,0.009723417,0.20104359,0.0008119297,0.00011029223,0.00022365607,0.0003382258,0.0012894267,0.013543718],"genre_scores_gemma":[0.95673835,0.0010535634,0.039462555,0.000044751014,0.00005290896,0.00003120682,0.0003175625,0.00010486689,0.002194254],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9962226,0.001597066,0.00026620255,0.0004376067,0.0010889465,0.00038748313],"domain_scores_gemma":[0.98342544,0.012204483,0.00058602635,0.0012385686,0.0023460423,0.00019944971],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038859788,0.00051735085,0.0012554851,0.0018144198,0.0006531327,0.0025822977,0.0009905263,0.00086469715,0.0029116606],"category_scores_gemma":[0.013199641,0.00020562121,0.000579562,0.0025703362,0.000477263,0.0029908847,0.00065281807,0.0005551391,0.00060090487],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018007542,0.0009792936,0.013906866,0.00033728115,0.00016612529,0.00006942569,0.0001829324,0.17996256,0.00524734,0.006726855,0.003333638,0.787287],"study_design_scores_gemma":[0.000031990665,0.00059271953,0.00863424,0.000016799317,0.00014046513,0.00009505334,0.00030504362,0.9785832,0.0062229633,0.0036775498,0.0016794674,0.000020476271],"about_ca_topic_score_codex":0.008352025,"about_ca_topic_score_gemma":0.006963532,"teacher_disagreement_score":0.008352025,"about_ca_system_score_codex":0.002479901,"about_ca_system_score_gemma":0.0019117048,"threshold_uncertainty_score":0.020551324},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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)","score_opus":0.028887705126131962,"score_gpt":0.3700693358111449,"score_spread":0.3411816306850129,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414929823","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1376416,0.00090209354,0.76543677,0.00038039027,0.00060376676,0.0009321593,0.022907063,0.054026265,0.017169928],"genre_scores_gemma":[0.45190176,0.0005239385,0.47545186,0.00033046576,0.00022893019,0.0009462212,0.0446434,0.0011931309,0.024780361],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9996363,0.000042740754,0.000016678072,0.00015466168,0.00008388569,0.000065755536],"domain_scores_gemma":[0.9996277,0.000057487323,0.000026398422,0.00009913614,0.00011498907,0.00007422744],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042531334,0.001489884,0.0008698409,0.0028834436,0.00091007905,0.0008997683,0.0015419876,0.00094717863,0.0118439365],"category_scores_gemma":[0.0010700291,0.00034732925,0.00092233485,0.0024850469,0.00024657257,0.001297303,0.0013937597,0.0009982531,0.00492043],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00084092753,0.00042273686,0.004922442,0.00018030443,0.00014897512,0.00023125838,0.00014478751,0.01803392,0.021529034,0.0033857627,0.06437941,0.88578033],"study_design_scores_gemma":[0.00006061798,0.00017299032,0.006048508,0.00003668719,0.00007823601,0.00017273694,0.00014747381,0.95660067,0.010899703,0.008990764,0.016728705,0.00006303525],"about_ca_topic_score_codex":0.022707138,"about_ca_topic_score_gemma":0.032612294,"teacher_disagreement_score":0.022707138,"about_ca_system_score_codex":0.0009346313,"about_ca_system_score_gemma":0.0010946821,"threshold_uncertainty_score":0.045149922},"labels":[],"label_agreement":null}]}