{"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92004716,0.00037287225,0.06790106,0.003944889,0.003460987,0.0002834461,0.000066839726,0.000122021964,0.0038007202],"genre_scores_gemma":[0.9968782,0.0002501681,0.0020505528,0.00036446477,0.00019743833,0.000014607933,0.00013904889,0.0000073407127,0.00009818237],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99774593,0.00020711063,0.00059092743,0.00034607228,0.0009580979,0.00015185188],"domain_scores_gemma":[0.9982672,0.00006927031,0.0004810671,0.0002092862,0.0006996115,0.0002735941],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006318645,0.00018132533,0.00023813822,0.0011804713,0.00011733185,0.0004429769,0.00038027417,0.00007078551,0.0004889267],"category_scores_gemma":[0.00008618997,0.00014841546,0.00022237754,0.0005166551,0.000040435614,0.00093266513,0.000057108122,0.00021724316,0.0000691577],"study_design_candidate":"design_other","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":[0.00024990793,0.0009845007,0.001903921,0.000006274236,0.0012237619,0.000029922376,0.0021656286,0.00014362988,0.0011712979,0.0036708226,0.00027280377,0.98817754],"study_design_scores_gemma":[0.029101312,0.013594714,0.21108271,0.001900192,0.0038451212,0.0016463365,0.0043900097,0.14094408,0.17323633,0.3741472,0.04063135,0.005480635],"about_ca_topic_score_codex":0.000052072373,"about_ca_topic_score_gemma":0.00002670753,"teacher_disagreement_score":0.9826969,"about_ca_system_score_codex":0.00013703541,"about_ca_system_score_gemma":0.00006560797,"threshold_uncertainty_score":0.60522074},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55495036,0.00008447279,0.43853003,0.0038712802,0.0007529883,0.00010005934,0.000003804848,0.000040363117,0.001666627],"genre_scores_gemma":[0.99063134,0.00078716315,0.00715433,0.00096213404,0.00022250958,0.000005918643,0.000022144886,0.0000045792326,0.00020986555],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99779284,0.000087981476,0.00061318575,0.00038078014,0.00092469517,0.00020053473],"domain_scores_gemma":[0.99888337,0.000050759667,0.00031301376,0.00015635477,0.00040098195,0.00019554234],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007732154,0.00018085037,0.00025311395,0.000639223,0.00014074841,0.0014774918,0.0002993817,0.000046936842,0.00011976175],"category_scores_gemma":[0.00006815047,0.00015015219,0.00018745499,0.0003065568,0.000033543074,0.0014468804,0.00008654938,0.00019930572,0.00003508867],"study_design_candidate":"design_other","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":[0.000089549074,0.00022201263,0.00014617229,0.000004626619,0.0009239389,0.00005156055,0.00033115398,0.00040707685,0.0010217932,0.0028700985,0.00015355625,0.99377847],"study_design_scores_gemma":[0.0066392827,0.0026939113,0.009217881,0.00070839934,0.0010645009,0.0005414179,0.0005042894,0.2417656,0.055567004,0.676715,0.0025065166,0.0020761713],"about_ca_topic_score_codex":0.000023501245,"about_ca_topic_score_gemma":0.000011079973,"teacher_disagreement_score":0.9917023,"about_ca_system_score_codex":0.00015677641,"about_ca_system_score_gemma":0.000025742364,"threshold_uncertainty_score":0.99955904},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12961747,0.00012852557,0.8672192,0.001044187,0.00048857887,0.00021435488,0.000041310326,0.00007006288,0.0011763087],"genre_scores_gemma":[0.8251649,0.00057852804,0.17273666,0.000915552,0.00019034209,0.000030922813,0.00006321827,0.000023001227,0.0002968388],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9966697,0.00062707503,0.00092891627,0.00042206908,0.001052031,0.00030018872],"domain_scores_gemma":[0.9970107,0.00047516185,0.00090703653,0.00025568076,0.001175178,0.00017623849],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023971922,0.000259615,0.00037514308,0.001124185,0.00041822082,0.0010165783,0.0006166101,0.00009318754,0.00043760383],"category_scores_gemma":[0.00024013409,0.00019352157,0.00049204467,0.00085340283,0.000089695524,0.00078679016,0.0000767481,0.00038724346,0.000019522287],"study_design_candidate":"design_other","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":[0.0002719,0.000535102,0.0025588116,0.000021812442,0.0042325286,0.0001180211,0.00034727776,0.0008152342,0.0049216147,0.0074164043,0.000293163,0.9784681],"study_design_scores_gemma":[0.010679294,0.0013984997,0.0025969825,0.0010944034,0.0027321423,0.00085610454,0.00074077887,0.141128,0.5740144,0.24475029,0.017758403,0.0022506728],"about_ca_topic_score_codex":0.00009321869,"about_ca_topic_score_gemma":0.000031192587,"teacher_disagreement_score":0.97621745,"about_ca_system_score_codex":0.00017139784,"about_ca_system_score_gemma":0.00012581573,"threshold_uncertainty_score":0.98028874},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18038218,0.00019287957,0.81754136,0.0010317736,0.00018885032,0.000074675714,0.000044278877,0.000044684963,0.00049934664],"genre_scores_gemma":[0.8208362,0.0047560516,0.17291857,0.000732114,0.00031828062,0.000008919226,0.0002934042,0.000014242959,0.0001222284],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978382,0.00014164919,0.0006829214,0.00048015753,0.00067530223,0.0001817825],"domain_scores_gemma":[0.9981058,0.00022566918,0.0005496759,0.00031518997,0.00066450174,0.0001391281],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010424843,0.00018753254,0.00037163982,0.00095406594,0.00014885835,0.000683229,0.00081802503,0.00007745756,0.00035293217],"category_scores_gemma":[0.00012257065,0.00015181344,0.0001250837,0.00073968485,0.000043165976,0.0014772656,0.00042651728,0.00021300049,0.000012129894],"study_design_candidate":"design_other","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":[0.00008111388,0.00013813635,0.004224346,0.0000072480702,0.0019450755,0.000096066506,0.00032007412,0.000024811325,0.0037458055,0.00029897288,0.0002228093,0.98889554],"study_design_scores_gemma":[0.011685769,0.0013875576,0.20019253,0.0030201292,0.0060041915,0.0040961835,0.002058103,0.21267524,0.160039,0.3759048,0.018978238,0.0039582592],"about_ca_topic_score_codex":0.0001823909,"about_ca_topic_score_gemma":0.00009082353,"teacher_disagreement_score":0.9849373,"about_ca_system_score_codex":0.000054873024,"about_ca_system_score_gemma":0.00004093974,"threshold_uncertainty_score":0.65883934},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13758983,0.00001972081,0.85630494,0.0030958275,0.00078858144,0.00036588623,0.00004322981,0.0003089543,0.0014830187],"genre_scores_gemma":[0.8092663,0.00012111614,0.18814854,0.0013184716,0.00057503115,0.0001258148,0.00016689026,0.000020470843,0.00025732344],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976018,0.000113232396,0.000727572,0.00048454406,0.000791952,0.00028086544],"domain_scores_gemma":[0.9972453,0.00037784356,0.00067972275,0.00025982843,0.0012234652,0.00021382266],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0013625317,0.00026640706,0.0003555993,0.0014272856,0.00035545178,0.0016053848,0.0007801151,0.00015628638,0.000462079],"category_scores_gemma":[0.00022102625,0.00022517449,0.000504142,0.00054196245,0.00007950753,0.00084682176,0.000093527124,0.0004950054,0.000023248558],"study_design_candidate":"design_other","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":[0.00013631895,0.00036729226,0.002113721,0.000012853354,0.0013781526,0.000053841744,0.00015301313,0.000006757163,0.0055721384,0.008426438,0.00070359645,0.9810759],"study_design_scores_gemma":[0.00514888,0.0019326146,0.009715371,0.0005506297,0.0017223868,0.0006270172,0.00020132896,0.03710374,0.3406563,0.56773984,0.03229599,0.0023058907],"about_ca_topic_score_codex":0.000051474886,"about_ca_topic_score_gemma":0.000061983206,"teacher_disagreement_score":0.97876996,"about_ca_system_score_codex":0.00009840934,"about_ca_system_score_gemma":0.000082667786,"threshold_uncertainty_score":0.9994311},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5366094,0.00017079803,0.4598084,0.00040469883,0.0003250287,0.00027905885,0.00007112967,0.00009580157,0.0022356294],"genre_scores_gemma":[0.9252828,0.0018789351,0.0715169,0.0005537316,0.00014414603,0.000039099737,0.00043899895,0.000017323257,0.00012808558],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99717695,0.00040366538,0.000807194,0.00053765526,0.00084491895,0.00022963145],"domain_scores_gemma":[0.9979575,0.000117420714,0.0006486931,0.00021812625,0.00082391675,0.00023433659],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001304892,0.00026066738,0.0003844112,0.0013838327,0.00020042715,0.00081355375,0.0003932641,0.00009022578,0.0003606643],"category_scores_gemma":[0.00010394136,0.00023041682,0.00021691484,0.00052037276,0.000092532864,0.0018358838,0.00007805687,0.00028806107,0.00001908651],"study_design_candidate":"design_other","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":[0.00013438425,0.0009181129,0.003207602,0.000033814864,0.0024974456,0.000060787715,0.0008764735,0.000041364154,0.0033243916,0.0019676983,0.00042838522,0.98650956],"study_design_scores_gemma":[0.010821653,0.0035058653,0.012172312,0.0008867252,0.0033578395,0.003284947,0.002630965,0.026215186,0.498644,0.4313875,0.0039839367,0.0031090556],"about_ca_topic_score_codex":0.000036411413,"about_ca_topic_score_gemma":0.000008797032,"teacher_disagreement_score":0.98340046,"about_ca_system_score_codex":0.00009318299,"about_ca_system_score_gemma":0.000049103346,"threshold_uncertainty_score":0.9396125},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014837047,0.0007962741,0.98297757,0.000740334,0.0002400298,0.00013412365,0.000011107277,0.000051388735,0.00021211407],"genre_scores_gemma":[0.12293885,0.00017316332,0.87599623,0.00028151096,0.00034378265,0.000007853337,0.00006442109,0.000010253681,0.00018391942],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998537,0.00005421435,0.0004180503,0.00025324413,0.00052035524,0.00021713102],"domain_scores_gemma":[0.9988362,0.00015208362,0.00038719113,0.00010302784,0.00032643575,0.00019503162],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009027748,0.00016419087,0.00022554243,0.000674525,0.00022012403,0.0007032399,0.0002819804,0.000086734464,0.000049180093],"category_scores_gemma":[0.00011823632,0.0001324545,0.00016804223,0.00031374732,0.000025237008,0.0012294349,0.0001121811,0.00021773386,0.000003536442],"study_design_candidate":"design_other","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":[0.00014387326,0.0004347127,0.00684798,0.00006754966,0.003974101,0.000020598616,0.0025884314,0.00014610114,0.0014331581,0.049812134,0.0015570496,0.93297434],"study_design_scores_gemma":[0.003142258,0.00023580922,0.0016101253,0.00053391466,0.0019815944,0.0016093747,0.00041486733,0.14893606,0.0047763675,0.83333576,0.002142276,0.0012816171],"about_ca_topic_score_codex":0.000017731343,"about_ca_topic_score_gemma":0.0000020212779,"teacher_disagreement_score":0.9316927,"about_ca_system_score_codex":0.00010478506,"about_ca_system_score_gemma":0.000040805437,"threshold_uncertainty_score":0.6781358},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02500197,0.000039466388,0.9697905,0.0018226684,0.00083894975,0.0005054013,0.00007002372,0.00017419443,0.0017567918],"genre_scores_gemma":[0.9405219,0.00046978894,0.056405272,0.0015070701,0.0003691086,0.00021871559,0.00032601113,0.000025050218,0.00015710897],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9957199,0.00031022858,0.0010541837,0.0007895563,0.0017496591,0.0003764909],"domain_scores_gemma":[0.9963782,0.00016257251,0.0008282248,0.0003690495,0.0019762237,0.00028575744],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0023483576,0.00039094407,0.0005407242,0.0036441374,0.00037795483,0.0007047917,0.0006409095,0.00015008316,0.0008840347],"category_scores_gemma":[0.00019829224,0.0003240305,0.0010641994,0.0013957175,0.000057440146,0.0009341728,0.000082880564,0.00034952024,0.00007946668],"study_design_candidate":"design_other","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":[0.0014274265,0.0020622609,0.003399379,0.0000369866,0.01758467,0.000118239,0.0009206844,0.00056993903,0.00065260305,0.0015687863,0.0011437482,0.97051525],"study_design_scores_gemma":[0.016749375,0.012452487,0.087288596,0.00208471,0.034073956,0.00027970513,0.0009401297,0.21631575,0.27709305,0.33289564,0.013866612,0.005960019],"about_ca_topic_score_codex":0.000109455876,"about_ca_topic_score_gemma":0.00010163819,"teacher_disagreement_score":0.96455526,"about_ca_system_score_codex":0.0005051079,"about_ca_system_score_gemma":0.00008529895,"threshold_uncertainty_score":0.9999212},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13421169,0.00007282832,0.86287576,0.00090969895,0.0003424365,0.00035727836,0.00009182437,0.00012758574,0.0010109154],"genre_scores_gemma":[0.88534373,0.00062284427,0.11184163,0.0012652308,0.00029603532,0.0001267096,0.00031135042,0.000028513949,0.00016396157],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9972438,0.00021329716,0.0007478267,0.00060252147,0.0007715062,0.00042101656],"domain_scores_gemma":[0.99744254,0.00032661678,0.0006145889,0.00020292969,0.001177291,0.00023600455],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0011760986,0.00031897466,0.0004156873,0.0012670939,0.00045322173,0.0012887914,0.00044084448,0.00013243308,0.00030475482],"category_scores_gemma":[0.00015842129,0.0002680748,0.00039495117,0.0004923626,0.000037616494,0.0020872883,0.00007275981,0.0003554187,0.000036115838],"study_design_candidate":"design_other","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":[0.0007757914,0.001574928,0.013183327,0.00007363849,0.009349973,0.00035048966,0.0017082525,0.00045949608,0.0026963134,0.019888962,0.0011747901,0.948764],"study_design_scores_gemma":[0.021721587,0.0027791911,0.0037244079,0.002570496,0.0031208093,0.0022566428,0.0012955759,0.39086512,0.13445391,0.4205827,0.012462535,0.0041670306],"about_ca_topic_score_codex":0.000010599827,"about_ca_topic_score_gemma":0.000045196084,"teacher_disagreement_score":0.944597,"about_ca_system_score_codex":0.00016737987,"about_ca_system_score_gemma":0.00008444432,"threshold_uncertainty_score":0.9999772},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9267631,0.000068678826,0.008092875,0.00046590998,0.013799365,0.0002641204,0.000073981995,0.00016781171,0.05030416],"genre_scores_gemma":[0.97118276,0.00085010275,0.0001518025,0.00046947773,0.026607852,0.000006705503,0.00014627658,0.000029083658,0.0005559228],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980364,0.0000654013,0.0006635678,0.00022186793,0.0007897799,0.00022302789],"domain_scores_gemma":[0.9990464,0.00013039746,0.00020815269,0.00009274877,0.00034807576,0.00017422954],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010554458,0.00021037165,0.0002666026,0.0016646618,0.00017437372,0.00037867308,0.00011866925,0.00017433662,0.0024627591],"category_scores_gemma":[0.00006110995,0.00018124921,0.00033525468,0.0005593708,0.000025344636,0.0002802883,0.000014253898,0.0004775551,0.00038773462],"study_design_candidate":"design_other","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":[0.0004686086,0.0001168698,0.00053419993,0.000007150918,0.002363487,0.00012793289,0.0001790961,0.0007968772,0.00027902078,0.000121061326,0.014012249,0.98099345],"study_design_scores_gemma":[0.007831357,0.0019895176,0.023413394,0.0008915353,0.0021951264,0.0006648671,0.0011502076,0.0034186968,0.04086235,0.015084127,0.9003491,0.0021497658],"about_ca_topic_score_codex":0.00002578617,"about_ca_topic_score_gemma":0.000052052994,"teacher_disagreement_score":0.9788437,"about_ca_system_score_codex":0.00019129508,"about_ca_system_score_gemma":0.000010157847,"threshold_uncertainty_score":0.99844915},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18333444,0.00004757466,0.81527,0.0001884279,0.0005479118,0.00026539553,0.00003013406,0.000079195204,0.0002369122],"genre_scores_gemma":[0.93028164,0.00070306996,0.067263775,0.00044909236,0.00032309102,0.0000717066,0.00048214497,0.000020472884,0.00040497992],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974627,0.00021444215,0.0007888861,0.00060556474,0.0006541448,0.00027425445],"domain_scores_gemma":[0.9979549,0.00011537979,0.0007276752,0.00019691807,0.0007964099,0.00020873372],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0012875672,0.00028527313,0.00047883077,0.0024414207,0.0003953869,0.001142993,0.000387594,0.00014175469,0.00021559994],"category_scores_gemma":[0.00006956796,0.00025100558,0.00041997308,0.00104451,0.000058985388,0.0014473227,0.000120246,0.00025839178,0.0000058761234],"study_design_candidate":"design_other","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":[0.000551429,0.0008498394,0.015456475,0.000041801224,0.021863438,0.000048073547,0.0032049457,0.00038844065,0.0044057774,0.0014903155,0.00016422787,0.9515352],"study_design_scores_gemma":[0.0054325983,0.0013237684,0.061846197,0.0004457251,0.015504569,0.0006443892,0.0010224114,0.8436058,0.044086542,0.021242982,0.002502173,0.002342843],"about_ca_topic_score_codex":0.00008322152,"about_ca_topic_score_gemma":0.000022346552,"teacher_disagreement_score":0.9491924,"about_ca_system_score_codex":0.00017059834,"about_ca_system_score_gemma":0.00003974867,"threshold_uncertainty_score":0.9999942},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.634381,0.00012340622,0.35813856,0.0007649934,0.00035822365,0.0002156329,0.000056135697,0.00011401333,0.0058480497],"genre_scores_gemma":[0.9480997,0.0013306541,0.04992367,0.00032113897,0.00011802005,0.000011024891,0.000044142038,0.00001075758,0.00014091651],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980052,0.00015391134,0.00068552204,0.00032068457,0.0006672787,0.0001673642],"domain_scores_gemma":[0.99835545,0.00015447951,0.00048358963,0.00016757654,0.00064749125,0.00019140939],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007521482,0.00017583903,0.0003150802,0.0010758355,0.00012013771,0.0002685564,0.00038128515,0.0001009534,0.001457274],"category_scores_gemma":[0.00014853136,0.00014176234,0.0002288896,0.00042443722,0.00009670984,0.00079920236,0.00015133411,0.00025451562,0.00005661203],"study_design_candidate":"design_other","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":[0.00050523866,0.0012918626,0.0025431167,0.00004777978,0.0043408102,0.00020707496,0.0035312625,0.0000016523549,0.006637692,0.007426254,0.0006401884,0.9728271],"study_design_scores_gemma":[0.0019456269,0.0008834123,0.010326257,0.0007325073,0.00096758985,0.0006619008,0.00035542666,0.0014276434,0.16928846,0.81221575,0.00048586138,0.0007095958],"about_ca_topic_score_codex":0.000014059304,"about_ca_topic_score_gemma":0.000002553724,"teacher_disagreement_score":0.9721175,"about_ca_system_score_codex":0.00004250039,"about_ca_system_score_gemma":0.000028407165,"threshold_uncertainty_score":0.9994555},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00074185577,0.000095550175,0.9939329,0.004421634,0.00019417338,0.00014253103,0.00003675346,0.00006593214,0.00036868665],"genre_scores_gemma":[0.7099068,0.0010703993,0.28440273,0.0021521924,0.0003515618,0.000085235806,0.00017179376,0.000017342478,0.0018419403],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985542,0.00007020024,0.00040919514,0.00030721523,0.0005096061,0.00014954289],"domain_scores_gemma":[0.99845266,0.000076000186,0.00033549874,0.0001294134,0.00090481807,0.00010162104],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036482455,0.00015593939,0.00018868598,0.0007657083,0.00021517297,0.0009353423,0.00037689175,0.00006445188,0.00020006142],"category_scores_gemma":[0.00004737906,0.00012693097,0.0002595999,0.00044990142,0.000039597373,0.0008100018,0.000037309794,0.00014765946,0.000018739234],"study_design_candidate":"design_other","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":[0.000022913076,0.0002577254,0.00008314396,0.0000044674744,0.00067245186,0.000012437409,0.00021658212,0.00036953317,0.00078990497,0.002505329,0.00064566795,0.9944199],"study_design_scores_gemma":[0.0006974758,0.00017293337,0.00015588872,0.00004469694,0.00015012381,0.000015766627,0.000014276665,0.9531544,0.024343636,0.019729545,0.001310531,0.00021072387],"about_ca_topic_score_codex":0.000002876882,"about_ca_topic_score_gemma":6.31709e-7,"teacher_disagreement_score":0.9942091,"about_ca_system_score_codex":0.00011623602,"about_ca_system_score_gemma":0.000025141499,"threshold_uncertainty_score":0.90195274},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7702852,0.00027199,0.0017609228,0.00040315767,0.049139943,0.000076269345,0.00014776982,0.000107737476,0.177807],"genre_scores_gemma":[0.94805366,0.0010357711,0.0015243634,0.0002983097,0.039066598,0.000015361691,0.00020415986,0.000022750328,0.009779055],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985182,0.000020571615,0.00040053783,0.00025035613,0.0006550544,0.00015526284],"domain_scores_gemma":[0.99910194,0.000040144532,0.00030574435,0.00011706798,0.0002835957,0.00015153106],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00021688062,0.00016081422,0.00018473645,0.0002015114,0.00015677811,0.00013048117,0.0002574761,0.00010116518,0.019784145],"category_scores_gemma":[0.00005662033,0.00013902901,0.00023205586,0.000111741625,0.000056635967,0.00029020835,0.000045384866,0.00034114587,0.00008489078],"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":[0.005917219,0.0050335187,0.03923455,0.00017652004,0.04663926,0.0008461443,0.0060170726,0.00029482556,0.10270922,0.0019377029,0.19231297,0.598881],"study_design_scores_gemma":[0.0037761754,0.00016265886,0.0005775803,0.00028460493,0.0019297574,0.00012476408,0.00062130217,0.000082293,0.20214097,0.022738608,0.76660657,0.0009546898],"about_ca_topic_score_codex":0.0000117989275,"about_ca_topic_score_gemma":0.000004439919,"teacher_disagreement_score":0.5979263,"about_ca_system_score_codex":0.00015139887,"about_ca_system_score_gemma":0.000034916124,"threshold_uncertainty_score":0.9811119},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10825861,0.00003810253,0.8845618,0.005084309,0.0005457238,0.0001027293,0.000016106911,0.000060052185,0.0013325964],"genre_scores_gemma":[0.9892564,0.00018300443,0.009859289,0.0002857599,0.00014251012,0.000011143649,0.000046093577,0.0000053399835,0.0002104987],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99834913,0.00006894509,0.00051221077,0.00025629214,0.0006933308,0.00012011828],"domain_scores_gemma":[0.99826545,0.000099684104,0.0005148352,0.00021792375,0.00079537416,0.00010674728],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005740627,0.00012612634,0.00020289251,0.0007068557,0.00011436082,0.00045165696,0.0005498212,0.00007439801,0.00029139992],"category_scores_gemma":[0.00007687239,0.00009950405,0.00023851814,0.0005212924,0.00007775392,0.0004892791,0.00004077048,0.00027972984,0.000017891001],"study_design_candidate":"design_other","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":[0.0001810743,0.00069380674,0.016709356,0.000017729617,0.0015834962,0.000028967492,0.0002201068,0.000016046759,0.074106544,0.06130179,0.0005625148,0.84457856],"study_design_scores_gemma":[0.0035782086,0.0007119065,0.2678179,0.00031721505,0.0010185438,0.00012881336,0.00018595274,0.062784806,0.52627146,0.10956762,0.026405098,0.0012124687],"about_ca_topic_score_codex":0.000010462405,"about_ca_topic_score_gemma":0.0000108645145,"teacher_disagreement_score":0.8809977,"about_ca_system_score_codex":0.000046244193,"about_ca_system_score_gemma":0.000056281504,"threshold_uncertainty_score":0.43553385},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022664014,0.00006242796,0.9732518,0.002034844,0.000570393,0.00017704669,0.000009481803,0.000053301363,0.0011766641],"genre_scores_gemma":[0.9432087,0.0009432451,0.053116553,0.0009069301,0.0002032543,0.00006461084,0.000075556025,0.000009340752,0.0014718252],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986458,0.00009770585,0.00039509044,0.00025602343,0.00047406135,0.00013133312],"domain_scores_gemma":[0.9987333,0.00012601292,0.0003586655,0.00010307233,0.0005877672,0.00009121084],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006423299,0.00012071724,0.00014847265,0.0005946447,0.0002028072,0.0007122993,0.00023595324,0.000056216253,0.00029755686],"category_scores_gemma":[0.00009649148,0.000099733756,0.00021782742,0.00037341923,0.000023484456,0.000808102,0.000018432738,0.0001232514,0.000029540483],"study_design_candidate":"design_other","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":[0.00018448573,0.00050717517,0.0012814159,0.000011331938,0.0023491762,0.000023701761,0.00034307537,0.000059368846,0.015215144,0.05233397,0.0017438998,0.92594725],"study_design_scores_gemma":[0.0050009373,0.0013761402,0.0119109275,0.0001525836,0.0013416698,0.00049819116,0.0006259129,0.020991085,0.6323516,0.2079805,0.116492875,0.0012775915],"about_ca_topic_score_codex":0.000004408563,"about_ca_topic_score_gemma":0.0000027987862,"teacher_disagreement_score":0.9246697,"about_ca_system_score_codex":0.00013866831,"about_ca_system_score_gemma":0.000038277474,"threshold_uncertainty_score":0.6868718},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01241016,0.00006523952,0.9810378,0.0052444474,0.000411131,0.00015775184,0.000017961615,0.000044993045,0.00061051734],"genre_scores_gemma":[0.982771,0.0006997115,0.015269486,0.0003576131,0.00027726725,0.000033162352,0.00009145814,0.000009085325,0.0004912333],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981232,0.000112697264,0.00061378727,0.00033520037,0.00066036946,0.0001547218],"domain_scores_gemma":[0.9972206,0.0001709822,0.0006838008,0.00021885737,0.0016089965,0.00009677656],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008846102,0.00016866149,0.00028589138,0.00074620836,0.00014791611,0.0005399585,0.00056560343,0.00007836185,0.000098797376],"category_scores_gemma":[0.00014148545,0.00013150126,0.00025604127,0.0006053763,0.00006227238,0.00067756907,0.00006841087,0.00013451412,0.0000107545875],"study_design_candidate":"design_other","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":[0.00013850463,0.00027500413,0.0012203967,0.000029723298,0.0011224872,0.0000029148107,0.00012764538,0.0000424317,0.012457777,0.0286225,0.0006828689,0.95527774],"study_design_scores_gemma":[0.0059176283,0.0012247316,0.20960593,0.00069492543,0.0020691184,0.00020591456,0.0003263254,0.053769793,0.26848605,0.35438126,0.10148302,0.0018352931],"about_ca_topic_score_codex":0.0000107860415,"about_ca_topic_score_gemma":0.000003082475,"teacher_disagreement_score":0.9703608,"about_ca_system_score_codex":0.00008488823,"about_ca_system_score_gemma":0.000043542044,"threshold_uncertainty_score":0.5362466},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11230906,0.000090433176,0.8824124,0.0042053,0.00030476673,0.00019735767,0.000050760893,0.000059563332,0.00037036033],"genre_scores_gemma":[0.93095607,0.0005722107,0.06669713,0.00036183442,0.0006688736,0.0000603697,0.00030013954,0.000012660734,0.0003707023],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983896,0.00005617135,0.00059844466,0.00027913408,0.0005307214,0.00014593756],"domain_scores_gemma":[0.9985135,0.00016895775,0.0003832767,0.00013182557,0.0007255724,0.00007685234],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034024866,0.00013034958,0.00020666777,0.0008326176,0.00011168628,0.0003321452,0.00030850046,0.00006553394,0.000089774774],"category_scores_gemma":[0.00005628692,0.00011536772,0.0003043014,0.00039381805,0.00004083056,0.00045453833,0.00004299171,0.00015458041,0.000009018536],"study_design_candidate":"design_other","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":[0.0004946385,0.0012413176,0.0075882124,0.00006332262,0.0040783817,0.00006914757,0.00041953512,0.00041318656,0.031585883,0.028401088,0.0033110466,0.92233425],"study_design_scores_gemma":[0.0053074057,0.0010079246,0.35291818,0.00054911705,0.0015989217,0.00057843485,0.000108567154,0.060642842,0.12785238,0.43079606,0.017110843,0.0015293257],"about_ca_topic_score_codex":0.000025485664,"about_ca_topic_score_gemma":0.0000038342223,"teacher_disagreement_score":0.9208049,"about_ca_system_score_codex":0.00006176568,"about_ca_system_score_gemma":0.00003208111,"threshold_uncertainty_score":0.4704559},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16256006,0.0001728805,0.8330472,0.002162812,0.00048808276,0.00013095897,0.00007189776,0.000072714975,0.0012933966],"genre_scores_gemma":[0.99004275,0.0012207298,0.007988664,0.00034991128,0.0000811511,0.0000072099388,0.00014063703,0.000005916825,0.0001630581],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9982841,0.00012250862,0.0005382645,0.00025327655,0.0006662561,0.00013561708],"domain_scores_gemma":[0.9979508,0.00008920679,0.0004839656,0.00014595017,0.0012276869,0.000102410115],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00094753236,0.00012799187,0.00022764964,0.0007844839,0.00010405423,0.0003938553,0.00042789444,0.000061781946,0.00026265625],"category_scores_gemma":[0.0001345045,0.00010509156,0.00017144241,0.00090547313,0.000046858306,0.000705357,0.00006789594,0.00017756966,0.000042296626],"study_design_candidate":"design_other","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":[0.00019267532,0.00074951694,0.0060945167,0.000012497727,0.0026820102,0.0000548949,0.000327774,0.000086150474,0.0026916293,0.003435523,0.0003249549,0.98334783],"study_design_scores_gemma":[0.0059682443,0.0015657529,0.32188076,0.00065840804,0.0010496732,0.0003671465,0.00017789414,0.0045631295,0.37499034,0.28390378,0.0033926398,0.0014822129],"about_ca_topic_score_codex":0.00023843399,"about_ca_topic_score_gemma":0.000038078615,"teacher_disagreement_score":0.98186564,"about_ca_system_score_codex":0.000110795365,"about_ca_system_score_gemma":0.00007872116,"threshold_uncertainty_score":0.42855096},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75629634,0.00022981458,0.23708858,0.0025973995,0.0002655585,0.00050071825,0.000060721508,0.00007015313,0.0028907328],"genre_scores_gemma":[0.97954416,0.0009252122,0.018713249,0.00016292805,0.00010516261,0.000053172276,0.00028413872,0.000009714541,0.00020227209],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9967981,0.00041322998,0.0009287193,0.0004224125,0.0012410108,0.0001965485],"domain_scores_gemma":[0.9970593,0.00014475068,0.00082875043,0.0001952438,0.0016644099,0.00010758596],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026100916,0.00021387967,0.00029871994,0.0010764025,0.00016482052,0.0007244788,0.00037978857,0.000077660734,0.0003577771],"category_scores_gemma":[0.000057730344,0.00017593641,0.00014106302,0.00062108086,0.000093955474,0.0009583492,0.00010691099,0.00025262756,0.000013623129],"study_design_candidate":"design_other","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":[0.00014520848,0.00031453077,0.033123076,0.000024149114,0.0012628044,0.000011285095,0.00022660999,0.000110431036,0.0012620753,0.0011532152,0.0009167804,0.96144986],"study_design_scores_gemma":[0.0027355398,0.0007365838,0.89327806,0.00031558584,0.00069429073,0.00012373443,0.00007572821,0.028491162,0.014169955,0.057130754,0.0015665408,0.000682054],"about_ca_topic_score_codex":0.00016387337,"about_ca_topic_score_gemma":0.00013109617,"teacher_disagreement_score":0.9607678,"about_ca_system_score_codex":0.00016904184,"about_ca_system_score_gemma":0.00008876112,"threshold_uncertainty_score":0.7174479},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00246502,0.00013745415,0.99431825,0.0022205925,0.00041563733,0.00021854352,0.000030211899,0.00003905779,0.00015524586],"genre_scores_gemma":[0.6910412,0.001036284,0.30630523,0.00070295756,0.00023622219,0.000086667555,0.000065681175,0.000016482281,0.00050928886],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979055,0.00019874601,0.0006978569,0.00032359269,0.0006972343,0.00017705276],"domain_scores_gemma":[0.9978723,0.00025980375,0.0005844597,0.00019682408,0.00097380206,0.00011280794],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012950143,0.00018450088,0.00029408326,0.00081569783,0.00018639599,0.00021752657,0.000653044,0.000084173254,0.00020867963],"category_scores_gemma":[0.00011577965,0.00012697998,0.0004114312,0.00048329576,0.000057728186,0.00046005228,0.000116342024,0.00020655002,0.000008653644],"study_design_candidate":"design_other","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":[0.00032717412,0.0004267794,0.0007689941,0.000017629547,0.003748052,0.000027100556,0.001401946,0.00011714505,0.00076342776,0.005301673,0.0023423263,0.9847578],"study_design_scores_gemma":[0.008404355,0.0044735298,0.019574089,0.0006918701,0.0054673417,0.0008042253,0.0010665306,0.1112003,0.40694666,0.4079522,0.031242086,0.0021768117],"about_ca_topic_score_codex":0.0001580659,"about_ca_topic_score_gemma":0.00001891089,"teacher_disagreement_score":0.98258096,"about_ca_system_score_codex":0.00024005902,"about_ca_system_score_gemma":0.00005665453,"threshold_uncertainty_score":0.51780933},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73204756,0.00025717187,0.25853372,0.0043576094,0.0011172676,0.00011409314,0.0000102220565,0.00004839269,0.0035139497],"genre_scores_gemma":[0.99312973,0.00048128032,0.0034878321,0.001619392,0.00032827753,0.000003878053,0.00005294586,0.000007230431,0.00088945247],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.997752,0.0001250738,0.00065439305,0.00034813792,0.0008372884,0.00028308906],"domain_scores_gemma":[0.9987441,0.00014361381,0.00033087676,0.00015001865,0.00039885024,0.00023257796],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018938534,0.000174775,0.00023424743,0.0013752552,0.00016408283,0.0005850069,0.00052282953,0.00010156506,0.000676151],"category_scores_gemma":[0.00010360445,0.0001491242,0.00025412897,0.0008399211,0.00003054987,0.0006595626,0.0001129938,0.000411899,0.00019704494],"study_design_candidate":"design_other","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":[0.0005302676,0.000638478,0.097530134,0.000013267954,0.0028518513,0.0015878892,0.002168062,0.00091087545,0.0020917046,0.024603626,0.0006022611,0.8664716],"study_design_scores_gemma":[0.009411152,0.0010344415,0.7406067,0.0006664636,0.0010602252,0.001720765,0.0017095141,0.025409143,0.040344395,0.14404643,0.031266768,0.0027239833],"about_ca_topic_score_codex":0.000060367805,"about_ca_topic_score_gemma":0.00006776847,"teacher_disagreement_score":0.8637476,"about_ca_system_score_codex":0.00019824978,"about_ca_system_score_gemma":0.00005374489,"threshold_uncertainty_score":0.74033797},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10719326,0.00013290384,0.88701296,0.001249031,0.0007176076,0.0001808018,0.000022235394,0.00016716473,0.0033240553],"genre_scores_gemma":[0.93712777,0.00022378296,0.060590602,0.0015637261,0.00023646513,0.000014432855,0.00006175961,0.000012254293,0.00016917822],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9980339,0.00016004304,0.0005021849,0.00038843288,0.0007148439,0.00020061371],"domain_scores_gemma":[0.99843854,0.000061904255,0.00042502797,0.00023509914,0.0006765689,0.0001628872],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005762335,0.00020594585,0.00023454559,0.0013770385,0.00019909012,0.00079996197,0.0006193857,0.00010778887,0.0009355406],"category_scores_gemma":[0.000047256104,0.00017127069,0.00031224673,0.0005489969,0.000054006217,0.000901935,0.00007060834,0.000303831,0.000055989647],"study_design_candidate":"design_other","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":[0.00026888214,0.0007797376,0.0058645187,0.000012944556,0.0032376132,0.00024045518,0.0010495448,0.00007527752,0.0029680398,0.005307234,0.0013345006,0.9788613],"study_design_scores_gemma":[0.008683669,0.002167348,0.17842455,0.001299327,0.004085522,0.001903395,0.0005373861,0.07787878,0.41303465,0.28820664,0.019448493,0.004330218],"about_ca_topic_score_codex":0.00005626146,"about_ca_topic_score_gemma":0.000013936334,"teacher_disagreement_score":0.97453105,"about_ca_system_score_codex":0.0001321927,"about_ca_system_score_gemma":0.000052757503,"threshold_uncertainty_score":0.99997777},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19070281,0.000052046373,0.79232186,0.014648752,0.00044285212,0.00037805768,0.000037010534,0.00008857426,0.0013280641],"genre_scores_gemma":[0.95791906,0.00013756641,0.037953604,0.0015247321,0.0013917251,0.00011465828,0.00024675814,0.000012549119,0.00069931627],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99864864,0.000036886802,0.00033315737,0.00036559804,0.00041151972,0.00020420169],"domain_scores_gemma":[0.9989246,0.00012539637,0.0002630386,0.00008974129,0.0004838877,0.00011333397],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034611794,0.00015757354,0.00019082744,0.00061244017,0.0003572481,0.0009661322,0.0002741584,0.000067022775,0.0000555016],"category_scores_gemma":[0.000018530385,0.00013662566,0.0002106257,0.0006193311,0.000013646224,0.00034869352,0.00004795803,0.0001729101,0.000031777938],"study_design_candidate":"design_other","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":[0.0001868035,0.00027076184,0.00095067406,0.000008696067,0.0010539314,0.000008746588,0.00009812791,0.0038155727,0.007474333,0.011752844,0.018399285,0.95598024],"study_design_scores_gemma":[0.0084849205,0.0014380664,0.027739476,0.00063519453,0.0024476054,0.0006777909,0.00034117405,0.100872055,0.10788531,0.5571783,0.18915358,0.003146529],"about_ca_topic_score_codex":0.000023375756,"about_ca_topic_score_gemma":0.00007395938,"teacher_disagreement_score":0.9528337,"about_ca_system_score_codex":0.00008801618,"about_ca_system_score_gemma":0.000018476489,"threshold_uncertainty_score":0.9316435},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95848507,0.000012281646,0.0021859568,0.00062766095,0.0019219418,0.00022358628,0.00011044821,0.00010692301,0.036326144],"genre_scores_gemma":[0.99706584,0.00025320385,0.00041637273,0.0006768159,0.0003944668,0.000025783946,0.00005104952,0.000016909611,0.0010995452],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9978677,0.00022772554,0.00061001576,0.00042374412,0.00064694183,0.00022385955],"domain_scores_gemma":[0.99859375,0.00020919136,0.00046652672,0.00013878146,0.0003978959,0.0001938431],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002086071,0.00020734036,0.00026220237,0.0009841319,0.00031302613,0.00042002523,0.00024064179,0.0000808334,0.0036475149],"category_scores_gemma":[0.0002906321,0.00017001443,0.00034799342,0.00042726408,0.00006806007,0.0006725476,0.000041695745,0.00036240745,0.0005567238],"study_design_candidate":"design_other","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":[0.006789332,0.0069416007,0.008764402,0.00020381865,0.015284939,0.004754606,0.0102834,0.0020939675,0.054953255,0.016162392,0.008098892,0.86566937],"study_design_scores_gemma":[0.015497594,0.004698388,0.032826733,0.0031682109,0.013539784,0.016883407,0.012941749,0.023400962,0.7405763,0.09071562,0.039646428,0.006104793],"about_ca_topic_score_codex":0.00007390393,"about_ca_topic_score_gemma":0.00004445036,"teacher_disagreement_score":0.8595646,"about_ca_system_score_codex":0.00020342914,"about_ca_system_score_gemma":0.000030372958,"threshold_uncertainty_score":0.9972633},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.084412545,0.00055470923,0.9027068,0.008389378,0.0006252944,0.00016150584,0.0000113336055,0.00017777592,0.0029606516],"genre_scores_gemma":[0.94353443,0.003321337,0.048552174,0.0026006121,0.0006041347,0.000008228227,0.000033964203,0.000012873571,0.0013322148],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99770963,0.00010040947,0.0005994131,0.00039497498,0.0009401027,0.00025546862],"domain_scores_gemma":[0.99857527,0.00010466373,0.00042161398,0.00020714295,0.0004931237,0.00019817034],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00060145097,0.00021260492,0.00027396603,0.0010209642,0.00022056444,0.0011679882,0.00070868345,0.000071517396,0.00043525558],"category_scores_gemma":[0.00011385061,0.00017351718,0.00031737014,0.0007236225,0.000039257422,0.0021612998,0.00016227944,0.00034719164,0.0000930623],"study_design_candidate":"design_other","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":[0.000069268244,0.0001521324,0.0021649126,0.0000023714992,0.0012881091,0.00009033875,0.00015392498,0.00004407565,0.000520501,0.002167451,0.0012931041,0.9920538],"study_design_scores_gemma":[0.00901345,0.0022052734,0.04328684,0.0009954526,0.002316491,0.0015974316,0.0003199102,0.018239787,0.2697621,0.30189008,0.34672603,0.003647167],"about_ca_topic_score_codex":0.000012787507,"about_ca_topic_score_gemma":0.0000066870643,"teacher_disagreement_score":0.98840666,"about_ca_system_score_codex":0.00021007015,"about_ca_system_score_gemma":0.000033413817,"threshold_uncertainty_score":0.99986887},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48604113,0.00046368488,0.50966483,0.0020063028,0.00058439886,0.00036682902,0.00002190044,0.00017107373,0.00067982386],"genre_scores_gemma":[0.95064074,0.0024947196,0.04586954,0.0004255404,0.00017225563,0.000028074417,0.000052036048,0.00001121615,0.00030585835],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.998065,0.00018544208,0.00050740293,0.00047108726,0.0005808507,0.00019019759],"domain_scores_gemma":[0.9987674,0.000058632588,0.00041672678,0.000103070495,0.0005144267,0.00013978747],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007547585,0.00021219488,0.00024376196,0.0016084791,0.00014159974,0.00053977943,0.00031968922,0.00019090348,0.00030534682],"category_scores_gemma":[0.000056463203,0.00018734002,0.00015498068,0.000633006,0.000034675802,0.0013437391,0.000067827736,0.0005917721,0.000021173293],"study_design_candidate":"design_other","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":[0.00027223252,0.0008329403,0.011021685,0.000012155773,0.0011601138,0.000147644,0.001186774,0.000033962046,0.012365858,0.0007558391,0.00032630414,0.9718845],"study_design_scores_gemma":[0.007325678,0.0015850232,0.73838705,0.0007271666,0.001059544,0.0019061074,0.0006138367,0.08070202,0.120326586,0.0398138,0.00562202,0.0019311432],"about_ca_topic_score_codex":0.000059756854,"about_ca_topic_score_gemma":0.00015163259,"teacher_disagreement_score":0.96995336,"about_ca_system_score_codex":0.0001764871,"about_ca_system_score_gemma":0.000031850836,"threshold_uncertainty_score":0.7639504},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.68049186,0.00021112007,0.30105183,0.017418738,0.00035465357,0.000088402616,0.0000036391612,0.000029011338,0.0003507409],"genre_scores_gemma":[0.98774254,0.0018915499,0.008751402,0.0011191709,0.00020956829,0.0000098219925,0.000011802755,0.000005502275,0.00025866777],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984738,0.00008837178,0.0003896956,0.00036664208,0.0005457802,0.00013571401],"domain_scores_gemma":[0.99906427,0.0001234333,0.0003160049,0.00009754487,0.00024463114,0.00015411757],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004699861,0.00014524822,0.00017404655,0.00053455273,0.00022471743,0.0009971967,0.0001956447,0.00004986249,0.00018808975],"category_scores_gemma":[0.00004755648,0.00009402844,0.00007932923,0.00021610704,0.00008511227,0.001160985,0.00010994357,0.000106700325,0.000020387683],"study_design_candidate":"design_other","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":[0.000034763925,0.00004242348,0.00421874,0.0000051304005,0.00040955842,0.00001167107,0.00041274048,0.0000025955417,0.0037062764,0.0029060114,0.0002641456,0.98798597],"study_design_scores_gemma":[0.011528196,0.0013306276,0.43943587,0.0017163063,0.0018640733,0.0008625968,0.0010286464,0.020702466,0.028151289,0.4695461,0.021558886,0.002274951],"about_ca_topic_score_codex":0.000016020686,"about_ca_topic_score_gemma":0.000016143866,"teacher_disagreement_score":0.985711,"about_ca_system_score_codex":0.000096731375,"about_ca_system_score_gemma":0.000027921733,"threshold_uncertainty_score":0.96159905},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0598067,0.000033595166,0.937019,0.0016989517,0.00021238744,0.00016063935,0.0002931628,0.000091632355,0.00068394945],"genre_scores_gemma":[0.72017115,0.00010482067,0.27728066,0.0016820921,0.00032770715,0.000032128326,0.00031026534,0.0000136655935,0.00007749445],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972646,0.00014596913,0.00068054046,0.0006040022,0.0009380853,0.000366784],"domain_scores_gemma":[0.99767977,0.00019637519,0.0006344196,0.00048216037,0.0007070524,0.0003002041],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0012312676,0.00027128143,0.00037019097,0.0010963597,0.0010375858,0.002694173,0.0011839194,0.0000688812,0.00015139388],"category_scores_gemma":[0.0005787194,0.00023572681,0.00032424266,0.0002532175,0.00005610547,0.0013337734,0.0003882868,0.0003515624,0.000010235579],"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":[0.00020256607,0.0024246287,0.0063872393,0.00004074901,0.002874963,0.00017169231,0.00067768723,0.034220956,0.0015442637,0.0075228373,0.0011175941,0.9428148],"study_design_scores_gemma":[0.0011531948,0.0001409724,0.0006585914,0.00025179735,0.00028997965,0.000075489006,0.00008532857,0.98494935,0.006434918,0.0044568265,0.0010042207,0.0004993102],"about_ca_topic_score_codex":0.000080877224,"about_ca_topic_score_gemma":0.00008427817,"teacher_disagreement_score":0.9507284,"about_ca_system_score_codex":0.00011591723,"about_ca_system_score_gemma":0.00008359702,"threshold_uncertainty_score":0.99834114},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6953447,0.00014276258,0.30034822,0.0021086412,0.00064791663,0.00016003387,0.00002683529,0.00012197695,0.0010989092],"genre_scores_gemma":[0.98863477,0.0009012459,0.008956488,0.0004068644,0.0005823358,0.000013214503,0.00017570492,0.0000112013595,0.0003181658],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99735606,0.0002980607,0.00076225406,0.00043207748,0.0009642543,0.00018731698],"domain_scores_gemma":[0.9974634,0.00035272154,0.00073481206,0.0001974411,0.0011110151,0.00014059627],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004729771,0.00021882214,0.00041759948,0.0010374322,0.00019909567,0.00058841903,0.0005660299,0.00011070938,0.0012921286],"category_scores_gemma":[0.0002287839,0.00017244401,0.00035884415,0.0005049712,0.00010714863,0.00068234664,0.00016704803,0.00035805357,0.000036580856],"study_design_candidate":"design_other","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":[0.00065384025,0.00072496064,0.019495446,0.00001172848,0.007414434,0.00009149003,0.0016110875,0.00010777246,0.029416222,0.0016720773,0.0018964362,0.9369045],"study_design_scores_gemma":[0.006221712,0.0021256541,0.08920935,0.0008012642,0.0017657548,0.00009035716,0.00051105913,0.032198537,0.6790616,0.18360709,0.003120504,0.001287112],"about_ca_topic_score_codex":0.00009861599,"about_ca_topic_score_gemma":0.00005075985,"teacher_disagreement_score":0.9356174,"about_ca_system_score_codex":0.0000765126,"about_ca_system_score_gemma":0.000030630577,"threshold_uncertainty_score":0.99962085},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15076545,0.00011876302,0.839635,0.0066983704,0.0011676479,0.00055063335,0.00023819442,0.00018438204,0.00064155646],"genre_scores_gemma":[0.9646047,0.00036902397,0.029536387,0.003227868,0.00023891227,0.0003691747,0.00072471506,0.000017601422,0.0009116535],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99649906,0.0003064619,0.0008614767,0.0005857575,0.0014512485,0.00029600802],"domain_scores_gemma":[0.99793136,0.00023928695,0.00072746736,0.00024862768,0.00066069426,0.00019257845],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015726315,0.00025727384,0.0004270423,0.002771539,0.000613853,0.0011895248,0.00083172764,0.000058410074,0.0017798474],"category_scores_gemma":[0.000059658752,0.00023962556,0.00079941994,0.0014661507,0.000035485275,0.00091041916,0.00027487805,0.00034056997,0.000030379571],"study_design_candidate":"design_other","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":[0.00075428025,0.0011504019,0.0064370735,0.000022280383,0.041047417,0.00019915242,0.002045864,0.0051214504,0.0016749325,0.011938439,0.007084363,0.92252433],"study_design_scores_gemma":[0.022176689,0.007601108,0.035494346,0.0003422185,0.037462506,0.0012098075,0.004706799,0.15271318,0.12522218,0.50272804,0.103819534,0.0065235836],"about_ca_topic_score_codex":0.00004918234,"about_ca_topic_score_gemma":0.000033417244,"teacher_disagreement_score":0.9160008,"about_ca_system_score_codex":0.00043711334,"about_ca_system_score_gemma":0.00006794308,"threshold_uncertainty_score":0.99984735},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3010729,0.00011991227,0.69520456,0.0026252756,0.00057693553,0.00010510893,0.000025256591,0.000016239197,0.00025380676],"genre_scores_gemma":[0.98626244,0.00012831231,0.012465767,0.0005955793,0.00019765494,0.000012555274,0.00007131408,0.0000067914643,0.0002595783],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998285,0.00010670019,0.00044915208,0.00025412656,0.0007732554,0.0001317577],"domain_scores_gemma":[0.9986771,0.00010333534,0.0006053888,0.0000988339,0.00044681432,0.000068562564],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067403837,0.00011231107,0.00020067902,0.00073285704,0.00032743532,0.00031729497,0.00038875078,0.00002540189,0.0002365444],"category_scores_gemma":[0.000032106447,0.000098623954,0.0002505445,0.00050610385,0.000034079854,0.0005340271,0.00011789467,0.00016588706,0.0000018327505],"study_design_candidate":"design_other","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":[0.0013599311,0.0009621651,0.0035497507,0.000055558972,0.0047302484,0.00016807845,0.0054115984,0.007650931,0.004293446,0.014341013,0.0047965087,0.95268077],"study_design_scores_gemma":[0.01843202,0.006199696,0.030088445,0.00085251074,0.0032770503,0.0014139944,0.009478924,0.122360736,0.041289523,0.70040387,0.06338447,0.0028187449],"about_ca_topic_score_codex":0.00001233782,"about_ca_topic_score_gemma":0.000004400053,"teacher_disagreement_score":0.949862,"about_ca_system_score_codex":0.000111435584,"about_ca_system_score_gemma":0.00006892836,"threshold_uncertainty_score":0.40217683},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06501989,0.00017037189,0.92851233,0.0037396846,0.001219438,0.00039117236,0.0001124684,0.00019095538,0.0006436731],"genre_scores_gemma":[0.970692,0.0009932509,0.023491776,0.0018389422,0.0010168658,0.0003113369,0.0010223796,0.000029769575,0.00060371484],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9968929,0.00031369357,0.0008747788,0.00057984685,0.0009969366,0.0003418206],"domain_scores_gemma":[0.99772656,0.00023519169,0.00074490655,0.00020701866,0.0008975998,0.00018871883],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0018337447,0.00025926952,0.00035864004,0.0015368889,0.0008534792,0.0010838183,0.00067190063,0.00008689681,0.00084144314],"category_scores_gemma":[0.000107264896,0.000251176,0.00056166947,0.0008110849,0.000040205166,0.0009257261,0.000277807,0.0005413669,0.000024355299],"study_design_candidate":"design_other","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":[0.00018579807,0.00029621425,0.0005634888,0.000006945524,0.0014594037,0.000059320297,0.00010885672,0.00052698376,0.0002927803,0.00061923754,0.001123653,0.9947573],"study_design_scores_gemma":[0.017677443,0.007615735,0.008345911,0.0010304317,0.004769905,0.0033024896,0.0017497299,0.41854626,0.022554286,0.44377205,0.065826334,0.0048094383],"about_ca_topic_score_codex":0.000028342496,"about_ca_topic_score_gemma":0.000016831544,"teacher_disagreement_score":0.98994786,"about_ca_system_score_codex":0.0003277574,"about_ca_system_score_gemma":0.00004665384,"threshold_uncertainty_score":0.99999404},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29540837,0.00019887065,0.69657916,0.0055825617,0.0011967839,0.00011849664,0.00006573413,0.000404079,0.00044593518],"genre_scores_gemma":[0.92945963,0.0016436423,0.06415938,0.0020705345,0.00076249987,0.000028335568,0.0010736336,0.000011321391,0.0007909949],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981197,0.00010545775,0.00052203727,0.00025968513,0.0007901908,0.00020291844],"domain_scores_gemma":[0.9987554,0.00011139964,0.0004081313,0.00014693868,0.00045478533,0.00012337565],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00066665356,0.00015491902,0.00020795088,0.0010206063,0.00022499627,0.0016029592,0.0004888465,0.00011751671,0.00036926183],"category_scores_gemma":[0.00008879191,0.00012280371,0.00020764809,0.0007564221,0.000022511831,0.0024284902,0.00015051263,0.00034566442,0.00016648683],"study_design_candidate":"design_other","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":[0.00011839018,0.00014777952,0.004409354,0.000005822922,0.0012491939,0.000118478936,0.0016087557,0.000099453624,0.0005317415,0.0012048163,0.008225637,0.98228055],"study_design_scores_gemma":[0.005453192,0.00073615107,0.13877945,0.00065509375,0.0014964734,0.0003890081,0.0019849134,0.16228713,0.027075034,0.5588711,0.09988011,0.0023923623],"about_ca_topic_score_codex":0.00049819343,"about_ca_topic_score_gemma":0.00053456856,"teacher_disagreement_score":0.9798882,"about_ca_system_score_codex":0.0001571578,"about_ca_system_score_gemma":0.00003906472,"threshold_uncertainty_score":0.99943346},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31562063,0.00010716892,0.65421057,0.02467105,0.0019923705,0.0004452776,0.0001135553,0.0009806076,0.0018587726],"genre_scores_gemma":[0.97019696,0.0015906118,0.022961833,0.002842041,0.0006274741,0.000039533992,0.0004915664,0.000029992249,0.0012199589],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99669105,0.00022427987,0.0007464107,0.00052871025,0.0014472825,0.00036225945],"domain_scores_gemma":[0.9978296,0.00024639876,0.00045359402,0.0002776618,0.0009177316,0.00027499357],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015227173,0.0002688454,0.00035391861,0.0023520885,0.00028278152,0.0017585527,0.0008379093,0.00011012799,0.0011180576],"category_scores_gemma":[0.000162438,0.00023033556,0.0004970539,0.0017624336,0.00006966511,0.0010919407,0.0002030955,0.00038822799,0.00066468347],"study_design_candidate":"design_other","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":[0.00082586496,0.001204089,0.0091504045,0.000059275822,0.012160312,0.003056395,0.0009316491,0.000362259,0.010014381,0.0074765906,0.038020715,0.91673803],"study_design_scores_gemma":[0.013818451,0.0030209695,0.06674486,0.001243435,0.0029025518,0.0008496717,0.000532879,0.041846134,0.45480084,0.34589636,0.06392308,0.0044207615],"about_ca_topic_score_codex":0.000018769448,"about_ca_topic_score_gemma":0.000006926574,"teacher_disagreement_score":0.9123173,"about_ca_system_score_codex":0.00023653921,"about_ca_system_score_gemma":0.00008664417,"threshold_uncertainty_score":0.9997951},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09615261,0.00018549143,0.89011544,0.0084554395,0.00179759,0.0006334542,0.0017502937,0.00039713152,0.00051255396],"genre_scores_gemma":[0.75083596,0.006126206,0.23110406,0.002371767,0.0014068168,0.00015815058,0.007236121,0.000060347324,0.00070055673],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99720776,0.00016275342,0.000757089,0.00070964533,0.00078517484,0.000377549],"domain_scores_gemma":[0.9978314,0.00048015645,0.00045602588,0.00042373865,0.00064232596,0.00016636512],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0013315587,0.00026135106,0.00039391418,0.0021817854,0.00021445334,0.0014074417,0.001278542,0.00017541685,0.00062247104],"category_scores_gemma":[0.00047384974,0.00023402326,0.00018548543,0.001752709,0.000047562844,0.0019515204,0.00035516455,0.0004711386,0.00006658815],"study_design_candidate":"design_other","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":[0.00013223701,0.0002018062,0.0019481572,0.000021320087,0.0014997597,0.00013635487,0.00022292577,0.00017831451,0.00047274737,0.0013999705,0.011639385,0.98214704],"study_design_scores_gemma":[0.0022692773,0.0003312908,0.00604308,0.00073128723,0.0005522802,0.00019348672,0.00028590235,0.03027204,0.015789399,0.9324067,0.010113361,0.001011882],"about_ca_topic_score_codex":0.000045702785,"about_ca_topic_score_gemma":0.000075562595,"teacher_disagreement_score":0.98113513,"about_ca_system_score_codex":0.00013514147,"about_ca_system_score_gemma":0.00007973612,"threshold_uncertainty_score":0.9996292},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97931594,0.000061997,0.017438877,0.0025691073,0.00030557206,0.00008539737,0.00005607918,0.000045936395,0.000121081044],"genre_scores_gemma":[0.9945189,0.0010470336,0.0035335845,0.0002461283,0.00028044803,0.0000068604604,0.00021381748,0.0000083524055,0.00014488284],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9980459,0.00011094819,0.0006870687,0.00037273508,0.0005802111,0.00020311447],"domain_scores_gemma":[0.9982071,0.00022992617,0.0006424779,0.00016085051,0.0006252703,0.00013438836],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009404945,0.00016861146,0.00033262515,0.0010768272,0.00019403196,0.00055779144,0.00031889096,0.00006367111,0.00022155844],"category_scores_gemma":[0.00026148083,0.00013658559,0.00028014282,0.00083229895,0.000056399815,0.0010684045,0.00020804157,0.00022020921,0.000019366391],"study_design_candidate":"design_other","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":[0.00007042774,0.00012831796,0.0060376045,0.000015801703,0.0012529775,0.00003907484,0.00040607477,0.000049275193,0.0009504187,0.00019783707,0.00007994211,0.99077225],"study_design_scores_gemma":[0.006605598,0.0014919575,0.5405193,0.00095604674,0.0035091087,0.0005773957,0.0031099261,0.33809426,0.013288429,0.08480094,0.0047942116,0.0022528246],"about_ca_topic_score_codex":0.000075753014,"about_ca_topic_score_gemma":0.000034727243,"teacher_disagreement_score":0.98851943,"about_ca_system_score_codex":0.000055337074,"about_ca_system_score_gemma":0.00003049101,"threshold_uncertainty_score":0.55697984},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98750013,0.0012956038,0.008718793,0.00048451647,0.0011150928,0.000069785514,0.00013601752,0.00006658845,0.0006134597],"genre_scores_gemma":[0.9956482,0.00022740198,0.0015599969,0.0003951632,0.0005774613,0.0000013269481,0.001299496,0.000005396584,0.00028553721],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99794436,0.00021981387,0.0005203752,0.0003209511,0.0007440701,0.0002504606],"domain_scores_gemma":[0.9991979,0.00016647673,0.00018629443,0.00008876774,0.00017624398,0.00018433474],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008469895,0.00019686557,0.00031579746,0.0011941906,0.00038201307,0.0016369136,0.00018946148,0.00007216789,0.014008929],"category_scores_gemma":[0.000026541296,0.00014213397,0.0006077333,0.0016533139,0.00005342186,0.00040983147,0.000009952185,0.00027076848,0.00019908529],"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":[0.00013627476,0.00007516941,0.3836281,0.000031262764,0.021328488,0.00048522494,0.00025675047,0.15244228,0.000024066465,0.00002677165,0.00036686155,0.44119874],"study_design_scores_gemma":[0.00029698355,0.00008856038,0.1922296,0.00016149059,0.0038285789,0.000058585432,0.0001440352,0.8004053,0.0000079615975,0.0014364292,0.0010688797,0.00027356148],"about_ca_topic_score_codex":0.00029981503,"about_ca_topic_score_gemma":0.0011626045,"teacher_disagreement_score":0.64796305,"about_ca_system_score_codex":0.000042389645,"about_ca_system_score_gemma":0.000057215166,"threshold_uncertainty_score":0.9993995},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.123182565,0.0003932663,0.87233937,0.0018923248,0.0015986356,0.00014310004,0.000012321112,0.00007687199,0.00036153785],"genre_scores_gemma":[0.8498691,0.00045999535,0.14703348,0.00082913955,0.0009414623,0.000016113208,0.000046060173,0.000026061327,0.0007786396],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975051,0.00020822906,0.00065750774,0.00052718027,0.00079505506,0.00030692594],"domain_scores_gemma":[0.9985569,0.00031744622,0.00025352387,0.00018086453,0.000517746,0.0001735173],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0014571798,0.00024695185,0.00032375453,0.0013728031,0.0003184533,0.003848292,0.0005163404,0.000073900876,0.00021116782],"category_scores_gemma":[0.000090035894,0.00020116147,0.00053565763,0.00065797876,0.00004890889,0.0016354726,0.000115152565,0.00026715355,0.00002886613],"study_design_candidate":"design_other","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":[0.00033903267,0.00021490162,0.00008660534,0.00005861455,0.0067847283,0.00054826064,0.0013722491,0.0013535294,0.08863408,0.004635962,0.0009802766,0.89499176],"study_design_scores_gemma":[0.0052607567,0.0008543258,0.0008163401,0.0016638108,0.0033807266,0.0009170812,0.00034080888,0.3335301,0.33253843,0.30570027,0.0131338285,0.0018635064],"about_ca_topic_score_codex":0.00003179956,"about_ca_topic_score_gemma":0.0000058918354,"teacher_disagreement_score":0.8931283,"about_ca_system_score_codex":0.000274052,"about_ca_system_score_gemma":0.00009733673,"threshold_uncertainty_score":0.9971858},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15386249,0.00006096737,0.84286225,0.001265264,0.0008063902,0.00014338561,0.000008731518,0.000115518604,0.00087501225],"genre_scores_gemma":[0.7650407,0.00044122172,0.23258694,0.0012893727,0.00021965503,0.000026529407,0.000056914996,0.000012018153,0.00032666564],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99768454,0.0004481201,0.0006763095,0.00042033533,0.00056395103,0.0002067164],"domain_scores_gemma":[0.99820215,0.00017645628,0.0004607002,0.00018071385,0.0008642381,0.00011573274],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0010397546,0.00021261428,0.00027954698,0.0022198646,0.0003030952,0.0014342378,0.0004482771,0.000099713594,0.00031472876],"category_scores_gemma":[0.000134249,0.00018962842,0.0003178103,0.0011918724,0.00005049815,0.0014516243,0.0001366416,0.0003440133,0.00001579467],"study_design_candidate":"design_other","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":[0.00005675526,0.00009989215,0.0003498661,0.0000051905836,0.0012938817,0.000026858195,0.00008924199,0.000064172564,0.024702292,0.00027478047,0.00010115924,0.9729359],"study_design_scores_gemma":[0.002863259,0.00041877475,0.011755678,0.00033983486,0.0017604848,0.00043554208,0.00032377793,0.26866567,0.62252307,0.087445885,0.0025030416,0.0009649789],"about_ca_topic_score_codex":0.00005514354,"about_ca_topic_score_gemma":0.000015076978,"teacher_disagreement_score":0.9719709,"about_ca_system_score_codex":0.00030234194,"about_ca_system_score_gemma":0.000050672483,"threshold_uncertainty_score":0.9996024},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029859968,0.00013836734,0.9648899,0.0023351896,0.00082539674,0.00030766355,0.00010528918,0.0001269085,0.0014113224],"genre_scores_gemma":[0.96067107,0.0014859079,0.032090683,0.0031526508,0.00057178474,0.0001390467,0.00063363276,0.000017601844,0.001237633],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997826,0.00013799948,0.0006997041,0.00047806912,0.00060533575,0.0002529117],"domain_scores_gemma":[0.99818754,0.00022895448,0.000455608,0.00021177455,0.00079653814,0.000119576805],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0011745642,0.0002110827,0.00030360802,0.0015955652,0.0003750279,0.0015391818,0.0006269617,0.00009180177,0.00020439996],"category_scores_gemma":[0.00020121329,0.00018921986,0.00025657596,0.00091004506,0.000028966642,0.0012713119,0.00017378744,0.00024945376,0.000028864026],"study_design_candidate":"design_other","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":[0.00010240412,0.0001432601,0.0009831645,0.00002001282,0.002377592,0.000024094083,0.000053977226,0.00002553768,0.0012510727,0.0022354885,0.002381221,0.99040216],"study_design_scores_gemma":[0.010766153,0.0014831608,0.013557623,0.0023381945,0.004422061,0.0004534999,0.00034944213,0.047181934,0.31674913,0.42167753,0.17833555,0.002685717],"about_ca_topic_score_codex":0.000023598657,"about_ca_topic_score_gemma":0.0000132394225,"teacher_disagreement_score":0.98771644,"about_ca_system_score_codex":0.00020545773,"about_ca_system_score_gemma":0.000060202325,"threshold_uncertainty_score":0.9994973},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3681466,0.0006720263,0.61945015,0.0074742823,0.0010663997,0.00031414497,0.000034027642,0.00016548963,0.0026768823],"genre_scores_gemma":[0.992269,0.0013036545,0.005081592,0.00038180273,0.00005509639,0.000036640675,0.00015575087,0.0000035493297,0.00071293017],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99721634,0.00022340279,0.0009704658,0.0005427836,0.00081540574,0.0002315897],"domain_scores_gemma":[0.9982194,0.00016495743,0.00064258213,0.00033115517,0.0005520002,0.00008996086],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00078910147,0.00023007551,0.00050715153,0.0051170555,0.00019849846,0.0019029364,0.0010123805,0.00011370922,0.00010852183],"category_scores_gemma":[0.000073135285,0.00020023396,0.00034864858,0.0038863758,0.0000696127,0.0019546023,0.00021137133,0.00036284697,0.000026773065],"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":[0.00047862952,0.0035826087,0.24218756,0.000058118374,0.05607975,0.00019592971,0.0033101835,0.027180657,0.0011387336,0.42086208,0.0028909384,0.24203481],"study_design_scores_gemma":[0.005146771,0.00030150547,0.5337169,0.00056096254,0.0053152437,0.00003257298,0.0064287023,0.35514057,0.001571392,0.0813398,0.009083667,0.0013618757],"about_ca_topic_score_codex":0.0001260417,"about_ca_topic_score_gemma":0.00024240765,"teacher_disagreement_score":0.6241224,"about_ca_system_score_codex":0.00041804987,"about_ca_system_score_gemma":0.0000615162,"threshold_uncertainty_score":0.99913317},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.70846313,0.0007729457,0.2516694,0.013676118,0.005463488,0.0008100863,0.00020054399,0.00010718845,0.018837066],"genre_scores_gemma":[0.98759353,0.0005164069,0.0011451272,0.0028468037,0.0009559187,0.00011285325,0.00041031482,0.000011661477,0.006407356],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9983482,0.00016246167,0.0006102929,0.00033397105,0.00033824268,0.00020685206],"domain_scores_gemma":[0.9987035,0.00024957,0.00031189897,0.00013653864,0.000483833,0.00011468213],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006855343,0.0001807759,0.0002891377,0.0009836142,0.00021795736,0.00030265225,0.00020495521,0.00012072125,0.0045960583],"category_scores_gemma":[0.000062666506,0.00014443822,0.00047432768,0.00064662565,0.000044732973,0.00012925426,0.000020146836,0.00022600117,0.00008995185],"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":[0.0067194435,0.0018316696,0.1121032,0.000025201522,0.024277624,0.000067371155,0.0018040029,0.0010108125,0.0007410871,0.030366955,0.15989178,0.6611608],"study_design_scores_gemma":[0.007816596,0.0006633647,0.7366803,0.00015512192,0.002441294,0.000048958093,0.0007724312,0.007234667,0.000038311224,0.06329805,0.180165,0.0006858783],"about_ca_topic_score_codex":0.00004348996,"about_ca_topic_score_gemma":0.00010486241,"teacher_disagreement_score":0.66047496,"about_ca_system_score_codex":0.00009774775,"about_ca_system_score_gemma":0.000031731855,"threshold_uncertainty_score":0.99631387},"labels":[],"label_agreement":null}]}