{"meta":{"query_hash":"03ce2755ddb7","filters":{"topic":"Handwritten Text Recognition Techniques"},"cohort_total":605,"direct_labels_cover":0,"predictions_cover":605,"exported":605,"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/03ce2755ddb7","api":"https://metacan.xera.ac/api/v1/cohort?topic=Handwritten+Text+Recognition+Techniques"},"results":[{"id":"W101006898","doi":"10.1007/978-3-540-78199-8_2","title":"A Review on Persian Script and Recognition Techniques","year":2008,"lang":"en","type":"review","venue":"Lecture notes in computer science","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Collège de Maisonneuve","funders":"","keywords":"Persian; Arabic; Alphabet; Arabic script; Natural language processing; Computer science; Linguistics; Artificial intelligence","score_opus":0.045037744360922394,"score_gpt":0.31603420570617013,"score_spread":0.27099646134524774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W101006898","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.0353397e-7,0.51532644,0.4830827,0.00016963338,0.00019157906,0.00081510446,0.0000046827417,0.00036137606,0.000048243106],"genre_scores_gemma":[0.000004291593,0.6952966,0.30114427,0.0032248127,0.00013513712,0.0001605266,0.00001043885,0.000023173667,7.3474126e-7],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9956658,0.00034219274,0.000793078,0.001842445,0.0006808601,0.0006756563],"domain_scores_gemma":[0.99737746,0.0004876604,0.00041159656,0.0012766983,0.00022857201,0.00021798948],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010606186,0.0007018084,0.001519173,0.001430697,0.00029761184,0.00041231333,0.0025485926,0.0003487119,0.000008307125],"category_scores_gemma":[0.00034544626,0.0005675929,0.000285156,0.00353558,0.0005857927,0.0008035184,0.0009026537,0.0010083966,0.00006458552],"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":[3.9106388e-7,0.000037932685,3.0930067e-7,0.0040024924,0.000005006874,0.000046442427,0.00007269984,1.4171627e-7,9.571414e-7,0.000022366663,0.00016567396,0.9956456],"study_design_scores_gemma":[0.00017823206,0.0008195569,0.0000025022055,0.30167285,0.000080243706,0.0037464504,1.8498807e-7,0.0020242725,0.0011118382,0.011124056,0.6770689,0.0021709441],"about_ca_topic_score_codex":0.000019299412,"about_ca_topic_score_gemma":0.0000059772337,"teacher_disagreement_score":0.99347466,"about_ca_system_score_codex":0.00032155067,"about_ca_system_score_gemma":0.00056835293,"threshold_uncertainty_score":0.99967754},"labels":[],"label_agreement":null},{"id":"W121443288","doi":"10.1007/978-3-642-02611-9_28","title":"A New Large-Scale Multi-purpose Handwritten Farsi Database","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":25,"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":"Computer science; Spotting; Numeral system; Artificial intelligence; Speech recognition; Set (abstract data type); Natural language processing; Word (group theory); Pattern recognition (psychology); Mathematics","score_opus":0.01924858629089466,"score_gpt":0.26368769122345126,"score_spread":0.2444391049325566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W121443288","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":[0.0000073513775,0.0008344925,0.99177027,0.0008040794,0.00091238855,0.0008086547,0.000039596962,0.00087686937,0.003946325],"genre_scores_gemma":[0.0019651519,0.00015529696,0.98943,0.0042909454,0.00055694056,0.000016400523,0.00003960422,0.000058454087,0.0034872035],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.993942,0.000064660904,0.0008183252,0.0025615247,0.0013770831,0.0012363665],"domain_scores_gemma":[0.9958029,0.00027083675,0.00038560096,0.0026040717,0.00037339077,0.00056320877],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012016376,0.0008946216,0.00085992645,0.0014814014,0.00037860166,0.001018735,0.0046457546,0.00056587585,0.00011530291],"category_scores_gemma":[0.000109343106,0.00086152105,0.00026655477,0.0010025968,0.00039604,0.0014749889,0.0022090545,0.00140395,0.00021333904],"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":[0.000005773443,0.00008078458,0.00001303074,0.000025394276,0.000008695976,0.00025393508,0.0005137734,0.00016202933,0.0003880388,0.003238598,0.0003974063,0.99491256],"study_design_scores_gemma":[0.0032748,0.0010899189,0.00026570354,0.003144917,0.00006572947,0.0009917694,9.346562e-7,0.5279676,0.040226027,0.31655252,0.101506285,0.0049138167],"about_ca_topic_score_codex":0.00005202234,"about_ca_topic_score_gemma":0.00032009507,"teacher_disagreement_score":0.9899987,"about_ca_system_score_codex":0.00035161135,"about_ca_system_score_gemma":0.001004843,"threshold_uncertainty_score":0.99938357},"labels":[],"label_agreement":null},{"id":"W1489964139","doi":"10.1007/978-3-540-24677-0_47","title":"Word Separation in Handwritten Legal Amounts on Bank Cheques Based on Spatial Gap Distances","year":2004,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","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":"Concordia University","funders":"","keywords":"Cheque; Computer science; Cluster analysis; Word (group theory); Measure (data warehouse); Artificial intelligence; Class (philosophy); Order (exchange); Data mining; Pattern recognition (psychology); Computer security; Finance; Mathematics","score_opus":0.014536166032834957,"score_gpt":0.2742027539875437,"score_spread":0.2596665879547087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1489964139","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":[0.00034667528,0.00008564012,0.9890519,0.0011430322,0.0014636719,0.00085392565,0.000016200771,0.00043641342,0.006602573],"genre_scores_gemma":[0.7877748,0.000026470478,0.20356698,0.0063540903,0.0009992042,0.00016017898,0.00007922857,0.00007391644,0.0009651594],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.994211,0.000183442,0.00078636967,0.0021574055,0.0017548981,0.00090686826],"domain_scores_gemma":[0.9971575,0.00063356775,0.00039414188,0.0013825746,0.00024647923,0.00018574916],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0011832551,0.00076902757,0.00073677464,0.0018820247,0.00025710624,0.0012458179,0.0031877025,0.0005106888,0.000028472106],"category_scores_gemma":[0.00018374708,0.0007137634,0.00016943621,0.0016056848,0.0005492956,0.001060605,0.0004116614,0.0013518217,0.000060846003],"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":[0.00008005159,0.00034667665,0.00015282257,0.000107937856,0.000008066454,0.00033156713,0.0007127423,0.051747553,0.00014118513,0.0037553606,0.00029002142,0.942326],"study_design_scores_gemma":[0.001790877,0.0017612675,0.0017571801,0.005497152,0.000011916325,0.00003148405,3.647922e-7,0.7716376,0.032703273,0.17750135,0.0050500105,0.0022574768],"about_ca_topic_score_codex":0.00017168968,"about_ca_topic_score_gemma":0.0015149206,"teacher_disagreement_score":0.94006854,"about_ca_system_score_codex":0.0026546288,"about_ca_system_score_gemma":0.0030627241,"threshold_uncertainty_score":0.99979097},"labels":[],"label_agreement":null},{"id":"W1490467121","doi":"10.1109/icosp.2004.1441471","title":"Optical character recognition system based on a novel fuzzy descriptive features","year":2005,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Thresholding; Optical character recognition; Code (set theory); Feature (linguistics); Artificial intelligence; Fuzzy logic; Character (mathematics); Character recognition; Pattern recognition (psychology); Speech recognition; Image (mathematics); Mathematics; Programming language","score_opus":0.02563839657080942,"score_gpt":0.24036065508723428,"score_spread":0.21472225851642485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1490467121","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":[0.004017645,0.0000071771856,0.88153076,0.0023701335,0.00017675276,0.00038870677,0.000014492168,0.0016713459,0.10982299],"genre_scores_gemma":[0.65690947,0.0000010844689,0.3397384,0.0026329756,0.00018717493,0.00009957446,0.000015898106,0.000013607973,0.00040182157],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99848884,0.000059797847,0.00026256742,0.0004947859,0.00037457084,0.00031940985],"domain_scores_gemma":[0.9990119,0.00012585224,0.00007795144,0.0004284083,0.00020828674,0.00014763165],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00032850736,0.00020504737,0.00019333922,0.00025129857,0.0001040911,0.00025537214,0.00045127372,0.00014707136,0.00007192956],"category_scores_gemma":[0.00005338174,0.00017169442,0.00010677185,0.00027640324,0.000037470458,0.00064968975,0.000074097064,0.00024465896,0.00091270567],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007314992,0.0007289745,0.000021901202,0.000057934052,0.000029490837,0.000032356915,0.00032158667,0.000010438548,0.019774381,0.07078149,0.008158975,0.90000933],"study_design_scores_gemma":[0.0019336579,0.00078257936,0.003737535,0.00066498783,0.000032244756,0.00023379372,0.00014925243,0.07927899,0.90393853,0.0012872436,0.0068488866,0.0011123167],"about_ca_topic_score_codex":0.000011895273,"about_ca_topic_score_gemma":0.0000073731894,"teacher_disagreement_score":0.898897,"about_ca_system_score_codex":0.00020411969,"about_ca_system_score_gemma":0.000055040065,"threshold_uncertainty_score":0.9998652},"labels":[],"label_agreement":null},{"id":"W1500159001","doi":"10.1007/978-3-642-04146-4_109","title":"Simultaneous Document Margin Removal and Skew Correction Based on Corner Detection in Projection Profiles","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":5,"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":"Margin (machine learning); Computer science; Skew; Document image processing; Segmentation; Projection (relational algebra); Artificial intelligence; Computer vision; Arabic; Image segmentation; Document processing; Noise (video); Image (mathematics); Pattern recognition (psychology); Computer graphics (images); Algorithm; Machine learning","score_opus":0.00945532706917567,"score_gpt":0.2380917494291764,"score_spread":0.22863642236000073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1500159001","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":[0.00041359253,0.00007022853,0.9937653,0.0002979912,0.0012175159,0.0012104795,0.0000022627235,0.00042298165,0.0025996703],"genre_scores_gemma":[0.6701976,0.00008596321,0.32665637,0.001775502,0.00039413906,0.00008349856,0.000012571866,0.000052631236,0.0007417312],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963303,0.000097900775,0.00054921955,0.0016454717,0.00086046883,0.0005166233],"domain_scores_gemma":[0.9980708,0.00056657114,0.00030024233,0.0007235507,0.00022054369,0.00011833732],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009910703,0.0005324498,0.00045327976,0.0018376233,0.00021705253,0.0005294326,0.0008148161,0.00043353,0.0000121947705],"category_scores_gemma":[0.0002006095,0.0005066375,0.00008386141,0.0008302132,0.00028894408,0.00054934894,0.00024073673,0.00097332144,0.00001646363],"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":[0.000030494719,0.000043151904,0.0000109346065,0.000026124098,0.000002081723,0.00013895612,0.00013239859,0.0058232215,0.0003365678,0.00035177937,0.000008434636,0.9930959],"study_design_scores_gemma":[0.00039508185,0.00095935137,0.000156006,0.0008210555,0.000006009576,0.00028074303,2.1561178e-7,0.9240807,0.023643827,0.048189674,0.0008361405,0.0006311862],"about_ca_topic_score_codex":0.00006714009,"about_ca_topic_score_gemma":0.00024403002,"teacher_disagreement_score":0.99246466,"about_ca_system_score_codex":0.00080713496,"about_ca_system_score_gemma":0.0002964282,"threshold_uncertainty_score":0.9997385},"labels":[],"label_agreement":null},{"id":"W1501272469","doi":"","title":"Sparse descriptor for lexicon reduction in handwritten Arabic documents","year":2012,"lang":"en","type":"article","venue":"Espace ÉTS (ETS)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; École de Technologie Supérieure","funders":"","keywords":"Lexicon; Artificial intelligence; Arabic; Computer science; Histogram; Pattern recognition (psychology); Word (group theory); Natural language processing; Skeleton (computer programming); Pixel; Reduction (mathematics); Image (mathematics); Mathematics; Linguistics","score_opus":0.02709086643507978,"score_gpt":0.28026055963873164,"score_spread":0.25316969320365185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1501272469","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":[0.33646485,0.0008127139,0.64678085,0.005364773,0.0029193615,0.0022003404,0.000014132884,0.0011953118,0.004247677],"genre_scores_gemma":[0.9067735,0.000050944225,0.089558885,0.0002858464,0.00032916755,0.00037495056,0.00001183464,0.000028829714,0.0025860276],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99820375,0.00011382796,0.00031338428,0.00044425545,0.00027507913,0.00064972515],"domain_scores_gemma":[0.99898463,0.00006226749,0.00013986322,0.00051571574,0.00010493524,0.00019259541],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007853696,0.00022339402,0.0002488557,0.0003496305,0.00011776148,0.00019032629,0.0005233483,0.00014886058,0.000060319293],"category_scores_gemma":[0.000112572874,0.00022439504,0.00010050527,0.00045240798,0.00005178382,0.0020425906,0.00014503275,0.00018858151,0.00022245734],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034846793,0.0022969719,0.021884922,0.00031129448,0.00015145857,0.000029512286,0.014727568,0.00002792475,0.13972405,0.09664143,0.13871473,0.58514166],"study_design_scores_gemma":[0.0047461176,0.0007773525,0.022702489,0.0005645822,0.000062151754,0.00024450896,0.0007550558,0.004582164,0.7270972,0.037257753,0.19909571,0.0021148922],"about_ca_topic_score_codex":0.000063412735,"about_ca_topic_score_gemma":0.00003371593,"teacher_disagreement_score":0.5873732,"about_ca_system_score_codex":0.00019450934,"about_ca_system_score_gemma":0.00006351556,"threshold_uncertainty_score":0.91505647},"labels":[],"label_agreement":null},{"id":"W1512670244","doi":"10.1109/icpr.1992.201782","title":"Off-line signature verification using directional PDF and neural networks","year":2003,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":true,"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; Artificial neural network; Signature (topology); Artificial intelligence; Pattern recognition (psychology); Classifier (UML); Probability density function; Feedforward neural network; Feature vector; Feature extraction; Feature (linguistics); Mathematics; Statistics","score_opus":0.01940022983190206,"score_gpt":0.25463759440985145,"score_spread":0.2352373645779494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1512670244","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":[0.011009174,0.00027346401,0.9844236,0.00016529846,0.00017620622,0.00010292408,3.8714273e-7,0.0002699328,0.0035790068],"genre_scores_gemma":[0.8363928,0.000043793974,0.16239662,0.00050770683,0.000059262315,0.00000802487,0.0000036240858,0.0000058514365,0.00058231165],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993177,0.00006778858,0.00012605962,0.00024064418,0.0001146244,0.00013316862],"domain_scores_gemma":[0.9996063,0.000045838926,0.00004379882,0.0001633329,0.00008473186,0.00005600234],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018013142,0.000084554216,0.0000768809,0.00006577992,0.00010743459,0.000109613065,0.00012361887,0.000079547346,0.00013899179],"category_scores_gemma":[0.000031748168,0.000077384044,0.000024553756,0.00025134656,0.000028256885,0.00037519913,0.000033217675,0.00012942638,0.000007900784],"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":[0.000016680884,0.00025879472,0.0023904121,0.000025546293,0.00004985136,0.000020671634,0.00021677664,0.0038331698,0.036939193,0.120855756,0.0059369504,0.8294562],"study_design_scores_gemma":[0.00014647726,0.000039939496,0.0008078417,0.000008813468,0.0000045235,0.00009229581,0.000006794693,0.9701792,0.021823691,0.0033158143,0.0034071342,0.00016745784],"about_ca_topic_score_codex":0.000006934014,"about_ca_topic_score_gemma":0.00000264576,"teacher_disagreement_score":0.966346,"about_ca_system_score_codex":0.000020763951,"about_ca_system_score_gemma":0.00001741984,"threshold_uncertainty_score":0.31556296},"labels":[],"label_agreement":null},{"id":"W152011799","doi":"","title":"Arabic Handwriting Descriptor Using Gaussian Steerable Filters.","year":2010,"lang":"en","type":"article","venue":"International Conference on Artificial Intelligence","topic":"Handwritten Text Recognition Techniques","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":"New York Institute of Technology","funders":"","keywords":"Handwriting; Computer science; Artificial intelligence; Arabic; Gaussian; Pattern recognition (psychology); Speech recognition; Physics; Linguistics","score_opus":0.12022237629839307,"score_gpt":0.34422809891050804,"score_spread":0.224005722612115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W152011799","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":[0.059400417,0.000005228566,0.91266024,0.0025177938,0.0020533807,0.0002299092,0.000015155861,0.0004270718,0.022690823],"genre_scores_gemma":[0.9214683,0.000013321075,0.077299386,0.00056452485,0.0003086029,0.000033700417,0.000007035608,0.000017154909,0.0002879764],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9977038,0.000070803784,0.00056907185,0.0006470617,0.000601257,0.00040800552],"domain_scores_gemma":[0.9984893,0.000113056536,0.00019242987,0.00052406295,0.000507681,0.00017346135],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004899346,0.00025706796,0.00020543055,0.00035845666,0.00024661014,0.0009800972,0.0017383056,0.00014695812,0.0014131594],"category_scores_gemma":[0.0002913236,0.00025924743,0.00011176735,0.00031742232,0.00016139055,0.00096298615,0.00022758805,0.00063656515,0.00050695497],"study_design_candidate":"theoretical_or_conceptual","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":[0.000013948539,0.00008647685,0.00006835589,0.0000041815747,0.0000142113495,0.000022879782,0.00022332543,0.000024172521,0.16258992,0.643945,0.00009225936,0.19291528],"study_design_scores_gemma":[0.000041577325,0.00011337633,0.00009976321,0.00014605199,0.0000052657106,0.000061756065,0.00017630949,0.34498364,0.49311927,0.1595985,0.001215874,0.00043861268],"about_ca_topic_score_codex":0.00018794155,"about_ca_topic_score_gemma":0.00020770138,"teacher_disagreement_score":0.8620679,"about_ca_system_score_codex":0.00008369925,"about_ca_system_score_gemma":0.0001561785,"threshold_uncertainty_score":0.999986},"labels":[],"label_agreement":null},{"id":"W1521608059","doi":"10.1109/icslp.1996.607430","title":"New efficient fillers for unlimited word recognition and keyword spotting","year":2002,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Keyword spotting; Spotting; Computer science; Word (group theory); Speech recognition; Natural language processing; Artificial intelligence; Linguistics","score_opus":0.04747308482185621,"score_gpt":0.24268679119017994,"score_spread":0.19521370636832375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1521608059","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":[0.018032897,0.00008786528,0.97108346,0.0013505339,0.00012404236,0.0004577549,0.000004883791,0.00084787875,0.008010673],"genre_scores_gemma":[0.14481136,0.00007301102,0.8510671,0.0010543517,0.00010442216,0.000066909044,0.000012169581,0.000018479059,0.0027921654],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99894965,0.000029308081,0.00022330463,0.00038188993,0.00014627459,0.00026959067],"domain_scores_gemma":[0.99926716,0.00019574277,0.00007328332,0.00021984048,0.00010160601,0.00014238918],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002125593,0.00013249034,0.00013271926,0.00018334549,0.00012671035,0.00018005806,0.00023662778,0.0000719719,0.0003486395],"category_scores_gemma":[0.00010090869,0.00012459843,0.00005793451,0.00034722715,0.000021454947,0.00023260909,0.00009343553,0.00008046513,0.00012397248],"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":[0.0000030375627,0.000026501371,0.000013850054,0.000010350659,0.00000636193,0.0000017713352,0.00024665205,0.0000027487044,0.00032189806,0.0005236306,0.014074779,0.9847684],"study_design_scores_gemma":[0.0038994267,0.00072725565,0.0009240219,0.0004157296,0.0000554041,0.00016597139,0.0002766144,0.77589065,0.11278536,0.04494023,0.058128163,0.0017911887],"about_ca_topic_score_codex":0.000021789145,"about_ca_topic_score_gemma":0.0000037327754,"teacher_disagreement_score":0.9829772,"about_ca_system_score_codex":0.000028659575,"about_ca_system_score_gemma":0.000011610977,"threshold_uncertainty_score":0.50809765},"labels":[],"label_agreement":null},{"id":"W1522548419","doi":"10.1007/3-540-44590-0_29","title":"Treatment of Diagrams in Document Image Analysis","year":2000,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":26,"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; Document processing; Rule-based machine translation; Optical character recognition; Artificial intelligence; Natural language processing; Syntax; Image processing; Text processing; Graph; Information retrieval; Pattern recognition (psychology); Image (mathematics); Theoretical computer science","score_opus":0.011672702102148384,"score_gpt":0.2589394180748358,"score_spread":0.2472667159726874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1522548419","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":[0.0005142449,0.00034655439,0.9928955,0.00029434453,0.00018715327,0.0004930967,0.000008665421,0.00014412095,0.005116311],"genre_scores_gemma":[0.356645,0.0008672572,0.6416568,0.0002917228,0.00013565559,0.000055951918,0.000019633751,0.000031575026,0.00029637458],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9964723,0.000054823784,0.00076772476,0.0013661084,0.0008051842,0.00053384603],"domain_scores_gemma":[0.99769473,0.00031692136,0.0002983458,0.0014065433,0.00015189344,0.00013157357],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00043251234,0.00050063134,0.00091809034,0.0026236766,0.0000699193,0.00028564068,0.0019999458,0.00025578795,0.00012575871],"category_scores_gemma":[0.00001951842,0.000433852,0.00033258912,0.0019144015,0.0005267325,0.0005213321,0.00036625325,0.00028621708,0.00003390435],"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":[0.0000049142936,0.00009910152,0.00019842012,0.000012246679,0.000048402144,0.00012540055,0.0006299096,0.0016783846,0.00008675593,0.0026318314,0.0000020424372,0.9944826],"study_design_scores_gemma":[0.0012930337,0.0018074078,0.001834205,0.00056827214,0.00019469562,0.00007697117,4.0948674e-7,0.24623407,0.050612587,0.6934118,0.0020298965,0.0019366257],"about_ca_topic_score_codex":0.00019517273,"about_ca_topic_score_gemma":0.00043298388,"teacher_disagreement_score":0.99254596,"about_ca_system_score_codex":0.0005721185,"about_ca_system_score_gemma":0.00028435345,"threshold_uncertainty_score":0.99981135},"labels":[],"label_agreement":null},{"id":"W1530576903","doi":"","title":"Fusing High- and Low-Level Features for Handwritten Word Recognition","year":2006,"lang":"en","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"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; Classifier (UML); Artificial intelligence; Pattern recognition (psychology); Word error rate; Word recognition; Hidden Markov model; Intelligent word recognition; Speech recognition; Segmentation; Lexicon; Handwriting recognition; Feature extraction; Word (group theory); Natural language processing; Character recognition; Intelligent character recognition; Mathematics; Image (mathematics)","score_opus":0.014740352480028052,"score_gpt":0.22042889612328068,"score_spread":0.20568854364325262,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1530576903","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":[0.07910541,0.00033792082,0.90490705,0.0070854435,0.000101807826,0.00048412196,0.000056665383,0.0005821534,0.007339456],"genre_scores_gemma":[0.52706915,0.00010290858,0.4695888,0.00021479833,0.000039719875,0.00011630187,0.00022269967,0.000026301992,0.0026193215],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99737227,0.0010339007,0.00036328592,0.0006159776,0.00026579117,0.0003487569],"domain_scores_gemma":[0.9963532,0.0010737223,0.0002317629,0.0008091792,0.0014190313,0.000113067756],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024412603,0.00022048893,0.00023008892,0.00021669766,0.00047125737,0.0006796319,0.0006789746,0.00015038025,0.000026028707],"category_scores_gemma":[0.00049230043,0.00023314555,0.000099618075,0.00042452736,0.00014545814,0.0005651212,0.00030861786,0.00018611336,0.00001870289],"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":[0.000010588182,0.00028423674,0.0002105783,0.000074314856,0.000019708787,0.0000034534035,0.0010122557,0.0000011084505,0.016560687,0.08120751,0.004175909,0.8964397],"study_design_scores_gemma":[0.0017460665,0.0000024708222,0.01617712,0.0013106954,0.000038749527,0.000073607946,0.00006195387,0.008236681,0.7700295,0.19351052,0.007971368,0.0008412634],"about_ca_topic_score_codex":0.00078694546,"about_ca_topic_score_gemma":0.00086304493,"teacher_disagreement_score":0.8955984,"about_ca_system_score_codex":0.000054398533,"about_ca_system_score_gemma":0.00007326388,"threshold_uncertainty_score":0.95074},"labels":[],"label_agreement":null},{"id":"W1536864280","doi":"10.1142/4648","title":"Hidden Markov Models","year":2001,"lang":"en","type":"book","venue":"Series in machine perception and artificial intelligence","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":79,"is_retracted":false,"has_abstract":true,"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; Hidden Markov model; Markov chain; Artificial intelligence; Machine learning","score_opus":0.03608557462599119,"score_gpt":0.2853434635284394,"score_spread":0.24925788890244824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1536864280","genre_codex":"methods","genre_gemma":"other","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":[0.0001380896,0.00024774222,0.7627964,0.0011688973,0.0003459714,0.00044542152,0.000028647755,0.00048673106,0.23434208],"genre_scores_gemma":[0.054197676,0.017530631,0.21379288,0.002195107,0.0010977533,0.00028298967,0.00036429195,0.00019048603,0.7103482],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99776256,0.000108331915,0.00067857554,0.0007654975,0.0003370392,0.00034798495],"domain_scores_gemma":[0.99899435,0.0000634578,0.0001636887,0.0005379066,0.00011890718,0.000121676814],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00043535704,0.00039809057,0.0004175931,0.00045736734,0.00014811639,0.00033460226,0.0007616644,0.00036152624,0.0007105509],"category_scores_gemma":[0.00003464284,0.00040803352,0.000105441664,0.00025649832,0.00027489342,0.0009829006,0.00041558238,0.0006411669,0.00021254265],"study_design_candidate":"theoretical_or_conceptual","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":[0.000019275387,0.000041460236,0.0000060387474,0.00003836121,0.0000064584747,0.000035234898,0.0010250395,0.000008937173,0.00013693584,0.1147495,0.0014693788,0.8824634],"study_design_scores_gemma":[0.000023085795,0.00014987956,0.000047518515,0.00022776723,0.000008927856,0.000105063365,0.00019626746,0.041394994,0.00029235103,0.94520414,0.011727573,0.0006224032],"about_ca_topic_score_codex":0.00007441139,"about_ca_topic_score_gemma":0.000343181,"teacher_disagreement_score":0.881841,"about_ca_system_score_codex":0.00016029495,"about_ca_system_score_gemma":0.000119149765,"threshold_uncertainty_score":0.99983716},"labels":[],"label_agreement":null},{"id":"W1536946665","doi":"10.1007/978-1-4471-4072-6_19","title":"A Robust Word Spotting System for Historical Arabic Manuscripts","year":2012,"lang":"en","type":"book-chapter","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":8,"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":"Spotting; Scripting language; Computer science; Word (group theory); Arabic; Artificial intelligence; Natural language processing; Representation (politics); Pattern recognition (psychology); Programming language; Linguistics","score_opus":0.06988390107918034,"score_gpt":0.23251826562804437,"score_spread":0.16263436454886404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1536946665","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[8.519996e-7,0.0007849211,0.6051347,0.00019313411,0.00095050805,0.0006007549,0.0000066465077,0.0015262909,0.39080217],"genre_scores_gemma":[0.0013060597,0.0000425793,0.32038686,0.00024424598,0.0008558374,0.00020168503,0.000020151063,0.00008856736,0.676854],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99763215,0.000023621395,0.00064531434,0.00075297174,0.00042238933,0.00052356115],"domain_scores_gemma":[0.9980825,0.00016054265,0.00037435695,0.0008639208,0.0002835346,0.00023511451],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005744284,0.00046622977,0.0006297657,0.00037602428,0.00018045124,0.00017937194,0.0010983797,0.0005287649,0.00013077597],"category_scores_gemma":[0.000027491735,0.00043474734,0.00037555848,0.00005611794,0.000031574324,0.00043584415,0.0003164207,0.00038126603,0.00041977435],"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":[0.000005221626,0.000019747222,0.0000020578807,0.00027445282,0.000039664377,0.000021031246,0.000046005825,2.3827577e-7,0.000023661261,0.6173712,0.040999964,0.34119675],"study_design_scores_gemma":[0.000278176,0.00010923396,0.000006025576,0.00079147087,0.000074983414,0.00017998485,0.0000063540456,0.0009500887,0.000725219,0.015637489,0.98024035,0.0010006576],"about_ca_topic_score_codex":0.000024523657,"about_ca_topic_score_gemma":0.00000780825,"teacher_disagreement_score":0.93924034,"about_ca_system_score_codex":0.0014099367,"about_ca_system_score_gemma":0.00008900288,"threshold_uncertainty_score":0.99981046},"labels":[],"label_agreement":null},{"id":"W1539681359","doi":"10.1007/3-540-44596-x_19","title":"Local Learning Framework for Recognition of Lowercase Handwritten Characters","year":2001,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":9,"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":"Computer science; Classifier (UML); Artificial intelligence; Artificial neural network; Learning vector quantization; Machine learning; Pattern recognition (psychology)","score_opus":0.023460606819466056,"score_gpt":0.26572467373689024,"score_spread":0.2422640669174242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1539681359","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":[0.00013770061,0.00016508077,0.9960301,0.00044919865,0.0008246527,0.00077288516,0.000016690996,0.0003510953,0.0012526284],"genre_scores_gemma":[0.1096106,0.0001901647,0.8883453,0.0010699676,0.0004194376,0.00006389389,0.00004293402,0.00006653556,0.0001911835],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9961797,0.00005457095,0.00079221744,0.0014516555,0.0008261295,0.00069570175],"domain_scores_gemma":[0.9964108,0.0012023152,0.0006129694,0.0009110157,0.0006722693,0.00019064883],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012266297,0.0005490035,0.0007352893,0.0012386575,0.00024274795,0.0003184998,0.0020887812,0.00064828177,0.000051633906],"category_scores_gemma":[0.00036077652,0.00055419037,0.00027291445,0.00071047555,0.0008245796,0.0007316681,0.00062192616,0.0011863722,0.000039231352],"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":[0.000018222303,0.000038837225,0.000011399662,0.00008146557,0.00001321051,0.000046851914,0.00031259816,0.00046244703,0.00016832472,0.007276599,0.000012208819,0.99155784],"study_design_scores_gemma":[0.00044825271,0.00081279257,0.0000325645,0.002323626,0.000025396776,0.0001680316,8.9397014e-7,0.11676251,0.028103892,0.8482417,0.0020508796,0.0010294733],"about_ca_topic_score_codex":0.000016852966,"about_ca_topic_score_gemma":0.000016201406,"teacher_disagreement_score":0.99052835,"about_ca_system_score_codex":0.00027082098,"about_ca_system_score_gemma":0.00035654736,"threshold_uncertainty_score":0.99969095},"labels":[],"label_agreement":null},{"id":"W1540846082","doi":"","title":"LR-upward drawing of ordered sets","year":2009,"lang":"en","type":"article","venue":"Machine Graphics & Vision International Journal archive","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Java; Decomposition; Set (abstract data type); Chain (unit); Order (exchange); Engineering drawing; Line (geometry); Flow (mathematics); Computer graphics (images); Programming language; Geometry; Mathematics; Engineering; Physics","score_opus":0.010006136910987538,"score_gpt":0.30033860858172695,"score_spread":0.2903324716707394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1540846082","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":[0.032013822,0.00012828257,0.9563813,0.0069421497,0.0006610413,0.00013449657,0.000038494858,0.00014443476,0.0035559416],"genre_scores_gemma":[0.894454,0.0003508689,0.10361558,0.0013957621,0.00012308317,0.0000028031134,0.000018655706,0.00001042866,0.000028837916],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976434,0.00017217838,0.00064067374,0.00029555155,0.0010090232,0.00023917815],"domain_scores_gemma":[0.99835134,0.00018555808,0.0004303568,0.000277634,0.0005859696,0.00016915161],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064672984,0.0001931767,0.00023689146,0.00097368937,0.00017529972,0.00029681777,0.0017928445,0.00005788072,0.00006692648],"category_scores_gemma":[0.00015861861,0.00016693123,0.00027123606,0.00036996065,0.00007794774,0.0005306596,0.0002694709,0.00059036305,0.000015546508],"study_design_candidate":"theoretical_or_conceptual","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":[0.00012880433,0.00055287324,0.0020913251,0.000009457716,0.00019292215,0.00028606504,0.0015406726,0.000063355415,0.019004267,0.17777051,0.0043856953,0.79397404],"study_design_scores_gemma":[0.0011706826,0.00076435466,0.023372307,0.00033184767,0.0000152716,0.0010788996,0.000021272688,0.038947448,0.008817082,0.9184236,0.0066838786,0.00037337467],"about_ca_topic_score_codex":0.000028687964,"about_ca_topic_score_gemma":0.000008679284,"teacher_disagreement_score":0.86244017,"about_ca_system_score_codex":0.00003662052,"about_ca_system_score_gemma":0.000078008365,"threshold_uncertainty_score":0.6807258},"labels":[],"label_agreement":null},{"id":"W1544414728","doi":"10.1109/iscas.2006.1693582","title":"A binarization method for scanned documents based on hidden Markov model","year":2006,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Shadow (psychology); Hidden Markov model; Artificial intelligence; Noise (video); Contrast (vision); Pattern recognition (psychology); Set (abstract data type); Image (mathematics); Markov process; Process (computing); Computer vision; Variable (mathematics); Markov chain; Algorithm; Machine learning; Mathematics; Statistics","score_opus":0.01349076468461433,"score_gpt":0.2869222883177574,"score_spread":0.27343152363314305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1544414728","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":[0.00017993907,0.000002897379,0.9845018,0.0013493123,0.000048546048,0.0005068032,0.0000064514,0.00064462976,0.012759668],"genre_scores_gemma":[0.1003943,6.075331e-7,0.8959104,0.0013877813,0.000026840864,0.00019748644,0.000024467474,0.000012246231,0.0020458624],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989252,0.000060225568,0.00020596062,0.00036262893,0.00023144689,0.00021452692],"domain_scores_gemma":[0.9993116,0.00009231363,0.000070724374,0.00034620683,0.00013335794,0.000045766203],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038088526,0.00012497079,0.000121126366,0.0002140244,0.000096659474,0.0001607735,0.00039552807,0.000070947994,0.00002888522],"category_scores_gemma":[0.000028476863,0.00011276704,0.00007328888,0.00027352662,0.000010094636,0.00036108194,0.00005291349,0.000046111425,0.000020103336],"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":[0.00007790856,0.000528172,0.00013587093,0.000058637117,0.000015534404,0.000004081218,0.00007364614,0.0034325358,0.009633235,0.13937077,0.04381656,0.80285305],"study_design_scores_gemma":[0.00044215666,0.000112503556,0.000038946066,0.000019066018,0.00000414713,8.246979e-7,0.0000011398058,0.8887678,0.04171395,0.06836877,0.00039077294,0.00013993701],"about_ca_topic_score_codex":0.000050611514,"about_ca_topic_score_gemma":0.000008595661,"teacher_disagreement_score":0.88533527,"about_ca_system_score_codex":0.0000617628,"about_ca_system_score_gemma":0.00005918643,"threshold_uncertainty_score":0.45985064},"labels":[],"label_agreement":null},{"id":"W1550006144","doi":"10.1109/nafips.2001.944303","title":"Injection of human knowledge into the rejection criterion of a neural network classifier","year":2002,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Numeral system; Computer science; Artificial neural network; Classifier (UML); Artificial intelligence; Pattern recognition (psychology); Machine learning; Data mining","score_opus":0.0362982887275483,"score_gpt":0.28484202929573915,"score_spread":0.24854374056819084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1550006144","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":[0.292409,0.0004786835,0.62621623,0.00089514715,0.0008371253,0.000559542,6.332826e-7,0.0007122096,0.07789146],"genre_scores_gemma":[0.9934627,0.000022110731,0.005522722,0.00008144482,0.00010150322,0.000019630128,7.8176737e-7,0.0000059385848,0.0007832143],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999085,0.00014951723,0.00031172883,0.0001848809,0.00013961634,0.00012927683],"domain_scores_gemma":[0.9992303,0.00006180086,0.00014270595,0.00035450605,0.00018497469,0.000025684027],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031748344,0.00008629852,0.00013234605,0.00011131645,0.00013327807,0.000036203994,0.00034832294,0.00006821513,0.00012651592],"category_scores_gemma":[0.000021988944,0.00006210344,0.000077191755,0.0005909724,0.00008331149,0.00033650754,0.000125597,0.00011809286,0.0000136772205],"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":[0.000009428168,0.0003200368,0.0013192061,0.00007722442,0.000030118632,0.0000011927665,0.0068868957,0.000047809663,0.035852127,0.040371723,0.034815375,0.8802689],"study_design_scores_gemma":[0.0009360885,0.0033256419,0.015426788,0.00032047599,0.00004969362,0.00012732708,0.0003836161,0.6074827,0.29937705,0.062269505,0.00958024,0.0007208889],"about_ca_topic_score_codex":0.00013321925,"about_ca_topic_score_gemma":0.00010570765,"teacher_disagreement_score":0.87954795,"about_ca_system_score_codex":0.000027631857,"about_ca_system_score_gemma":0.0000068706877,"threshold_uncertainty_score":0.2532505},"labels":[],"label_agreement":null},{"id":"W1557952530","doi":"10.48550/arxiv.1310.1811","title":"End-to-End Text Recognition with Hybrid HMM Maxout Models","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":100,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Hidden Markov model; Benchmark (surveying); Computer science; Speech recognition; Artificial intelligence; Pattern recognition (psychology); End-to-end principle; Character (mathematics); Word (group theory); Character recognition; Text recognition; Machine learning; Mathematics","score_opus":0.07374208121636969,"score_gpt":0.18628781125673685,"score_spread":0.11254573004036716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1557952530","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":[0.13754645,0.000018328823,0.8465027,0.0002637939,0.00022554978,0.0009453113,0.00008266193,0.0011443121,0.013270845],"genre_scores_gemma":[0.9551993,0.00013339707,0.041704208,0.00048496854,0.000083980616,0.00002422894,0.00009962838,0.00005117616,0.00221911],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99674857,0.00020664615,0.0003264408,0.0018602161,0.00024463012,0.00061349163],"domain_scores_gemma":[0.9968281,0.0001147814,0.00034320896,0.0016596556,0.00061816594,0.00043608868],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00031121538,0.0005727515,0.0005207307,0.00077152037,0.00019709885,0.00040333506,0.0022195028,0.00030946502,0.00040622492],"category_scores_gemma":[0.000024998428,0.000613184,0.00022389638,0.00073087186,0.00014738493,0.0014021961,0.0020207262,0.0008417496,0.0012859699],"study_design_candidate":"theoretical_or_conceptual","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":[0.00047516808,0.001744982,0.0010434985,0.0009778779,0.0013766449,0.0051021436,0.002449437,0.1062821,0.00085867825,0.32621858,0.02772185,0.525749],"study_design_scores_gemma":[0.00096472725,0.0004321674,0.0002207696,0.0006888243,0.0001814119,0.000107559594,0.00009045973,0.42823878,0.010493139,0.55450267,0.0019189824,0.0021604814],"about_ca_topic_score_codex":0.00042132102,"about_ca_topic_score_gemma":0.000059654063,"teacher_disagreement_score":0.8176529,"about_ca_system_score_codex":0.000327007,"about_ca_system_score_gemma":0.00028223605,"threshold_uncertainty_score":0.99963194},"labels":[],"label_agreement":null},{"id":"W1568762422","doi":"10.1109/ccece.1993.332249","title":"Intelligent OCR editor","year":2002,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Global Affairs Canada","funders":"","keywords":"Computer science; Word error rate; Optical character recognition; Error detection and correction; Artificial intelligence; Throughput; Automation; Expert system; Artificial neural network; Speech recognition; Premise; Pattern recognition (psychology); Algorithm; Engineering; Telecommunications","score_opus":0.025353752115742607,"score_gpt":0.24859226331337164,"score_spread":0.22323851119762902,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1568762422","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":[0.00012229086,0.00007155647,0.915015,0.0013726492,0.001176311,0.00007837136,3.4535827e-7,0.0009653994,0.08119809],"genre_scores_gemma":[0.36328086,0.00037496304,0.60294384,0.0045877798,0.003756692,0.000079839236,0.0000015744531,0.000020076497,0.024954394],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99937344,0.00001833001,0.000118647,0.00018565998,0.00015765357,0.00014628914],"domain_scores_gemma":[0.9995137,0.00003358196,0.00002178604,0.0003073585,0.00005565309,0.000067906774],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00008365297,0.00006531594,0.00006285455,0.00007104292,0.000039956452,0.00009649694,0.00048665606,0.000036484023,0.0017665395],"category_scores_gemma":[0.000022091723,0.00005499141,0.000039003127,0.00017813545,0.000017279388,0.00028917188,0.000119677046,0.00006645593,0.0026990406],"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":[1.2715604e-7,0.000047732672,0.000020527177,0.0000019942777,0.000002891495,0.000004349224,0.000114986455,1.0651582e-7,0.00016840977,0.01038934,0.48057234,0.5086772],"study_design_scores_gemma":[0.00007881046,0.0000938408,0.000034461824,0.000011668158,0.0000015933737,0.000020345436,0.000009543919,0.022271363,0.12980562,0.010811912,0.8366399,0.00022096703],"about_ca_topic_score_codex":0.0000063698044,"about_ca_topic_score_gemma":0.0000015535136,"teacher_disagreement_score":0.50845623,"about_ca_system_score_codex":0.000015740017,"about_ca_system_score_gemma":0.0000032445978,"threshold_uncertainty_score":0.999146},"labels":[],"label_agreement":null},{"id":"W1569245971","doi":"10.1109/tip.2015.2442923","title":"Influence of Color-to-Gray Conversion on the Performance of Document Image Binarization: Toward a Novel Optimization Problem","year":2015,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; McGill University","funders":"","keywords":"Artificial intelligence; Computer science; Pixel; Preprocessor; Pattern recognition (psychology); Computer vision; Contrast (vision); Historical document","score_opus":0.018611814523702544,"score_gpt":0.2554577894300295,"score_spread":0.23684597490632697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1569245971","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":[0.108608335,0.000008234275,0.8896744,0.00079494773,0.000047333015,0.0004983876,0.0000061967958,0.00015142818,0.00021069853],"genre_scores_gemma":[0.7445512,0.000014265532,0.2551074,0.00019653264,0.0000058822534,0.00008356169,9.965628e-7,0.000011122385,0.000029080698],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985467,0.00005789696,0.00040587,0.0003117921,0.0004911149,0.00018663214],"domain_scores_gemma":[0.9982678,0.000058845246,0.0002651868,0.00031435126,0.0010023026,0.00009146041],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046906967,0.00016898019,0.00018775351,0.0002840232,0.00017605862,0.00013569053,0.0005135501,0.000064094085,0.000010437476],"category_scores_gemma":[0.00002654443,0.00013420338,0.000050742554,0.0010236462,0.00013750023,0.001474869,0.0000099132485,0.00017235301,0.000015773729],"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":[0.00022207518,0.0007442157,0.000026706086,0.00061512715,0.000030761857,0.0000024727178,0.00636433,0.76558244,0.19199301,0.00021036668,0.000096304415,0.03411219],"study_design_scores_gemma":[0.00039593203,0.00057138567,0.000025238423,0.000496179,0.000014843002,0.000007692162,0.000094328134,0.24200442,0.7561349,0.00008198002,0.000025322053,0.00014772471],"about_ca_topic_score_codex":0.000017258037,"about_ca_topic_score_gemma":6.5534016e-7,"teacher_disagreement_score":0.6359428,"about_ca_system_score_codex":0.000099688594,"about_ca_system_score_gemma":0.0002241889,"threshold_uncertainty_score":0.5472655},"labels":[],"label_agreement":null},{"id":"W157034376","doi":"10.1007/978-1-4471-4072-6_11","title":"Handwritten Farsi Word Recognition Using Hidden Markov Models","year":2012,"lang":"en","type":"book-chapter","venue":"","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":"Concordia University","funders":"","keywords":"Hidden Markov model; Computer science; Artificial intelligence; Natural language processing; Word (group theory); Persian; Speech recognition; Arabic; Word recognition; Alphabet; Pattern recognition (psychology); Linguistics; Reading (process)","score_opus":0.06494784647678918,"score_gpt":0.25799545980839456,"score_spread":0.19304761333160536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W157034376","genre_codex":"other","genre_gemma":"methods","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":[0.000015631013,0.00059584633,0.4764995,0.00013857576,0.00030449108,0.00047629687,0.000035218556,0.0010895245,0.52084494],"genre_scores_gemma":[0.0014656064,0.0010605991,0.699661,0.0011980658,0.0007629657,0.00006290583,0.00018114751,0.00018755859,0.29542014],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9968493,0.0000621212,0.0007369404,0.0009700977,0.0007078995,0.00067364407],"domain_scores_gemma":[0.9975654,0.000112823705,0.0004370852,0.0011178892,0.0004469397,0.00031989647],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005328869,0.0006996235,0.00067171647,0.0006840761,0.00020676933,0.00039679493,0.0012391536,0.0008529799,0.002043342],"category_scores_gemma":[0.0000149085445,0.0007053999,0.00037481522,0.0001202801,0.00011057239,0.0019460326,0.0007118721,0.0005875116,0.0009391277],"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":[0.0000064769724,0.000028476312,8.4879366e-7,0.000041998737,0.000069744776,0.000023298899,0.00008199394,3.0982994e-7,0.00008615609,0.031365804,0.004877915,0.963417],"study_design_scores_gemma":[0.00049696467,0.000105221974,0.0000034872132,0.0010398998,0.00019833971,0.0003482597,0.000010943584,0.013531548,0.0031197718,0.9178769,0.060967203,0.002301453],"about_ca_topic_score_codex":0.000048011814,"about_ca_topic_score_gemma":0.000019408071,"teacher_disagreement_score":0.96111554,"about_ca_system_score_codex":0.00026180304,"about_ca_system_score_gemma":0.0001496943,"threshold_uncertainty_score":0.99983877},"labels":[],"label_agreement":null},{"id":"W1577720392","doi":"10.1007/978-3-540-27868-9_109","title":"Recognition of Handwritten Numerals Using a Combined Classifier with Hybrid Features","year":2004,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":15,"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":"Numeral system; Pattern recognition (psychology); Computer science; Classifier (UML); Artificial intelligence; Artificial neural network; Feature extraction; Speech recognition","score_opus":0.024374849944460066,"score_gpt":0.25110632167619323,"score_spread":0.22673147173173316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1577720392","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":[0.000947122,0.0001952448,0.9944822,0.00042302304,0.00044620497,0.0007360524,0.000025432671,0.0003077389,0.0024369524],"genre_scores_gemma":[0.23622647,0.000051689352,0.7623238,0.00094596896,0.00020377718,0.000020115724,0.000024503832,0.000063031024,0.00014064921],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99581754,0.00005886797,0.0007314955,0.0015097646,0.0012198796,0.0006624767],"domain_scores_gemma":[0.9969294,0.00027533565,0.00065335975,0.0012147092,0.0007386473,0.000188542],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007239973,0.00066614256,0.00085426384,0.0013384356,0.00022613825,0.0004419873,0.0022280724,0.00034617507,0.00005523603],"category_scores_gemma":[0.00006742967,0.0005717231,0.00017916349,0.0007708553,0.0010154201,0.0009456958,0.00067976426,0.00091064157,0.000017274007],"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":[0.00006635401,0.0001405999,0.000053607655,0.00019481641,0.00006307455,0.00030204887,0.0005561787,0.002547955,0.0025698817,0.009386712,0.000043248467,0.98407555],"study_design_scores_gemma":[0.0013765425,0.0011562428,0.00013182186,0.0043042256,0.00005364308,0.0006889515,4.4428072e-7,0.040906638,0.17865898,0.77103966,0.00012775,0.0015551185],"about_ca_topic_score_codex":0.0000956369,"about_ca_topic_score_gemma":0.00006744659,"teacher_disagreement_score":0.9825204,"about_ca_system_score_codex":0.00041665678,"about_ca_system_score_gemma":0.0010864598,"threshold_uncertainty_score":0.9996734},"labels":[],"label_agreement":null},{"id":"W1586903287","doi":"10.1007/978-3-642-12127-2_27","title":"A Multi-Classifier System for Off-Line Signature Verification Based on Dissimilarity Representation","year":2010,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":10,"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; Classifier (UML); Artificial intelligence; Pattern recognition (psychology); Signature (topology); Representation (politics); Data mining; Machine learning; Mathematics","score_opus":0.037513046173295254,"score_gpt":0.2953351542035944,"score_spread":0.25782210803029915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1586903287","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":[0.000023262935,0.00007178088,0.9943635,0.0010173226,0.0016214619,0.0014838242,0.000048392732,0.00061038206,0.0007600984],"genre_scores_gemma":[0.120569825,0.0000109372195,0.8773703,0.0011280068,0.00042516628,0.0001458397,0.00008428133,0.000049184986,0.00021647263],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.995942,0.00006622064,0.0006241635,0.0019085737,0.00095253764,0.0005064818],"domain_scores_gemma":[0.99605477,0.0007560693,0.00049493887,0.0018482317,0.0006667122,0.00017929505],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011583911,0.00054327206,0.0005288213,0.0009513597,0.00037409368,0.0005809167,0.0023858326,0.0008348431,0.0000136187955],"category_scores_gemma":[0.00030031876,0.00049678347,0.00021593015,0.0005611807,0.00040480975,0.00053527986,0.00031046668,0.0012730713,0.000019205014],"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":[0.000045276174,0.00014516995,0.000019332148,0.00019804332,0.000011634418,0.000033210075,0.00023872935,0.004754583,0.009999651,0.006055773,0.00005927362,0.97843933],"study_design_scores_gemma":[0.00054377946,0.00024147469,0.000110898516,0.00059030065,0.000012672577,0.000014729543,2.0246698e-7,0.9032984,0.0810926,0.012281904,0.0012489151,0.00056412444],"about_ca_topic_score_codex":0.000008680763,"about_ca_topic_score_gemma":0.00004740826,"teacher_disagreement_score":0.9778752,"about_ca_system_score_codex":0.0003806286,"about_ca_system_score_gemma":0.00047208185,"threshold_uncertainty_score":0.9997484},"labels":[],"label_agreement":null},{"id":"W1587454593","doi":"","title":"OWNERSHIP, ERPS AND THE SELF-REFERENTIAL ENCODING EFFECT","year":2013,"lang":"en","type":"article","venue":"Bristol Research (University of Bristol)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Dalhousie University","funders":"","keywords":"Object (grammar); Psychology; Fixation (population genetics); Cognitive psychology; sort; Social psychology; Communication; Artificial intelligence; Computer science; Mathematics; Arithmetic","score_opus":0.026004475420101415,"score_gpt":0.2635593854173355,"score_spread":0.23755490999723405,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1587454593","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":[0.7646658,0.00087409373,0.16493723,0.013231958,0.00021958293,0.0033038938,0.000013416738,0.0010759026,0.051678155],"genre_scores_gemma":[0.9892605,0.00023689652,0.008774692,0.000033293476,0.000028789118,0.000005972656,0.0000028000889,0.000009339238,0.0016477075],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99716854,0.00094949023,0.0001534422,0.00045253267,0.0008356135,0.0004404091],"domain_scores_gemma":[0.9973498,0.0011861871,0.00011862065,0.0006109895,0.00053868274,0.00019571377],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026198865,0.00013760474,0.00030003232,0.00037532096,0.0006712596,0.00022368964,0.0016818546,0.00012506418,0.00017103534],"category_scores_gemma":[0.00028706106,0.00011859662,0.00012310156,0.00065531017,0.0008646301,0.0009476009,0.0010914687,0.0005687208,0.00021805169],"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":[0.0003669703,0.0003848172,0.0022236481,0.00055950735,0.0003313265,0.00018748775,0.008577372,0.0000011706975,0.0062988424,0.08461165,0.16135433,0.7351029],"study_design_scores_gemma":[0.05214451,0.008424368,0.08169438,0.0024460435,0.0006377703,0.001162427,0.021293653,0.16535181,0.06892781,0.27783328,0.31367406,0.006409872],"about_ca_topic_score_codex":0.0041478444,"about_ca_topic_score_gemma":0.0001845828,"teacher_disagreement_score":0.728693,"about_ca_system_score_codex":0.00012803516,"about_ca_system_score_gemma":0.00014885183,"threshold_uncertainty_score":0.62703276},"labels":[],"label_agreement":null},{"id":"W1595054451","doi":"10.1007/978-3-642-04146-4_58","title":"A New Large Urdu Database for Off-Line Handwriting Recognition","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":60,"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":"Urdu; Computer science; Handwriting; Numeral system; Artificial intelligence; Handwriting recognition; Pattern recognition (psychology); Character recognition; Arabic; Speech recognition; Feature extraction; Natural language processing; Image (mathematics); Linguistics","score_opus":0.03112518242818602,"score_gpt":0.2809702338494022,"score_spread":0.24984505142121616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1595054451","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":[0.000010574019,0.00079418276,0.99299026,0.0011019729,0.0007551509,0.0011217365,0.000107657586,0.0006647357,0.002453741],"genre_scores_gemma":[0.00222835,0.00021379263,0.9914547,0.003705586,0.0012692285,0.000038322323,0.00016783788,0.00005437575,0.0008677855],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9952215,0.000041985888,0.0008139349,0.0019931833,0.0009283641,0.0010010217],"domain_scores_gemma":[0.9966279,0.0006508995,0.00045000843,0.0013627673,0.0005739967,0.00033440327],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0016868698,0.0006702981,0.0006835268,0.0012102755,0.00039119102,0.00082791207,0.0028175698,0.0004401947,0.000073001385],"category_scores_gemma":[0.00034025635,0.00067781855,0.00024153943,0.000680783,0.00019621855,0.0013298804,0.00092156563,0.0008517061,0.000076950244],"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":[0.000009618264,0.000035862275,0.0000015353816,0.000043083422,0.0000071751665,0.00004061727,0.00013748827,0.000052928142,0.00027239195,0.0036183884,0.00034442087,0.9954365],"study_design_scores_gemma":[0.0014610338,0.0008282752,0.000011997566,0.00243559,0.00003500089,0.00021666715,2.9908804e-7,0.26264986,0.033318434,0.6727286,0.02459963,0.0017146099],"about_ca_topic_score_codex":0.0000178759,"about_ca_topic_score_gemma":0.000118335105,"teacher_disagreement_score":0.9937219,"about_ca_system_score_codex":0.00026713396,"about_ca_system_score_gemma":0.00081282406,"threshold_uncertainty_score":0.99956733},"labels":[],"label_agreement":null},{"id":"W1598903884","doi":"10.1007/978-3-642-03767-2_20","title":"A New Approach for Segmentation and Recognition of Arabic Handwritten Touching Numeral Pairs","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":16,"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":"Numeral system; Computer science; Artificial intelligence; Pattern recognition (psychology); Arabic numerals; Segmentation; Speech recognition; Set (abstract data type); Image segmentation; Arabic; Connected component; Linguistics","score_opus":0.024528157741548356,"score_gpt":0.2580449394556602,"score_spread":0.23351678171411186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1598903884","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":[0.000087219836,0.00020321282,0.99658746,0.00027095608,0.00020826828,0.0009444466,0.000010655951,0.00017766184,0.0015101234],"genre_scores_gemma":[0.010675143,0.00006410263,0.9881151,0.00061570725,0.00022549658,0.000026733987,0.000037100934,0.000022212656,0.0002184502],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99729645,0.000037470654,0.0005577804,0.0011644727,0.0005500766,0.00039376863],"domain_scores_gemma":[0.99836457,0.0003002603,0.00038211784,0.00053396117,0.0002722676,0.00014680138],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00084618316,0.00038728665,0.0005007511,0.00081517815,0.00015940581,0.00035323342,0.001030407,0.0002812799,0.000011715827],"category_scores_gemma":[0.00007901237,0.0003767488,0.00012492077,0.0003639008,0.00022276244,0.00084240595,0.000285779,0.0003794292,0.0000034172829],"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":[0.000009450496,0.00001995955,0.000007287666,0.00006722329,0.000007954898,0.0000027275644,0.0005296312,0.00021771858,0.00064588303,0.00085505715,0.00004461316,0.9975925],"study_design_scores_gemma":[0.00094147125,0.00065755856,0.00007884522,0.0007960034,0.00003298182,0.000113951464,0.0000010070306,0.26545516,0.037547905,0.69327223,0.00020112991,0.0009017274],"about_ca_topic_score_codex":0.000034660527,"about_ca_topic_score_gemma":0.000013666078,"teacher_disagreement_score":0.99669075,"about_ca_system_score_codex":0.00013964127,"about_ca_system_score_gemma":0.00029353428,"threshold_uncertainty_score":0.99986845},"labels":[],"label_agreement":null},{"id":"W1599524329","doi":"","title":"Directions in recognizing tabular structures of handwritten mathematics notation","year":2001,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Notation; Representation (politics); Limit (mathematics); Computer science; Mathematical notation; Variety (cybernetics); Function (biology); Algebra over a field; Mathematics; Artificial intelligence; Arithmetic; Pure mathematics","score_opus":0.021261534938920735,"score_gpt":0.26614061239768133,"score_spread":0.24487907745876059,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1599524329","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":[0.10259346,0.00007274945,0.88311833,0.00033105843,0.00008942248,0.0002200358,0.0000014302142,0.0003462937,0.01322721],"genre_scores_gemma":[0.586437,0.00012000872,0.41306734,0.00008654018,0.000018110084,0.000024492605,0.0000028402326,0.000007862653,0.0002358146],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990713,0.00003938156,0.0003460212,0.00020189781,0.00018287775,0.00015853847],"domain_scores_gemma":[0.9993587,0.0001025986,0.0001050255,0.0002716162,0.00012436851,0.000037681373],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025045025,0.000095399795,0.00016549657,0.00031904527,0.000044841046,0.00005422773,0.00030147636,0.000064475906,0.00010055167],"category_scores_gemma":[0.000100032834,0.00008799805,0.00004591214,0.0006935378,0.00002733039,0.0004190809,0.00006946479,0.0000944614,0.000015992664],"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":[0.000008396083,0.00041496434,0.007040637,0.00010305352,0.000036745376,0.00003537975,0.0033645954,0.000036556994,0.027195148,0.08915505,0.0010343714,0.8715751],"study_design_scores_gemma":[0.0010601813,0.00021061425,0.01727386,0.00030072912,0.000021658525,0.00014893206,0.0007867145,0.052287586,0.48148715,0.44153404,0.0041711745,0.0007173561],"about_ca_topic_score_codex":0.00011184193,"about_ca_topic_score_gemma":0.00016823097,"teacher_disagreement_score":0.8708578,"about_ca_system_score_codex":0.000029781548,"about_ca_system_score_gemma":0.000024463967,"threshold_uncertainty_score":0.35884565},"labels":[],"label_agreement":null},{"id":"W1601013115","doi":"10.1007/3-540-44522-6_33","title":"Parallel Techniques for Rule-Based Scene Interpretation","year":2000,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","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":"University of Alberta","funders":"","keywords":"Computer science; Unary operation; Artificial intelligence; Consistency (knowledge bases); Extension (predicate logic); Interpretation (philosophy); Pattern recognition (psychology); Isolation (microbiology); Programming language; Mathematics","score_opus":0.015346595561618465,"score_gpt":0.2624215813510269,"score_spread":0.24707498578940842,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1601013115","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":[0.0000058226187,0.00017697869,0.9922434,0.0009600389,0.00044715387,0.0012572341,0.00002864141,0.0010306741,0.0038500596],"genre_scores_gemma":[0.016649192,0.00005276588,0.9794108,0.0031640546,0.00028195503,0.00016843596,0.000029159337,0.00005315495,0.00019044103],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99622047,0.000042084015,0.00068154634,0.0016308541,0.00076653884,0.0006585295],"domain_scores_gemma":[0.9972777,0.0005643402,0.00032526976,0.0012617998,0.00040883778,0.00016204616],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009236267,0.00060235464,0.0005878924,0.001344975,0.00023910239,0.0005076283,0.0031320641,0.0004808388,0.000051258467],"category_scores_gemma":[0.000086838445,0.0005851834,0.0002484205,0.0004779561,0.0005529169,0.0007319827,0.00039180394,0.00060908747,0.000042094573],"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":[0.00002063538,0.000029603552,0.000002993011,0.00004269789,0.0000058493733,0.0000164193,0.00010337298,0.00089734833,0.00014293854,0.004311169,0.000062053914,0.9943649],"study_design_scores_gemma":[0.00026790117,0.0003421128,0.000008775535,0.00077637966,0.000009443458,0.000029008326,3.2680184e-8,0.45830047,0.030282324,0.50493455,0.004325356,0.0007236241],"about_ca_topic_score_codex":0.0000112447,"about_ca_topic_score_gemma":0.000022925287,"teacher_disagreement_score":0.9936413,"about_ca_system_score_codex":0.00034806214,"about_ca_system_score_gemma":0.0006067645,"threshold_uncertainty_score":0.99965996},"labels":[],"label_agreement":null},{"id":"W1735900717","doi":"10.1109/icpr.1988.28459","title":"Online handwriting recognition-a survey","year":2003,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Handwriting; Computer science; Preprocessor; Handwriting recognition; Code (set theory); Speech recognition; Artificial intelligence; Natural language processing; Pattern recognition (psychology); Feature extraction; Programming language","score_opus":0.05323647362602463,"score_gpt":0.28333014319992517,"score_spread":0.23009366957390054,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1735900717","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":[0.02405502,0.000045324952,0.9244183,0.00018128467,0.00014892631,0.00015585474,0.000022224875,0.0010390776,0.04993402],"genre_scores_gemma":[0.5200834,0.00003900775,0.47742882,0.0013158153,0.000033909015,0.000022561653,0.000061397644,0.000014176773,0.0010008828],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99867916,0.00027062235,0.0002575724,0.00033738874,0.00019131492,0.00026392716],"domain_scores_gemma":[0.99896944,0.00026195642,0.00006090915,0.00034821138,0.00025713092,0.00010236266],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00088475243,0.00012227919,0.00013619482,0.00012813474,0.00011139838,0.00016886026,0.00037638724,0.00006635723,0.00044152234],"category_scores_gemma":[0.0005637879,0.00011599013,0.00005177877,0.0004905758,0.000027329746,0.0004846488,0.00006397808,0.00013106751,0.0003738519],"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":[0.000004327267,0.000812713,0.008930908,0.000025910735,0.000040121,0.000040789757,0.00019966702,7.379526e-7,0.0016107173,0.045943573,0.016208915,0.9261816],"study_design_scores_gemma":[0.002687547,0.000584458,0.049882688,0.0002720565,0.000022169785,0.00056826934,0.00026364188,0.0064683245,0.63523716,0.2507818,0.050306298,0.0029256074],"about_ca_topic_score_codex":0.00008794996,"about_ca_topic_score_gemma":0.00017335829,"teacher_disagreement_score":0.92325604,"about_ca_system_score_codex":0.000022793944,"about_ca_system_score_gemma":0.000058016416,"threshold_uncertainty_score":0.483436},"labels":[],"label_agreement":null},{"id":"W1769047002","doi":"10.5565/rev/elcvia.476","title":"Handwritten Digit Recognition by Fourier-Packet Descriptors","year":2012,"lang":"en","type":"article","venue":"ELCVIA Electronic Letters on Computer Vision and Image Analysis","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Laboratory of Pattern Recognition","keywords":"Pattern recognition (psychology); Computer science; Artificial intelligence; Classifier (UML); Feature extraction; Fourier transform; Speech recognition; Wavelet; Support vector machine; Mathematics","score_opus":0.006371722149941457,"score_gpt":0.2320714452342103,"score_spread":0.22569972308426886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1769047002","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":[0.12026518,0.00031118467,0.87410116,0.004174921,0.00013412084,0.00022497876,0.000013491353,0.0004853829,0.00028955858],"genre_scores_gemma":[0.91604245,0.00035137133,0.0657246,0.017019479,0.00037389563,0.000054831075,0.00022556572,0.00004521654,0.00016260496],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9968467,0.00028413514,0.0004732512,0.00079918327,0.0005496946,0.0010470392],"domain_scores_gemma":[0.99847806,0.00015091707,0.00020822095,0.00070043956,0.00011859844,0.00034374653],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00062722294,0.00042582015,0.0005313337,0.00081743096,0.00030062284,0.00074906915,0.00062114367,0.00012552954,0.00013043582],"category_scores_gemma":[0.000021619086,0.00037845632,0.00035654256,0.0014465345,0.000099110366,0.0020822375,0.00024250604,0.00044553608,0.0002144044],"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":[0.00003591837,0.00047968308,0.00085516874,0.00001856331,0.00093502953,0.000016955159,0.00038170558,0.0000020981297,0.017656637,0.00044413365,0.17325656,0.80591756],"study_design_scores_gemma":[0.0073135514,0.005947499,0.012552901,0.0004314933,0.0036007247,0.0004327204,0.00009307052,0.22756426,0.4522858,0.008595875,0.27317393,0.008008181],"about_ca_topic_score_codex":0.00003258441,"about_ca_topic_score_gemma":0.0000058197925,"teacher_disagreement_score":0.8083766,"about_ca_system_score_codex":0.00018122004,"about_ca_system_score_gemma":0.000028184322,"threshold_uncertainty_score":0.9998667},"labels":[],"label_agreement":null},{"id":"W179605015","doi":"10.1007/978-3-642-37484-5_1","title":"Historical Document Binarization Based on Phase Information of Images","year":2013,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":31,"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; Artificial intelligence; Robustness (evolution); Maxima and minima; Pattern recognition (psychology); Gaussian; Phase congruency; Gaussian filter; Filter (signal processing); Historical document; Binary number; Feature (linguistics); Computer vision; Image (mathematics); Mathematics","score_opus":0.01132746934662753,"score_gpt":0.24698485900489434,"score_spread":0.2356573896582668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W179605015","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":[0.000025183705,0.000052391722,0.9942265,0.0008356293,0.0006700212,0.000535375,0.0000040653126,0.00021437094,0.0034364555],"genre_scores_gemma":[0.17975092,0.00003528368,0.8177987,0.001915646,0.00016575055,0.00005166726,0.000022263157,0.000025586567,0.00023423578],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997286,0.000036467212,0.0006908861,0.0006131587,0.0010555465,0.00031791415],"domain_scores_gemma":[0.9977235,0.00022374337,0.0005251833,0.00091067865,0.0005029923,0.000113908514],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006137789,0.00035022493,0.0004078273,0.0015324085,0.00010901435,0.00034215936,0.0016252171,0.00024812663,0.000058627313],"category_scores_gemma":[0.00012461338,0.00031678798,0.00011049034,0.0005402841,0.00023168504,0.001591144,0.00035512305,0.00041665934,0.000069201844],"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":[0.000006578819,0.00006411465,0.000004743076,0.00005365838,0.0000028986028,0.0000056079234,0.00019908627,0.0030315018,0.00024037733,0.0062578954,0.00018884496,0.9899447],"study_design_scores_gemma":[0.0011855861,0.0018195945,0.00004406015,0.0011020919,0.000013036901,0.000018001716,1.12814234e-7,0.76146984,0.057264943,0.16645809,0.009648231,0.00097640144],"about_ca_topic_score_codex":0.000032467782,"about_ca_topic_score_gemma":0.0000014978378,"teacher_disagreement_score":0.9889683,"about_ca_system_score_codex":0.0008266937,"about_ca_system_score_gemma":0.0003602223,"threshold_uncertainty_score":0.9999284},"labels":[],"label_agreement":null},{"id":"W1799095500","doi":"10.1007/978-3-642-04146-4_16","title":"Integration of Contextual Information in Online Handwriting Representation","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Handwritten Text Recognition Techniques","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":"Concordia University","funders":"","keywords":"Computer science; Cursive; Artificial intelligence; Handwriting recognition; Robustness (evolution); Optimal distinctiveness theory; Pattern recognition (psychology); Intelligent character recognition; Handwriting; Classifier (UML); Representation (politics); Scripting language; Support vector machine; Machine learning; Character recognition; Feature extraction","score_opus":0.023769106847008923,"score_gpt":0.2828602374181504,"score_spread":0.25909113057114147,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1799095500","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":[0.000894667,0.00007346494,0.9953919,0.00039582688,0.0002484974,0.0004588876,0.000009415527,0.00014549239,0.0023818724],"genre_scores_gemma":[0.45483652,0.0000698845,0.5439066,0.00091174035,0.00012801442,0.000009760444,0.00007017714,0.000011445502,0.000055806704],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973422,0.00004737652,0.00096130796,0.00059483416,0.00074342586,0.00031084943],"domain_scores_gemma":[0.9979634,0.00030529615,0.00054908067,0.00063083874,0.0004875589,0.00006380579],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008342253,0.00029969105,0.0004452162,0.0016844135,0.00006979696,0.0002769025,0.0012844724,0.00027493518,0.000010112276],"category_scores_gemma":[0.0003028839,0.00029610752,0.000087152715,0.000778504,0.00026845915,0.002278563,0.00032912934,0.0005961901,0.000009328174],"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":[0.0000052311602,0.000025755482,0.000022754193,0.0000172276,0.0000017660195,0.0000073854108,0.0009389499,0.0011961472,0.0007505826,0.005780967,0.000006306925,0.99124694],"study_design_scores_gemma":[0.000756672,0.00046239595,0.0012348199,0.0021599105,0.0000068164168,0.00006338682,0.0000044268418,0.6728913,0.05301449,0.26835814,0.00030870203,0.0007388869],"about_ca_topic_score_codex":0.0000783044,"about_ca_topic_score_gemma":0.00024168524,"teacher_disagreement_score":0.990508,"about_ca_system_score_codex":0.00024654515,"about_ca_system_score_gemma":0.00026968637,"threshold_uncertainty_score":0.9999491},"labels":[],"label_agreement":null},{"id":"W180164409","doi":"","title":"Reliable Recognition of Handwritten Digits Using A Cascade Ensemble Classifier System and Hybrid Features","year":2006,"lang":"en","type":"dissertation","venue":"Spectrum Research Repository (Concordia University)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Word error rate; Pattern recognition (psychology); Computer science; Artificial intelligence; Classifier (UML); Discriminative model; MNIST database; Cascade; Dimensionality reduction; Feature extraction; Speech recognition; Linear discriminant analysis; Artificial neural network; Machine learning; Engineering","score_opus":0.028246303138315176,"score_gpt":0.2673176914936217,"score_spread":0.23907138835530656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W180164409","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":[0.8336548,0.0005293091,0.005107119,0.000063905885,0.0006521887,0.0010335915,0.00004881526,0.00050674466,0.1584035],"genre_scores_gemma":[0.9690923,0.00018482895,0.0018113219,0.0000046562523,0.00022861808,0.000010225367,0.00018098202,0.00006122555,0.028425854],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9960199,0.00055582414,0.0005041852,0.0011110476,0.0010304565,0.00077858294],"domain_scores_gemma":[0.9973208,0.00025512467,0.00048480116,0.00079190644,0.0008670538,0.00028033246],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006733258,0.00041183727,0.0006694118,0.0021964363,0.00072631775,0.00046929414,0.0010579546,0.0005024182,0.000005015996],"category_scores_gemma":[0.000060290415,0.00047235197,0.00022691903,0.0013680251,0.00023977325,0.0010149751,0.00032122922,0.0011365468,0.0000107652395],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003602174,0.0017842974,0.0146091,0.01749728,0.0023876138,0.02443609,0.003589065,0.000049875085,0.6660156,0.039479453,0.054272216,0.1722772],"study_design_scores_gemma":[0.00088574877,0.0005162427,0.0081410445,0.002258156,0.00014603231,0.0006194097,0.0014356725,0.0014050348,0.97725624,0.002535652,0.003891272,0.00090952177],"about_ca_topic_score_codex":0.017153908,"about_ca_topic_score_gemma":0.0030881655,"teacher_disagreement_score":0.31124058,"about_ca_system_score_codex":0.0008329816,"about_ca_system_score_gemma":0.0009240352,"threshold_uncertainty_score":0.99977285},"labels":[],"label_agreement":null},{"id":"W181793689","doi":"","title":"A language for specifying and comparing table recognition strategies","year":2005,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"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; Table (database); Interpretation (philosophy); Simple (philosophy); Artificial intelligence; Precision and recall; Recall; Machine learning; Sequence (biology); Natural language processing; Theoretical computer science; Data mining; Programming language","score_opus":0.04233067524236712,"score_gpt":0.28877516748368853,"score_spread":0.24644449224132142,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W181793689","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":[0.056755982,0.00011423075,0.9139841,0.000307606,0.000029056768,0.00022181578,0.000002139486,0.0005688639,0.02801621],"genre_scores_gemma":[0.5917892,0.000018284112,0.4076131,0.00018556861,0.00007746746,0.000041872358,0.0000057253524,0.0000050816684,0.0002637204],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99940664,0.000013740609,0.00013092777,0.00020892915,0.000073264746,0.00016647777],"domain_scores_gemma":[0.9996759,0.000053416727,0.000037087208,0.00013291762,0.000056207187,0.000044429587],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018344654,0.00007714422,0.000102068065,0.00007975609,0.00008747011,0.00034065975,0.00015774829,0.00003338947,0.000044317545],"category_scores_gemma":[0.000015260539,0.00007298486,0.000021557267,0.000106718006,0.00001755593,0.0010697693,0.00006923569,0.000052558207,0.000029177023],"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":[0.000006200418,0.000045576944,0.0001512955,0.000044806566,0.0000106832795,0.0000023008213,0.0012778277,0.0000033485392,0.0072892094,0.027583651,0.002519738,0.96106535],"study_design_scores_gemma":[0.0023684045,0.00036831244,0.0011670471,0.0002427654,0.000027281816,0.00016111105,0.0036401674,0.29566306,0.5679124,0.095170334,0.032053467,0.0012256675],"about_ca_topic_score_codex":0.000039601393,"about_ca_topic_score_gemma":0.00010113264,"teacher_disagreement_score":0.9598397,"about_ca_system_score_codex":0.000018458824,"about_ca_system_score_gemma":0.000019339272,"threshold_uncertainty_score":0.328499},"labels":[],"label_agreement":null},{"id":"W1834432298","doi":"10.1007/978-3-642-01818-3_24","title":"Co-Training on Handwritten Digit Recognition","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","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":"Western University","funders":"","keywords":"Digit recognition; Computer science; Construct (python library); Numerical digit; Speech recognition; Artificial intelligence; Pattern recognition (psychology); Training (meteorology); Artificial neural network; Arithmetic; Mathematics","score_opus":0.03589896077276799,"score_gpt":0.27124257374988664,"score_spread":0.23534361297711864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1834432298","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":[0.0000701085,0.00008066684,0.9417371,0.001342183,0.0006668522,0.000548029,0.000017403578,0.00083616417,0.054701503],"genre_scores_gemma":[0.10762391,0.0002982294,0.86920923,0.018986441,0.0017443926,0.00006665621,0.000112815505,0.00014440832,0.0018139048],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9949979,0.000055509747,0.0007069298,0.0019957991,0.001354438,0.00088937656],"domain_scores_gemma":[0.99704826,0.0005544617,0.00038522278,0.0013909239,0.0003487908,0.00027232434],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0009631893,0.0007321899,0.00071611884,0.0016392722,0.0003478035,0.0011055787,0.0030389524,0.00073842204,0.00007022512],"category_scores_gemma":[0.0001640973,0.00071062986,0.00021434094,0.0006575644,0.00056091975,0.0010138095,0.0003392789,0.0016790262,0.00040814333],"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":[0.0000057797906,0.00003216072,0.0000023299071,0.000012878432,0.0000068841023,0.00011069028,0.00038501693,0.00013351577,0.00017848946,0.0027543546,0.00010780074,0.9962701],"study_design_scores_gemma":[0.00063571386,0.0011391639,0.00010168036,0.0023876692,0.00001610594,0.00030779527,4.504978e-7,0.02705475,0.04959639,0.903133,0.013544184,0.0020831407],"about_ca_topic_score_codex":0.0000070792657,"about_ca_topic_score_gemma":0.000017467595,"teacher_disagreement_score":0.99418694,"about_ca_system_score_codex":0.00040356893,"about_ca_system_score_gemma":0.0004963947,"threshold_uncertainty_score":0.9999314},"labels":[],"label_agreement":null},{"id":"W1842747459","doi":"10.1007/978-3-642-39320-4_11","title":"Determining Points on Handwritten Mathematical Symbols","year":2013,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":9,"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":"Handwriting; Computer science; Variety (cybernetics); Diagram; Simple (philosophy); Baseline (sea); Scale (ratio); Artificial intelligence; Pattern recognition (psychology); Natural language processing; Mathematics; Geography; Cartography","score_opus":0.021306751936100744,"score_gpt":0.25835828361839874,"score_spread":0.237051531682298,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1842747459","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":[0.00013972358,0.00005203744,0.9723123,0.0009497756,0.0006238966,0.0006888455,0.0000042380525,0.00059210684,0.024637124],"genre_scores_gemma":[0.06649829,0.000032726653,0.9270382,0.0046249805,0.0004769535,0.00007623034,0.0000054972093,0.00008338292,0.0011637757],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99509925,0.000056493267,0.00077705126,0.0018271314,0.0013570988,0.0008829649],"domain_scores_gemma":[0.9963132,0.00089205726,0.00034168828,0.0018359723,0.00031235692,0.00030471344],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010058775,0.00073121017,0.000785982,0.0012165518,0.0002648038,0.0011217787,0.003964803,0.0005069374,0.0002856409],"category_scores_gemma":[0.00022439736,0.0006389561,0.00020396363,0.00046948198,0.00066214206,0.00083718984,0.0014270736,0.00113446,0.0015194924],"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":[0.000001998321,0.000043223834,0.000007691434,0.000047699683,0.000009959711,0.00012317103,0.000349655,0.00008774545,0.00015435327,0.040407706,0.00012779552,0.958639],"study_design_scores_gemma":[0.0002921684,0.00044590826,0.000048468733,0.0018530275,0.000009784492,0.00023627002,1.8468162e-7,0.16627282,0.013056275,0.81588894,0.0008118892,0.0010842915],"about_ca_topic_score_codex":0.0000037503555,"about_ca_topic_score_gemma":0.000004522229,"teacher_disagreement_score":0.9575547,"about_ca_system_score_codex":0.00029812168,"about_ca_system_score_gemma":0.00031273277,"threshold_uncertainty_score":0.9999151},"labels":[],"label_agreement":null},{"id":"W184986784","doi":"","title":"Computer analysis of composite documents with non-uniform background","year":2004,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Thresholding; Optical character recognition; Artificial intelligence; Pixel; Segmentation; Pattern recognition (psychology); Preprocessor; Document processing; Skew; Digitization; Feature (linguistics); Computer vision; Image (mathematics); Telecommunications","score_opus":0.01174129417886988,"score_gpt":0.2567374607094722,"score_spread":0.2449961665306023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W184986784","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":[0.11010835,0.0000032556268,0.8823709,0.00015270662,0.000026193897,0.00012573897,0.0000023942725,0.00018958612,0.0070208833],"genre_scores_gemma":[0.52538645,0.0000038888493,0.47420967,0.00029244003,0.00000817574,0.000006130804,0.000008457444,0.000004101224,0.000080683836],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989017,0.000016357322,0.00026679397,0.00029970557,0.00031913893,0.00019630224],"domain_scores_gemma":[0.9991087,0.0000288349,0.000118174845,0.0004918734,0.00016881069,0.000083656036],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013836798,0.0001362028,0.00029818426,0.00046381506,0.000055396715,0.00012515686,0.00060248864,0.000044823348,0.00007086593],"category_scores_gemma":[6.069976e-7,0.00010271178,0.0001122837,0.001545949,0.00005994818,0.00062946323,0.00017314256,0.00007266231,0.000041307583],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022730032,0.0052465145,0.0508377,0.00035431137,0.01818858,0.00043671293,0.007260059,0.03273505,0.023206007,0.41123146,0.0043531326,0.44592318],"study_design_scores_gemma":[0.0077552097,0.0035722936,0.13879408,0.00046279907,0.0018494115,0.00014510972,0.00016736706,0.32926524,0.49029008,0.023396533,0.0017369054,0.0025650044],"about_ca_topic_score_codex":0.0002602087,"about_ca_topic_score_gemma":0.00009555826,"teacher_disagreement_score":0.46708405,"about_ca_system_score_codex":0.000060578306,"about_ca_system_score_gemma":0.0000420524,"threshold_uncertainty_score":0.41884652},"labels":[],"label_agreement":null},{"id":"W1874190160","doi":"10.1007/3-540-45268-0_2","title":"Content Based Indexing and Retrieval in a Digital Library of Arabic Scripts and Calligraphy","year":2000,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","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 Saskatchewan","funders":"","keywords":"Search engine indexing; Computer science; Scripting language; Calligraphy; Information retrieval; Feature (linguistics); Feature extraction; Glyph (data visualization); Cursive; Artificial intelligence; Arabic; Visual Word; Visualization; Pattern recognition (psychology); Image retrieval; Natural language processing; Image (mathematics)","score_opus":0.019516869207877895,"score_gpt":0.21704200602613963,"score_spread":0.19752513681826173,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1874190160","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":[0.008905779,0.0011983524,0.98719954,0.00036004977,0.00015118561,0.00044706668,0.00002655398,0.00016792689,0.0015435594],"genre_scores_gemma":[0.78856844,0.0002579246,0.20961861,0.0013791411,0.00007067774,0.0000064361084,0.000009088929,0.000032956134,0.000056696543],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9974406,0.000025010724,0.00054318295,0.0010578153,0.0005539141,0.00037947122],"domain_scores_gemma":[0.9986692,0.00035658025,0.00020138756,0.00053439743,0.00008995775,0.00014846738],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003740431,0.00036885566,0.00051617797,0.0014720787,0.00007216269,0.0006033146,0.0010613706,0.00027233065,0.000011883083],"category_scores_gemma":[0.00005886259,0.00034322182,0.000074566655,0.0006931433,0.00090545934,0.0013346386,0.000612099,0.0005661773,0.0000019126114],"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":[0.00003715459,0.00005192144,0.002689073,0.00012293237,0.000008353468,0.00013625258,0.0003881487,0.000102252336,0.00029853472,0.003250968,0.000009136199,0.99290526],"study_design_scores_gemma":[0.00195145,0.0012357774,0.005906485,0.005563522,0.000017178889,0.0002730457,0.0000010394905,0.25484625,0.045104682,0.68165946,0.0012666313,0.002174454],"about_ca_topic_score_codex":0.000014510544,"about_ca_topic_score_gemma":0.000011814974,"teacher_disagreement_score":0.9907308,"about_ca_system_score_codex":0.00004683455,"about_ca_system_score_gemma":0.00027815052,"threshold_uncertainty_score":0.99990195},"labels":[],"label_agreement":null},{"id":"W19096729","doi":"10.1007/978-3-319-11656-3_21","title":"End-Shape Recognition for Arabic Handwritten Text Segmentation","year":2014,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":8,"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":"King Abdulaziz University","keywords":"Computer science; Spotting; Arabic; Text segmentation; Segmentation; Artificial intelligence; Natural language processing; Handwriting; Text recognition; Handwriting recognition; Speech recognition; Word (group theory); Pattern recognition (psychology); Feature extraction; Linguistics; Image (mathematics)","score_opus":0.023558543297169263,"score_gpt":0.2611351952739788,"score_spread":0.23757665197680955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W19096729","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":[0.00007483533,0.00014863213,0.99346167,0.00084110757,0.0011644445,0.0013159837,0.000030839645,0.00054938346,0.0024131245],"genre_scores_gemma":[0.031204266,0.000087893415,0.96360224,0.0033266332,0.0008460836,0.00020918572,0.00012287367,0.00007459924,0.00052621256],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99564594,0.00006269021,0.00076064485,0.001844357,0.0009408209,0.00074555475],"domain_scores_gemma":[0.9966893,0.000880736,0.0004994045,0.0010736791,0.00065588555,0.00020100363],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014695138,0.0006338834,0.00062873104,0.0012595858,0.00036594048,0.0008056617,0.0023534764,0.00048230262,0.00011876323],"category_scores_gemma":[0.00018642799,0.00062329683,0.00023732365,0.0005197115,0.00049899716,0.00084710796,0.0005884409,0.00061549933,0.00017519397],"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":[0.000007512229,0.00002027109,0.0000073622855,0.00006451846,0.000009996338,0.000008435571,0.0001907225,0.00009897629,0.00067175087,0.0029752702,0.000117950214,0.99582726],"study_design_scores_gemma":[0.00082904514,0.00066075637,0.000053446005,0.00090082927,0.000030109939,0.000118417476,3.087996e-7,0.39373475,0.04490785,0.5531445,0.0042523607,0.0013676208],"about_ca_topic_score_codex":0.000012345885,"about_ca_topic_score_gemma":0.00004700745,"teacher_disagreement_score":0.9944596,"about_ca_system_score_codex":0.00030434757,"about_ca_system_score_gemma":0.00036492434,"threshold_uncertainty_score":0.9996218},"labels":[],"label_agreement":null},{"id":"W1914787714","doi":"10.1109/icpr.1998.712067","title":"Handwriting and signature: one or two personality identifiers?","year":2002,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Handwriting; Computer science; Identifier; Signature (topology); Personality; Artificial intelligence; Psychology; Computer network; Mathematics; Social psychology","score_opus":0.04726895103109744,"score_gpt":0.2741892735097559,"score_spread":0.22692032247865848,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1914787714","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":[0.024766328,0.0006755436,0.93008035,0.0030364883,0.00012470389,0.00030881824,0.0000042985785,0.0013992449,0.03960422],"genre_scores_gemma":[0.8667274,0.0000882038,0.12702253,0.0012851253,0.000076263925,0.00001848013,0.0000010922118,0.0000080518475,0.004772823],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988766,0.000065819724,0.00018584136,0.00038539383,0.00025055974,0.00023581585],"domain_scores_gemma":[0.99935067,0.000119931065,0.000052786218,0.0002743302,0.00008906112,0.00011320903],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00033547124,0.00011656257,0.00014449163,0.00008759655,0.00016433523,0.0003720329,0.00035172518,0.00006360033,0.0011928763],"category_scores_gemma":[0.00008164345,0.00009800758,0.000041488463,0.00032130466,0.0000639697,0.0006889472,0.0001913245,0.0001677285,0.00009285188],"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":[0.000008874098,0.00025429632,0.0005832602,0.00008186827,0.000052894273,0.00009621727,0.001695946,2.0259965e-7,0.0125248255,0.050528817,0.020678613,0.91349417],"study_design_scores_gemma":[0.0065013045,0.000987524,0.0076833563,0.00075582566,0.00011097652,0.0012370942,0.0009474722,0.2077572,0.62992793,0.1124542,0.027851658,0.0037854412],"about_ca_topic_score_codex":0.000050455248,"about_ca_topic_score_gemma":0.000044136286,"teacher_disagreement_score":0.90970874,"about_ca_system_score_codex":0.00002081501,"about_ca_system_score_gemma":0.000009005693,"threshold_uncertainty_score":0.99972016},"labels":[],"label_agreement":null},{"id":"W1916578673","doi":"10.1109/sibgra.2004.1352947","title":"Handwritten recognition with multiple classifiers for restricted lexicon","year":2004,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Computer science; Hidden Markov model; Classifier (UML); Artificial intelligence; Pattern recognition (psychology); Lexicon; Artificial neural network; Cascading classifiers; Random subspace method; Intelligent word recognition; Speech recognition; Handwriting recognition; Feature extraction; Character recognition; Machine learning; Intelligent character recognition","score_opus":0.029787946916947427,"score_gpt":0.24968750378517854,"score_spread":0.21989955686823112,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1916578673","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":[0.013393771,0.0000118200705,0.9775688,0.001906938,0.000081667655,0.00076250924,0.000013239829,0.0013087182,0.0049525322],"genre_scores_gemma":[0.40778014,0.000014666204,0.5906608,0.0007639534,0.000055930836,0.0003316398,0.0000482194,0.000019740948,0.00032490207],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998712,0.000029182227,0.00023875799,0.0004651028,0.00021860025,0.0003363654],"domain_scores_gemma":[0.9989821,0.00013503079,0.000096207405,0.00036892988,0.0002912156,0.00012654751],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001441903,0.00017353856,0.00017013703,0.00021363772,0.00016859767,0.0001928117,0.0004176803,0.00011560832,0.0000199155],"category_scores_gemma":[0.00010474858,0.00014054633,0.000071913164,0.0004780939,0.00006129912,0.00075218244,0.00005639281,0.00012206236,0.0000678499],"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":[0.00034260235,0.000713745,0.000853404,0.00011055592,0.00013807126,0.000058998594,0.0007471599,0.000044480497,0.034297276,0.05523734,0.009973865,0.8974825],"study_design_scores_gemma":[0.0085566025,0.0022481736,0.0023195497,0.00026553095,0.000039410446,0.000139245,0.00018647735,0.0058514597,0.77077657,0.19931166,0.009175998,0.0011293094],"about_ca_topic_score_codex":0.00009993774,"about_ca_topic_score_gemma":0.00014735077,"teacher_disagreement_score":0.8963532,"about_ca_system_score_codex":0.00009650512,"about_ca_system_score_gemma":0.00016107706,"threshold_uncertainty_score":0.57313126},"labels":[],"label_agreement":null},{"id":"W1917590724","doi":"10.1109/pacrim.1999.799511","title":"A novel intelligent system for defining similar symbols","year":2003,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Symbol (formal); Computer science; Artificial intelligence; Representation (politics); Set (abstract data type); Pattern recognition (psychology); Line (geometry); Natural language processing; Speech recognition; Mathematics; Programming language","score_opus":0.03364527772354298,"score_gpt":0.26961025468497885,"score_spread":0.23596497696143587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1917590724","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":[0.00021296248,0.00006326665,0.97012204,0.00012130742,0.00019247728,0.00038442534,0.0000041473036,0.0009225505,0.027976803],"genre_scores_gemma":[0.28926584,0.0000048840634,0.70985824,0.0003729046,0.00001313818,0.00017255855,0.0000017824564,0.000011088369,0.00029956934],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989909,0.000030020132,0.0002524901,0.0003175425,0.00014965195,0.00025938923],"domain_scores_gemma":[0.9991893,0.00016652684,0.00006174156,0.0003554563,0.0001435006,0.00008346038],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005003932,0.00012088504,0.00015564592,0.000081275895,0.000098225864,0.00014851411,0.00041288088,0.00006317854,0.00002213453],"category_scores_gemma":[0.00011788187,0.000106998494,0.000090254725,0.00021801272,0.000014331435,0.00022469477,0.000060654045,0.00006183675,0.00010427144],"study_design_candidate":"theoretical_or_conceptual","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":[0.000001137002,0.00004249566,0.00002333975,0.000049663413,0.000011810872,0.0000018516689,0.000107591404,0.000003586303,0.0023996814,0.96988165,0.0012637929,0.026213372],"study_design_scores_gemma":[0.00047056744,0.00019780186,0.00001480368,0.00017348219,0.000013122877,0.00016270993,0.0003499958,0.018536748,0.93036187,0.012058158,0.037191797,0.000468969],"about_ca_topic_score_codex":0.0000056785234,"about_ca_topic_score_gemma":0.0000025319089,"teacher_disagreement_score":0.9578235,"about_ca_system_score_codex":0.0000651313,"about_ca_system_score_gemma":0.00005586947,"threshold_uncertainty_score":0.4363272},"labels":[],"label_agreement":null},{"id":"W194037823","doi":"","title":"An Improved Method for Finding Knight Covers.","year":2007,"lang":"en","type":"article","venue":"Ars Combinatoria","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mathematics; Knight; Physics","score_opus":0.017309905796442555,"score_gpt":0.31301052109491656,"score_spread":0.295700615298474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W194037823","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":[0.019164046,0.000023461773,0.976456,0.00016959803,0.001167736,0.00045658764,0.000004459913,0.0006810288,0.0018770694],"genre_scores_gemma":[0.58605415,0.0000027426638,0.4133382,0.00038493724,0.000017164817,0.00004398651,0.000007994478,0.000017293993,0.0001334963],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99856484,0.00007071369,0.00028653888,0.00045012514,0.00019271745,0.0004350719],"domain_scores_gemma":[0.9985405,0.00040974683,0.00012238843,0.0005831019,0.00017311593,0.00017113978],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001747802,0.00016195812,0.00020020423,0.00018207333,0.00019104884,0.0001767024,0.00085426046,0.00013568059,0.000016807106],"category_scores_gemma":[0.000114582836,0.00016660488,0.00009711019,0.0003689405,0.000024078226,0.0007314117,0.00010659714,0.00014704613,0.000023155342],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001881027,0.00014951978,0.00011354794,0.000013690074,0.000020207499,0.000009766466,0.00034999996,9.195428e-7,0.020281257,0.8123286,0.0019569811,0.1647567],"study_design_scores_gemma":[0.00095129653,0.0004683889,0.00036381566,0.000016787686,0.000010091129,0.000013151299,0.000030756597,0.018955823,0.3455388,0.6260919,0.0072311265,0.0003280667],"about_ca_topic_score_codex":0.000024824842,"about_ca_topic_score_gemma":0.000005600091,"teacher_disagreement_score":0.5668901,"about_ca_system_score_codex":0.000093165596,"about_ca_system_score_gemma":0.00005755309,"threshold_uncertainty_score":0.67939496},"labels":[],"label_agreement":null},{"id":"W1964159865","doi":"10.1016/j.patcog.2009.05.009","title":"Reducing forgeries in writer-independent off-line signature verification through ensemble of classifiers","year":2009,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":203,"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; Pattern recognition (psychology); Artificial intelligence; Signature (topology); Random subspace method; Random forest; Feature (linguistics); Set (abstract data type); Feature extraction; Machine learning; Mathematics; Support vector machine","score_opus":0.03730559397107888,"score_gpt":0.2786587819514879,"score_spread":0.24135318798040903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1964159865","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":[0.27732697,0.00016752457,0.71787626,0.0011057525,0.00021115942,0.00043780488,0.000023134957,0.0002775735,0.0025738312],"genre_scores_gemma":[0.9723051,0.00022809318,0.0265955,0.00059944345,0.0000693812,0.000046788122,0.00011355975,0.000012363378,0.000029748846],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9982193,0.00013188648,0.0005533696,0.00047674717,0.00033247462,0.00028623795],"domain_scores_gemma":[0.99897146,0.00007254947,0.00028513867,0.00040561112,0.00021346309,0.000051756157],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039313157,0.0001907005,0.00025999325,0.00027290502,0.00006141246,0.00008727539,0.00037640712,0.00019814815,0.000049290607],"category_scores_gemma":[0.00006838417,0.00020150447,0.000091618866,0.00047603884,0.000035932782,0.0010795303,0.000046859644,0.00028977834,0.00003912266],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016532187,0.00016065723,0.00019850994,0.000034075605,0.000006622774,0.000010790232,0.00091577304,0.000004309752,0.041120525,0.00014266682,0.00019652912,0.957193],"study_design_scores_gemma":[0.00088840234,0.00052589027,0.010641893,0.00066110067,0.000017524306,0.00004532801,0.0002176918,0.0073016756,0.92623365,0.05257632,0.00038430523,0.00050621154],"about_ca_topic_score_codex":0.000055936336,"about_ca_topic_score_gemma":0.00003188074,"teacher_disagreement_score":0.9566868,"about_ca_system_score_codex":0.000091261616,"about_ca_system_score_gemma":0.000043394928,"threshold_uncertainty_score":0.8217114},"labels":[],"label_agreement":null},{"id":"W1968677253","doi":"10.1016/j.patcog.2008.10.007","title":"A new benchmark on the recognition of handwritten Bangla and Farsi numeral characters","year":2008,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":119,"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":"Numeral system; Computer science; Artificial intelligence; Pattern recognition (psychology); Bengali; Normalization (sociology); Grayscale; Feature extraction; Handwriting; Speech recognition; Arabic; Image (mathematics)","score_opus":0.03535804179603201,"score_gpt":0.22965450570605825,"score_spread":0.19429646391002625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1968677253","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":[0.8163055,0.00006751497,0.17649241,0.00300533,0.0002818899,0.0007067275,0.00007448042,0.00033475147,0.0027313721],"genre_scores_gemma":[0.98876804,0.00035409088,0.008031983,0.002296509,0.00018196412,0.00010142899,0.00014014504,0.00002448739,0.00010133145],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99819624,0.00020571784,0.0004198004,0.00048122514,0.00039102318,0.0003059865],"domain_scores_gemma":[0.99870956,0.00029938712,0.000269388,0.00038282032,0.00019980923,0.00013905721],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003693378,0.00024780535,0.00026259996,0.00025015624,0.00022325781,0.00009173596,0.00039113284,0.00012941356,0.00031484652],"category_scores_gemma":[0.00009349459,0.00020119533,0.00012015475,0.00033828832,0.000100350226,0.00061385136,0.00011325852,0.0002758543,0.00025377545],"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":[0.000021704232,0.00008092374,0.0011020069,0.000024900515,0.000030387444,0.000018282182,0.0007532188,4.361863e-8,0.0019844049,0.00004660468,0.0027120758,0.99322546],"study_design_scores_gemma":[0.005068633,0.0027932373,0.17998101,0.0024384602,0.00017469759,0.0016489854,0.0003465006,0.0027087785,0.7088968,0.089927554,0.003292015,0.0027233453],"about_ca_topic_score_codex":0.00016234312,"about_ca_topic_score_gemma":0.0000141633855,"teacher_disagreement_score":0.9905021,"about_ca_system_score_codex":0.000037108923,"about_ca_system_score_gemma":0.000053605214,"threshold_uncertainty_score":0.8204508},"labels":[],"label_agreement":null},{"id":"W1968734870","doi":"10.1016/j.cviu.2012.11.003","title":"A learning framework for the optimization and automation of document binarization methods","year":2012,"lang":"en","type":"article","venue":"Computer Vision and Image Understanding","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":39,"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; Pattern recognition (psychology); Artificial intelligence; Set (abstract data type); Feature (linguistics); Support vector machine; Image (mathematics); Automation; Grid; Feature vector; Data mining; Mathematics","score_opus":0.0398230236819171,"score_gpt":0.3547683067541055,"score_spread":0.3149452830721884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1968734870","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":[0.00025482147,0.00026151753,0.998329,0.00053214637,0.00016571817,0.00029610874,3.1886907e-7,0.00012709177,0.000033308224],"genre_scores_gemma":[0.24616687,0.00013948021,0.75355303,0.000079061465,0.000038882707,0.000010024928,0.0000020730342,0.000005694666,0.0000049046535],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992365,0.00014632495,0.0001971813,0.00016584391,0.00011090123,0.00014324421],"domain_scores_gemma":[0.99899745,0.00061197765,0.00014571662,0.00012756351,0.00006624548,0.000051022784],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009760151,0.00009374558,0.00011869949,0.00013190972,0.00029041924,0.00027100762,0.000117292744,0.000056781322,0.0000059667223],"category_scores_gemma":[0.000085262014,0.00006934643,0.00003021753,0.00020213134,0.00005876932,0.0009665074,0.00016358476,0.00008614202,3.9667037e-7],"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":[0.000013417298,0.00004519686,0.00016772635,0.00012767907,0.0000324521,2.321657e-7,0.0057083275,0.0008187454,0.002377617,0.40271717,0.00016741848,0.58782405],"study_design_scores_gemma":[0.00020592632,0.00018959114,0.00017751816,0.00012592411,0.000013608087,0.000009527207,0.00024115178,0.9563011,0.0024244038,0.040034875,0.00017845565,0.00009790386],"about_ca_topic_score_codex":0.0000010285,"about_ca_topic_score_gemma":4.0890423e-8,"teacher_disagreement_score":0.95548236,"about_ca_system_score_codex":0.00004571769,"about_ca_system_score_gemma":0.000006905193,"threshold_uncertainty_score":0.28278655},"labels":[],"label_agreement":null},{"id":"W1969663682","doi":"10.1109/icdar.2013.119","title":"Verification of Hierarchical Classifier Results for Handwritten Arabic Word Spotting","year":2013,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Spotting; Computer science; Classifier (UML); Artificial intelligence; Word (group theory); Keyword spotting; Speech recognition; Natural language processing; Arabic; Recall rate; Mathematics","score_opus":0.025449667339370884,"score_gpt":0.2639441580145219,"score_spread":0.23849449067515105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1969663682","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":[0.029080598,0.00001368134,0.9529063,0.0033715798,0.0000944996,0.000699964,0.000006668794,0.00040603592,0.01342068],"genre_scores_gemma":[0.6507404,0.0000074598875,0.34764895,0.00023182978,0.0000489092,0.00019626069,0.000012105009,0.000007646871,0.0011064927],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986646,0.000055422108,0.0004668006,0.00037105463,0.00019974638,0.00024234701],"domain_scores_gemma":[0.99864024,0.00029327645,0.00015669757,0.0005016851,0.0003230697,0.0000850471],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046317544,0.00010912052,0.00017460716,0.00015464175,0.000077204626,0.000114822884,0.0005594546,0.00009821871,0.00004017941],"category_scores_gemma":[0.00025749268,0.00009511213,0.00008852522,0.00028293484,0.000065630025,0.000568586,0.00009454384,0.00011019651,0.00007899124],"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":[0.000031068288,0.00012367919,0.00015091871,0.000045044722,0.00001782308,6.490678e-7,0.0003870173,0.0000011430094,0.031330053,0.039049573,0.021717122,0.9071459],"study_design_scores_gemma":[0.0028364132,0.00063027383,0.03381044,0.00022403373,0.000020742851,0.000023700348,0.00019078486,0.115255386,0.63452524,0.19069606,0.020925833,0.00086111896],"about_ca_topic_score_codex":0.00003686783,"about_ca_topic_score_gemma":0.000003727847,"teacher_disagreement_score":0.9062848,"about_ca_system_score_codex":0.0000234999,"about_ca_system_score_gemma":0.000043983728,"threshold_uncertainty_score":0.387856},"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":"W1971452976","doi":"10.1117/12.806163","title":"Online computation of similarity between handwritten characters","year":2008,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Legendre polynomials; Matching (statistics); Similarity (geometry); Computation; Sobolev space; Computer science; Handwriting; Constant (computer programming); Measure (data warehouse); Mathematics; Handwriting recognition; Identification (biology); Pattern recognition (psychology); Artificial intelligence; Image (mathematics); Algorithm; Mathematical analysis; Feature extraction; Data mining; Statistics","score_opus":0.022013310649674673,"score_gpt":0.2502193990071913,"score_spread":0.22820608835751663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1971452976","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":[0.9917151,0.00004154495,0.0045063645,0.0023534878,0.00012554732,0.00048055925,0.00007543585,0.00019883673,0.00050314603],"genre_scores_gemma":[0.69124633,0.000087810804,0.3081886,0.000108856795,0.00023039403,0.000049516286,0.000019833227,0.000030560226,0.00003808276],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99748796,3.1521804e-8,0.00090223993,0.00042535676,0.0008394983,0.00034491133],"domain_scores_gemma":[0.99660724,0.0001823882,0.0006213798,0.00007898439,0.0023818393,0.00012818593],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00060089043,0.00029300345,0.0005342097,0.0001823272,0.00010224175,0.00007264704,0.0015054084,0.00020956223,0.0000040190866],"category_scores_gemma":[0.00038920715,0.00026160822,0.0005945785,0.0005043485,0.00030045424,0.0009977396,0.00030066533,0.0003409307,0.0000011884089],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007290888,0.0007206289,0.005656894,0.0010614651,0.0008592345,5.693392e-7,0.0010503182,0.000051867082,0.6129786,0.3672187,0.0048469,0.0054819537],"study_design_scores_gemma":[0.0025605874,0.0011248029,0.04662227,0.0010172456,0.00023193592,0.00007799286,0.00071210595,0.07167195,0.8623166,0.011302814,0.0013337462,0.0010279614],"about_ca_topic_score_codex":0.000013295799,"about_ca_topic_score_gemma":9.63372e-8,"teacher_disagreement_score":0.35591587,"about_ca_system_score_codex":0.000112320275,"about_ca_system_score_gemma":0.0000525495,"threshold_uncertainty_score":0.9999836},"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":"W1973691454","doi":"10.1109/icfhr.2012.169","title":"A Structure for Adaptive Handwriting Recognition","year":2012,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Handwriting recognition; Handwriting; Computer science; Pattern recognition (psychology); Artificial intelligence; Character (mathematics); Character recognition; Weight function; Class (philosophy); Training set; Intelligent character recognition; Test set; Set (abstract data type); Adaptation (eye); Speech recognition; Mathematics; Statistics; Feature extraction","score_opus":0.03888323323101743,"score_gpt":0.271282896161667,"score_spread":0.23239966293064956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1973691454","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":[0.0052977866,0.000056675934,0.98683566,0.00019513402,0.00016640696,0.00036027687,0.000022061988,0.00060781604,0.0064581707],"genre_scores_gemma":[0.5410139,0.0000023404982,0.4582265,0.00041687748,0.00015806934,0.00006309864,0.000010835477,0.0000065848426,0.0001018034],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99917734,0.00003350796,0.0001543362,0.0001921799,0.00011905485,0.0003235804],"domain_scores_gemma":[0.99937767,0.0001241916,0.00006142728,0.00017858476,0.00015851976,0.00009962072],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024095816,0.000103781036,0.000104866296,0.00009196231,0.000115647024,0.000085952306,0.0002402619,0.00007511518,0.00010982729],"category_scores_gemma":[0.00006928214,0.00009245439,0.000061002058,0.00016670012,0.000017552791,0.0010783991,0.000071959235,0.00007828345,0.00004904368],"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":[0.000008128025,0.00004803361,0.00013765389,0.000015983442,0.000015440204,4.6757162e-7,0.00041135473,1.09732106e-7,0.005123253,0.04194066,0.004108624,0.9481903],"study_design_scores_gemma":[0.0007207979,0.00027143373,0.0005891564,0.0000734242,0.000018584316,0.00008406841,0.00021250514,0.0068870005,0.8165064,0.16642684,0.007616605,0.0005931915],"about_ca_topic_score_codex":0.000006745851,"about_ca_topic_score_gemma":0.0000046096684,"teacher_disagreement_score":0.9475971,"about_ca_system_score_codex":0.000029394001,"about_ca_system_score_gemma":0.000017601937,"threshold_uncertainty_score":0.3770181},"labels":[],"label_agreement":null},{"id":"W1973759055","doi":"10.1007/s100440070003","title":"An HMM-MLP Hybrid Model for Cursive Script Recognition","year":2000,"lang":"en","type":"article","venue":"Pattern Analysis and Applications","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":33,"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; Kyungil University","keywords":"Cursive; Hidden Markov model; Computer science; Pattern recognition (psychology); Artificial intelligence; Speech recognition","score_opus":0.02367950298016299,"score_gpt":0.2816651684398643,"score_spread":0.2579856654597013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1973759055","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":[0.009972707,0.0000337363,0.98824525,0.00044662922,0.0000044855838,0.00042385582,0.00018311503,0.0002140185,0.0004761842],"genre_scores_gemma":[0.9423528,0.00023404787,0.054237295,0.0010210306,0.00006623003,0.0014416287,0.00043188996,0.000010882679,0.00020419943],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99895346,0.00003084231,0.00023220557,0.00048658694,0.00011930492,0.00017760399],"domain_scores_gemma":[0.9991353,0.000033275704,0.00007654407,0.00048327542,0.00015049738,0.00012106551],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016559304,0.00012074232,0.0001818907,0.00022019033,0.00023159265,0.00020314596,0.00034805026,0.00003804344,0.00012542102],"category_scores_gemma":[0.000002818757,0.00012170759,0.00013301187,0.0005037763,0.00003506973,0.00038441026,0.000024485376,0.00006364378,0.00005771587],"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":[0.0000011389707,0.00009380476,0.000179321,0.000005465154,0.00008326764,1.9894922e-7,0.00009139929,0.00009309489,0.00033166184,0.00044924,0.00025633356,0.99841505],"study_design_scores_gemma":[0.00014829717,0.000034695713,0.00040666317,0.0000057985544,0.00031217578,0.0000034840843,0.0000148450545,0.94681764,0.0063699884,0.043895997,0.0017699361,0.0002204784],"about_ca_topic_score_codex":0.000052504827,"about_ca_topic_score_gemma":0.00005258145,"teacher_disagreement_score":0.9981946,"about_ca_system_score_codex":0.000016670101,"about_ca_system_score_gemma":0.000014538209,"threshold_uncertainty_score":0.49630916},"labels":[],"label_agreement":null},{"id":"W1975016170","doi":"10.1109/icfhr.2014.102","title":"Are Sparse Representation and Dictionary Learning Good for Handwritten Character Recognition?","year":2014,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Artificial intelligence; MNIST database; Pattern recognition (psychology); Character (mathematics); Optical character recognition; Sparse approximation; Facial recognition system; Intelligent character recognition; Dictionary learning; Character recognition; Intelligent word recognition; Representation (politics); Benchmark (surveying); Face (sociological concept); Speech recognition; Image (mathematics); Deep learning; Mathematics","score_opus":0.032430356457621504,"score_gpt":0.2698902446191224,"score_spread":0.23745988816150093,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1975016170","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":[0.03234173,0.000017006927,0.95947695,0.0019037233,0.0001587735,0.00038880034,0.0000056038352,0.00080319366,0.004904249],"genre_scores_gemma":[0.83522606,0.000058997062,0.1594859,0.0017938449,0.00032703407,0.00038681104,0.00008309816,0.000025712261,0.0026125186],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9988892,0.00010758603,0.00022268212,0.0004346073,0.00015337253,0.0001925258],"domain_scores_gemma":[0.99905103,0.0002578551,0.0001825646,0.00022028656,0.00020155648,0.00008667496],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039643332,0.00012220487,0.00015517209,0.0001496336,0.00022663907,0.00020115978,0.00017658382,0.00008003836,0.00005372761],"category_scores_gemma":[0.00022846427,0.00011706399,0.000059081798,0.00016215436,0.000034186865,0.000808243,0.00010036428,0.00012364016,0.00007241193],"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":[0.000025561767,0.00011305204,0.015433228,0.000054657277,0.000037942755,0.0000049896125,0.00029801417,0.0000022932072,0.0028371292,0.0074455068,0.0050039487,0.9687437],"study_design_scores_gemma":[0.0050064796,0.001431768,0.27638188,0.00048297684,0.00011224588,0.00049689383,0.0006112757,0.17357312,0.14082858,0.24918771,0.14973018,0.0021568697],"about_ca_topic_score_codex":0.000010232344,"about_ca_topic_score_gemma":0.000006388907,"teacher_disagreement_score":0.9665868,"about_ca_system_score_codex":0.000015956692,"about_ca_system_score_gemma":0.000008973766,"threshold_uncertainty_score":0.4773731},"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":"W197734339","doi":"","title":"Effects of Manual Phonetic Transcriptions on Recognition Accuracy of Streetnames","year":2002,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Transcription (linguistics); Speech recognition; Phonetic transcription; Computer science; Natural language processing; Artificial intelligence; Linguistics","score_opus":0.017572373551511172,"score_gpt":0.23287530803747344,"score_spread":0.21530293448596227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W197734339","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":[0.37353292,0.00016266388,0.61423624,0.00007888048,0.00026978907,0.00083228014,0.000049578113,0.0004396664,0.010397963],"genre_scores_gemma":[0.9854132,0.00015118605,0.014176821,0.00010247136,0.000017195227,0.00008688392,0.000028205026,0.000006726453,0.000017307673],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985889,0.0000931095,0.0006703111,0.00012688425,0.00032925967,0.00019150184],"domain_scores_gemma":[0.99862665,0.0002601554,0.0004573297,0.00027548187,0.00032416658,0.00005623257],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020108168,0.0001540984,0.00023287642,0.00046900008,0.00009215033,0.00007764435,0.0003519922,0.0001040001,0.00007028996],"category_scores_gemma":[0.00034889914,0.00015349517,0.00010726977,0.00050997647,0.00011312076,0.0027999713,0.000037261,0.00011368094,0.000119169694],"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":[0.000013359498,0.00014729919,0.00003870976,0.0007988843,0.000027187487,0.0000013784327,0.0070513254,0.000015167325,0.005411799,0.002125772,0.00048364865,0.98388547],"study_design_scores_gemma":[0.0012590326,0.0011818211,0.0065938937,0.0015783254,0.00005016407,0.000037699647,0.00041665643,0.018845074,0.93690896,0.031971138,0.00067834917,0.00047888767],"about_ca_topic_score_codex":0.000038858405,"about_ca_topic_score_gemma":0.0000031190038,"teacher_disagreement_score":0.9834066,"about_ca_system_score_codex":0.00007190123,"about_ca_system_score_gemma":0.000020628271,"threshold_uncertainty_score":0.62593514},"labels":[],"label_agreement":null},{"id":"W1977597938","doi":"10.1155/2008/247354","title":"Arabic Handwritten Word Recognition Using HMMs with Explicit State Duration","year":2007,"lang":"en","type":"article","venue":"EURASIP Journal on Advances in Signal Processing","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":43,"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":"Agence Universitaire de la Francophonie","keywords":"Hidden Markov model; Computer science; Speech recognition; Word recognition; Viterbi algorithm; Word (group theory); Duration (music); Artificial intelligence; Sliding window protocol; Pattern recognition (psychology); Handwriting; Intelligent word recognition; Spotting; Handwriting recognition; Cursive; Natural language processing; Intelligent character recognition; Window (computing); Character recognition; Feature extraction; Mathematics; Image (mathematics); Reading (process)","score_opus":0.026208253775838606,"score_gpt":0.29866400061739257,"score_spread":0.27245574684155394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1977597938","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":[0.15950799,0.0011214709,0.83805084,0.000116467236,0.00011304988,0.00019916428,0.0000011106921,0.00017662493,0.0007132476],"genre_scores_gemma":[0.8054644,0.0002864894,0.19353165,0.00042961308,0.00020990641,0.000009459836,0.0000028227737,0.000031825613,0.000033825265],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99718666,0.00014892676,0.0008498725,0.00048255702,0.0007378559,0.00059410796],"domain_scores_gemma":[0.99825776,0.00018119982,0.00073433464,0.00017262145,0.0004606488,0.0001934102],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0016174038,0.00030383098,0.0003027091,0.00072498416,0.00041478724,0.0006830887,0.00049148285,0.00008080879,0.000024206412],"category_scores_gemma":[0.000071016206,0.00025126938,0.00006368147,0.0011783174,0.000073216775,0.005916784,0.00004932623,0.00078139186,0.000018320437],"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":[0.00019648125,0.000105142906,0.0008303447,0.000037355327,0.0000057591174,0.0003024257,0.00048685636,0.0004961256,0.0045630243,0.000025907068,0.00000655971,0.992944],"study_design_scores_gemma":[0.009906723,0.004855468,0.009431521,0.020241117,0.00009224917,0.01320023,0.002285576,0.12451986,0.6580397,0.14485154,0.0076444615,0.004931544],"about_ca_topic_score_codex":0.0000028370355,"about_ca_topic_score_gemma":0.00002288771,"teacher_disagreement_score":0.9880125,"about_ca_system_score_codex":0.00028692678,"about_ca_system_score_gemma":0.00015031215,"threshold_uncertainty_score":0.999994},"labels":[],"label_agreement":null},{"id":"W1978781165","doi":"10.1109/icdar.2011.32","title":"Ternary Entropy-Based Binarization of Degraded Document Images Using Morphological Operators","year":2011,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"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; Concordia University","keywords":"Computer science; Pixel; Handwriting; Artificial intelligence; Pattern recognition (psychology); Grayscale; Entropy (arrow of time); Binary image; Handwriting recognition; Morphing; Image (mathematics); Computer vision; Feature extraction; Image processing","score_opus":0.041851559585270245,"score_gpt":0.2658521324842364,"score_spread":0.22400057289896613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1978781165","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":[0.1666489,0.000021597381,0.83209276,0.00006616985,0.00005655953,0.00014902613,0.0000012263307,0.00027108728,0.00069264986],"genre_scores_gemma":[0.5962521,0.0000035184044,0.40354514,0.00015941577,0.000006242659,0.000008275694,0.0000016232116,0.000004003259,0.000019680023],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99903226,0.00009173654,0.00026307517,0.00025920503,0.00019043626,0.00016326994],"domain_scores_gemma":[0.99941266,0.000018601904,0.00009827264,0.000294244,0.00011423396,0.000062016225],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001716332,0.00011308184,0.00014272386,0.00015507489,0.000048744958,0.000046727582,0.00045850393,0.00006350317,0.0003013709],"category_scores_gemma":[0.00002155156,0.000088245266,0.000059553517,0.00026964056,0.00006780134,0.00040111117,0.00013454244,0.00006324984,0.000016489814],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005895459,0.00127614,0.038148113,0.00007885965,0.000064621454,0.00032760907,0.0010625023,0.000035875655,0.835077,0.064702995,0.00068957056,0.058477793],"study_design_scores_gemma":[0.00023977601,0.0002039933,0.0019777173,0.00002794563,0.0000066927323,0.000020994717,0.000011419898,0.012990469,0.9795299,0.004824856,0.000026057032,0.00014016489],"about_ca_topic_score_codex":0.00011768803,"about_ca_topic_score_gemma":5.392345e-7,"teacher_disagreement_score":0.42960322,"about_ca_system_score_codex":0.000033900673,"about_ca_system_score_gemma":0.000047110352,"threshold_uncertainty_score":0.35985374},"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":"W1986467948","doi":"10.1016/j.patrec.2006.03.002","title":"An EMD-based recognition method for Chinese fonts and styles","year":2006,"lang":"en","type":"article","venue":"Pattern Recognition Letters","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":41,"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":"Computer science; Artificial intelligence; Pattern recognition (psychology); Character recognition; Speech recognition; Natural language processing; Image (mathematics)","score_opus":0.018177387796835455,"score_gpt":0.2849106033999969,"score_spread":0.26673321560316143,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1986467948","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":[0.19290335,0.000020092695,0.8025035,0.0026134541,0.00014776917,0.0007349289,0.00019938889,0.00072043383,0.0001570484],"genre_scores_gemma":[0.4981529,0.0000074789464,0.48962834,0.010228909,0.00035376629,0.00065814465,0.0009126671,0.000049488888,0.000008278085],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9975769,0.00031460167,0.0004959362,0.00084670767,0.00030520392,0.00046064425],"domain_scores_gemma":[0.9985043,0.00041031878,0.00025486553,0.0004248496,0.00025385438,0.00015181435],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000714937,0.00035742988,0.00031984074,0.00043691092,0.00024638738,0.0004239389,0.00040514919,0.00014713871,0.00007057889],"category_scores_gemma":[0.00006026961,0.00035597532,0.00014969063,0.00031176695,0.0000656102,0.0011743857,0.000051313422,0.00018084812,0.00007478838],"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":[0.00002456742,0.00018888939,0.0025270097,0.00008909797,0.000018405479,0.000012727009,0.00007087321,0.000006607882,0.029584242,0.0000152216735,0.0016050889,0.96585727],"study_design_scores_gemma":[0.012258889,0.0019414198,0.072878264,0.00091551495,0.00028873014,0.0003642442,0.0001396968,0.31217486,0.46645388,0.12393807,0.0033797363,0.0052667107],"about_ca_topic_score_codex":0.00023501173,"about_ca_topic_score_gemma":0.000111852125,"teacher_disagreement_score":0.96059054,"about_ca_system_score_codex":0.000059423335,"about_ca_system_score_gemma":0.0000275733,"threshold_uncertainty_score":0.9998892},"labels":[],"label_agreement":null},{"id":"W1992504041","doi":"10.1080/00085030.2009.10757606","title":"Forgery by Scanning","year":2009,"lang":"en","type":"article","venue":"Canadian Society of Forensic Science Journal","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Authentication (law); Signature (topology); Computer security; Computer science; Internet privacy; Mathematics","score_opus":0.013637630120100117,"score_gpt":0.2483467033931919,"score_spread":0.2347090732730918,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1992504041","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":[0.17071684,0.0029224772,0.7668834,0.041113775,0.0015594807,0.000425918,0.000026205948,0.00035599127,0.015995972],"genre_scores_gemma":[0.58170766,0.00014594784,0.4025209,0.015247776,0.00013657281,0.0000016439012,0.0000012441257,0.000007366836,0.00023093335],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9981191,0.000014248187,0.00030472802,0.00026933677,0.00062865776,0.00066391064],"domain_scores_gemma":[0.9982453,0.00002367683,0.00019092983,0.00029471962,0.00041885398,0.00082653033],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001325838,0.0001186345,0.00017191116,0.00025579854,0.00069462217,0.00036353862,0.0013822361,0.000069407375,0.000036895322],"category_scores_gemma":[0.00006686129,0.000113952265,0.00019143835,0.0012762187,0.000566865,0.001479882,0.00004060808,0.00028194525,0.0000057573034],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.638728e-7,0.000009081253,0.00022693202,0.0000019038225,0.000004709438,0.000005842157,0.00067188253,0.0000017152049,0.008735996,0.0009002206,0.55709136,0.43235],"study_design_scores_gemma":[0.0010547189,0.0009510546,0.0131311305,0.00052749645,0.000025989239,0.00238147,0.0015680668,0.019631928,0.76257277,0.075148225,0.12154,0.001467171],"about_ca_topic_score_codex":0.0006672144,"about_ca_topic_score_gemma":0.00019411366,"teacher_disagreement_score":0.75383675,"about_ca_system_score_codex":0.0004041581,"about_ca_system_score_gemma":0.001816751,"threshold_uncertainty_score":0.53425425},"labels":[],"label_agreement":null},{"id":"W1993283713","doi":"10.1007/s00107-006-0101-4","title":"UF resin efficiency of MDF as affected by resin content loss, coverage level and pre-cure","year":2006,"lang":"de","type":"article","venue":"European Journal of Wood and Wood Products","topic":"Handwritten Text Recognition 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":false,"ca_institutions":"Université Laval; Intertek (Canada)","funders":"","keywords":"Materials science; Composite material; Resin composite; Factorial experiment; Composite number; Mathematics","score_opus":0.020088190224217525,"score_gpt":0.22413957280229901,"score_spread":0.20405138257808147,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993283713","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":[0.9250649,0.053918287,0.012532721,0.004906928,0.00082404574,0.0007205505,0.00012344371,0.00008893026,0.0018201986],"genre_scores_gemma":[0.9884799,0.0033322792,0.0054724338,0.00020603513,0.0007770802,0.0000011421861,0.000012314865,0.000055225362,0.0016635875],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99518555,0.0014887201,0.0013378462,0.0007167606,0.0007651352,0.00050595886],"domain_scores_gemma":[0.9966458,0.00013836511,0.0014111885,0.0005436174,0.0009889527,0.00027203868],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0027413804,0.00045345395,0.0007158639,0.00035031134,0.00022906932,0.00041372725,0.0007565631,0.000090716676,0.000017899494],"category_scores_gemma":[0.00053206325,0.00039006353,0.0001230459,0.0006454213,0.00040237556,0.00065255613,0.00033565707,0.00068191934,0.000024501147],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011782452,0.0043752436,0.0012310522,0.0015643629,0.00065448816,0.0033446783,0.00607029,0.00001672912,0.50125355,0.0019447078,0.2725952,0.20577143],"study_design_scores_gemma":[0.007792962,0.01175887,0.037801106,0.0044740355,0.00049534824,0.002507057,0.00012676005,0.000094652896,0.86969554,0.0019881455,0.06170587,0.0015596685],"about_ca_topic_score_codex":0.000040965555,"about_ca_topic_score_gemma":0.0000027053838,"teacher_disagreement_score":0.36844194,"about_ca_system_score_codex":0.000038771108,"about_ca_system_score_gemma":0.00023655087,"threshold_uncertainty_score":0.9998551},"labels":[],"label_agreement":null},{"id":"W1996777176","doi":"10.1109/icfhr.2012.165","title":"A Novel Approach for Stroke Extraction of Off-Line Chinese Handwritten Characters Based on Optimum Paths","year":2012,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Ambiguity; Pattern recognition (psychology); Segmentation; Line (geometry); Artificial intelligence; Chinese characters; Intersection (aeronautics); Matching (statistics); Feature extraction; Property (philosophy); Line segment; Speech recognition; Mathematics; Engineering","score_opus":0.026975599268354165,"score_gpt":0.28438948864951624,"score_spread":0.25741388938116205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1996777176","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":[0.014149362,0.00002060141,0.980859,0.0002831271,0.00018455082,0.0006689153,0.00004623765,0.00035300548,0.0034352115],"genre_scores_gemma":[0.5842837,0.000004587659,0.41468844,0.00039764997,0.00011427677,0.00015541629,0.00004116037,0.000014347992,0.00030044644],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99854076,0.00003963263,0.00037039313,0.00034563462,0.00033070968,0.0003728924],"domain_scores_gemma":[0.99872524,0.00021303457,0.00021270495,0.00051339256,0.00018879797,0.00014683433],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006897077,0.00021865101,0.00028244522,0.0002848769,0.00007539696,0.000061726125,0.0004590475,0.0001268853,0.00002969783],"category_scores_gemma":[0.00009678064,0.00017367536,0.00018043826,0.00027549113,0.000036761703,0.0008717396,0.00006511527,0.00014579087,0.000010077851],"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":[0.00038252978,0.008077492,0.0040953956,0.0003612126,0.00011827041,0.0000018752747,0.00067410746,0.0003354435,0.43377143,0.01057499,0.0016410787,0.53996617],"study_design_scores_gemma":[0.0020729196,0.0007113954,0.008490202,0.000052780983,0.0000249585,0.000024415594,0.000038988186,0.80278623,0.18426152,0.00017810655,0.0008479504,0.00051054015],"about_ca_topic_score_codex":0.000016202732,"about_ca_topic_score_gemma":0.0000011049319,"teacher_disagreement_score":0.8024508,"about_ca_system_score_codex":0.000045990346,"about_ca_system_score_gemma":0.0000425424,"threshold_uncertainty_score":0.7082275},"labels":[],"label_agreement":null},{"id":"W1997960409","doi":"10.5539/mas.v9n1p137","title":"About One Method of On-Line Signature Verification Using Radial Basis Function","year":2014,"lang":"en","type":"article","venue":"Modern Applied Science","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Signature (topology); Basis (linear algebra); Wavelet; Function (biology); Radial basis function; Invariant (physics); Algorithm; Magnitude (astronomy); Basis function; Wavelet transform; Line (geometry); Representation (politics); Computer science; Position (finance); Mathematics; Mathematical analysis; Artificial intelligence; Physics; Geometry; Artificial neural network","score_opus":0.039011290371292334,"score_gpt":0.29257288327570213,"score_spread":0.2535615929044098,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1997960409","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":[0.0062582074,0.000014074252,0.98896766,0.00010234205,0.0001455926,0.00024741984,0.0000020859143,0.00023172503,0.0040308763],"genre_scores_gemma":[0.6366964,0.0000025249103,0.3628775,0.00033495092,0.00005022871,0.000017456388,0.0000017959012,0.0000064751234,0.0000126712175],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979658,0.00006882682,0.00028044876,0.00066266436,0.00073763414,0.000284606],"domain_scores_gemma":[0.9986339,0.000110566056,0.00020891118,0.000703047,0.00021062276,0.00013292267],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016373099,0.00014308389,0.00020197869,0.00034716594,0.00025176042,0.00012834821,0.000989774,0.00009842768,0.00001153136],"category_scores_gemma":[0.00010644212,0.00014023908,0.000046638936,0.0010923122,0.0002180078,0.00042593115,0.00013921884,0.00018882033,0.000020147012],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001471863,0.00004967165,0.0000030309889,0.000007441146,0.000002234396,7.195072e-8,0.00020057234,0.0006412695,0.6376761,0.033287928,0.000011954359,0.32810497],"study_design_scores_gemma":[0.00013720743,0.00008903765,0.00010659844,0.000017976967,0.000005077857,0.0000014641047,0.0000051591746,0.56435454,0.4097487,0.025308158,0.00011402142,0.00011206164],"about_ca_topic_score_codex":0.000010781339,"about_ca_topic_score_gemma":0.0000010417373,"teacher_disagreement_score":0.6304382,"about_ca_system_score_codex":0.00008648719,"about_ca_system_score_gemma":0.00015156539,"threshold_uncertainty_score":0.5718784},"labels":[],"label_agreement":null},{"id":"W1998157976","doi":"10.1109/tip.2014.2322451","title":"Phase-Based Binarization of Ancient Document Images: Model and Applications","year":2014,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":64,"is_retracted":false,"has_abstract":true,"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":"Artificial intelligence; Preprocessor; Robustness (evolution); Ground truth; Computer science; Pattern recognition (psychology); Historical document; Phase congruency; Computer vision; Feature (linguistics); Image (mathematics)","score_opus":0.01304638156847595,"score_gpt":0.2772989232520176,"score_spread":0.2642525416835417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1998157976","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":[0.0013578042,0.00004978868,0.99740154,0.0002264246,0.000023624438,0.00031479695,0.000008877961,0.00031864652,0.0002985182],"genre_scores_gemma":[0.7271665,0.000010039392,0.27235904,0.00023507325,0.000008041479,0.00018981319,0.0000017697687,0.000010429025,0.000019298848],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989389,0.000041684143,0.00027679728,0.00034751766,0.00022994964,0.0001651212],"domain_scores_gemma":[0.9991886,0.000039826242,0.00013849838,0.00029165938,0.00026494663,0.000076471806],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022354098,0.0001344813,0.00014393144,0.000272109,0.00023976163,0.00018916452,0.00023903127,0.000050232393,0.000005272691],"category_scores_gemma":[0.000005746254,0.00013557886,0.000046045552,0.0004452081,0.00010942543,0.00080261886,0.0000027336196,0.000116109055,0.0000056803638],"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":[0.000009384462,0.00050643587,9.221333e-7,0.00015068412,0.0000043877953,2.593507e-7,0.00017554786,0.0038681207,0.14950816,0.00025151373,0.000018731658,0.84550583],"study_design_scores_gemma":[0.0005454277,0.00012367468,0.0000021340588,0.00007660185,0.000013562685,0.0000026797086,0.0000110537885,0.55692333,0.44002604,0.002075944,0.000086724496,0.00011283329],"about_ca_topic_score_codex":0.0000044788753,"about_ca_topic_score_gemma":0.0000012398298,"teacher_disagreement_score":0.845393,"about_ca_system_score_codex":0.000039261136,"about_ca_system_score_gemma":0.000093577524,"threshold_uncertainty_score":0.55287457},"labels":[],"label_agreement":null},{"id":"W1998570028","doi":"10.1109/icpr.2010.504","title":"Automatic Discrimination between Confusing Classes with Writing Styles Verification in Arabic Handwritten Numeral Recognition","year":2010,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Numeral system; Handwriting; Computer science; Word error rate; Linear discriminant analysis; Speech recognition; Writing style; Artificial intelligence; Arabic; Handwriting recognition; Pattern recognition (psychology); Arabic numerals; Style (visual arts); Natural language processing; Feature extraction; Linguistics","score_opus":0.02362943470899868,"score_gpt":0.26755656360599905,"score_spread":0.24392712889700038,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1998570028","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":[0.6722639,0.0000047537337,0.32256693,0.00076316245,0.00004843051,0.00034375294,0.000003770936,0.0006690148,0.003336259],"genre_scores_gemma":[0.81640065,0.000005523479,0.18321072,0.00011671993,0.0000712319,0.00008759754,0.00006503262,0.000015583159,0.00002693405],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99829227,0.00011897542,0.000481439,0.00046819742,0.0003285224,0.00031058755],"domain_scores_gemma":[0.9988949,0.00021442889,0.00020126466,0.00036895456,0.0002373423,0.00008312427],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006510406,0.00019579638,0.00023049887,0.0004029846,0.00015649528,0.00044365975,0.00039024,0.00013731848,0.00008656171],"category_scores_gemma":[0.00011314363,0.00017272186,0.000040888954,0.00056033896,0.00008296125,0.0018397924,0.000066333436,0.0003655103,0.000055474633],"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":[0.0000042628562,0.00010111114,0.015679399,0.00006800189,0.000011976044,0.00000768557,0.00054723973,6.955879e-7,0.019607726,0.005340338,0.00006262543,0.95856893],"study_design_scores_gemma":[0.0022203368,0.00046019003,0.54033715,0.0010200823,0.00006839566,0.00013819158,0.0011894464,0.09059257,0.32805723,0.03407735,0.00030047048,0.0015385738],"about_ca_topic_score_codex":0.000132725,"about_ca_topic_score_gemma":0.00038899764,"teacher_disagreement_score":0.95703036,"about_ca_system_score_codex":0.00005789775,"about_ca_system_score_gemma":0.000080029735,"threshold_uncertainty_score":0.70433927},"labels":[],"label_agreement":null},{"id":"W2000084002","doi":"10.1109/synasc.2013.15","title":"Identifying Features via Homotopy on Handwritten Mathematical Symbols","year":2013,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Homotopy; Character (mathematics); Relation (database); Symbol (formal); Point (geometry); Simple (philosophy); Mathematics; Computer science; Algorithm; Pattern recognition (psychology); Artificial intelligence; Data mining; Pure mathematics; Geometry","score_opus":0.01707174316952911,"score_gpt":0.26291868726581125,"score_spread":0.24584694409628213,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2000084002","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":[0.005914772,0.000024248744,0.9333645,0.0018973565,0.000109171844,0.0005234899,6.933539e-7,0.0012746666,0.056891076],"genre_scores_gemma":[0.6447959,0.000012188408,0.34602275,0.0024112463,0.00009724285,0.00030318706,0.0000031431457,0.000024278035,0.0063300896],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984703,0.00006400819,0.0002789233,0.00042354382,0.0004026702,0.00036056835],"domain_scores_gemma":[0.99883026,0.00015394461,0.00006293517,0.00066527387,0.00012891596,0.00015866758],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00022788526,0.00019465828,0.00022133747,0.00019343435,0.00013722904,0.00070946774,0.00089787354,0.00011512215,0.0012966054],"category_scores_gemma":[0.000054439854,0.000150926,0.00010999212,0.00026997298,0.000049140595,0.000821378,0.00024384036,0.00022246144,0.0055008796],"study_design_candidate":"theoretical_or_conceptual","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":[0.0000034591608,0.0003915834,0.00011400564,0.00009188524,0.000053225616,0.00004187208,0.0007669728,4.85253e-7,0.023901932,0.3748099,0.08310593,0.51671875],"study_design_scores_gemma":[0.00033888285,0.00020112477,0.0034104718,0.0001737541,0.000008732365,0.00015918048,0.00006784913,0.0044283303,0.2797738,0.7102174,0.00068190956,0.00053854875],"about_ca_topic_score_codex":0.00003576093,"about_ca_topic_score_gemma":0.0000023653101,"teacher_disagreement_score":0.6388811,"about_ca_system_score_codex":0.00003412991,"about_ca_system_score_gemma":0.000016332318,"threshold_uncertainty_score":0.9996163},"labels":[],"label_agreement":null},{"id":"W2001392867","doi":"10.1016/j.patcog.2007.03.022","title":"A novel cascade ensemble classifier system with a high recognition performance on handwritten digits","year":2007,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":91,"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","keywords":"Pattern recognition (psychology); Word error rate; Cascade; Computer science; MNIST database; Artificial intelligence; Discriminative model; Numeral system; Classifier (UML); Cascading classifiers; Artificial neural network; Random subspace method; Speech recognition; Machine learning; Engineering","score_opus":0.031181442298990846,"score_gpt":0.23553637931797833,"score_spread":0.2043549370189875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2001392867","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":[0.38148385,0.000008340953,0.61022854,0.00014733298,0.00025322766,0.00054103095,0.000052926844,0.00095899974,0.006325759],"genre_scores_gemma":[0.9737805,0.00002750665,0.024223775,0.0009852804,0.00031831872,0.00023844672,0.00024867617,0.0000629112,0.000114546245],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9967919,0.00009111881,0.00063877454,0.00093874405,0.0007627274,0.0007767424],"domain_scores_gemma":[0.99806386,0.00023736423,0.00037133845,0.0005908761,0.00047294536,0.00026360893],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00089288584,0.00045660333,0.00038769701,0.00059193,0.00030943885,0.0003568937,0.000515948,0.000276997,0.000045826753],"category_scores_gemma":[0.000036610534,0.00040561965,0.000113532864,0.0006532858,0.00007419697,0.0012954106,0.000107315,0.0004795279,0.0012356921],"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":[0.00011828165,0.00025650614,0.0004217691,0.00017383946,0.00004535095,0.0000848579,0.00020557172,0.0000021384772,0.0047970284,0.0000631222,0.0002201037,0.99361145],"study_design_scores_gemma":[0.0053330944,0.0032095476,0.029086031,0.0051258127,0.00012676702,0.0024964937,0.0004294879,0.01037858,0.93928105,0.0011180511,0.0009234186,0.0024916818],"about_ca_topic_score_codex":0.00015029268,"about_ca_topic_score_gemma":0.00013438343,"teacher_disagreement_score":0.99111974,"about_ca_system_score_codex":0.00030809484,"about_ca_system_score_gemma":0.00006392319,"threshold_uncertainty_score":0.99983954},"labels":[],"label_agreement":null},{"id":"W2002580920","doi":"10.1109/icdar.2011.136","title":"Digit/Symbol Pruning and Verification for Arabic Handwritten Digit/Symbol Spotting","year":2011,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Numerical digit; Pattern recognition (psychology); Spotting; Speech recognition; Artificial intelligence; Classifier (UML); False positive paradox; Keyword spotting; Handwriting recognition; Arabic numerals; Arabic; Feature extraction; Arithmetic; Mathematics","score_opus":0.04061288132383164,"score_gpt":0.24173941805957685,"score_spread":0.2011265367357452,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2002580920","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":[0.088437885,0.00004604827,0.885638,0.00025839228,0.00012465425,0.00080655527,0.0000061243995,0.0011978274,0.023484537],"genre_scores_gemma":[0.845407,0.000024893096,0.15321402,0.0003075893,0.000059251364,0.00020256123,0.000010313419,0.000022595033,0.0007517407],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998398,0.00003812767,0.000381854,0.00059307535,0.00020015963,0.00038875756],"domain_scores_gemma":[0.99885565,0.0001303446,0.00015286452,0.0005070166,0.00020548994,0.00014865423],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000329484,0.00021405004,0.00022641354,0.00019456969,0.00023302274,0.00036336595,0.0005866645,0.00011362923,0.000033096374],"category_scores_gemma":[0.00013553796,0.00019800509,0.00007638959,0.0002558123,0.00007293484,0.0014653254,0.00019192057,0.00012092835,0.0000412952],"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":[0.000023846203,0.00016493828,0.005438396,0.00009491772,0.00004245772,0.0000069275347,0.0033864914,3.330071e-7,0.0073066717,0.02661427,0.001366541,0.9555542],"study_design_scores_gemma":[0.0019141742,0.0007300968,0.023376832,0.00034118554,0.000056584086,0.00013502236,0.0009605534,0.020212736,0.8506736,0.09075369,0.009213084,0.0016323989],"about_ca_topic_score_codex":0.00003180064,"about_ca_topic_score_gemma":0.0000059079744,"teacher_disagreement_score":0.9539218,"about_ca_system_score_codex":0.000034982517,"about_ca_system_score_gemma":0.00004711676,"threshold_uncertainty_score":0.80744135},"labels":[],"label_agreement":null},{"id":"W2003072187","doi":"10.1117/12.874706","title":"Automatic extraction of numeric strings in unconstrained handwritten document images","year":2010,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Mitacs","keywords":"Computer science; Merge (version control); Optical character recognition; Pruning; Pattern recognition (psychology); Artificial intelligence; Document processing; Segmentation; Handwriting recognition; Probabilistic logic; Algorithm; Feature extraction; Image (mathematics); Information retrieval","score_opus":0.007920035026247323,"score_gpt":0.24172142803468016,"score_spread":0.23380139300843283,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2003072187","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":[0.99434525,0.000027886459,0.001391293,0.0017062578,0.00023915966,0.00058683276,0.000016376142,0.00018443221,0.0015025046],"genre_scores_gemma":[0.64892673,0.000033555196,0.3506922,0.000038906845,0.00009575881,0.00013657707,0.0000027025285,0.000024087945,0.000049446964],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9975528,3.09066e-8,0.0009391413,0.0004187175,0.00072038185,0.0003689309],"domain_scores_gemma":[0.99765944,0.00020632571,0.0005934875,0.00009805487,0.0013356237,0.00010705993],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010016134,0.00029001795,0.0004525991,0.00025717693,0.000052990174,0.00015972888,0.0014438279,0.00020219239,0.000027024094],"category_scores_gemma":[0.000580574,0.00025514173,0.00044938218,0.000593716,0.00024993494,0.0013161727,0.00023225481,0.00048069394,0.0000015635503],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015061092,0.00013884476,0.00041318175,0.0003319056,0.000107018976,1.729503e-7,0.00018784261,0.0000066800662,0.74164456,0.25025633,0.00054731645,0.0063510947],"study_design_scores_gemma":[0.0012044589,0.0003373755,0.0032748065,0.00048719358,0.00006293758,0.000051971816,0.00057203195,0.03603405,0.9457851,0.011238908,0.0005347968,0.00041635302],"about_ca_topic_score_codex":0.000029202014,"about_ca_topic_score_gemma":5.8445556e-7,"teacher_disagreement_score":0.34930092,"about_ca_system_score_codex":0.000112520735,"about_ca_system_score_gemma":0.000060016722,"threshold_uncertainty_score":0.9999901},"labels":[],"label_agreement":null},{"id":"W2005443073","doi":"10.1109/hpcsim.2012.6266913","title":"A neural network approach to online Devanagari handwritten character recognition","year":2012,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Devanagari; Computer science; Handwriting; Artificial intelligence; Character (mathematics); Feature extraction; Artificial neural network; Pattern recognition (psychology); Discrete cosine transform; Feature (linguistics); Speech recognition; Set (abstract data type); Character encoding; Handwriting recognition; Character recognition; Mathematics; Image (mathematics)","score_opus":0.04082976831277993,"score_gpt":0.2630173403252038,"score_spread":0.22218757201242387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2005443073","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":[0.031014381,0.00007424766,0.93867195,0.0013692252,0.0005004308,0.00061421975,0.000012077224,0.0014080617,0.026335388],"genre_scores_gemma":[0.38331157,0.000011847172,0.6057704,0.008726875,0.0010770547,0.00014302917,0.000111626854,0.000025611458,0.000821949],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980652,0.00011921497,0.00033736983,0.00042998945,0.00029845338,0.00074981287],"domain_scores_gemma":[0.99881184,0.00006394691,0.00008025852,0.00050843746,0.00015244714,0.00038306805],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005325356,0.00022837328,0.00023603429,0.00018167868,0.00013571765,0.0002056154,0.0006587041,0.000119268865,0.00010292038],"category_scores_gemma":[0.000046443834,0.00019998144,0.0000988674,0.0006931571,0.000024012497,0.0013634544,0.00034973994,0.00022621443,0.00067681586],"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":[0.000017862121,0.00081416266,0.00189929,0.000025831074,0.000038200968,0.0000037599966,0.0006627286,0.000009888738,0.00064474996,0.005462415,0.038341276,0.95207983],"study_design_scores_gemma":[0.0048952354,0.0019697014,0.23235849,0.00061498885,0.00027918402,0.0018517798,0.00057630165,0.20843427,0.057965536,0.045480046,0.43590948,0.009665013],"about_ca_topic_score_codex":0.00002399897,"about_ca_topic_score_gemma":0.000008335569,"teacher_disagreement_score":0.9424148,"about_ca_system_score_codex":0.00004820905,"about_ca_system_score_gemma":0.000020049145,"threshold_uncertainty_score":0.8699324},"labels":[],"label_agreement":null},{"id":"W2006189769","doi":"10.1117/12.2003351","title":"Document segmentation via oblique cuts","year":2013,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Segmentation; Oblique case; Computer science; Generalization; Identification (biology); Image segmentation; Bar (unit); Artificial intelligence; Line (geometry); Line segment; Pattern recognition (psychology); Computer vision; Algorithm; Geometry; Mathematics","score_opus":0.008792574357049407,"score_gpt":0.23234843759606927,"score_spread":0.22355586323901985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2006189769","genre_codex":"empirical","genre_gemma":"methods","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":[0.98107296,0.00004492313,0.009662882,0.0049023954,0.00021911245,0.0010145922,0.000008853162,0.0002939714,0.0027803297],"genre_scores_gemma":[0.2750744,0.0001058418,0.7228992,0.00043108469,0.0002728262,0.00079905964,0.000008578166,0.00004983799,0.0003591823],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9976364,1.936836e-8,0.0007214153,0.0004557235,0.0007855557,0.00040091714],"domain_scores_gemma":[0.9970057,0.00011884521,0.0004182718,0.00008689935,0.002222676,0.00014757978],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005780337,0.0003035048,0.00033173215,0.00015223211,0.000090294445,0.00034763454,0.0016055846,0.00017631009,0.000039076982],"category_scores_gemma":[0.00021903393,0.00025665868,0.00048371524,0.00042240217,0.00013908013,0.0019785347,0.00032120972,0.00027305543,0.000013758285],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009466675,0.00008749809,0.000110166555,0.00019114053,0.00017097317,5.6166847e-8,0.0002105423,0.00000914079,0.57385767,0.4136555,0.006858934,0.004838899],"study_design_scores_gemma":[0.00091040146,0.0004580102,0.00086179044,0.0002920268,0.00006573814,0.00003254055,0.00046382233,0.040090255,0.9173422,0.0365087,0.0024470473,0.00052747113],"about_ca_topic_score_codex":0.000028448487,"about_ca_topic_score_gemma":1.0970312e-7,"teacher_disagreement_score":0.71323633,"about_ca_system_score_codex":0.00020517097,"about_ca_system_score_gemma":0.00003476389,"threshold_uncertainty_score":0.99998856},"labels":[],"label_agreement":null},{"id":"W2006251269","doi":"10.1016/s0031-3203(00)00081-9","title":"Character string extraction from color documents","year":2001,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":44,"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":"Character (mathematics); String (physics); Computer science; Artificial intelligence; Segmentation; Binary number; Pattern recognition (psychology); Mathematics; Physics; Arithmetic; Geometry; Theoretical physics","score_opus":0.030751206845463192,"score_gpt":0.2796954382318739,"score_spread":0.24894423138641072,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2006251269","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":[0.4676305,0.000017482895,0.52923846,0.00032250045,0.0004033715,0.0002210139,0.000025361453,0.0005412623,0.0016000288],"genre_scores_gemma":[0.9849618,0.00018584802,0.012865117,0.0010560354,0.00034371263,0.00015186047,0.00027010986,0.000020384332,0.00014511251],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99848306,0.00010360987,0.0003257586,0.00048819216,0.00030325074,0.00029610022],"domain_scores_gemma":[0.99914265,0.00010221932,0.00018523436,0.00032428867,0.00014049823,0.00010513254],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00020723166,0.000182168,0.00016189978,0.00018791268,0.00012393275,0.00030219657,0.00034979856,0.0001210468,0.00098356],"category_scores_gemma":[0.000029749448,0.00019342746,0.00008044975,0.00023837999,0.000017534852,0.0017453117,0.00010285435,0.00020814937,0.0022029502],"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":[0.00000838533,0.00008978144,0.0038280373,0.000004974561,0.000017616252,0.000040528415,0.00010158239,1.0651097e-7,0.008211016,0.000008659272,0.00037581124,0.9873135],"study_design_scores_gemma":[0.003763789,0.0006019634,0.19350486,0.00089667714,0.000122688,0.0004672903,0.00016200237,0.01422073,0.676179,0.06687597,0.040732674,0.002472347],"about_ca_topic_score_codex":0.00024739327,"about_ca_topic_score_gemma":0.000040576437,"teacher_disagreement_score":0.98484117,"about_ca_system_score_codex":0.000095278934,"about_ca_system_score_gemma":0.000016860777,"threshold_uncertainty_score":0.99992967},"labels":[],"label_agreement":null},{"id":"W2006651074","doi":"","title":"A Segmentation Method for Touching Italic Characters","year":2008,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec; Concordia University","funders":"","keywords":"Segmentation; Computer science; Artificial intelligence; Computer vision; Scale-space segmentation; Point (geometry); Image segmentation; Path (computing); Projection (relational algebra); Segmentation-based object categorization; Pattern recognition (psychology); Mathematics; Algorithm","score_opus":0.035364618699264855,"score_gpt":0.3139189256846657,"score_spread":0.27855430698540085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2006651074","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":[0.009241793,0.000005570987,0.98729265,0.00062239997,0.00008252123,0.00030308584,0.0000014100361,0.0005455613,0.0019050366],"genre_scores_gemma":[0.07154342,0.000008657,0.9262216,0.0014082246,0.000035736743,0.00010015899,0.0000067169394,0.000006002986,0.0006694511],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993616,0.000036702622,0.00013943408,0.00020998062,0.000111947425,0.00014038393],"domain_scores_gemma":[0.99956787,0.00010530938,0.000049797887,0.00017035575,0.00006272663,0.000043938508],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021786703,0.00007099974,0.000085753825,0.000094426614,0.00012400797,0.000053682725,0.00024491557,0.000030950618,0.000019491748],"category_scores_gemma":[0.000027199136,0.000064269094,0.000058124217,0.00013817195,0.000009959658,0.0006193007,0.00004487241,0.000039206505,0.000028989809],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000071128993,0.00008489352,0.00015154306,0.000024561617,0.000027454054,0.000010445637,0.0029362238,0.0000018471081,0.08336568,0.048545007,0.0068717287,0.8579735],"study_design_scores_gemma":[0.0006180612,0.00020869436,0.0013216707,0.000019605894,0.000007193482,0.00018118632,0.00009305987,0.052450426,0.925661,0.015381949,0.0036879003,0.00036922903],"about_ca_topic_score_codex":0.000018937884,"about_ca_topic_score_gemma":0.0000018545074,"teacher_disagreement_score":0.85760427,"about_ca_system_score_codex":0.000028195012,"about_ca_system_score_gemma":0.000023473669,"threshold_uncertainty_score":0.26208174},"labels":[],"label_agreement":null},{"id":"W2007163663","doi":"10.1109/icdar.2013.65","title":"Feature Design for Offline Arabic Handwriting Recognition: Handcrafted vs Automated?","year":2013,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":true,"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; Heuristics; Benchmark (surveying); Feature (linguistics); Task (project management); Handwriting recognition; Connectionism; Artificial neural network; Intelligent character recognition; Pattern recognition (psychology); Handwriting; Probabilistic logic; Feature extraction; Machine learning; Speech recognition; Natural language processing; Image (mathematics)","score_opus":0.0314695678777866,"score_gpt":0.26387193234846995,"score_spread":0.23240236447068335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2007163663","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":[0.0018884545,0.00006910567,0.98080707,0.007186388,0.00015841809,0.0016042897,0.000010629938,0.0061194245,0.0021562136],"genre_scores_gemma":[0.062692076,0.000017656177,0.9307716,0.0024070228,0.00017464161,0.0012103356,0.000047351343,0.000031974287,0.002647372],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99822956,0.00011622444,0.0003209648,0.00058047986,0.00025060953,0.0005021558],"domain_scores_gemma":[0.9981064,0.00038874685,0.00013665123,0.00045072188,0.0007384387,0.00017903611],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000513048,0.00026194396,0.0002931637,0.00022752197,0.00026307727,0.0005852118,0.0006331187,0.00021156645,0.00031851558],"category_scores_gemma":[0.00021215837,0.00022875247,0.00013376142,0.00050191884,0.000048249505,0.00091241265,0.0001259319,0.00018149897,0.0006509943],"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":[0.000026967951,0.00015943882,0.000034025008,0.00009207124,0.000055977463,0.0000110678075,0.00015591062,0.0000119603665,0.011992115,0.0012155304,0.4831789,0.503066],"study_design_scores_gemma":[0.0014720954,0.000609406,0.0003709295,0.00023025127,0.000023804107,0.00012822171,0.000044130433,0.773548,0.1787149,0.037138145,0.0069298977,0.00079020055],"about_ca_topic_score_codex":0.000027277747,"about_ca_topic_score_gemma":0.0000065711993,"teacher_disagreement_score":0.7735361,"about_ca_system_score_codex":0.00005091811,"about_ca_system_score_gemma":0.00007321563,"threshold_uncertainty_score":0.9328255},"labels":[],"label_agreement":null},{"id":"W2007932135","doi":"10.1007/s10044-004-0226-1","title":"Feature dimensionality reduction for the verification of handwritten numerals","year":2004,"lang":"en","type":"article","venue":"Pattern Analysis and Applications","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":13,"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; Royal Society of Canada","keywords":"Pattern recognition (psychology); Dimensionality reduction; Artificial intelligence; Computer science; Linear discriminant analysis; Feature extraction; Principal component analysis; Classifier (UML); Curse of dimensionality; Artificial neural network; Discriminant","score_opus":0.015898302070796747,"score_gpt":0.2761278753260146,"score_spread":0.2602295732552179,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2007932135","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":[0.003058822,0.00017789277,0.98782086,0.008389909,0.000010956371,0.00042029683,0.00002794319,0.000055862492,0.00003747069],"genre_scores_gemma":[0.9779797,0.00012839737,0.020945627,0.0001395474,0.000045870813,0.0006380694,0.000056204623,0.0000038036271,0.00006277806],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993561,0.000020849619,0.00016314437,0.0002550841,0.000121530094,0.00008332966],"domain_scores_gemma":[0.99914443,0.000065343,0.00014143653,0.00044137886,0.00017438894,0.000033023956],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024365527,0.000072109935,0.00013633422,0.000104350496,0.00022530518,0.000059031907,0.0002471161,0.00004119085,0.00000516431],"category_scores_gemma":[0.000007713475,0.000052471507,0.00012235394,0.0006758588,0.00005393073,0.000117836455,0.000039630948,0.000051671974,0.000002981738],"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":[0.000005486295,0.00025019323,0.001777284,0.000047412403,0.0006820756,1.0666234e-7,0.00036487047,0.00025057988,0.030892689,0.076319866,0.0007700649,0.8886394],"study_design_scores_gemma":[0.0016882187,0.00018221326,0.18006907,0.000075988275,0.0029878085,0.000031816864,0.00043949025,0.031301547,0.5536984,0.18346389,0.04510172,0.00095980027],"about_ca_topic_score_codex":0.00010739252,"about_ca_topic_score_gemma":0.000023063714,"teacher_disagreement_score":0.97492087,"about_ca_system_score_codex":0.000016166889,"about_ca_system_score_gemma":0.000015841042,"threshold_uncertainty_score":0.2139726},"labels":[],"label_agreement":null},{"id":"W2009868947","doi":"10.1134/s1054661806040079","title":"Off-line recognition of handwritten middle age Persian characters using moment","year":2006,"lang":"en","type":"article","venue":"Pattern Recognition and Image Analysis","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Zernike polynomials; Pattern recognition (psychology); Artificial intelligence; Character (mathematics); Velocity Moments; Character recognition; Invariant (physics); Moment (physics); Mathematics; Grayscale; Computer science; Image (mathematics); Geometry; Physics","score_opus":0.04402382656179163,"score_gpt":0.25684297126566163,"score_spread":0.21281914470387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2009868947","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":[0.4585988,0.00009387967,0.5400491,0.00021779639,0.00004020255,0.00018937724,0.00013161432,0.00014302395,0.0005362259],"genre_scores_gemma":[0.9624159,0.00026603616,0.035508845,0.0004916162,0.00011219799,0.000039743172,0.0010415657,0.000023183089,0.00010095505],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99784976,0.0001759213,0.0006741277,0.0006003792,0.00036482268,0.00033498518],"domain_scores_gemma":[0.9986625,0.000059872666,0.00040352182,0.00036282075,0.00038829385,0.00012303896],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00041983987,0.0002720897,0.00051517994,0.0010938192,0.00015005466,0.0002606016,0.0002659726,0.00011343761,0.00032175644],"category_scores_gemma":[0.000020532892,0.0002794358,0.000350449,0.0012097375,0.00011697493,0.0009177787,0.00012169341,0.00015721207,0.00007484098],"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":[0.00001961881,0.0004539891,0.0033896388,0.00013658048,0.0005990603,0.00008485315,0.00057479675,0.000003998655,0.04125925,0.0000076035067,0.00013215005,0.95333844],"study_design_scores_gemma":[0.005631449,0.0010175637,0.07120627,0.0012779329,0.007016885,0.00027204084,0.0013455072,0.21217799,0.6731881,0.021947775,0.00083388126,0.0040846276],"about_ca_topic_score_codex":0.0008184464,"about_ca_topic_score_gemma":0.00014704434,"teacher_disagreement_score":0.94925386,"about_ca_system_score_codex":0.000060865987,"about_ca_system_score_gemma":0.000021233247,"threshold_uncertainty_score":0.9999658},"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":"W2011012373","doi":"10.1109/icdar.2013.107","title":"Improving HMM-Based Keyword Spotting with Character Language Models","year":2013,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Keyword spotting; Computer science; Spotting; Hidden Markov model; Artificial intelligence; Lexicon; Character (mathematics); Language model; Natural language processing; Speech recognition; Handwriting recognition; Context (archaeology); Optical character recognition; Pattern recognition (psychology); Feature extraction; Image (mathematics)","score_opus":0.009690508726509334,"score_gpt":0.21087664708086376,"score_spread":0.20118613835435442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2011012373","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":[0.08404182,0.000010365205,0.9037604,0.0005215269,0.000030112384,0.00030071195,7.4440277e-7,0.0011396171,0.010194741],"genre_scores_gemma":[0.6510567,5.0563233e-7,0.34649774,0.0014154154,0.000034712877,0.0000836305,0.0000028285872,0.00001254897,0.00089590886],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99890727,0.000034296743,0.00017800553,0.00034677918,0.0002240647,0.00030959098],"domain_scores_gemma":[0.9991568,0.00005765709,0.00008762253,0.00046221563,0.00013632375,0.000099435834],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017330349,0.00014786485,0.00013494304,0.00012920782,0.00007839507,0.00034872803,0.0005025614,0.000055034576,0.0002867511],"category_scores_gemma":[0.0000130761655,0.00010836192,0.000042114003,0.00022634963,0.000026026784,0.0014500496,0.00011149207,0.00013822957,0.00026771703],"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":[0.000005410119,0.00010212978,0.0004352008,0.000050190727,0.000015874239,0.00003950742,0.00084261247,0.000030044781,0.03727086,0.0089102,0.00094110303,0.9513569],"study_design_scores_gemma":[0.00040067057,0.00012407884,0.00057469314,0.00006858241,0.0000048837983,0.000020317493,0.00008501534,0.79644936,0.20010698,0.0016509008,0.00010781404,0.00040670764],"about_ca_topic_score_codex":0.00040914532,"about_ca_topic_score_gemma":0.000010142056,"teacher_disagreement_score":0.95095015,"about_ca_system_score_codex":0.000028262171,"about_ca_system_score_gemma":0.000050691775,"threshold_uncertainty_score":0.44188708},"labels":[],"label_agreement":null},{"id":"W2011488234","doi":"10.1145/1463788.1463796","title":"Online stroke modeling for handwriting recognition","year":2008,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Networks of Centres of Excellence of Canada; Mitacs","keywords":"Handwriting; Computer science; Handwriting recognition; Intelligent character recognition; Artificial intelligence; Process (computing); Pattern recognition (psychology); Character (mathematics); Character recognition; Constant (computer programming); Speech recognition; Feature extraction; Mathematics; Image (mathematics)","score_opus":0.0782072319297144,"score_gpt":0.2842568044055304,"score_spread":0.206049572475816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2011488234","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":[0.039762966,0.000030753843,0.95564544,0.00038273534,0.000075558404,0.00028054297,0.00002915526,0.0009895003,0.0028033587],"genre_scores_gemma":[0.3830318,0.000052554988,0.61572593,0.0005168063,0.00011177657,0.000065337874,0.00004012859,0.000010493447,0.00044517365],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989554,0.000023980732,0.00027075715,0.00032425608,0.00016783409,0.0002577375],"domain_scores_gemma":[0.99926686,0.0000920084,0.000051866577,0.00023099112,0.00028333275,0.00007491326],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020603924,0.00011479096,0.0001393246,0.0001434667,0.00023687184,0.00006343885,0.00033284834,0.000069915164,0.000029780796],"category_scores_gemma":[0.000092576774,0.00011257683,0.00009683793,0.00015319428,0.000020359565,0.00061762205,0.00008238906,0.00009608341,0.00003704618],"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":[0.00001127443,0.00029316833,0.000057138976,0.000033923476,0.000022160368,0.00001470811,0.00029466368,0.00007269283,0.0053926655,0.003294979,0.0019384354,0.9885742],"study_design_scores_gemma":[0.00055832876,0.0001376141,0.000012780769,0.0000461709,0.0000053598037,0.00011217915,0.00005816537,0.9241391,0.05673495,0.017017605,0.00088734156,0.00029043065],"about_ca_topic_score_codex":0.000022984737,"about_ca_topic_score_gemma":0.00001228957,"teacher_disagreement_score":0.98828375,"about_ca_system_score_codex":0.00002709764,"about_ca_system_score_gemma":0.00004497219,"threshold_uncertainty_score":0.459075},"labels":[],"label_agreement":null},{"id":"W2012442176","doi":"10.1016/j.patcog.2008.12.021","title":"Text line segmentation in handwritten documents using Mumford–Shah model","year":2009,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":76,"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":"Morphing; Segmentation; Line (geometry); Computer science; Artificial intelligence; Pattern recognition (psychology); Computer vision; Image segmentation; Document processing; Document image processing; Natural language processing; Image (mathematics); Mathematics; Geometry","score_opus":0.04366332411408295,"score_gpt":0.30500938663770966,"score_spread":0.2613460625236267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2012442176","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":[0.26403657,0.000024526391,0.7340443,0.0003052469,0.00009016591,0.00038312897,0.000015334897,0.00028080386,0.0008198839],"genre_scores_gemma":[0.8904195,0.00006694702,0.10730073,0.0018796328,0.00008173494,0.000056531382,0.00013114096,0.00001649502,0.0000473121],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981236,0.00010663016,0.00050206366,0.0005241887,0.00035641182,0.0003871333],"domain_scores_gemma":[0.9992349,0.000035645604,0.00018517232,0.0003027929,0.00014290436,0.00009859069],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00036981158,0.00023267065,0.00022362194,0.00046142342,0.00010305955,0.00021543827,0.0003732106,0.00013237353,0.00007344654],"category_scores_gemma":[0.00002734528,0.0002521663,0.00007996488,0.00045817695,0.000025112278,0.0015938755,0.00007887456,0.00021630262,0.00015263082],"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":[0.000009345852,0.00018559748,0.00041548765,0.0000163026,0.000006555231,0.000017018561,0.0004087379,0.00015247954,0.0157463,0.000016723448,0.00012873221,0.98289675],"study_design_scores_gemma":[0.0015235837,0.00025681217,0.0020351412,0.00037242734,0.0000203404,0.000052640356,0.000064759304,0.82374763,0.11549837,0.05580203,0.000024999827,0.00060127414],"about_ca_topic_score_codex":0.000081436105,"about_ca_topic_score_gemma":0.000052813855,"teacher_disagreement_score":0.98229545,"about_ca_system_score_codex":0.0001809487,"about_ca_system_score_gemma":0.00004212684,"threshold_uncertainty_score":0.9999931},"labels":[],"label_agreement":null},{"id":"W2012796857","doi":"10.3115/1614049.1614079","title":"Quantitative methods for classifying writing systems","year":2006,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Artificial intelligence; Quantitative analysis (chemistry); Natural language processing; Data mining","score_opus":0.06734261640466951,"score_gpt":0.39399309724239256,"score_spread":0.3266504808377231,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2012796857","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":[0.0002093787,0.00022577278,0.97404027,0.0002535021,0.0001738656,0.00036782157,0.0000018766873,0.000903604,0.023823895],"genre_scores_gemma":[0.051363517,0.0000028502268,0.94751906,0.00010982956,0.00006398849,0.00018641517,0.0000033650947,0.000009873974,0.0007410938],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99892277,0.00014642502,0.00030014417,0.00029228625,0.00010005959,0.00023834639],"domain_scores_gemma":[0.99865985,0.000780619,0.00009786513,0.00022155803,0.00020501182,0.000035123074],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010693716,0.000101413054,0.00016173416,0.00012701178,0.00014004995,0.00030693182,0.00036072332,0.00005828286,0.000006058812],"category_scores_gemma":[0.00008669909,0.00009094481,0.00007198689,0.00024043513,0.000023823262,0.00045890012,0.00007738453,0.00006554369,0.00001852202],"study_design_candidate":"theoretical_or_conceptual","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":[0.0000013722437,0.00001828733,0.000034341825,0.00003258327,0.0000058012834,9.840002e-7,0.000034408604,0.0000069939124,0.009263111,0.8832041,0.0021656316,0.10523238],"study_design_scores_gemma":[0.00038500107,0.00022266062,0.0001505338,0.00010959039,0.00000961753,0.000031527805,0.0002780742,0.72750473,0.12668407,0.12229999,0.021882948,0.0004412607],"about_ca_topic_score_codex":0.00010482989,"about_ca_topic_score_gemma":0.0000047468666,"teacher_disagreement_score":0.76090413,"about_ca_system_score_codex":0.00003756898,"about_ca_system_score_gemma":0.000026713426,"threshold_uncertainty_score":0.3708622},"labels":[],"label_agreement":null},{"id":"W2014920175","doi":"10.1109/icfhr.2014.97","title":"Training of On-Line Handwriting Text Recognizers with Synthetic Text Generated Using the Kinematic Theory of Rapid Human Movements","year":2014,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"Universitat Politècnica de València; Natural Sciences and Engineering Research Council of Canada; Ministerio de Economía y Competitividad","keywords":"Kinematics; Hidden Markov model; Computer science; Handwriting; Log-normal distribution; Sigma; Artificial intelligence; Speech recognition; Line (geometry); Word (group theory); Sample (material); Pattern recognition (psychology); Natural language processing; Mathematics; Statistics; Physics","score_opus":0.06782552045651452,"score_gpt":0.28920092397163516,"score_spread":0.22137540351512064,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014920175","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":[0.16144551,0.000026280475,0.8260518,0.00008898974,0.00003767926,0.00038401943,0.0000032216544,0.00017200474,0.011790511],"genre_scores_gemma":[0.91778505,0.0000046720334,0.08161178,0.00039077533,0.00002751349,0.00002111999,0.0000030115118,0.000023434508,0.00013265174],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9978888,0.00042051167,0.0006239225,0.00036126023,0.00041127775,0.00029425177],"domain_scores_gemma":[0.9980368,0.0005516347,0.0004520638,0.0006346167,0.00026227743,0.00006257997],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018450674,0.00022133287,0.00039879364,0.0002347733,0.000197606,0.00007183835,0.0007177118,0.00006455919,0.0001566067],"category_scores_gemma":[0.00018751697,0.0001390564,0.0000881412,0.0005091395,0.00021683399,0.00020069332,0.000118625525,0.00015850479,0.0000051594716],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004275805,0.00030240775,0.00006717505,0.0002083747,0.0001851561,0.0000039755946,0.003101904,0.0007404175,0.1666701,0.043158665,0.00004373911,0.7854753],"study_design_scores_gemma":[0.0009957519,0.0011155717,0.00005957724,0.0012953356,0.00005343758,0.000028187858,0.0011779931,0.17981188,0.80289924,0.01213753,0.00004135428,0.00038415188],"about_ca_topic_score_codex":0.00003289027,"about_ca_topic_score_gemma":0.000009026553,"teacher_disagreement_score":0.78509116,"about_ca_system_score_codex":0.00002405694,"about_ca_system_score_gemma":0.000050029117,"threshold_uncertainty_score":0.5670555},"labels":[],"label_agreement":null},{"id":"W2019010736","doi":"10.1109/icip.2014.7025519","title":"Context-dependent BLSTM models. Application to offline handwriting recognition","year":2014,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"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; Context (archaeology); Context model; Speech recognition; Feature (linguistics); Handwriting; Artificial intelligence; Cluster analysis; Hidden Markov model; Natural language processing; Pattern recognition (psychology); Linguistics; Object (grammar)","score_opus":0.022512955938347474,"score_gpt":0.24903204405621235,"score_spread":0.22651908811786486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2019010736","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":[0.0022332221,0.000021926573,0.9670584,0.0013803535,0.00007123291,0.0005036051,0.0000044759495,0.0012326611,0.027494079],"genre_scores_gemma":[0.807772,0.000010341354,0.18830225,0.003205095,0.00011249388,0.00024138839,0.000018247789,0.000015131615,0.00032309198],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983338,0.0000880272,0.0003662449,0.0005703709,0.00034806455,0.00029348786],"domain_scores_gemma":[0.99871606,0.00010458829,0.00008924737,0.0005887094,0.00031964367,0.00018175351],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00077826105,0.00016572977,0.00020191383,0.0002034347,0.00013187419,0.00020642353,0.0005936331,0.00009135254,0.000051841856],"category_scores_gemma":[0.00008861678,0.00016345624,0.000077556935,0.0003324876,0.000018708404,0.0007353373,0.00021699218,0.00012805374,0.0007836451],"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":[0.0000035848357,0.000047296544,0.000007169679,0.0000086108275,0.0000064653495,5.378318e-7,0.000101288824,0.000039747138,0.0029126236,0.028459616,0.0007842554,0.9676288],"study_design_scores_gemma":[0.0006430399,0.00027226468,0.00005016264,0.000084301755,0.000014239732,0.000033804386,0.00006900642,0.54819137,0.22533685,0.21216787,0.012527016,0.0006100866],"about_ca_topic_score_codex":0.00013565278,"about_ca_topic_score_gemma":0.00007834625,"teacher_disagreement_score":0.9670187,"about_ca_system_score_codex":0.00005582504,"about_ca_system_score_gemma":0.000021847653,"threshold_uncertainty_score":0.99999434},"labels":[],"label_agreement":null},{"id":"W2023478387","doi":"10.1111/j.1556-4029.2010.01348.x","title":"The LongPen™—The World’s First Original Remote Signing Device*","year":2010,"lang":"en","type":"article","venue":"Journal of Forensic Sciences","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Office of the Chief Medical Examiner","funders":"","keywords":"Handwriting; Inscribed figure; Computer science; Visual arts; History; Computer graphics (images); Art; Artificial intelligence; Mathematics","score_opus":0.023617580839695628,"score_gpt":0.29598743248281173,"score_spread":0.2723698516431161,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2023478387","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":[0.43086818,0.0012639225,0.4074909,0.11246795,0.01245078,0.00065042457,0.0000017643599,0.0003308895,0.034475166],"genre_scores_gemma":[0.7460593,0.000074445554,0.2517386,0.0009150228,0.0006789592,0.0000020135071,6.287747e-8,0.000007052988,0.00052452413],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99804115,0.00007952107,0.0004611944,0.00019448118,0.000877789,0.0003458749],"domain_scores_gemma":[0.99761134,0.0009769211,0.0005636899,0.0003472053,0.00038703877,0.00011378812],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0041213594,0.00012430197,0.00015876678,0.0002138217,0.0013627232,0.00096582476,0.0028006723,0.00003740651,0.00003270846],"category_scores_gemma":[0.00041467443,0.00005833266,0.00013648547,0.0011613562,0.0009487598,0.00096616737,0.0001739782,0.0005742858,0.000029232555],"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":[0.000010485487,0.000026906022,0.0013768108,0.0000057421125,0.00002587285,0.000057835325,0.00057401875,0.000021408201,0.0019802041,0.043950107,0.026866963,0.92510366],"study_design_scores_gemma":[0.0006768072,0.0010303255,0.0065324963,0.00041765464,0.000054648553,0.0038752405,0.00055066496,0.024935538,0.14304474,0.21215028,0.6060662,0.00066541065],"about_ca_topic_score_codex":0.000028223927,"about_ca_topic_score_gemma":0.0011718854,"teacher_disagreement_score":0.92443824,"about_ca_system_score_codex":0.00002642219,"about_ca_system_score_gemma":0.00029212786,"threshold_uncertainty_score":0.99993736},"labels":[],"label_agreement":null},{"id":"W2025492775","doi":"10.1109/icdar.2009.89","title":"A Novel Rejection Measurement in Handwritten Numeral Recognition Based on Linear Discriminant Analysis","year":2009,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Linear discriminant analysis; Numeral system; Computer science; Pattern recognition (psychology); Classifier (UML); Discriminant; Artificial intelligence; Reliability (semiconductor); Optimal discriminant analysis; Kernel Fisher discriminant analysis; Handwriting recognition; Rank (graph theory); Feature extraction; Speech recognition; Mathematics","score_opus":0.04579482409146963,"score_gpt":0.2723923813535883,"score_spread":0.22659755726211867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2025492775","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":[0.0050687124,0.0000069594685,0.9863912,0.002822937,0.00006858775,0.0003140086,0.0000042942183,0.00046289273,0.0048604175],"genre_scores_gemma":[0.8516506,0.0000069788844,0.14626463,0.0018950297,0.000040429837,0.000050585997,0.000024507623,0.0000068948007,0.00006034966],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997901,0.000107337255,0.0004183801,0.0005788164,0.00067952246,0.00031493764],"domain_scores_gemma":[0.9990191,0.00003793429,0.000107388776,0.00047639667,0.00026327086,0.0000959283],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00097524724,0.00020323836,0.00027946685,0.0011092628,0.000091683825,0.0001328384,0.00034420952,0.0001023303,0.00006385003],"category_scores_gemma":[0.00010248663,0.00017754726,0.000191664,0.0019447989,0.000016683738,0.00045434904,0.00002884343,0.00019826643,0.000057262023],"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":[0.00014860019,0.0027923833,0.0010120095,0.00002150786,0.00011383704,0.000037602833,0.00037555717,0.00083218457,0.03578991,0.0015627001,0.00094626105,0.95636743],"study_design_scores_gemma":[0.0017613987,0.0011893064,0.058208723,0.00021401563,0.00015078338,0.000010843367,0.000042118027,0.8126999,0.11913783,0.0055118254,0.00033232712,0.00074091833],"about_ca_topic_score_codex":0.0002905606,"about_ca_topic_score_gemma":0.00038620443,"teacher_disagreement_score":0.95562655,"about_ca_system_score_codex":0.00024637033,"about_ca_system_score_gemma":0.00006213439,"threshold_uncertainty_score":0.7240167},"labels":[],"label_agreement":null},{"id":"W2027421981","doi":"10.1109/icfhr.2012.257","title":"Recognition of Relatively Small Handwritten Characters or "Size Matters"","year":2012,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Heuristics; Space (punctuation); Feature (linguistics); Pattern recognition (psychology); Artificial intelligence; Handwriting; Scale (ratio); Feature extraction; Speech recognition","score_opus":0.07217325506283395,"score_gpt":0.28086208604974355,"score_spread":0.2086888309869096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2027421981","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":[0.15643063,0.000102916994,0.8249854,0.0043474953,0.0006625075,0.0009418068,0.000058860718,0.0015232943,0.010947125],"genre_scores_gemma":[0.24520335,0.00018134929,0.73500097,0.0065153404,0.00031469757,0.00022907002,0.00010213613,0.000084136984,0.012368958],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9970089,0.00030333386,0.0008192499,0.0005937576,0.0004915713,0.0007831841],"domain_scores_gemma":[0.9973006,0.0006847767,0.00045577277,0.0008508452,0.00036762157,0.00034033103],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0011074295,0.00040122864,0.0005202655,0.00036673786,0.00016253344,0.00015025909,0.00093972654,0.00025908262,0.002008722],"category_scores_gemma":[0.00036325716,0.00033573218,0.0002230498,0.0007810209,0.00015062906,0.0019148978,0.00037066368,0.0003705473,0.0018919636],"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":[0.0005659418,0.0029990934,0.012483939,0.0006847429,0.00064155855,0.000024292638,0.013381481,8.4559184e-7,0.17659087,0.011167782,0.08904537,0.69241405],"study_design_scores_gemma":[0.005831358,0.0012446085,0.09526833,0.0016473754,0.00035296025,0.0010389974,0.0005873113,0.00022470749,0.47010824,0.032224607,0.38606516,0.005406349],"about_ca_topic_score_codex":0.00012403578,"about_ca_topic_score_gemma":0.000083128834,"teacher_disagreement_score":0.6870077,"about_ca_system_score_codex":0.000106134445,"about_ca_system_score_gemma":0.00008008569,"threshold_uncertainty_score":0.99990946},"labels":[],"label_agreement":null},{"id":"W2028003041","doi":"10.1109/icdar.2013.261","title":"A Binarization-Free Clustering Approach to Segment Curved Text Lines in Historical Manuscripts","year":2013,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Computer science; Artificial intelligence; Cluster analysis; Search engine indexing; Segmentation; Line (geometry); Curvature; Point (geometry); Pattern recognition (psychology); Spotting; Image segmentation; Word (group theory); Image (mathematics); Computer vision; Information retrieval; Mathematics; Geometry","score_opus":0.030674790776367932,"score_gpt":0.23363054911025508,"score_spread":0.20295575833388715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2028003041","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":[0.0049951146,0.00002923825,0.98104054,0.0028900513,0.00017507949,0.00062209176,4.042827e-7,0.0005364443,0.009711044],"genre_scores_gemma":[0.26457024,0.00000811393,0.72990346,0.001487035,0.00006411986,0.0005657609,0.0000036422468,0.00001599383,0.0033816556],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99860334,0.00006486073,0.00033853817,0.0004417635,0.00026401746,0.00028744843],"domain_scores_gemma":[0.99904084,0.00002800437,0.000046167916,0.0006195915,0.00012224719,0.00014311902],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022286881,0.00015048933,0.00018112462,0.00034498225,0.000053805557,0.00020885366,0.0009786766,0.000075107746,0.00005373331],"category_scores_gemma":[0.00008624533,0.00013541458,0.000042139003,0.00064911053,0.000010372585,0.0005975947,0.0006584562,0.00010993672,0.0002220127],"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":[0.000015718457,0.0020431217,0.0073434073,0.0001764878,0.00003381917,0.00002442688,0.0057742414,0.0003567566,0.012828012,0.016120968,0.23327443,0.7220086],"study_design_scores_gemma":[0.0026530866,0.0007319456,0.040321607,0.00031102932,0.000011672222,0.00009073771,0.0002724743,0.8757498,0.015382966,0.023647025,0.03844968,0.0023779608],"about_ca_topic_score_codex":0.00066003,"about_ca_topic_score_gemma":0.000057583256,"teacher_disagreement_score":0.87539303,"about_ca_system_score_codex":0.00035443035,"about_ca_system_score_gemma":0.000027404307,"threshold_uncertainty_score":0.55220467},"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":"W2029712404","doi":"10.1145/2494266.2494318","title":"Evaluating glyph binarizations based on their properties","year":2013,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":9,"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":"Azrieli Foundation; Tel Aviv University","keywords":"Glyph (data visualization); Ground truth; Computer science; Enhanced Data Rates for GSM Evolution; Consistency (knowledge bases); Artificial intelligence; Noise (video); Binary number; Pattern recognition (psychology); Data mining; Image (mathematics); Visualization; Mathematics","score_opus":0.07087540454819835,"score_gpt":0.2915898430936089,"score_spread":0.22071443854541056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2029712404","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":[0.016090546,0.000008617186,0.9410952,0.003580219,0.00006744191,0.00051771064,6.921549e-7,0.0010197173,0.03761987],"genre_scores_gemma":[0.8179349,0.000001006384,0.17905316,0.002037085,0.00001879987,0.00024331608,0.000003178028,0.00000717653,0.0007014277],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991466,0.00008507424,0.00015439387,0.00023756111,0.00020988777,0.00016650891],"domain_scores_gemma":[0.999208,0.00007584606,0.000040930285,0.0004087769,0.00021340071,0.000053048003],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021546506,0.00009991321,0.000080772625,0.00012819853,0.00014311289,0.0002714105,0.00043636496,0.000038212507,0.00071171846],"category_scores_gemma":[0.0001021458,0.000066426386,0.00003831062,0.00029193278,0.00002780661,0.00047688486,0.000082111335,0.00007443118,0.0005241174],"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":[0.000003555178,0.0003411095,0.00031616125,0.000030120758,0.000013973356,0.0000015304848,0.00067319046,0.00054858514,0.09058894,0.028998205,0.0113489395,0.8671357],"study_design_scores_gemma":[0.00012171159,0.00020782492,0.00044754543,0.00004295904,0.0000012094921,0.0000014462742,0.000024653953,0.8466698,0.14575088,0.0063162562,0.0002792217,0.00013651975],"about_ca_topic_score_codex":0.00005116522,"about_ca_topic_score_gemma":0.0000020031903,"teacher_disagreement_score":0.86699915,"about_ca_system_score_codex":0.000024637804,"about_ca_system_score_gemma":0.000063229294,"threshold_uncertainty_score":0.7792818},"labels":[],"label_agreement":null},{"id":"W2030402611","doi":"10.1109/ispa.2013.6703737","title":"Ancient degraded document image binarization based on texture features","year":2013,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"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; Artificial intelligence; Texture (cosmology); Historical document; Pattern recognition (psychology); Image (mathematics); Image texture; Set (abstract data type); Computer vision; National library; Matrix (chemical analysis); Image segmentation","score_opus":0.007082616623175842,"score_gpt":0.23216351246172753,"score_spread":0.2250808958385517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2030402611","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":[0.0021611655,0.00002691943,0.97258687,0.005673786,0.00012728204,0.0005417602,0.000001075992,0.0009719819,0.017909158],"genre_scores_gemma":[0.778018,0.000004130494,0.2136484,0.006689686,0.0000338514,0.00017147609,0.000012059656,0.000011106594,0.0014112893],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998786,0.000067162626,0.00016541265,0.0003749234,0.00035646494,0.00025008203],"domain_scores_gemma":[0.9991138,0.000043330256,0.00006232316,0.00049893546,0.0001712502,0.00011036502],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014857335,0.00015431001,0.00011011673,0.00019839713,0.00010514327,0.0004693395,0.00050278346,0.00008171676,0.0004949111],"category_scores_gemma":[0.00004086112,0.00011599626,0.0000616239,0.00040424592,0.000030455622,0.0006515915,0.00008514373,0.00013256882,0.0006027769],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000978731,0.00053516356,0.0003133214,0.00004781292,0.000017094353,0.000023738443,0.00042652394,0.0000373378,0.056644473,0.06529154,0.26072466,0.61592853],"study_design_scores_gemma":[0.0012592974,0.00093900255,0.032958,0.00017363978,0.000011704712,0.00002445211,0.000054062275,0.13664731,0.776211,0.03779704,0.012892964,0.0010314877],"about_ca_topic_score_codex":0.00005776592,"about_ca_topic_score_gemma":0.0000037947957,"teacher_disagreement_score":0.77585685,"about_ca_system_score_codex":0.00006689048,"about_ca_system_score_gemma":0.000040710893,"threshold_uncertainty_score":0.7747678},"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":"W2032116850","doi":"10.1109/icpr.2010.933","title":"On-Line Signature Verification Using 1-D Velocity-Based Directional Analysis","year":2010,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Signature (topology); Trajectory; Curvature; Computer science; Line (geometry); Support vector machine; Boundary (topology); Basis (linear algebra); Line segment; Feature (linguistics); Flexibility (engineering); Algorithm; Artificial intelligence; Pattern recognition (psychology); Mathematics; Geometry; Mathematical analysis; Physics","score_opus":0.023433061458722357,"score_gpt":0.2884764498404503,"score_spread":0.2650433883817279,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2032116850","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":[0.032209575,0.0000027471808,0.9644145,0.00052754866,0.00017653292,0.00008789073,0.0000046085934,0.00055515015,0.0020214496],"genre_scores_gemma":[0.6150936,4.0812006e-7,0.3841294,0.00061076623,0.000041927287,0.000009775047,0.000018087916,0.000004148025,0.000091879636],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99905676,0.000043019576,0.00015913772,0.0003346958,0.0002725175,0.00013386301],"domain_scores_gemma":[0.9991112,0.00012062939,0.00007263782,0.00042904596,0.0001992293,0.00006728728],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002776917,0.00010352572,0.000122053454,0.0004144981,0.00013482296,0.000118202704,0.00036114507,0.000119538825,0.00036706546],"category_scores_gemma":[0.00007123658,0.0000929754,0.00011570896,0.0012946922,0.000032526663,0.00022081954,0.000031659427,0.0002773648,0.000043339707],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004389813,0.0010780072,0.0017632346,0.000024796811,0.0005051272,0.000018599818,0.00017175832,0.007414186,0.5926295,0.20105408,0.00373919,0.19155762],"study_design_scores_gemma":[0.00014164145,0.000045683228,0.00172633,0.0000046112377,0.00004408675,0.000002642444,0.0000015190109,0.6908325,0.29936314,0.0066827894,0.0009610075,0.00019405971],"about_ca_topic_score_codex":0.000034593762,"about_ca_topic_score_gemma":0.000041144925,"teacher_disagreement_score":0.68341833,"about_ca_system_score_codex":0.000031138512,"about_ca_system_score_gemma":0.00007215876,"threshold_uncertainty_score":0.40191093},"labels":[],"label_agreement":null},{"id":"W2032203728","doi":"10.1109/icdar.2007.4377102","title":"Aspects of Mathematical Expression Analysis in Arabic Handwriting","year":2007,"lang":"en","type":"article","venue":"Proceedings of the International Conference on Document Analysis and Recognition","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Arabic; Handwriting; Computer science; Handwriting recognition; Context (archaeology); Expression (computer science); Natural language processing; Artificial intelligence; Linguistics; Feature extraction; Programming language","score_opus":0.024144143333013676,"score_gpt":0.28534212896288397,"score_spread":0.2611979856298703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2032203728","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":[0.91949034,0.0000123185955,0.05382343,0.00052980933,0.000036013083,0.00016880433,0.00000492341,0.000031889307,0.025902472],"genre_scores_gemma":[0.99123585,0.00005943174,0.008563786,0.000039944094,0.000018248338,0.000011614305,0.00000676718,0.0000032373518,0.00006113151],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99842554,0.000013548106,0.0005735632,0.00029371446,0.00055711105,0.00013653474],"domain_scores_gemma":[0.99872017,0.00009794519,0.0004883797,0.000101939535,0.00054894283,0.00004265348],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001059725,0.000118904754,0.00031702436,0.0012642806,0.00004323574,0.00011946875,0.0005234765,0.00006479115,0.00014463461],"category_scores_gemma":[0.00012894248,0.00008573708,0.0002343402,0.0015703116,0.00006508999,0.0004205212,0.00017569252,0.000128177,0.0000021647159],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019249154,0.0009932141,0.091363244,0.00020988107,0.0034683135,0.000004739339,0.00207506,0.00002115733,0.28610817,0.46324265,0.00005540274,0.15226567],"study_design_scores_gemma":[0.00029160513,0.00006963567,0.020687932,0.00037006143,0.00044893485,0.000002416419,0.00032796603,0.011823389,0.7126258,0.25319394,0.000003156755,0.00015511841],"about_ca_topic_score_codex":0.000032826505,"about_ca_topic_score_gemma":0.000039007857,"teacher_disagreement_score":0.42651767,"about_ca_system_score_codex":0.00004447185,"about_ca_system_score_gemma":0.00001398975,"threshold_uncertainty_score":0.34962568},"labels":[],"label_agreement":null},{"id":"W2032227036","doi":"10.1145/502187.502211","title":"Extraction of text areas in printed document images","year":2001,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"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":"","keywords":"Computer science; Grayscale; Relevance (law); Heuristic; Artificial intelligence; Texture (cosmology); Information retrieval; Historical document; Pattern recognition (psychology); Image texture; Image (mathematics); Image segmentation","score_opus":0.013972864250300365,"score_gpt":0.28539172061515583,"score_spread":0.27141885636485547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2032227036","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":[0.06286649,0.000024560264,0.88504744,0.00072505453,0.00005433153,0.00018482943,3.0318802e-7,0.0002888247,0.05080818],"genre_scores_gemma":[0.9299114,0.00007714816,0.06869326,0.000090645604,0.000008965404,0.000021219648,7.003567e-7,0.000003236814,0.0011934415],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992966,0.00003904647,0.00021816087,0.00017909537,0.00014496571,0.00012214946],"domain_scores_gemma":[0.99953306,0.000058189053,0.000063519445,0.00023974151,0.000073356205,0.000032142405],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021834773,0.00006509085,0.00009495744,0.00018541193,0.000013426107,0.000037696762,0.00025860398,0.00003515874,0.0003183735],"category_scores_gemma":[0.000040366536,0.000057726756,0.000031287378,0.00032945024,0.000019502026,0.000517099,0.00007751062,0.00007085472,0.00005426177],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014707256,0.0003298712,0.008231701,0.0000183894,0.000009942101,0.00005217979,0.00023731578,0.0000049351015,0.045992397,0.020401224,0.0021818785,0.92252547],"study_design_scores_gemma":[0.00040579247,0.00014150942,0.077810116,0.00011851181,0.0000028516554,0.000121495956,0.000075636075,0.0020149879,0.88555783,0.027123436,0.006378682,0.00024913877],"about_ca_topic_score_codex":0.00016861758,"about_ca_topic_score_gemma":0.000035051227,"teacher_disagreement_score":0.9222763,"about_ca_system_score_codex":0.0000391227,"about_ca_system_score_gemma":0.000019202858,"threshold_uncertainty_score":0.34859666},"labels":[],"label_agreement":null},{"id":"W2033947775","doi":"10.1109/wescan.1993.270572","title":"Garbage collection software integrated with the system swapper in a virtual memory system","year":2002,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Garbage; Garbage collection; Computer science; Lisp; Manual memory management; Modular design; Table (database); Hash table; Operating system; Software; Virtual memory; Database; Memory management; Programming language; Hash function","score_opus":0.010461911833280045,"score_gpt":0.19104870113556421,"score_spread":0.18058678930228417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2033947775","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":[0.016137298,0.000046944173,0.9593982,0.00037498717,0.00013825406,0.0006674895,0.0000022146553,0.0025383276,0.02069629],"genre_scores_gemma":[0.98043996,0.000003345354,0.014957048,0.00019260397,0.000027175487,0.0002290322,0.0000015345046,0.000015737613,0.0041335877],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99856144,0.00023036671,0.00026100705,0.00037351614,0.0003148266,0.00025881233],"domain_scores_gemma":[0.99910307,0.00012029515,0.000087419714,0.00047338608,0.00015570427,0.000060152335],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041261996,0.00017731467,0.00020557483,0.00023244422,0.00018690941,0.00021223901,0.00058077415,0.00009424043,0.00005865913],"category_scores_gemma":[0.000021678965,0.00010271228,0.00004537201,0.0012285704,0.00005040085,0.0003788898,0.00009016149,0.0002320381,0.00019059391],"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":[0.00025131745,0.0013228134,0.0032509167,0.0014895789,0.0004391771,0.001711775,0.028507808,0.00060617266,0.0036463127,0.16470796,0.28235254,0.5117136],"study_design_scores_gemma":[0.0029694627,0.001509897,0.0008447091,0.0023479448,0.000045595232,0.0020221171,0.02329518,0.9228281,0.03841861,0.0000710494,0.0041726558,0.0014747268],"about_ca_topic_score_codex":0.00023501595,"about_ca_topic_score_gemma":0.00027217314,"teacher_disagreement_score":0.96430266,"about_ca_system_score_codex":0.00033811195,"about_ca_system_score_gemma":0.000040179875,"threshold_uncertainty_score":0.4188485},"labels":[],"label_agreement":null},{"id":"W2034249906","doi":"10.1145/1815330.1815332","title":"IBN SINA","year":2010,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":42,"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; École de Technologie Supérieure; EcoSynthetix (Canada)","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Support vector machine; Preprocessor; Artificial intelligence; Feature extraction; Class (philosophy); Pattern recognition (psychology); Process (computing); Set (abstract data type); Data mining; Machine learning","score_opus":0.009366595314929501,"score_gpt":0.24436113237064913,"score_spread":0.23499453705571963,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2034249906","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":[0.009597527,0.000002282477,0.82368404,0.0012454967,0.00022024396,0.000055132026,2.273481e-7,0.0010216518,0.1641734],"genre_scores_gemma":[0.5970229,0.0000013543034,0.4005826,0.0007379112,0.000039358016,0.000008659724,3.6717753e-7,0.0000028020124,0.0016040263],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99957013,0.0000084277435,0.000071290975,0.00014580895,0.00009379482,0.00011055492],"domain_scores_gemma":[0.99952745,0.000024954425,0.00001561161,0.00033104743,0.000048750633,0.000052169667],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011998293,0.000046480596,0.0000446921,0.000050985094,0.000038584763,0.000094004725,0.00046113957,0.000040311857,0.00039577295],"category_scores_gemma":[0.000025358166,0.000038623755,0.000025028376,0.00013253427,0.000020761077,0.0002975179,0.000101770784,0.000118682074,0.00060328294],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[2.7841372e-7,0.000034941266,0.00019017982,0.000001815406,0.0000019980291,0.000006738262,0.000053024323,1.4934397e-8,0.043511465,0.42262074,0.014535159,0.5190436],"study_design_scores_gemma":[0.00014815421,0.00006129774,0.002081842,0.0000043073965,0.0000013961186,0.00007348277,0.00000513876,0.003447975,0.73020554,0.1214624,0.14225332,0.0002551528],"about_ca_topic_score_codex":0.000014588156,"about_ca_topic_score_gemma":0.000022576256,"teacher_disagreement_score":0.6866941,"about_ca_system_score_codex":0.0000029854725,"about_ca_system_score_gemma":0.000017508552,"threshold_uncertainty_score":0.77541834},"labels":[],"label_agreement":null},{"id":"W2037378121","doi":"10.1109/isccsp.2012.6217760","title":"A novel segmentation technique for splitting a typed Persian text to sub-words","year":2012,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Persian; Computer science; Natural language processing; Segmentation; Component (thermodynamics); Artificial intelligence; Character (mathematics); Word (group theory); Text segmentation; Text recognition; Speech recognition; Linguistics; Mathematics; Image (mathematics)","score_opus":0.027183132473885572,"score_gpt":0.29423794349684723,"score_spread":0.26705481102296164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2037378121","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":[0.0019390051,0.000010975772,0.99110425,0.00076604297,0.000105295156,0.0011817286,0.000004529676,0.0004713338,0.004416836],"genre_scores_gemma":[0.329051,0.0000010795239,0.6691231,0.00083992997,0.00008458199,0.0005842687,0.000004564599,0.000011541628,0.000299932],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99900365,0.000022484837,0.00020073487,0.0002553112,0.00015729442,0.0003605076],"domain_scores_gemma":[0.9993105,0.00008068045,0.00005963953,0.00027554756,0.00011605599,0.0001575615],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061378104,0.00012336354,0.0001176415,0.00018994027,0.00010691646,0.00009798572,0.0003495995,0.000072770796,0.00003865465],"category_scores_gemma":[0.00007760716,0.000116704796,0.00006680509,0.000380287,0.000012294248,0.0006327063,0.00013083908,0.000068976085,0.00009392083],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005339131,0.00009248109,0.00014648456,0.000018981611,0.0000075580656,2.1008624e-7,0.0009949969,2.8032363e-7,0.9293747,0.013931905,0.0018024918,0.05362457],"study_design_scores_gemma":[0.00019955127,0.00012311344,0.00040069243,0.000030754418,0.000005907759,0.000025739606,0.00017023226,0.00039679502,0.995479,0.0008274736,0.002113939,0.00022679746],"about_ca_topic_score_codex":0.000026670452,"about_ca_topic_score_gemma":0.000007833211,"teacher_disagreement_score":0.327112,"about_ca_system_score_codex":0.00008563743,"about_ca_system_score_gemma":0.000033863027,"threshold_uncertainty_score":0.47590834},"labels":[],"label_agreement":null},{"id":"W2040412378","doi":"10.1109/inmic.2008.4777782","title":"Segmentation of Iranian bank checks","year":2008,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Component (thermodynamics); Segmentation; Computer science; Set (abstract data type); Image segmentation; Data mining; Artificial intelligence; Algorithm","score_opus":0.02461787120115904,"score_gpt":0.25413953193820904,"score_spread":0.22952166073705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2040412378","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":[0.030976133,0.000013441163,0.9194764,0.00023431345,0.00004017951,0.00009943688,7.0335625e-7,0.00029837835,0.04886101],"genre_scores_gemma":[0.68876517,0.000018655619,0.30954832,0.00022328347,0.000010760296,0.000008320425,0.0000015485057,0.0000026869334,0.0014212689],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99950045,0.000019188277,0.00013939381,0.00012028603,0.00014092762,0.00007977735],"domain_scores_gemma":[0.99965423,0.000017737333,0.00004524673,0.00018582621,0.00006709891,0.000029829383],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008008011,0.000047271125,0.00006997384,0.00007268542,0.000037251568,0.000010079862,0.0002396925,0.00002728461,0.00015219557],"category_scores_gemma":[0.000008835,0.000042571897,0.00003177162,0.00018297508,0.000029416888,0.0002898419,0.00004661431,0.00003289783,0.000060432354],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000142427,0.00056012784,0.00956659,0.00010528992,0.00006184919,0.00007539033,0.008156301,0.000003048488,0.20751585,0.098258644,0.055427555,0.6202551],"study_design_scores_gemma":[0.00020046766,0.000051093488,0.0035512485,0.000009843614,0.0000014670068,0.000028451286,0.000017871987,0.00061682804,0.99040115,0.0035676162,0.0014556542,0.0000983051],"about_ca_topic_score_codex":0.000016639944,"about_ca_topic_score_gemma":0.000004470695,"teacher_disagreement_score":0.7828853,"about_ca_system_score_codex":0.000011089679,"about_ca_system_score_gemma":0.000022315924,"threshold_uncertainty_score":0.17360315},"labels":[],"label_agreement":null},{"id":"W2045220951","doi":"10.1007/s13735-012-0004-6","title":"Optical music recognition: state-of-the-art and open issues","year":2012,"lang":"en","type":"article","venue":"International Journal of Multimedia Information Retrieval","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":248,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Fundação para a Ciência e a Tecnologia; University of Texas at Austin","keywords":"Computer science; Musical; Optical character recognition; Scheme (mathematics); State (computer science); Computer music; Character (mathematics); Artificial intelligence; Speech recognition; Natural language processing; Multimedia; Image (mathematics); Programming language; Visual arts","score_opus":0.028366212247756005,"score_gpt":0.29742305074465025,"score_spread":0.26905683849689427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2045220951","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":[0.3875933,0.00043216182,0.578747,0.012618648,0.009718899,0.0011914183,0.00010682866,0.00013190319,0.009459846],"genre_scores_gemma":[0.7537103,0.00022576236,0.24425796,0.0012405753,0.00040666037,0.000006140411,0.000019608658,0.000008614651,0.00012436834],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99813366,0.000065508255,0.0007792226,0.000059530772,0.0008172241,0.00014485283],"domain_scores_gemma":[0.9974514,0.00018654985,0.0007498234,0.00014339067,0.0013370978,0.0001317224],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011025413,0.00010047754,0.00017755294,0.000260088,0.00004594452,0.0002931209,0.001343465,0.0000574006,0.00010916093],"category_scores_gemma":[0.000801734,0.00007541805,0.00008435958,0.00021463739,0.000093457194,0.006805247,0.00051517977,0.00021885565,0.00007922298],"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":[0.00017439085,0.00015824352,0.0018572485,0.000019188177,0.00013066884,0.000004077449,0.0038664767,0.0000050618733,0.001004745,0.0011427075,0.0098225465,0.9818146],"study_design_scores_gemma":[0.006149016,0.00069895014,0.054390535,0.00081189704,0.000076990866,0.0022912675,0.00044106573,0.011352483,0.70341843,0.01460956,0.20496163,0.0007981792],"about_ca_topic_score_codex":0.0000044733765,"about_ca_topic_score_gemma":7.985251e-7,"teacher_disagreement_score":0.98101646,"about_ca_system_score_codex":0.00006435479,"about_ca_system_score_gemma":0.00010757476,"threshold_uncertainty_score":0.493364},"labels":[],"label_agreement":null},{"id":"W2047149517","doi":"10.1109/isspa.2012.6310446","title":"Off-line Uyghur signature recognition based on modified grid information features","year":2012,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"National Natural Science Foundation of China","keywords":"Handwriting recognition; Pattern recognition (psychology); Handwriting; Computer science; Artificial intelligence; Normalization (sociology); Signature recognition; Classifier (UML); Feature extraction; Naive Bayes classifier; Preprocessor; Signature (topology); Character recognition; Mathematics; Support vector machine","score_opus":0.020583232116077415,"score_gpt":0.24925669935152814,"score_spread":0.22867346723545073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2047149517","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":[0.0028855456,0.00005914687,0.9260323,0.0017108148,0.00063258293,0.00049450604,0.000033208955,0.0015921063,0.06655977],"genre_scores_gemma":[0.896101,0.000021830714,0.09393055,0.008908362,0.00032661817,0.00009367457,0.00029761138,0.000012016591,0.00030831463],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986811,0.000090269816,0.0002805459,0.00018752705,0.00041269296,0.00034786583],"domain_scores_gemma":[0.99896026,0.00012187931,0.00013069538,0.00041053956,0.00022223579,0.00015440593],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046814105,0.00019375175,0.00014814598,0.0004659846,0.00011441287,0.00019408036,0.00040589986,0.00020886143,0.00017480568],"category_scores_gemma":[0.00012353329,0.00016080952,0.00008642626,0.00053225335,0.000021990245,0.0028346973,0.00006913688,0.00030946554,0.00056418043],"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":[0.000044378947,0.0002501328,0.000048958103,0.00003569479,0.000012013723,0.0000016432211,0.00030056204,0.00008718236,0.00074546726,0.01120702,0.050457384,0.93680954],"study_design_scores_gemma":[0.0027869418,0.0010857761,0.0065455865,0.00031798988,0.000043580978,0.00006607006,0.00009378969,0.1757871,0.7328357,0.015882468,0.06266525,0.0018897261],"about_ca_topic_score_codex":0.000011947589,"about_ca_topic_score_gemma":0.0000025016463,"teacher_disagreement_score":0.93491983,"about_ca_system_score_codex":0.000059429844,"about_ca_system_score_gemma":0.000039564984,"threshold_uncertainty_score":0.72515863},"labels":[],"label_agreement":null},{"id":"W2050467853","doi":"10.1145/2637002.2637025","title":"A qualitative exploration of secondary assessor relevance judging behavior","year":2014,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; King Saud bin Abdulaziz University for Health Science; University of Waterloo; King Abdulaziz University; King Saud University","keywords":"Relevance (law); Think aloud protocol; Certainty; Psychology; Quality (philosophy); Test (biology); Information retrieval; Computer science; Mathematics; Epistemology; Human–computer interaction","score_opus":0.059380010204380954,"score_gpt":0.3608155720620532,"score_spread":0.3014355618576723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2050467853","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":[0.021103982,0.000011545068,0.968123,0.0003654961,0.000073831856,0.00016448996,0.0000014791049,0.00035449344,0.009801677],"genre_scores_gemma":[0.70035666,0.0000046521513,0.29914784,0.00015390887,0.000015211263,0.00008368246,0.0000030109363,0.0000053801914,0.0002296513],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99890155,0.0002146493,0.00030921656,0.00023685826,0.00020985285,0.00012790474],"domain_scores_gemma":[0.99894464,0.00031813508,0.00016405506,0.00032031105,0.00021119404,0.00004168114],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00072012184,0.000086188986,0.00015949157,0.00011870558,0.000047352158,0.00005443428,0.00033993123,0.000045815428,0.000058766833],"category_scores_gemma":[0.00021307317,0.00008068675,0.000045892368,0.00024222177,0.000040424336,0.0017414002,0.00008706828,0.00010184481,0.000040290855],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000029059554,0.00012777229,0.00007453658,0.00003362802,0.000007171847,0.0000013559485,0.01019782,0.0000013946205,0.020227687,0.17793484,0.0008633123,0.7905276],"study_design_scores_gemma":[0.00042490385,0.0003979681,0.00076146267,0.00008506195,0.000011909366,0.000006203567,0.0018279608,0.008573955,0.8705108,0.114690475,0.002344798,0.00036446334],"about_ca_topic_score_codex":0.000014714048,"about_ca_topic_score_gemma":0.0000108844,"teacher_disagreement_score":0.85028315,"about_ca_system_score_codex":0.000018748056,"about_ca_system_score_gemma":0.00003869812,"threshold_uncertainty_score":0.32903102},"labels":[],"label_agreement":null},{"id":"W2051284700","doi":"10.1016/j.patcog.2014.04.025","title":"Arabic word descriptor for handwritten word indexing and lexicon reduction","year":2014,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":18,"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":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada","keywords":"Lexicon; Computer science; Word (group theory); Natural language processing; Artificial intelligence; Search engine indexing; Speech recognition; Context (archaeology); Reduction (mathematics); Word recognition; Arabic; Pattern recognition (psychology); Mathematics; Linguistics; Reading (process)","score_opus":0.0314805224316948,"score_gpt":0.2533956168225437,"score_spread":0.2219150943908489,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2051284700","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":[0.15589476,0.000049495673,0.84128475,0.0008198896,0.00045842933,0.000555402,0.00001287975,0.00054643775,0.00037798221],"genre_scores_gemma":[0.93029666,0.00006123285,0.067796186,0.00066612853,0.00046140232,0.000445827,0.00009041716,0.0000345269,0.00014763373],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9982663,0.00014438045,0.00036936492,0.00063301274,0.00021356555,0.0003733848],"domain_scores_gemma":[0.99898344,0.00014119777,0.00019192537,0.00031330797,0.00023582378,0.00013429341],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067467836,0.00023209683,0.0002450842,0.00028778415,0.00023895715,0.0003612021,0.0002796736,0.00016041266,0.000034283326],"category_scores_gemma":[0.00013054248,0.0002426869,0.00009023956,0.00022994116,0.00006295481,0.0010157324,0.00010072963,0.00019006807,0.00007567386],"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":[0.00001308819,0.000039519582,0.0002951688,0.00005987851,0.000012732501,7.316002e-7,0.00023001974,1.8517672e-7,0.0048491796,0.0000993092,0.00053279405,0.9938674],"study_design_scores_gemma":[0.006160794,0.0016429572,0.01643974,0.0020198838,0.0001961068,0.00061671506,0.00040559022,0.05470283,0.5308254,0.36216927,0.021641169,0.0031795625],"about_ca_topic_score_codex":0.000037698213,"about_ca_topic_score_gemma":0.000019735508,"teacher_disagreement_score":0.99068785,"about_ca_system_score_codex":0.000060884973,"about_ca_system_score_gemma":0.000025130485,"threshold_uncertainty_score":0.98964846},"labels":[],"label_agreement":null},{"id":"W2052918223","doi":"10.1045/march2006-choudhury","title":"Document Recognition for a Million Books","year":2006,"lang":"en","type":"article","venue":"D-Lib Magazine","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; World Wide Web; Information retrieval; Scalability; Process (computing); Digital library; Order (exchange); Database; Linguistics","score_opus":0.01687287626591295,"score_gpt":0.2506368321123671,"score_spread":0.23376395584645415,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2052918223","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":[0.006921027,0.00011968502,0.9676587,0.0014295308,0.00024630144,0.0007534119,0.000024807385,0.0010122585,0.021834252],"genre_scores_gemma":[0.24729921,0.00006691457,0.73672396,0.0021058721,0.00073757855,0.0011385166,0.00043487386,0.0000637521,0.011429304],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99878806,0.000038495047,0.00029689982,0.00037986122,0.00020385534,0.0002928148],"domain_scores_gemma":[0.9992473,0.00007668415,0.00010446502,0.00033073677,0.0001811124,0.00005971486],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029099776,0.00015407753,0.00015558723,0.00017609877,0.00009772711,0.00017543633,0.0003399594,0.00007605446,0.00007227171],"category_scores_gemma":[0.000028985078,0.00015065716,0.000102676655,0.0002183741,0.000028381191,0.0004915275,0.000085259664,0.00007970831,0.00046971109],"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":[0.000032174532,0.00020332243,0.00006192093,0.000074798656,0.000017969422,0.000019896555,0.00007491382,0.0000022481954,0.023646213,0.02598008,0.18116127,0.7687252],"study_design_scores_gemma":[0.0012843462,0.00037211183,0.0011446165,0.00009139849,0.000020723117,0.000051481118,0.0000039422694,0.0023552468,0.22487743,0.4321438,0.3371295,0.0005253881],"about_ca_topic_score_codex":0.00002168072,"about_ca_topic_score_gemma":0.000021017524,"teacher_disagreement_score":0.7681998,"about_ca_system_score_codex":0.00004386431,"about_ca_system_score_gemma":0.000028072323,"threshold_uncertainty_score":0.61436206},"labels":[],"label_agreement":null},{"id":"W2053642301","doi":"10.1016/j.patcog.2014.09.025","title":"Tensor representation learning based image patch analysis for text identification and recognition","year":2014,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":21,"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":"Fundamental Research Funds for the Central Universities; Guangdong Academy of Sciences; National Natural Science Foundation of China","keywords":"Artificial intelligence; Pattern recognition (psychology); Subspace topology; Computer science; Robustness (evolution); Tensor (intrinsic definition); Arabic numerals; Representation (politics); Classifier (UML); Identification (biology); Mathematics","score_opus":0.03298347598447665,"score_gpt":0.28515633749623703,"score_spread":0.2521728615117604,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2053642301","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":[0.117793225,0.000009521232,0.8800585,0.0006632334,0.00010026949,0.0005992942,0.000048335893,0.00053381233,0.00019379467],"genre_scores_gemma":[0.9147852,0.000035036832,0.0822547,0.00046294078,0.00012713269,0.00060943724,0.0016326043,0.000028662242,0.00006425802],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976531,0.0004052869,0.00054383214,0.00080214796,0.00030054702,0.00029508438],"domain_scores_gemma":[0.997901,0.0005256207,0.00042334697,0.0003718546,0.00066807616,0.00011006427],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001120961,0.0002205216,0.00029362092,0.00069886836,0.00028271604,0.0005035656,0.00023020263,0.00014068953,0.0000909499],"category_scores_gemma":[0.00056296587,0.0002425587,0.00019277987,0.0008296295,0.00005164611,0.001064014,0.000056108114,0.00017616453,0.0001767377],"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":[0.000014570184,0.00006664698,0.0065428154,0.000066575936,0.00006710219,9.3970306e-7,0.00017552811,0.000008123784,0.0073973686,0.0000063327425,0.00010295525,0.98555106],"study_design_scores_gemma":[0.0016810142,0.00040366253,0.06527878,0.00015096283,0.0006123944,0.000016332264,0.00013930902,0.6367313,0.26793486,0.025675267,0.00048411224,0.00089195743],"about_ca_topic_score_codex":0.00012764486,"about_ca_topic_score_gemma":0.000052592484,"teacher_disagreement_score":0.9846591,"about_ca_system_score_codex":0.000050759176,"about_ca_system_score_gemma":0.000016599897,"threshold_uncertainty_score":0.9891257},"labels":[],"label_agreement":null},{"id":"W2053735135","doi":"10.1142/s0218001404003307","title":"WORD-LEVEL OPTICAL FONT RECOGNITION USING TYPOGRAPHICAL FEATURES","year":2004,"lang":"en","type":"article","venue":"International Journal of Pattern Recognition and Artificial Intelligence","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Font; Typeface; Computer science; Natural language processing; Optical character recognition; Artificial intelligence; Word (group theory); Point (geometry); Classifier (UML); Speech recognition; Linguistics; Mathematics","score_opus":0.12811484785667576,"score_gpt":0.33641536239971376,"score_spread":0.208300514543038,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2053735135","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":[0.24651198,0.00006363526,0.7503678,0.0019020626,0.0008549552,0.00010083786,0.000031113676,0.000056559948,0.00011106414],"genre_scores_gemma":[0.896544,0.00023361134,0.10183178,0.00084857154,0.00050266954,0.0000058575024,0.000016747921,0.000013835011,0.0000029667028],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99786776,0.00008664605,0.0008352812,0.00030868532,0.00066201837,0.00023962569],"domain_scores_gemma":[0.99788123,0.00014228179,0.0004273947,0.00013086847,0.0012204197,0.00019780647],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000565376,0.00020286856,0.00023911732,0.0006022096,0.00010353334,0.00045076438,0.0006362684,0.00014481842,0.00010751181],"category_scores_gemma":[0.00023173708,0.00018984856,0.00018852862,0.00027586168,0.00015287049,0.0009769867,0.00013911788,0.00044140188,0.00008167855],"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":[0.000052179865,0.00022110327,0.000047706577,0.0000065927347,0.0000647527,0.00021267912,0.00033185366,0.00001941681,0.004007698,0.00096123654,0.000018682616,0.9940561],"study_design_scores_gemma":[0.00041279927,0.00046578675,0.001848693,0.0009333385,0.000058236197,0.0046303584,0.00049845537,0.0017925992,0.33859602,0.6500664,0.00010166787,0.00059567555],"about_ca_topic_score_codex":0.000059428658,"about_ca_topic_score_gemma":0.000046916808,"teacher_disagreement_score":0.9934604,"about_ca_system_score_codex":0.00010940803,"about_ca_system_score_gemma":0.00010199721,"threshold_uncertainty_score":0.77418},"labels":[],"label_agreement":null},{"id":"W2054716638","doi":"10.1109/ccece.2014.6901136","title":"Variation of grip force profile during signature writing","year":2014,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Holland Bloorview Kids Rehabilitation Hospital","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Biometrics; Signature (topology); Linear discriminant analysis; Nonparametric statistics; Classifier (UML); Pattern recognition (psychology); Computer science; Artificial intelligence; Nonlinear system; Variation (astronomy); Speech recognition; Mathematics; Statistics; Physics","score_opus":0.007128317047552893,"score_gpt":0.22238023533125387,"score_spread":0.21525191828370097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054716638","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":[0.030852081,0.000008026688,0.94471884,0.0001673719,0.00006845703,0.00013931398,8.603518e-7,0.0004575653,0.023587491],"genre_scores_gemma":[0.80103064,0.0000014371238,0.19823368,0.00009345335,0.00006655953,0.00001502193,0.0000018266296,0.000004722544,0.00055265933],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999244,0.000050671,0.0002024914,0.0001947931,0.00017059827,0.0001374636],"domain_scores_gemma":[0.9994159,0.000070403716,0.00010040177,0.00025027897,0.00012934345,0.000033673645],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031909315,0.000070200455,0.00010111149,0.00009055231,0.000058191443,0.00004904857,0.00032662312,0.00006838445,0.00006971059],"category_scores_gemma":[0.00007466174,0.00006376334,0.00003799477,0.00021213705,0.000011904657,0.00041737678,0.000108737055,0.000091501504,0.00002099415],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000061212904,0.000093178984,0.0005443188,0.00021536322,0.000018937139,0.0000024516094,0.00088685995,0.00001517761,0.5599346,0.28800592,0.00068041513,0.14959666],"study_design_scores_gemma":[0.00029037404,0.00008749752,0.015183135,0.00008377967,0.0000039409206,0.00001192399,0.000017136183,0.038025167,0.9265638,0.019321008,0.0002113015,0.00020091522],"about_ca_topic_score_codex":0.000010451254,"about_ca_topic_score_gemma":0.0000016896824,"teacher_disagreement_score":0.77017856,"about_ca_system_score_codex":0.000014506854,"about_ca_system_score_gemma":0.0000140107295,"threshold_uncertainty_score":0.26001936},"labels":[],"label_agreement":null},{"id":"W2054919485","doi":"10.1117/12.586046","title":"<title>New approach for segmentation and recognition of handwritten numeral strings</title>","year":2005,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Segmentation; Computer science; Numeral system; Pattern recognition (psychology); NIST; Artificial intelligence; Matching (statistics); Feature extraction; Feature (linguistics); Image segmentation; Representation (politics); Population; Speech recognition; Mathematics","score_opus":0.016539109148548423,"score_gpt":0.23860544883642168,"score_spread":0.22206633968787326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054919485","genre_codex":"empirical","genre_gemma":"methods","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":[0.91696846,0.00024396107,0.046344955,0.0018959531,0.00022980515,0.0011464179,0.000084404535,0.00025349596,0.03283253],"genre_scores_gemma":[0.05215043,0.00012972645,0.94619185,0.00008875412,0.00035235885,0.000106552805,0.000020354073,0.0000294982,0.00093050033],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989585,2.0590988e-8,0.0003384868,0.00023767009,0.00029844328,0.00016682247],"domain_scores_gemma":[0.99900377,0.000053409018,0.00020004355,0.000038752234,0.00064074027,0.00006329886],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003126586,0.00014052604,0.00019220257,0.00008781695,0.00003617521,0.000073732255,0.00041256938,0.000108664266,0.00003311676],"category_scores_gemma":[0.00013210415,0.00012699502,0.00020186983,0.00015831308,0.00006869387,0.00043446902,0.00008364695,0.00010305914,0.000005148913],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003925863,0.0001424543,0.00003496558,0.0005210954,0.00024233156,3.183e-8,0.0002836994,0.000012439522,0.40015838,0.48172173,0.042199746,0.07464389],"study_design_scores_gemma":[0.002217504,0.00052781624,0.000221226,0.00047268273,0.00020183445,0.000036748344,0.00028048074,0.1556376,0.7829827,0.01886087,0.037823714,0.00073682447],"about_ca_topic_score_codex":0.000001862424,"about_ca_topic_score_gemma":4.619772e-8,"teacher_disagreement_score":0.89984685,"about_ca_system_score_codex":0.000061447005,"about_ca_system_score_gemma":0.000024776109,"threshold_uncertainty_score":0.51787066},"labels":[],"label_agreement":null},{"id":"W2057330140","doi":"10.1145/1753326.1753328","title":"Estimating residual error rate in recognized handwritten documents using artificial error injection","year":2010,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Residual; Handwriting; Word error rate; Handwriting recognition; Set (abstract data type); Speech recognition; Measure (data warehouse); Artificial intelligence; Pattern recognition (psychology); Data mining; Feature extraction; Algorithm","score_opus":0.03983830630952655,"score_gpt":0.32245638899161655,"score_spread":0.28261808268209,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2057330140","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":[0.58213717,0.0000022004203,0.41418657,0.00041832522,0.00084761914,0.0003799018,0.0000019432973,0.0005837847,0.0014424906],"genre_scores_gemma":[0.5225544,3.6261878e-7,0.47679967,0.0002357457,0.00017530406,0.000045536723,0.000005739598,0.000017885488,0.00016536341],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977287,0.00021365347,0.0006374761,0.00063572364,0.00030849074,0.00047592176],"domain_scores_gemma":[0.99889904,0.00012093256,0.00020414665,0.00047986905,0.00017529617,0.00012071813],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015076443,0.00023667054,0.00028010455,0.00049722695,0.00022674575,0.00043833654,0.00057269284,0.00020172803,0.0002196265],"category_scores_gemma":[0.0003936149,0.00023242072,0.00006896536,0.000769971,0.00006763605,0.0014691912,0.00026229772,0.0005485984,0.000117851174],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000108683606,0.0005579184,0.0039438424,0.00006981821,0.000049463877,0.00012551389,0.0015662168,0.00036498444,0.45039746,0.009177036,0.0013239165,0.53231514],"study_design_scores_gemma":[0.0011622973,0.0002061358,0.0030154083,0.00014834618,0.000018283425,0.0001660247,0.00010388579,0.6687248,0.23882788,0.086637475,0.00017556926,0.00081389444],"about_ca_topic_score_codex":0.00057453144,"about_ca_topic_score_gemma":0.0008929134,"teacher_disagreement_score":0.6683598,"about_ca_system_score_codex":0.000075424425,"about_ca_system_score_gemma":0.00013104854,"threshold_uncertainty_score":0.9477842},"labels":[],"label_agreement":null},{"id":"W2057340122","doi":"10.1109/icpr.2010.496","title":"A Novel Handwritten Urdu Word Spotting Based on Connected Components Analysis","year":2010,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Spotting; Urdu; Computer science; Artificial intelligence; Word (group theory); Keyword spotting; Speech recognition; Word recognition; Natural language processing; Recall rate; Pattern recognition (psychology); Word error rate; Mathematics; Reading (process)","score_opus":0.01797248907648489,"score_gpt":0.25166927292157143,"score_spread":0.23369678384508655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2057340122","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":[0.14508525,0.0000014094907,0.8439272,0.0010975823,0.00015905338,0.00020964858,0.000008109907,0.0012397433,0.0082719885],"genre_scores_gemma":[0.71514857,4.2785257e-7,0.28305647,0.0014763452,0.00004057139,0.000029360279,0.000024573317,0.000011010047,0.00021266987],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99813837,0.000050559684,0.00035811483,0.00061603583,0.00045729888,0.00037963066],"domain_scores_gemma":[0.99819475,0.00033958355,0.00014162318,0.0009065888,0.00022808161,0.00018937631],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053120684,0.00022775569,0.00033108087,0.00079674413,0.00018406172,0.00031864268,0.0009816246,0.00013887134,0.0004838569],"category_scores_gemma":[0.0001673135,0.00020204908,0.00022528613,0.00187639,0.000058020487,0.0003142422,0.00016125616,0.00039106113,0.00015554775],"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":[0.000070604096,0.0019428064,0.01941988,0.000035777262,0.0006680134,0.00007988077,0.0003447519,0.00018803755,0.70322776,0.031453073,0.0025242155,0.24004523],"study_design_scores_gemma":[0.0011499246,0.00010913716,0.050021626,0.000036583424,0.00011099155,0.000013153079,0.000012455208,0.8394275,0.10568609,0.00084691786,0.0019893758,0.0005962519],"about_ca_topic_score_codex":0.00017764399,"about_ca_topic_score_gemma":0.00017698453,"teacher_disagreement_score":0.8392395,"about_ca_system_score_codex":0.000027150063,"about_ca_system_score_gemma":0.000045993038,"threshold_uncertainty_score":0.82393223},"labels":[],"label_agreement":null},{"id":"W2059906468","doi":"10.1587/transinf.e92.d.653","title":"Probabilistic Synthesis of Personal-Style Handwriting","year":2009,"lang":"en","type":"article","venue":"IEICE Transactions on Information and Systems","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Handwriting; Computer science; Naturalness; Character (mathematics); Style (visual arts); Probabilistic logic; Natural language processing; Natural (archaeology); Speech recognition; Artificial intelligence; Mathematics; Literature; Art","score_opus":0.01316318079131615,"score_gpt":0.23206487674241927,"score_spread":0.21890169595110312,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2059906468","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":[0.0052664187,0.00003398603,0.98645777,0.00036979094,0.000094562376,0.00031337515,0.000018272814,0.00026534323,0.007180507],"genre_scores_gemma":[0.99675447,0.00003256892,0.0029403644,0.00014887562,0.00000985457,0.000057475194,0.0000016935383,0.000002301305,0.00005242683],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990608,0.00005369736,0.00042435576,0.00010514831,0.00023297906,0.00012303247],"domain_scores_gemma":[0.9993116,0.000140147,0.00015515603,0.00016624699,0.00016427497,0.00006252163],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003408286,0.000098780954,0.00016257865,0.0002506994,0.00014874195,0.0001878301,0.00015275403,0.00006465107,0.000012508375],"category_scores_gemma":[0.000035536974,0.00009117571,0.00005147201,0.00025087994,0.000027342323,0.0013547513,0.0000019087433,0.00009379116,0.000026751706],"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":[0.000018804834,0.00012163012,0.000007699899,0.00033864297,0.000024974122,9.839074e-7,0.004421439,0.00030828232,0.00039021095,0.017672908,0.0001814829,0.97651297],"study_design_scores_gemma":[0.0015181942,0.0011467048,0.0014624373,0.0018702856,0.00008429034,0.00038495485,0.0062087607,0.9284038,0.046366677,0.0018017724,0.009646374,0.0011057537],"about_ca_topic_score_codex":0.000030647647,"about_ca_topic_score_gemma":0.0000015925615,"teacher_disagreement_score":0.99148804,"about_ca_system_score_codex":0.000030125426,"about_ca_system_score_gemma":0.000029432445,"threshold_uncertainty_score":0.37180376},"labels":[],"label_agreement":null},{"id":"W2063954715","doi":"10.1109/icdar.2013.144","title":"Unsupervised Ensemble of Experts (EoE) Framework for Automatic Binarization of Document Images","year":2013,"lang":"en","type":"preprint","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"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; Artificial intelligence; Thresholding; Leverage (statistics); Ensemble learning; Graph; Grid; CONTEST; Machine learning; Pattern recognition (psychology); Image (mathematics); Theoretical computer science; Mathematics","score_opus":0.022206950265854532,"score_gpt":0.29214824294367664,"score_spread":0.26994129267782213,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2063954715","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":[0.014222727,0.00016197842,0.98199135,0.000490449,0.0002816165,0.001661878,0.0000114225995,0.00051588495,0.0006626848],"genre_scores_gemma":[0.35063496,0.000083568215,0.6484404,0.00009145195,0.000025182788,0.0005494335,0.00002044708,0.000017768445,0.00013677723],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979404,0.0000990422,0.00081480935,0.00052773923,0.00038183804,0.00023617374],"domain_scores_gemma":[0.9973056,0.00029494235,0.00057415175,0.0011086551,0.00064389186,0.00007279392],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00034838865,0.0002765988,0.000576263,0.00032588773,0.000039757062,0.0001397314,0.0011541158,0.00038040744,0.00020081512],"category_scores_gemma":[0.00019457948,0.00024644966,0.00023045372,0.00022004612,0.00006569787,0.0003355605,0.0009015203,0.00015697014,0.0000100693105],"study_design_candidate":"theoretical_or_conceptual","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":[0.000015119953,0.00079511624,0.0001804635,0.0061162007,0.00029769487,0.000002873177,0.006393647,0.00012220907,0.039173506,0.29118234,0.00995499,0.64576584],"study_design_scores_gemma":[0.00017731871,0.00015123062,0.00009180287,0.0010201465,0.00002070276,0.0000015166515,0.00005026366,0.029573228,0.48151812,0.48706234,0.00006781117,0.00026552202],"about_ca_topic_score_codex":0.00012677477,"about_ca_topic_score_gemma":0.000001299353,"teacher_disagreement_score":0.6455003,"about_ca_system_score_codex":0.000055070494,"about_ca_system_score_gemma":0.00014897245,"threshold_uncertainty_score":0.99999875},"labels":[],"label_agreement":null},{"id":"W2065409946","doi":"10.1142/s0218348x0000010x","title":"HOW TO USE FRACTAL DIMENSIONS TO QUALIFY WRITINGS AND WRITERS","year":2000,"lang":"en","type":"article","venue":"Fractals","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Fractal; Handwriting; Field (mathematics); Computer science; Domain (mathematical analysis); Fractal dimension; Artificial intelligence; Authentication (law); Fractal analysis; Statistical physics; Mathematics; Pure mathematics; Mathematical analysis; Physics; Computer security","score_opus":0.022719837423440796,"score_gpt":0.26961178387194645,"score_spread":0.24689194644850565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2065409946","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":[0.8870815,0.000037395224,0.09344172,0.016481837,0.00007878381,0.00049818953,0.0000326839,0.0007051524,0.0016427112],"genre_scores_gemma":[0.84885997,0.000028335995,0.13713124,0.011106652,0.00006743983,0.000065589054,0.000006511772,0.000020272426,0.002714005],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984443,0.00008051024,0.0002321917,0.0005413032,0.00031633675,0.00038534548],"domain_scores_gemma":[0.9986485,0.00026543057,0.000049048853,0.0004988247,0.00010336666,0.000434819],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002750719,0.0001930855,0.0002370311,0.00022004583,0.0001615178,0.0009650263,0.00042968307,0.00009711988,0.00014398084],"category_scores_gemma":[0.00022535073,0.000192116,0.000058680842,0.00045606418,0.00003181347,0.0014350602,0.00022020566,0.00016333176,0.0004514257],"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":[0.000018856723,0.000119403616,0.0009406864,0.000016180296,0.000022008378,0.000086723856,0.0021796024,0.0000030817137,0.03224806,0.0015307536,0.040329177,0.92250544],"study_design_scores_gemma":[0.0005768991,0.0007098888,0.027393123,0.00034171634,0.000019810257,0.00019655802,0.00020891198,0.0008467614,0.062054235,0.0026435836,0.9036286,0.0013799258],"about_ca_topic_score_codex":0.00011015507,"about_ca_topic_score_gemma":0.0000118085145,"teacher_disagreement_score":0.92112553,"about_ca_system_score_codex":0.00003493539,"about_ca_system_score_gemma":0.00002176703,"threshold_uncertainty_score":0.9305771},"labels":[],"label_agreement":null},{"id":"W2067467853","doi":"10.1109/icpr.2010.502","title":"Noise Tolerant Script Identification of Printed Oriental and English Documents Using a Downgraded Pixel Density Feature","year":2010,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Feature (linguistics); Computer science; Pixel; Identification (biology); Noise (video); Artificial intelligence; Pattern recognition (psychology); Feature extraction; Document image processing; Font; Image (mathematics); Speech recognition; Computer vision; Data mining; Image segmentation; Linguistics","score_opus":0.009778655799840889,"score_gpt":0.24954292943985656,"score_spread":0.23976427364001568,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2067467853","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":[0.8162084,0.0000073105048,0.18255474,0.000079883706,0.00041699538,0.00024761123,0.000003512413,0.00022358546,0.00025796358],"genre_scores_gemma":[0.91994405,0.0000034379186,0.07975662,0.00007554505,0.000036133482,0.000007930791,0.0000049158334,0.000005850322,0.00016553297],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99894893,0.000039820745,0.00025947436,0.00034714062,0.00024759714,0.00015701904],"domain_scores_gemma":[0.99897766,0.000021729677,0.00015160537,0.0004059475,0.0003556681,0.00008738546],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029160062,0.0001189023,0.00015033092,0.0001373515,0.00009200355,0.00018154949,0.00033039754,0.00010433615,0.000022523047],"category_scores_gemma":[0.00008331689,0.00010668993,0.0000437655,0.00021438347,0.000080548074,0.0007251064,0.00021933566,0.00020786606,0.000004702051],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000074466197,0.000092249495,0.0035730689,0.000019227566,0.000011498804,0.0000023753737,0.00084828644,1.3533516e-7,0.9803238,0.0038369042,0.00022627068,0.011058724],"study_design_scores_gemma":[0.0004191486,0.000038252103,0.019311074,0.000029490498,0.000013854982,0.000046418907,0.00007386682,0.010749,0.9667016,0.0018546752,0.000559182,0.00020339125],"about_ca_topic_score_codex":0.000074830736,"about_ca_topic_score_gemma":0.0000373363,"teacher_disagreement_score":0.10373563,"about_ca_system_score_codex":0.000021407583,"about_ca_system_score_gemma":0.000032438842,"threshold_uncertainty_score":0.4350689},"labels":[],"label_agreement":null},{"id":"W2075069329","doi":"10.1049/iet-bmt.2013.0024","title":"Hybrid writer‐independent–writer‐dependent offline signature verification system","year":2013,"lang":"en","type":"article","venue":"IET Biometrics","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":86,"is_retracted":false,"has_abstract":true,"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; Signature (topology); Natural language processing; Artificial intelligence; Information retrieval","score_opus":0.014622102569356714,"score_gpt":0.23427902081303756,"score_spread":0.21965691824368083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2075069329","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":[0.025464986,0.00069451076,0.96598583,0.0007161353,0.0010178257,0.0009774527,0.0000747908,0.0018253681,0.0032430806],"genre_scores_gemma":[0.9437423,0.000088335124,0.05453672,0.0003987935,0.0001924183,0.00016077819,0.00007990371,0.000032390897,0.000768402],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99686074,0.00014732822,0.0006293778,0.00080660667,0.0010317214,0.0005242017],"domain_scores_gemma":[0.99730057,0.00015455946,0.00030957488,0.0012641619,0.00070269685,0.00026843578],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007417982,0.000318269,0.00033381183,0.0023437776,0.00016679711,0.0009516969,0.0018257224,0.0002582829,0.00013771035],"category_scores_gemma":[0.00017543884,0.00030098855,0.00014908661,0.0038992397,0.000050970393,0.0012972085,0.00036538692,0.00039490903,0.0016554835],"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":[0.000010627171,0.0005819153,0.0006502666,0.00035111862,0.00010185388,0.00015280025,0.00025066934,0.000005902084,0.053893816,0.01088832,0.04605293,0.8870598],"study_design_scores_gemma":[0.003204283,0.0012133233,0.0145348,0.0005191192,0.000107012806,0.0011642309,0.00031553008,0.11466942,0.8029057,0.008534152,0.049503867,0.0033286132],"about_ca_topic_score_codex":0.000096203396,"about_ca_topic_score_gemma":0.0000013126721,"teacher_disagreement_score":0.91827726,"about_ca_system_score_codex":0.00028941207,"about_ca_system_score_gemma":0.000064720894,"threshold_uncertainty_score":0.9999442},"labels":[],"label_agreement":null},{"id":"W2077253340","doi":"10.1134/s1054661807040219","title":"A hybrid multiple classifier system of unconstrained handwritten numeral recognition","year":2007,"lang":"en","type":"article","venue":"Pattern Recognition and Image Analysis","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Numeral system; Pattern recognition (psychology); Classifier (UML); Computer science; Artificial intelligence; Support vector machine; Random subspace method; Machine learning; Speech recognition","score_opus":0.023009646219446837,"score_gpt":0.24637784398309476,"score_spread":0.2233681977636479,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2077253340","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":[0.20005825,0.000040696803,0.79696107,0.00011680026,0.00007047579,0.00024258575,0.00019547995,0.0003354843,0.0019791797],"genre_scores_gemma":[0.9589842,0.000046813064,0.040014777,0.00033104848,0.00007452626,0.00004036783,0.00045095946,0.000018470864,0.000038809703],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9975236,0.00018244032,0.0008453956,0.0006408567,0.00039288666,0.00041479972],"domain_scores_gemma":[0.9980364,0.00026643404,0.0004268161,0.00041135243,0.00063701655,0.0002219893],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011080964,0.00028216798,0.00056469295,0.0011626937,0.00015162631,0.0002107974,0.0003112078,0.0001159117,0.00022499256],"category_scores_gemma":[0.00010892052,0.0002789787,0.0003736552,0.00110273,0.00014415961,0.00084979954,0.00011821131,0.00020739433,0.00014889672],"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":[0.000027398151,0.00013810415,0.0053755944,0.00012811055,0.0005383579,0.00007587385,0.00022781179,1.8053152e-7,0.007837006,0.000009496636,0.00017052406,0.98547155],"study_design_scores_gemma":[0.0056724558,0.0006760628,0.038518775,0.0008985972,0.0034564037,0.00064347265,0.002307781,0.09684796,0.8417771,0.006178883,0.0004247622,0.00259774],"about_ca_topic_score_codex":0.0003012958,"about_ca_topic_score_gemma":0.00014529428,"teacher_disagreement_score":0.9828738,"about_ca_system_score_codex":0.00006333092,"about_ca_system_score_gemma":0.00003013874,"threshold_uncertainty_score":0.99996626},"labels":[],"label_agreement":null},{"id":"W2078293714","doi":"10.1142/s0218001412560149","title":"A NOVEL AND PRACTICAL SYSTEM FOR VERIFYING SIGNATURES ON PERSIAN HANDWRITTEN BANK CHECKS","year":2012,"lang":"en","type":"article","venue":"International Journal of Pattern Recognition and Artificial Intelligence","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Signature (topology); Computer science; Pattern recognition (psychology); Artificial intelligence; Fractal dimension; Feature extraction; Feature (linguistics); Data mining; Database; Fractal; Mathematics","score_opus":0.11019135053166676,"score_gpt":0.34648697323863625,"score_spread":0.2362956227069695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2078293714","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":[0.047602914,0.00009407873,0.9486336,0.002207309,0.0010311375,0.0001652203,0.000036515077,0.00004748676,0.00018173378],"genre_scores_gemma":[0.96085805,0.000074088166,0.037568647,0.0007667524,0.00069167715,0.000015998214,0.000007413836,0.000011010088,0.0000063463312],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99861896,0.000061457955,0.00051266263,0.00020291585,0.0003889876,0.00021504275],"domain_scores_gemma":[0.9984216,0.00036819288,0.00035690275,0.00008377279,0.00059210556,0.00017742687],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00075817533,0.0001505617,0.00018700032,0.0003011771,0.000104975436,0.00033229846,0.0002425652,0.00010193486,0.000028514505],"category_scores_gemma":[0.00025908792,0.00013393111,0.00009752538,0.0000795501,0.00006908496,0.00090969645,0.00007985879,0.00026625366,0.000019398094],"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":[0.00012420995,0.0002632552,0.000113750124,0.000039535353,0.00009158202,0.000029284161,0.0010511708,0.0000023894083,0.010076812,0.0066979937,0.0001119273,0.9813981],"study_design_scores_gemma":[0.0013858376,0.0024953207,0.0028571105,0.0034787792,0.00021271387,0.00841735,0.0068503893,0.04935913,0.8763726,0.04194635,0.0049769427,0.0016474951],"about_ca_topic_score_codex":0.000010249162,"about_ca_topic_score_gemma":0.0000036725075,"teacher_disagreement_score":0.9797506,"about_ca_system_score_codex":0.00006429858,"about_ca_system_score_gemma":0.000035184203,"threshold_uncertainty_score":0.5461553},"labels":[],"label_agreement":null},{"id":"W2079279637","doi":"10.1016/j.patcog.2011.12.011","title":"Synthetic on-line signature generation. Part I: Methodology and algorithms","year":2011,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":82,"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; National Institute of Standards and Technology; Ministerio de Economía y Competitividad","keywords":"Algorithm; Signature (topology); Computer science; Line (geometry); Artificial intelligence; Mathematics","score_opus":0.2096118314133996,"score_gpt":0.3119696942014851,"score_spread":0.10235786278808554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2079279637","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":[0.01679318,0.00009132293,0.97975224,0.00042755718,0.00046304287,0.00027700677,0.000029687315,0.0004070429,0.0017589018],"genre_scores_gemma":[0.5905284,0.00031260395,0.4040608,0.004044759,0.0005089009,0.00027009143,0.00012380077,0.000035792564,0.0001148167],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99833965,0.0004077191,0.00027817182,0.0005532067,0.0001777516,0.00024348953],"domain_scores_gemma":[0.99909526,0.00019347608,0.00012543245,0.00032947713,0.00015311022,0.00010325812],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00065990136,0.00018842422,0.00020509212,0.0001985505,0.00011370218,0.00007437892,0.00025348424,0.00017129877,0.00037276366],"category_scores_gemma":[0.00011862053,0.00017526154,0.000056634126,0.00015995844,0.000057234927,0.00033590358,0.00009269614,0.00023494902,0.00027919505],"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":[0.000004071546,0.00007872325,0.000051752195,0.000011418333,0.000015346599,0.000018929288,0.00033136853,2.1908171e-7,0.0011175644,0.00016792721,0.0006073723,0.9975953],"study_design_scores_gemma":[0.001086381,0.001661659,0.0012465112,0.00029101784,0.00007876677,0.0004402368,0.00007270533,0.0377879,0.86666757,0.0873699,0.0021020814,0.0011952847],"about_ca_topic_score_codex":0.000035752408,"about_ca_topic_score_gemma":0.000016101418,"teacher_disagreement_score":0.9964,"about_ca_system_score_codex":0.000021312915,"about_ca_system_score_gemma":0.000015964026,"threshold_uncertainty_score":0.7146958},"labels":[],"label_agreement":null},{"id":"W2081622490","doi":"10.5555/338219.338260","title":"A fast algorithm to generate unlabeled necklaces","year":2000,"lang":"en","type":"article","venue":"Symposium on Discrete Algorithms","topic":"Handwritten Text Recognition Techniques","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":"Computer science; Artificial intelligence; Algorithm","score_opus":0.009245848424656271,"score_gpt":0.2503925321792809,"score_spread":0.24114668375462464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2081622490","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":[0.012593121,0.00015707988,0.9259532,0.009957537,0.00073751673,0.0013786134,0.00013601455,0.0027785187,0.04630839],"genre_scores_gemma":[0.03168552,0.00056376617,0.9322719,0.009608596,0.0010062497,0.00078151544,0.00008695993,0.00015589141,0.023839623],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99650794,0.00019474402,0.00052895414,0.0011814984,0.0007295637,0.0008573205],"domain_scores_gemma":[0.9979436,0.00007623962,0.00009927425,0.0011964219,0.00016587836,0.0005186047],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00040795104,0.0004961346,0.00043801745,0.00035269107,0.00031221783,0.00059420255,0.0016075744,0.00017411883,0.0005993999],"category_scores_gemma":[0.000014940479,0.0004494015,0.00019095601,0.001127856,0.00007729486,0.0007365729,0.0002412259,0.00031113075,0.003074656],"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":[0.000017419794,0.00012619174,0.000007058545,0.000007947593,0.000041884938,0.0000755253,0.00051296025,0.00015867798,0.004418968,0.0011213354,0.00583948,0.98767257],"study_design_scores_gemma":[0.002945738,0.003940029,0.0004680603,0.0003929658,0.00007128357,0.00026865603,0.00010939726,0.335895,0.46228772,0.008417352,0.18149629,0.0037075062],"about_ca_topic_score_codex":0.00008325704,"about_ca_topic_score_gemma":0.000005996405,"teacher_disagreement_score":0.98396504,"about_ca_system_score_codex":0.000121384706,"about_ca_system_score_gemma":0.0000882612,"threshold_uncertainty_score":0.9997958},"labels":[],"label_agreement":null},{"id":"W2082489355","doi":"10.1145/1572741.1572763","title":"Tools for the efficient generation of hand-drawn corpora based on context-free grammars","year":2009,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"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; Grammar; Context (archaeology); Rule-based machine translation; Artificial intelligence; Ground truth; Symbol (formal); Domain (mathematical analysis); Sketch recognition; Context-free grammar; Theoretical computer science; Algorithm; Programming language; Linguistics; Mathematics","score_opus":0.05454921578927355,"score_gpt":0.268285942490044,"score_spread":0.21373672670077046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2082489355","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":[0.0034572072,0.000023652654,0.9901858,0.0042259507,0.0001220126,0.0007326878,0.000010790866,0.00017416006,0.001067729],"genre_scores_gemma":[0.89557606,0.0000016719721,0.10097272,0.0032038302,0.000046981997,0.00006608911,0.000009925134,0.0000046961522,0.00011802275],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99902266,0.000044981844,0.0002552527,0.000244495,0.00027001358,0.00016259942],"domain_scores_gemma":[0.99845976,0.00042551727,0.00012487912,0.00071870623,0.00022917251,0.000041971936],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004698418,0.000110685214,0.000136671,0.00008951892,0.00020696795,0.0003790218,0.0007516109,0.000053672866,0.000023900715],"category_scores_gemma":[0.00023752176,0.00007279893,0.00010355952,0.00020560928,0.00007615865,0.00015064335,0.00004019609,0.000060149046,0.0000072562493],"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":[0.00002730199,0.00020203274,0.0000059046074,0.0000064716005,0.0000070879005,0.0000011771116,0.00011268934,0.0008526604,0.016492367,0.16262554,0.013992931,0.80567384],"study_design_scores_gemma":[0.00060907763,0.000556581,0.0001945575,0.000018735866,0.000006404843,0.0000015432487,0.0000091553175,0.5674775,0.42205596,0.006723581,0.0022359411,0.00011090688],"about_ca_topic_score_codex":0.0000143863,"about_ca_topic_score_gemma":0.000014301718,"teacher_disagreement_score":0.8921189,"about_ca_system_score_codex":0.000027932234,"about_ca_system_score_gemma":0.00007999818,"threshold_uncertainty_score":0.3654916},"labels":[],"label_agreement":null},{"id":"W2083849171","doi":"10.1117/12.912112","title":"Improving isolated and in-context classication of handwritten characters","year":2011,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Mathematics; Invariant (physics); Affine transformation; Legendre polynomials; Pattern recognition (psychology); Context (archaeology); Series (stratigraphy); Algorithm; Artificial intelligence; Computer science; Pure mathematics; Mathematical analysis","score_opus":0.013506250815399447,"score_gpt":0.21603227768624836,"score_spread":0.20252602687084892,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2083849171","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":[0.99605846,0.00006508254,0.0016317803,0.0007347243,0.000091161906,0.00045331905,0.000010161688,0.00009995345,0.0008553499],"genre_scores_gemma":[0.8389844,0.00007504336,0.16065316,0.00007458253,0.00005344512,0.000097481556,0.0000021909639,0.00002337859,0.00003634806],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99826074,2.4317364e-8,0.0007032839,0.00037579334,0.0003795824,0.0002805859],"domain_scores_gemma":[0.9980636,0.000086889435,0.0005049627,0.000071111615,0.0011880939,0.0000853289],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061921065,0.00022380441,0.00035831143,0.00019510082,0.00004161863,0.00007596618,0.0010177718,0.00017105813,0.0000044663743],"category_scores_gemma":[0.00028673085,0.0001973709,0.00026243815,0.00037582434,0.00019240036,0.0010925735,0.00024496813,0.00024777238,6.5078876e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000680968,0.00012809996,0.0009089973,0.0003406177,0.000121086865,1.0106622e-7,0.0009874102,5.7530514e-7,0.65393484,0.3354067,0.0001487553,0.007954749],"study_design_scores_gemma":[0.001513719,0.0006267569,0.011988129,0.00068486703,0.00008359264,0.000029183253,0.0012387037,0.07287625,0.90325433,0.006942044,0.00024475486,0.0005176548],"about_ca_topic_score_codex":0.000031734744,"about_ca_topic_score_gemma":5.421209e-7,"teacher_disagreement_score":0.32846466,"about_ca_system_score_codex":0.00008248141,"about_ca_system_score_gemma":0.000029857234,"threshold_uncertainty_score":0.80485517},"labels":[],"label_agreement":null},{"id":"W2088257085","doi":"10.1109/icfhr.2014.33","title":"Novel Handwritten Words and Documents Databases of Five Middle Eastern Languages","year":2014,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Lexicon; Artificial intelligence; Natural language processing; Urdu; Support vector machine; Arabic; Perceptron; Linguistics; Artificial neural network","score_opus":0.024637850127209135,"score_gpt":0.2770583939029918,"score_spread":0.25242054377578266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2088257085","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":[0.06455395,0.00008476221,0.9226332,0.00022650986,0.00004528496,0.00012912895,0.000013918421,0.00022573852,0.012087525],"genre_scores_gemma":[0.76244676,0.00002530151,0.2345222,0.00042852768,0.000035176436,0.000014948419,0.000009741761,0.000007954426,0.0025094093],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991296,0.000036579186,0.00019307807,0.00028273388,0.00019427904,0.0001637316],"domain_scores_gemma":[0.99926805,0.00011109411,0.00008026203,0.0004014035,0.00006472116,0.00007444273],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023986041,0.00011148915,0.00016783777,0.00011199327,0.000039349747,0.000075105316,0.0003848329,0.000031528987,0.00005440967],"category_scores_gemma":[0.00006393798,0.000093159084,0.000030366675,0.000140507,0.000061697436,0.00053299544,0.00036609336,0.00005807387,0.00002539659],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026225955,0.0005751434,0.014026235,0.00030286028,0.00011710852,0.000012940462,0.0034693526,0.000001951682,0.046737712,0.089935824,0.004600529,0.8401941],"study_design_scores_gemma":[0.0050403434,0.0009612392,0.01715636,0.0011880061,0.00007934226,0.0002139996,0.0017426276,0.05677231,0.8785415,0.0122054,0.024244195,0.0018546735],"about_ca_topic_score_codex":0.00040928955,"about_ca_topic_score_gemma":0.00006371736,"teacher_disagreement_score":0.83833945,"about_ca_system_score_codex":0.000006636015,"about_ca_system_score_gemma":0.000012116651,"threshold_uncertainty_score":0.37989172},"labels":[],"label_agreement":null},{"id":"W2090115161","doi":"10.1016/j.patrec.2011.09.014","title":"Shape based local thresholding for binarization of document images","year":2011,"lang":"en","type":"article","venue":"Pattern Recognition Letters","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":"University of Alberta","funders":"","keywords":"Thresholding; Artificial intelligence; Segmentation; Pattern recognition (psychology); Computer science; Historical document; Feature (linguistics); Computer vision; Intensity (physics); Image segmentation; Image (mathematics)","score_opus":0.03975795047290146,"score_gpt":0.25121834762029577,"score_spread":0.2114603971473943,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2090115161","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":[0.038861718,0.000011709369,0.9588007,0.0010528181,0.00018147477,0.0005309106,0.000035088422,0.0003023276,0.00022330605],"genre_scores_gemma":[0.8758788,0.000006694951,0.11930647,0.0044158027,0.000043174732,0.0002555987,0.00006919884,0.000021181586,0.0000030667343],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985987,0.00007822188,0.00040908493,0.00040025546,0.0002412993,0.0002724699],"domain_scores_gemma":[0.99908656,0.000092366805,0.00024556782,0.0002922196,0.00021149033,0.00007180196],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035403285,0.0001784891,0.00019503558,0.00031163098,0.000082772494,0.00006566188,0.00041757367,0.00007101282,0.00025638746],"category_scores_gemma":[0.000030648996,0.00018461295,0.00013673575,0.00023821468,0.000083006904,0.0006535594,0.00007023394,0.00009071948,0.00005026714],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024218483,0.00013188118,0.0012652846,0.00015079873,0.000028890343,0.00000834964,0.0004241119,0.0000054859875,0.0238342,0.000083224906,0.0009887539,0.9730548],"study_design_scores_gemma":[0.0011264478,0.00031370638,0.00231419,0.00033284718,0.000038565755,0.000010912362,0.00004391207,0.024684291,0.9641763,0.006271521,0.00021297061,0.00047433213],"about_ca_topic_score_codex":0.00004101107,"about_ca_topic_score_gemma":0.0000022017746,"teacher_disagreement_score":0.9725805,"about_ca_system_score_codex":0.000049938473,"about_ca_system_score_gemma":0.000024159024,"threshold_uncertainty_score":0.75282973},"labels":[],"label_agreement":null},{"id":"W2090458888","doi":"10.1145/1815330.1815360","title":"Typeface personality traits and their design characteristics","year":2010,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Typeface; Legibility; Big Five personality traits; Readability; Personality; Psychology; Computer science; Cognitive psychology; Social psychology; Visual arts; Art","score_opus":0.02535077174877393,"score_gpt":0.24565314640780284,"score_spread":0.2203023746590289,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2090458888","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":[0.07182604,0.000007403687,0.92355967,0.00062909164,0.00006241938,0.00011481332,0.0000037139744,0.0003824555,0.003414423],"genre_scores_gemma":[0.80337006,0.000007803669,0.19580972,0.00044600456,0.000035663903,0.000009130294,6.5968595e-7,0.0000045126603,0.0003164325],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99945,0.00003974165,0.00009909617,0.00020806631,0.000072692215,0.0001303789],"domain_scores_gemma":[0.99957865,0.00009599834,0.000032312546,0.00014238125,0.00007082883,0.00007981018],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032546622,0.00008858783,0.0000959864,0.000034488563,0.00006475408,0.00012946632,0.00027954782,0.00006338408,0.00013705286],"category_scores_gemma":[0.000051142928,0.000066044035,0.000021474118,0.000086995344,0.00004937447,0.0002314099,0.000079923855,0.00015598888,0.000041020943],"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":[0.0000037657983,0.000062090585,0.00034837585,0.0000116327,0.000010536115,0.000004525012,0.0009755722,1.3964933e-8,0.12836896,0.03586116,0.0018743426,0.832479],"study_design_scores_gemma":[0.0006569187,0.0003825379,0.18929973,0.000037054735,0.000012346298,0.00038178772,0.00010571483,0.039810177,0.65686744,0.074375294,0.036851045,0.0012199507],"about_ca_topic_score_codex":0.000009178612,"about_ca_topic_score_gemma":0.0000075102485,"teacher_disagreement_score":0.8312591,"about_ca_system_score_codex":0.0000041479393,"about_ca_system_score_gemma":0.000029325343,"threshold_uncertainty_score":0.26931974},"labels":[],"label_agreement":null},{"id":"W2092217867","doi":"10.1016/s0895-7177(00)00065-0","title":"Crucial combinations of parts for handwritten alphanumeric characters","year":2000,"lang":"en","type":"article","venue":"Mathematical and Computer Modelling","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":3,"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":"Alphanumeric; Confusion; Character (mathematics); Optimal distinctiveness theory; Pattern recognition (psychology); Computer science; Mathematics; Arithmetic; Artificial intelligence","score_opus":0.024460993746048668,"score_gpt":0.24042330370271636,"score_spread":0.2159623099566677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2092217867","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":[0.024596984,0.00003842426,0.97408634,0.00032576034,0.000049954306,0.00028339511,0.000004041955,0.00015294524,0.00046216202],"genre_scores_gemma":[0.42969826,0.000052508345,0.56962216,0.00024045746,0.00009405982,0.00008129399,0.000005539449,0.000011796221,0.00019394275],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990178,0.000026557997,0.00034095734,0.00026245692,0.00015316061,0.00019907484],"domain_scores_gemma":[0.9993891,0.0001701983,0.00006481136,0.0002094698,0.000083803025,0.00008258078],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019660703,0.00012638432,0.00026455743,0.00007635123,0.0001066698,0.000103890554,0.00028669572,0.000055140914,0.0000317573],"category_scores_gemma":[0.0000037918517,0.00011310714,0.000085483065,0.00012364145,0.00005655976,0.00026985773,0.000063932064,0.00006444683,0.000015097006],"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":[0.000012114144,0.0005524086,0.0000050700146,0.00019081146,0.000038173934,0.0000026890823,0.0013547092,0.00069936796,0.00005758743,0.40728444,0.00028393575,0.58951867],"study_design_scores_gemma":[0.0003342603,0.000095534124,0.00000801508,0.000080160455,0.000008946304,0.000012276808,0.000002624293,0.790813,0.0010160187,0.20690757,0.00060358574,0.000117970725],"about_ca_topic_score_codex":0.0000021513101,"about_ca_topic_score_gemma":1.04472235e-7,"teacher_disagreement_score":0.7901137,"about_ca_system_score_codex":0.000006842583,"about_ca_system_score_gemma":0.000013693851,"threshold_uncertainty_score":0.46123755},"labels":[],"label_agreement":null},{"id":"W2092619501","doi":"10.1007/s10044-007-0094-6","title":"Ensemble of HMM classifiers based on the clustering validity index for a handwritten numeral recognizer","year":2007,"lang":"en","type":"article","venue":"Pattern Analysis and Applications","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":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hidden Markov model; Codebook; Pattern recognition (psychology); Computer science; Vector quantization; Artificial intelligence; Cluster analysis; Linde–Buzo–Gray algorithm; Speech recognition","score_opus":0.03782214546971913,"score_gpt":0.2895338379360944,"score_spread":0.25171169246637526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2092619501","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":[0.0059954072,0.0000070470987,0.9914974,0.0012231272,0.000011096669,0.00046926865,0.000023803657,0.00006762745,0.0007052043],"genre_scores_gemma":[0.9860153,0.000008165718,0.012495621,0.0009725033,0.000040124723,0.000383738,0.000020457432,0.0000072403095,0.00005683419],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99896896,0.000045525547,0.0003021486,0.000322058,0.00017608421,0.00018520853],"domain_scores_gemma":[0.99868083,0.00045603153,0.00016572849,0.0004849117,0.00014336528,0.0000691479],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00082085875,0.00011182463,0.0002038149,0.00026860714,0.00019743969,0.00008809115,0.0003548658,0.000058385896,0.00002600683],"category_scores_gemma":[0.000022325587,0.000084333675,0.00018500509,0.0007991619,0.00005323017,0.00007389409,0.00006248289,0.00009022156,0.000004259269],"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":[0.000017215585,0.00022731141,0.029026786,0.0000464071,0.00026296175,6.556921e-7,0.00018305088,0.000085668005,0.0025451074,0.0017919798,0.0005735855,0.9652393],"study_design_scores_gemma":[0.000744908,0.00017272538,0.050167315,0.000050619743,0.0005061055,0.0000026730397,0.00015113484,0.8583084,0.07400125,0.008575822,0.006818311,0.0005007749],"about_ca_topic_score_codex":0.0000855956,"about_ca_topic_score_gemma":0.0002220875,"teacher_disagreement_score":0.9800199,"about_ca_system_score_codex":0.000019886362,"about_ca_system_score_gemma":0.000016207332,"threshold_uncertainty_score":0.34390274},"labels":[],"label_agreement":null},{"id":"W2096088936","doi":"10.1109/pria.2013.6528442","title":"Persian heritage image binarization competition (PHIBC 2012)","year":2013,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Persian; Image (mathematics); Competition (biology); Document image processing; Conjunction (astronomy); Pattern recognition (psychology)","score_opus":0.008267718112751865,"score_gpt":0.2191035136803283,"score_spread":0.21083579556757642,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096088936","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":[0.004123953,0.000019003866,0.94283664,0.0037988035,0.000099019315,0.0003166993,0.0000012027391,0.001131629,0.047673035],"genre_scores_gemma":[0.744236,0.000020035504,0.25259334,0.0008610626,0.000052935626,0.000083280254,0.000017231507,0.000012260188,0.002123848],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99909496,0.000055786644,0.00017545556,0.00027720229,0.0001869401,0.00020963456],"domain_scores_gemma":[0.9992974,0.000019349938,0.00005453282,0.00034441828,0.00019135686,0.00009297373],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00011470982,0.000113714275,0.00010104667,0.00014109387,0.00010934058,0.000373248,0.0004209387,0.00006571755,0.0021806909],"category_scores_gemma":[0.000012806978,0.00010577089,0.000051220704,0.00029580022,0.00006914851,0.0025751428,0.00012767292,0.00008713087,0.0027843004],"study_design_candidate":"theoretical_or_conceptual","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":[0.0000030640103,0.0004279204,0.0005230635,0.000077584766,0.000029342733,0.000019802894,0.0018152245,0.0000015845727,0.14896478,0.5739371,0.062489018,0.21171153],"study_design_scores_gemma":[0.0029017015,0.0015171944,0.02798823,0.00042984623,0.000040863426,0.00033450755,0.0028222417,0.19614819,0.41944915,0.2880434,0.056457207,0.0038674495],"about_ca_topic_score_codex":0.00017499756,"about_ca_topic_score_gemma":0.000018519133,"teacher_disagreement_score":0.74011207,"about_ca_system_score_codex":0.000035803656,"about_ca_system_score_gemma":0.000018839839,"threshold_uncertainty_score":0.99873143},"labels":[],"label_agreement":null},{"id":"W2096355136","doi":"10.1109/icpr.2008.4761532","title":"A new courtesy amount recognition module of a Check Reading System","year":2008,"lang":"en","type":"article","venue":"Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Concordia University","funders":"","keywords":"Numeral system; Courtesy; Computer science; Reading (process); Segmentation; Task (project management); Artificial intelligence; Speech recognition; Convolutional neural network; Pattern recognition (psychology); Optical character recognition; Image (mathematics); Engineering","score_opus":0.08019205348795666,"score_gpt":0.2874870085866602,"score_spread":0.20729495509870355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096355136","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":[0.4967806,0.000030593455,0.1776433,0.0063497424,0.0049885036,0.0034399284,0.0025843924,0.003331115,0.30485183],"genre_scores_gemma":[0.9803906,0.0008460475,0.012222801,0.0015821971,0.00147272,0.00093664665,0.0015949003,0.00019082059,0.0007632676],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.989418,0.00007932124,0.0026785152,0.0028951815,0.0036165807,0.0013123977],"domain_scores_gemma":[0.9862993,0.00019923401,0.0027828785,0.00046109108,0.009452345,0.00080519094],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["metaepi_narrow","insufficient_payload"],"category_scores_codex":[0.00115911,0.0015573712,0.0013353941,0.0027066278,0.00061417173,0.0015686128,0.0034307744,0.0008015227,0.0037208027],"category_scores_gemma":[0.00048822133,0.0017088011,0.00069719326,0.0010841509,0.0003416585,0.0045133065,0.0006297455,0.001626477,0.002655494],"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":[0.0011369439,0.002347182,0.011268142,0.0008790848,0.0014208531,0.0001734681,0.0034578524,0.0000028275276,0.029139606,0.030435005,0.012677795,0.9070612],"study_design_scores_gemma":[0.022053087,0.008282693,0.022400565,0.036208186,0.0008158409,0.005672165,0.010527671,0.17151429,0.58322895,0.12373675,0.0027053172,0.012854477],"about_ca_topic_score_codex":0.00045496953,"about_ca_topic_score_gemma":0.000032561795,"teacher_disagreement_score":0.89420676,"about_ca_system_score_codex":0.0012291238,"about_ca_system_score_gemma":0.00048342798,"threshold_uncertainty_score":0.9997175},"labels":[],"label_agreement":null},{"id":"W2096837246","doi":"10.1109/icfhr.2012.183","title":"Arabic handwritten word spotting using language models","year":2012,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Spotting; Computer science; Handwriting; Artificial intelligence; Natural language processing; Arabic; Classifier (UML); Word (group theory); Set (abstract data type); Handwriting recognition; Process (computing); Speech recognition; Identification (biology); Keyword spotting; Feature extraction; Linguistics; Programming language","score_opus":0.037572390943335324,"score_gpt":0.2838805264607805,"score_spread":0.24630813551744518,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096837246","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":[0.109125435,0.0002896752,0.8779258,0.000110633795,0.0001300493,0.00012817762,8.4194687e-7,0.0008818294,0.011407521],"genre_scores_gemma":[0.65394133,0.0000056897907,0.34519196,0.0004050373,0.00012007214,0.0000089442165,0.0000011975071,0.00001086945,0.00031489253],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99873745,0.00006260349,0.00022244456,0.00024722304,0.00023545367,0.0004948161],"domain_scores_gemma":[0.9992091,0.00005658969,0.0000710224,0.000439076,0.00006263124,0.00016154927],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050608185,0.00014647587,0.00015692545,0.00015485586,0.00012026524,0.00015526889,0.0005051295,0.00007588503,0.00010190999],"category_scores_gemma":[0.00002665304,0.00012997544,0.00007308293,0.00034868828,0.000026465921,0.0020475134,0.00025535264,0.0001363592,0.00012141466],"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":[0.0000038107135,0.00018305231,0.0016194426,0.000032596196,0.000030327375,0.000021727976,0.004422384,0.00007529897,0.025608048,0.041214097,0.0007340395,0.9260552],"study_design_scores_gemma":[0.0006931126,0.000059296395,0.0011128018,0.00018811082,0.00003215021,0.00035794207,0.0006322282,0.6266919,0.3408503,0.026191827,0.0018738116,0.0013165259],"about_ca_topic_score_codex":0.00009527951,"about_ca_topic_score_gemma":0.0000038028659,"teacher_disagreement_score":0.92473865,"about_ca_system_score_codex":0.000050925846,"about_ca_system_score_gemma":0.000025967236,"threshold_uncertainty_score":0.53002447},"labels":[],"label_agreement":null},{"id":"W2097217897","doi":"10.1109/icdar.1995.602125","title":"Document skew detection based on the fractal and least squares method","year":2002,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Skew; Computer science; Segmentation; Fractal; Algorithm; Pattern recognition (psychology); Identification (biology); Artificial intelligence; Mathematics","score_opus":0.019573391366664403,"score_gpt":0.26085390701313627,"score_spread":0.24128051564647185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2097217897","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":[0.0016817001,0.000020806603,0.9791877,0.0041295122,0.000049389135,0.0001758344,4.843255e-7,0.00035462703,0.014399924],"genre_scores_gemma":[0.86737084,0.00001028142,0.13010286,0.0020940343,0.000025651058,0.000046556288,2.1128892e-7,0.0000049775217,0.0003445868],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991667,0.00014916818,0.00011157188,0.00023674178,0.00020419518,0.00013160014],"domain_scores_gemma":[0.9993044,0.00028171437,0.00003854573,0.00028978602,0.00003754136,0.000047992162],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035973446,0.00009246466,0.00007256712,0.00008214759,0.00014447545,0.00020714915,0.00023542052,0.000040859344,0.0005479165],"category_scores_gemma":[0.00004606911,0.000058455313,0.000037072878,0.00017113757,0.000024502406,0.0002371319,0.000060214563,0.000115202776,0.000101400954],"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":[0.0000021448468,0.000040215687,0.00001794336,0.0000038515027,0.000004175428,0.000002780004,0.00010476714,0.0000030123351,0.0012147912,0.007914962,0.0013153707,0.989376],"study_design_scores_gemma":[0.0003235554,0.0004934655,0.00077099237,0.00003709503,0.000007589876,0.00003363413,0.000041007217,0.57024807,0.39650106,0.019330872,0.0119269565,0.0002857307],"about_ca_topic_score_codex":0.00003750773,"about_ca_topic_score_gemma":0.000012358818,"teacher_disagreement_score":0.98909026,"about_ca_system_score_codex":0.000022957029,"about_ca_system_score_gemma":0.0000044986973,"threshold_uncertainty_score":0.59993017},"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":"W2099334203","doi":"10.1109/icdar.2001.953914","title":"A feedback-based approach for segmenting handwritten legal amounts on bank cheques","year":2002,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"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","keywords":"Segmentation; Computer science; Artificial intelligence; Market segmentation; Classifier (UML); Pattern recognition (psychology); Artificial neural network; Process (computing); Machine learning","score_opus":0.0308766079221791,"score_gpt":0.24758794071327633,"score_spread":0.21671133279109722,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2099334203","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":[0.0016830241,0.000030455647,0.9383204,0.0008828725,0.00010342094,0.0006410747,0.0000075474977,0.0012291237,0.05710207],"genre_scores_gemma":[0.4548479,0.0000043880923,0.53667897,0.0027024192,0.000120782955,0.00035990792,0.00001803176,0.00002644293,0.0052411538],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99815094,0.0000612174,0.00031703472,0.00063123,0.0003562533,0.00048331334],"domain_scores_gemma":[0.99893504,0.00013682689,0.00010747279,0.00054266385,0.00015666817,0.00012134822],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003897914,0.00024281329,0.00024297838,0.00022916187,0.00022748706,0.000500404,0.0007842141,0.000117479714,0.00018257536],"category_scores_gemma":[0.00006457581,0.00021519804,0.00016458446,0.00033005484,0.000040797593,0.0006141123,0.00010367647,0.00015771633,0.000116058436],"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":[0.000056067896,0.002155498,0.0005629544,0.00030731666,0.00012576673,0.000021556014,0.0005522634,0.00010481376,0.00921702,0.07773646,0.13337423,0.77578604],"study_design_scores_gemma":[0.002019709,0.00066666876,0.00017947149,0.00010932895,0.000020512402,0.000014306066,0.000038072503,0.6332041,0.33751577,0.0019136291,0.023442889,0.00087552104],"about_ca_topic_score_codex":0.000021872898,"about_ca_topic_score_gemma":0.0000033564834,"teacher_disagreement_score":0.7749105,"about_ca_system_score_codex":0.00007730598,"about_ca_system_score_gemma":0.000023610184,"threshold_uncertainty_score":0.87755215},"labels":[],"label_agreement":null},{"id":"W2099382657","doi":"10.1109/icpr.1992.201779","title":"A handwriting model for syntactic recognition of cursive script","year":2003,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Cursive; Computer science; Handwriting; Natural language processing; Speech recognition; Artificial intelligence; Parsing; Handwriting recognition; Adjacency list; Feature extraction; Algorithm","score_opus":0.045292365671962806,"score_gpt":0.2789198459317149,"score_spread":0.2336274802597521,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2099382657","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":[0.0033541324,0.000029455772,0.9829453,0.00013105075,0.00006683119,0.00038718298,0.0000099469635,0.000247615,0.012828486],"genre_scores_gemma":[0.5047316,0.000010516015,0.4946252,0.00023034963,0.000008515767,0.00009854019,0.0000035093935,0.000007557878,0.00028420973],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990363,0.000049291833,0.00027427348,0.00027332007,0.00014963937,0.00021715969],"domain_scores_gemma":[0.9990461,0.00015717404,0.00012612861,0.00024105757,0.00036919562,0.000060355767],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039749264,0.00010487885,0.00016113414,0.00014647332,0.00007899202,0.000059137677,0.00024457724,0.00006464447,0.000033911936],"category_scores_gemma":[0.0003570544,0.00010356933,0.00009862052,0.00021266949,0.000028222468,0.00060240395,0.00003265423,0.00006688837,0.000016091002],"study_design_candidate":"theoretical_or_conceptual","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":[0.00003368643,0.0005099012,0.00011271748,0.00034221236,0.000078741214,0.0000055237933,0.0016632894,0.00005080273,0.041851006,0.4802028,0.006595838,0.46855348],"study_design_scores_gemma":[0.0004690046,0.000121050405,0.000004805795,0.0000985524,0.000014160501,0.000023927794,0.00010278121,0.23035777,0.52044153,0.24794593,0.00021484816,0.00020564343],"about_ca_topic_score_codex":0.0000067210435,"about_ca_topic_score_gemma":0.0000037849106,"teacher_disagreement_score":0.50137746,"about_ca_system_score_codex":0.000029346833,"about_ca_system_score_gemma":0.000075797805,"threshold_uncertainty_score":0.42234346},"labels":[],"label_agreement":null},{"id":"W2099576249","doi":"10.1109/icpr.1994.576887","title":"Handwritten sentence recognition: from signal to syntax","year":2002,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Natural language processing; Parsing; Artificial intelligence; Sentence; Syntax; Lexicon; TRACE (psycholinguistics); String (physics); Speech recognition; Identification (biology); Segmentation; Linguistics","score_opus":0.035320788519988565,"score_gpt":0.2364135518315771,"score_spread":0.20109276331158854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2099576249","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":[0.006198659,0.00006396693,0.9435773,0.0052068084,0.00016553415,0.0002807143,0.000021977745,0.0013447964,0.043140255],"genre_scores_gemma":[0.53861165,0.00004889508,0.44973505,0.008094951,0.00022811892,0.00012796103,0.000013564,0.000018402976,0.0031213958],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99832886,0.000067472734,0.00029341422,0.0005960141,0.0003680575,0.00034617068],"domain_scores_gemma":[0.9988252,0.00014528283,0.00005598059,0.0005241397,0.00018286676,0.0002665501],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00015558294,0.00018623518,0.00019087328,0.00017662268,0.00013016922,0.00029569512,0.00087175117,0.00008642158,0.0077302232],"category_scores_gemma":[0.000046817793,0.00017592969,0.00008589433,0.00053470576,0.000034059296,0.000707486,0.00027188615,0.00015068127,0.0066991583],"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":[0.0000037455216,0.00013185131,0.00014956688,0.0000037131583,0.000020811673,0.000066576096,0.00041624645,6.032814e-7,0.0051854644,0.00094430684,0.083149165,0.90992796],"study_design_scores_gemma":[0.0014761694,0.00093128934,0.0015911906,0.00040049176,0.00004524365,0.00026959722,0.0003222061,0.0439551,0.74748105,0.11942454,0.08144753,0.0026555904],"about_ca_topic_score_codex":0.00016299554,"about_ca_topic_score_gemma":0.00003081153,"teacher_disagreement_score":0.90727234,"about_ca_system_score_codex":0.000043937995,"about_ca_system_score_gemma":0.000011981628,"threshold_uncertainty_score":0.9940742},"labels":[],"label_agreement":null},{"id":"W2099926249","doi":"10.1016/s0031-3203(00)00098-4","title":"A lexicon-driven approach for optimal segment combination in off-line recognition of unconstrained handwritten Korean words","year":2001,"lang":"en","type":"article","venue":"Pattern Recognition","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":"Concordia University","funders":"Korea Science and Engineering Foundation","keywords":"Computer science; Lexicon; Artificial intelligence; Segmentation; Pattern recognition (psychology); Word (group theory); Classifier (UML); Intelligent word recognition; Handwriting recognition; Line (geometry); Speech recognition; Text segmentation; Image (mathematics); Character recognition; Feature extraction; Intelligent character recognition; Mathematics","score_opus":0.042080975095281185,"score_gpt":0.2732928643360469,"score_spread":0.2312118892407657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2099926249","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":[0.21526602,0.000032569555,0.7812663,0.00035187404,0.00012071509,0.0013347864,0.00015775162,0.000258406,0.0012115798],"genre_scores_gemma":[0.83240443,0.00012760011,0.16456152,0.00026176788,0.00010203314,0.0007794012,0.0016946374,0.000033258075,0.000035338675],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99736464,0.00021152418,0.000868008,0.0006971693,0.00039683445,0.0004618213],"domain_scores_gemma":[0.9984083,0.00019437243,0.00042799185,0.00035515722,0.0004966337,0.0001175556],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008548358,0.00031613495,0.00044753673,0.0006927165,0.00009519018,0.00011673835,0.00044019712,0.00022488885,0.000084428284],"category_scores_gemma":[0.000107392334,0.0003444451,0.00018707539,0.0006757123,0.00009551246,0.0008711502,0.00010856438,0.00023685739,0.000032361342],"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":[0.00007999955,0.0008236963,0.0014652761,0.00012700693,0.000034508277,0.000009666905,0.0005316151,0.000030247296,0.0021953466,0.000047338188,0.000102064405,0.9945532],"study_design_scores_gemma":[0.015943091,0.0035430852,0.004734938,0.0017626535,0.0001746154,0.00036810612,0.0011362657,0.6593489,0.2582903,0.052200343,0.00021601481,0.0022816726],"about_ca_topic_score_codex":0.00008130213,"about_ca_topic_score_gemma":0.000067073015,"teacher_disagreement_score":0.99227154,"about_ca_system_score_codex":0.00016128422,"about_ca_system_score_gemma":0.00008791335,"threshold_uncertainty_score":0.99990076},"labels":[],"label_agreement":null},{"id":"W2101025914","doi":"10.1109/ccece.2004.1345055","title":"A stroke based algorithm for dynamic signature verification","year":2004,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Signature (topology); Biometrics; Computer science; Matching (statistics); Algorithm; Pattern recognition (psychology); Correlation; Artificial intelligence; Identity (music); Mathematics; Statistics; Geometry","score_opus":0.009521704553165112,"score_gpt":0.25369228995698256,"score_spread":0.24417058540381745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2101025914","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":[0.00011948854,0.000037347192,0.9964976,0.0013398494,0.00008650137,0.00038539548,0.0000186064,0.0007719556,0.000743285],"genre_scores_gemma":[0.08837819,0.0000047114077,0.91032845,0.00078267534,0.000017654975,0.00014625747,0.000024104445,0.000007777366,0.0003101542],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992815,0.000013741624,0.00012766603,0.00027494185,0.00014015661,0.00016198112],"domain_scores_gemma":[0.99942327,0.0000412105,0.000044987723,0.0003096324,0.00012976667,0.0000511271],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014423918,0.0000898636,0.00008254387,0.00010564742,0.00007069312,0.00009251814,0.0004007297,0.00008581317,0.0000196397],"category_scores_gemma":[0.000014974817,0.00008266045,0.00006761693,0.00017719438,0.000017247217,0.0002879454,0.000026262967,0.000078120385,0.00003314295],"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":[0.0000012755762,0.00005755619,7.688327e-7,0.0000048819697,0.0000041237217,0.000001262333,0.00002620907,0.000009628666,0.0056700404,0.009539404,0.00026224603,0.9844226],"study_design_scores_gemma":[0.0011025737,0.0002486023,0.00013062276,0.000026469022,0.0000066801977,0.0000066259804,0.000013297056,0.64353466,0.3122405,0.037142467,0.005260416,0.0002870829],"about_ca_topic_score_codex":0.000008520622,"about_ca_topic_score_gemma":0.000006319903,"teacher_disagreement_score":0.9841355,"about_ca_system_score_codex":0.000076961915,"about_ca_system_score_gemma":0.00008748494,"threshold_uncertainty_score":0.33707952},"labels":[],"label_agreement":null},{"id":"W2101835200","doi":"10.1109/icpr.1992.201853","title":"Background region-based algorithm for the segmentation of connected digits","year":2003,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Segmentation; Computer science; Pixel; Character (mathematics); Image segmentation; Artificial intelligence; Connected component; Algorithm; Pattern recognition (psychology); Connected-component labeling; Scale-space segmentation; Computer vision; Mathematics","score_opus":0.03666728385650789,"score_gpt":0.27963310848459116,"score_spread":0.24296582462808328,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2101835200","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":[0.0003139381,0.000037794056,0.9967308,0.00036826654,0.000082356746,0.0004651667,0.0000031744094,0.00018790714,0.001810584],"genre_scores_gemma":[0.1309516,0.00001235079,0.86759424,0.00081711326,0.000015339981,0.00016310245,0.00000773042,0.000008414592,0.00043009216],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99934936,0.000053167194,0.00017819135,0.00016617753,0.00013377902,0.00011933623],"domain_scores_gemma":[0.9988055,0.00058513996,0.000088795765,0.00026918913,0.00022328303,0.000028070901],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021753807,0.00007333168,0.000086841785,0.00005653921,0.00007742482,0.000072912604,0.00027485035,0.000035015077,0.000031075066],"category_scores_gemma":[0.00004570886,0.00005049029,0.000057704165,0.00025567278,0.000039924325,0.00022323732,0.000015275022,0.000033271222,0.000005923536],"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":[0.000002229941,0.000066154826,0.000031448584,0.000011623513,0.000017558488,8.571518e-7,0.00006078573,0.000003404966,0.0007548644,0.048465278,0.0033501645,0.94723564],"study_design_scores_gemma":[0.00097071315,0.00022837822,0.00013888499,0.000025065858,0.000014115507,0.000012439366,0.0001427186,0.17456256,0.8006124,0.015739772,0.007355489,0.00019744341],"about_ca_topic_score_codex":0.000012750658,"about_ca_topic_score_gemma":0.0000039267325,"teacher_disagreement_score":0.9470382,"about_ca_system_score_codex":0.000020593196,"about_ca_system_score_gemma":0.00006444944,"threshold_uncertainty_score":0.20589343},"labels":[],"label_agreement":null},{"id":"W2103090617","doi":"10.1109/have.2003.1244729","title":"Optical character recognition for model-based object recognition applications","year":2004,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Optical character recognition; Character recognition; Cognitive neuroscience of visual object recognition; Character (mathematics); Artificial intelligence; 3D single-object recognition; Intelligent character recognition; Pattern recognition (psychology); Moment (physics); Object (grammar); Fourier transform; Feature extraction; Speech recognition; Computer vision; Image (mathematics); Mathematics","score_opus":0.037449591039336184,"score_gpt":0.2779836298658601,"score_spread":0.24053403882652394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103090617","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":[0.001697321,0.0000069301536,0.98812574,0.0017724939,0.00006121528,0.0014031987,0.000052437943,0.001268933,0.005611741],"genre_scores_gemma":[0.15677343,0.000010443024,0.83731675,0.0023199557,0.00011737343,0.0030364788,0.00031382995,0.00002303711,0.00008868844],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99854493,0.000023968892,0.0003436038,0.0005428232,0.00021678676,0.0003278658],"domain_scores_gemma":[0.9987811,0.0001283934,0.00009760422,0.00042249408,0.0004312565,0.00013917607],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032705304,0.00018583238,0.00017440182,0.00023020481,0.00018165179,0.00018685553,0.00040553967,0.00015497212,0.000046787816],"category_scores_gemma":[0.000059836308,0.00018418737,0.00015240507,0.00033962034,0.000050425646,0.00072179013,0.00004972987,0.00014022,0.00047170144],"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":[0.000023251125,0.00041396622,0.0000036718454,0.00005108956,0.000014868699,0.0000015907916,0.00005990451,0.00008595505,0.00674323,0.01925553,0.00040770558,0.97293925],"study_design_scores_gemma":[0.0012823204,0.00021457674,0.000037423175,0.00006849431,0.000025869685,0.000017801427,0.000008273305,0.06408614,0.45789737,0.47457445,0.0013016427,0.0004856382],"about_ca_topic_score_codex":0.0000060962816,"about_ca_topic_score_gemma":0.000007869896,"teacher_disagreement_score":0.9724536,"about_ca_system_score_codex":0.00009156345,"about_ca_system_score_gemma":0.00017785981,"threshold_uncertainty_score":0.7510943},"labels":[],"label_agreement":null},{"id":"W2104327860","doi":"10.1007/978-3-540-31880-4_53","title":"A Multi-objective Memetic Algorithm for Intelligent Feature Extraction","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":14,"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":"Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Computer science; Memetic algorithm; Domain (mathematical analysis); Coding (social sciences); Artificial intelligence; Genetic algorithm; Set (abstract data type); Optimization problem; Context (archaeology); Representation (politics); Machine learning; Algorithm; Mathematics","score_opus":0.023686369001430257,"score_gpt":0.2906340616218436,"score_spread":0.2669476926204133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2104327860","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":[0.0000023975836,0.0006262579,0.99435747,0.0007632546,0.001538283,0.0014425309,0.00002418548,0.000520703,0.00072492094],"genre_scores_gemma":[0.001465068,0.0001418216,0.99495465,0.0011899578,0.0007746661,0.00011780317,0.000015070206,0.0000541136,0.0012868287],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958287,0.000044543634,0.0005545743,0.0019509455,0.00086768804,0.0007535837],"domain_scores_gemma":[0.99692726,0.0006186591,0.00040508606,0.0011369883,0.000703496,0.00020849524],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010197813,0.0006803155,0.00061846146,0.0013129192,0.00031354913,0.0006190948,0.0025544695,0.0006121773,0.000031382315],"category_scores_gemma":[0.00013577759,0.0006441951,0.00028796963,0.00061448116,0.00045519756,0.00091058254,0.0007196504,0.001112069,0.000057876376],"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":[0.0000033585086,0.000054464315,0.0000011337723,0.000021065553,0.00001493262,0.000021920237,0.00038804952,0.00041785708,0.00022670778,0.00086367753,0.00007008906,0.99791676],"study_design_scores_gemma":[0.00043454306,0.00040857444,0.000027512835,0.0005131472,0.000023946754,0.00020834064,5.620548e-7,0.8799417,0.0340794,0.070715964,0.012562711,0.0010835673],"about_ca_topic_score_codex":0.000014250044,"about_ca_topic_score_gemma":0.00008835125,"teacher_disagreement_score":0.9968332,"about_ca_system_score_codex":0.00076827634,"about_ca_system_score_gemma":0.0004906889,"threshold_uncertainty_score":0.99960095},"labels":[],"label_agreement":null},{"id":"W2105290303","doi":"10.1109/icpr.2002.1047810","title":"Applying compiler techniques to diagram recognition","year":2003,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"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; Compiler; Parsing; Programming language; Natural language processing; Artificial intelligence; Compiler construction","score_opus":0.02997458595742849,"score_gpt":0.2721530483834389,"score_spread":0.2421784624260104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105290303","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":[0.0008634178,0.000009732255,0.8776416,0.0003261328,0.00009278913,0.00087956345,0.000001873283,0.0022934072,0.1178915],"genre_scores_gemma":[0.17403519,0.0000161141,0.81925756,0.004669399,0.000034646,0.0015212197,0.0000054972097,0.000015668973,0.00044470024],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99870235,0.000105663596,0.00024932946,0.00041162546,0.00023105869,0.00029998738],"domain_scores_gemma":[0.9991209,0.00006954025,0.0000489966,0.00043440756,0.00016652128,0.00015963211],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004604943,0.00015441467,0.00015530376,0.0002549205,0.00011402432,0.00020533164,0.0004386505,0.00008385671,0.0002555133],"category_scores_gemma":[0.00011055787,0.00014539114,0.00006360251,0.0005932758,0.000020134583,0.00047991582,0.00010530475,0.00012943205,0.0008474129],"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":[9.72827e-7,0.000058805068,0.00006657823,0.000005653558,0.0000044233816,0.0000048084335,0.00005869955,1.2588124e-7,0.0034800917,0.021165246,0.010610227,0.96454436],"study_design_scores_gemma":[0.00010002512,0.0001400408,0.000068627014,0.00004457989,0.0000033490182,0.000042424417,0.000021179652,0.00019249544,0.77791506,0.050328158,0.17076497,0.0003790822],"about_ca_topic_score_codex":0.000016553646,"about_ca_topic_score_gemma":0.000007149316,"teacher_disagreement_score":0.9641653,"about_ca_system_score_codex":0.000047818725,"about_ca_system_score_gemma":0.00003023201,"threshold_uncertainty_score":0.99993056},"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":"W2109663225","doi":"10.1142/s0218001404003629","title":"STUDY OF PERCEPTUAL SIMILARITY BETWEEN DIFFERENT LEXICONS","year":2004,"lang":"en","type":"article","venue":"International Journal of Pattern Recognition and Artificial Intelligence","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"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; Similarity (geometry); Artificial intelligence; Perception; Word error rate; Pattern recognition (psychology); Feature (linguistics); Set (abstract data type); Representation (politics); Natural language processing; Speech recognition; Sequence (biology); Image (mathematics); Linguistics; Psychology","score_opus":0.13680864188787842,"score_gpt":0.34698867681264006,"score_spread":0.21018003492476164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109663225","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":[0.56429267,0.000008679728,0.43476707,0.00049943745,0.0002610019,0.00008996918,0.000017792074,0.000020348909,0.000043040778],"genre_scores_gemma":[0.9967028,0.000060698185,0.0028100803,0.00017080293,0.00023559174,0.000004765762,0.0000061135243,0.000007225424,0.000001934761],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9980534,0.00010810277,0.00089934864,0.0002126649,0.00059051235,0.00013600255],"domain_scores_gemma":[0.99828035,0.0001463732,0.000505163,0.00012844671,0.0008266928,0.0001129926],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037578068,0.0001471464,0.00026700652,0.000379067,0.000057193418,0.00015469897,0.0006805013,0.00006467295,0.00010622986],"category_scores_gemma":[0.00011215447,0.00012931987,0.000109331006,0.000129946,0.00009680391,0.0005290381,0.00016071831,0.00026790737,0.00002264008],"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":[0.000026201378,0.0010641915,0.0049377894,0.0000073057226,0.0001273741,0.00008261189,0.0040025287,0.000016086495,0.0018277066,0.0004993986,0.000009656292,0.98739916],"study_design_scores_gemma":[0.0011238578,0.004401358,0.0493503,0.0008045582,0.00013463761,0.0005746438,0.010935805,0.00053328235,0.50365776,0.42765594,0.000050811712,0.00077703374],"about_ca_topic_score_codex":0.0000683286,"about_ca_topic_score_gemma":0.00006639397,"teacher_disagreement_score":0.9866221,"about_ca_system_score_codex":0.000057812085,"about_ca_system_score_gemma":0.00004673513,"threshold_uncertainty_score":0.52735114},"labels":[],"label_agreement":null},{"id":"W2109683879","doi":"10.1109/icdar.1995.598975","title":"An extended-shadow-code based approach for off-line signature verification. II. Evaluation of several multi-classifier combination strategies","year":2002,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"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; Classifier (UML); Artificial intelligence; Signature (topology); Pattern recognition (psychology); Machine learning; Data mining; Programming language; Mathematics","score_opus":0.08746193863621023,"score_gpt":0.32566464355170277,"score_spread":0.23820270491549256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109683879","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":[0.0025193102,0.00010864544,0.9922498,0.00030396393,0.00007122259,0.0011782768,0.000027266533,0.00043663383,0.003104914],"genre_scores_gemma":[0.6248077,0.00000607049,0.37442133,0.0001233695,0.000019705572,0.00025063872,0.0001486496,0.000010600462,0.00021193756],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99802244,0.00022148497,0.00039831403,0.00050763687,0.000639707,0.00021043606],"domain_scores_gemma":[0.9977185,0.00006529577,0.00022289816,0.0006104492,0.0013100945,0.00007272693],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011372454,0.00018400935,0.0001997436,0.00023432785,0.00017244184,0.00014583653,0.00059703115,0.00018991677,0.00018224676],"category_scores_gemma":[0.00008822533,0.00017083816,0.00008969454,0.00038574796,0.000060797942,0.0014141034,0.000037141202,0.00013650075,0.0000048118636],"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":[0.00005493955,0.007989064,0.000045426055,0.0002114403,0.00007925585,8.6278334e-7,0.0016141881,0.018981928,0.050553475,0.13884638,0.0065709497,0.7750521],"study_design_scores_gemma":[0.0014894173,0.0003412792,0.00069401425,0.000013166804,0.000026122718,0.0000016112953,0.00010253985,0.9522074,0.039461307,0.0053308117,0.00012329733,0.00020903611],"about_ca_topic_score_codex":0.000009992128,"about_ca_topic_score_gemma":0.000010804294,"teacher_disagreement_score":0.93322545,"about_ca_system_score_codex":0.00008217695,"about_ca_system_score_gemma":0.00011777345,"threshold_uncertainty_score":0.6966578},"labels":[],"label_agreement":null},{"id":"W2110003681","doi":"10.1109/icpr.2002.1047858","title":"Efficient estimation of pen trajectory from off-line handwritten words","year":2005,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal; Concordia University","funders":"","keywords":"Computer science; Trajectory; Speech recognition; Line (geometry); Artificial intelligence; Estimation; Pattern recognition (psychology); Computer vision; Mathematics; Engineering","score_opus":0.015569416082776706,"score_gpt":0.2612524065158973,"score_spread":0.2456829904331206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110003681","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":[0.15745263,0.00013337168,0.83596236,0.000689289,0.00006950342,0.00018717673,0.0000063626203,0.00046148634,0.0050378344],"genre_scores_gemma":[0.6613875,0.000008843933,0.33800024,0.00021817195,0.000053743057,0.000015139833,0.000009255869,0.0000066248244,0.0003004971],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987281,0.000056201905,0.00037783963,0.00031660328,0.00033443974,0.00018680409],"domain_scores_gemma":[0.9991149,0.00011876585,0.00012078165,0.00045835032,0.000108400156,0.000078849174],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028647739,0.00013303485,0.00020253086,0.00016461458,0.000048828384,0.00005989716,0.00055916095,0.000076963144,0.0003411387],"category_scores_gemma":[0.000047173427,0.00011844924,0.000082007304,0.00028529007,0.0000484875,0.00021586055,0.00013059055,0.000101093414,0.00013898418],"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":[0.000007082925,0.00022122801,0.000051703064,0.000008224535,0.000015793174,0.0000020807709,0.00060320314,0.0036371944,0.0051620533,0.0026616217,0.0010318899,0.9865979],"study_design_scores_gemma":[0.000367637,0.000083515064,0.0012277969,0.000045445326,0.000008905482,0.0000039522824,0.000019841686,0.7573003,0.23827325,0.001454402,0.00103745,0.00017745692],"about_ca_topic_score_codex":0.00008135451,"about_ca_topic_score_gemma":0.000038160826,"teacher_disagreement_score":0.98642045,"about_ca_system_score_codex":0.00005035578,"about_ca_system_score_gemma":0.000054904747,"threshold_uncertainty_score":0.483022},"labels":[],"label_agreement":null},{"id":"W2110834413","doi":"10.1145/2037342.2037344","title":"Style-based retrieval for ancient Syriac manuscripts","year":2011,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Handwriting; Computer science; Style (visual arts); Set (abstract data type); Identification (biology); Natural language processing; Artificial intelligence; Character (mathematics); Affine transformation; Information retrieval; Economic shortage; Writing style; Feature (linguistics); Task (project management); Linguistics; Art; Literature; Mathematics; Programming language; Philosophy","score_opus":0.062413179254914866,"score_gpt":0.2597821515741907,"score_spread":0.19736897231927586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110834413","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":[0.004612293,0.000021516045,0.9752982,0.00025330673,0.0002860261,0.0004645217,0.000005925289,0.0009149796,0.018143233],"genre_scores_gemma":[0.41096362,0.0000017287182,0.58587134,0.0021197468,0.000038008595,0.000063190615,0.0000045029587,0.000010905085,0.0009269723],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99889225,0.00003301808,0.00020802298,0.00036328606,0.00020724826,0.00029618415],"domain_scores_gemma":[0.999082,0.000057147845,0.00006400238,0.0004863166,0.00019799627,0.00011249488],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042865524,0.0001196277,0.00012839837,0.0001360228,0.00008645432,0.00008230394,0.00065861485,0.00006918076,0.00021055828],"category_scores_gemma":[0.000063181185,0.000104248305,0.00009877595,0.000251759,0.000036820966,0.00031924626,0.0000911969,0.00006397791,0.000114965726],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034266894,0.0013983073,0.0008340986,0.00016670315,0.0000757941,0.000065554974,0.0018192206,9.709032e-7,0.03417623,0.4416232,0.17728871,0.34220853],"study_design_scores_gemma":[0.00080580515,0.0005835975,0.0016091185,0.000029925981,0.000009010735,0.000007463527,0.000020041793,0.012769156,0.9457624,0.0150150815,0.023018653,0.000369722],"about_ca_topic_score_codex":0.000017478422,"about_ca_topic_score_gemma":0.0000043678347,"teacher_disagreement_score":0.9115862,"about_ca_system_score_codex":0.000039013477,"about_ca_system_score_gemma":0.00006930165,"threshold_uncertainty_score":0.42511225},"labels":[],"label_agreement":null},{"id":"W2110945668","doi":"10.1109/icfhr.2010.125","title":"Error Reduction Based on Error Categorization in Arabic Handwritten Numeral Recognition","year":2010,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Numeral system; Word error rate; Categorization; Computer science; Speech recognition; Pattern recognition (psychology); Reliability (semiconductor); Arabic; Arabic numerals; Artificial intelligence; Reduction (mathematics); Digit recognition; Error detection and correction; Intelligent word recognition; Intelligent character recognition; Mathematics; Algorithm; Image (mathematics); Character recognition; Artificial neural network; Linguistics","score_opus":0.02213760232286031,"score_gpt":0.2668816595531024,"score_spread":0.2447440572302421,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110945668","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":[0.2053434,0.00000445262,0.7676363,0.0047873002,0.001523011,0.0009721472,0.000009858492,0.001737777,0.017985735],"genre_scores_gemma":[0.9249969,0.0000030952608,0.073587425,0.0006501928,0.0001391503,0.00016293568,0.00010779185,0.000020454076,0.00033206315],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99823,0.00013154659,0.00038640478,0.0005869072,0.00033892138,0.00032621785],"domain_scores_gemma":[0.9990077,0.00006154355,0.0001250095,0.0005099411,0.0001864925,0.000109329565],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055912184,0.00021058446,0.00018597195,0.0006064259,0.0001176908,0.00018597966,0.0004222055,0.00023779135,0.00038305897],"category_scores_gemma":[0.000115634495,0.0002017997,0.00006632215,0.0007838926,0.000051116298,0.0009956381,0.000045294033,0.00051823806,0.00035815078],"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":[0.00012578887,0.0013113548,0.0013883852,0.000061300896,0.000015572183,0.000039966508,0.00069849484,0.0001706507,0.14268132,0.013837394,0.0059787207,0.83369106],"study_design_scores_gemma":[0.0026449806,0.00078456197,0.010836242,0.00015954283,0.000018147623,0.00011340258,0.00010814282,0.4397149,0.48396817,0.057644993,0.0026700401,0.0013368701],"about_ca_topic_score_codex":0.00017392231,"about_ca_topic_score_gemma":0.0001929166,"teacher_disagreement_score":0.8323542,"about_ca_system_score_codex":0.00007480233,"about_ca_system_score_gemma":0.00009560342,"threshold_uncertainty_score":0.8229153},"labels":[],"label_agreement":null},{"id":"W2111318059","doi":"10.1109/icdar.2009.251","title":"Pen Acoustic Emissions for Text and Gesture Recognition","year":2009,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"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; Cursive; Speech recognition; Gesture; Similarity (geometry); Artificial intelligence; SIGNAL (programming language); Template matching; Pattern recognition (psychology); Image (mathematics)","score_opus":0.02315801403522359,"score_gpt":0.2754912154432502,"score_spread":0.2523332014080266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111318059","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":[0.00363453,0.000049074326,0.9829811,0.0037677696,0.000046732705,0.00038585882,0.0000056874774,0.0006174034,0.008511839],"genre_scores_gemma":[0.618917,0.00006184021,0.37697938,0.0026077975,0.00006902496,0.000055453012,0.0000132770165,0.0000065820423,0.0012896471],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993211,0.000018819877,0.00013116025,0.00026657572,0.00009399251,0.00016832074],"domain_scores_gemma":[0.9994543,0.00010630957,0.000037754027,0.00019145239,0.00011060201,0.00009954165],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015245966,0.00009460425,0.00009998964,0.00008431612,0.00012668445,0.00013133182,0.00021426087,0.00007945823,0.000058263027],"category_scores_gemma":[0.000102636586,0.00007876796,0.00003636132,0.0001364435,0.000015753654,0.00036197138,0.00004255907,0.00007699256,0.000028506325],"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":[0.0000037953666,0.000047026613,0.000011170384,0.000009050944,0.000003306998,0.0000022436457,0.00011967755,2.5447542e-7,0.009991782,0.0022728306,0.017031742,0.97050714],"study_design_scores_gemma":[0.0017174319,0.0016680488,0.008898454,0.0002707359,0.00006165461,0.00028582514,0.00015472563,0.030889878,0.15434577,0.7757616,0.024742555,0.001203327],"about_ca_topic_score_codex":0.0000026956468,"about_ca_topic_score_gemma":0.0000032222101,"teacher_disagreement_score":0.9693038,"about_ca_system_score_codex":0.000013007196,"about_ca_system_score_gemma":0.000024136154,"threshold_uncertainty_score":0.3212064},"labels":[],"label_agreement":null},{"id":"W2111676986","doi":"10.1109/icdar.2009.104","title":"Application of Multi-Level Classifiers and Clustering for Automatic Word Spotting in Historical Document Images","year":2009,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":53,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Spotting; Computer science; Artificial intelligence; Word (group theory); Historical document; Preprocessor; Natural language processing; Cluster analysis; Pattern recognition (psychology); Text segmentation; Segmentation; Speech recognition; Mathematics","score_opus":0.03382729573277333,"score_gpt":0.2929195803504617,"score_spread":0.25909228461768835,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111676986","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":[0.0060821385,0.000038419177,0.99235827,0.0007599176,0.00002246218,0.00037999358,5.2648994e-7,0.00017738358,0.00018089908],"genre_scores_gemma":[0.4774685,0.0000058243045,0.5223173,0.00007599878,0.0000053390454,0.000044012417,5.3375703e-7,0.0000022199445,0.000080262704],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992569,0.00002011065,0.0002809956,0.00021457903,0.00009335174,0.00013406044],"domain_scores_gemma":[0.99958456,0.000079721656,0.00009298599,0.0001614379,0.000043376498,0.000037941358],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030832505,0.00007556269,0.00013975675,0.00014462031,0.0000305356,0.000036341557,0.00018934542,0.00004217545,0.0000017190837],"category_scores_gemma":[0.000042865042,0.000071642455,0.000026852824,0.00015652849,0.000012691993,0.0002656725,0.00005323617,0.000048884493,8.610995e-7],"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":[0.0000017347191,0.00003832162,0.00016584908,0.000029553928,0.0000013662547,4.25387e-7,0.0001544251,0.0000031482693,0.005113179,0.0009876435,0.00010402855,0.99340034],"study_design_scores_gemma":[0.00094689237,0.0001664475,0.036949515,0.00010629678,0.000005870648,0.000010301464,0.00005804127,0.9109047,0.038305588,0.011844342,0.00043790945,0.00026408],"about_ca_topic_score_codex":0.00003808147,"about_ca_topic_score_gemma":0.000014454676,"teacher_disagreement_score":0.9931362,"about_ca_system_score_codex":0.00016572056,"about_ca_system_score_gemma":0.000013817765,"threshold_uncertainty_score":0.29214945},"labels":[],"label_agreement":null},{"id":"W2112792356","doi":"10.1109/iwfhr.2004.41","title":"Extraction of Hybrid Complex Wavelet Features for the Verification of Handwritten Numerals","year":2004,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Numeral system; Feature extraction; Pattern recognition (psychology); Computer science; Artificial intelligence; Wavelet; Wavelet transform; Classifier (UML); Wavelet packet decomposition; Speech recognition","score_opus":0.03134073346791645,"score_gpt":0.29745683982856846,"score_spread":0.266116106360652,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112792356","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":[0.0075411447,0.00006139382,0.9884161,0.0022277937,0.00007177862,0.00047102582,0.000015306907,0.0001255252,0.0010699404],"genre_scores_gemma":[0.8072384,0.00004018239,0.1923252,0.00018267715,0.000025541756,0.00005729309,0.000011931989,0.0000054302063,0.00011331814],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992087,0.00002683587,0.00027974532,0.00018058535,0.00018599951,0.000118117285],"domain_scores_gemma":[0.9989392,0.00018235113,0.00019441085,0.00039747226,0.00026206882,0.000024452202],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030629244,0.00008409137,0.00014650541,0.00007870166,0.00007811958,0.000036782625,0.00046537037,0.000030576815,0.00003012293],"category_scores_gemma":[0.000056421235,0.000059005277,0.000093640374,0.0001639603,0.0000648195,0.00028880616,0.0000407645,0.00005947373,0.0000043412165],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048996328,0.0003242318,0.00002810153,0.000109452616,0.00007773362,0.000001280902,0.00054615753,0.000089384295,0.46404365,0.17187724,0.01238607,0.3504677],"study_design_scores_gemma":[0.00038126923,0.00012324726,0.0036465775,0.000024719251,0.000011145905,0.000028311297,0.0000430387,0.0019492848,0.9650654,0.02599368,0.0026442711,0.000089010726],"about_ca_topic_score_codex":0.00012528706,"about_ca_topic_score_gemma":0.000008660509,"teacher_disagreement_score":0.7996973,"about_ca_system_score_codex":0.000023349095,"about_ca_system_score_gemma":0.000041376534,"threshold_uncertainty_score":0.24061655},"labels":[],"label_agreement":null},{"id":"W2113243342","doi":"10.1109/icmla.2008.111","title":"Online Writer-Independent Character Recognition Using a Novel Relational Context Representation","year":2008,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Intelligent character recognition; Handwriting; Handwriting recognition; Artificial intelligence; Classifier (UML); Pattern recognition (psychology); Support vector machine; Feature extraction; Natural language processing; Intelligent word recognition; Character (mathematics); Representation (politics); Optical character recognition; Feature (linguistics); Speech recognition; Character recognition; Image (mathematics)","score_opus":0.13940729914102146,"score_gpt":0.3073723931655371,"score_spread":0.16796509402451565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2113243342","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":[0.26490903,0.000010623353,0.7325541,0.00046139426,0.00014761601,0.00023216952,0.000024323297,0.00041324826,0.001247515],"genre_scores_gemma":[0.5864515,0.000021011787,0.4117412,0.0010900453,0.00014390495,0.00002126302,0.00014718859,0.000012475464,0.00037143542],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983875,0.00006786081,0.00042141927,0.00046236045,0.00044176288,0.00021905774],"domain_scores_gemma":[0.99890286,0.00010276682,0.00017570438,0.00035553734,0.000368982,0.00009413074],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019896828,0.0001534374,0.00016548153,0.0002546919,0.00019890186,0.000079959034,0.00028776025,0.000115672614,0.00038760132],"category_scores_gemma":[0.00006114628,0.000152915,0.000095769145,0.00036166806,0.00005016476,0.0015535853,0.00012942064,0.00019410359,0.00017532974],"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":[0.00012181185,0.0030052299,0.020873833,0.000052675554,0.00021155732,0.00023827243,0.004197118,0.00002977965,0.19086328,0.020329796,0.00435029,0.75572634],"study_design_scores_gemma":[0.007164336,0.000601981,0.29652247,0.00048217495,0.00007798396,0.0074536875,0.00043402263,0.35438702,0.29532555,0.02630068,0.008392054,0.002858055],"about_ca_topic_score_codex":0.00009945388,"about_ca_topic_score_gemma":0.000019199973,"teacher_disagreement_score":0.7528683,"about_ca_system_score_codex":0.00009496566,"about_ca_system_score_gemma":0.000084532265,"threshold_uncertainty_score":0.6235693},"labels":[],"label_agreement":null},{"id":"W2114315283","doi":"10.1145/2037342.2037359","title":"Combining statistical and geometrical classifiers for text extraction in multispectral document images","year":2011,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Multispectral image; Weighting; Feature extraction; Pattern recognition (psychology); Grayscale; Classifier (UML); Image (mathematics)","score_opus":0.03855397325297608,"score_gpt":0.3057172324178245,"score_spread":0.2671632591648484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2114315283","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":[0.00844939,0.000020831321,0.98649096,0.0001617437,0.00007656608,0.00028972217,0.0000034980574,0.00019580651,0.004311507],"genre_scores_gemma":[0.56035525,0.000016283519,0.4394054,0.00007012012,0.000007074108,0.00005426148,0.0000017304051,0.000004092259,0.00008578459],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990469,0.000042217278,0.00022948488,0.00031368446,0.00012034369,0.00024733972],"domain_scores_gemma":[0.99936205,0.0003184192,0.00004443756,0.00013455465,0.000044190067,0.00009633926],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033454603,0.000097602395,0.00013467157,0.00030608944,0.000053020674,0.00010077139,0.00017194366,0.000062708474,0.00009344508],"category_scores_gemma":[0.00012634645,0.00008909749,0.00002441554,0.0002528959,0.000059240905,0.00053510885,0.00007186707,0.00012464134,0.000011611112],"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":[0.00004143622,0.00026939166,0.0040716976,0.000027295515,0.000014192162,0.000036091064,0.0006868858,2.7685257e-7,0.0019471826,0.26912826,0.002179262,0.721598],"study_design_scores_gemma":[0.004918702,0.002288378,0.31381416,0.00009760296,0.000030171417,0.00019958397,0.00065762305,0.059754483,0.238848,0.37620878,0.0018867464,0.0012957602],"about_ca_topic_score_codex":0.00014247204,"about_ca_topic_score_gemma":0.000022177339,"teacher_disagreement_score":0.7203023,"about_ca_system_score_codex":0.000054090397,"about_ca_system_score_gemma":0.000020252122,"threshold_uncertainty_score":0.36332902},"labels":[],"label_agreement":null},{"id":"W2114660801","doi":"10.1109/caia.1990.89205","title":"Letter pattern recognition","year":2002,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Block (permutation group theory); Artificial intelligence; Matching (statistics); Representation (politics); Character (mathematics); Pattern recognition (psychology); Segmentation; Position (finance); Optical character recognition; Natural language processing; Computer vision; Image (mathematics); Mathematics","score_opus":0.03697278254293288,"score_gpt":0.23435777596605853,"score_spread":0.19738499342312565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2114660801","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":[0.0012008506,0.000016274822,0.9194079,0.005692922,0.00011738063,0.00009163751,0.0000012188328,0.0009989362,0.0724729],"genre_scores_gemma":[0.7632321,0.000058344136,0.18591242,0.04689769,0.00028554577,0.00008409796,0.0000070848537,0.000018043416,0.003504679],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99928606,0.00003508578,0.00013403935,0.00022919996,0.00014665553,0.00016895945],"domain_scores_gemma":[0.99954724,0.000029084924,0.000031280557,0.00028492758,0.000055043034,0.000052441377],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00008975256,0.000080197686,0.000069133705,0.000092772956,0.000048740323,0.000121357305,0.00033360437,0.000045293044,0.0026524249],"category_scores_gemma":[0.000011295419,0.00007195018,0.000044141554,0.00016735494,0.000015541305,0.0005294219,0.0000782558,0.000082129416,0.0050520925],"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":[7.3559185e-8,0.000025453457,0.000044019234,0.0000019627312,0.0000021223982,0.000007798371,0.00005350551,1.2175671e-8,0.0001613655,0.0001130057,0.11594719,0.8836435],"study_design_scores_gemma":[0.0012555969,0.00041990203,0.0015463372,0.000120662626,0.000015882644,0.0003130137,0.000017631226,0.08684699,0.329935,0.055236205,0.5225832,0.0017095751],"about_ca_topic_score_codex":0.000011250351,"about_ca_topic_score_gemma":0.0000034875543,"teacher_disagreement_score":0.8819339,"about_ca_system_score_codex":0.000014670153,"about_ca_system_score_gemma":0.0000018140706,"threshold_uncertainty_score":0.9982593},"labels":[],"label_agreement":null},{"id":"W2115496941","doi":"10.1109/tpami.2008.254","title":"Leave-One-Out-Training and Leave-One-Out-Testing Hidden Markov Models for a Handwritten Numeral Recognizer: The Implications of a Single Classifier and Multiple Classifications","year":2008,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; University of Toronto","funders":"","keywords":"Hidden Markov model; Classifier (UML); Numeral system; Computer science; Artificial intelligence; Pattern recognition (psychology); Speech recognition; Sequence labeling; Noise (video); Handwriting recognition; Sequence (biology); Machine learning; Feature extraction; Engineering","score_opus":0.13076417778571175,"score_gpt":0.29496038741358327,"score_spread":0.16419620962787151,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115496941","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":[0.012173487,0.00022904018,0.9847443,0.0016931271,0.000053281437,0.00055869634,0.00020943095,0.00014871653,0.00018992454],"genre_scores_gemma":[0.9354516,0.0006276578,0.06310096,0.00041361607,0.00002976363,0.00021472607,0.000016573822,0.00002408087,0.00012102249],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99778616,0.00013890138,0.0007109436,0.0007520655,0.00026582528,0.00034609315],"domain_scores_gemma":[0.99742883,0.0011699691,0.00030122756,0.0005936506,0.00033732198,0.00016900292],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00047285188,0.00029586628,0.00051113736,0.00051099656,0.000809498,0.0002014351,0.00047563805,0.00012840626,0.000016995493],"category_scores_gemma":[0.000055250104,0.0002594677,0.00022089342,0.0008193306,0.00034762756,0.0004852877,0.000023774488,0.000314671,0.000002648555],"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":[0.000015490245,0.00025961318,0.00081484,0.00003359587,0.00044074084,9.651719e-7,0.0033581783,0.00016662401,0.0067239916,0.00011218649,0.000021251339,0.98805255],"study_design_scores_gemma":[0.00081179274,0.0006945467,0.0063779866,0.00026499052,0.0018946396,0.00014171026,0.0011940221,0.8186371,0.15652893,0.012118332,0.00018664447,0.0011492955],"about_ca_topic_score_codex":0.0004089287,"about_ca_topic_score_gemma":0.0018204673,"teacher_disagreement_score":0.98690325,"about_ca_system_score_codex":0.000034932724,"about_ca_system_score_gemma":0.00005621104,"threshold_uncertainty_score":0.99998575},"labels":[],"label_agreement":null},{"id":"W2115575843","doi":"10.1109/icdar.1997.619857","title":"A hybrid classifier for recognizing handwritten numerals","year":2002,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Classifier (UML); Computer science; Artificial intelligence; Pattern recognition (psychology); Numeral system; Character encoding; Artificial neural network; Character recognition; Character (mathematics); Mathematics","score_opus":0.05055425275056022,"score_gpt":0.2621375771525208,"score_spread":0.21158332440196057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115575843","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":[0.0010139118,0.0001124537,0.9495283,0.0035609833,0.00019557621,0.00046704526,0.000007220504,0.0011903709,0.04392418],"genre_scores_gemma":[0.2805715,0.00009749148,0.6944261,0.004868996,0.00021277364,0.00043745735,0.0000079686715,0.000034890898,0.019342799],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99858487,0.000043584645,0.00030352495,0.00047377433,0.00019421773,0.00040005753],"domain_scores_gemma":[0.99897724,0.00017419273,0.000079248086,0.00046568675,0.00017679742,0.00012682799],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030474557,0.00016670117,0.00020583028,0.00016245314,0.00016784438,0.00029075623,0.00066456175,0.00006438539,0.0006578682],"category_scores_gemma":[0.000102734615,0.00015018646,0.00014348446,0.00019790886,0.000031704498,0.00074063387,0.00012704312,0.000109589506,0.00049066707],"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":[0.0000025055133,0.00008550328,0.000036416033,0.000017305078,0.000021172487,0.000009484135,0.00012443309,1.7350074e-7,0.0018881016,0.013247201,0.2074785,0.7770892],"study_design_scores_gemma":[0.0015133774,0.00041176792,0.00008366,0.00010752652,0.000023179773,0.0001967425,0.000031225576,0.15166108,0.3037646,0.111994974,0.42915773,0.0010541315],"about_ca_topic_score_codex":0.000008641958,"about_ca_topic_score_gemma":0.000002786157,"teacher_disagreement_score":0.7760351,"about_ca_system_score_codex":0.000034611785,"about_ca_system_score_gemma":0.00001272677,"threshold_uncertainty_score":0.72031957},"labels":[],"label_agreement":null},{"id":"W2116826706","doi":"10.1145/1384429.1384454","title":"Managing ambiguity in mathematical matrices","year":2007,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Ambiguity; Ellipsis (linguistics); Row; Computer science; Matrix (chemical analysis); Row and column spaces; Algorithm; Cluster analysis; Theoretical computer science; Algebra over a field; Mathematics; Artificial intelligence; Programming language; Pure mathematics","score_opus":0.018740211753234606,"score_gpt":0.2869817390468414,"score_spread":0.2682415272936068,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2116826706","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":[0.008153816,0.00002476145,0.86903393,0.00050361047,0.000028022352,0.000087860346,8.7582286e-8,0.00046673653,0.12170117],"genre_scores_gemma":[0.57992554,0.000020275473,0.41912952,0.00045007502,0.000018923656,0.0000064467017,2.8480514e-7,0.000004674799,0.000444298],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991524,0.000018394838,0.00022507273,0.00019283887,0.00017392501,0.00023737155],"domain_scores_gemma":[0.99953675,0.00010058991,0.00003097437,0.0002484384,0.000026689364,0.000056577763],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000937888,0.0000692763,0.000096711505,0.0002377333,0.0000269656,0.000055901655,0.00045360404,0.00004123967,0.0001145325],"category_scores_gemma":[0.000028976574,0.000060752052,0.000028910474,0.0004445937,0.00001831912,0.00035049822,0.00016141497,0.0000925766,0.0002517852],"study_design_candidate":"theoretical_or_conceptual","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":[0.0000024239694,0.00012988952,0.0010845751,0.00003793805,0.0000035873675,0.00012419799,0.00034478688,5.052522e-7,0.0005477107,0.3003732,0.0011917279,0.6961595],"study_design_scores_gemma":[0.00026581122,0.000046926376,0.007428351,0.000074188974,0.0000021464527,0.000065987515,0.00009534631,0.013318258,0.06945204,0.9074044,0.0015361554,0.0003103897],"about_ca_topic_score_codex":0.00003243406,"about_ca_topic_score_gemma":0.00004155755,"teacher_disagreement_score":0.69584906,"about_ca_system_score_codex":0.000034147473,"about_ca_system_score_gemma":0.0000098913215,"threshold_uncertainty_score":0.32362735},"labels":[],"label_agreement":null},{"id":"W2118845658","doi":"10.1109/icdar.2005.23","title":"A new method of recognizing Chinese fonts","year":2005,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Hilbert–Huang transform; Pattern recognition (psychology); Artificial intelligence; Classifier (UML); Feature (linguistics); Feature vector; Feature extraction; Chinese characters; Speech recognition; Mode (computer interface); Computer vision","score_opus":0.019998405457766735,"score_gpt":0.3218083564132845,"score_spread":0.30180995095551777,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2118845658","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":[0.000978595,0.000037403628,0.9580756,0.001067998,0.000050120794,0.000100968944,5.054513e-7,0.00042523706,0.039263617],"genre_scores_gemma":[0.06333524,0.000010517741,0.9341926,0.0004922003,0.00007636656,0.0000056547924,5.322282e-7,0.00000603855,0.0018808257],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99916035,0.00005186912,0.00023964226,0.00022590495,0.0001692694,0.00015294591],"domain_scores_gemma":[0.9993061,0.0001052736,0.00007801264,0.00033466204,0.00008441624,0.000091570146],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003577175,0.00009419374,0.00015921236,0.00013349684,0.000025648464,0.00004108181,0.00052603125,0.000048816273,0.00031110138],"category_scores_gemma":[0.00007613212,0.00007529153,0.00007158211,0.00038336488,0.0000075944686,0.0005399524,0.0001547724,0.00007353632,0.00010977951],"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":[0.0000011493559,0.000019456878,0.00014308433,0.0000035029618,0.0000059379518,7.7803867e-7,0.0001500523,8.867022e-7,0.003861248,0.0036020176,0.0031873065,0.9890246],"study_design_scores_gemma":[0.00090013933,0.0001871635,0.0026654794,0.00008079123,0.0000111595855,0.000115053204,0.000020257809,0.033179056,0.8438698,0.09363294,0.024814699,0.00052343885],"about_ca_topic_score_codex":0.00009934663,"about_ca_topic_score_gemma":0.000044405646,"teacher_disagreement_score":0.98850113,"about_ca_system_score_codex":0.000017647317,"about_ca_system_score_gemma":0.000055780973,"threshold_uncertainty_score":0.3406342},"labels":[],"label_agreement":null},{"id":"W2118923639","doi":"10.1109/icdar.2011.195","title":"Discovering Legible Chinese Typefaces for Reading Digital Documents","year":2011,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Typeface; Legibility; Reading (process); Computer science; Character (mathematics); Typography; Font; Multimedia; Computer graphics (images); Artificial intelligence; Visual arts; Art; Linguistics","score_opus":0.023441354695147392,"score_gpt":0.2690134176462312,"score_spread":0.24557206295108383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2118923639","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":[0.035376187,0.000009241089,0.8488202,0.000046976063,0.00013278151,0.00019238773,0.0000036973981,0.0005082049,0.1149103],"genre_scores_gemma":[0.85583466,0.000004885799,0.14085862,0.00007632761,0.000029059338,0.000046498186,0.0000032786932,0.000008489977,0.003138181],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99934024,0.0000055030914,0.00013391928,0.0002309901,0.0000994926,0.00018985277],"domain_scores_gemma":[0.99958503,0.00003578958,0.000040912502,0.00024088456,0.00004286433,0.00005448752],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000094252806,0.000097466844,0.00009637322,0.00007811455,0.00006794012,0.00028406613,0.000442631,0.000030138346,0.00006545206],"category_scores_gemma":[0.00003612801,0.00007403161,0.000052423267,0.00015103312,0.000016646994,0.0021872502,0.00017612574,0.00003740664,0.00008614905],"study_design_candidate":"theoretical_or_conceptual","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":[0.000060137627,0.0005320347,0.04851905,0.00014598524,0.0001567776,0.000030430057,0.006452213,0.0000025778943,0.0063709444,0.26845923,0.011761826,0.6575088],"study_design_scores_gemma":[0.0017196814,0.0009649034,0.008876342,0.00019691297,0.000020717871,0.00008478874,0.00028559982,0.01331431,0.41691697,0.52867794,0.027148431,0.0017934113],"about_ca_topic_score_codex":0.000038352773,"about_ca_topic_score_gemma":0.000005266328,"teacher_disagreement_score":0.8204585,"about_ca_system_score_codex":0.000017304208,"about_ca_system_score_gemma":0.000014292431,"threshold_uncertainty_score":0.30189213},"labels":[],"label_agreement":null},{"id":"W2119306545","doi":"10.1109/icdar.2005.32","title":"A statistical learning approach to document image analysis","year":2005,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Document layout analysis; Heuristic; Artificial intelligence; Field (mathematics); Segmentation; Image segmentation; Classifier (UML); Software; Statistical learning; Machine learning; Statistical analysis; Variety (cybernetics); Image (mathematics); Pattern recognition (psychology); Data mining","score_opus":0.01128092482742816,"score_gpt":0.27701107669833214,"score_spread":0.265730151870904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119306545","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":[0.0007855088,0.0000041789895,0.9212212,0.00072460563,0.000007660626,0.0001178694,9.661555e-7,0.0005738319,0.076564185],"genre_scores_gemma":[0.31610647,0.000001787108,0.68193966,0.0005217774,0.000021360369,0.000035701356,0.0000054623874,0.0000035504545,0.0013642183],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99887085,0.00007641422,0.00019210964,0.00036624147,0.00026271312,0.00023167141],"domain_scores_gemma":[0.9993957,0.000056082506,0.000028788227,0.00028691354,0.00007286,0.00015965261],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003389385,0.0000955176,0.00015769085,0.00029928572,0.000071762326,0.0002706416,0.00042116496,0.00002988416,0.0003750396],"category_scores_gemma":[0.00004977534,0.000083224084,0.000066982095,0.00090169604,0.000017835278,0.00036857848,0.00020397105,0.00011521749,0.0005735373],"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":[0.000004638602,0.0002603259,0.00044297284,0.000009821781,0.00021475923,0.000008943807,0.0009929182,0.0008127075,0.00095468125,0.24139519,0.012642358,0.7422607],"study_design_scores_gemma":[0.0006400966,0.00043382033,0.0073390636,0.000013737489,0.00027392246,0.00003786463,0.00018633438,0.833349,0.0474421,0.012618201,0.09632444,0.0013414375],"about_ca_topic_score_codex":0.000034625984,"about_ca_topic_score_gemma":0.000008174728,"teacher_disagreement_score":0.8325363,"about_ca_system_score_codex":0.00005380891,"about_ca_system_score_gemma":0.00001730131,"threshold_uncertainty_score":0.7371853},"labels":[],"label_agreement":null},{"id":"W2120022046","doi":"10.1109/icdar.2005.129","title":"Hybrid feature extraction and feature selection for improving recognition accuracy of handwritten numerals","year":2005,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Pattern recognition (psychology); Feature extraction; Computer science; MNIST database; Artificial intelligence; Numeral system; Feature selection; Feature (linguistics); Divergence (linguistics); Artificial neural network","score_opus":0.016163927056523468,"score_gpt":0.27518425841763045,"score_spread":0.25902033136110697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120022046","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":[0.03774634,0.00019055675,0.9558259,0.003967936,0.00011736589,0.00078873633,0.000021898386,0.00056609267,0.0007751735],"genre_scores_gemma":[0.47212195,0.00007911054,0.5258945,0.00045090597,0.0002286749,0.00012007968,0.00003783043,0.000016841475,0.0010500628],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99882096,0.00005330469,0.00024703288,0.00044110845,0.00018833693,0.0002492804],"domain_scores_gemma":[0.9988511,0.00021536928,0.0002557417,0.00020354585,0.00039386103,0.00008036316],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003818853,0.00018144496,0.00021290204,0.00022153364,0.00016743575,0.00018564922,0.0002085974,0.00015203096,0.00003250292],"category_scores_gemma":[0.00020635652,0.000169212,0.00009055595,0.00021886597,0.000027967144,0.001955543,0.00006198559,0.00021416204,0.000008696126],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023952973,0.000052369694,0.000054588472,0.00006479207,0.000012895593,3.9350084e-7,0.00006643807,9.386783e-7,0.090339236,0.00036159105,0.009381764,0.89964104],"study_design_scores_gemma":[0.00068519166,0.00026044602,0.0005341303,0.000065780485,0.000030149125,0.00021469788,0.000023833676,0.029441476,0.950541,0.006277006,0.011615461,0.00031080772],"about_ca_topic_score_codex":0.000038417034,"about_ca_topic_score_gemma":0.000036505964,"teacher_disagreement_score":0.89933026,"about_ca_system_score_codex":0.000058914753,"about_ca_system_score_gemma":0.000047930956,"threshold_uncertainty_score":0.69002646},"labels":[],"label_agreement":null},{"id":"W2120118130","doi":"10.1109/icpr.2008.4761931","title":"An interactive system for the automatic generation of huge handwriting databases from a few specimens","year":2008,"lang":"en","type":"article","venue":"Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Handwriting; Computer science; Software; Generator (circuit theory); Word (group theory); Log-normal distribution; Handwriting recognition; Fiducial marker; Artificial intelligence; Kinematics; Natural language processing; Speech recognition; Feature extraction; Mathematics; Statistics; Programming language","score_opus":0.155616274681353,"score_gpt":0.32743795526726743,"score_spread":0.17182168058591443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120118130","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":[0.6123323,0.000027023092,0.34041744,0.0041508186,0.0035018828,0.0031837742,0.0056798314,0.0015366863,0.029170273],"genre_scores_gemma":[0.9810623,0.0004188693,0.01022104,0.0013347607,0.0018333362,0.0017448317,0.0031637403,0.00011921509,0.00010192068],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99290544,0.00007612286,0.0019302648,0.002118396,0.0021671369,0.00080265536],"domain_scores_gemma":[0.98887897,0.0005063969,0.0021666682,0.00042744185,0.0076696374,0.00035090715],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000984671,0.0010386573,0.000854482,0.0012260069,0.00079132395,0.0015565411,0.0028708945,0.00034419284,0.0017631012],"category_scores_gemma":[0.00048218868,0.0009694932,0.00045042872,0.00048978295,0.00032021647,0.0044091367,0.00038438314,0.00093452714,0.00042809913],"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":[0.00080537534,0.0026672261,0.0061345287,0.00051342475,0.0017136054,0.000053905915,0.0049441312,0.0000064423116,0.09681446,0.03229383,0.004088092,0.849965],"study_design_scores_gemma":[0.005657604,0.0021219302,0.006390107,0.0063315528,0.00033456663,0.00048046117,0.007260654,0.5884839,0.36902976,0.010738848,0.0004741821,0.0026963693],"about_ca_topic_score_codex":0.00037547137,"about_ca_topic_score_gemma":0.00008199996,"teacher_disagreement_score":0.8472686,"about_ca_system_score_codex":0.00065092015,"about_ca_system_score_gemma":0.0002268316,"threshold_uncertainty_score":0.99947995},"labels":[],"label_agreement":null},{"id":"W2120840444","doi":"10.1109/icdar.1997.620586","title":"Structure recognition of on-line handwritten documents based on SGML","year":2002,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; SGML; Document Structure Description; Document processing; Document layout analysis; Information retrieval; Natural language processing; Document type definition; Artificial intelligence; Markup language; Segmentation; Fragment (logic); Programming language; XML; World Wide Web","score_opus":0.03239758140990524,"score_gpt":0.26265044990391806,"score_spread":0.23025286849401283,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120840444","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":[0.04259331,0.00003695326,0.8323449,0.004034085,0.00049433974,0.000990395,0.000114859606,0.0015318254,0.11785935],"genre_scores_gemma":[0.9275806,0.000016377653,0.0687333,0.00283073,0.000053677926,0.000021161293,0.000024134073,0.000013832405,0.0007261644],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985271,0.00008223828,0.0003129908,0.00039979428,0.0004510218,0.00022681848],"domain_scores_gemma":[0.99894536,0.00012309111,0.00012968965,0.00054805895,0.000162202,0.00009162465],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00014473287,0.00018397707,0.00020297847,0.00029986526,0.00006727145,0.00007924886,0.0005039742,0.00011236607,0.002352292],"category_scores_gemma":[0.000062961604,0.00015345191,0.00008734814,0.0003899422,0.000039345236,0.0003033792,0.00005689191,0.00017375845,0.00028978407],"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":[0.000032806864,0.0005394777,0.00010765367,0.00003484066,0.000024440433,0.000018753575,0.00012557393,0.00007190778,0.0036535445,0.0022840363,0.018961526,0.9741454],"study_design_scores_gemma":[0.0016744811,0.0019520691,0.00026560278,0.00027367251,0.000014237638,0.000012536386,0.000011529178,0.15173692,0.8167554,0.024532178,0.0022597474,0.0005116041],"about_ca_topic_score_codex":0.000014771214,"about_ca_topic_score_gemma":0.000005244774,"teacher_disagreement_score":0.9736338,"about_ca_system_score_codex":0.00003933021,"about_ca_system_score_gemma":0.000012595456,"threshold_uncertainty_score":0.9985597},"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":"W2121448658","doi":"10.1109/icdar.2009.247","title":"Issues in Performance Evaluation: A Case Study of Math Recognition","year":2009,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada; Xerox Foundation","keywords":"Computer science; Context (archaeology); Range (aeronautics); Machine learning; Artificial intelligence; Engineering","score_opus":0.0537565135134561,"score_gpt":0.3329474294971629,"score_spread":0.27919091598370677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121448658","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":[0.98770994,0.000028029875,0.008112025,0.00017945349,0.000028575429,0.00057807233,3.543683e-7,0.0001657149,0.0031978474],"genre_scores_gemma":[0.9742307,0.000017057635,0.02553461,0.000105368024,0.000013847024,0.00004945465,0.0000013422343,0.000002322983,0.00004530906],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989665,0.00011387139,0.00028697704,0.00021820469,0.00030263368,0.00011178322],"domain_scores_gemma":[0.99935603,0.000026143945,0.00007264345,0.0002847885,0.00023394791,0.000026454634],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008175296,0.00007909186,0.00012805886,0.0002195638,0.000034851513,0.00003951658,0.00020272666,0.00003408049,0.00006140421],"category_scores_gemma":[0.000029777466,0.000071403556,0.000018364763,0.00046407114,0.00000906878,0.00061947,0.00003576713,0.000070882736,0.000026455511],"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":[0.00000345839,0.00058351987,0.00084147847,0.000004634567,0.000002606569,0.000120657984,0.0024724721,0.0000041269914,0.00011147038,0.00015070173,0.00008780558,0.9956171],"study_design_scores_gemma":[0.0076701473,0.013368595,0.08216692,0.00046754838,0.00007147641,0.005220878,0.012657822,0.72580713,0.11629698,0.034646943,0.00019666181,0.0014288928],"about_ca_topic_score_codex":0.00020347428,"about_ca_topic_score_gemma":0.00012631736,"teacher_disagreement_score":0.9941882,"about_ca_system_score_codex":0.00003192347,"about_ca_system_score_gemma":0.00003070845,"threshold_uncertainty_score":0.29117525},"labels":[],"label_agreement":null},{"id":"W2122287370","doi":"10.1109/have.2003.1244730","title":"Dynamic signature verification system using stroked based features","year":2004,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Feature extraction; Pattern recognition (psychology); Signature (topology); Artificial intelligence; Probabilistic logic; Correlation; Classifier (UML); Feature (linguistics); Data mining; Mathematics","score_opus":0.011140186714434567,"score_gpt":0.24909115260101364,"score_spread":0.23795096588657907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122287370","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":[0.010511533,0.000059034413,0.9853675,0.00038345467,0.0001349338,0.00023810116,0.0000035189578,0.0014251142,0.0018768333],"genre_scores_gemma":[0.6374495,8.919565e-7,0.36228487,0.00017888428,0.000010415906,0.0000112174985,0.0000064545698,0.000006736067,0.000051014526],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99904764,0.000045352248,0.00016292644,0.0003224089,0.00023576806,0.00018592896],"domain_scores_gemma":[0.99926674,0.000022975873,0.00007717322,0.00045034956,0.00011922057,0.00006353839],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015918206,0.00012508684,0.000117113676,0.00015714014,0.00011365413,0.00016689561,0.00048435866,0.00012384079,0.000010737807],"category_scores_gemma":[0.0000139778185,0.00011131385,0.00006076593,0.00034711874,0.00002214223,0.00037459485,0.000045379544,0.00014824649,0.00003183741],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002921254,0.00034182926,0.00007848511,0.00033772681,0.00006036029,0.000105465515,0.0005107934,0.0062331315,0.54749805,0.3575892,0.00073315756,0.086482584],"study_design_scores_gemma":[0.0011183062,0.00014392418,0.0018713713,0.0003451117,0.000021489894,0.00011049747,0.00014548274,0.41628453,0.5744359,0.00445817,0.00042186558,0.00064339355],"about_ca_topic_score_codex":0.000056100474,"about_ca_topic_score_gemma":0.000015207165,"teacher_disagreement_score":0.626938,"about_ca_system_score_codex":0.00026604778,"about_ca_system_score_gemma":0.00011243947,"threshold_uncertainty_score":0.45392472},"labels":[],"label_agreement":null},{"id":"W2122943204","doi":"10.1109/sibgra.2002.1167176","title":"Human-perception handwritten character recognition using wavelets","year":2003,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"National Institute of Standards and Technology; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Artificial intelligence; Computer science; NIST; Wavelet; Wavelet transform; Computer vision; Pattern recognition (psychology); Numeral system; Character recognition; Speech recognition; Feature extraction; Character (mathematics); Diagonal; Perception; Optical character recognition; Image (mathematics); Mathematics","score_opus":0.04866743481114697,"score_gpt":0.2881899210094696,"score_spread":0.23952248619832264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122943204","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":[0.28011823,0.000015425345,0.67059934,0.00016521747,0.0002532471,0.0004602369,0.0000029242083,0.0008663234,0.04751907],"genre_scores_gemma":[0.78355634,0.000008439094,0.21492587,0.0009584942,0.00007841273,0.00005447556,0.000017974495,0.000017937748,0.00038203227],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983457,0.00021063205,0.00030781177,0.00046317984,0.00034698707,0.00032568927],"domain_scores_gemma":[0.9990719,0.000020298683,0.00009921138,0.00041905293,0.00028455275,0.00010499248],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00070243585,0.00018045324,0.00016800723,0.00024115879,0.00023287746,0.00024410745,0.0003082993,0.00012834667,0.0015762376],"category_scores_gemma":[0.000048229336,0.00017321698,0.00009053314,0.00033422696,0.000036067417,0.001138328,0.000060080467,0.00016181743,0.00045243418],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000024470426,0.00027426207,0.0003443466,0.000026238164,0.00003338981,0.000023609491,0.00041684695,7.872011e-7,0.23511414,0.0087171495,0.0028134244,0.7522334],"study_design_scores_gemma":[0.003438915,0.000520701,0.012355497,0.00039566812,0.00012616893,0.0011170274,0.00035904892,0.038156964,0.7483995,0.17086889,0.021107381,0.0031542548],"about_ca_topic_score_codex":0.000031231564,"about_ca_topic_score_gemma":0.0000067920723,"teacher_disagreement_score":0.7490791,"about_ca_system_score_codex":0.00012312892,"about_ca_system_score_gemma":0.000047566868,"threshold_uncertainty_score":0.9993365},"labels":[],"label_agreement":null},{"id":"W2122970629","doi":"10.1109/icdar.2009.144","title":"Error-Correcting Output Coding for the Convolutional Neural Network for Optical Character Recognition","year":2009,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Convolutional neural network; Optical character recognition; Hamming distance; Coding (social sciences); Artificial intelligence; Convolutional code; Character (mathematics); Pattern recognition (psychology); Speech recognition; Error detection and correction; Segmentation; Code (set theory); Algorithm; Image (mathematics); Decoding methods; Mathematics","score_opus":0.060711153289304036,"score_gpt":0.2935590856141292,"score_spread":0.23284793232482515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122970629","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":[0.003302299,0.000031515352,0.9875294,0.0058884374,0.0007345993,0.0009896022,0.000013411836,0.00054075127,0.00097000855],"genre_scores_gemma":[0.5955796,0.000008303094,0.39556134,0.0065019005,0.001302159,0.00040249663,0.00007440992,0.000015271838,0.0005545156],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998706,0.000032287986,0.0003041413,0.0003522506,0.00016992992,0.00043541018],"domain_scores_gemma":[0.99810225,0.0012354333,0.00010653789,0.00021765103,0.000266919,0.00007123446],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007737363,0.00014959215,0.00015939864,0.000054014916,0.00046242023,0.00023794077,0.00042346667,0.00009818204,0.000025995025],"category_scores_gemma":[0.00023101916,0.00011126874,0.00015104726,0.00016403763,0.000036784983,0.00049650593,0.000051186256,0.0001657271,0.0000218906],"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":[0.00003549433,0.000041642765,0.000034757024,0.000007393856,0.000014966341,7.396603e-7,0.00007212275,0.00003499535,0.0003021667,0.02191166,0.015838195,0.96170586],"study_design_scores_gemma":[0.0012033728,0.0007576482,0.004055788,0.000096179574,0.000054569635,0.00015227572,0.00007685567,0.86530614,0.014089281,0.097972475,0.015587754,0.0006476699],"about_ca_topic_score_codex":0.0000031904685,"about_ca_topic_score_gemma":0.000004128756,"teacher_disagreement_score":0.9610582,"about_ca_system_score_codex":0.000043153865,"about_ca_system_score_gemma":0.000035853678,"threshold_uncertainty_score":0.45374075},"labels":[],"label_agreement":null},{"id":"W2123708640","doi":"10.1109/icpr.1994.576981","title":"Vector templates and handprinted digit recognition","year":2002,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Template; Template matching; Pattern recognition (psychology); Computer science; Artificial intelligence; Numerical digit; Character (mathematics); Set (abstract data type); Matching (statistics); Pixel; Computer vision; Image (mathematics); Mathematics; Arithmetic","score_opus":0.03424594335407063,"score_gpt":0.22921694688928687,"score_spread":0.19497100353521624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2123708640","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":[0.14598532,0.0002208275,0.7338571,0.0037140576,0.0002184607,0.0005074363,0.000009203467,0.003807566,0.11168003],"genre_scores_gemma":[0.94176394,0.000113899325,0.056312263,0.00048133606,0.000029024432,0.000028433462,0.0000031613242,0.000007299882,0.0012606585],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99933505,0.000023253431,0.00013599373,0.00025321904,0.00010452144,0.00014794775],"domain_scores_gemma":[0.9995646,0.0000668072,0.000033216875,0.0001889727,0.000070672664,0.00007571634],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006742904,0.00008961279,0.00009096106,0.00009725501,0.00006976767,0.0002172484,0.00018596658,0.000049182923,0.0004915257],"category_scores_gemma":[0.000042776705,0.000078388155,0.00002558497,0.00017976653,0.00003205799,0.00056867534,0.00010045703,0.000070122296,0.0004753726],"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":[0.0000010308779,0.000047268637,0.00020057728,0.000008466049,0.000008238489,0.000008184268,0.00014868796,1.6753255e-8,0.0027951247,0.0019555541,0.0048099207,0.99001694],"study_design_scores_gemma":[0.0011156299,0.00048051245,0.00481628,0.00016819658,0.000015259213,0.0003983097,0.000051870225,0.03198374,0.8618234,0.069580756,0.02853192,0.0010341228],"about_ca_topic_score_codex":0.000013522129,"about_ca_topic_score_gemma":0.0000051677684,"teacher_disagreement_score":0.9889828,"about_ca_system_score_codex":0.000012285946,"about_ca_system_score_gemma":0.0000030132455,"threshold_uncertainty_score":0.61101115},"labels":[],"label_agreement":null},{"id":"W2123837361","doi":"10.1109/icpr.1994.576986","title":"A method of combining multiple classifiers-a neural network approach","year":2002,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Numeral system; Computer science; Artificial neural network; Artificial intelligence; Classifier (UML); Pattern recognition (psychology); Transformation (genetics); Random subspace method; Noise (video); Machine learning; Speech recognition; Image (mathematics)","score_opus":0.05903841681622824,"score_gpt":0.27615802214363905,"score_spread":0.21711960532741081,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2123837361","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":[0.0005646921,0.00005321679,0.9455625,0.00018377442,0.00007474857,0.00016339493,6.422868e-7,0.00051178026,0.052885275],"genre_scores_gemma":[0.36453423,0.0000053428694,0.6347686,0.00027860628,0.000028102719,0.00001950695,9.918598e-7,0.0000061650967,0.00035846338],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998759,0.00016275537,0.00028253393,0.00030738531,0.00021083165,0.00027750607],"domain_scores_gemma":[0.9990819,0.00024143724,0.00010942734,0.0004093292,0.000079287376,0.00007862992],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004101894,0.000119270095,0.000218948,0.00008704406,0.00007313242,0.00006166093,0.0006287284,0.00007593135,0.00010624095],"category_scores_gemma":[0.00003802854,0.00010528426,0.00009262075,0.000501546,0.000042034237,0.0003263121,0.00020679073,0.00015391831,0.000023192464],"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":[0.0000049966407,0.0003058121,0.0018855601,0.0000371174,0.000041067018,0.000007736161,0.0009628613,0.00050788105,0.0014171238,0.05721009,0.028394999,0.90922475],"study_design_scores_gemma":[0.00029151118,0.000080091966,0.00022451131,0.000011372156,0.0000043137584,0.000032894248,0.00003260469,0.98869437,0.0061344886,0.003014576,0.0013268936,0.00015235867],"about_ca_topic_score_codex":0.000021505193,"about_ca_topic_score_gemma":0.0000017915866,"teacher_disagreement_score":0.9881865,"about_ca_system_score_codex":0.000013313156,"about_ca_system_score_gemma":0.000006559739,"threshold_uncertainty_score":0.42933676},"labels":[],"label_agreement":null},{"id":"W2125446732","doi":"10.1109/icpr.1994.576882","title":"Machine vs humans in a cursive script reading experiment without linguistic knowledge","year":2002,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal; Université Laval","funders":"","keywords":"Cursive; Computer science; Rule-based machine translation; Natural language processing; Parsing; Artificial intelligence; Character (mathematics); Reading (process); Optical character recognition; Speech recognition; Linguistics; Mathematics","score_opus":0.03191983527834675,"score_gpt":0.2966610411689689,"score_spread":0.26474120589062217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125446732","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":[0.0057361834,0.0014129686,0.60440177,0.00054142554,0.00051903655,0.0006088455,0.0000025135053,0.0013834684,0.3853938],"genre_scores_gemma":[0.9353834,0.000053807766,0.05961244,0.00035938274,0.000076950106,0.00008940407,0.0000018019547,0.000015136563,0.004407676],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986679,0.00008230896,0.00030361753,0.00044264048,0.00017354716,0.00033000138],"domain_scores_gemma":[0.9992328,0.000054205353,0.000060829145,0.0004412848,0.0001061046,0.00010472519],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022724309,0.00017637927,0.00022129984,0.00031125537,0.000090322435,0.00013188264,0.00059560564,0.000062469175,0.00044458028],"category_scores_gemma":[0.000104122235,0.00016422312,0.000054549804,0.0003819553,0.00004399027,0.0002366526,0.00020608786,0.0001812449,0.00043204968],"study_design_candidate":"theoretical_or_conceptual","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":[0.00003196903,0.0033529485,0.010845328,0.00016845016,0.000083684434,0.000468285,0.10473928,0.000005858416,0.014249662,0.5042821,0.042321943,0.31945047],"study_design_scores_gemma":[0.0039483816,0.0015018105,0.0019025463,0.0012318098,0.000033076452,0.00016399221,0.0005851224,0.47173676,0.36461195,0.04793932,0.10356069,0.0027845148],"about_ca_topic_score_codex":0.00011818905,"about_ca_topic_score_gemma":0.00007245379,"teacher_disagreement_score":0.9296472,"about_ca_system_score_codex":0.00013332973,"about_ca_system_score_gemma":0.0000166677,"threshold_uncertainty_score":0.66968244},"labels":[],"label_agreement":null},{"id":"W2126196216","doi":"10.1109/icdar.1995.598947","title":"A new system for reading handwritten zip codes","year":2002,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Zip code; Computer science; Numerical digit; Set (abstract data type); Reading (process); Code (set theory); Arithmetic; Speech recognition; Symbol (formal); Test set; Pattern recognition (psychology); Digit recognition; Artificial intelligence; Artificial neural network; Mathematics; Programming language; Database","score_opus":0.028828741574848816,"score_gpt":0.24972571915924838,"score_spread":0.22089697758439955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126196216","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":[0.00013944444,0.00008045732,0.95256746,0.00094872306,0.00014629308,0.00034838388,0.0000028623763,0.0017880759,0.043978274],"genre_scores_gemma":[0.2680907,0.000015089972,0.7179082,0.00042218718,0.00016487368,0.00010537964,0.0000021938747,0.000016385338,0.013275012],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99893004,0.000028955614,0.00023511198,0.00034436767,0.00017194962,0.0002895598],"domain_scores_gemma":[0.9991605,0.00013304927,0.000063577034,0.00039804634,0.00010033087,0.00014448905],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022715138,0.00012959594,0.00018677975,0.00013457613,0.00012830527,0.00027005002,0.00060965226,0.00007436565,0.00013729495],"category_scores_gemma":[0.00003821675,0.000113743976,0.0000923765,0.00024981386,0.00001319766,0.00046048226,0.00009678363,0.00006238394,0.00025999313],"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":[0.0000033584843,0.000034887773,0.00006400959,0.00009254385,0.000026928376,0.000011579772,0.0004107766,6.498886e-7,0.002904606,0.21075517,0.19953646,0.58615905],"study_design_scores_gemma":[0.002480087,0.0006743238,0.00011873553,0.0006386684,0.00004912437,0.00042442538,0.0003097477,0.25337926,0.5675862,0.02629689,0.14659747,0.0014450756],"about_ca_topic_score_codex":0.00005290807,"about_ca_topic_score_gemma":0.000008442747,"teacher_disagreement_score":0.58471394,"about_ca_system_score_codex":0.000060440016,"about_ca_system_score_gemma":0.000017878749,"threshold_uncertainty_score":0.46383446},"labels":[],"label_agreement":null},{"id":"W2127184823","doi":"10.1109/euvip.2010.5699135","title":"Text extraction from degraded document images","year":2010,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"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":"Skeletonization; Computer science; Cluster analysis; Artificial intelligence; Segmentation; Image segmentation; Pattern recognition (psychology); Pixel; Coherence (philosophical gambling strategy); Historical document; Image (mathematics); Computer vision; Mathematics","score_opus":0.010751542598869242,"score_gpt":0.26948680289658483,"score_spread":0.2587352602977156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2127184823","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":[0.038208608,0.00002286919,0.93030196,0.0018846084,0.0005246959,0.00014847294,0.0000024858518,0.0012485534,0.027657768],"genre_scores_gemma":[0.61593723,0.000011389859,0.38244355,0.00034112902,0.000082317616,0.000028133654,0.0000042943598,0.0000054399457,0.0011465148],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991455,0.00002855788,0.00016283346,0.0003041944,0.00019562327,0.00016326788],"domain_scores_gemma":[0.9992416,0.000092368144,0.00005591556,0.00045754382,0.000068414774,0.00008417964],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00015417056,0.00010184734,0.00008922747,0.00008476647,0.000073754556,0.00027590318,0.0004882818,0.000077318255,0.0012344673],"category_scores_gemma":[0.00003364866,0.00008657813,0.000050313287,0.00014141928,0.000029816858,0.0009147764,0.00010937466,0.00022802038,0.00067722733],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014768451,0.000053537122,0.00020398453,0.0000013796783,0.000007640107,0.000008559381,0.00006946888,3.050683e-8,0.29572684,0.014783156,0.010910799,0.67823315],"study_design_scores_gemma":[0.00013391531,0.000025999925,0.0047500296,0.000004841229,0.0000030932256,0.000015447373,0.000011158265,0.00038331325,0.92110693,0.057545092,0.015864618,0.00015556422],"about_ca_topic_score_codex":0.00030325883,"about_ca_topic_score_gemma":0.00007221917,"teacher_disagreement_score":0.6780776,"about_ca_system_score_codex":0.000015397001,"about_ca_system_score_gemma":0.000023976183,"threshold_uncertainty_score":0.99967855},"labels":[],"label_agreement":null},{"id":"W2127373776","doi":"10.1109/iwfhr.2004.21","title":"Automatic Segmentation of Unconstrained Handwritten Numeral Strings","year":2004,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Segmentation; Computer science; Pattern recognition (psychology); Artificial intelligence; Connected-component labeling; Intersection (aeronautics); Feature (linguistics); Connected component; Image segmentation; Tracing; Tree traversal; Numeral system; Feature extraction; Computer vision; Scale-space segmentation; Algorithm","score_opus":0.011300059691231549,"score_gpt":0.2484724519001812,"score_spread":0.23717239220894965,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2127373776","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":[0.12934041,0.000009043628,0.86500007,0.0005975991,0.000051883217,0.00020260784,0.0000019470428,0.00060630444,0.004190137],"genre_scores_gemma":[0.6529719,0.0000024661545,0.34676123,0.00017275404,0.000008714704,0.000014777624,0.0000029829762,0.0000038340168,0.0000612826],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99910516,0.000023736306,0.00029175193,0.00019387518,0.00022864476,0.00015686231],"domain_scores_gemma":[0.9994715,0.000031559855,0.00010486993,0.00023819158,0.000096087795,0.00005783328],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017388766,0.000097774624,0.0001425026,0.00013971305,0.00004269714,0.00006284961,0.00035452348,0.000045515666,0.0001491285],"category_scores_gemma":[0.000022211867,0.00008826675,0.000058410737,0.00031209426,0.000050944716,0.000544837,0.00007349387,0.00005972757,0.000043709588],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000035532023,0.0002550459,0.0005628308,0.000091516944,0.000051314557,0.00001629373,0.001382657,0.000029604294,0.06678987,0.14372474,0.00051175465,0.7865808],"study_design_scores_gemma":[0.0010771609,0.00019824653,0.0010818233,0.00008766612,0.000008293871,0.00003950999,0.00010562591,0.0037657642,0.93076247,0.06262312,0.000041916268,0.00020840603],"about_ca_topic_score_codex":0.00009136359,"about_ca_topic_score_gemma":0.000009603845,"teacher_disagreement_score":0.8639726,"about_ca_system_score_codex":0.000051407445,"about_ca_system_score_gemma":0.00008795778,"threshold_uncertainty_score":0.35994136},"labels":[],"label_agreement":null},{"id":"W2128446254","doi":"10.1109/icpr.1990.118143","title":"Complementary algorithms for the recognition of totally unconstrained handwritten numerals","year":2002,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":70,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Numeral system; Computer science; Reliability (semiconductor); Artificial intelligence; Substitution (logic); Complementarity (molecular biology); Pattern recognition (psychology); Algorithm; Speech recognition; Programming language","score_opus":0.06877897661628128,"score_gpt":0.2812801912057318,"score_spread":0.21250121458945048,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128446254","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":[0.00041673591,0.00010658721,0.98065686,0.0051064086,0.00014517942,0.0008230935,0.00007500458,0.00030822481,0.012361879],"genre_scores_gemma":[0.31150177,0.00010672234,0.684451,0.0024141704,0.00013309522,0.00031597275,0.00004813128,0.000018806824,0.0010103517],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99879116,0.000053427684,0.000399018,0.00027655577,0.00023323987,0.00024658092],"domain_scores_gemma":[0.99873626,0.00044251358,0.00013482476,0.00037813894,0.0002520424,0.00005621384],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00041497097,0.00013785154,0.00018801095,0.000095858486,0.00015441846,0.000087975444,0.0006418849,0.00004912036,0.0011701937],"category_scores_gemma":[0.00004335561,0.00009813398,0.00013729304,0.00025531088,0.00009460526,0.0003844474,0.00011051877,0.000077876284,0.000049566643],"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":[0.0000041571957,0.0001028641,0.000014672946,0.000017633041,0.000054331722,0.0000014444873,0.00022560115,7.522374e-7,0.0014729592,0.0059824013,0.02272287,0.9694003],"study_design_scores_gemma":[0.0054109194,0.0018902384,0.0004998087,0.00023024791,0.00015087954,0.00020520216,0.00075544964,0.3194,0.4331286,0.19405498,0.042921893,0.0013517643],"about_ca_topic_score_codex":0.000069661306,"about_ca_topic_score_gemma":0.000021741782,"teacher_disagreement_score":0.9680486,"about_ca_system_score_codex":0.000020904248,"about_ca_system_score_gemma":0.000015883665,"threshold_uncertainty_score":0.99974287},"labels":[],"label_agreement":null},{"id":"W2129455469","doi":"10.1109/icsmc.1991.169684","title":"Computer algorithms for recognizing the distinct parts of handprinted characters","year":2002,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Pattern recognition (psychology); Decomposition; Scheme (mathematics); Artificial intelligence; Hierarchy; Algorithm; Mathematics; Biology","score_opus":0.05516415497909053,"score_gpt":0.2652172191097001,"score_spread":0.21005306413060956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129455469","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":[0.002988834,0.000023899296,0.9925534,0.0017257956,0.00023193694,0.0004154348,0.000005506445,0.00033042746,0.0017247515],"genre_scores_gemma":[0.6587679,0.000023770735,0.3392475,0.00095567724,0.00014976811,0.00013061191,0.000006157957,0.000014496111,0.0007041359],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990071,0.000051559324,0.00029016545,0.00027296317,0.00015692168,0.00022131376],"domain_scores_gemma":[0.99895424,0.00029956998,0.000127296,0.00039234533,0.00017410652,0.000052425894],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003373464,0.00011796928,0.0001681796,0.00007113053,0.00011210987,0.00010042943,0.0006335889,0.000045482,0.00010225607],"category_scores_gemma":[0.000039501894,0.00007836468,0.000113241535,0.00020398629,0.00006419342,0.00025695108,0.00015455796,0.00008302508,0.000039074937],"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":[0.000002204572,0.00006903898,0.000107417334,0.000016762358,0.000021870317,0.0000016001253,0.00036547243,5.0124106e-7,0.00028931614,0.002839467,0.006105569,0.9901808],"study_design_scores_gemma":[0.0010598917,0.00050028285,0.004146485,0.00017487831,0.000027497475,0.00006378217,0.000042342414,0.79651237,0.15400298,0.0074697672,0.03540297,0.0005967539],"about_ca_topic_score_codex":0.000010810865,"about_ca_topic_score_gemma":0.00000436957,"teacher_disagreement_score":0.989584,"about_ca_system_score_codex":0.000015007913,"about_ca_system_score_gemma":0.000007141835,"threshold_uncertainty_score":0.3195619},"labels":[],"label_agreement":null},{"id":"W2129488191","doi":"10.1109/ccst.1989.751966","title":"How to detect problematic signers for automatic signature verification","year":2005,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Signature (topology); Handwriting; Computer science; Set (abstract data type); Parametric statistics; Artificial intelligence; Pattern recognition (psychology); Speech recognition; Mathematics; Statistics","score_opus":0.015493412693446148,"score_gpt":0.25377184716476303,"score_spread":0.23827843447131689,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129488191","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":[0.0008785148,0.000021024414,0.97843826,0.017208036,0.000042549837,0.0013108336,0.0000016608358,0.0012487156,0.0008503961],"genre_scores_gemma":[0.36337435,0.0000011159756,0.63450384,0.00087285566,0.000036700425,0.00048664206,0.0000023111565,0.00000855198,0.0007136119],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999026,0.000034966026,0.00019236654,0.0003203801,0.00019353381,0.00023273806],"domain_scores_gemma":[0.9991528,0.00011094711,0.00007321901,0.00042238727,0.00014003836,0.000100628145],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002966956,0.0001272449,0.00013980381,0.00016607215,0.000080694335,0.00032930975,0.00057875714,0.00007966198,0.000026630485],"category_scores_gemma":[0.00014013573,0.0001079215,0.00006476567,0.00035579308,0.000011459619,0.0006375157,0.00005496548,0.00006757896,0.000092492875],"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":[0.0000015038986,0.000024746032,9.70476e-7,0.0000770349,0.000008669284,3.4597426e-7,0.0002692539,0.000017266122,0.041122224,0.008432928,0.015717775,0.9343273],"study_design_scores_gemma":[0.0004357251,0.00042768553,0.000117148564,0.00011508113,0.000015899417,0.0000143839015,0.000046422098,0.24001323,0.6859921,0.04643794,0.025844516,0.0005398556],"about_ca_topic_score_codex":0.0000011491347,"about_ca_topic_score_gemma":0.0000069471157,"teacher_disagreement_score":0.9337874,"about_ca_system_score_codex":0.000069037575,"about_ca_system_score_gemma":0.00003813904,"threshold_uncertainty_score":0.4400911},"labels":[],"label_agreement":null},{"id":"W2129766592","doi":"10.1016/j.patcog.2011.10.011","title":"Dynamic selection of generative–discriminative ensembles for off-line signature verification","year":2011,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":98,"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":"Discriminative model; Computer science; Pattern recognition (psychology); Signature (topology); Classifier (UML); Artificial intelligence; Hidden Markov model; Feature selection; Generative model; Subspace topology; Machine learning; Selection (genetic algorithm); Codebook; Generative grammar; Mathematics","score_opus":0.05284061859672254,"score_gpt":0.2807842239529998,"score_spread":0.22794360535627725,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129766592","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":[0.060587306,0.00006635343,0.9375572,0.00010504828,0.00015771996,0.00063535915,0.00008355814,0.00024445148,0.00056300865],"genre_scores_gemma":[0.81732583,0.000093763534,0.18180874,0.00012750587,0.000038472946,0.00030190768,0.00023909198,0.00001786411,0.000046793622],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987472,0.00012292739,0.00035304643,0.00040740022,0.00017436419,0.00019504524],"domain_scores_gemma":[0.9986956,0.000084003565,0.0003058319,0.00020120849,0.0006651686,0.000048162372],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028621312,0.00017194895,0.00019331691,0.000246999,0.000098077275,0.00003444899,0.00026349924,0.00014188785,0.00010672015],"category_scores_gemma":[0.00006616836,0.00017227813,0.00010121591,0.00027181502,0.00004272137,0.0005882208,0.000039410774,0.0001273103,0.00002871632],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025415107,0.0001691141,0.000076313896,0.00006599418,0.000026921685,7.421353e-7,0.0009649087,5.9803233e-7,0.053926475,0.00017164508,0.00019732551,0.94437456],"study_design_scores_gemma":[0.00044109268,0.0007083928,0.002583775,0.00011048486,0.00003724735,0.000013337009,0.00008716823,0.037329756,0.9366,0.021729825,0.00008650011,0.00027242058],"about_ca_topic_score_codex":0.000027873906,"about_ca_topic_score_gemma":0.000055575758,"teacher_disagreement_score":0.9441021,"about_ca_system_score_codex":0.000059712245,"about_ca_system_score_gemma":0.00003639778,"threshold_uncertainty_score":0.70252985},"labels":[],"label_agreement":null},{"id":"W2130723172","doi":"10.1109/icdar.2015.7333910","title":"Evaluation of deep convolutional nets for document image classification and retrieval","year":2015,"lang":"en","type":"preprint","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada; Universities Space Research Association","keywords":"Computer science; Convolutional neural network; Artificial intelligence; Abstraction; Pattern recognition (psychology); Representation (politics); Variety (cybernetics); Feature (linguistics); Document classification; Object (grammar); Deep learning; Feature learning; Contextual image classification; Image (mathematics); Information retrieval; Machine learning","score_opus":0.08440360538665913,"score_gpt":0.3544672008181142,"score_spread":0.2700635954314551,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130723172","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":[0.0054972167,0.0003573724,0.98748803,0.00093153096,0.00026263657,0.0016043724,0.000026108433,0.0001837935,0.0036489137],"genre_scores_gemma":[0.5567975,0.00005535719,0.4424086,0.00007901324,0.00007144693,0.0003197417,0.00017077893,0.000011788809,0.00008574988],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976389,0.00022549603,0.00043879362,0.00052200654,0.0010308073,0.00014400562],"domain_scores_gemma":[0.9951639,0.00011245964,0.00036710763,0.0004871455,0.0037855008,0.000083892985],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004790388,0.00016259566,0.00023211539,0.00017854293,0.00004353764,0.00014206287,0.000433216,0.00021872876,0.00005098181],"category_scores_gemma":[0.00046875363,0.00015900575,0.00007294316,0.00010542989,0.00008713794,0.0003260945,0.0004958315,0.00014694336,0.000006801279],"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":[0.00010438547,0.0003312298,0.00013851572,0.0005050266,0.00027119956,8.135287e-7,0.0010848882,0.00011339264,0.013492494,0.18136477,0.020711197,0.78188205],"study_design_scores_gemma":[0.0005552947,0.00008931819,0.0011876824,0.000046733556,0.00008109715,0.000004160386,0.000021592688,0.52687734,0.014016432,0.45663616,0.0002981596,0.00018598443],"about_ca_topic_score_codex":0.000016982192,"about_ca_topic_score_gemma":0.0000074031514,"teacher_disagreement_score":0.7816961,"about_ca_system_score_codex":0.00028831788,"about_ca_system_score_gemma":0.00058443047,"threshold_uncertainty_score":0.6484066},"labels":[],"label_agreement":null},{"id":"W2130790880","doi":"10.1111/j.1556-4029.2012.02244.x","title":"Detection of Transcribed Seal Impressions Using 3‐D Pressure Traces","year":2012,"lang":"en","type":"article","venue":"Journal of Forensic Sciences","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"GF Strong Rehabilitation Centre","funders":"","keywords":"Impression; Seal (emblem); Computer science; Suspect; Cartridge; Scanner; TRACE (psycholinguistics); Artificial intelligence; Computer vision; Engineering; World Wide Web; Psychology; History; Archaeology; Mechanical engineering","score_opus":0.04438992538813063,"score_gpt":0.3074691193618928,"score_spread":0.26307919397376217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130790880","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":[0.6389586,0.0010695494,0.3585921,0.00019934836,0.0007099623,0.000075339274,0.0000018937664,0.000031348718,0.0003619215],"genre_scores_gemma":[0.9067221,0.000025386084,0.09307513,0.00002980221,0.00013519297,7.929122e-7,3.8055116e-8,0.0000028857417,0.000008618905],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99851197,0.00010086542,0.00043470133,0.00011171212,0.00059046043,0.00025029937],"domain_scores_gemma":[0.9988566,0.000112256144,0.000515589,0.00012734153,0.00026216355,0.00012605183],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014032465,0.00009062884,0.00020809913,0.0003067778,0.00017030728,0.00007047815,0.00061598147,0.00005913497,0.000014316804],"category_scores_gemma":[0.00009145058,0.00006363227,0.00013656514,0.00044243145,0.00026684266,0.0022158483,0.000042844873,0.00014955008,7.631476e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018189436,0.00016475967,0.0023974925,0.000035147852,0.00004630817,0.0000037462942,0.0023535038,0.00013702449,0.76262563,0.0029530625,0.00017899995,0.22908613],"study_design_scores_gemma":[0.00020032754,0.00036616545,0.0035080586,0.00013807649,0.000044943914,0.00037423728,0.00026023464,0.0059552994,0.98587275,0.0027406497,0.0004255902,0.00011369198],"about_ca_topic_score_codex":0.000017216222,"about_ca_topic_score_gemma":0.0000053376666,"teacher_disagreement_score":0.2677636,"about_ca_system_score_codex":0.000015680534,"about_ca_system_score_gemma":0.000112993526,"threshold_uncertainty_score":0.25948486},"labels":[],"label_agreement":null},{"id":"W2130854383","doi":"10.1016/s0167-8655(00)00047-7","title":"Crucial combinations for the recognition of handwritten letters","year":2000,"lang":"en","type":"article","venue":"Pattern Recognition Letters","topic":"Handwritten Text Recognition Techniques","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":"Concordia University","funders":"","keywords":"Confusion; Computer science; Identification (biology); Artificial intelligence; Selection (genetic algorithm); Pattern recognition (psychology); Simple (philosophy); Machine learning; Natural language processing; Psychology","score_opus":0.027999890381510073,"score_gpt":0.25154892007867613,"score_spread":0.22354902969716606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130854383","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":[0.14839964,0.000041025403,0.82538867,0.023236826,0.0004237055,0.0013050693,0.00025589502,0.00042386184,0.0005253049],"genre_scores_gemma":[0.91780466,0.0002552994,0.043730374,0.03494954,0.0005988618,0.0018860693,0.0005843415,0.00008414381,0.00010668654],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9977453,0.00019069383,0.0006572401,0.0005404619,0.00042467393,0.00044163232],"domain_scores_gemma":[0.99813414,0.00069230964,0.00027500998,0.00053323846,0.00026954158,0.00009573648],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006004068,0.00028095336,0.00030170014,0.00028202482,0.00037578665,0.00021464696,0.0008566859,0.00010295676,0.0007839609],"category_scores_gemma":[0.00007998745,0.00024776717,0.00030466774,0.00046417586,0.00018764235,0.0008050058,0.00006608958,0.00023196373,0.00037787002],"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":[0.000021615473,0.00014233674,0.00009971718,0.00004156669,0.000063983134,0.0000037085156,0.00032514078,0.000005739023,0.008630041,0.000022278602,0.009986241,0.98065764],"study_design_scores_gemma":[0.025075976,0.002073109,0.028594755,0.0025650342,0.0012536596,0.00064809417,0.0005498067,0.048027594,0.7565392,0.06184948,0.06577326,0.0070499848],"about_ca_topic_score_codex":0.000086658336,"about_ca_topic_score_gemma":0.000021141681,"teacher_disagreement_score":0.97360766,"about_ca_system_score_codex":0.00006065486,"about_ca_system_score_gemma":0.000028980076,"threshold_uncertainty_score":0.99999744},"labels":[],"label_agreement":null},{"id":"W2131831414","doi":"10.1109/tpami.2005.207","title":"Recognition and verification of unconstrained handwritten words","year":2005,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":69,"is_retracted":false,"has_abstract":true,"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":"Intelligent word recognition; Word recognition; Computer science; Word (group theory); Vocabulary; Artificial intelligence; Pattern recognition (psychology); Speech recognition; Intelligent character recognition; Word error rate; Natural language processing; Optical character recognition; Character (mathematics); Handwriting recognition; Segmentation; Signature recognition; Feature extraction; Image (mathematics); Character recognition; Mathematics; Linguistics","score_opus":0.026597093954232313,"score_gpt":0.26554716109910825,"score_spread":0.23895006714487593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131831414","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":[0.018000446,0.00007658618,0.9809482,0.0005154138,0.00003696151,0.00012981429,0.000056633213,0.00010991149,0.00012601938],"genre_scores_gemma":[0.9848491,0.0006255989,0.01416903,0.00023857984,0.000014356638,0.000029468807,0.000011643726,0.0000070964593,0.00005514898],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987639,0.00007771153,0.00040930352,0.00040848635,0.00019366713,0.00014688914],"domain_scores_gemma":[0.9992283,0.000107314336,0.0001381587,0.0003147167,0.000116462295,0.00009507818],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002870958,0.00016386516,0.0002667466,0.0005915915,0.00010589688,0.00008216084,0.00020944899,0.00007392138,0.00014467433],"category_scores_gemma":[0.000005900652,0.00015381302,0.00012866725,0.000782545,0.00010811215,0.00034701618,0.000004348066,0.00016450687,0.000019012641],"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":[0.0000067810474,0.0001007729,0.00011750419,0.000012878471,0.00014124134,9.1348323e-7,0.00030258016,0.00012980404,0.001664996,0.000031810818,0.0000030588028,0.99748766],"study_design_scores_gemma":[0.00017940438,0.00021187158,0.0011219612,0.00006283502,0.00038893818,0.000025591673,0.00008024584,0.07912143,0.9168657,0.0015284078,0.00008528867,0.0003283341],"about_ca_topic_score_codex":0.00032543828,"about_ca_topic_score_gemma":0.00055930647,"teacher_disagreement_score":0.9971593,"about_ca_system_score_codex":0.000021104004,"about_ca_system_score_gemma":0.000014942096,"threshold_uncertainty_score":0.62723124},"labels":[],"label_agreement":null},{"id":"W2131877510","doi":"10.1109/icdar.1995.598933","title":"Cursive script recognition applied to the processing of bank cheques","year":2002,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":53,"is_retracted":false,"has_abstract":true,"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":"Cursive; Computer science; Lexicon; Handwriting; Speech recognition; Natural language processing; Process (computing); Domain (mathematical analysis); Handwriting recognition; Artificial intelligence; Reading (process); Segmentation; Feature extraction; Linguistics; Programming language; Mathematics","score_opus":0.03687812625994893,"score_gpt":0.24752674939808775,"score_spread":0.2106486231381388,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131877510","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":[0.0024719024,0.00010330351,0.8909297,0.0030975917,0.00007071033,0.00047046464,0.0000031712802,0.00051110797,0.10234206],"genre_scores_gemma":[0.8416615,0.000029358403,0.15531608,0.0023118895,0.00006465287,0.000121697434,0.000002526377,0.000009588157,0.00048271564],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990605,0.000034028304,0.00022406534,0.00026057576,0.00023531447,0.0001855272],"domain_scores_gemma":[0.9992862,0.000039129536,0.00009087956,0.0003082157,0.00021678962,0.000058830105],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023688108,0.00010343578,0.0001247631,0.00012150559,0.00010042973,0.00011577196,0.0005891585,0.000046857098,0.00025915258],"category_scores_gemma":[0.00004280073,0.00007262236,0.000040191513,0.0005238354,0.000041457428,0.0003447958,0.00012403973,0.0000922849,0.00032715953],"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":[0.0000016322517,0.000047960486,0.0000051150423,0.0000146705015,0.0000053924655,7.7268686e-7,0.0012457859,5.6753885e-7,0.0039439225,0.002638914,0.0121927885,0.9799025],"study_design_scores_gemma":[0.00026980301,0.00019394612,0.00018597096,0.00015457797,0.0000174562,0.000022550015,0.00030750976,0.008258112,0.9435963,0.03235695,0.014239303,0.0003975101],"about_ca_topic_score_codex":0.000013473964,"about_ca_topic_score_gemma":0.0000071998893,"teacher_disagreement_score":0.97950494,"about_ca_system_score_codex":0.00002298178,"about_ca_system_score_gemma":0.000013904581,"threshold_uncertainty_score":0.4205083},"labels":[],"label_agreement":null},{"id":"W2133729881","doi":"10.1109/icpr.2006.256","title":"An interactive trajectory synthesizer to study outlier patterns in handwriting recognition and signature verification","year":2006,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Trajectory; Handwriting; Context (archaeology); Handwriting recognition; Kinematics; Outlier; Signature (topology); Software; Set (abstract data type); Artificial intelligence; Anomaly detection; Interface (matter); Computer vision; Pattern recognition (psychology); Feature extraction; Mathematics","score_opus":0.018418631780681274,"score_gpt":0.26646868879753755,"score_spread":0.24805005701685628,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133729881","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":[0.76496696,0.000009039281,0.2334244,0.00010992754,0.000037592767,0.0005566132,0.0000063626667,0.00029274737,0.00059634855],"genre_scores_gemma":[0.9775319,0.0000025797165,0.021921514,0.00026742084,0.000050043433,0.00017350048,0.000013909243,0.000012681467,0.00002643446],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9986234,0.00021800937,0.00027815683,0.0005172165,0.00017329474,0.00018996595],"domain_scores_gemma":[0.999363,0.00011890627,0.00006591699,0.00027618895,0.000109368266,0.00006660747],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042730634,0.00014590556,0.00015246464,0.00031883674,0.00006863983,0.00023097293,0.0002561333,0.00007565243,0.000048392925],"category_scores_gemma":[0.00003905008,0.00014238425,0.000022221215,0.0003127301,0.000011670968,0.000944902,0.000057601897,0.0001805806,0.000027788197],"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":[0.000038967795,0.0014289456,0.017839648,0.000016295004,0.000014400637,0.000052407107,0.0050420417,0.0000062940812,0.03268361,0.00016863407,0.00010668097,0.9426021],"study_design_scores_gemma":[0.0012462464,0.0010568488,0.6834975,0.00022800284,0.000019576664,0.00003709576,0.0043685175,0.0046722363,0.2973577,0.0065558665,0.000079016296,0.0008814363],"about_ca_topic_score_codex":0.00039539963,"about_ca_topic_score_gemma":0.00055491494,"teacher_disagreement_score":0.94172066,"about_ca_system_score_codex":0.000058753772,"about_ca_system_score_gemma":0.000013225726,"threshold_uncertainty_score":0.58062613},"labels":[],"label_agreement":null},{"id":"W2134697566","doi":"10.1109/isspa.2007.4555625","title":"State-of-the-art in Farsi script recognition","year":2007,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Scripting language; Arabic script; Natural language processing; Artificial intelligence; Persian; Character recognition; Optical character recognition; Arabic; Transliteration; Alphabet; Point (geometry); Character (mathematics); Speech recognition; Linguistics; Pattern recognition (psychology); Image (mathematics); Mathematics; Programming language","score_opus":0.020362548347045005,"score_gpt":0.2541756617834633,"score_spread":0.23381311343641828,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134697566","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":[0.080340095,0.000018576106,0.87560683,0.00044727678,0.00022747897,0.00026262537,0.0000020631069,0.00024256858,0.042852458],"genre_scores_gemma":[0.86692256,0.000015962367,0.13052312,0.00087430154,0.000015725454,0.000013252588,0.000002676156,0.000008146915,0.0016242677],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999073,0.00004384434,0.00029063423,0.00018667188,0.0002017778,0.00020401737],"domain_scores_gemma":[0.99942863,0.000061255676,0.000073712996,0.00029372427,0.000103234524,0.00003945338],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00070931076,0.00007380886,0.00009417941,0.0001825174,0.000028928971,0.00003138779,0.0004622114,0.000039192157,0.000058831192],"category_scores_gemma":[0.000052042025,0.000057671445,0.000049406044,0.00060799235,0.00003973845,0.00036011962,0.00013179482,0.00011412656,0.00012563821],"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":[0.000004575712,0.000081707476,0.0010837322,0.000009503444,0.000003853984,0.0000082990355,0.00023196428,3.6242514e-7,0.0054249684,0.0016691757,0.0032882383,0.98819363],"study_design_scores_gemma":[0.00028141594,0.00006834497,0.011480505,0.00007755529,0.0000020986563,0.000021324851,0.000023934546,0.00041033106,0.9059508,0.075207725,0.006299611,0.00017634813],"about_ca_topic_score_codex":0.000046697132,"about_ca_topic_score_gemma":0.00023695618,"teacher_disagreement_score":0.98801726,"about_ca_system_score_codex":0.00003858632,"about_ca_system_score_gemma":0.000030360148,"threshold_uncertainty_score":0.23517734},"labels":[],"label_agreement":null},{"id":"W2137343758","doi":"10.1109/icdar.2001.953832","title":"Online recognition of sketched electrical diagrams","year":2002,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"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; Simple (philosophy); Invariant (physics); Matching (statistics); Translation (biology); Rotation (mathematics); Artificial intelligence; Algorithm; Theoretical computer science; Mathematics","score_opus":0.038434627882310474,"score_gpt":0.25654169490619533,"score_spread":0.21810706702388485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2137343758","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":[0.04981591,0.00009685388,0.9349719,0.00087462575,0.00006799171,0.00020221328,0.000006133107,0.000844909,0.013119407],"genre_scores_gemma":[0.69714564,0.00016168474,0.3015676,0.00052497967,0.00004758965,0.000018273304,0.000012529358,0.000007763728,0.0005139148],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99909514,0.00005245061,0.00025238656,0.00022147325,0.00020071256,0.00017783204],"domain_scores_gemma":[0.9993754,0.000092996655,0.00007349669,0.00027036585,0.000121105404,0.00006665192],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012273253,0.000087811866,0.00014177222,0.00013968148,0.000026139513,0.000031365536,0.00036668946,0.00007100733,0.0005680611],"category_scores_gemma":[0.00008101031,0.000077548124,0.00006988346,0.0005380185,0.00002845278,0.00028723365,0.000065987995,0.00010722492,0.0001761844],"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":[9.594772e-7,0.00040703523,0.00009677593,0.000004905451,0.0000057300476,0.0000037661275,0.00006584374,5.314113e-8,0.002638851,0.0023607023,0.0033922133,0.9910232],"study_design_scores_gemma":[0.0010427147,0.000991826,0.0023093726,0.00007301497,0.000021506066,0.000098151264,0.000022999095,0.10832925,0.77110505,0.11127796,0.0040092575,0.00071891845],"about_ca_topic_score_codex":0.000013138941,"about_ca_topic_score_gemma":0.000007190474,"teacher_disagreement_score":0.99030423,"about_ca_system_score_codex":0.000019176763,"about_ca_system_score_gemma":0.000007882868,"threshold_uncertainty_score":0.62198704},"labels":[],"label_agreement":null},{"id":"W213803360","doi":"","title":"Issues of Provenance in the Last Emperor’s Art Collecting","year":2012,"lang":"en","type":"article","venue":"Sound Ideas (University of Puget Sound)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Emperor; Provenance; Art; History; Ancient history; Geology; Geochemistry","score_opus":0.02243441006326411,"score_gpt":0.25243490189319867,"score_spread":0.23000049182993457,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W213803360","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":[0.8938152,0.00024619306,0.093893476,0.00052205863,0.00011215344,0.00030844795,0.000007731833,0.00011145629,0.010983234],"genre_scores_gemma":[0.9819576,0.000030711264,0.017118514,0.00007525141,0.000034167177,0.0000012261685,0.0000031963848,0.0000057195975,0.0007735756],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99886125,0.00016410276,0.00016848737,0.00019999674,0.0003160123,0.00029014598],"domain_scores_gemma":[0.99904954,0.00015699196,0.00020852503,0.00039913034,0.00013416463,0.000051628052],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008281313,0.000112896254,0.00022308475,0.0002023052,0.00018294845,0.000040687817,0.00092648645,0.00007687347,0.00004710615],"category_scores_gemma":[0.000083580875,0.000112035756,0.00009772466,0.0007607618,0.00017982612,0.0009888022,0.00021480855,0.00016564228,0.000048455964],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018469977,0.000373871,0.041640274,0.000102665,0.00003873069,0.000010469394,0.030379893,0.0000050758117,0.00029853694,0.91940653,0.006814241,0.00091124576],"study_design_scores_gemma":[0.00032608974,0.00009921482,0.010718493,0.00006413333,0.000011407807,0.00001616979,0.0053268652,0.00016249962,0.00016785532,0.9803951,0.0025466955,0.00016550037],"about_ca_topic_score_codex":0.00020868084,"about_ca_topic_score_gemma":0.0002995855,"teacher_disagreement_score":0.088142395,"about_ca_system_score_codex":0.000059883118,"about_ca_system_score_gemma":0.000053398166,"threshold_uncertainty_score":0.45686856},"labels":[],"label_agreement":null},{"id":"W2139109513","doi":"10.1109/icdar.1997.619858","title":"A feature for character recognition based on directional distance distributions","year":2002,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Pattern recognition (psychology); Numeral system; Computer science; Artificial intelligence; Feature extraction; Feature (linguistics); Character recognition; Classifier (UML); Artificial neural network; Intelligent character recognition; Handwriting recognition; Character (mathematics); Speech recognition; Mathematics; Image (mathematics)","score_opus":0.02723109808343117,"score_gpt":0.24568898994500618,"score_spread":0.21845789186157502,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139109513","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":[0.0001530152,0.000012025616,0.9779242,0.0108111175,0.00019066482,0.00036367905,0.0002446907,0.00075292145,0.009547682],"genre_scores_gemma":[0.4420559,0.00002646322,0.5411304,0.005308937,0.00038323886,0.0014128521,0.0006223569,0.00002921562,0.009030585],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99908507,0.000034872086,0.0001190536,0.000355005,0.00019038,0.00021562447],"domain_scores_gemma":[0.99921095,0.00018417447,0.000059750702,0.00027994456,0.00018842888,0.000076736396],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012568671,0.00012833891,0.000107051215,0.00010274678,0.00020467315,0.00013933743,0.00024323366,0.000084652595,0.00037233063],"category_scores_gemma":[0.00009106402,0.00011486609,0.00011261986,0.0002952289,0.00002733223,0.0003697471,0.000020924077,0.0001232233,0.00020250132],"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":[0.000032684646,0.0007397416,0.00013448346,0.00003483534,0.000020693074,0.000006329188,0.000049956827,0.0000021726091,0.001244869,0.031470906,0.31772834,0.648535],"study_design_scores_gemma":[0.0014323079,0.0005789154,0.002486335,0.00017995019,0.000020634296,0.000029879142,0.0000055198248,0.30453154,0.09733482,0.02553134,0.5669999,0.0008688353],"about_ca_topic_score_codex":0.0000013162025,"about_ca_topic_score_gemma":0.0000043780688,"teacher_disagreement_score":0.64766616,"about_ca_system_score_codex":0.00007518967,"about_ca_system_score_gemma":0.000012356508,"threshold_uncertainty_score":0.4684103},"labels":[],"label_agreement":null},{"id":"W2139307815","doi":"10.1109/icdar.1995.598934","title":"Symbolic/neural recognition of cursive amounts on bank cheques","year":2002,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Cursive; Computer science; Speech recognition; Artificial intelligence; Artificial neural network; Pattern recognition (psychology); Natural language processing","score_opus":0.03859048849129588,"score_gpt":0.2567163389764583,"score_spread":0.21812585048516242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139307815","genre_codex":"other","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":[0.36515555,0.00023138916,0.19056313,0.0035410975,0.00094559696,0.0011763913,0.000050548806,0.0030501436,0.43528616],"genre_scores_gemma":[0.9797812,0.0000812241,0.017942665,0.0009815455,0.00005756942,0.000034837918,0.0000065129925,0.0000108306995,0.001103613],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99884033,0.00007245814,0.000267965,0.00031525953,0.00028338048,0.0002206013],"domain_scores_gemma":[0.9991337,0.00009421373,0.00011772842,0.00037458484,0.00020471757,0.0000750422],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013220332,0.00014107971,0.00018161314,0.0002129241,0.000051718802,0.00006278844,0.00047025495,0.00008116927,0.00084745785],"category_scores_gemma":[0.00006587479,0.00012659299,0.000085864616,0.00032293933,0.0000563078,0.0005337929,0.000082869345,0.00012743038,0.000594945],"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":[0.0000074896566,0.00037842512,0.00018063418,0.000031008196,0.000025057308,0.000016396521,0.0007963703,9.980765e-7,0.0049256366,0.013030172,0.026658325,0.9539495],"study_design_scores_gemma":[0.0005496144,0.00078699505,0.0014425749,0.00017030105,0.000012897101,0.000060843053,0.000044650544,0.016253125,0.94520044,0.033447918,0.0015277617,0.00050284754],"about_ca_topic_score_codex":0.000031095085,"about_ca_topic_score_gemma":0.000004046406,"teacher_disagreement_score":0.9534466,"about_ca_system_score_codex":0.000034076667,"about_ca_system_score_gemma":0.0000072031125,"threshold_uncertainty_score":0.92790693},"labels":[],"label_agreement":null},{"id":"W2139332812","doi":"10.1109/sibgra.1998.722790","title":"Morphological approach of handwritten word skew correction","year":2002,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Skew; Computer science; Word (group theory); Artificial intelligence; Heuristic; Task (project management); Speech recognition; Handwriting recognition; Convex hull; Pattern recognition (psychology); Regular polygon; Feature extraction; Mathematics; Engineering","score_opus":0.03124099905645732,"score_gpt":0.2368856396100069,"score_spread":0.20564464055354956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139332812","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":[0.003222331,0.000057033933,0.867611,0.0001832644,0.00014003509,0.00014296388,7.8330675e-7,0.0005994947,0.12804312],"genre_scores_gemma":[0.72124916,0.000046917492,0.27451706,0.00024549695,0.000033370437,0.00003277911,0.0000023289433,0.000005739793,0.003867112],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989735,0.000065354805,0.00024410208,0.00031188288,0.00021839634,0.00018676622],"domain_scores_gemma":[0.9993301,0.000058844755,0.00007828632,0.00037050826,0.00009569231,0.000066561544],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019615945,0.000107517226,0.0001791164,0.00012371689,0.000052689848,0.0000531319,0.00050499354,0.000099826655,0.0005913079],"category_scores_gemma":[0.000043936365,0.00008650671,0.00008046873,0.00043520768,0.00006499816,0.0002950992,0.0001377503,0.00013133486,0.0001392889],"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":[0.0000048885486,0.0006583876,0.0006186495,0.000020010693,0.000020397,0.000019552961,0.0003508985,0.0000034525697,0.003747644,0.016507262,0.102751374,0.8752975],"study_design_scores_gemma":[0.0018613322,0.00127709,0.008142012,0.00012235531,0.000039625225,0.0015363151,0.00019443154,0.5689013,0.35496464,0.036008917,0.025376614,0.0015753654],"about_ca_topic_score_codex":0.000018819104,"about_ca_topic_score_gemma":7.798708e-7,"teacher_disagreement_score":0.87372214,"about_ca_system_score_codex":0.000019152085,"about_ca_system_score_gemma":0.0000056413373,"threshold_uncertainty_score":0.6474407},"labels":[],"label_agreement":null},{"id":"W2139392961","doi":"10.1016/j.imavis.2006.01.005","title":"Methodology for the design of NN-based month-word recognizers written on Brazilian bank checks","year":2006,"lang":"en","type":"article","venue":"Image and Vision Computing","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":16,"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; Modular design; Set (abstract data type); Feature (linguistics); Artificial intelligence; Artificial neural network; Perceptron; Speech recognition; Context (archaeology); Modular neural network; Class (philosophy); Feature extraction; Word (group theory); Pattern recognition (psychology); Natural language processing; Time delay neural network; Mathematics","score_opus":0.0490991960448673,"score_gpt":0.34488985252260457,"score_spread":0.2957906564777373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139392961","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":[0.0040558297,0.0001473216,0.9931925,0.00137347,0.00014701742,0.00054789154,0.0000048180154,0.00019951984,0.00033162185],"genre_scores_gemma":[0.3000163,0.000010336805,0.6991551,0.00065456185,0.00009132676,0.000017053218,0.000004140718,0.000013909532,0.00003728064],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983094,0.0003805469,0.00040610487,0.00043295053,0.00018402417,0.00028697055],"domain_scores_gemma":[0.9947915,0.004344035,0.00022415341,0.00038017562,0.00021329212,0.000046863162],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002169739,0.0001748747,0.00027926738,0.00016199563,0.0002771888,0.00014099372,0.0005090215,0.00009407404,0.000009649542],"category_scores_gemma":[0.00028831247,0.00012937492,0.000107749416,0.00027010968,0.00011929913,0.00016449063,0.00013160428,0.00015864254,0.0000047913472],"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":[0.000053286545,0.00006289525,0.00007479863,0.00003578004,0.000012203975,0.0000047081007,0.00009848062,0.00034082963,0.01206756,0.0006407399,0.0048917304,0.981717],"study_design_scores_gemma":[0.001147137,0.00071471545,0.0026007092,0.00020545402,0.00002634507,0.000012888237,0.00004114552,0.7828822,0.19820952,0.012071031,0.0017847485,0.00030408992],"about_ca_topic_score_codex":0.00007723545,"about_ca_topic_score_gemma":0.000003418193,"teacher_disagreement_score":0.9814129,"about_ca_system_score_codex":0.000017739754,"about_ca_system_score_gemma":0.000041750198,"threshold_uncertainty_score":0.5275756},"labels":[],"label_agreement":null},{"id":"W2140301238","doi":"10.1109/icdar.2009.229","title":"Online Recognition of Multi-Stroke Symbols with Orthogonal Series","year":2009,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Robustness (evolution); Support vector machine; Legendre polynomials; Computation; Pattern recognition (psychology); Computer science; Artificial intelligence; Mathematics; Algorithm; Mathematical analysis","score_opus":0.027996240833454637,"score_gpt":0.26506800217056203,"score_spread":0.2370717613371074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140301238","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":[0.12818581,0.000025440344,0.8654314,0.001007917,0.00003566712,0.00024848463,0.000048087422,0.0006910633,0.0043261126],"genre_scores_gemma":[0.41787735,0.000025362979,0.58096474,0.00043441902,0.00002159199,0.0000080203245,0.000027388794,0.000004788865,0.00063633063],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990688,0.0000370931,0.0002424073,0.00025223035,0.00022736783,0.00017207822],"domain_scores_gemma":[0.99926436,0.000028276861,0.00010276229,0.00027229957,0.00026691135,0.0000653926],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012802081,0.00012318803,0.00017274547,0.00013507412,0.000042214535,0.000045958885,0.00031164815,0.000058077796,0.00008220642],"category_scores_gemma":[0.000023162276,0.00009575154,0.000049685787,0.00026372957,0.00004990885,0.00070798886,0.000039643757,0.000101276135,0.000023662384],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045312816,0.0009162579,0.0007108359,0.000021818018,0.000024844003,0.000026305794,0.0002131261,0.000002092591,0.025065491,0.008465008,0.00042125536,0.96408767],"study_design_scores_gemma":[0.0013363576,0.0024862923,0.021962292,0.00022050648,0.000023109353,0.0002746888,0.0001412535,0.002987921,0.95496696,0.014181772,0.0008004347,0.00061841944],"about_ca_topic_score_codex":0.000007169091,"about_ca_topic_score_gemma":0.000045188877,"teacher_disagreement_score":0.9634692,"about_ca_system_score_codex":0.0000124604585,"about_ca_system_score_gemma":0.000050296374,"threshold_uncertainty_score":0.3904634},"labels":[],"label_agreement":null},{"id":"W2140565904","doi":"10.5539/cis.v7n1p162","title":"Layout Analysis for Scanned PDF and Transformation to the Structured PDF Suitable for Vocalization and Navigation","year":2014,"lang":"en","type":"article","venue":"Computer and Information Science","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Optical character recognition; Software; Graphics; Reading (process); Section (typography); Information retrieval; Transformation (genetics); Font; ASCII; Representation (politics); Artificial intelligence; Computer graphics (images); Image (mathematics); Programming language","score_opus":0.009019937935547423,"score_gpt":0.24878208890446957,"score_spread":0.23976215096892214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140565904","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":[0.02335754,0.000007185281,0.9745152,0.00087491394,0.00010128743,0.00076360547,0.000011530262,0.00006696104,0.00030177776],"genre_scores_gemma":[0.8770046,0.000010723435,0.121291384,0.0014973736,0.00003760197,0.00008999976,0.000050128096,0.0000021051774,0.00001606834],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99906087,0.000025833595,0.0002954903,0.00020321606,0.00022868268,0.00018589845],"domain_scores_gemma":[0.9990685,0.000117284144,0.00011303084,0.00017760687,0.00042118484,0.00010237561],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0012986147,0.000099169934,0.00012999633,0.00039458508,0.00058432214,0.0010430003,0.00028990835,0.000042717285,0.0000030271378],"category_scores_gemma":[0.00007441709,0.000075210795,0.000029303434,0.0009998144,0.00010177641,0.006290242,0.00008737789,0.000037632348,0.000006021851],"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":[0.000016424081,0.000007047917,0.00033270652,0.00010636111,0.000020583238,1.2457041e-8,0.0107633,0.0014318416,0.0002893669,0.074783504,0.00040685688,0.911842],"study_design_scores_gemma":[0.0003149662,0.00015033608,0.013735258,0.000015655885,0.000020785521,0.0000051719617,0.00005909748,0.96717155,0.002770859,0.0028529193,0.012781084,0.0001223178],"about_ca_topic_score_codex":0.00000590338,"about_ca_topic_score_gemma":0.0000044662147,"teacher_disagreement_score":0.9657397,"about_ca_system_score_codex":0.000020550266,"about_ca_system_score_gemma":0.000034078188,"threshold_uncertainty_score":0.99999404},"labels":[],"label_agreement":null},{"id":"W2140602248","doi":"10.1109/icdar.2005.195","title":"Recognition for large sets of handwritten mathematical symbols","year":2005,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Handwriting recognition; Computer science; Artificial intelligence; Pattern recognition (psychology); Handwriting; Character recognition; Matching (statistics); Computation; Intelligent character recognition; Set (abstract data type); Intelligent word recognition; Feature extraction; Speech recognition; Algorithm; Mathematics; Image (mathematics)","score_opus":0.028482399441100807,"score_gpt":0.29071525914526786,"score_spread":0.26223285970416704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140602248","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":[0.00543617,0.000020255047,0.9799757,0.001202203,0.000032625776,0.00047364438,0.000030484298,0.00042316748,0.012405762],"genre_scores_gemma":[0.31784892,0.000009910038,0.6808971,0.00056888256,0.000052717827,0.0001414677,0.000017011693,0.0000107738515,0.00045316957],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99890953,0.000032254884,0.00035860314,0.00025052796,0.00019336327,0.00025571484],"domain_scores_gemma":[0.9990949,0.0001956647,0.0000940552,0.0003142035,0.00022699567,0.00007418031],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005106896,0.00011162341,0.00020821381,0.00012636674,0.00005655737,0.00005657548,0.00038838005,0.00008850439,0.0003407404],"category_scores_gemma":[0.00011011035,0.000097726304,0.00011323938,0.00016859986,0.000020524525,0.0004968853,0.00009640635,0.00006328562,0.00023196175],"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":[0.000012622391,0.0005488057,0.0000452624,0.00015054269,0.00003350998,0.0000015625624,0.00045899616,2.6365447e-7,0.0037901134,0.16995893,0.016002852,0.80899656],"study_design_scores_gemma":[0.0011803183,0.000261237,0.00012728722,0.00015289799,0.000022071205,0.000042988628,0.00005853003,0.03603707,0.5927512,0.35912895,0.009859628,0.0003777853],"about_ca_topic_score_codex":0.0000012489314,"about_ca_topic_score_gemma":0.0000046407094,"teacher_disagreement_score":0.8086187,"about_ca_system_score_codex":0.000016387463,"about_ca_system_score_gemma":0.00002770161,"threshold_uncertainty_score":0.3985163},"labels":[],"label_agreement":null},{"id":"W2141365733","doi":"10.1142/s0218126605002192","title":"A NEURAL-BASED PAGE SEGMENTATION SYSTEM","year":2005,"lang":"en","type":"article","venue":"Journal of Circuits Systems and Computers","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Halftone; Computer science; Artificial intelligence; Artificial neural network; Graphics; Segmentation; Block (permutation group theory); Pattern recognition (psychology); Optical character recognition; Computer vision; Perceptron; Computer graphics; Image segmentation; Flowchart; Image (mathematics); Computer graphics (images); Mathematics","score_opus":0.015838938468749394,"score_gpt":0.2359935067461417,"score_spread":0.2201545682773923,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2141365733","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":[0.043943115,0.00066412496,0.9535878,0.0004203503,0.00075937907,0.00018879895,0.0000014322036,0.00013510737,0.0002999073],"genre_scores_gemma":[0.98519456,0.0000124849175,0.014167984,0.00027122928,0.00032206404,0.000006029122,5.5530376e-7,0.0000086647115,0.000016406211],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985031,0.00015894495,0.00061202544,0.00017199748,0.00038019684,0.00017373936],"domain_scores_gemma":[0.9987582,0.000097738164,0.0005597757,0.00018940082,0.00024410244,0.00015076005],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006042811,0.00013571257,0.0002948886,0.00028420173,0.00008776656,0.00038430138,0.0004075953,0.000057586316,0.0000012614418],"category_scores_gemma":[0.0000072451835,0.00011383185,0.000096051204,0.0001972784,0.000021510772,0.00073757384,0.00003826564,0.00013878656,0.000005792321],"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":[0.000010929395,0.00016152866,0.00077410747,0.00058787793,0.00012591312,0.0002453995,0.0012140686,0.004292584,0.0097154435,0.012695257,0.005360297,0.9648166],"study_design_scores_gemma":[0.0023674811,0.0008506302,0.0015039736,0.0014885901,0.000050325052,0.004170126,0.0004200559,0.97588736,0.006841902,0.00011071925,0.005781008,0.0005278251],"about_ca_topic_score_codex":0.0000080181435,"about_ca_topic_score_gemma":5.9777534e-7,"teacher_disagreement_score":0.97159475,"about_ca_system_score_codex":0.00011475433,"about_ca_system_score_gemma":0.000060874027,"threshold_uncertainty_score":0.4641928},"labels":[],"label_agreement":null},{"id":"W2141812924","doi":"10.1109/iwfhr.2002.1030951","title":"Feature sets evaluation for handwritten word recognition","year":2003,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"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; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Feature (linguistics); Computer science; Lexicon; Artificial intelligence; Pattern recognition (psychology); Set (abstract data type); Word (group theory); Feature extraction; Speech recognition; Segmentation; Baseline (sea); Natural language processing; Mathematics; Linguistics","score_opus":0.0449068260755966,"score_gpt":0.3047346712737821,"score_spread":0.2598278451981855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2141812924","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":[0.0030778202,0.000100275785,0.96867144,0.0021687408,0.00028952365,0.0012197478,0.000009193756,0.000684145,0.02377914],"genre_scores_gemma":[0.15474224,0.000027540402,0.8407436,0.0015380785,0.00006583543,0.00092261937,0.00009379292,0.000021779126,0.0018445136],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986557,0.00016249818,0.00016213523,0.00041479792,0.00034135158,0.00026354432],"domain_scores_gemma":[0.9987754,0.00013138291,0.000081878105,0.00035367807,0.0005742679,0.0000833566],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012438608,0.00014413906,0.00013718785,0.00015100045,0.00014662766,0.00019797488,0.00028799527,0.00013427332,0.00020205643],"category_scores_gemma":[0.00036048793,0.00013232132,0.000093767565,0.00034632947,0.000019053809,0.0006585296,0.000030799678,0.00010381664,0.00013259266],"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":[0.000004787255,0.000050071696,0.000024995254,0.000013145073,0.000012960747,8.6339367e-7,0.00008871044,6.045945e-7,0.00089490775,0.0061924723,0.045195937,0.94752055],"study_design_scores_gemma":[0.0024571102,0.000339929,0.0005385706,0.00010796573,0.000068518275,0.00009888824,0.00009807308,0.026446283,0.33522835,0.5163235,0.11742165,0.00087112054],"about_ca_topic_score_codex":0.000002931032,"about_ca_topic_score_gemma":0.000011976145,"teacher_disagreement_score":0.94664943,"about_ca_system_score_codex":0.000068874266,"about_ca_system_score_gemma":0.000097137825,"threshold_uncertainty_score":0.5395907},"labels":[],"label_agreement":null},{"id":"W2142069714","doi":"10.1109/34.824821","title":"Online and off-line handwriting recognition: a comprehensive survey","year":2000,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":2489,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Handwriting; Computer science; Handwriting recognition; Intelligent character recognition; Preprocessor; Speech recognition; Artificial intelligence; Character (mathematics); Natural language processing; Reading (process); Word (group theory); Word recognition; Right-to-left; Character recognition; Feature extraction; Image (mathematics); Linguistics","score_opus":0.047210766476225824,"score_gpt":0.29516786016176455,"score_spread":0.24795709368553873,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142069714","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":[0.08270099,0.00025309794,0.91593283,0.0003325498,0.00004581918,0.00015368534,0.00031270276,0.00019884609,0.00006949147],"genre_scores_gemma":[0.98872364,0.0042847525,0.005547666,0.0011008544,0.000023986631,0.0000249479,0.000069066955,0.000014402745,0.00021066023],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99806005,0.00023955741,0.00050104107,0.00068112713,0.00025287172,0.00026538418],"domain_scores_gemma":[0.99876577,0.00035526385,0.00009810795,0.00039724808,0.00020432075,0.00017930372],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00031405565,0.00027782368,0.00042659946,0.00050858565,0.00027506333,0.00022199735,0.00029932908,0.00009281442,0.0007576719],"category_scores_gemma":[0.0000073386427,0.00026113327,0.00016726177,0.0011601013,0.000116331415,0.00033119417,0.000007275473,0.00033959688,0.00005343977],"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":[0.00001391798,0.00020827336,0.00029708084,0.000012714069,0.00021687483,0.0000117006575,0.000121417754,0.00027630938,0.00008642333,0.0000022311408,0.000007258606,0.9987458],"study_design_scores_gemma":[0.0010654782,0.00146045,0.043509845,0.00042566395,0.0014479146,0.0003852046,0.00023313084,0.66465366,0.2808706,0.0025440787,0.0010101281,0.0023938622],"about_ca_topic_score_codex":0.001827967,"about_ca_topic_score_gemma":0.0038280543,"teacher_disagreement_score":0.99635196,"about_ca_system_score_codex":0.000020222436,"about_ca_system_score_gemma":0.000015894282,"threshold_uncertainty_score":0.9999841},"labels":[],"label_agreement":null},{"id":"W2142978586","doi":"10.1109/tpami.2007.70753","title":"Bayes Classification of Online Arabic Characters by Gibbs Modeling of Class Conditional Densities","year":2008,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":61,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique; École de Technologie Supérieure; Hôpital Notre-Dame","funders":"","keywords":"Pattern recognition (psychology); Artificial intelligence; Bayes' theorem; Histogram; Principle of maximum entropy; Density estimation; Bayes error rate; Naive Bayes classifier; Mathematics; Computer science; Conditional probability distribution; Gibbs sampling; Probability density function; Bayes classifier; Support vector machine; Bayesian probability; Statistics; Image (mathematics)","score_opus":0.03388004897220471,"score_gpt":0.2716556090274912,"score_spread":0.2377755600552865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142978586","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":[0.14603156,0.00004875562,0.853117,0.000346468,0.00003605965,0.00008410624,0.00025925768,0.00006016013,0.000016654247],"genre_scores_gemma":[0.99648064,0.00074515,0.0023990509,0.00020835949,0.0000079418,0.000016922188,0.00007834213,0.000008185655,0.00005540125],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998507,0.00008211892,0.00058258185,0.00036349567,0.0003235528,0.00014119974],"domain_scores_gemma":[0.99897206,0.00012446159,0.00022835197,0.00032597757,0.00027730173,0.00007182352],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001582411,0.00017090286,0.0003662217,0.0005927225,0.0001196973,0.000023202174,0.00029871293,0.00007456919,0.000062021245],"category_scores_gemma":[0.0000055416067,0.00016095628,0.00022591106,0.00065346743,0.0001578661,0.00031866683,0.000004413519,0.00018509585,0.000003757118],"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":[0.00006319589,0.0018469818,0.0021699425,0.00014487318,0.0016709659,0.000012484041,0.0014488252,0.0456416,0.048730765,0.00079217023,0.00007915879,0.897399],"study_design_scores_gemma":[0.00006606284,0.00010185137,0.0015923665,0.000031224143,0.00014682265,0.000015632808,0.000054852073,0.7182584,0.27912068,0.0004457427,0.000008461549,0.00015795618],"about_ca_topic_score_codex":0.00040926962,"about_ca_topic_score_gemma":0.00019091545,"teacher_disagreement_score":0.89724106,"about_ca_system_score_codex":0.000025143328,"about_ca_system_score_gemma":0.000038663748,"threshold_uncertainty_score":0.6563606},"labels":[],"label_agreement":null},{"id":"W2143155961","doi":"10.1109/icdar.2009.80","title":"Isolated Handwritten Farsi Numerals Recognition Using Sparse and Over-Complete Representations","year":2009,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Numeral system; Computer science; Pattern recognition (psychology); Artificial intelligence; Classifier (UML); Handwriting recognition; Convolutional neural network; Speech recognition; Generalization; K-SVD; Feature extraction; Sparse approximation; Mathematics","score_opus":0.05087033088613559,"score_gpt":0.30035959959991104,"score_spread":0.24948926871377547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2143155961","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":[0.116889566,0.000057985515,0.8766127,0.0011187262,0.000072148745,0.00033807528,0.000011832962,0.0008047242,0.0040942235],"genre_scores_gemma":[0.7361975,0.0000726586,0.26119548,0.0022148753,0.00005765697,0.000012873493,0.00002681853,0.000011457549,0.00021071738],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985306,0.00010195995,0.0003488748,0.0005044758,0.00021606687,0.00029799592],"domain_scores_gemma":[0.99912083,0.000073438874,0.00011769995,0.0004042697,0.00014819046,0.0001355536],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022632028,0.00017872115,0.00020734404,0.00025774358,0.00023372579,0.00036752856,0.0002966741,0.000095592004,0.00015804594],"category_scores_gemma":[0.000046325295,0.00017813951,0.00006602869,0.00050173776,0.000044514538,0.0012475961,0.0000987389,0.00014198411,0.000053331914],"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":[0.000023307348,0.00020610912,0.000501526,0.000014171092,0.000044248554,0.000052367293,0.0006340124,0.0000058710125,0.11733384,0.006173488,0.003254621,0.87175643],"study_design_scores_gemma":[0.0030318552,0.0010399068,0.027180942,0.00037165,0.00011111621,0.0009674368,0.00017958904,0.50679696,0.10377294,0.35130614,0.0031058078,0.0021356684],"about_ca_topic_score_codex":0.00014319253,"about_ca_topic_score_gemma":0.000010938369,"teacher_disagreement_score":0.8696208,"about_ca_system_score_codex":0.00003632341,"about_ca_system_score_gemma":0.00002968472,"threshold_uncertainty_score":0.72643185},"labels":[],"label_agreement":null},{"id":"W2144026429","doi":"10.1109/icdar.2001.953836","title":"Character recognition experiments using Unipen data","year":2002,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"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":"Backpropagation; Computer science; Pattern recognition (psychology); Handwriting; Artificial intelligence; Cursive; Classifier (UML); Character recognition; Handwriting recognition; Artificial neural network; Speech recognition; Training set; Representation (politics); Optical character recognition; Feature extraction","score_opus":0.2512199841090454,"score_gpt":0.33291980309020597,"score_spread":0.08169981898116058,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144026429","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":[0.024489334,0.00006994176,0.9413934,0.00051612366,0.00026374665,0.00028987147,0.000018428358,0.0010274908,0.03193168],"genre_scores_gemma":[0.34113023,0.000079728845,0.654891,0.0021977278,0.00016647775,0.000023877115,0.00009766724,0.000021516315,0.0013917462],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989276,0.000055846653,0.00019251253,0.00042415064,0.00019692819,0.00020295785],"domain_scores_gemma":[0.9987648,0.00002548384,0.00006434267,0.0010036493,0.00006839119,0.000073327865],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00018163616,0.00010695972,0.00010214783,0.00011326956,0.000086691216,0.00020144944,0.0011488181,0.000055448785,0.0017763721],"category_scores_gemma":[0.000024318864,0.00010074954,0.00002338671,0.00022699583,0.000021076828,0.0020941303,0.0006001047,0.0000820294,0.0010196472],"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":[0.0000016813491,0.0002267887,0.00011237982,0.000008309244,0.000022524118,0.000024830319,0.00042909355,8.4641236e-8,0.022691675,0.0006140826,0.015289764,0.9605788],"study_design_scores_gemma":[0.00082936144,0.00012758416,0.0002754614,0.00013133843,0.000020186138,0.00019941007,0.00007848832,0.4580191,0.49550024,0.0062063085,0.037604842,0.0010076816],"about_ca_topic_score_codex":0.000030376785,"about_ca_topic_score_gemma":0.0000015650553,"teacher_disagreement_score":0.9595711,"about_ca_system_score_codex":0.000030541036,"about_ca_system_score_gemma":0.000008518902,"threshold_uncertainty_score":0.9997582},"labels":[],"label_agreement":null},{"id":"W2144108697","doi":"10.1109/mwscas.2011.6026438","title":"Online Arabic/Persian character recognition using neural network classifier and DCT features","year":2011,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Cursive; Computer science; Intelligent character recognition; Handwriting recognition; Artificial intelligence; Character recognition; Handwriting; Classifier (UML); Arabic; Character (mathematics); Pattern recognition (psychology); Feature extraction; Speech recognition; Artificial neural network; Intelligent word recognition; Persian; Set (abstract data type); Arabic script; Feature (linguistics); Optical character recognition; Image (mathematics); Mathematics","score_opus":0.0769545768451445,"score_gpt":0.2648684599243065,"score_spread":0.18791388307916201,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144108697","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":[0.7668701,0.00017610929,0.21133792,0.00094315375,0.0006979852,0.0005311056,0.00001688858,0.0013593805,0.018067364],"genre_scores_gemma":[0.5985599,0.000053960983,0.39804813,0.0026023677,0.0003426306,0.000012590638,0.000026057958,0.000020326615,0.00033400135],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9988135,0.00008846093,0.00021605124,0.00040501019,0.00014781857,0.0003291499],"domain_scores_gemma":[0.99935037,0.000035386904,0.000091970294,0.00028681927,0.00010703221,0.00012840967],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001863473,0.0001772464,0.00017301118,0.00011979299,0.0001419545,0.00014273646,0.0002921428,0.00012680369,0.00019686467],"category_scores_gemma":[0.00001726433,0.00015108497,0.00006298401,0.00024975996,0.00006709084,0.0009121444,0.00016365807,0.0002246119,0.000026167572],"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":[0.00003456882,0.0002723156,0.0032349878,0.000027047243,0.000049887352,0.000064543136,0.001081773,0.0000015477146,0.0019479858,0.0022323837,0.00420812,0.98684484],"study_design_scores_gemma":[0.0029694217,0.0016231645,0.5482702,0.0007817868,0.00022155975,0.0027881041,0.000662409,0.24841218,0.06837189,0.11380767,0.007663784,0.0044278195],"about_ca_topic_score_codex":0.00007540118,"about_ca_topic_score_gemma":0.00004684992,"teacher_disagreement_score":0.98241705,"about_ca_system_score_codex":0.000022766762,"about_ca_system_score_gemma":0.000020780632,"threshold_uncertainty_score":0.6161066},"labels":[],"label_agreement":null},{"id":"W2145785542","doi":"10.1080/02643290802421160","title":"The spatio-temporal dynamics of visual letter recognition","year":2008,"lang":"en","type":"article","venue":"Cognitive Neuropsychology","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":61,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; University of Victoria","funders":"","keywords":"Identification (biology); Feature (linguistics); Pattern recognition (psychology); Artificial intelligence; Dynamics (music); Space (punctuation); Psychology; Computer science; Speech recognition; Linguistics","score_opus":0.028493038014201093,"score_gpt":0.29309013254341304,"score_spread":0.26459709452921193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145785542","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":[0.45829734,0.00005039041,0.5292461,0.003033472,0.0007137439,0.00047410047,0.000026041434,0.00037425506,0.0077845743],"genre_scores_gemma":[0.9919547,0.00014737906,0.0030521941,0.0043031145,0.00012148909,0.00007308137,0.00008315758,0.000023488587,0.00024139223],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9980618,0.00044712884,0.00042835902,0.0004793393,0.00024941293,0.00033395994],"domain_scores_gemma":[0.99820757,0.00058549386,0.00026720364,0.0003274199,0.00053925713,0.00007308533],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027894942,0.00018726375,0.00021621528,0.00017257282,0.00029125423,0.000026518452,0.0005680612,0.00011216399,0.000049398026],"category_scores_gemma":[0.00025670574,0.00015496225,0.00011175914,0.0004622951,0.0005744145,0.00029708582,0.00015163029,0.00031457847,0.00023691858],"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":[0.00025493355,0.0006426675,0.013195734,0.000019004729,0.000079191756,0.00039911532,0.00061378273,2.153373e-7,0.0010702552,0.0021583217,0.0171028,0.96446395],"study_design_scores_gemma":[0.012671936,0.013591202,0.5478334,0.0005454167,0.00021723173,0.009187602,0.0005260815,0.019530643,0.17117985,0.1710952,0.04913425,0.00448723],"about_ca_topic_score_codex":0.000009483961,"about_ca_topic_score_gemma":0.00001862093,"teacher_disagreement_score":0.95997673,"about_ca_system_score_codex":0.000022388704,"about_ca_system_score_gemma":0.000046818834,"threshold_uncertainty_score":0.6319177},"labels":[],"label_agreement":null},{"id":"W2145786073","doi":"10.1109/83.935031","title":"Stroke-model-based character extraction from gray-level document images","year":2001,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":88,"is_retracted":false,"has_abstract":true,"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":"Thresholding; Artificial intelligence; Computer science; Pattern recognition (psychology); Segmentation; Character (mathematics); Font; Image segmentation; Handwriting; Computer vision; Image (mathematics); Mathematics","score_opus":0.024958479433401754,"score_gpt":0.2910954083966361,"score_spread":0.2661369289632344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145786073","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":[0.0073950216,0.00005319048,0.9891887,0.00089150807,0.00029008216,0.00028561807,0.00006518448,0.0011280517,0.0007027012],"genre_scores_gemma":[0.6723907,0.00004102522,0.3261687,0.0006235241,0.00005911021,0.00014359296,0.0000079762885,0.000030045328,0.0005353593],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99781024,0.000082138096,0.0004410874,0.00071962294,0.000512637,0.0004342825],"domain_scores_gemma":[0.99869734,0.000098534474,0.00020188953,0.0005248751,0.00031568517,0.00016167588],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00025386925,0.000333935,0.0002555452,0.00040808375,0.00048768605,0.00088417553,0.0005576271,0.00014280273,0.00017436127],"category_scores_gemma":[0.0000083257955,0.00033577002,0.0001705573,0.00044887135,0.00009030336,0.00340053,0.0000041400986,0.00049610273,0.00013315337],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045479544,0.00034544282,0.000011243736,0.00002103145,0.000019203326,0.00003383772,0.0001854251,0.0005623561,0.16265279,0.000009599571,0.00013266783,0.8359809],"study_design_scores_gemma":[0.0006395389,0.000079737576,0.00027113486,0.0001664557,0.00004011256,0.000030076315,0.000025718897,0.17137527,0.8250263,0.0015667435,0.0003312615,0.00044766648],"about_ca_topic_score_codex":0.00007566261,"about_ca_topic_score_gemma":0.000020321271,"teacher_disagreement_score":0.83553326,"about_ca_system_score_codex":0.00017597353,"about_ca_system_score_gemma":0.00017711884,"threshold_uncertainty_score":0.99990946},"labels":[],"label_agreement":null},{"id":"W2146182466","doi":"10.1109/icdar.2007.4378694","title":"A Human-Centric Off-Line Signature Verification System","year":2007,"lang":"en","type":"article","venue":"Proceedings of the International Conference on Document Analysis and Recognition","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"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; Signature (topology); Classifier (UML); Hidden Markov model; Artificial intelligence; Receiver operating characteristic; Machine learning; Task (project management); Data mining; Exploit; Authentication (law); Pattern recognition (psychology); Computer security; Engineering","score_opus":0.025903278226412127,"score_gpt":0.2823272085924719,"score_spread":0.25642393036605976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2146182466","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":[0.91045153,0.00007481868,0.052881412,0.0024079399,0.0003396669,0.00058192795,0.00002023801,0.0002726791,0.032969803],"genre_scores_gemma":[0.99659616,0.000085876854,0.0027835742,0.00010909,0.00006452706,0.000019639258,0.000020787173,0.0000050076983,0.0003153613],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985184,0.000011467595,0.00042105318,0.0003420002,0.0005655126,0.00014158587],"domain_scores_gemma":[0.9983822,0.000028946502,0.00048249774,0.00011535504,0.00093691016,0.00005409853],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00079056254,0.00013737081,0.0001918434,0.0005934971,0.00012750401,0.00025805918,0.00066634954,0.00008810836,0.00006289252],"category_scores_gemma":[0.00004425742,0.00010061039,0.00015737113,0.00081326644,0.000048299382,0.000459644,0.00014111772,0.00016218907,0.0000084681415],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010109159,0.00041200058,0.0046484154,0.00014862113,0.0013632888,0.000002872758,0.00061942014,0.0000051751344,0.14123328,0.51169884,0.0006240799,0.3391429],"study_design_scores_gemma":[0.0011836109,0.00039024462,0.023802169,0.00085302786,0.00083601696,0.000029448049,0.0010087715,0.027098417,0.86688673,0.07676395,0.0004494033,0.00069817854],"about_ca_topic_score_codex":0.000026820388,"about_ca_topic_score_gemma":0.000009868165,"teacher_disagreement_score":0.72565347,"about_ca_system_score_codex":0.000102411264,"about_ca_system_score_gemma":0.000014927304,"threshold_uncertainty_score":0.41027728},"labels":[],"label_agreement":null},{"id":"W2146466859","doi":"10.1109/icdar.1995.602024","title":"A comparative study of the k nearest neighbour, threshold and neural network classifiers for handwritten signature verification using an enhanced directional PDF","year":2002,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"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":"Classifier (UML); Backpropagation; Pattern recognition (psychology); Computer science; Artificial neural network; Artificial intelligence; Nearest neighbour; Machine learning; Speech recognition","score_opus":0.061717943050056956,"score_gpt":0.29249125750748456,"score_spread":0.2307733144574276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2146466859","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":[0.66531104,0.000090949434,0.33144462,0.00022362715,0.00023566833,0.0012681312,0.000004474781,0.00016052002,0.0012609544],"genre_scores_gemma":[0.98222625,0.0000047969124,0.017228756,0.00016594781,0.000088527675,0.000080765494,0.000002457825,0.000007537563,0.0001949862],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99880636,0.0001268103,0.00025439437,0.0003763058,0.00023292573,0.00020322588],"domain_scores_gemma":[0.99910533,0.0001130943,0.0001614157,0.00035608554,0.00019956581,0.000064498],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018750958,0.00014587391,0.00021406765,0.0000584842,0.00035371896,0.00014573794,0.00040794132,0.000079487116,0.00005184837],"category_scores_gemma":[0.000015316824,0.000107190725,0.00005376049,0.0004065288,0.000092878254,0.0005322835,0.00009659311,0.0001638352,0.0000014412266],"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":[0.0008747018,0.016340062,0.039530497,0.00030930317,0.0013310548,0.000015477799,0.08203743,0.049106687,0.47880387,0.046235893,0.04787682,0.23753822],"study_design_scores_gemma":[0.0009342771,0.0007187928,0.011627374,0.000035491965,0.000031471307,0.000010382761,0.00073945435,0.9532304,0.030018901,0.0022392482,0.00015311135,0.0002610899],"about_ca_topic_score_codex":0.000027354386,"about_ca_topic_score_gemma":0.00010742009,"teacher_disagreement_score":0.9041237,"about_ca_system_score_codex":0.000029626308,"about_ca_system_score_gemma":0.00001701028,"threshold_uncertainty_score":0.43711108},"labels":[],"label_agreement":null},{"id":"W2146945386","doi":"10.1109/icdar.2003.1227717","title":"Automatic filter selection using image quality assessment","year":2004,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal; École de Technologie Supérieure; Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Selection (genetic algorithm); Quality (philosophy); Image quality; Artificial intelligence; Filter (signal processing); Computer vision; Quality assessment; Image (mathematics); Reliability engineering; Engineering; Evaluation methods","score_opus":0.04898168066732066,"score_gpt":0.3573884840698989,"score_spread":0.30840680340257826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2146945386","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":[0.09001171,0.0000018743139,0.9025662,0.00041257316,0.00006666505,0.00014605318,5.6598606e-7,0.0011301106,0.0056642494],"genre_scores_gemma":[0.4092315,7.3546096e-7,0.59039104,0.00029695278,0.000016845685,0.000010682656,8.54383e-7,0.000004009275,0.00004733967],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99899733,0.000083877,0.00024501892,0.00025137546,0.0002380381,0.00018438179],"domain_scores_gemma":[0.9994728,0.000030797815,0.00007654031,0.00025484842,0.000108722576,0.000056278335],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042401912,0.00009677788,0.00011713158,0.0001011207,0.000107336564,0.00022128382,0.00027285356,0.000045809953,0.0002634042],"category_scores_gemma":[0.000021186603,0.00008718092,0.00005448955,0.000310061,0.000022223054,0.0008394001,0.000100990896,0.00010016168,0.00007447839],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000024741055,0.0007522202,0.0013542352,0.00015377396,0.00006827977,0.000027419595,0.000749547,0.000110351306,0.35275722,0.23131552,0.0015057257,0.41120324],"study_design_scores_gemma":[0.0007512607,0.00016421171,0.015618171,0.00008604431,0.000011787776,0.0001176586,0.000040090268,0.25348184,0.5899186,0.13902658,0.00021830208,0.0005654778],"about_ca_topic_score_codex":0.00021309643,"about_ca_topic_score_gemma":0.000018053519,"teacher_disagreement_score":0.41063774,"about_ca_system_score_codex":0.00022059727,"about_ca_system_score_gemma":0.00012223594,"threshold_uncertainty_score":0.35551345},"labels":[],"label_agreement":null},{"id":"W2147122038","doi":"10.1109/iwfhr.2004.53","title":"Handwritten Brazilian Month Recognition: An Analysis of Two NN Architectures and a Rejection Mechanism","year":2004,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"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; Modular design; Handwriting; Feature extraction; Handwriting recognition; Class (philosophy); Pattern recognition (psychology); Artificial intelligence; Feature (linguistics); Feed forward; Speech recognition; Modular neural network; Set (abstract data type); Architecture; Perceptron; Artificial neural network; Time delay neural network; Engineering","score_opus":0.015181083729453999,"score_gpt":0.267196482259825,"score_spread":0.252015398530371,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147122038","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":[0.29091373,0.000031550386,0.70679665,0.00033230893,0.00003910231,0.00018835039,0.000011824538,0.0004404756,0.0012460542],"genre_scores_gemma":[0.79916507,0.000029114248,0.20031266,0.0003533566,0.000029252107,0.00003081265,0.000023557544,0.000008983805,0.00004717496],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985288,0.0001005955,0.0003382871,0.00052903604,0.00028363848,0.00021968788],"domain_scores_gemma":[0.99899495,0.000047840625,0.00013442556,0.00049215707,0.00018276033,0.00014787122],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003756673,0.0001748246,0.00032295918,0.0008819419,0.00012527435,0.00013581487,0.00035260184,0.00008633769,0.000083914085],"category_scores_gemma":[0.000032586704,0.00015854284,0.00013061835,0.0012560317,0.000072535164,0.00043752877,0.00011477898,0.00013131,0.000007735101],"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":[0.000051002255,0.0005956864,0.000845804,0.000051262243,0.0008303434,0.000039326304,0.003367961,0.00039300087,0.03034375,0.07617733,0.00005708438,0.88724744],"study_design_scores_gemma":[0.0012717565,0.0008533136,0.0062398217,0.00006499809,0.00039780902,0.00008692207,0.00015675656,0.022547567,0.4013838,0.5664163,0.000053507953,0.0005274393],"about_ca_topic_score_codex":0.0009866393,"about_ca_topic_score_gemma":0.0020187648,"teacher_disagreement_score":0.88672,"about_ca_system_score_codex":0.0000389428,"about_ca_system_score_gemma":0.000042123796,"threshold_uncertainty_score":0.64651895},"labels":[],"label_agreement":null},{"id":"W2147321602","doi":"10.1007/978-3-540-78199-8_1","title":"Visual Recognition of Arabic Handwriting: Challenges and New Directions","year":2008,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Handwritten Text Recognition 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":"Université du Québec à Montréal; École de Technologie Supérieure","funders":"","keywords":"Handwriting; Arabic; Computer science; Intelligent character recognition; Natural language processing; Arabic script; Handwriting recognition; Speech recognition; Artificial intelligence; Linguistics; Character recognition; Image (mathematics); Feature extraction","score_opus":0.043749658325244446,"score_gpt":0.2699760798265204,"score_spread":0.22622642150127595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147321602","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":[0.00022395256,0.0067066443,0.9848705,0.0006679975,0.00047210781,0.00036062676,0.000004998451,0.00033453334,0.006358645],"genre_scores_gemma":[0.10713449,0.029026339,0.86156535,0.0007373972,0.000893119,0.000031666987,0.000014971241,0.00007960063,0.00051703845],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99702764,0.00004591088,0.00057297765,0.0012441882,0.00068033044,0.0004289783],"domain_scores_gemma":[0.997991,0.0004742303,0.0003536712,0.0006158014,0.0003528409,0.00021245761],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00052473514,0.0004309776,0.00057304965,0.0011918703,0.0002011291,0.00015990295,0.0010509983,0.00035335644,0.000018019984],"category_scores_gemma":[0.0001470261,0.00043190035,0.00011843734,0.00040565289,0.00073261326,0.00070721604,0.00065067055,0.00059030764,0.000018734609],"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":[0.0000029076011,0.000028174863,0.000004443514,0.000041311498,0.000008382238,0.000022178867,0.00071683206,0.00001387578,0.00017727837,0.0009766683,0.000027007465,0.99798095],"study_design_scores_gemma":[0.0014405446,0.001985716,0.00112542,0.0049234997,0.000057467307,0.0019054305,0.0000025176378,0.067451075,0.09083554,0.8179207,0.009287656,0.003064455],"about_ca_topic_score_codex":0.00003392069,"about_ca_topic_score_gemma":0.00008101864,"teacher_disagreement_score":0.9949165,"about_ca_system_score_codex":0.000114477705,"about_ca_system_score_gemma":0.00042833903,"threshold_uncertainty_score":0.99981326},"labels":[],"label_agreement":null},{"id":"W2147597509","doi":"10.1109/ccece.2009.5090216","title":"On-line signature verification using global features","year":2009,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Signature (topology); Computer science; Session (web analytics); Data mining; Linear discriminant analysis; Line (geometry); Pattern recognition (psychology); Artificial intelligence; Algorithm; Mathematics","score_opus":0.024911393281637648,"score_gpt":0.3040436276255757,"score_spread":0.279132234343938,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147597509","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":[0.0051498045,0.00005947271,0.97341126,0.0018122528,0.00009782177,0.00012821173,0.0000025369252,0.0007646715,0.018573966],"genre_scores_gemma":[0.79909915,0.000005009665,0.19737116,0.003304576,0.000048578928,0.0000019060274,0.000004126822,0.000002236286,0.00016328087],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99925107,0.000029558858,0.000111374844,0.00026302112,0.00019584243,0.00014913313],"domain_scores_gemma":[0.99946153,0.000019400222,0.00004308258,0.00033833485,0.00008232068,0.00005533265],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000098076984,0.00009877725,0.00008269076,0.000051489587,0.00007189149,0.00012621935,0.0004098345,0.00009524067,0.00003134978],"category_scores_gemma":[0.000031733034,0.00008318524,0.00004171676,0.00035469566,0.000012301322,0.0002843296,0.000027732773,0.00011091986,0.000042066895],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009330486,0.00012948534,0.00001176437,0.0000025091422,0.000005384452,0.000011236541,0.000040719624,0.00010700464,0.008527864,0.5269381,0.01299688,0.45121977],"study_design_scores_gemma":[0.00060651696,0.0008925502,0.00682816,0.000093571696,0.000012136284,0.00013542119,0.000014667239,0.069749214,0.31043774,0.6078965,0.0026066343,0.0007268944],"about_ca_topic_score_codex":0.000008345188,"about_ca_topic_score_gemma":0.0000018965837,"teacher_disagreement_score":0.7939493,"about_ca_system_score_codex":0.000064783955,"about_ca_system_score_gemma":0.00002994095,"threshold_uncertainty_score":0.33921957},"labels":[],"label_agreement":null},{"id":"W2148440013","doi":"10.1109/icfhr.2010.28","title":"Word Spotting in Gray Scale Handwritten Pashto Documents","year":2010,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Spotting; Artificial intelligence; Computer science; Handwriting; Pattern recognition (psychology); Word (group theory); Grayscale; Feature vector; Binary number; Handwriting recognition; Scripting language; Feature (linguistics); Speech recognition; Feature extraction; Natural language processing; Pixel; Mathematics; Arithmetic","score_opus":0.007786585934421827,"score_gpt":0.25220589950314337,"score_spread":0.24441931356872154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148440013","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":[0.6513317,0.000021355383,0.26603046,0.0020686553,0.00061732734,0.00047223046,0.0000016227629,0.001456586,0.078],"genre_scores_gemma":[0.78566945,0.000008052142,0.2122631,0.00062925555,0.000059227157,0.000050540068,0.000002003134,0.00001039359,0.0013079621],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985833,0.00004677421,0.00030658115,0.0004238838,0.00026263305,0.00037680593],"domain_scores_gemma":[0.99915177,0.00006977245,0.00006440043,0.0005236556,0.00007073985,0.000119692646],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005724623,0.00014965763,0.0001692337,0.00025989162,0.00007982632,0.00026699822,0.00086276745,0.00011088925,0.000370187],"category_scores_gemma":[0.000052435993,0.000133427,0.000058034606,0.00052046025,0.00004470861,0.00085060426,0.00029802893,0.0003636502,0.0003066041],"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":[0.0000054327,0.00016447612,0.033353347,0.000013249503,0.0000067036904,0.000040284616,0.0005015438,3.202399e-7,0.025317172,0.006215788,0.0034747657,0.9309069],"study_design_scores_gemma":[0.002276438,0.00017438518,0.09830268,0.00021932504,0.000010113681,0.00016124117,0.00016927306,0.0072516403,0.7354175,0.09736399,0.05703536,0.0016180483],"about_ca_topic_score_codex":0.00014680054,"about_ca_topic_score_gemma":0.0007218048,"teacher_disagreement_score":0.92928886,"about_ca_system_score_codex":0.000024262961,"about_ca_system_score_gemma":0.000033651766,"threshold_uncertainty_score":0.54409957},"labels":[],"label_agreement":null},{"id":"W2148667307","doi":"10.1109/icdar.1997.619872","title":"Piecewise linear modulation model of handwriting","year":2002,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Handwriting; Impulse response; Piecewise linear function; Computer science; Piecewise; Trajectory; Computation; Algorithm; Control theory (sociology); Mathematics; Artificial intelligence; Mathematical analysis","score_opus":0.04648492237161261,"score_gpt":0.25372452874065365,"score_spread":0.20723960636904104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148667307","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":[0.011740479,0.00002257232,0.9642991,0.00026666536,0.000019186775,0.00008780187,0.000001362085,0.0003925664,0.0231703],"genre_scores_gemma":[0.647714,0.000014215132,0.3515289,0.0001074949,0.000013849243,0.0000059152685,6.563658e-7,0.0000037874595,0.0006111371],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992679,0.000019209425,0.00022293188,0.00018196179,0.00017996815,0.00012805632],"domain_scores_gemma":[0.9994506,0.000030631712,0.000069196416,0.00027868326,0.00012782832,0.000043050044],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014087379,0.00007100341,0.00010386485,0.000107800224,0.00004306687,0.00002954709,0.00029302822,0.000047212176,0.000104710154],"category_scores_gemma":[0.00003315379,0.000067356676,0.000047349426,0.00020355618,0.000021263559,0.00048010077,0.000086852684,0.00005812118,0.000051771425],"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":[0.0000018151113,0.00021998893,0.00024978918,0.000040821356,0.000013584853,0.0000027624117,0.0007899623,0.0041047377,0.046743337,0.084177084,0.0026208675,0.8610352],"study_design_scores_gemma":[0.00010221332,0.000022662703,0.000024546205,0.000014481925,0.0000012896157,0.0000025034458,0.000003934846,0.90970534,0.08123763,0.008764227,0.000045279587,0.00007590235],"about_ca_topic_score_codex":0.000008185514,"about_ca_topic_score_gemma":0.000001397248,"teacher_disagreement_score":0.9056006,"about_ca_system_score_codex":0.000011898497,"about_ca_system_score_gemma":0.0000065683776,"threshold_uncertainty_score":0.27467254},"labels":[],"label_agreement":null},{"id":"W2149617283","doi":"10.1109/tip.2004.833101","title":"Iterative Multimodel Subimage Binarization for Handwritten Character Segmentation","year":2004,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Artificial intelligence; Computer science; Segmentation; Image segmentation; Pattern recognition (psychology); Character (mathematics); Computer vision; Image (mathematics); Image processing; Mathematics","score_opus":0.018880491509708767,"score_gpt":0.2821144217659209,"score_spread":0.2632339302562121,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2149617283","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":[0.0032935578,0.000022239365,0.99405736,0.000902108,0.00017557325,0.00072235556,0.00002888256,0.0006806658,0.00011725816],"genre_scores_gemma":[0.573695,0.000011366685,0.42532367,0.00041386785,0.00003491822,0.00039006525,0.00001342219,0.00002356908,0.00009410523],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985727,0.000039908078,0.00033440802,0.0005093731,0.00024853865,0.00029507253],"domain_scores_gemma":[0.99902534,0.00004062126,0.00015084387,0.00023538645,0.00046444015,0.00008338597],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019595903,0.00022880505,0.00017982959,0.00033465863,0.00055027223,0.0006876565,0.00029046493,0.000096744305,0.000012995027],"category_scores_gemma":[0.000010158574,0.0002307634,0.00010682987,0.00045301553,0.00006480428,0.0034709855,0.0000026391567,0.00019176265,0.000040082356],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058748847,0.0005018765,0.0000021157562,0.00016006215,0.000025609732,0.000007306813,0.004341022,0.0012748236,0.37364838,0.00016968916,0.000023158302,0.6197872],"study_design_scores_gemma":[0.0012851398,0.00018069256,0.000020824738,0.00020712258,0.00002354596,0.000018434182,0.00006990363,0.10906777,0.885268,0.003511936,0.000043569507,0.00030309302],"about_ca_topic_score_codex":0.000010360591,"about_ca_topic_score_gemma":0.000005797276,"teacher_disagreement_score":0.6194841,"about_ca_system_score_codex":0.00017164981,"about_ca_system_score_gemma":0.0001265702,"threshold_uncertainty_score":0.94102585},"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":"W2150437165","doi":"10.1109/icdar.2001.953892","title":"Baseline structure analysis of handwritten mathematics notation","year":2002,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Notation; Backtracking; Computer science; Parsing; Syntax; Executable; Semantics (computer science); Symbol (formal); Programming language; Artificial intelligence; Theoretical computer science; Mathematics; Arithmetic","score_opus":0.01853471796675723,"score_gpt":0.24466082510390563,"score_spread":0.2261261071371484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2150437165","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":[0.013249996,0.000029564866,0.98261666,0.00036235387,0.000024178858,0.00009088699,0.000014344795,0.000241666,0.003370328],"genre_scores_gemma":[0.61366624,0.000014714912,0.38573387,0.00017844039,0.000009950152,0.0000037209093,0.000010025174,0.0000037965979,0.00037926456],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990838,0.000037422426,0.00031420344,0.00019433591,0.0002541056,0.00011612767],"domain_scores_gemma":[0.99910134,0.00011309425,0.00012875265,0.0004211666,0.0001905042,0.000045122048],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000177823,0.00009150867,0.00023029133,0.000454289,0.000033280412,0.00005021961,0.0003769369,0.000057206835,0.001554908],"category_scores_gemma":[0.000068746405,0.00007571511,0.00011087099,0.00149882,0.00002423065,0.00026980846,0.000061167004,0.000058468195,0.000025015042],"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":[0.0000038008964,0.0008305875,0.0022177813,0.00016979886,0.0016802138,0.000018234039,0.0060958015,0.00040074397,0.047059216,0.12177813,0.0166143,0.8031314],"study_design_scores_gemma":[0.00012727587,0.000038759765,0.00065841904,0.000011247402,0.00017691101,0.0000040114646,0.000031303975,0.91660357,0.07576657,0.0061765197,0.00026252613,0.00014290883],"about_ca_topic_score_codex":0.000013686941,"about_ca_topic_score_gemma":0.000029630415,"teacher_disagreement_score":0.9162028,"about_ca_system_score_codex":0.000013205552,"about_ca_system_score_gemma":0.0000050433555,"threshold_uncertainty_score":0.9993578},"labels":[],"label_agreement":null},{"id":"W2151094955","doi":"10.1109/icdar.2001.953939","title":"Training with positive and negative data samples: effects on a classifier for hand-drawn geometric shapes","year":2002,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Classifier (UML); Correctness; Computer science; A priori and a posteriori; Artificial intelligence; Segmentation; Pattern recognition (psychology); Machine learning; Algorithm","score_opus":0.09886384641754678,"score_gpt":0.28820395773893487,"score_spread":0.1893401113213881,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151094955","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":[0.0062035904,0.00007717162,0.98667324,0.00073437113,0.000028149172,0.0007417984,0.000058822596,0.000284732,0.0051981197],"genre_scores_gemma":[0.7377218,0.000020332187,0.26049614,0.0012225336,0.000051955678,0.00010939223,0.00001535489,0.000014718889,0.00034778425],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986159,0.00006474568,0.00015011615,0.00065353734,0.00021955922,0.0002961208],"domain_scores_gemma":[0.9973842,0.0019130311,0.00007716288,0.00040151627,0.00011192132,0.000112183],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024393265,0.00018530176,0.00023352243,0.00036664912,0.000291561,0.00054859644,0.00059279724,0.00006608487,0.000038732956],"category_scores_gemma":[0.00029871485,0.00013574478,0.000027063912,0.0006895229,0.00013061157,0.0007804174,0.00020487607,0.00011796401,0.000014690842],"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":[0.000018222421,0.000058434445,0.000036446032,0.000028379432,0.000048597834,0.00001083882,0.0020018301,3.4613564e-7,0.00025876006,0.0037900615,0.0023136302,0.99143445],"study_design_scores_gemma":[0.012340035,0.018361332,0.019610086,0.0022251036,0.00027101216,0.00045102544,0.0017203828,0.44028157,0.4378946,0.033715088,0.029336765,0.0037929679],"about_ca_topic_score_codex":0.000029542904,"about_ca_topic_score_gemma":0.00003112788,"teacher_disagreement_score":0.9876415,"about_ca_system_score_codex":0.000026970132,"about_ca_system_score_gemma":0.00002909985,"threshold_uncertainty_score":0.55355114},"labels":[],"label_agreement":null},{"id":"W2151666999","doi":"10.1142/s0218001410007816","title":"STATISTICAL CHARACTERISTICS OF SLANT ANGLES IN HANDWRITTEN NUMERAL STRINGS AND EFFECTS OF SLANT CORRECTION ON SEGMENTATION","year":2010,"lang":"en","type":"article","venue":"International Journal of Pattern Recognition and Artificial Intelligence","topic":"Handwritten Text Recognition Techniques","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":"Concordia University; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Numeral system; Segmentation; Pattern recognition (psychology); Artificial intelligence; Computer science; String (physics); Connected component; Image segmentation; Mathematics","score_opus":0.0224923108163034,"score_gpt":0.28861760511434426,"score_spread":0.2661252942980409,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151666999","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":[0.6314629,0.000008172841,0.36744758,0.00014404608,0.0007946821,0.00008500051,0.0000316181,0.000007942227,0.000018096414],"genre_scores_gemma":[0.9936565,0.00019012399,0.0058935946,0.00011940697,0.00011024281,0.000005038106,0.000016528915,0.0000057931084,0.0000027505896],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985817,0.0000784689,0.00072973344,0.0001622365,0.00034644397,0.0001014292],"domain_scores_gemma":[0.9984598,0.0004129559,0.0005369736,0.000066046625,0.0004595378,0.00006464067],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000375654,0.00011070809,0.000219949,0.00040153798,0.000023908482,0.00008149575,0.00020538304,0.00006783097,0.00004400971],"category_scores_gemma":[0.00026661265,0.000102304766,0.000043076376,0.000098230696,0.00010037489,0.00032257414,0.000051082792,0.00026879064,0.000004156738],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000080933285,0.00019563563,0.0039653126,0.000034154582,0.000023276381,0.000042223495,0.00052716443,8.90756e-7,0.060171057,0.0005802687,0.000013888744,0.9343652],"study_design_scores_gemma":[0.00027666724,0.0008199534,0.045873042,0.0008130831,0.00002051558,0.0002439989,0.00018841149,0.0070391083,0.9231462,0.021368902,0.000020323654,0.00018979481],"about_ca_topic_score_codex":0.00006994271,"about_ca_topic_score_gemma":0.00004857202,"teacher_disagreement_score":0.9341754,"about_ca_system_score_codex":0.000020647585,"about_ca_system_score_gemma":0.000030156834,"threshold_uncertainty_score":0.41718674},"labels":[],"label_agreement":null},{"id":"W2152233159","doi":"10.1109/icdar.1993.395772","title":"Document architecture language (DAL) approach to document processing","year":2002,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"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","keywords":"Computer science; Architecture; Newspaper; Document processing; Process (computing); Natural language processing; Historical document; Information retrieval; Artificial intelligence; World Wide Web; Programming language","score_opus":0.013442304732480995,"score_gpt":0.2491626721435957,"score_spread":0.23572036741111468,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2152233159","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":[0.0015434686,0.0001641923,0.8771186,0.0018235847,0.00004051029,0.000409011,6.184464e-7,0.0009974183,0.11790259],"genre_scores_gemma":[0.37898654,0.000006637696,0.61319256,0.002334838,0.000062124294,0.00013874964,0.0000019537188,0.000012540004,0.00526404],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99847716,0.00005265724,0.00022527098,0.00049800565,0.00038822135,0.0003586861],"domain_scores_gemma":[0.99918354,0.000020587267,0.000050346425,0.00049684884,0.00006202974,0.00018664787],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021695922,0.00018047588,0.00015773304,0.00019919193,0.00010928531,0.00045999073,0.00080469,0.000057010624,0.00024663165],"category_scores_gemma":[0.000022227601,0.00014390219,0.0000600527,0.0004928656,0.00002094289,0.00043138475,0.0002951007,0.00015622172,0.00033358816],"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":[0.0000011943627,0.00009980224,0.000007321318,0.00003124599,0.0000069011,0.000009629099,0.004391245,0.00001589205,0.0010009623,0.0054851994,0.009007426,0.97994316],"study_design_scores_gemma":[0.0031286464,0.001553177,0.0006029507,0.0006329064,0.00006701343,0.0010142413,0.0022801647,0.083718814,0.5696296,0.069378994,0.2626617,0.0053318185],"about_ca_topic_score_codex":0.000029651508,"about_ca_topic_score_gemma":0.000004355306,"teacher_disagreement_score":0.97461134,"about_ca_system_score_codex":0.00006972536,"about_ca_system_score_gemma":0.000013100097,"threshold_uncertainty_score":0.5868161},"labels":[],"label_agreement":null},{"id":"W2152235937","doi":"10.1109/icme.2006.262882","title":"Multiscale Edge-Based Text Extraction from Complex Images","year":2006,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":140,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Artificial intelligence; Text detection; Segmentation; Feature extraction; Computer vision; Font; Edge detection; Pattern recognition (psychology); Enhanced Data Rates for GSM Evolution; Image segmentation; Identification (biology); Orientation (vector space); Text segmentation; Mobile robot; Image (mathematics); Robot; Image processing","score_opus":0.01943581435024508,"score_gpt":0.26742213632777684,"score_spread":0.24798632197753176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2152235937","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":[0.006065535,0.000030283249,0.9615855,0.0010259303,0.000116797324,0.00016345912,0.000015501146,0.001385968,0.029610986],"genre_scores_gemma":[0.5834856,0.0000016780238,0.41498756,0.00041867708,0.00009642352,0.000024932497,0.00004229137,0.00000815365,0.00093469006],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988875,0.00006140611,0.00023724417,0.00037711734,0.00022487869,0.0002118678],"domain_scores_gemma":[0.99918145,0.00015829268,0.00007885679,0.00041906766,0.00010495274,0.000057409998],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000112077054,0.00013738351,0.00013513752,0.00011714011,0.000110093795,0.00022790974,0.0004371907,0.000072544,0.000814819],"category_scores_gemma":[0.000014024283,0.0001273125,0.00007539511,0.000210245,0.000051426025,0.0005550194,0.00007060699,0.000106172265,0.00057599024],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009218061,0.0005200347,0.002256372,0.000010539611,0.000011161253,0.000035587655,0.000032659547,0.00003163465,0.32757503,0.005203643,0.18017876,0.4841354],"study_design_scores_gemma":[0.0005738075,0.00005222134,0.06453684,0.000020167972,0.000006303052,0.000007702738,0.000008397991,0.052769396,0.841163,0.015476559,0.025030931,0.00035470107],"about_ca_topic_score_codex":0.0016203306,"about_ca_topic_score_gemma":0.00013015527,"teacher_disagreement_score":0.57742006,"about_ca_system_score_codex":0.000042786214,"about_ca_system_score_gemma":0.000027919743,"threshold_uncertainty_score":0.89216965},"labels":[],"label_agreement":null},{"id":"W2152260845","doi":"10.1142/s0219467805001756","title":"NATURAL SKELETONIZATION: NEW APPROACH FOR THE SKELETONIZATION OF HANDWRITTEN CHARACTERS","year":2005,"lang":"en","type":"article","venue":"International Journal of Image and Graphics","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Skeletonization; Artificial intelligence; Pixel; Computer science; Pattern recognition (psychology); Computer vision; Binary image; Aerenchyma; Medial axis; Image processing; Image (mathematics); Botany","score_opus":0.01214410654730863,"score_gpt":0.2683526044565506,"score_spread":0.256208497909242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2152260845","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":[0.0030017705,0.00051844836,0.9876826,0.008260791,0.00026880612,0.00012974878,0.0000048829343,0.000019503259,0.0001134719],"genre_scores_gemma":[0.6886718,0.0012525951,0.3076361,0.0013981177,0.0007897292,0.000005723763,0.000016507825,0.000011767511,0.00021760685],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989517,0.000029872133,0.00041187392,0.0001214898,0.00038861355,0.00009647369],"domain_scores_gemma":[0.9979789,0.00017403264,0.00042947056,0.00012581305,0.0012381007,0.00005364652],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043155352,0.00009351287,0.00013864487,0.0002612355,0.00006607213,0.00018631539,0.0007471734,0.000046943016,0.000007853931],"category_scores_gemma":[0.00015742866,0.000066722,0.00012501849,0.00021821691,0.00007684281,0.0010153163,0.00007149639,0.00015538528,7.594347e-7],"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":[0.00013179428,0.00027344085,0.0011502566,0.000046215962,0.0005490972,0.00001103805,0.0017429172,0.00008509537,0.014145619,0.077651225,0.013614666,0.89059865],"study_design_scores_gemma":[0.012746079,0.001204587,0.04616256,0.00071428454,0.0004555,0.0035524867,0.00063804217,0.44991836,0.2623137,0.07643661,0.14415264,0.0017051524],"about_ca_topic_score_codex":0.000006854605,"about_ca_topic_score_gemma":0.0000024803994,"teacher_disagreement_score":0.8888935,"about_ca_system_score_codex":0.000021364469,"about_ca_system_score_gemma":0.00008685341,"threshold_uncertainty_score":0.27208441},"labels":[],"label_agreement":null},{"id":"W2152502945","doi":"10.1109/ccece.2003.1226292","title":"Analysis of manuscript characters by the moments of wavelet packets","year":2004,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Wavelet; Pattern recognition (psychology); Word error rate; Artificial intelligence; Computer science; Support vector machine; Feature extraction; Wavelet packet decomposition; Principal component analysis; Network packet; Wavelet transform; Speech recognition; Mathematics; Computer security","score_opus":0.015342076771700562,"score_gpt":0.24417840541321614,"score_spread":0.22883632864151557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2152502945","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":[0.28122967,0.000034077162,0.7066179,0.004109672,0.00007190873,0.00025518637,0.000032778025,0.00017248189,0.007476358],"genre_scores_gemma":[0.9928948,0.000033494078,0.0058748275,0.0007461027,0.0000036028107,0.000011317922,0.000011166138,0.0000034328561,0.00042125548],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99911666,0.000035112338,0.00027184468,0.00017518854,0.0002708453,0.00013036617],"domain_scores_gemma":[0.99921674,0.000031204734,0.00015302384,0.00046419437,0.000098688026,0.00003614884],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023351995,0.00007950256,0.00020346633,0.00021773508,0.000027647135,0.00002469257,0.00064136845,0.000034310546,0.000059410755],"category_scores_gemma":[0.000010167324,0.00005287259,0.00013106992,0.0009279448,0.000061172024,0.00021571796,0.0001088575,0.000052339514,0.000009170533],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022839675,0.0013935127,0.0034330818,0.00008088059,0.0035550357,0.000013843541,0.004356023,0.000029485289,0.1251291,0.09054091,0.021267688,0.7501776],"study_design_scores_gemma":[0.00031727366,0.00012378568,0.011016388,0.000022753029,0.000162209,0.0000028937554,0.00006783878,0.0012236305,0.97666407,0.009025828,0.0012028294,0.00017047947],"about_ca_topic_score_codex":0.00008151756,"about_ca_topic_score_gemma":0.000008120191,"teacher_disagreement_score":0.85153496,"about_ca_system_score_codex":0.00002449136,"about_ca_system_score_gemma":0.000018309678,"threshold_uncertainty_score":0.21560818},"labels":[],"label_agreement":null},{"id":"W2153113544","doi":"10.1007/978-3-642-54423-1_45","title":"Semantic Word Cloud Representations: Hardness and Approximation Algorithms","year":2014,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Handwritten Text Recognition 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":"University of Waterloo","funders":"","keywords":"Computer science; Adjacency list; Combinatorics; Bounded function; Vertex (graph theory); Theoretical computer science; Discrete mathematics; Algorithm; Graph; Mathematics","score_opus":0.019508694708693222,"score_gpt":0.2656033699389722,"score_spread":0.246094675230279,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2153113544","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":[0.000049513816,0.00024801109,0.9944858,0.0008952843,0.0014980416,0.00058840617,0.0000036051133,0.00043182974,0.0017995121],"genre_scores_gemma":[0.037836462,0.00015030548,0.9590201,0.0013190582,0.0007350573,0.00005245453,0.00001645748,0.000045365818,0.00082475354],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964787,0.000069317466,0.0005670677,0.0015615762,0.000851463,0.0004718868],"domain_scores_gemma":[0.9975762,0.00035982204,0.00033781317,0.0012297387,0.00033225835,0.00016418847],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011609781,0.00044757794,0.0004963838,0.00094071124,0.000283098,0.0008836118,0.0018282416,0.00030890058,0.000017396318],"category_scores_gemma":[0.00015743764,0.00043075377,0.00008969916,0.0005649436,0.0006553494,0.00069462374,0.0010546212,0.000601701,0.00004597063],"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":[0.0000016451439,0.000012916504,0.000021067888,0.000058905236,0.0000067869296,0.00002070031,0.00041969123,0.00016648357,0.000064326516,0.01799416,0.00007236674,0.98116094],"study_design_scores_gemma":[0.00025963597,0.0001106774,0.00014667887,0.0006179111,0.000012412228,0.0001687551,3.198657e-7,0.5322589,0.0040533356,0.46013728,0.0015160757,0.0007179762],"about_ca_topic_score_codex":0.00002383257,"about_ca_topic_score_gemma":0.000023123175,"teacher_disagreement_score":0.980443,"about_ca_system_score_codex":0.00014268911,"about_ca_system_score_gemma":0.00019958132,"threshold_uncertainty_score":0.99981445},"labels":[],"label_agreement":null},{"id":"W2154127072","doi":"10.1109/cvprw.2003.10020","title":"Information Retrieval Based on OCR Errors in Scanned Documents","year":2003,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; École de Technologie Supérieure; Concordia University","funders":"","keywords":"Computer science; Optical character recognition; Information retrieval; Relevance (law); Lexicon; n-gram; Artificial intelligence; Document retrieval; Matching (statistics); Process (computing); Error detection and correction; Character (mathematics); Pattern recognition (psychology); Natural language processing; Image (mathematics); Language model; Algorithm","score_opus":0.01046746240552175,"score_gpt":0.25122585619480886,"score_spread":0.24075839378928712,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154127072","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":[0.027094413,0.0000028179059,0.7898042,0.0007863291,0.00018820202,0.00040529683,0.0000015358929,0.0005622102,0.18115495],"genre_scores_gemma":[0.94267774,0.0000021396597,0.054506093,0.0025575333,0.0000038129274,0.000013325303,0.00000530285,0.0000034552672,0.00023059532],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990678,0.000083468796,0.00024227107,0.00012444008,0.00029212952,0.00018989852],"domain_scores_gemma":[0.9994843,0.00004381367,0.000059434828,0.0002906421,0.00006388185,0.00005791546],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045801062,0.00009222543,0.00008791523,0.00034944393,0.000039711478,0.0001262276,0.0002869937,0.000059705464,0.00018243903],"category_scores_gemma":[0.00015570207,0.000084143896,0.0000311187,0.0006039558,0.000013608745,0.0013286128,0.000026983296,0.000100915524,0.00029991017],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028935462,0.0013333453,0.015645627,0.00015049346,0.00003438574,0.000061945066,0.0031468703,0.0009887698,0.0020303708,0.47202694,0.047355313,0.45693657],"study_design_scores_gemma":[0.0049746856,0.0011548763,0.009556348,0.0002544807,0.000005984499,0.000020268753,0.00021257109,0.17236175,0.7092602,0.044249326,0.0566926,0.0012568653],"about_ca_topic_score_codex":0.000022104705,"about_ca_topic_score_gemma":0.0000068029535,"teacher_disagreement_score":0.9155833,"about_ca_system_score_codex":0.00008825474,"about_ca_system_score_gemma":0.000068914575,"threshold_uncertainty_score":0.38548383},"labels":[],"label_agreement":null},{"id":"W2155440966","doi":"10.1109/icpr.1992.201940","title":"Binary character/graphics image extraction: a new technique and six evaluation aspects","year":2003,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Grayscale; Character (mathematics); Computer science; Graphics; Artificial intelligence; Font; Binary number; Image (mathematics); Computer graphics; Quality (philosophy); Computer vision; Information retrieval; Pattern recognition (psychology); Computer graphics (images); Mathematics; Arithmetic","score_opus":0.02599451987807253,"score_gpt":0.29936601260310003,"score_spread":0.2733714927250275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155440966","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":[0.0035397212,0.00015377393,0.9607831,0.0011361352,0.00013222176,0.0008126645,7.863142e-7,0.0008617134,0.03257985],"genre_scores_gemma":[0.5144689,0.00017467121,0.4835463,0.00077162276,0.00007418331,0.00023290371,0.000006132596,0.000019238772,0.00070607936],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985344,0.00019000482,0.00023883054,0.0004425409,0.00037758896,0.00021662969],"domain_scores_gemma":[0.99899733,0.00008508002,0.00010443991,0.00043351462,0.00023204238,0.0001475872],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010338682,0.00016492952,0.00014258591,0.0002908704,0.00012447301,0.0002465241,0.00024606942,0.00012581798,0.00035309346],"category_scores_gemma":[0.00015242258,0.00015762715,0.000051869156,0.0005577743,0.000045892262,0.0013776757,0.0000686891,0.00020496165,0.0000578493],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008729111,0.00026613811,0.0002789652,0.00004227171,0.00003280609,0.00006322291,0.00030035878,2.1100557e-7,0.33635765,0.40166417,0.010504266,0.25048122],"study_design_scores_gemma":[0.0008118257,0.00043607844,0.005378753,0.00009768555,0.000037095757,0.00095089216,0.00003614941,0.0073142587,0.7141738,0.24384573,0.026170868,0.00074687443],"about_ca_topic_score_codex":0.000030935385,"about_ca_topic_score_gemma":0.000011908329,"teacher_disagreement_score":0.51092917,"about_ca_system_score_codex":0.000051137602,"about_ca_system_score_gemma":0.00019742758,"threshold_uncertainty_score":0.64278483},"labels":[],"label_agreement":null},{"id":"W2155559525","doi":"10.1109/icdar.2001.953782","title":"Segmenting document images using diagonal white runs and vertical edges","year":2002,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Diagonal; Graphics; Computer science; Pixel; Artificial intelligence; White (mutation); Image segmentation; Set (abstract data type); Enhanced Data Rates for GSM Evolution; Computer graphics (images); Image (mathematics); Computer vision; Pattern recognition (psychology); Mathematics; Geometry","score_opus":0.026993164290077972,"score_gpt":0.2560192635743032,"score_spread":0.22902609928422524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155559525","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":[0.059930366,0.00018705161,0.928133,0.0012061588,0.00007952658,0.00012085769,6.7402874e-7,0.00043926644,0.009903105],"genre_scores_gemma":[0.70460856,0.00006733545,0.2939824,0.00052819325,0.00005651228,0.000010298748,5.3235266e-7,0.000007991483,0.00073817617],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99904346,0.000040633808,0.0001752211,0.0002916831,0.00019642175,0.0002525734],"domain_scores_gemma":[0.99957573,0.000057954738,0.000022455204,0.00019377987,0.000048852577,0.00010122632],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016730808,0.000109420886,0.000110145345,0.00008604118,0.00012849727,0.00033310117,0.00022307063,0.000039865816,0.00050711475],"category_scores_gemma":[0.00002618284,0.00009668924,0.000034349363,0.00014174728,0.000057072422,0.00065968506,0.0002870153,0.00008628645,0.00005031439],"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":[0.0000034713253,0.00027167914,0.016445057,0.00006647097,0.0000654407,0.00009356704,0.001391701,0.0000048990555,0.03789657,0.025579749,0.0152843995,0.902897],"study_design_scores_gemma":[0.00120984,0.00029006542,0.012012851,0.0002264317,0.000051786545,0.0004382289,0.00013970972,0.20121655,0.75850415,0.020370308,0.004198114,0.0013419939],"about_ca_topic_score_codex":0.0000109585035,"about_ca_topic_score_gemma":0.0000016463991,"teacher_disagreement_score":0.901555,"about_ca_system_score_codex":0.00002789351,"about_ca_system_score_gemma":0.00000725854,"threshold_uncertainty_score":0.55525506},"labels":[],"label_agreement":null},{"id":"W2157057015","doi":"10.1109/icpr.2010.468","title":"Holistic Urdu Handwritten Word Recognition Using Support Vector Machine","year":2010,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":55,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Urdu; Cursive; Computer science; Artificial intelligence; Support vector machine; Word (group theory); Natural language processing; Arabic; Speech recognition; Feature (linguistics); Compound; Arabic script; Pattern recognition (psychology); Feature extraction; Word recognition; Reading (process); Mathematics; Linguistics","score_opus":0.04250751311295106,"score_gpt":0.2913897140188765,"score_spread":0.24888220090592542,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2157057015","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":[0.10014606,0.000013354702,0.8832817,0.0006938012,0.0009764378,0.00036882504,0.000026985907,0.0016486363,0.012844195],"genre_scores_gemma":[0.6620639,0.0000080061445,0.33631802,0.00079340127,0.0002014545,0.00003144297,0.00003778842,0.000023341347,0.0005226538],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983521,0.000059361482,0.00035503253,0.00051096344,0.00031892207,0.00040361407],"domain_scores_gemma":[0.9987435,0.00009687495,0.00011785084,0.0006084275,0.00023008036,0.00020327287],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004594531,0.00022230545,0.00022530067,0.000257713,0.00018049865,0.0003322539,0.00070035656,0.00015976248,0.0017570187],"category_scores_gemma":[0.00014556688,0.00020578093,0.00010279252,0.00045853114,0.000078080186,0.00085365534,0.00022685977,0.00042756155,0.00062315667],"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":[0.000013639372,0.00022842531,0.00063973566,0.000034778477,0.000030919164,0.00008616976,0.0002183773,4.937268e-7,0.092625864,0.0046484903,0.0041802065,0.8972929],"study_design_scores_gemma":[0.0030008142,0.00074890954,0.010203357,0.00020440538,0.0001507281,0.0023035603,0.00008280776,0.13831587,0.67782074,0.124849156,0.038791202,0.0035284637],"about_ca_topic_score_codex":0.00017554376,"about_ca_topic_score_gemma":0.00012726862,"teacher_disagreement_score":0.89376444,"about_ca_system_score_codex":0.00003605351,"about_ca_system_score_gemma":0.000098823555,"threshold_uncertainty_score":0.9991555},"labels":[],"label_agreement":null},{"id":"W2157769407","doi":"10.1145/2501115.2501123","title":"Generation of learning samples for historical handwriting recognition using image degradation","year":2013,"lang":"en","type":"preprint","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; Agence Nationale de la Recherche","keywords":"Handwriting; Computer science; Artificial intelligence; Character (mathematics); Hidden Markov model; Handwriting recognition; Pattern recognition (psychology); Inkwell; Intelligent character recognition; Image (mathematics); Speech recognition; Character recognition; Computer vision; Feature extraction; Mathematics","score_opus":0.16465553690069076,"score_gpt":0.3151988945103646,"score_spread":0.15054335760967383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2157769407","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":[0.0466933,0.00010470918,0.9509486,0.00016567436,0.00037966992,0.0008614184,0.0000145060585,0.00048405037,0.0003480528],"genre_scores_gemma":[0.076288395,0.000062802064,0.9224544,0.00003851022,0.00032537946,0.00026441825,0.00035995117,0.000029134833,0.00017701837],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978912,0.00017985729,0.00074195006,0.0006387927,0.00029943,0.00024877183],"domain_scores_gemma":[0.99761736,0.00021232812,0.0006916963,0.00035754734,0.0010537226,0.00006732043],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007100608,0.0002547818,0.00040277897,0.00037661518,0.00020779438,0.00033831078,0.00042841767,0.0003256668,0.000052877574],"category_scores_gemma":[0.00047852565,0.00027174948,0.00020507294,0.00016739061,0.00003056195,0.000751135,0.00041205646,0.0003621526,0.0000089320465],"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":[0.0000074703635,0.00012916853,0.00014763059,0.00060773664,0.000056410197,0.0000011665895,0.00034188526,0.00021314912,0.22418764,0.0026586342,0.0030616825,0.7685874],"study_design_scores_gemma":[0.00024495163,0.00010865816,0.000028243358,0.0002911799,0.0000447867,0.000009894773,0.000035650788,0.6442123,0.3320007,0.022116376,0.0004471282,0.00046009535],"about_ca_topic_score_codex":0.0006431166,"about_ca_topic_score_gemma":0.000018012353,"teacher_disagreement_score":0.7681273,"about_ca_system_score_codex":0.0004963207,"about_ca_system_score_gemma":0.00015737193,"threshold_uncertainty_score":0.9999735},"labels":[],"label_agreement":null},{"id":"W2157982465","doi":"10.1109/ism.2008.115","title":"On-line Signature Verification Using Most Discriminating Features and Fisher Linear Discriminant Analysis (FLD)","year":2008,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Signature (topology); Linear discriminant analysis; Trajectory; Pattern recognition (psychology); Discriminant; Computer science; Feature (linguistics); Line (geometry); Artificial intelligence; Algorithm; Feature extraction; Mathematics; Data mining; Geometry; Physics","score_opus":0.04236780205218008,"score_gpt":0.2923647655178345,"score_spread":0.24999696346565445,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2157982465","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":[0.126055,0.00008425567,0.8708993,0.0006534134,0.000061182676,0.00017237844,0.000006953739,0.0003384141,0.0017290976],"genre_scores_gemma":[0.82847375,0.00004751398,0.17035744,0.0005059946,0.00004573489,0.000011207045,0.000024596382,0.000011383732,0.0005223527],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99860954,0.000076255805,0.00025256546,0.0005220108,0.00030489286,0.00023470412],"domain_scores_gemma":[0.9990542,0.00011794458,0.000115152914,0.00046809562,0.00014670011,0.000097929566],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019200804,0.00019538257,0.00024443073,0.00035020878,0.00032420634,0.00011908342,0.00035591994,0.00012081756,0.000037965307],"category_scores_gemma":[0.00011255195,0.00015248713,0.000090278714,0.0010341889,0.00008242375,0.0005114584,0.00014323936,0.00023198719,0.0000055570526],"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":[0.00019324965,0.0026859904,0.015484249,0.00038558192,0.0016764716,0.0007481656,0.021308333,0.0067316997,0.14575945,0.14881629,0.035066433,0.6211441],"study_design_scores_gemma":[0.00054321456,0.0003557443,0.031378973,0.000103280065,0.00033701462,0.00020879334,0.00027299856,0.8253115,0.13489828,0.005320492,0.00029858117,0.0009711304],"about_ca_topic_score_codex":0.00015622984,"about_ca_topic_score_gemma":0.000038944374,"teacher_disagreement_score":0.8185798,"about_ca_system_score_codex":0.000037941216,"about_ca_system_score_gemma":0.00003232105,"threshold_uncertainty_score":0.6218245},"labels":[],"label_agreement":null},{"id":"W2159772502","doi":"10.1109/icdar.2009.5","title":"A Multi-Hypothesis Approach for Off-Line Signature Verification with HMMs","year":2009,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"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; Computer science; Signature (topology); Artificial intelligence; Pattern recognition (psychology); Set (abstract data type); Line (geometry); Training set; Construct (python library); Machine learning; Mathematics","score_opus":0.03449403091647901,"score_gpt":0.2583579288671386,"score_spread":0.22386389795065958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159772502","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":[0.00037794327,0.00008104327,0.9952101,0.00060207886,0.000013375342,0.000588587,0.0000035868245,0.00071439263,0.0024088998],"genre_scores_gemma":[0.22006439,0.000012177405,0.7780385,0.0008665774,0.000029479157,0.00009692658,0.000011418213,0.0000068920726,0.0008736188],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991126,0.000024529018,0.00014814782,0.0003744581,0.00015458488,0.00018565691],"domain_scores_gemma":[0.99925154,0.000052845895,0.00006712236,0.00040483708,0.00016300085,0.000060657243],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017692888,0.00012699634,0.00013506952,0.00009850935,0.000074782816,0.00010389978,0.00046349867,0.000094517,0.0000107924425],"category_scores_gemma":[0.000035796256,0.00009272199,0.000050481376,0.00028898218,0.000020199426,0.0003494899,0.000018105298,0.00008771487,0.000009609276],"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":[0.00003246318,0.00047887093,0.00001540072,0.000018212642,0.000016398644,0.0000016071737,0.00020731855,0.00002968081,0.024344433,0.0056169094,0.0033375833,0.96590114],"study_design_scores_gemma":[0.0019323603,0.0014065459,0.0033731842,0.0000456948,0.000029882756,0.000042322594,0.00006611458,0.41141424,0.56696874,0.006310279,0.007606929,0.0008037024],"about_ca_topic_score_codex":0.00000257789,"about_ca_topic_score_gemma":0.0000016713358,"teacher_disagreement_score":0.9650974,"about_ca_system_score_codex":0.00002277491,"about_ca_system_score_gemma":0.000031199943,"threshold_uncertainty_score":0.3781093},"labels":[],"label_agreement":null},{"id":"W2160689653","doi":"10.1109/icdar.1997.620589","title":"Shape matrices as a mixed shape factor for off-line signature verification","year":2002,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Shape factor; Signature (topology); Shape analysis (program analysis); Similarity (geometry); Representation (politics); Measure (data warehouse); Heat kernel signature; Active shape model; Factor (programming language); Interpretation (philosophy); Mathematics; Line (geometry); Position (finance); Pattern recognition (psychology); Artificial intelligence; Planar; Computer science; Geometry; Data mining; Image (mathematics); Segmentation","score_opus":0.035971923841923124,"score_gpt":0.2736312178851078,"score_spread":0.23765929404318467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160689653","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":[0.031984504,0.0015068522,0.94873,0.004442894,0.00037469377,0.0013649848,0.000060053913,0.0026360843,0.008899916],"genre_scores_gemma":[0.79224044,0.0003284335,0.2025798,0.0014043344,0.00014620447,0.00019325249,0.000020105837,0.000022737817,0.0030646613],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99873805,0.00003655953,0.00026729124,0.00045000445,0.00024951523,0.00025857435],"domain_scores_gemma":[0.9989958,0.00015772006,0.00011725947,0.00040554663,0.00022486593,0.000098850614],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000137165,0.00016828818,0.00016703413,0.00016998668,0.000113141235,0.0002168844,0.00074124295,0.00016022238,0.0025018745],"category_scores_gemma":[0.000101421436,0.00014551441,0.00010462835,0.00040406315,0.000023439938,0.0006486122,0.00008482097,0.00012636682,0.00048535937],"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":[0.0000052287633,0.00010403347,0.000010851226,0.000023554328,0.000012603874,0.000002399586,0.00019152377,4.400949e-7,0.0077221044,0.0058844113,0.013182458,0.9728604],"study_design_scores_gemma":[0.0007507911,0.0005771001,0.00073787494,0.00004742964,0.000017552618,0.000028282919,0.00003599313,0.68149394,0.2030224,0.007984154,0.10466399,0.0006404511],"about_ca_topic_score_codex":0.000005410447,"about_ca_topic_score_gemma":0.0000038088858,"teacher_disagreement_score":0.97221994,"about_ca_system_score_codex":0.00003229378,"about_ca_system_score_gemma":0.000018765231,"threshold_uncertainty_score":0.99841},"labels":[],"label_agreement":null},{"id":"W2161141535","doi":"10.1109/icpr.2008.4761057","title":"On-line signature verification by using most discriminating points","year":2008,"lang":"en","type":"article","venue":"Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Feature (linguistics); Signature (topology); Computer science; Line (geometry); Pattern recognition (psychology); Set (abstract data type); Trajectory; Artificial intelligence; Feature extraction; Basis (linear algebra); Mathematics; Geometry","score_opus":0.10836411191923412,"score_gpt":0.3141470014458735,"score_spread":0.20578288952663937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2161141535","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":[0.6207176,0.00002903452,0.18399565,0.015109388,0.004495852,0.0030338035,0.003549273,0.0026841718,0.16638525],"genre_scores_gemma":[0.9831192,0.00062854687,0.0048578833,0.0061309002,0.001006564,0.00075692637,0.002757539,0.00018959759,0.00055282953],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99028116,0.00007978629,0.0019695181,0.003039812,0.003380806,0.00124892],"domain_scores_gemma":[0.9893314,0.00023855947,0.0020012653,0.00041504687,0.0074019083,0.0006117877],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["metaepi_narrow","insufficient_payload"],"category_scores_codex":[0.0009493182,0.0015330509,0.0009389252,0.0019591292,0.00093797373,0.0021456736,0.0032512585,0.00078141975,0.0035083976],"category_scores_gemma":[0.0007625836,0.001642638,0.00045008166,0.00094156386,0.0003698375,0.004193939,0.0005230435,0.0020541844,0.0017090536],"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":[0.0010939818,0.0047590574,0.004321535,0.0003781827,0.0010628079,0.00015079149,0.0030796935,0.000012358477,0.07268926,0.042321954,0.021953946,0.8481764],"study_design_scores_gemma":[0.012020549,0.005706608,0.00308657,0.011385664,0.00036150488,0.0017186289,0.0036694796,0.39699617,0.4207565,0.13316116,0.0019539364,0.009183262],"about_ca_topic_score_codex":0.00014375462,"about_ca_topic_score_gemma":0.0000148025965,"teacher_disagreement_score":0.8389932,"about_ca_system_score_codex":0.0010572784,"about_ca_system_score_gemma":0.00025811457,"threshold_uncertainty_score":0.9997418},"labels":[],"label_agreement":null},{"id":"W2165015303","doi":"10.1109/icip.1994.413292","title":"A morphological approach to text string extraction from regular periodic overlapping text/background images","year":2002,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"String (physics); Character (mathematics); Computer science; Artificial intelligence; Image (mathematics); Distortion (music); String searching algorithm; Pattern recognition (psychology); Natural language processing; Computer vision; Mathematics; Geometry; Pattern matching","score_opus":0.04591469961088389,"score_gpt":0.26516930247289133,"score_spread":0.21925460286200743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2165015303","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":[0.09310405,0.00015002176,0.869254,0.0005972827,0.00010307173,0.000346081,0.0000058875166,0.0011904283,0.035249215],"genre_scores_gemma":[0.6650713,0.00003312041,0.33272094,0.0005688878,0.0001106776,0.00007694305,0.000006693375,0.00001402135,0.0013973954],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9977771,0.00011671956,0.00036812952,0.00087277294,0.0004308669,0.00043438183],"domain_scores_gemma":[0.9987637,0.00011966512,0.00010045713,0.00071012066,0.000097280536,0.00020877125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028817306,0.00025543166,0.0002801926,0.00022899837,0.00023700885,0.00069833884,0.00082311773,0.00016639946,0.00090126036],"category_scores_gemma":[0.000060551585,0.000230119,0.000120437224,0.0005669965,0.00006435761,0.0011340524,0.00034387343,0.0002961511,0.00075741176],"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":[0.000018268765,0.0010976562,0.00048794548,0.000035425783,0.0000791171,0.00020689909,0.0014399785,0.000059633898,0.21974921,0.01757113,0.04140262,0.7178521],"study_design_scores_gemma":[0.0042478894,0.0017179672,0.063619584,0.00059466274,0.00014334658,0.0025625594,0.0037934675,0.30490184,0.4690722,0.039409924,0.103021145,0.006915436],"about_ca_topic_score_codex":0.00015256769,"about_ca_topic_score_gemma":0.0000028598397,"teacher_disagreement_score":0.71093667,"about_ca_system_score_codex":0.00012351401,"about_ca_system_score_gemma":0.000013736494,"threshold_uncertainty_score":0.9868169},"labels":[],"label_agreement":null},{"id":"W2166309735","doi":"10.1109/iwfhr.2004.34","title":"Distinguishing Text from Graphics in On-Line Handwritten Ink","year":2004,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":64,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Microsoft Research; Microsoft","keywords":"Inkwell; Computer science; Graphics; Computer graphics (images); Line (geometry); Artificial intelligence; Handwriting recognition; Speech recognition; Feature extraction","score_opus":0.028504508277850518,"score_gpt":0.27317968748802746,"score_spread":0.24467517921017695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2166309735","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":[0.07899171,0.00004974693,0.89964944,0.003871791,0.00018435925,0.00022503777,0.00000784049,0.0010319129,0.015988152],"genre_scores_gemma":[0.85895556,0.000024438375,0.13826911,0.0025431525,0.00007392743,0.000025209492,0.000011659474,0.000012528507,0.000084400555],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99855393,0.000045533518,0.00032512879,0.00047927187,0.00029924134,0.0002968712],"domain_scores_gemma":[0.9990801,0.00016788607,0.00007034284,0.0005046809,0.00007737339,0.000099602905],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030421306,0.00017109618,0.00019928183,0.00027959666,0.00008379754,0.00024327051,0.00081181433,0.000110220964,0.000045790643],"category_scores_gemma":[0.00022248777,0.00015426645,0.0000655742,0.00066334807,0.00004716932,0.00042763178,0.00021290236,0.00031917266,0.00014397877],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025852794,0.00093197066,0.0057888837,0.000024132729,0.000038953152,0.00042472698,0.0024232746,0.00025749308,0.0019589048,0.64010864,0.0020502845,0.3459669],"study_design_scores_gemma":[0.0024609282,0.0004724219,0.012199798,0.00058680534,0.000007748428,0.000021325293,0.00008389649,0.011917118,0.09071453,0.8769065,0.0036595003,0.0009694186],"about_ca_topic_score_codex":0.0014750069,"about_ca_topic_score_gemma":0.0007106033,"teacher_disagreement_score":0.77996385,"about_ca_system_score_codex":0.000078689205,"about_ca_system_score_gemma":0.000056081477,"threshold_uncertainty_score":0.62908036},"labels":[],"label_agreement":null},{"id":"W2166388477","doi":"10.1016/j.patcog.2010.02.011","title":"Velocity and pressure-based partitions of horizontal and vertical trajectories for on-line signature verification","year":2010,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":55,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Signature (topology); Pattern recognition (psychology); Computer science; Feature (linguistics); Artificial intelligence; Trajectory; Invariant (physics); Line (geometry); Rotation (mathematics); Partition (number theory); Acceleration; Algorithm; Mathematics; Geometry; Physics","score_opus":0.028417016723524986,"score_gpt":0.2719150356142068,"score_spread":0.24349801889068184,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2166388477","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":[0.46002752,0.000022310702,0.53865194,0.0004746284,0.00014267843,0.0003696997,0.00013406361,0.00012163207,0.00005552443],"genre_scores_gemma":[0.9816826,0.000012016365,0.017746493,0.0001723732,0.000077039935,0.0001836219,0.000114197435,0.000009282139,0.0000023481086],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99918985,0.00004288073,0.00019698568,0.0002985766,0.00013719668,0.00013453088],"domain_scores_gemma":[0.99926376,0.00023114069,0.00006357184,0.00017499228,0.00019419647,0.00007232292],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020455458,0.000114609764,0.00013866018,0.000091909445,0.00009856979,0.000064786545,0.00010838441,0.0001356276,0.000020060186],"category_scores_gemma":[0.0001366052,0.000112085094,0.000038787766,0.00009370158,0.00009763195,0.0002441855,0.000023244475,0.0001838858,0.0000033967615],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007792886,0.00031407454,0.0011996329,0.00020429079,0.0000308945,0.0000013401936,0.00025418063,0.0000010231317,0.08110172,0.001163813,0.0002351174,0.915416],"study_design_scores_gemma":[0.0010801896,0.00095391757,0.014942325,0.0001127705,0.00006225927,0.000011684344,0.000017666029,0.028512154,0.9355507,0.017969692,0.0004834931,0.0003031436],"about_ca_topic_score_codex":0.000015674115,"about_ca_topic_score_gemma":0.00004209439,"teacher_disagreement_score":0.91511285,"about_ca_system_score_codex":0.0000063362495,"about_ca_system_score_gemma":0.000026009227,"threshold_uncertainty_score":0.45706972},"labels":[],"label_agreement":null},{"id":"W2166637660","doi":"10.1109/icdar.2009.230","title":"Evaluation of Different Strategies to Optimize an HMM-Based Character Recognition System","year":2009,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"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; Computer science; Character (mathematics); Pattern recognition (psychology); Character recognition; Speech recognition; Artificial intelligence; Noise (video); Noise reduction; Reduction (mathematics); Process (computing); Optical character recognition; Mathematics","score_opus":0.05528795764964188,"score_gpt":0.30681301930207516,"score_spread":0.25152506165243327,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2166637660","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":[0.23775226,0.000005432574,0.7535113,0.00036839384,0.00008913186,0.00062778156,0.00000520859,0.0006085175,0.007031948],"genre_scores_gemma":[0.9106128,0.0000011164783,0.08889682,0.00032711233,0.0000360098,0.00008274949,0.0000266421,0.000005517136,0.000011181701],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99805677,0.0003213862,0.0003407287,0.00033942488,0.00076433714,0.00017735362],"domain_scores_gemma":[0.9983656,0.00003674001,0.000124196,0.0004425877,0.0009216946,0.00010919313],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011659345,0.00014572917,0.00019935792,0.00024808006,0.000047773636,0.0001903397,0.0003780915,0.00007272328,0.00010431963],"category_scores_gemma":[0.000033727112,0.000122029676,0.00006022072,0.00024644344,0.000011871455,0.00086660235,0.000024828809,0.00006566643,0.00004783354],"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":[0.000018887536,0.0003147209,0.000011871762,0.000028507018,0.000012174401,0.0000016333693,0.00027056312,0.000129277,0.023280522,0.0057488554,0.00013133638,0.97005165],"study_design_scores_gemma":[0.00094442023,0.001325979,0.008744427,0.0002715777,0.0000713798,0.000008756873,0.0002590951,0.32158554,0.6519214,0.0144311115,0.000017259037,0.00041909376],"about_ca_topic_score_codex":0.000014512972,"about_ca_topic_score_gemma":0.000009737735,"teacher_disagreement_score":0.96963257,"about_ca_system_score_codex":0.00012161058,"about_ca_system_score_gemma":0.00011792061,"threshold_uncertainty_score":0.49762258},"labels":[],"label_agreement":null},{"id":"W2166933059","doi":"10.1109/icdar.2003.1227857","title":"Shock filters for character image enhancement and peeling","year":2005,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal; École de Technologie Supérieure","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Character (mathematics); Partial differential equation; Computer science; Image (mathematics); Set (abstract data type); Image processing; Image quality; Image enhancement; Image restoration; Artificial intelligence; Computer vision; Algorithm; Mathematics; Mathematical analysis; Geometry","score_opus":0.014646952810296727,"score_gpt":0.2659774267223254,"score_spread":0.2513304739120287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2166933059","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":[0.01003981,0.000023506425,0.9822649,0.0035918814,0.000048027912,0.00025176458,0.0000019674924,0.00024166562,0.0035364954],"genre_scores_gemma":[0.17771515,0.000028178212,0.81802267,0.0023239627,0.000100835045,0.00010053452,0.000003761077,0.0000064281753,0.0016984664],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99934065,0.00001022797,0.00014307722,0.00023872603,0.00009250152,0.000174841],"domain_scores_gemma":[0.9996198,0.00004774407,0.00003271429,0.00017713099,0.00006820605,0.000054406046],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018669061,0.0000798145,0.000082705796,0.000061734856,0.000064426575,0.00014950368,0.0002034066,0.000027451699,0.000121510595],"category_scores_gemma":[0.000014645092,0.00007009281,0.000032234882,0.000051610303,0.000017223218,0.00057737407,0.00009561511,0.000040933162,0.00005569805],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000046843243,0.00004891565,0.000023072662,0.000019117859,0.000009197028,0.0000010019331,0.00034983337,1.1888247e-7,0.07147734,0.0060912874,0.008130397,0.91384506],"study_design_scores_gemma":[0.00035740342,0.00012156759,0.00014861002,0.000021321417,0.0000042399697,0.0000101517435,0.000017970395,0.030155966,0.9060686,0.002186173,0.060677525,0.00023042233],"about_ca_topic_score_codex":0.000002411484,"about_ca_topic_score_gemma":0.0000030301571,"teacher_disagreement_score":0.91361463,"about_ca_system_score_codex":0.00002080053,"about_ca_system_score_gemma":0.0000094948,"threshold_uncertainty_score":0.28583017},"labels":[],"label_agreement":null},{"id":"W2167188088","doi":"10.1109/tpami.2007.70749","title":"A Comparative Study of Staff Removal Algorithms","year":2008,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":120,"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":"Social Sciences and Humanities Research Council of Canada; Johns Hopkins University; Institute of Museum and Library Services; National Science Foundation","keywords":"Computer science; Notation; Skeletonization; Robustness (evolution); Algorithm; Artificial intelligence; Image segmentation; Segmentation; Mathematics","score_opus":0.04405373487622228,"score_gpt":0.30693736338767974,"score_spread":0.26288362851145747,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167188088","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":[0.121240124,0.000033768876,0.87817204,0.000038707527,0.00005318818,0.00021160784,0.000021872958,0.00010881513,0.00011989873],"genre_scores_gemma":[0.9922225,0.00020461851,0.0073681963,0.000053904965,0.0000072548028,0.00003302004,0.0000018385307,0.0000063565244,0.0001022973],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983812,0.00014841826,0.00046437874,0.0004765952,0.00035876775,0.00017063804],"domain_scores_gemma":[0.9989913,0.00011956338,0.0001472112,0.00048398555,0.00015939586,0.000098514734],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001835874,0.00019802216,0.0004801635,0.0006698807,0.00019743167,0.000039207498,0.00042534288,0.000046022513,0.00009313829],"category_scores_gemma":[0.0000020177627,0.00017290386,0.00018484233,0.0013626533,0.000097829114,0.00022619322,0.0000073795127,0.00022089694,0.000014759326],"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":[0.00002068558,0.002704754,0.00049171044,0.000012706437,0.0011517596,0.00009695245,0.00856136,0.0028852776,0.00048280784,0.00002499931,0.000015700043,0.98355126],"study_design_scores_gemma":[0.0004758945,0.00283074,0.0030562147,0.000045863035,0.00075284,0.0002038074,0.0016308976,0.29439136,0.69549406,0.00037800273,0.000058238787,0.000682103],"about_ca_topic_score_codex":0.0015424324,"about_ca_topic_score_gemma":0.0011369422,"teacher_disagreement_score":0.9828692,"about_ca_system_score_codex":0.00002074851,"about_ca_system_score_gemma":0.000020134888,"threshold_uncertainty_score":0.70508146},"labels":[],"label_agreement":null},{"id":"W2168598196","doi":"10.1109/icdar.1993.395725","title":"Cursive script recognition: A fast reader scheme","year":2002,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"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","keywords":"Cursive; Computer science; Context (archaeology); Character (mathematics); Orthography; Syntax; Natural language processing; Semantics (computer science); Sentence; Reading (process); Artificial intelligence; Abstraction; Process (computing); Programming language; Linguistics","score_opus":0.046994524096886744,"score_gpt":0.2501268248773216,"score_spread":0.20313230078043482,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2168598196","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":[0.0011309005,0.000153403,0.7340395,0.004633879,0.00024502925,0.00026805984,0.000005899538,0.0018090092,0.2577143],"genre_scores_gemma":[0.10003684,0.00019609927,0.87385696,0.0075223413,0.00026684263,0.00017423082,0.000014776927,0.00003060792,0.017901322],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99872506,0.00005113335,0.00022661427,0.0004213065,0.000267587,0.0003082944],"domain_scores_gemma":[0.99906147,0.000041684492,0.000064649335,0.0004728968,0.00022553034,0.00013375466],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00013165649,0.00015223105,0.00014205382,0.00016663893,0.00011500383,0.00019922544,0.00057992234,0.00009124602,0.003726528],"category_scores_gemma":[0.00005187661,0.00014223013,0.000079508885,0.00047712578,0.0000597263,0.00094227836,0.00014799838,0.00016904641,0.004936933],"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":[0.0000015340107,0.00018510004,0.00006737726,0.000012432313,0.00002770134,0.00004504703,0.0006881305,4.1932953e-8,0.0015679962,0.011753034,0.2008619,0.7847897],"study_design_scores_gemma":[0.0025938514,0.0009949169,0.0005391115,0.00045660118,0.000049864804,0.001114725,0.000755703,0.058113586,0.45966378,0.1545992,0.31802458,0.0030940606],"about_ca_topic_score_codex":0.000013062966,"about_ca_topic_score_gemma":0.0000037948882,"teacher_disagreement_score":0.78169566,"about_ca_system_score_codex":0.00003642229,"about_ca_system_score_gemma":0.000012231413,"threshold_uncertainty_score":0.9971842},"labels":[],"label_agreement":null},{"id":"W2170331650","doi":"10.4172/2155-6180.1000174","title":"Grip Kinetic Profile Variability in Adult Signature Writing","year":2013,"lang":"en","type":"article","venue":"Journal of Biometrics & Biostatistics","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Holland Bloorview Kids Rehabilitation Hospital; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Signature (topology); Computer science; Kinetic energy; Physics; Mathematics","score_opus":0.010754869146243035,"score_gpt":0.2562011430607787,"score_spread":0.24544627391453563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170331650","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":[0.016444804,0.00015524456,0.9811323,0.0007275816,0.00040266162,0.0003136262,0.000043444332,0.00006255236,0.00071773474],"genre_scores_gemma":[0.54195046,0.000093112794,0.4576134,0.000239952,0.00006869248,0.000005853502,0.0000035558946,0.000008535869,0.000016390046],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9974275,0.0002498843,0.0010557607,0.00024987667,0.0006679847,0.0003489416],"domain_scores_gemma":[0.9956614,0.0012333475,0.00069020514,0.0003136455,0.0019077206,0.00019372108],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017936581,0.00017950966,0.00034690354,0.0023469804,0.000053325068,0.00031245014,0.00086489023,0.00018462235,0.000103064805],"category_scores_gemma":[0.0049806247,0.0001552127,0.000085439766,0.0053952555,0.00007157376,0.0006148748,0.00016358087,0.0005762339,0.000044341054],"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":[0.000008854313,0.0005493153,0.006636992,0.00016779684,0.000032589945,0.0001874806,0.00031004727,0.000003397571,0.011592924,0.016062448,0.015744982,0.94870317],"study_design_scores_gemma":[0.0057901945,0.0048245015,0.28573906,0.0015704518,0.00015100962,0.0016580713,0.0006088948,0.1487285,0.14458537,0.39715657,0.006147391,0.0030399922],"about_ca_topic_score_codex":0.000042346997,"about_ca_topic_score_gemma":0.0000018778885,"teacher_disagreement_score":0.94566315,"about_ca_system_score_codex":0.00016906326,"about_ca_system_score_gemma":0.00014205187,"threshold_uncertainty_score":0.63293904},"labels":[],"label_agreement":null},{"id":"W2170460607","doi":"10.1109/icpr.1994.576979","title":"An extended-shadow-code based approach for off-line signature verification. I. Evaluation of the bar mask definition","year":2002,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Signature (topology); Computer science; Shadow (psychology); Handwriting; Code (set theory); Diagonal; Feature (linguistics); Bar (unit); Segmentation; Artificial intelligence; Resolution (logic); Line (geometry); Pattern recognition (psychology); Computer vision; Algorithm; Mathematics; Programming language; Physics; Geometry","score_opus":0.08076222823194633,"score_gpt":0.29466180389726293,"score_spread":0.2138995756653166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170460607","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":[0.0012134687,0.00015279779,0.9888106,0.00061572314,0.00006731438,0.0011199575,0.000035499517,0.00028018293,0.0077044326],"genre_scores_gemma":[0.6632301,0.000009419933,0.33589548,0.00041481253,0.000031152376,0.0002923234,0.000057092144,0.000009663035,0.000059939513],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981997,0.0002682596,0.00031810542,0.0004113317,0.00063079427,0.000171795],"domain_scores_gemma":[0.9980957,0.0000830206,0.00018395526,0.0008679155,0.00071583997,0.000053571155],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00122255,0.00013782355,0.00013784626,0.00011417184,0.00013679457,0.00007406489,0.0007802457,0.00013901311,0.000265967],"category_scores_gemma":[0.00015145827,0.000102404345,0.00011119263,0.00039560487,0.000052849686,0.00048478573,0.000036758698,0.00012104818,0.000010836215],"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":[0.000024268697,0.0017524231,0.00007536011,0.000112831076,0.000034266177,2.664952e-7,0.0005393046,0.0023503203,0.035357796,0.1065029,0.006979181,0.8462711],"study_design_scores_gemma":[0.00051575014,0.00011637003,0.0005225141,0.000015307776,0.000031575877,0.000002292422,0.000024610319,0.8953974,0.087105624,0.015893701,0.00023914312,0.00013566659],"about_ca_topic_score_codex":0.000004763663,"about_ca_topic_score_gemma":0.000004103466,"teacher_disagreement_score":0.8930471,"about_ca_system_score_codex":0.000057873585,"about_ca_system_score_gemma":0.00006598147,"threshold_uncertainty_score":0.4175928},"labels":[],"label_agreement":null},{"id":"W2170654949","doi":"10.1109/icdar.2005.206","title":"Script identification using steerable Gabor filters","year":2005,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Gabor filter; Gabor wavelet; Artificial intelligence; Computer science; Computer vision; Gabor transform; Pattern recognition (psychology); Identification (biology); Filter (signal processing); Computation; Scripting language; Filter bank; Feature extraction; Rotation (mathematics); Time–frequency analysis; Algorithm","score_opus":0.028581998775540025,"score_gpt":0.2767923243620172,"score_spread":0.24821032558647715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170654949","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":[0.014317075,0.000040552783,0.9767858,0.0009887078,0.00013372302,0.00013339365,0.0000012158974,0.00066805497,0.006931516],"genre_scores_gemma":[0.5339221,0.000008847978,0.46176967,0.0010053777,0.000071428025,0.000013897533,0.0000024958886,0.0000070921733,0.0031991075],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991449,0.000034698813,0.00020825992,0.0002535878,0.00018048711,0.00017805965],"domain_scores_gemma":[0.99937403,0.000018000666,0.000060182327,0.00038310015,0.00010737827,0.000057329384],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002570684,0.00007849947,0.00007595739,0.00012719347,0.000099870726,0.000269843,0.00044573794,0.00003966433,0.00020847999],"category_scores_gemma":[0.000019241525,0.000076011835,0.000037028567,0.00027424624,0.000019046223,0.0012353533,0.00008017945,0.000062471125,0.0003182687],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000283174,0.00015538497,0.00020735592,0.000018850951,0.000019425399,0.000005421035,0.00054100243,0.00008450491,0.27388132,0.04459686,0.03847452,0.64201254],"study_design_scores_gemma":[0.00019854511,0.000026534048,0.000586064,0.000025117364,0.0000059891536,0.000030936706,0.000034772,0.18403548,0.78077567,0.004629622,0.029367503,0.00028375984],"about_ca_topic_score_codex":0.00003321678,"about_ca_topic_score_gemma":0.000008919195,"teacher_disagreement_score":0.64172876,"about_ca_system_score_codex":0.00006504178,"about_ca_system_score_gemma":0.00003207759,"threshold_uncertainty_score":0.40908062},"labels":[],"label_agreement":null},{"id":"W2170663025","doi":"10.1109/icdar.2001.953746","title":"Recognition of unconstrained handwritten numeral strings using decision value generator","year":2002,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Numeral system; Segmentation; NIST; Computer science; Pattern recognition (psychology); String (physics); Artificial intelligence; Generator (circuit theory); Speech recognition; Handwriting recognition; Value (mathematics); Digit recognition; Image segmentation; Feature extraction; Mathematics; Machine learning; Artificial neural network","score_opus":0.04148312018554125,"score_gpt":0.2585545261814907,"score_spread":0.21707140599594948,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170663025","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":[0.21113141,0.00005861154,0.78475827,0.000117335265,0.00013391433,0.0001906464,0.00000889231,0.00034355163,0.0032573827],"genre_scores_gemma":[0.50580996,0.000023869366,0.49377975,0.0002335764,0.000050460043,0.00000772807,0.0000032925605,0.00001009966,0.000081278995],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99841106,0.000076530065,0.0004784061,0.0003945024,0.00036857172,0.00027091222],"domain_scores_gemma":[0.9989438,0.000116744945,0.0001623024,0.00038723677,0.00027253406,0.000117382224],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031701344,0.00017384182,0.0002441382,0.00027606302,0.000105171355,0.0001225488,0.0004713437,0.00011904156,0.00064026064],"category_scores_gemma":[0.000090781105,0.00016214947,0.00011725119,0.00054856786,0.0000668763,0.0007699194,0.00014654956,0.00012327408,0.00008635],"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":[0.0000069042203,0.00016567852,0.00023412234,0.000019029183,0.000026292584,0.000015652515,0.00020123155,0.000016404423,0.051985815,0.0037235254,0.0019458347,0.9416595],"study_design_scores_gemma":[0.0010515522,0.00023613141,0.00013876671,0.000206715,0.000023168486,0.00014172595,0.00003673122,0.26367095,0.7080409,0.025401156,0.0005436354,0.000508593],"about_ca_topic_score_codex":0.00007097278,"about_ca_topic_score_gemma":0.0000047114504,"teacher_disagreement_score":0.9411509,"about_ca_system_score_codex":0.00005481341,"about_ca_system_score_gemma":0.000033429536,"threshold_uncertainty_score":0.7010405},"labels":[],"label_agreement":null},{"id":"W2171498274","doi":"10.1007/s10044-002-0169-3","title":"Large vocabulary off-line handwriting recognition: A survey","year":2003,"lang":"en","type":"article","venue":"Pattern Analysis and Applications","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":165,"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; Université du Québec à Montréal","funders":"","keywords":"Computer science; Vocabulary; Lexicon; Handwriting; Intelligent character recognition; Handwriting recognition; Key (lock); Natural language processing; Word recognition; Artificial intelligence; Software deployment; Speech recognition; Process (computing); Word (group theory); Line (geometry); Character recognition; Feature extraction; Linguistics; Reading (process); Software engineering","score_opus":0.028867063532360654,"score_gpt":0.2801902910180454,"score_spread":0.2513232274856847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171498274","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":[0.008993214,0.00029643538,0.9886625,0.00019254551,0.000009720437,0.00022095905,0.0001007471,0.00019622789,0.0013276865],"genre_scores_gemma":[0.9871905,0.00029756213,0.011000307,0.00072061585,0.000040435752,0.00033804306,0.0002766949,0.000009940047,0.0001259019],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9985718,0.0001979766,0.00032909616,0.000488173,0.00017380154,0.00023916125],"domain_scores_gemma":[0.99890274,0.00015044645,0.00012746174,0.00049103925,0.00020532757,0.00012295914],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008861933,0.00014159038,0.00024722278,0.00029969084,0.00028362699,0.00021849383,0.0002708131,0.000062854786,0.00016877943],"category_scores_gemma":[0.000044432403,0.00014151297,0.00012360263,0.0016419969,0.00003197829,0.00020348858,0.00008314208,0.00011923997,0.00009977875],"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":[0.0000010107457,0.00029955586,0.079983465,0.000020690619,0.0003678484,0.0000040958257,0.00014409971,0.0000021556516,0.00024213559,0.0031979093,0.0003027577,0.9154343],"study_design_scores_gemma":[0.004461076,0.00040037127,0.50224423,0.00022899736,0.003329195,0.00022955927,0.0008154893,0.12535413,0.098517716,0.07393754,0.18511939,0.0053622825],"about_ca_topic_score_codex":0.00008495145,"about_ca_topic_score_gemma":0.0004634061,"teacher_disagreement_score":0.9781973,"about_ca_system_score_codex":0.0000147540895,"about_ca_system_score_gemma":0.000021029453,"threshold_uncertainty_score":0.57707316},"labels":[],"label_agreement":null},{"id":"W2174657119","doi":"10.5815/ijitcs.2015.11.06","title":"Time and Accuracy Analysis of Skew Detection Methods for Document Images","year":2015,"lang":"en","type":"article","venue":"International Journal of Information Technology and Computer Science","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Computer science; Hough transform; Skew; Wavelet transform; Artificial intelligence; Radon transform; Pattern recognition (psychology); Robustness (evolution); Wavelet; Principal component analysis; Discrete wavelet transform; Computer vision; Image (mathematics)","score_opus":0.011329604318656728,"score_gpt":0.33096635037813055,"score_spread":0.31963674605947384,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2174657119","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":[0.032180145,0.000070898546,0.9663616,0.00096958334,0.0002478391,0.00008180195,0.0000027236397,0.00004602203,0.000039433016],"genre_scores_gemma":[0.3441938,0.00004098326,0.6556088,0.00013270527,0.000015466865,0.000004053052,9.2484817e-7,9.326879e-7,0.0000023764112],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989674,0.000028193628,0.0004954973,0.0001062444,0.000304688,0.00009794091],"domain_scores_gemma":[0.99711907,0.00014690195,0.0006252079,0.00012888972,0.0019121787,0.000067731125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001769118,0.00007285897,0.00018437042,0.0030180982,0.00006164739,0.0002050988,0.00088859926,0.000057745667,0.0000017169089],"category_scores_gemma":[0.0003911388,0.00006176284,0.00005255096,0.0012309143,0.0002696087,0.0035658127,0.00032219023,0.00009104992,0.0000011295841],"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":[0.000012376199,0.000012091041,0.00005964831,0.0000030030658,0.000101975354,5.4879797e-7,0.00035051012,0.000054653257,0.0016352198,0.013677867,0.000029820354,0.9840623],"study_design_scores_gemma":[0.0009277723,0.00077085855,0.0017355502,0.000055209657,0.00009529689,0.00044128622,0.00007782136,0.5461887,0.33550072,0.111251004,0.0027624697,0.00019327905],"about_ca_topic_score_codex":0.0000025242052,"about_ca_topic_score_gemma":3.568061e-7,"teacher_disagreement_score":0.983869,"about_ca_system_score_codex":0.000052822386,"about_ca_system_score_gemma":0.00011158445,"threshold_uncertainty_score":0.26930174},"labels":[],"label_agreement":null},{"id":"W2203557800","doi":"","title":"Novel Curve Signatures and a Combination Method for Thai On-Line Handwriting Character Recognition.","year":2013,"lang":"en","type":"article","venue":"The Florida AI Research Society","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Handwriting; Handwriting recognition; Character (mathematics); Computer science; Pattern recognition (psychology); Artificial intelligence; Similarity (geometry); Ranking (information retrieval); Tangent; Speech recognition; Mathematics; Feature extraction; Image (mathematics)","score_opus":0.10033848484166157,"score_gpt":0.3862604222922593,"score_spread":0.28592193745059774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2203557800","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":[0.0116013205,0.00010207322,0.9615817,0.023681026,0.0001673188,0.0020464966,0.000048478778,0.0003149896,0.00045658482],"genre_scores_gemma":[0.4287509,0.00038832545,0.5544365,0.009494653,0.001239771,0.0041598883,0.00012526533,0.000077737706,0.0013269401],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975019,0.00037487023,0.0002795658,0.00053160806,0.00071955734,0.0005925122],"domain_scores_gemma":[0.9952471,0.0027901388,0.00009168272,0.00046422958,0.0012722175,0.00013457684],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0051459046,0.0001882761,0.00021007296,0.0001194612,0.00087686797,0.000785142,0.0007759988,0.00017123503,0.000051285293],"category_scores_gemma":[0.00061545265,0.00013503681,0.0001692629,0.00055469514,0.0001998546,0.0008807408,0.0003881684,0.00090414623,0.00006798185],"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":[0.00004759275,0.0004616685,0.00003825702,0.00022551326,0.00017894548,0.0000019571323,0.0060788444,0.000007544467,0.08006856,0.03127795,0.111758344,0.76985484],"study_design_scores_gemma":[0.0028328367,0.0013049458,0.0015370235,0.00037160385,0.000022803148,0.000037641355,0.0009945915,0.49397025,0.19869317,0.2919711,0.0075232354,0.00074081484],"about_ca_topic_score_codex":0.00011803861,"about_ca_topic_score_gemma":0.0000040367504,"teacher_disagreement_score":0.769114,"about_ca_system_score_codex":0.00008637697,"about_ca_system_score_gemma":0.00008396077,"threshold_uncertainty_score":0.7571143},"labels":[],"label_agreement":null},{"id":"W2222770805","doi":"10.1007/978-3-642-41827-3_14","title":"An Arabic Optical Character Recognition System Using Restricted Boltzmann Machines","year":2013,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Handwritten Text Recognition Techniques","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":"University of Waterloo","funders":"","keywords":"Hidden Markov model; Computer science; Character (mathematics); Arabic; Optical character recognition; Boltzmann machine; Artificial intelligence; Speech recognition; Natural language processing; Pattern recognition (psychology); Artificial neural network; Linguistics; Image (mathematics); Mathematics","score_opus":0.0263644193559066,"score_gpt":0.2605655171339826,"score_spread":0.23420109777807602,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2222770805","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":[0.0037239564,0.00010701732,0.98984826,0.00020031957,0.0014256964,0.00090135774,0.000016914295,0.0011053483,0.00267115],"genre_scores_gemma":[0.18030807,0.000031247928,0.81741273,0.0008865059,0.0010676257,0.000049466573,0.000055403507,0.0000849951,0.00010394138],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9947672,0.00012125287,0.0009207403,0.0021105602,0.0011966582,0.00088357914],"domain_scores_gemma":[0.9962551,0.0003227648,0.0005022449,0.0017573128,0.0007814359,0.0003811584],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0008164606,0.00078033505,0.0007767998,0.0016556362,0.0003703466,0.0014920682,0.003229984,0.00068158226,0.0000685647],"category_scores_gemma":[0.000093188566,0.00071288005,0.00017692467,0.0008503724,0.00056383596,0.0023566827,0.00079949695,0.001180365,0.00029919413],"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":[0.0000064181227,0.00005554772,0.00002034239,0.00009439977,0.000012790111,0.00013911891,0.00017707782,0.0003033263,0.003369127,0.0036769947,0.00001600816,0.99212885],"study_design_scores_gemma":[0.0003293029,0.00040018398,0.00034958712,0.0016574936,0.000029567113,0.00068037235,3.4763428e-7,0.9163442,0.014779008,0.063768074,0.00021444974,0.0014473941],"about_ca_topic_score_codex":0.000073384464,"about_ca_topic_score_gemma":0.000018141372,"teacher_disagreement_score":0.99068147,"about_ca_system_score_codex":0.00060939667,"about_ca_system_score_gemma":0.00044734837,"threshold_uncertainty_score":0.9995445},"labels":[],"label_agreement":null},{"id":"W2228104382","doi":"10.5539/mas.v9n13p148","title":"A Bilingual Numeral OCR System for Creating Uni-Lingual Digitized Numeral Document","year":2015,"lang":"en","type":"article","venue":"Modern Applied Science","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Numeral system; Computer science; Tamil; Optical character recognition; Natural language processing; Artificial intelligence; Document processing; Arabic numerals; Speech recognition; Linguistics; Image (mathematics)","score_opus":0.029068963903023062,"score_gpt":0.2884901105079798,"score_spread":0.25942114660495674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2228104382","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":[0.07142491,0.00003098442,0.91314787,0.00014728335,0.00036044203,0.0009756879,0.000009564152,0.0015610156,0.012342229],"genre_scores_gemma":[0.8258879,7.7790565e-7,0.17321533,0.00024726556,0.0001412804,0.00025160806,0.000004904356,0.000021295533,0.00022960521],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996163,0.000046525733,0.00055437617,0.001146398,0.0011750846,0.0009146115],"domain_scores_gemma":[0.9976639,0.00014825848,0.0002386197,0.0008129087,0.0005292418,0.00060704217],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0024104777,0.00031401607,0.00037997836,0.00032225132,0.0006561307,0.0011731421,0.0021354894,0.000094704264,0.0000050869717],"category_scores_gemma":[0.00026784703,0.00028846608,0.00010122898,0.00095720723,0.00035103504,0.0010179153,0.0006210132,0.00019478661,0.000053253],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019862356,0.00023060173,0.00016912248,0.0001944243,0.00004667265,0.000049665945,0.020435764,0.00060274644,0.23093562,0.38279945,0.0007038099,0.3636335],"study_design_scores_gemma":[0.0023312196,0.00027590446,0.00001845936,0.00012271063,0.00001810326,0.00009665534,0.00090794265,0.51770204,0.3847519,0.09184488,0.00103091,0.00089929445],"about_ca_topic_score_codex":0.00005697047,"about_ca_topic_score_gemma":0.0000065850513,"teacher_disagreement_score":0.754463,"about_ca_system_score_codex":0.00049965014,"about_ca_system_score_gemma":0.0014631274,"threshold_uncertainty_score":0.9999567},"labels":[],"label_agreement":null},{"id":"W2228330368","doi":"10.1007/978-3-642-21557-5_18","title":"Dynamic Ensemble Selection for Off-Line Signature Verification","year":2011,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":10,"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":"Discriminative model; Computer science; Signature (topology); Selection (genetic algorithm); Artificial intelligence; Pattern recognition (psychology); Line (geometry); Machine learning; k-nearest neighbors algorithm; Data mining; Mathematics","score_opus":0.019692748215553873,"score_gpt":0.2584632837468577,"score_spread":0.2387705355313038,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2228330368","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":[0.000029096622,0.00052575115,0.9946151,0.00036115892,0.0010093177,0.0009849382,0.000011076761,0.0005718122,0.0018917779],"genre_scores_gemma":[0.09192088,0.00019262916,0.9053829,0.0009949039,0.0002693946,0.00009450094,0.00003859893,0.00006010329,0.0010461381],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966725,0.000032872114,0.00053456123,0.0015845022,0.0005986608,0.0005768808],"domain_scores_gemma":[0.99755216,0.0002905481,0.0003869345,0.0009777592,0.0006579642,0.0001346083],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008552504,0.000505135,0.00045951383,0.000992603,0.0002796139,0.0003474429,0.0022615772,0.00060578325,0.000031674237],"category_scores_gemma":[0.0001058977,0.000495614,0.0001701443,0.00062285265,0.00030283484,0.00073710893,0.00040032947,0.0007623407,0.000044025044],"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":[0.000010146551,0.000031969987,0.0000029936411,0.00004114942,0.000008782539,0.000004135051,0.00022173641,0.000507131,0.0026945104,0.012022413,0.00006345473,0.98439157],"study_design_scores_gemma":[0.00024775436,0.00044129894,0.000029915911,0.00028613844,0.000013955016,0.00006286783,5.8929157e-8,0.49937597,0.042464353,0.4522118,0.0041707777,0.00069513265],"about_ca_topic_score_codex":0.000011995081,"about_ca_topic_score_gemma":0.00011031682,"teacher_disagreement_score":0.98369646,"about_ca_system_score_codex":0.00038587145,"about_ca_system_score_gemma":0.0004622035,"threshold_uncertainty_score":0.99974954},"labels":[],"label_agreement":null},{"id":"W2244599202","doi":"10.1007/978-3-642-38457-8_35","title":"Shape-Based Analysis for Automatic Segmentation of Arabic Handwritten Text","year":2013,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","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":"Concordia University","funders":"","keywords":"Computer science; Scripting language; Segmentation; Spotting; Arabic; Artificial intelligence; Natural language processing; Text segmentation; Image segmentation; Market segmentation; Pattern recognition (psychology); Speech recognition; Linguistics","score_opus":0.018844337319278006,"score_gpt":0.26083554903246015,"score_spread":0.24199121171318214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2244599202","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":[0.0003995735,0.00013053157,0.9966834,0.00042366653,0.0002869713,0.0011769595,0.000020108624,0.00029669874,0.0005820563],"genre_scores_gemma":[0.16664572,0.000011051458,0.8320923,0.0008219709,0.00009243949,0.00012556848,0.000034444543,0.000029035007,0.00014748317],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99636084,0.00004789769,0.0008715227,0.0012766897,0.0009303119,0.00051274576],"domain_scores_gemma":[0.9964472,0.0008529737,0.0006780569,0.0011945413,0.00068531506,0.00014193522],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00093659613,0.0004896149,0.0008573803,0.0024791698,0.00016761555,0.00043181208,0.0024306462,0.0003203699,0.00018085858],"category_scores_gemma":[0.000109889,0.00044802786,0.00040317143,0.0014929668,0.000503255,0.00067494955,0.0003748014,0.00033101393,0.000036582147],"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":[0.000003146188,0.000047194546,0.000095562595,0.0001455492,0.00008351477,0.0000045314123,0.00022571466,0.0048201615,0.0008144559,0.0020958665,0.00003692787,0.9916274],"study_design_scores_gemma":[0.00033138116,0.0002515131,0.00031197348,0.0003053842,0.00009773841,0.0000051409324,1.7553414e-7,0.90842015,0.02508033,0.06462839,0.00008141298,0.0004864355],"about_ca_topic_score_codex":0.0000275446,"about_ca_topic_score_gemma":0.000040811017,"teacher_disagreement_score":0.99114096,"about_ca_system_score_codex":0.00025035898,"about_ca_system_score_gemma":0.00044445935,"threshold_uncertainty_score":0.99979717},"labels":[],"label_agreement":null},{"id":"W2256856437","doi":"10.1007/s10044-016-0536-0","title":"Direction histogram: novel discriminative global feature for Thai offline handwritten OCR","year":2016,"lang":"en","type":"article","venue":"Pattern Analysis and Applications","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","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":"York University","funders":"","keywords":"Pattern recognition (psychology); Artificial intelligence; Histogram; Feature (linguistics); Computer science; Discriminative model; Handwriting; Convolutional neural network; Feature extraction; Character (mathematics); Pixel; Artificial neural network; Image (mathematics); Mathematics","score_opus":0.01614470884737868,"score_gpt":0.2822022742602904,"score_spread":0.2660575654129117,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2256856437","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":[0.0005393646,0.00008483028,0.99235815,0.00563338,0.000019521352,0.00041523192,0.0002687961,0.00021614,0.00046457353],"genre_scores_gemma":[0.94220823,0.00010545718,0.0546906,0.000455443,0.00012305069,0.0013600278,0.000083926134,0.000009691273,0.00096359436],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989414,0.000022978258,0.00019618828,0.0005045498,0.00014674192,0.00018813023],"domain_scores_gemma":[0.9990888,0.000092042086,0.00013654657,0.0004017417,0.0001834845,0.00009733551],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001540689,0.000146626,0.00022719758,0.00016087102,0.00021025834,0.000120289216,0.00031992208,0.00006931691,0.000015109264],"category_scores_gemma":[0.000015824375,0.00010222797,0.00018811287,0.00082956377,0.00006588111,0.00022843701,0.000096577605,0.000045880377,0.0000099768495],"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":[0.000002072848,0.00012010459,0.0049193786,0.000009673436,0.00018806472,1.6087851e-7,0.000050819664,2.9042806e-7,0.003027243,0.005482236,0.0007486505,0.9854513],"study_design_scores_gemma":[0.0053941696,0.00063529203,0.3769559,0.0002417918,0.0048163747,0.00007271613,0.00035079767,0.059945222,0.058464967,0.10031483,0.38935563,0.0034523152],"about_ca_topic_score_codex":0.00009179428,"about_ca_topic_score_gemma":0.00027853655,"teacher_disagreement_score":0.981999,"about_ca_system_score_codex":0.00007182564,"about_ca_system_score_gemma":0.000014250156,"threshold_uncertainty_score":0.41687354},"labels":[],"label_agreement":null},{"id":"W2270798212","doi":"10.1007/s10489-015-0753-z","title":"Document segmentation using textural features summarization and feedforward neural network","year":2016,"lang":"en","type":"article","venue":"Applied Intelligence","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":55,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"University of Nicosia","keywords":"Computer science; Automatic summarization; Artificial intelligence; Segmentation; Pattern recognition (psychology); Entropy (arrow of time); Artificial neural network","score_opus":0.017060836715258314,"score_gpt":0.26583255067561,"score_spread":0.2487717139603517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2270798212","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":[0.021844424,0.00008682484,0.9762522,0.00033207497,0.0001508406,0.0003338999,0.0000012855937,0.00026891995,0.0007295118],"genre_scores_gemma":[0.8757168,0.00012170032,0.12353896,0.00038668598,0.00009366168,0.00003880156,0.0000037937316,0.000010032022,0.000089563335],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99882925,0.000038346818,0.0002456925,0.00038805022,0.00021958484,0.0002790946],"domain_scores_gemma":[0.9993801,0.000108523214,0.00011682413,0.00024855084,0.000066749526,0.00007926233],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002146059,0.0001584875,0.00012757763,0.00007731374,0.0001554478,0.00019867737,0.00033668644,0.0000690064,0.00003453549],"category_scores_gemma":[0.000015845493,0.00011463568,0.00002933799,0.00028505112,0.00007899024,0.00057254493,0.00020272304,0.000078079756,0.000029023066],"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":[0.000009885422,0.0000091888905,0.00031309115,0.000008077294,0.000010006519,0.0000018076423,0.00019205775,0.00014844883,0.028128805,0.059343096,0.00034446607,0.9114911],"study_design_scores_gemma":[0.00034552277,0.00019306797,0.0040875766,0.00018172682,0.00003223872,0.00010105258,0.0001332961,0.018204829,0.74458605,0.23028904,0.0009262185,0.0009193956],"about_ca_topic_score_codex":0.00002096318,"about_ca_topic_score_gemma":0.000006398328,"teacher_disagreement_score":0.9105717,"about_ca_system_score_codex":0.00007127107,"about_ca_system_score_gemma":0.00001975206,"threshold_uncertainty_score":0.46747074},"labels":[],"label_agreement":null},{"id":"W2275174132","doi":"","title":"Modeling segmentation cuts using support vector machines","year":2006,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Segmentation; Artificial intelligence; Scale-space segmentation; Computer science; Pattern recognition (psychology); Segmentation-based object categorization; Classifier (UML); Support vector machine; Image segmentation; Cut; Computer vision","score_opus":0.024983247090907556,"score_gpt":0.2822975182036474,"score_spread":0.25731427111273986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2275174132","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":[0.06542461,0.000009704331,0.9277699,0.00012776346,0.00009066824,0.00011094613,0.0000012501679,0.0006210341,0.0058441167],"genre_scores_gemma":[0.6087633,0.0000015740923,0.39063665,0.00017393977,0.000057642763,0.0000073687465,0.000008370142,0.0000062627455,0.000344907],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99921834,0.000025249135,0.00019685531,0.0002212287,0.00017800466,0.0001603061],"domain_scores_gemma":[0.99966097,0.0000120034465,0.000034734796,0.00018315639,0.0000772521,0.000031865893],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013184914,0.0000909494,0.00008266372,0.000109261586,0.000083858766,0.00014354031,0.00022860784,0.000036677957,0.0000879725],"category_scores_gemma":[0.0000045990537,0.000083734136,0.000039601993,0.00018328907,0.000009162443,0.0006404505,0.00007433762,0.000049216644,0.000048741487],"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":[0.000016580407,0.0006074984,0.008930374,0.00011361914,0.0000557395,0.00011135623,0.00085932086,0.03490355,0.42026538,0.10298462,0.010671174,0.4204808],"study_design_scores_gemma":[0.0000976868,0.000019176285,0.000073282485,0.0000068459804,0.0000031198356,0.00002377651,0.0000049762207,0.9324465,0.058460463,0.008686299,0.00005356741,0.00012431068],"about_ca_topic_score_codex":0.000528185,"about_ca_topic_score_gemma":0.000026990814,"teacher_disagreement_score":0.89754295,"about_ca_system_score_codex":0.000042563555,"about_ca_system_score_gemma":0.00003328168,"threshold_uncertainty_score":0.3414579},"labels":[],"label_agreement":null},{"id":"W2297010807","doi":"10.5539/cis.v9n2p1","title":"Invarianceness for Character Recognition Using Geo-Discretization Features","year":2016,"lang":"en","type":"article","venue":"Computer and Information Science","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Character (mathematics); Computer science; Handwriting; Font; Similarity (geometry); Artificial intelligence; Word error rate; Feature (linguistics); Pattern recognition (psychology); Variation (astronomy); Speech recognition; Intelligent character recognition; Line (geometry); Discretization; Intelligent word recognition; Feature extraction; Natural language processing; Character recognition; Linguistics; Mathematics; Image (mathematics)","score_opus":0.024952303809268078,"score_gpt":0.2637275323714315,"score_spread":0.2387752285621634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2297010807","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":[0.015126479,0.000006764317,0.98292464,0.00060209207,0.0003705829,0.00031695573,0.000013824673,0.00018914469,0.00044950144],"genre_scores_gemma":[0.46883732,0.000075667616,0.5285238,0.0022920063,0.00017332812,0.00005749817,0.000019345749,0.000005437885,0.000015587308],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989862,0.000020452555,0.0002681134,0.00023291318,0.00026335244,0.00022901059],"domain_scores_gemma":[0.9988751,0.00007571302,0.00016011475,0.00021840128,0.000578858,0.00009180927],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006480254,0.000105388644,0.00010065358,0.0003554211,0.0003278143,0.00064136344,0.0004456195,0.000050683404,0.0000070984033],"category_scores_gemma":[0.00008209812,0.00007463563,0.0000274054,0.0005144694,0.00016035367,0.018889522,0.00019385635,0.00003778766,0.000022852673],"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":[0.000004941817,0.0000067183887,0.0000716257,0.000018038372,0.000001713034,1.1109247e-7,0.00034861377,0.000002178817,0.0043558986,0.018281097,0.00020580056,0.9767033],"study_design_scores_gemma":[0.0030062506,0.00052779855,0.05458461,0.0008235491,0.00002039849,0.00030254433,0.000052956122,0.5354148,0.3159252,0.049171142,0.038648453,0.0015222811],"about_ca_topic_score_codex":0.0000030636188,"about_ca_topic_score_gemma":2.613798e-7,"teacher_disagreement_score":0.975181,"about_ca_system_score_codex":0.00005319511,"about_ca_system_score_gemma":0.00010362677,"threshold_uncertainty_score":0.99483275},"labels":[],"label_agreement":null},{"id":"W2297626085","doi":"","title":"Un état de l'art des méthodes de localisation de symboles dans les documents graphiques","year":2010,"lang":"fr","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Francophone University Association","funders":"","keywords":"Humanities; Philosophy","score_opus":0.022134786465651517,"score_gpt":0.2652323200998076,"score_spread":0.24309753363415607,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2297626085","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":[0.23655781,0.0010387419,0.7358069,0.011229303,0.0001733071,0.00029103053,0.000027021997,0.0005938636,0.014282062],"genre_scores_gemma":[0.5081239,0.0018985608,0.48426452,0.00023581268,0.000041846546,0.00008572201,0.000059611295,0.000043804415,0.005246246],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9872851,0.009900328,0.0006335019,0.0007816585,0.00046572732,0.0009336779],"domain_scores_gemma":[0.99354273,0.0018912925,0.00040438274,0.0015896751,0.0020685238,0.0005034033],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.012231229,0.0004204902,0.0003348734,0.00031067725,0.0009649072,0.0012674852,0.001901127,0.00046291086,0.0003370412],"category_scores_gemma":[0.002590578,0.0004917238,0.00024632487,0.00085687696,0.0013025312,0.0011187013,0.0005739257,0.0008324022,0.00008415504],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008555274,0.0007898675,0.03479937,0.00015267813,0.00006637708,0.00002305735,0.02807883,0.0000085066295,0.08273037,0.42812565,0.0017067316,0.42351002],"study_design_scores_gemma":[0.0004355523,0.0000026781677,0.02068117,0.0013892548,0.000064772794,0.00023226115,0.00032481735,0.0287727,0.7594414,0.16929461,0.018791912,0.0005689088],"about_ca_topic_score_codex":0.005035991,"about_ca_topic_score_gemma":0.010645034,"teacher_disagreement_score":0.67671096,"about_ca_system_score_codex":0.00039323504,"about_ca_system_score_gemma":0.00057422766,"threshold_uncertainty_score":0.9997693},"labels":[],"label_agreement":null},{"id":"W2315062801","doi":"10.5121/csit.2014.4219","title":"Off-Line System for the Recognition of Handwritten Arabic Character","year":2014,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Character (mathematics); Artificial intelligence; Intelligent word recognition; Intelligent character recognition; Arabic; Preprocessor; Handwriting recognition; Speech recognition; Handwriting; Optical character recognition; Pattern recognition (psychology); Character recognition; Feature extraction; Word (group theory); Variation (astronomy); Natural language processing; Line (geometry); Image (mathematics); Mathematics; Linguistics","score_opus":0.025827710840424685,"score_gpt":0.24901430210771253,"score_spread":0.22318659126728785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2315062801","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":[0.0047565945,0.000043911696,0.989105,0.0013324786,0.000248961,0.0005608114,0.000011532418,0.00044520939,0.0034955083],"genre_scores_gemma":[0.93444914,0.000029351713,0.06386688,0.0006448306,0.00021982082,0.00026881124,0.00001691215,0.000014375142,0.0004898901],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989257,0.000079758254,0.00034870987,0.0002612561,0.00019040308,0.00019418569],"domain_scores_gemma":[0.99845326,0.00048327516,0.00017115576,0.0004944372,0.00035133585,0.00004651835],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000913877,0.00011932908,0.00020127915,0.00009943543,0.0001050825,0.00008261173,0.0006056548,0.00007283284,0.000028961698],"category_scores_gemma":[0.00010254121,0.00007589107,0.000120521145,0.00019221856,0.00004458213,0.0003217865,0.00008683604,0.00007747028,0.00007936106],"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":[0.000012532565,0.000045410863,0.000031030777,0.00010548396,0.000024618732,3.1156594e-7,0.00008228633,5.6305953e-7,0.0044632065,0.015993908,0.0014907175,0.97774994],"study_design_scores_gemma":[0.0013801478,0.00069052377,0.0014087376,0.00036217234,0.00006881677,0.00006352679,0.0001005457,0.15427563,0.7928593,0.015503112,0.03278636,0.00050113315],"about_ca_topic_score_codex":0.000016945294,"about_ca_topic_score_gemma":0.0000073434426,"teacher_disagreement_score":0.9772488,"about_ca_system_score_codex":0.000021478034,"about_ca_system_score_gemma":0.000020460064,"threshold_uncertainty_score":0.3094748},"labels":[],"label_agreement":null},{"id":"W2331934883","doi":"10.1142/9789812701695_0001","title":"WAVELET FEATURE EXTRACTION FOR THE RECOGNITION AND VERIFICATION OF HANDWRITTEN NUMERALS","year":2005,"lang":"en","type":"book-chapter","venue":"World Scientific Publishing Company eBooks","topic":"Handwritten Text Recognition Techniques","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":"Concordia University","funders":"","keywords":"Numeral system; Pattern recognition (psychology); Computer science; Wavelet; Artificial intelligence; Feature extraction; Speech recognition","score_opus":0.051100394972569116,"score_gpt":0.26505670921861474,"score_spread":0.2139563142460456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2331934883","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020282478,0.0022868845,0.42023265,0.011133621,0.0052140206,0.005092622,0.000909277,0.0014481089,0.55348],"genre_scores_gemma":[0.023608074,0.00005215523,0.06729433,0.00056468585,0.00084276125,0.0003050746,0.0007147184,0.00009787432,0.9065203],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99685323,0.000076524375,0.0007177126,0.0011041586,0.00084214454,0.00040622192],"domain_scores_gemma":[0.9958046,0.000693129,0.0009909144,0.0012348836,0.0011265512,0.00014989465],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0026541534,0.0004233062,0.00051308854,0.0010074684,0.0008016811,0.00557057,0.0015561769,0.00035497142,0.00006424853],"category_scores_gemma":[0.0001718518,0.0003597532,0.00025997014,0.00019889462,0.00046723135,0.0021422294,0.00030381282,0.0008208909,0.0000249817],"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":[0.000021091431,0.00002656597,0.0000012879794,0.00010026979,0.00007617034,0.0000015571147,0.00048854155,9.1071695e-7,0.0018824267,0.05397794,0.14075151,0.80267173],"study_design_scores_gemma":[0.0003928279,0.00004435986,0.000060697363,0.00054449437,0.00010178523,0.000036651978,0.000020665204,0.0036405579,0.0067692595,0.091805615,0.896069,0.00051410974],"about_ca_topic_score_codex":0.00002080062,"about_ca_topic_score_gemma":0.00026924475,"teacher_disagreement_score":0.8021576,"about_ca_system_score_codex":0.00013904304,"about_ca_system_score_gemma":0.00020261611,"threshold_uncertainty_score":0.99988544},"labels":[],"label_agreement":null},{"id":"W2339619249","doi":"10.1073/pnas.1522200113","title":"Algorithmic handwriting analysis of Judah’s military correspondence sheds light on composition of biblical texts","year":2016,"lang":"en","type":"article","venue":"Proceedings of the National Academy of Sciences","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":68,"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":"European Research Council; Tel Aviv University; Azrieli Foundation; Israel Science Foundation","keywords":"Literacy; Fortress (chess); Handwriting; Demise; Composition (language); Biblical studies; Literature; History; Computer science; Ancient history; Archaeology; Art; Political science; Law","score_opus":0.027180845318661384,"score_gpt":0.3010477378835328,"score_spread":0.2738668925648714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2339619249","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":[0.9851758,0.00013440417,0.003910111,0.006320517,0.000033387078,0.00031876596,0.0000721714,0.000063684325,0.003971165],"genre_scores_gemma":[0.98473597,0.00005142817,0.0149776265,0.00015801442,0.000025513666,0.000010972134,1.8478678e-7,0.0000028834725,0.000037405345],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9970292,0.000027663102,0.00066465844,0.0003732008,0.0017320132,0.00017327044],"domain_scores_gemma":[0.99792635,0.0004998215,0.0006811713,0.000031175296,0.0008146387,0.00004685248],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002079076,0.00011986407,0.0003337029,0.0018760401,0.00012315836,0.00001699605,0.0017820727,0.0001016608,0.000037736903],"category_scores_gemma":[0.00047898843,0.0000727129,0.00020515737,0.0052863597,0.0008136742,0.0009250519,0.00027727103,0.00011682583,0.000001701388],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022916964,0.00012915133,0.002943914,0.000046530226,0.00006940514,1.4528066e-8,0.00016771833,0.000018829378,0.9417456,0.043626674,0.00043289515,0.010796387],"study_design_scores_gemma":[0.00015139638,0.00015207689,0.0483984,0.0003530272,0.000043267515,0.0000041459434,0.000025370226,0.007942377,0.9155348,0.027280305,0.000022171589,0.00009265],"about_ca_topic_score_codex":0.000008436227,"about_ca_topic_score_gemma":1.1670377e-7,"teacher_disagreement_score":0.045454487,"about_ca_system_score_codex":0.00004160644,"about_ca_system_score_gemma":0.00004706117,"threshold_uncertainty_score":0.33115643},"labels":[],"label_agreement":null},{"id":"W2342468814","doi":"10.1109/tcyb.2015.2490165","title":"Feature Set Evaluation for Offline Handwriting Recognition Systems: Application to the Recurrent Neural Network Model","year":2015,"lang":"en","type":"article","venue":"IEEE Transactions on Cybernetics","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":63,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Handwriting recognition; Pattern recognition (psychology); Recurrent neural network; Classifier (UML); Feature (linguistics); Artificial neural network; Handwriting; Benchmark (surveying); Machine learning; Feature extraction","score_opus":0.07700851734809266,"score_gpt":0.31496991498928845,"score_spread":0.23796139764119578,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2342468814","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":[0.0014922767,0.00011504336,0.9908955,0.0031881232,0.001022897,0.0026195494,0.000117766926,0.00036795228,0.00018089247],"genre_scores_gemma":[0.8851062,0.00003575401,0.11008072,0.000794511,0.00043067255,0.0031292445,0.00009557224,0.00003856664,0.0002887779],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99805796,0.00020634601,0.00033072053,0.00047808862,0.0005960216,0.00033085127],"domain_scores_gemma":[0.9979511,0.00018403461,0.00015670479,0.00055098545,0.0009807013,0.00017647959],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014595994,0.00021414601,0.0001852339,0.00012873301,0.00029195604,0.0002522579,0.00048802665,0.00014934131,0.000001947293],"category_scores_gemma":[0.000042904117,0.00018401364,0.00010162869,0.00054209784,0.000025591089,0.00026976725,0.0000060300285,0.00028577147,0.000055657416],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003090278,0.00006293994,6.9794817e-7,0.000015818256,0.000014847587,1.8612756e-7,0.00040071338,0.5551502,0.00008955062,0.00021178219,0.013091525,0.43093085],"study_design_scores_gemma":[0.00048739533,0.0002652674,0.0000035351661,0.00008835188,0.00006995549,0.000015397383,0.00007084884,0.9887458,0.003104131,0.003002888,0.0039148806,0.00023151866],"about_ca_topic_score_codex":0.000017827551,"about_ca_topic_score_gemma":0.000088238696,"teacher_disagreement_score":0.8836139,"about_ca_system_score_codex":0.00021193207,"about_ca_system_score_gemma":0.000119102326,"threshold_uncertainty_score":0.7503859},"labels":[],"label_agreement":null},{"id":"W2349309870","doi":"10.5539/jel.v5n3p122","title":"An Autonomous Learning System of Bengali Characters Using Web-Based Intelligent Handwriting Recognition","year":2016,"lang":"en","type":"article","venue":"Journal of Education and Learning","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Handwriting; Computer science; TUTOR; Population; Bengali; Handwriting recognition; Artificial intelligence; Intelligent character recognition; Speech recognition; Natural language processing; Machine learning; Multimedia; Feature extraction; Character recognition","score_opus":0.026363941849071017,"score_gpt":0.28882593892691744,"score_spread":0.2624619970778464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2349309870","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":[0.68262523,0.000097561024,0.31659505,0.0001750315,0.00024007492,0.00006244359,3.739356e-7,0.000068363035,0.00013587174],"genre_scores_gemma":[0.9610586,0.00004060454,0.038630296,0.000052637402,0.00016582437,0.0000031320285,0.0000018209257,0.0000118566295,0.0000351913],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99839646,0.00049953535,0.0005744114,0.00016591561,0.0002140297,0.00014964241],"domain_scores_gemma":[0.9979316,0.00022998363,0.0010069918,0.00010532476,0.0005920448,0.00013404638],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016107422,0.00011060084,0.00021954389,0.00047528997,0.00019408598,0.000126914,0.00019724538,0.00006828245,0.000025123314],"category_scores_gemma":[0.0003449594,0.000088301495,0.000075091695,0.0001967129,0.00003747385,0.0008543297,0.000022252156,0.00033182805,0.0000037063069],"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":[0.000014591581,0.000113296206,0.004379933,0.00008478655,0.000016196958,0.0000027550789,0.001286367,0.000101120764,0.09980922,0.00020423802,0.000009000152,0.8939785],"study_design_scores_gemma":[0.004268828,0.005144512,0.026640171,0.021974003,0.0002936715,0.0025269864,0.034129966,0.25341898,0.6403665,0.0010111294,0.008334975,0.0018902728],"about_ca_topic_score_codex":0.0000140251295,"about_ca_topic_score_gemma":6.878649e-7,"teacher_disagreement_score":0.89208823,"about_ca_system_score_codex":0.00014753814,"about_ca_system_score_gemma":0.00040843026,"threshold_uncertainty_score":0.36008304},"labels":[],"label_agreement":null},{"id":"W2350017110","doi":"","title":"A System of Table Line Processing that Base on the One—way and Quasi Connection","year":2006,"lang":"en","type":"article","venue":"Microcomputer applications","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Table (database); Line (geometry); Connection (principal bundle); Process (computing); Base (topology); Artificial intelligence; Algorithm; Data mining; Programming language; Mathematics; Geometry","score_opus":0.018042031138931026,"score_gpt":0.23247059330366762,"score_spread":0.2144285621647366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2350017110","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":[0.0063596657,0.00012377156,0.99010205,0.00087258656,0.000008096169,0.0007444458,0.000009092123,0.00037405762,0.0014062318],"genre_scores_gemma":[0.779088,0.0000057209454,0.22001831,0.00022284793,0.00008559573,0.0004914866,0.000010329223,0.000010258239,0.0000674524],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990825,0.000050749033,0.0002428859,0.00033209578,0.00014056798,0.00015117103],"domain_scores_gemma":[0.9991729,0.00012353736,0.00016813594,0.00035469804,0.00014693793,0.000033749962],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002544259,0.000119155826,0.00014605705,0.000114465205,0.00024155616,0.00016546452,0.0003916213,0.00005459827,0.0000032356133],"category_scores_gemma":[7.0750593e-7,0.000095077055,0.00003521056,0.00041170884,0.0000579275,0.00018268128,0.00011525201,0.000103656224,0.000017402612],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000067504707,0.0006927987,0.00019750212,0.00035767813,0.000023640174,0.0000014245592,0.00035285554,0.000046514768,0.0663278,0.26329532,0.0032094736,0.66548824],"study_design_scores_gemma":[0.0005921956,0.00020823246,0.0014680091,0.00048374783,0.00003523303,0.00010932253,0.00015066468,0.07384766,0.8584199,0.011407683,0.052790873,0.00048648173],"about_ca_topic_score_codex":0.000058093217,"about_ca_topic_score_gemma":0.000008469355,"teacher_disagreement_score":0.7920921,"about_ca_system_score_codex":0.0000397708,"about_ca_system_score_gemma":0.00002964512,"threshold_uncertainty_score":0.387713},"labels":[],"label_agreement":null},{"id":"W2358096917","doi":"","title":"Text Information Extraction in Colorful Scene Image Based on Mean-Shift Algorithm","year":2009,"lang":"en","type":"article","venue":"Microcomputer applications","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Mean-shift; Semantics (computer science); Artificial intelligence; Information extraction; Image (mathematics); Annotation; Algorithm; Projection (relational algebra); Pattern recognition (psychology); Computer vision; Natural language processing; Information retrieval","score_opus":0.006564150840877742,"score_gpt":0.2538023095956642,"score_spread":0.24723815875478644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2358096917","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":[0.00027221505,0.000009764935,0.99184936,0.0024294525,0.000022486178,0.0010521081,0.00001318225,0.0006665975,0.0036848465],"genre_scores_gemma":[0.06466754,0.000008567515,0.9309379,0.003714366,0.00007990342,0.00046529912,0.0000935095,0.000008571557,0.000024346878],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985477,0.000061227125,0.00045977542,0.00039017174,0.00024586482,0.0002952977],"domain_scores_gemma":[0.9989659,0.00008696379,0.00016530909,0.0005407857,0.0001468336,0.00009416105],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029111307,0.00020406711,0.00017625048,0.00057573855,0.00015084527,0.00035008343,0.00070771633,0.00012597746,0.000026819134],"category_scores_gemma":[0.0000015999744,0.00022114605,0.00007664608,0.0008914379,0.000031849282,0.001419581,0.00006175199,0.00026831342,0.0007737722],"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":[0.0000032746445,0.00025134606,0.000009116437,0.0000063296097,0.000001994902,0.0000018373764,0.0001716638,0.00003704675,0.0018917125,0.0023100083,0.0020223742,0.9932933],"study_design_scores_gemma":[0.001782273,0.00041784762,0.015549842,0.000122319,0.0000117784375,0.00004304087,0.000019378143,0.5031473,0.10620368,0.018659668,0.35308135,0.000961524],"about_ca_topic_score_codex":0.000019672014,"about_ca_topic_score_gemma":0.000004842173,"teacher_disagreement_score":0.99233174,"about_ca_system_score_codex":0.00017036799,"about_ca_system_score_gemma":0.000072219394,"threshold_uncertainty_score":0.99455345},"labels":[],"label_agreement":null},{"id":"W2396383033","doi":"","title":"A ROBUST BORDER DETECTION ALGORITHM WITH APPLICATION TO MEDIEVAL MUSIC MANUSCRIPTS","year":2009,"lang":"en","type":"article","venue":"Bern Open Repository and Information System (University of Bern)","topic":"Handwritten Text Recognition Techniques","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":"Social Sciences and Humanities Research Council of Canada","keywords":"Computer science; Musical; Natural (archaeology); Process (computing); Simple (philosophy); Artificial intelligence; Image (mathematics); Algorithm; Computer vision; Art; Programming language; Visual arts; Archaeology; History","score_opus":0.010896574013397924,"score_gpt":0.19550014137614113,"score_spread":0.18460356736274322,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2396383033","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":[0.019590808,0.0000058458913,0.96233463,0.0001900233,0.00006702168,0.00071792176,0.000005504548,0.00017713904,0.016911082],"genre_scores_gemma":[0.9218424,0.0000031938484,0.07752017,0.00017832393,0.000021073492,0.0000052623463,0.000011782433,0.0000030681028,0.00041471238],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991571,0.00005618578,0.00021122642,0.00019199251,0.00026791485,0.00011561268],"domain_scores_gemma":[0.99900436,0.000011898436,0.00027563647,0.0003024515,0.00030031073,0.00010531745],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028927156,0.00010439549,0.0001730984,0.00019503284,0.00033774262,0.0002231716,0.000533395,0.00007603508,0.0000040104774],"category_scores_gemma":[0.0000021838534,0.00011077381,0.000028414053,0.0003327332,0.000028373433,0.0052068797,0.00016820472,0.00006974419,0.000029315208],"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":[0.00014432383,0.000052593627,0.00014672008,0.00013086674,0.00004196004,0.000012868976,0.0060761245,0.00006938693,0.0014459883,0.00415601,0.0005774356,0.9871457],"study_design_scores_gemma":[0.0126415575,0.0072430293,0.18919179,0.002809446,0.00039574548,0.003898862,0.042451147,0.50156206,0.10176257,0.0006073711,0.13350049,0.0039359387],"about_ca_topic_score_codex":0.0003748562,"about_ca_topic_score_gemma":0.000025499783,"teacher_disagreement_score":0.9832098,"about_ca_system_score_codex":0.000087194996,"about_ca_system_score_gemma":0.000039730803,"threshold_uncertainty_score":0.4517225},"labels":[],"label_agreement":null},{"id":"W2401704894","doi":"10.5281/zenodo.1415579","title":"Automatic Pitch Detection In Printed Square Notation.","year":2011,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Notation; Computer science; Square (algebra); Speech recognition; Arithmetic; Mathematics; Geometry","score_opus":0.04102528881559375,"score_gpt":0.24286202755136185,"score_spread":0.2018367387357681,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2401704894","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":[0.07512362,0.000020981879,0.84028596,0.00027797517,0.00012647072,0.00080797344,0.000015825342,0.0048082476,0.07853294],"genre_scores_gemma":[0.9883657,0.000014704008,0.010988585,0.00009096172,0.00002406377,2.2656971e-7,0.000069298025,0.0003505126,0.000095911455],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99847025,0.00031363958,0.00028502618,0.00038062598,0.00027454685,0.00027590708],"domain_scores_gemma":[0.99889433,0.000019283973,0.000101322905,0.00045511316,0.00042811877,0.00010181374],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0006229096,0.00011442692,0.00011250462,0.00046582383,0.00063958444,0.00044049002,0.001139374,0.00006331529,0.0043460447],"category_scores_gemma":[0.00038444408,0.00012540982,0.00003792868,0.0009884847,0.00006116647,0.00066740334,0.00070403225,0.00022161736,0.0045810756],"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":[0.000010144681,0.00016324135,0.000008805989,0.00004343493,0.000009792852,0.000016959439,0.0034067142,0.0000017237359,0.0040781107,0.0048562386,0.002320942,0.9850839],"study_design_scores_gemma":[0.0034283863,0.0022562097,0.055250123,0.00051454536,0.00003204375,0.00096471305,0.001488026,0.12668487,0.24073318,0.02742731,0.5393671,0.0018534842],"about_ca_topic_score_codex":0.00003315875,"about_ca_topic_score_gemma":0.0000018990928,"teacher_disagreement_score":0.9832304,"about_ca_system_score_codex":0.00015102574,"about_ca_system_score_gemma":0.0000038294297,"threshold_uncertainty_score":0.9965641},"labels":[],"label_agreement":null},{"id":"W2402361188","doi":"","title":"Recommendation systems in mathematical character recognition.","year":2013,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Handwriting; Character (mathematics); Computer science; Intelligent character recognition; Natural language processing; Handwriting recognition; Artificial intelligence; Character recognition; Linguistics; Psychology; Mathematics; Feature extraction","score_opus":0.02847597501542912,"score_gpt":0.2519982296700952,"score_spread":0.2235222546546661,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2402361188","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":[0.015197538,0.000005592294,0.9107669,0.0031819455,0.00017837221,0.000709561,0.0000018407704,0.0006876652,0.069270566],"genre_scores_gemma":[0.753051,0.00004090353,0.24205987,0.0019661016,0.00011752562,0.0012827673,0.00005365021,0.000022521814,0.0014056826],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990265,0.00008721911,0.00033088014,0.0002425726,0.000118250144,0.00019457273],"domain_scores_gemma":[0.9994279,0.00010160924,0.000061813385,0.00022658707,0.00011723541,0.00006481437],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0003271118,0.00009470001,0.00013411834,0.00019676343,0.000029167542,0.00029365855,0.0002683907,0.00007117439,0.0035553202],"category_scores_gemma":[0.00004799862,0.00008105143,0.000029519726,0.00025272073,0.000013195722,0.0013220451,0.00007988858,0.00011192296,0.006232446],"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":[9.2100464e-7,0.00018767136,0.00019147109,0.000041930536,0.0000069251287,0.0000036436077,0.00020951922,1.5452306e-7,0.0014146648,0.023663165,0.0091743395,0.9651056],"study_design_scores_gemma":[0.0016448091,0.00031522856,0.0126410555,0.0004866676,0.000010256311,0.00032060393,0.00040701483,0.26655132,0.0404101,0.65145534,0.024046602,0.0017110303],"about_ca_topic_score_codex":0.00008862777,"about_ca_topic_score_gemma":0.0000028655916,"teacher_disagreement_score":0.9633946,"about_ca_system_score_codex":0.00004585113,"about_ca_system_score_gemma":0.000013859359,"threshold_uncertainty_score":0.9973556},"labels":[],"label_agreement":null},{"id":"W244376972","doi":"10.1007/978-3-319-11737-9_21","title":"On the Formal Analysis of HMM Using Theorem Proving","year":2014,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","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":"Concordia University","funders":"","keywords":"Hidden Markov model; Computer science; Mathematics; Natural language processing; Artificial intelligence","score_opus":0.019743993375926982,"score_gpt":0.25327196177820066,"score_spread":0.2335279684022737,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W244376972","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":[0.0008653907,0.0000417324,0.99438673,0.00025718898,0.0002959362,0.0003680509,0.0000050765125,0.00013802522,0.003641841],"genre_scores_gemma":[0.7180484,0.000007982565,0.28013098,0.0015808262,0.00012705644,0.000008275712,0.0000030122208,0.000023671117,0.00006978101],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968513,0.00008229154,0.00056785427,0.0009696699,0.001014952,0.00051389955],"domain_scores_gemma":[0.99624497,0.0012855091,0.0005180297,0.0015558645,0.0003132739,0.000082355364],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0021605897,0.00039685017,0.00062839704,0.0017762101,0.00027604096,0.00034919754,0.0034710527,0.00022983532,0.000036686062],"category_scores_gemma":[0.00019428671,0.00027185955,0.000298293,0.0015478273,0.0007401825,0.00038898355,0.0011273068,0.0006204953,0.000008958795],"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":[0.0000044696685,0.000018185063,0.000028390972,0.000023514518,0.000084500265,0.000009551495,0.0004932619,0.015397386,0.00030136795,0.3366941,0.000007036416,0.64693826],"study_design_scores_gemma":[0.000060065064,0.00013084339,0.000041147083,0.00027753762,0.000065086664,0.0000108136155,1.2714708e-7,0.78254354,0.008160744,0.20831938,0.000071952294,0.00031875193],"about_ca_topic_score_codex":0.00002646541,"about_ca_topic_score_gemma":0.000043661512,"teacher_disagreement_score":0.76714617,"about_ca_system_score_codex":0.00017591163,"about_ca_system_score_gemma":0.000269775,"threshold_uncertainty_score":0.99997336},"labels":[],"label_agreement":null},{"id":"W2475693720","doi":"10.4018/978-1-59904-807-9.ch003","title":"State of the Art in Off-Line Signature Verification","year":2008,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Defence Research and Development Canada; École de Technologie Supérieure","funders":"","keywords":"Signature (topology); Computer science; Biometrics; Field (mathematics); Face (sociological concept); State (computer science); Data mining; Feature extraction; Feature (linguistics); Digital signature; Line (geometry); Artificial intelligence; Pattern recognition (psychology); Computer security; Algorithm; Mathematics","score_opus":0.016710659542468476,"score_gpt":0.23928067619746682,"score_spread":0.22257001665499834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2475693720","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00016845136,0.00044981093,0.01286957,0.00019204943,0.00026237316,0.00060981035,0.00013030846,0.00022289973,0.9850947],"genre_scores_gemma":[0.6354059,0.0005608783,0.029140504,0.0031870822,0.00032365342,0.00013546101,0.000035209723,0.00013279436,0.33107853],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984751,0.00003785939,0.00045088417,0.0004097399,0.00043402257,0.00019243443],"domain_scores_gemma":[0.99854684,0.000027645205,0.0003471976,0.00084368006,0.00018231213,0.00005234155],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001395772,0.00025630137,0.00031368123,0.000093059534,0.000043099,0.000034623456,0.0010620367,0.00027709093,0.000009190528],"category_scores_gemma":[0.000018662096,0.00020831414,0.00016315331,0.00006153328,0.0001250767,0.00008056319,0.00024825873,0.00040184433,0.000071977665],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016156324,0.0000301842,0.000010690697,0.000038262853,0.000032194705,0.00005358568,0.00017418759,0.000008444516,0.00029202065,0.72097296,0.013918792,0.26445255],"study_design_scores_gemma":[0.00047957493,0.00016247871,0.00039528956,0.0008107049,0.000020986527,0.00012636144,0.0000015975451,0.00047543456,0.016323315,0.8125366,0.1679831,0.00068458664],"about_ca_topic_score_codex":0.00001637729,"about_ca_topic_score_gemma":0.00007661156,"teacher_disagreement_score":0.6540162,"about_ca_system_score_codex":0.0001540872,"about_ca_system_score_gemma":0.00022298966,"threshold_uncertainty_score":0.8494804},"labels":[],"label_agreement":null},{"id":"W2494353616","doi":"10.4018/978-1-4666-3970-6.ch005","title":"Selection of an Optimal Set of Features for Bengali Character Recognition","year":2013,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Francis Xavier University","funders":"","keywords":"Bengali; Artificial intelligence; Computer science; Classifier (UML); Character encoding; Alphabet; Character (mathematics); Pattern recognition (psychology); Feature (linguistics); Set (abstract data type); Natural language processing; Feature selection; Consonant; Mathematics; Speech recognition; Vowel; Linguistics","score_opus":0.026703715638455618,"score_gpt":0.2670353191727851,"score_spread":0.2403316035343295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2494353616","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031233414,0.00008265593,0.09293498,0.000084999134,0.00055927224,0.002599704,0.0017858604,0.0007323318,0.89809686],"genre_scores_gemma":[0.2636001,0.00003986365,0.6858103,0.0009016996,0.0016464781,0.0007455473,0.0006376358,0.00022789749,0.04639048],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982497,0.000040125557,0.0005622432,0.0005374242,0.00035398916,0.00025649328],"domain_scores_gemma":[0.9979026,0.000053337735,0.0006567437,0.00043890643,0.00083712145,0.00011130331],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00022595517,0.00035167925,0.0005279575,0.0001828781,0.00006215511,0.00008439299,0.00057533034,0.0005562511,0.00009149517],"category_scores_gemma":[0.000024593137,0.00035808893,0.0002697673,0.000034664146,0.000085861946,0.00033932336,0.000114562885,0.00023605967,0.00003163434],"study_design_candidate":"theoretical_or_conceptual","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":[0.00008939726,0.00003883416,0.0000017735388,0.00022550294,0.0001359502,0.000003228478,0.00013150461,4.807286e-7,0.0020961037,0.47999406,0.0040369793,0.5132462],"study_design_scores_gemma":[0.0008882128,0.0021774613,0.00013951349,0.00088330905,0.00017894046,0.00018576186,0.000012442281,0.00075063645,0.24324818,0.7401454,0.010293124,0.0010970323],"about_ca_topic_score_codex":0.00005009386,"about_ca_topic_score_gemma":0.00002395487,"teacher_disagreement_score":0.8517064,"about_ca_system_score_codex":0.00009951001,"about_ca_system_score_gemma":0.00013749937,"threshold_uncertainty_score":0.9998871},"labels":[],"label_agreement":null},{"id":"W2496788274","doi":"10.1080/10798587.2016.1210257","title":"Comparing the Machine Ability to Recognize Hand-Written Hindu and Arabic Digits","year":2016,"lang":"en","type":"article","venue":"Intelligent Automation & Soft Computing","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Arabic; Hinduism; Artificial intelligence; Speech recognition; Natural language processing; Linguistics; Philosophy","score_opus":0.03010893928752632,"score_gpt":0.27136043018663214,"score_spread":0.24125149089910583,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2496788274","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":[0.29624242,0.000072599454,0.69783497,0.003984327,0.00020071106,0.00042399773,0.0000030488732,0.00089494686,0.00034295485],"genre_scores_gemma":[0.9683491,0.000012817978,0.030708784,0.00070796325,0.00009588465,0.000026017506,0.00000310342,0.000017993432,0.00007831231],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977257,0.00023209116,0.0006031835,0.00063494436,0.00039204786,0.00041198617],"domain_scores_gemma":[0.9976336,0.0010639447,0.00023735342,0.00059583155,0.0002928283,0.00017643684],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014309086,0.00025960474,0.00029094133,0.00019025392,0.00046113526,0.00065694185,0.0008744863,0.00008136428,0.000028954699],"category_scores_gemma":[0.00065697334,0.00016511432,0.00008672813,0.0004672763,0.00012376768,0.0006011215,0.0007179095,0.0001847555,0.00023806609],"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":[0.000005304125,0.000042576154,0.008657085,0.000022695498,0.00001655866,0.000002335875,0.0011861013,0.00004517863,0.0032184084,0.0016680537,0.0004448618,0.98469085],"study_design_scores_gemma":[0.0008882291,0.00031489247,0.084515706,0.0012579499,0.000035396195,0.00018938244,0.00011776651,0.6618736,0.20868286,0.02784219,0.012919931,0.0013621207],"about_ca_topic_score_codex":0.00003940114,"about_ca_topic_score_gemma":0.00003050909,"teacher_disagreement_score":0.9833287,"about_ca_system_score_codex":0.00013475513,"about_ca_system_score_gemma":0.000044485783,"threshold_uncertainty_score":0.67331666},"labels":[],"label_agreement":null},{"id":"W2525112519","doi":"10.21700/ijcis.2016.103","title":"Word Extraction and Recognition in Arabic Handwritten Text","year":2016,"lang":"en","type":"article","venue":"International Journal of Computing and Information Sciences","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Arabic; Natural language processing; Word (group theory); Computer science; Artificial intelligence; Word recognition; Speech recognition; Linguistics; Reading (process)","score_opus":0.019484836446898395,"score_gpt":0.2985998062361725,"score_spread":0.2791149697892741,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2525112519","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":[0.49125668,0.000052605363,0.5038433,0.0033385584,0.00039487638,0.00004593871,0.0000010954794,0.000029602572,0.0010373571],"genre_scores_gemma":[0.9731513,0.00033777294,0.026063358,0.0003671686,0.000070826594,8.206157e-7,4.4527437e-7,0.0000011537089,0.000007116069],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9988249,0.000049857914,0.00051072694,0.00009163259,0.0004184763,0.00010442999],"domain_scores_gemma":[0.99879354,0.00024536822,0.00044123092,0.00004301234,0.0004261176,0.000050700404],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013449574,0.00006848478,0.000101104335,0.0006921574,0.00007510974,0.0004005236,0.0003496928,0.000036207533,0.000008794383],"category_scores_gemma":[0.00025635102,0.0000459207,0.000025481962,0.00022195232,0.00010986461,0.00730852,0.00008706135,0.00008606865,0.000008889687],"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":[0.0000075032135,0.000010267999,0.0017698214,0.000002496852,0.00000473199,0.0000022655568,0.00052191,0.000005048733,0.00038754707,0.0012853469,0.00008338205,0.9959197],"study_design_scores_gemma":[0.010065068,0.0020706444,0.51331335,0.0060086027,0.000029094306,0.0092946505,0.0028295808,0.120404325,0.05893297,0.2415217,0.033823974,0.0017060263],"about_ca_topic_score_codex":0.000012061888,"about_ca_topic_score_gemma":0.000002321407,"teacher_disagreement_score":0.99421364,"about_ca_system_score_codex":0.000038844486,"about_ca_system_score_gemma":0.00005584635,"threshold_uncertainty_score":0.52985007},"labels":[],"label_agreement":null},{"id":"W2525631569","doi":"10.21700/ijcis.2016.104","title":"Automatic Script and Type Identification in Bi-lingual Forms","year":2016,"lang":"en","type":"article","venue":"International Journal of Computing and Information Sciences","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Identification (biology); Type (biology); Computer science; Natural language processing; Artificial intelligence; Biology","score_opus":0.01826649669564782,"score_gpt":0.3110490505737062,"score_spread":0.29278255387805835,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2525631569","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":[0.7328486,0.000041987467,0.2644639,0.0017206959,0.00043246904,0.000037325764,5.383385e-7,0.000028815095,0.00042569428],"genre_scores_gemma":[0.98701906,0.00011296322,0.01256371,0.00026235648,0.00003503027,3.4942826e-7,2.879379e-7,8.950282e-7,0.000005358205],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988646,0.000028554297,0.00053544034,0.0000704597,0.00041411538,0.000086816995],"domain_scores_gemma":[0.9988977,0.00013120039,0.00043318828,0.00004781655,0.00045058035,0.000039535436],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014257635,0.000054022727,0.00008469551,0.00057042827,0.000067206776,0.00043071888,0.00044501678,0.000024723866,0.0000053041017],"category_scores_gemma":[0.00034560292,0.000034145385,0.000017294604,0.00024362572,0.00009815419,0.0052477345,0.00010195402,0.000053822863,0.0000062937565],"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":[0.0000028059194,0.00000869233,0.0031379664,0.000004375861,0.0000053673803,0.0000013876181,0.001125331,0.000008676186,0.00047843176,0.011362404,0.00007724797,0.9837873],"study_design_scores_gemma":[0.003598355,0.0011300487,0.3445765,0.00231165,0.000013363874,0.0024411848,0.0017705921,0.4808414,0.04152846,0.11139028,0.009629796,0.0007683486],"about_ca_topic_score_codex":0.0000052408786,"about_ca_topic_score_gemma":0.000001059079,"teacher_disagreement_score":0.983019,"about_ca_system_score_codex":0.000031227028,"about_ca_system_score_gemma":0.000076357224,"threshold_uncertainty_score":0.4153432},"labels":[],"label_agreement":null},{"id":"W2545629393","doi":"10.1109/icaetr.2014.7012888","title":"Comparison of smoothing techniques and recognition methods for online Kannada character recognition system","year":2014,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":9,"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":"Vector Institute","keywords":"Computer science; Smoothing; Artificial intelligence; Pattern recognition (psychology); Character (mathematics); Optical character recognition; Normalization (sociology); Support vector machine; Speech recognition; Handwriting recognition; Character recognition; Segmentation; Offset (computer science); Feature extraction; Computer vision; Mathematics","score_opus":0.06730922071027931,"score_gpt":0.38179800464035046,"score_spread":0.3144887839300712,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2545629393","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":[0.012731514,0.00005261334,0.9825968,0.00026795376,0.00014822718,0.0007056595,0.000030696807,0.0010956381,0.0023708686],"genre_scores_gemma":[0.11375076,0.000019893072,0.88558686,0.00018943523,0.00011725493,0.00017174719,0.00010401314,0.000019242663,0.000040792394],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99817085,0.00032921208,0.0006547851,0.0004476999,0.0001616049,0.00023583032],"domain_scores_gemma":[0.9981346,0.0005841324,0.00038039524,0.00032950545,0.00048290883,0.00008846093],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016370742,0.00019715905,0.0004543194,0.00029140536,0.00010703853,0.0001102521,0.00031527993,0.00017160008,0.000011481074],"category_scores_gemma":[0.00018104711,0.00018339655,0.00009217764,0.00023051279,0.000052533003,0.0006693945,0.00012210455,0.00015514452,0.000005497592],"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":[0.00001096425,0.000076534925,0.000039518494,0.00023402582,0.000012316708,2.422884e-7,0.00013826891,1.8550097e-8,0.009153683,0.0014149855,0.00019641747,0.98872304],"study_design_scores_gemma":[0.00038282186,0.00052592275,0.0001033495,0.0005150375,0.000035158675,0.000045349625,0.00010890852,0.03417337,0.9322966,0.022834266,0.008626423,0.00035280728],"about_ca_topic_score_codex":0.00006400649,"about_ca_topic_score_gemma":0.0000117328445,"teacher_disagreement_score":0.98837024,"about_ca_system_score_codex":0.000043839093,"about_ca_system_score_gemma":0.000022112856,"threshold_uncertainty_score":0.74786943},"labels":[],"label_agreement":null},{"id":"W2548004707","doi":"","title":"Improvement in handwritten numeral string recognition by slant normalization and contextual information","year":2004,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Numeral system; Normalization (sociology); NIST; String (physics); Pattern recognition (psychology); Artificial intelligence; Computer science; Speech recognition; Segmentation; Mathematics","score_opus":0.008501452204767307,"score_gpt":0.21589041113391097,"score_spread":0.20738895892914366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2548004707","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":[0.15430038,0.000022668337,0.8432971,0.0005036815,0.000052877615,0.00035198094,0.000010871262,0.00026755407,0.0011928458],"genre_scores_gemma":[0.9775495,0.000084073385,0.021185577,0.0009647889,0.000013648867,0.00006435607,0.000109440276,0.0000046477467,0.000023945204],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99904686,0.000022798102,0.00035633726,0.00018261696,0.00018949594,0.0002019133],"domain_scores_gemma":[0.99960434,0.000014403756,0.000093641975,0.00012648395,0.00009803893,0.00006305928],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025836573,0.000117130214,0.00011408824,0.0002091413,0.00006797223,0.00024689565,0.0001559471,0.00007170507,0.000019297147],"category_scores_gemma":[0.000028292377,0.000113807946,0.000019611807,0.00024333819,0.000020962745,0.0029649641,0.000094553,0.000097650656,0.00003608955],"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":[0.000012855722,0.00008324359,0.00052954996,0.000032005206,0.000008242462,0.0000030253598,0.0011721627,0.000010343889,0.0062351734,0.009677801,0.0005559325,0.9816797],"study_design_scores_gemma":[0.011346751,0.0015887237,0.0064129345,0.000523035,0.000019672505,0.0001263593,0.0010987752,0.023976963,0.8658287,0.08248589,0.0049033347,0.0016888785],"about_ca_topic_score_codex":0.00047534448,"about_ca_topic_score_gemma":0.00009278636,"teacher_disagreement_score":0.9799908,"about_ca_system_score_codex":0.00009991431,"about_ca_system_score_gemma":0.000034323708,"threshold_uncertainty_score":0.46409532},"labels":[],"label_agreement":null},{"id":"W2557666158","doi":"10.1109/cec.2016.7744000","title":"Bio-inspired BAT optimization algorithm for handwritten Arabic characters recognition","year":2016,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Artificial intelligence; Character (mathematics); Pattern recognition (psychology); Handwriting recognition; Naive Bayes classifier; Artificial neural network; Feature (linguistics); Set (abstract data type); Arabic; Handwriting; Variation (astronomy); Feature extraction; Algorithm; Support vector machine; Mathematics","score_opus":0.02124833557189377,"score_gpt":0.24225537573486386,"score_spread":0.2210070401629701,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2557666158","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":[0.00057234213,0.000014419402,0.99308383,0.0029832565,0.00030891856,0.0007034532,0.000042437878,0.001336946,0.0009544025],"genre_scores_gemma":[0.01327001,0.00015050509,0.9832154,0.0012390901,0.0001915977,0.0004890148,0.00008312885,0.00003243426,0.0013288306],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983894,0.000065557615,0.0003674533,0.00057128235,0.0002291058,0.00037715334],"domain_scores_gemma":[0.9987103,0.00018812904,0.00015447054,0.0004155969,0.0003960241,0.00013551007],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038192063,0.00020948431,0.0002112859,0.00028565148,0.00015424064,0.00019121668,0.0005066034,0.00014514888,0.00017461629],"category_scores_gemma":[0.00009442751,0.00014912177,0.00013194149,0.00032348203,0.000054964905,0.0015752115,0.00009524347,0.0000546943,0.00021748633],"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":[0.000005090189,0.00004959469,0.00001399646,0.000006846022,0.000014076251,0.0000016610703,0.00002892094,7.255421e-7,0.0030620815,0.0003976348,0.0014445921,0.9949748],"study_design_scores_gemma":[0.0046905214,0.0010018324,0.00061838306,0.00046997165,0.000057265177,0.000089110785,0.000035513545,0.29019445,0.65715975,0.033653155,0.01031824,0.001711837],"about_ca_topic_score_codex":0.000008265871,"about_ca_topic_score_gemma":0.000002528113,"teacher_disagreement_score":0.99326295,"about_ca_system_score_codex":0.000089804766,"about_ca_system_score_gemma":0.000050397975,"threshold_uncertainty_score":0.60810095},"labels":[],"label_agreement":null},{"id":"W2573517006","doi":"10.21700/ijcis.2016.124","title":"Audio-Textual Classification System Design for Arabic News Videos","year":2016,"lang":"en","type":"article","venue":"International Journal of Computing and Information Sciences","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Arabic; Computer science; Multimedia; Audio visual; Natural language processing; Speech recognition; Linguistics","score_opus":0.04278800917725355,"score_gpt":0.3099066852825845,"score_spread":0.26711867610533097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2573517006","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":[0.010598111,0.000020169487,0.9843258,0.0031908369,0.00061365723,0.00012241074,0.0000025270174,0.00007315177,0.0010532968],"genre_scores_gemma":[0.8642806,0.00003844254,0.13522056,0.00030247844,0.0001446571,0.0000031948723,5.6411807e-7,0.0000015634929,0.000007971576],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998477,0.00006725708,0.00066389714,0.00010405861,0.00056066015,0.00012713927],"domain_scores_gemma":[0.99739116,0.00051770365,0.00082272885,0.00007678739,0.0011267436,0.000064901615],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018830001,0.000081672275,0.00012475402,0.00045840384,0.0001619379,0.00052005687,0.00085700623,0.00003865169,0.0000026395783],"category_scores_gemma":[0.0003609529,0.00005159174,0.00006118426,0.00018054087,0.00010097418,0.005142215,0.00007566752,0.00005029384,0.000011614583],"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":[0.000020076448,0.000013617428,0.00032866083,0.000011342295,0.000023207747,7.3438434e-7,0.00055383,0.000120745804,0.0009043099,0.12307524,0.0018076071,0.87314063],"study_design_scores_gemma":[0.0044318903,0.002094285,0.011031006,0.002279596,0.00003250371,0.0022345097,0.0039358805,0.8606494,0.04597641,0.024413718,0.042059775,0.00086101453],"about_ca_topic_score_codex":0.0000032597588,"about_ca_topic_score_gemma":2.53124e-7,"teacher_disagreement_score":0.8722796,"about_ca_system_score_codex":0.00008298141,"about_ca_system_score_gemma":0.00015468289,"threshold_uncertainty_score":0.501492},"labels":[],"label_agreement":null},{"id":"W2577349305","doi":"","title":"Training & Quality Assessment of an Optical Character Recognition Model for Northern Haida.","year":2016,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":8,"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":"Optical character recognition; Computer science; Character (mathematics); Language model; Unicode; Porting; Artificial intelligence; Natural language processing; Hidden Markov model; Speech recognition; Set (abstract data type); Image (mathematics)","score_opus":0.12266473322717336,"score_gpt":0.38797495915431435,"score_spread":0.265310225927141,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2577349305","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":[0.5494052,0.000020214133,0.44986635,0.00016343247,0.000012750772,0.00021591144,0.000015984739,0.000052324154,0.00024779956],"genre_scores_gemma":[0.89926636,0.000007110665,0.10041912,0.00007082118,0.000057101464,0.000106463944,0.000030938245,0.000007057726,0.000035041834],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988783,0.00014900265,0.00025644427,0.00025810732,0.0003238359,0.00013433804],"domain_scores_gemma":[0.9991954,0.00015576436,0.00014464831,0.00020830099,0.0002371745,0.000058715555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019998343,0.00008227371,0.00014140774,0.000071189905,0.000058497997,0.00005442922,0.00013358574,0.000062401625,0.000020489093],"category_scores_gemma":[0.00013206212,0.00005870962,0.000043256747,0.00005849314,0.0000320948,0.0004420023,0.00003415371,0.00003743924,0.0000014750748],"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":[0.000009485324,0.00003286807,0.00010664787,0.000016577904,0.000006971291,1.9982068e-7,0.0044937325,0.000008503348,0.022796053,0.00028420988,0.0000015533025,0.9722432],"study_design_scores_gemma":[0.00093292934,0.00022495356,0.009958346,0.00010819838,0.00003125879,0.0000049847913,0.00051712815,0.9643353,0.011937032,0.01172173,0.000038334612,0.0001897604],"about_ca_topic_score_codex":0.000019042835,"about_ca_topic_score_gemma":0.000073229814,"teacher_disagreement_score":0.9720534,"about_ca_system_score_codex":0.000034000364,"about_ca_system_score_gemma":0.000045718807,"threshold_uncertainty_score":0.23941088},"labels":[],"label_agreement":null},{"id":"W2582767714","doi":"","title":"Wortelonkruiden aanpakken : PPO test Canadese Rod Weeder om wortelonkruiden mechanisch te bestrijden","year":2010,"lang":"nl","type":"article","venue":"Boerderij","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Test (biology); Biology; Botany","score_opus":0.014737584600896827,"score_gpt":0.2551702044369272,"score_spread":0.24043261983603034,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2582767714","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":[0.2396709,0.005535998,0.43364096,0.1004275,0.035743386,0.01766762,0.0021018542,0.017374586,0.1478372],"genre_scores_gemma":[0.9173484,0.0002610628,0.04882442,0.0029631802,0.0023018601,0.00039584088,0.00010172738,0.00029873662,0.02750479],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9911003,0.00031432416,0.0018212185,0.0025431141,0.0018497854,0.0023712574],"domain_scores_gemma":[0.9923855,0.00094742904,0.00081926334,0.0033665348,0.0010393193,0.0014419525],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","insufficient_payload"],"category_scores_codex":[0.0017882964,0.0013793719,0.0013057364,0.0008868227,0.0010434756,0.0021746359,0.004499021,0.0012801666,0.0048490525],"category_scores_gemma":[0.0016538778,0.0014682754,0.0005273484,0.0020831276,0.00046481978,0.0020328546,0.001776005,0.0027302306,0.0058234693],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007769976,0.0018620666,0.0068484275,0.00035625842,0.00061981665,0.002247009,0.0033778625,0.000006162313,0.082748465,0.016294673,0.34951094,0.5360506],"study_design_scores_gemma":[0.004940662,0.002357665,0.016860686,0.0016056625,0.0008795619,0.002226636,0.0017144025,0.017715575,0.24460834,0.03855265,0.65904015,0.009497999],"about_ca_topic_score_codex":0.013023186,"about_ca_topic_score_gemma":0.025613453,"teacher_disagreement_score":0.6776775,"about_ca_system_score_codex":0.0002982693,"about_ca_system_score_gemma":0.002023405,"threshold_uncertainty_score":0.9998957},"labels":[],"label_agreement":null},{"id":"W2586783582","doi":"10.1109/icpr.1992.201787","title":"Analysis and recognition of alphanumeric handprints by parts","year":2003,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Alphanumeric; Character (mathematics); Computer science; Handwriting; Set (abstract data type); Artificial intelligence; Intelligent character recognition; Confusion; Character encoding; Pattern recognition (psychology); Handwriting recognition; Natural language processing; Character recognition; Speech recognition; Feature extraction; Mathematics; Psychology","score_opus":0.014881650224856921,"score_gpt":0.24244673980261636,"score_spread":0.22756508957775945,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2586783582","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":[0.05835932,0.00007942821,0.93324786,0.000050496154,0.000021980568,0.00008427555,0.000004151005,0.00013796997,0.008014507],"genre_scores_gemma":[0.91345656,0.000102287195,0.085951574,0.00014624817,0.0000023235432,0.000016047978,0.0000070846563,0.00000328869,0.00031458688],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992418,0.00007826641,0.00018849371,0.00024127503,0.00013064628,0.00011946163],"domain_scores_gemma":[0.99949825,0.000050529306,0.000078423334,0.00021908851,0.00008990989,0.00006382047],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002563839,0.00007705795,0.00016326293,0.0002036309,0.000033372384,0.000045195306,0.00013336018,0.000040564155,0.00022607436],"category_scores_gemma":[0.00004337601,0.00007079152,0.000055684468,0.00079017156,0.00003633843,0.00026166262,0.00003784931,0.00003907231,0.000021711287],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000034636087,0.00021004998,0.012478281,0.00002584431,0.00031549222,0.000004056484,0.0003085579,5.473506e-7,0.01094706,0.003201282,0.0031797553,0.9693256],"study_design_scores_gemma":[0.00024201586,0.000087664135,0.0019790651,0.000011675068,0.00009277353,0.0000114435425,0.000022018721,0.0012742783,0.97743756,0.016636861,0.0019857392,0.00021889572],"about_ca_topic_score_codex":0.000044404576,"about_ca_topic_score_gemma":0.000009321052,"teacher_disagreement_score":0.96910673,"about_ca_system_score_codex":0.0000074196164,"about_ca_system_score_gemma":0.000011372409,"threshold_uncertainty_score":0.28867942},"labels":[],"label_agreement":null},{"id":"W2589751987","doi":"10.1007/s11760-017-1070-2","title":"A new efficient binarization method: application to degraded historical document images","year":2017,"lang":"en","type":"article","venue":"Signal Image and Video Processing","topic":"Handwritten Text Recognition 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":"École de Technologie Supérieure","funders":"","keywords":"Historical document; Computer science; Artificial intelligence; Computer vision; Pattern recognition (psychology); Information retrieval","score_opus":0.016965996584146985,"score_gpt":0.3129806156329752,"score_spread":0.2960146190488282,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2589751987","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":[0.0004416183,0.00026343588,0.99474615,0.003447336,0.0000421574,0.00028877344,4.9831476e-7,0.00025029306,0.0005197434],"genre_scores_gemma":[0.35991228,0.000007816943,0.6393793,0.00026638104,0.00008365908,0.000057522342,0.0000014012712,0.00001038741,0.00028124766],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987408,0.000058954385,0.00023215916,0.0004928266,0.0002538692,0.00022140233],"domain_scores_gemma":[0.99900246,0.000036958594,0.00020135853,0.0003731787,0.0001922643,0.00019377169],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.000537258,0.00014841791,0.00016819975,0.00014952889,0.0006403851,0.0014746531,0.0005464265,0.00005646114,0.000007176986],"category_scores_gemma":[0.00011933835,0.00013669745,0.00003644106,0.00017537628,0.000026875072,0.0010781675,0.00027453987,0.000106039835,0.000020387643],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006166061,0.000021850334,0.00003731426,0.00003197075,0.0000025760553,0.000004410127,0.0003962709,0.000005210723,0.103992276,0.00036564432,0.0007283872,0.8944079],"study_design_scores_gemma":[0.0007543071,0.00024661602,0.0018742428,0.0003466495,0.000044928467,0.00006345461,0.00003957896,0.07390487,0.88232476,0.031059222,0.0086165825,0.0007248178],"about_ca_topic_score_codex":0.00018105829,"about_ca_topic_score_gemma":0.0000023643217,"teacher_disagreement_score":0.8936831,"about_ca_system_score_codex":0.00013904927,"about_ca_system_score_gemma":0.00009479696,"threshold_uncertainty_score":0.9995619},"labels":[],"label_agreement":null},{"id":"W2590383062","doi":"10.1016/j.patcog.2017.02.020","title":"PSI: Patch-based script identification using non-negative matrix factorization","year":2017,"lang":"en","type":"article","venue":"Pattern Recognition","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":"École de Technologie Supérieure","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Non-negative matrix factorization; Artificial intelligence; Pattern recognition (psychology); Identification (biology); Normalization (sociology); Representation (politics); Matrix decomposition; Set (abstract data type)","score_opus":0.05510593265417631,"score_gpt":0.3205421891221328,"score_spread":0.2654362564679565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2590383062","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":[0.12517816,0.0000061737232,0.8725756,0.00032379557,0.0006889067,0.0004974173,0.000067406596,0.00030805107,0.000354491],"genre_scores_gemma":[0.96587276,0.0000130438475,0.033356655,0.0002380174,0.00017754883,0.00010124017,0.00016213031,0.00002866343,0.000049950522],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9980933,0.00013202714,0.00045454854,0.00059994886,0.00041139414,0.00030875328],"domain_scores_gemma":[0.99765664,0.000069578775,0.000731144,0.00090380525,0.0005313939,0.000107408014],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00043539956,0.00023777464,0.00021095558,0.00027758806,0.00075136864,0.0011705532,0.00083439937,0.0001589645,0.00009630238],"category_scores_gemma":[0.00022235424,0.0002587413,0.000111576155,0.00017192317,0.00008227484,0.0022834288,0.00014286986,0.00018689128,0.00042875652],"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":[0.000013467598,0.00019772368,0.012450502,0.00011164262,0.000033861106,0.000018785619,0.00049868587,0.000010211984,0.06597605,0.000037093738,0.000330776,0.9203212],"study_design_scores_gemma":[0.0008973497,0.0000975801,0.03544667,0.0003532008,0.000044181415,0.000014051637,0.000041471747,0.19727322,0.74786377,0.017254662,0.00008650419,0.0006273032],"about_ca_topic_score_codex":0.00052029797,"about_ca_topic_score_gemma":0.00005638445,"teacher_disagreement_score":0.9196939,"about_ca_system_score_codex":0.00014893229,"about_ca_system_score_gemma":0.000075119526,"threshold_uncertainty_score":0.99998647},"labels":[],"label_agreement":null},{"id":"W2591127855","doi":"","title":"“One Against One” or “One Against All”: Which One is Better for Handwriting Recognition with SVMs?","year":2006,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":205,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Handwriting; Support vector machine; Computer science; Handwriting recognition; Pattern recognition (psychology); Artificial intelligence; Character (mathematics); Point (geometry); Speech recognition; Class (philosophy); Intelligent character recognition; Character recognition; Machine learning; Feature extraction; Mathematics; Image (mathematics)","score_opus":0.04277814179642096,"score_gpt":0.25677146213772334,"score_spread":0.21399332034130236,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2591127855","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":[0.060596228,0.000046294947,0.90096515,0.00773178,0.00007814387,0.0015425204,0.000081483704,0.001761386,0.027197002],"genre_scores_gemma":[0.29208666,0.000105257044,0.69107324,0.013568686,0.0005833414,0.0006115611,0.00038057024,0.00009031793,0.0015003718],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99616677,0.00011918491,0.0008455776,0.0011485686,0.0007886131,0.0009312984],"domain_scores_gemma":[0.997259,0.00032107512,0.00034940502,0.00078804005,0.001072106,0.00021034383],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00076546037,0.00045038265,0.0005987066,0.00040941106,0.0003872565,0.0007072665,0.0008110809,0.00029367753,0.00025115846],"category_scores_gemma":[0.00010251107,0.00042667845,0.00015007048,0.00095455255,0.00010048333,0.0014677531,0.00023744117,0.00035885765,0.0002570142],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016942715,0.0014706005,0.00020046603,0.00029386833,0.00024484072,0.000021476542,0.00033871515,0.0000042670817,0.046303965,0.001247627,0.010440196,0.93926454],"study_design_scores_gemma":[0.0054060994,0.0015718763,0.0013467609,0.0019788693,0.0001881747,0.00003801335,0.00013603027,0.01095774,0.9414559,0.023777768,0.010671231,0.0024715206],"about_ca_topic_score_codex":0.00013453074,"about_ca_topic_score_gemma":0.00071580586,"teacher_disagreement_score":0.936793,"about_ca_system_score_codex":0.00014306958,"about_ca_system_score_gemma":0.00014440886,"threshold_uncertainty_score":0.9998185},"labels":[],"label_agreement":null},{"id":"W2591660153","doi":"10.1111/1556-4029.13483","title":"Relative Width and Height of Handwritten Letter","year":2017,"lang":"en","type":"article","venue":"Journal of Forensic Sciences","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Value (mathematics); Mathematics; Literature; Psychology; Linguistics; Statistics; Art; Philosophy","score_opus":0.028861675598455976,"score_gpt":0.2891232275145544,"score_spread":0.2602615519160984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2591660153","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":[0.6408954,0.0010065541,0.31368625,0.024843795,0.0012292124,0.00020680971,0.0000035307246,0.00005075411,0.018077672],"genre_scores_gemma":[0.8322072,0.00007798103,0.16722724,0.00031090376,0.00010136,6.5960785e-7,3.3662513e-8,0.0000023525445,0.00007226713],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988108,0.00004535439,0.0003569784,0.00016103202,0.00046895663,0.00015682296],"domain_scores_gemma":[0.9983466,0.00012654222,0.0008988195,0.00026547184,0.0002839607,0.00007856856],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012015356,0.00008695343,0.00023465008,0.00020427087,0.00036109742,0.000300901,0.0011421484,0.000042457465,0.000009608388],"category_scores_gemma":[0.00026937097,0.00005836914,0.000081262035,0.00012880791,0.001045011,0.0023248415,0.00020455828,0.00013747178,0.000002177222],"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":[0.000030007363,0.00011279851,0.02566464,0.000039073984,0.00010525062,0.00014323,0.0025472322,0.0000038598905,0.009846982,0.082843415,0.02094764,0.85771585],"study_design_scores_gemma":[0.0013507977,0.0023267646,0.083645806,0.00084277237,0.000054267894,0.00111446,0.00015776535,0.0025252786,0.3339709,0.56795007,0.0055828523,0.00047823208],"about_ca_topic_score_codex":0.000013370345,"about_ca_topic_score_gemma":0.000006399652,"teacher_disagreement_score":0.85723764,"about_ca_system_score_codex":0.000011898519,"about_ca_system_score_gemma":0.00008778303,"threshold_uncertainty_score":0.38503864},"labels":[],"label_agreement":null},{"id":"W2592908060","doi":"","title":"A Dissimilarity Measure for On-Line Signature Verification Based on the Sigma-Lognormal Model","year":2015,"lang":"en","type":"preprint","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Measure (data warehouse); Dynamic time warping; Signature (topology); Artificial intelligence; Image warping; Pattern recognition (psychology); Line (geometry); Data mining; Mathematics","score_opus":0.04256734429828776,"score_gpt":0.27146585868751794,"score_spread":0.22889851438923017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2592908060","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":[0.0005924322,0.00027624558,0.959096,0.03090944,0.00028794707,0.0043594325,0.00068004045,0.0026489259,0.0011494923],"genre_scores_gemma":[0.6830604,0.000043728513,0.29765624,0.010999049,0.0002786271,0.007187835,0.0003481105,0.0001298064,0.00029621075],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9947064,0.00051743287,0.0008579309,0.0016132884,0.0013084626,0.0009965054],"domain_scores_gemma":[0.9931925,0.00065884925,0.00074519985,0.0038617984,0.0010610764,0.00048060608],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.003699847,0.0009630593,0.0007789772,0.00073776493,0.0005383434,0.0008648068,0.003928378,0.0015608957,0.000013206541],"category_scores_gemma":[0.0013426625,0.00077261473,0.00059893593,0.0006387117,0.00015680102,0.00039247717,0.00094438746,0.0027040318,0.0000058684527],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005595287,0.0013248044,0.00011861499,0.000225495,0.00011892797,0.00003285994,0.00039698882,0.7614037,0.0011236859,0.11116482,0.067268215,0.056262363],"study_design_scores_gemma":[0.00048213446,0.00041874647,0.000086680986,0.00033296942,0.00005049308,0.000008756559,0.000010709122,0.9061198,0.020071784,0.07074977,0.00089051045,0.0007776121],"about_ca_topic_score_codex":0.00033698475,"about_ca_topic_score_gemma":0.00030464708,"teacher_disagreement_score":0.68246794,"about_ca_system_score_codex":0.0010428621,"about_ca_system_score_gemma":0.0017074706,"threshold_uncertainty_score":0.9997353},"labels":[],"label_agreement":null},{"id":"W2594435365","doi":"10.1007/s11042-017-4538-8","title":"Detecting Uyghur text in complex background images with convolutional neural network","year":2017,"lang":"en","type":"article","venue":"Multimedia Tools and Applications","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":21,"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 Ottawa","funders":"National Natural Science Foundation of China","keywords":"Computer science; Convolutional neural network; Pooling; Benchmark (surveying); Artificial intelligence; Pattern recognition (psychology); Feature (linguistics); Minimum bounding box; Bounding overwatch; Network architecture; Image (mathematics); Text detection; Data mining; Cartography","score_opus":0.053243245776935906,"score_gpt":0.296618537616401,"score_spread":0.2433752918394651,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2594435365","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":[0.056085847,0.0001902426,0.9339233,0.0025075243,0.00005911811,0.0013396413,0.00006027637,0.00042688925,0.005407156],"genre_scores_gemma":[0.81664205,0.000024760337,0.18241733,0.0001512292,0.00016102103,0.00050737004,0.000023170469,0.000008798772,0.00006424917],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99903446,0.00002852776,0.00019160245,0.00035553073,0.00013296845,0.00025691168],"domain_scores_gemma":[0.9989795,0.00019418882,0.00014478911,0.00050869514,0.00008280689,0.00009002702],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018700787,0.00012665344,0.00014978882,0.00004858427,0.00064579747,0.0005882426,0.00054888485,0.000051197898,0.000024180656],"category_scores_gemma":[0.000027300714,0.00011328089,0.000024774816,0.00012352355,0.00020728476,0.0006527026,0.00021252989,0.00016119822,0.000028636623],"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":[0.0000079768,0.000086481006,0.018663973,0.000017509054,0.000013647074,0.000006722697,0.000106348576,0.000083832354,0.0019704124,0.008306674,0.0009192271,0.9698172],"study_design_scores_gemma":[0.0011639963,0.00008120443,0.81095487,0.000059614304,0.0000117902455,0.00006813127,0.000059798247,0.16424076,0.0016702021,0.0071649076,0.014015474,0.0005092239],"about_ca_topic_score_codex":0.000086283086,"about_ca_topic_score_gemma":0.00010876823,"teacher_disagreement_score":0.96930796,"about_ca_system_score_codex":0.000023603106,"about_ca_system_score_gemma":0.00002974549,"threshold_uncertainty_score":0.5672437},"labels":[],"label_agreement":null},{"id":"W2597548388","doi":"10.21529/resi.2004.0301003","title":"A Strategy for Selecting Classes of Symbols from Classes of Graphemes in HMM-Based Handwritten Word Recognition","year":2004,"lang":"pt","type":"article","venue":"Revista Eletrônica de Sistemas de Informação","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"Fundação Araucária; Pontificia Universidade Católica do Paraná; École de technologie supérieure","keywords":"Hidden Markov model; Computer science; Humanities; Word (group theory); Artificial intelligence; Linguistics; Art; Philosophy","score_opus":0.04589129414805366,"score_gpt":0.30435230863412877,"score_spread":0.2584610144860751,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2597548388","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":[0.41082522,0.002549038,0.5818091,0.00035086228,0.0001206047,0.0026699172,0.00050367217,0.00033333377,0.0008382277],"genre_scores_gemma":[0.91943645,0.0005154212,0.07897354,0.00036440045,0.0000858267,0.0003384857,0.00018635666,0.000065646775,0.000033864795],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9938077,0.00035190932,0.0031518063,0.0007933577,0.00072939077,0.0011658787],"domain_scores_gemma":[0.99356276,0.001800942,0.0021865808,0.0010034147,0.001148335,0.0002979515],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0023755794,0.00068677333,0.0016394642,0.0010550566,0.0001829613,0.0004783749,0.0013450929,0.0006689425,0.000048110105],"category_scores_gemma":[0.0014073147,0.00074366084,0.00079577026,0.0023072835,0.0002738428,0.0012504539,0.00019537273,0.00071508664,0.000013913074],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002176648,0.004061006,0.026031675,0.038432065,0.0015760243,0.00013257172,0.009048115,0.0017305681,0.053866163,0.022948077,0.0011907935,0.8388063],"study_design_scores_gemma":[0.018186526,0.0065050432,0.014998477,0.057304587,0.001299638,0.00020009287,0.00571447,0.03468434,0.79378253,0.058529068,0.003968224,0.0048269755],"about_ca_topic_score_codex":0.00049789704,"about_ca_topic_score_gemma":0.00039486965,"teacher_disagreement_score":0.8339793,"about_ca_system_score_codex":0.0006405577,"about_ca_system_score_gemma":0.0022128827,"threshold_uncertainty_score":0.99950147},"labels":[],"label_agreement":null},{"id":"W2603324824","doi":"10.16995/dm.15","title":"Palaeography and Image-Processing: Some Solutions and Problems","year":2007,"lang":"en","type":"article","venue":"Digital Medievalist","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Handwriting; Computer science; Palaeography; Cluster analysis; Document processing; Identification (biology); Image processing; Feature extraction; Feature (linguistics); Handwriting recognition; Artificial intelligence; Information retrieval; Data mining; Pattern recognition (psychology); Image (mathematics); History","score_opus":0.017337646227530493,"score_gpt":0.2504362372777787,"score_spread":0.23309859105024822,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2603324824","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":[0.039846428,0.0037940198,0.9171832,0.003095769,0.00023915964,0.000561439,0.000047752717,0.0016236884,0.03360855],"genre_scores_gemma":[0.9793577,0.00011994114,0.019951848,0.00033518762,0.00008336554,0.000018302217,0.000013023262,0.000013664211,0.00010693114],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99881434,0.000012019105,0.0002279789,0.00035692312,0.00023800491,0.00035071344],"domain_scores_gemma":[0.99931574,0.00008392639,0.00007102112,0.00020148649,0.00011665906,0.00021114583],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040518565,0.00014447077,0.0001394027,0.00020430953,0.00018594232,0.0007791646,0.00023897518,0.00006322843,0.0000019871136],"category_scores_gemma":[0.00008953299,0.00013252156,0.00003732672,0.00031367125,0.00034714816,0.002136104,0.00024211376,0.000115473464,0.000009427261],"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":[0.0000051217676,0.00011503511,0.0023134358,0.00012514126,0.000017474436,0.000038590042,0.0007205011,3.4820076e-8,0.0023169895,0.022970127,0.0010940579,0.9702835],"study_design_scores_gemma":[0.0029486723,0.0011753167,0.05699924,0.0009991146,0.0000791218,0.0012620952,0.00081127277,0.0068853954,0.030466573,0.78814185,0.10717459,0.0030567804],"about_ca_topic_score_codex":0.000009187092,"about_ca_topic_score_gemma":0.000008043696,"teacher_disagreement_score":0.9672267,"about_ca_system_score_codex":0.00001356899,"about_ca_system_score_gemma":0.000022981081,"threshold_uncertainty_score":0.7513502},"labels":[],"label_agreement":null},{"id":"W2608352657","doi":"10.1109/icpr.2016.7900137","title":"Layered ground truth: Conveying structural and statistical information for document image analysis and evaluation","year":2016,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Ground truth; Computer science; Pixel; Artificial intelligence; Representation (politics); Segmentation; Context (archaeology); Object (grammar); Perspective (graphical); Focus (optics); Figure–ground; Pattern recognition (psychology); Data mining; Information retrieval; Natural language processing","score_opus":0.016698146437921724,"score_gpt":0.3057740632495097,"score_spread":0.28907591681158795,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2608352657","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":[0.09062084,0.000007945445,0.9083634,0.00036189667,0.000035045,0.00032295336,0.00002305517,0.00009319588,0.00017166392],"genre_scores_gemma":[0.7618417,0.000008419825,0.23798387,0.00007166558,0.000008263534,0.00005278272,0.000020266978,0.0000016883967,0.000011351219],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99920076,0.000060178652,0.00022459152,0.00017580602,0.00021266815,0.00012600503],"domain_scores_gemma":[0.9991156,0.00039064663,0.00007770096,0.00013260737,0.00021915346,0.000064327374],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058331405,0.00008063545,0.00012085843,0.00018487245,0.00008607309,0.0003492243,0.000091569316,0.000029950785,0.000082308245],"category_scores_gemma":[0.00019485745,0.00005324865,0.00002339286,0.00015285483,0.00004831531,0.0021294625,0.00006759303,0.000021747059,0.000004414642],"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":[0.000008549466,0.000002219572,0.0003656508,0.000013665604,0.00005524435,1.6596057e-7,0.000181537,1.8761122e-7,0.0007534167,0.051046267,0.00008990263,0.9474832],"study_design_scores_gemma":[0.0031069976,0.00032603284,0.16842945,0.00003285735,0.0003728327,0.000022731978,0.00011471837,0.3479908,0.02491113,0.4538603,0.0003014894,0.00053065206],"about_ca_topic_score_codex":0.000029952105,"about_ca_topic_score_gemma":0.00001502206,"teacher_disagreement_score":0.9469525,"about_ca_system_score_codex":0.00004384706,"about_ca_system_score_gemma":0.00002265279,"threshold_uncertainty_score":0.3367578},"labels":[],"label_agreement":null},{"id":"W2608426471","doi":"10.1109/icpr.2016.7899791","title":"Approaching the intra-class variability in multi-script static signature evaluation","year":2016,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"Indian Statistical Institute; University of Technology Sydney; European Commission","keywords":"Signature (topology); Computer science; Scripting language; Devanagari; Artificial intelligence; Handwriting recognition; Classifier (UML); Lexicon; Pattern recognition (psychology); Signature recognition; Class (philosophy); Natural language processing; Feature extraction; Programming language; Character recognition; Mathematics","score_opus":0.042824987639999666,"score_gpt":0.2950090160908056,"score_spread":0.25218402845080595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2608426471","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":[0.0052881185,0.000015023371,0.9859006,0.0044721267,0.00012446202,0.0007019121,0.0000019824845,0.00028195453,0.0032138415],"genre_scores_gemma":[0.86878896,0.0000044912267,0.13022183,0.0006742138,0.000016093867,0.00015926447,0.0000013492828,0.000005745394,0.00012804093],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976812,0.0010181359,0.0002771078,0.00039417954,0.00039363632,0.00023572307],"domain_scores_gemma":[0.9985183,0.0006147043,0.00007408541,0.0005855136,0.00016131016,0.00004609516],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0057361186,0.000118871256,0.00011735337,0.000095122006,0.00007504305,0.00011118378,0.00069894886,0.0000877052,0.00012621669],"category_scores_gemma":[0.0009992883,0.00005919505,0.00003917917,0.00033834248,0.000057130314,0.0006697679,0.00014216533,0.00020012906,0.00003748815],"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":[0.0000031827178,0.0001370594,0.0005389628,0.000010901785,0.000007728958,0.0000013733783,0.00093878014,0.00001008915,0.00853355,0.026346153,0.0008322034,0.96264],"study_design_scores_gemma":[0.0011934063,0.000069112764,0.008433662,0.00009787866,0.000012674157,0.000009827679,0.000111847716,0.7626293,0.04186231,0.18424933,0.0009586692,0.00037202035],"about_ca_topic_score_codex":0.000040085695,"about_ca_topic_score_gemma":0.00006642263,"teacher_disagreement_score":0.962268,"about_ca_system_score_codex":0.00017138703,"about_ca_system_score_gemma":0.00010280519,"threshold_uncertainty_score":0.24139039},"labels":[],"label_agreement":null},{"id":"W2610087018","doi":"10.1109/icpr.2016.7900098","title":"Multi-script writer identification using dissimilarity","year":2016,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Scripting language; Computer science; Artificial intelligence; Natural language processing; Identification (biology); Classifier (UML); Arabic; Writing style; Task (project management); Pattern recognition (psychology); Speech recognition; Linguistics","score_opus":0.06017134908167774,"score_gpt":0.3098885004045753,"score_spread":0.24971715132289754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2610087018","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":[0.009280391,0.000011443721,0.98797613,0.0011844189,0.00016629527,0.0001257687,0.0000038749,0.0006361022,0.00061554724],"genre_scores_gemma":[0.5674732,0.000008211971,0.43052357,0.00032362383,0.000027687702,0.00001228392,8.5274877e-7,0.000006297932,0.0016242866],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99906373,0.000054520708,0.0002196141,0.00032021158,0.00016378255,0.00017813059],"domain_scores_gemma":[0.999182,0.000034335073,0.00006515995,0.0005230706,0.00012494255,0.00007049651],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027607314,0.00008942404,0.00008335741,0.00010306393,0.00008731519,0.00017496078,0.0005182174,0.000058012214,0.00014781735],"category_scores_gemma":[0.000058490517,0.00005854185,0.000049324633,0.0001720246,0.000039146053,0.0011239063,0.0001526832,0.000043933163,0.00017313597],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000015301357,0.00011043765,0.002003822,0.000007661175,0.000008546857,0.0000056230324,0.00011834196,9.4314764e-8,0.6967292,0.008838954,0.002341159,0.28983465],"study_design_scores_gemma":[0.00048600585,0.000028437978,0.019595003,0.0000780817,0.000007797936,0.0000332887,0.000012704336,0.03312507,0.9269399,0.013899483,0.0053852987,0.00040895416],"about_ca_topic_score_codex":0.00001972355,"about_ca_topic_score_gemma":0.000007811122,"teacher_disagreement_score":0.5581928,"about_ca_system_score_codex":0.00005173772,"about_ca_system_score_gemma":0.000022002932,"threshold_uncertainty_score":0.23872674},"labels":[],"label_agreement":null},{"id":"W2612182074","doi":"10.16995/dm.44","title":"New Tools for Exploring, Analysing and Categorising Medieval Scripts | Digital Medievalist","year":2012,"lang":"en","type":"article","venue":"Digital Medievalist","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Scripting language; Leverage (statistics); Computer science; Context (archaeology); Natural language processing; Engineering drawing; Software engineering; Programming language; Artificial intelligence; Engineering; Archaeology; Geography","score_opus":0.08445399431652979,"score_gpt":0.2894591112931267,"score_spread":0.2050051169765969,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2612182074","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":[0.031489614,0.0016892607,0.94393533,0.0011486788,0.002349213,0.00093003263,0.0002172636,0.0014030696,0.01683751],"genre_scores_gemma":[0.96495914,0.00007983868,0.032053735,0.0003297382,0.0014868067,0.00011828129,0.00024044696,0.00007098223,0.0006610536],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9965408,0.000042724812,0.00071267184,0.00076275226,0.000872118,0.0010689393],"domain_scores_gemma":[0.99714714,0.0006479048,0.0002617455,0.0006784087,0.00029185647,0.0009729382],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.00069595047,0.0004887769,0.00057268055,0.00034615106,0.00030867176,0.0042232503,0.00084437424,0.00015489111,0.000019081106],"category_scores_gemma":[0.0014863354,0.0004617048,0.00023546845,0.00057694287,0.00019836007,0.016799932,0.0005044969,0.00024140195,0.00004877592],"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":[0.00003601151,0.00012931906,0.0013883942,0.000099517914,0.00011716891,0.000016154438,0.0023320762,4.74359e-7,0.0005645527,0.0106215505,0.0071313074,0.9775635],"study_design_scores_gemma":[0.006650196,0.0016275103,0.004219136,0.0012238452,0.0005474381,0.001083272,0.004661544,0.0061108503,0.06848279,0.059478085,0.83946884,0.0064464733],"about_ca_topic_score_codex":0.000043389777,"about_ca_topic_score_gemma":0.000010799432,"teacher_disagreement_score":0.971117,"about_ca_system_score_codex":0.00015965448,"about_ca_system_score_gemma":0.00016580735,"threshold_uncertainty_score":0.99978346},"labels":[],"label_agreement":null},{"id":"W2617572518","doi":"10.1007/978-3-319-59876-5_70","title":"Footnote-Based Document Image Classification","year":2017,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","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":"McGill University; École de Technologie Supérieure; Université du Québec à Montréal","funders":"","keywords":"Computer science; Salient; AdaBoost; Support vector machine; Artificial intelligence; Key (lock); Feature (linguistics); Task (project management); Information retrieval; Font; Pattern recognition (psychology); Machine learning; Data mining","score_opus":0.024942363513238495,"score_gpt":0.2805036651627935,"score_spread":0.25556130164955504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2617572518","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":[0.000012195885,0.000116829695,0.9802731,0.0023620748,0.0010192073,0.00061667006,0.000006430558,0.0005263573,0.015067104],"genre_scores_gemma":[0.093020394,0.00004797238,0.9039362,0.0017191678,0.00040158496,0.000055692137,0.000017055236,0.000051058367,0.0007508534],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9956336,0.000049489136,0.0005945601,0.0018456558,0.0012154073,0.000661257],"domain_scores_gemma":[0.9953202,0.0003377809,0.0006265085,0.0030117626,0.00049010984,0.0002136091],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0012557053,0.00058458047,0.00052949914,0.0010458836,0.0005087432,0.0018589473,0.005574312,0.00041776797,0.000059099635],"category_scores_gemma":[0.00017563322,0.0005567603,0.00019441858,0.0002247206,0.0010352058,0.0012178937,0.0010607567,0.000844764,0.00020306569],"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":[0.0000037904395,0.000026154263,0.000010587432,0.00003547955,0.0000058872056,0.000063964486,0.00010327427,0.00014173122,0.0009252807,0.015579615,0.00008495519,0.9830193],"study_design_scores_gemma":[0.00054393074,0.00033456413,0.00029455373,0.000963201,0.000016012526,0.000054318356,7.787867e-8,0.28526175,0.04820397,0.654178,0.0087201,0.0014294868],"about_ca_topic_score_codex":0.000024224431,"about_ca_topic_score_gemma":0.000047465663,"teacher_disagreement_score":0.9815898,"about_ca_system_score_codex":0.00051949744,"about_ca_system_score_gemma":0.0008733572,"threshold_uncertainty_score":0.999806},"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":"W2731900166","doi":"10.1016/j.patcog.2018.08.011","title":"A selectional auto-encoder approach for document image binarization","year":2018,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":166,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Artificial intelligence; Parsing; Encoder; Convolutional neural network; Workflow; Key (lock); Pixel; Process (computing); Pattern recognition (psychology); Image (mathematics); Computer vision; Database","score_opus":0.023655382755806986,"score_gpt":0.2715072332501407,"score_spread":0.24785185049433373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2731900166","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":[0.003505804,0.000008511513,0.9915762,0.00037645543,0.0002683478,0.00072769466,0.000028631193,0.0007223984,0.0027859332],"genre_scores_gemma":[0.49164003,0.000011216373,0.5054246,0.0009996975,0.0005372101,0.0008530321,0.00038068302,0.000027162481,0.0001263492],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99848497,0.00008997926,0.00029910082,0.0005400387,0.0002768063,0.0003090871],"domain_scores_gemma":[0.998815,0.000050477192,0.00014698843,0.00024982213,0.0006568894,0.000080830985],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004127086,0.00017690338,0.0001446071,0.00024245589,0.00026333125,0.0002918327,0.00031324543,0.00011045498,0.00016241352],"category_scores_gemma":[0.000058797676,0.00018095673,0.00009196813,0.00037610272,0.00006559817,0.0010094119,0.000084533254,0.00010557205,0.00029639914],"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":[0.000019471307,0.00023690339,0.00021301539,0.00008114857,0.00003709258,0.0000014503221,0.00058172725,7.246594e-7,0.009563821,0.00028258708,0.0038301838,0.9851519],"study_design_scores_gemma":[0.0027198086,0.0018967146,0.002735766,0.00023658796,0.00008690689,0.0002260649,0.00009025611,0.43253803,0.4026528,0.1489928,0.006281085,0.0015431624],"about_ca_topic_score_codex":0.00002310927,"about_ca_topic_score_gemma":0.000005610829,"teacher_disagreement_score":0.9836087,"about_ca_system_score_codex":0.000097228105,"about_ca_system_score_gemma":0.000052915486,"threshold_uncertainty_score":0.7379201},"labels":[],"label_agreement":null},{"id":"W2732227915","doi":"","title":"Proposition d'un descripteur de formes et du modèle vectoriel pour la recherche de symboles","year":2008,"lang":"fr","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Francophone University Association","funders":"","keywords":"Humanities; Physics; Art","score_opus":0.08728154186566449,"score_gpt":0.2821869848544044,"score_spread":0.1949054429887399,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2732227915","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":[0.034258153,0.0012988573,0.85927296,0.029847708,0.00024643034,0.000845817,0.00007174554,0.0010533066,0.073105045],"genre_scores_gemma":[0.31186172,0.008916147,0.6688179,0.0004871385,0.00007506931,0.00034617237,0.00023517737,0.00009950392,0.009161155],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.96027786,0.035500456,0.0009972973,0.0014659226,0.00074435974,0.0010140932],"domain_scores_gemma":[0.98599994,0.0059169903,0.0008572721,0.0026320473,0.0040625203,0.0005312537],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.022542138,0.0007632785,0.00068879797,0.00036873404,0.0008041013,0.0013854556,0.0031075566,0.0013678278,0.00015581003],"category_scores_gemma":[0.0067602,0.0008796631,0.0004938732,0.00087398605,0.00057704485,0.0009489093,0.0021492695,0.0024651126,0.00015786452],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033910488,0.002319743,0.0024294653,0.00038628554,0.00019787152,0.00011317633,0.0605738,0.00007985173,0.030718353,0.4929623,0.006281056,0.40390417],"study_design_scores_gemma":[0.0010341988,0.0000046764244,0.005969125,0.005335733,0.00013010803,0.001109159,0.00031058353,0.11860916,0.6613635,0.16808634,0.036585722,0.0014616991],"about_ca_topic_score_codex":0.0032278243,"about_ca_topic_score_gemma":0.0006843317,"teacher_disagreement_score":0.63064516,"about_ca_system_score_codex":0.0012739829,"about_ca_system_score_gemma":0.0026619234,"threshold_uncertainty_score":0.9999286},"labels":[],"label_agreement":null},{"id":"W2738242160","doi":"10.1049/iet-cvi.2016.0404","title":"Deep neural network with attention model for scene text recognition","year":2017,"lang":"en","type":"article","venue":"IET Computer Vision","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China","keywords":"Computer science; Closed captioning; Artificial intelligence; Artificial neural network; Feature (linguistics); Pattern recognition (psychology); Feature extraction; Segmentation; Sequence (biology); Image (mathematics); Speech recognition; Sequence labeling","score_opus":0.030337371239994887,"score_gpt":0.2842737255532839,"score_spread":0.253936354313289,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2738242160","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":[0.014871903,0.000023851988,0.98219013,0.0010218641,0.0004710053,0.0006260856,0.000004809813,0.00053454924,0.00025582357],"genre_scores_gemma":[0.43971303,0.000010844637,0.55929905,0.00043756256,0.00036344802,0.00006339719,0.000033671426,0.000020698828,0.000058315556],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982675,0.000059286074,0.00029763093,0.00065043,0.0003038213,0.00042134107],"domain_scores_gemma":[0.99815845,0.00007159344,0.00032022962,0.00096759415,0.00035772525,0.00012441722],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040293616,0.00023854095,0.00024371716,0.00010181888,0.00082770333,0.0010071651,0.0010515813,0.00013339275,0.000006594523],"category_scores_gemma":[0.000012981626,0.00020611944,0.00013018532,0.000106417756,0.00007225683,0.0016983084,0.0003930638,0.00017123322,0.00005298486],"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":[0.00005812418,0.000083317755,0.00015169974,0.000026422778,0.00001596109,0.0000092253795,0.000063498635,0.002989523,0.00021427638,0.00033706735,0.0043946747,0.9916562],"study_design_scores_gemma":[0.0007922494,0.00060973637,0.0028657275,0.00017504214,0.000014169874,0.00003931552,0.0000010068269,0.97834396,0.00047476773,0.016137555,0.00023352355,0.00031294345],"about_ca_topic_score_codex":0.0000066312728,"about_ca_topic_score_gemma":0.000021261298,"teacher_disagreement_score":0.99134326,"about_ca_system_score_codex":0.00004205727,"about_ca_system_score_gemma":0.000027320577,"threshold_uncertainty_score":0.9712116},"labels":[],"label_agreement":null},{"id":"W2751365095","doi":"10.1016/j.jksuci.2017.09.001","title":"TEDLESS – Text detection using least-square SVM from natural scene","year":2017,"lang":"en","type":"article","venue":"Journal of King Saud University - Computer and Information Sciences","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":21,"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":"University Grants Commission; Canadian Institute for Advanced Research","keywords":"Artificial intelligence; Computer science; Support vector machine; Pattern recognition (psychology); Contrast (vision); Set (abstract data type); Image (mathematics); Binary number; Computer vision; Mathematics","score_opus":0.02160435173513687,"score_gpt":0.24600844604738253,"score_spread":0.22440409431224567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2751365095","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":[0.3182347,0.000021191301,0.68053234,0.0002497127,0.0005066839,0.000039597562,0.000001965416,0.000031588806,0.00038222375],"genre_scores_gemma":[0.90898466,0.000040627237,0.09072944,0.00014417748,0.00009430633,2.7002873e-8,4.7366262e-7,0.0000010859671,0.000005231746],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99906355,0.000050043076,0.00025232948,0.00011136307,0.00038640067,0.00013631332],"domain_scores_gemma":[0.9985671,0.000055172368,0.0007664003,0.00016393309,0.00036668716,0.00008070989],"candidate_categories":["scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0005015028,0.000091903974,0.00014983433,0.00044811002,0.001212879,0.0012217356,0.0010057671,0.00005012633,0.0000042886845],"category_scores_gemma":[0.00003654885,0.00008149133,0.0000660837,0.00020581404,0.00019213247,0.015610712,0.00031836345,0.00017426112,0.000003342723],"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":[0.000016618667,0.000016435451,0.003682889,0.0000134303245,0.000020871565,0.000012227422,0.0015404992,0.00020319001,0.00060486124,0.0010208203,0.000070124705,0.99279803],"study_design_scores_gemma":[0.0009824121,0.00033639505,0.109633386,0.0003919232,0.000025707126,0.0003310045,0.0007577147,0.8726704,0.005710866,0.0013822186,0.0074274354,0.00035050846],"about_ca_topic_score_codex":0.00019581274,"about_ca_topic_score_gemma":0.000015058123,"teacher_disagreement_score":0.9924475,"about_ca_system_score_codex":0.000068799185,"about_ca_system_score_gemma":0.00009718606,"threshold_uncertainty_score":0.9998151},"labels":[],"label_agreement":null},{"id":"W2765215346","doi":"10.1111/1556-4029.13678","title":"Measuring the Frequency Occurrence of Handwritten Numeral Characteristics","year":2017,"lang":"en","type":"article","venue":"Journal of Forensic Sciences","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Thomas Hospital","funders":"","keywords":"Numeral system; Handwriting; Population; Statistics; Confidence interval; Pattern recognition (psychology); Speech recognition; Mathematics; Computer science; Demography; Artificial intelligence","score_opus":0.056482244319415495,"score_gpt":0.29464391486720537,"score_spread":0.23816167054778986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2765215346","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":[0.81316775,0.0004904234,0.17229646,0.0062376554,0.0026454222,0.00021145117,0.000016212929,0.00005490852,0.004879684],"genre_scores_gemma":[0.95137316,0.00008239507,0.04827495,0.0001130549,0.00014018471,0.0000015202673,1.16594535e-7,0.0000022024421,0.00001242912],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99816674,0.00007030052,0.00055969454,0.0001692147,0.00080020685,0.00023385015],"domain_scores_gemma":[0.9971407,0.00014871122,0.0015209254,0.00050961395,0.0005996068,0.00008046596],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002222442,0.00011260519,0.00026955668,0.00015960517,0.0007004212,0.0005558988,0.00353965,0.000040326915,0.0000130253875],"category_scores_gemma":[0.00081555755,0.000066220826,0.00014307053,0.00020512527,0.0010118185,0.0015609825,0.00023932324,0.00021864066,0.000004872301],"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":[0.000014093394,0.00011817673,0.06395719,0.00004239354,0.00006140828,0.000075081225,0.0016369341,0.0000027073756,0.010508047,0.030946478,0.0030652736,0.8895722],"study_design_scores_gemma":[0.0012080406,0.0021592432,0.40632716,0.0017202585,0.00010102296,0.0018566718,0.0003916743,0.0039093923,0.32581782,0.25396302,0.0016668008,0.00087888545],"about_ca_topic_score_codex":0.000031612435,"about_ca_topic_score_gemma":0.000007876882,"teacher_disagreement_score":0.88869333,"about_ca_system_score_codex":0.00002184924,"about_ca_system_score_gemma":0.00026208285,"threshold_uncertainty_score":0.657761},"labels":[],"label_agreement":null},{"id":"W2767607030","doi":"10.3390/info8040142","title":"Arabic Handwritten Digit Recognition Based on Restricted Boltzmann Machine and Convolutional Neural Networks","year":2017,"lang":"en","type":"article","venue":"Information","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":64,"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":"Universiti Malaysia Pahang; Trent University; Nottingham Trent University","keywords":"Computer science; Artificial intelligence; Convolutional neural network; Restricted Boltzmann machine; Digit recognition; Deep learning; Boltzmann machine; Feature extraction; Arabic numerals; Pattern recognition (psychology); Feature (linguistics); Speech recognition; Numerical digit; Artificial neural network; Handwriting recognition; Arithmetic; Mathematics","score_opus":0.016477029754989284,"score_gpt":0.23759080170935984,"score_spread":0.22111377195437054,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2767607030","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":[0.030048952,0.000022125825,0.95814925,0.0027605721,0.0003427498,0.00048168332,0.000051756364,0.00070883933,0.0074340785],"genre_scores_gemma":[0.9925286,0.000022450242,0.0056084204,0.0013696132,0.00007115672,0.000056435867,0.0003016532,0.000005756951,0.000035905803],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99894834,0.000043325188,0.00032788995,0.00017569421,0.00028961603,0.00021513691],"domain_scores_gemma":[0.99879104,0.00008654551,0.0003281145,0.00047972964,0.00021787237,0.00009670464],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00020077787,0.00015148561,0.00013119692,0.00023297175,0.00055106246,0.001050428,0.00043575015,0.00011579318,0.00001877781],"category_scores_gemma":[0.00021943348,0.0001436968,0.00004561778,0.0001121741,0.00008164819,0.0047150454,0.000117068455,0.00020654341,0.00007185007],"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":[0.000054447595,0.000040533356,0.001393714,0.000022239925,0.000008813084,0.000004320031,0.000087974026,0.0003603106,0.000019495516,0.0011173281,0.0029403612,0.9939505],"study_design_scores_gemma":[0.0007855108,0.0001607608,0.049897227,0.00006090457,0.000005790623,0.000019657524,0.0000036008757,0.94375604,0.0005941497,0.0016393359,0.002869107,0.00020793435],"about_ca_topic_score_codex":0.000047045087,"about_ca_topic_score_gemma":0.0000063554035,"teacher_disagreement_score":0.9937425,"about_ca_system_score_codex":0.000048202688,"about_ca_system_score_gemma":0.000032149113,"threshold_uncertainty_score":0.9999866},"labels":[],"label_agreement":null},{"id":"W2767743248","doi":"10.1016/j.forsciint.2017.11.012","title":"What is the error margin of your signature analysis?","year":2017,"lang":"en","type":"article","venue":"Forensic Science International","topic":"Handwritten Text Recognition 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":"Université du Québec à Trois-Rivières","funders":"","keywords":"Signature (topology); Margin (machine learning); Non-sampling error; Statistics; Computer science; Computational biology; Mathematics; Artificial intelligence; Biology; Machine learning","score_opus":0.031606708389415886,"score_gpt":0.3302033507895892,"score_spread":0.2985966424001733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2767743248","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":[0.34361967,0.00026467015,0.5291529,0.089137815,0.0093202125,0.0007071639,0.000067723435,0.00035035436,0.027379438],"genre_scores_gemma":[0.97840846,0.000027949638,0.019903788,0.0008311275,0.00007764262,0.00001247716,0.0000025840013,0.0000031045656,0.0007328992],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99809337,0.00001896345,0.00022743698,0.0004013016,0.0010510411,0.0002078663],"domain_scores_gemma":[0.99775505,0.000061630606,0.0003525572,0.0010875505,0.00068199495,0.0000612146],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.00090964034,0.000102382415,0.00013956754,0.00038249773,0.00046758263,0.0014863531,0.0054168114,0.00004511961,0.00016304372],"category_scores_gemma":[0.00024073849,0.00006920876,0.00016073679,0.0006099747,0.0010107845,0.0033858968,0.0007599869,0.0001411512,0.000031655407],"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":[0.000029390812,0.00019922674,0.018073823,0.000011175542,0.0005746638,0.000033051165,0.006603894,0.00008960356,0.012598435,0.23685543,0.014015148,0.71091616],"study_design_scores_gemma":[0.0005169265,0.00015652057,0.20128517,0.00018020923,0.00011154274,0.0000527736,0.00062629825,0.23655158,0.4219621,0.12786289,0.010134372,0.00055960886],"about_ca_topic_score_codex":0.000051194776,"about_ca_topic_score_gemma":0.00003852998,"teacher_disagreement_score":0.71035653,"about_ca_system_score_codex":0.000050450857,"about_ca_system_score_gemma":0.00011286735,"threshold_uncertainty_score":0.99996436},"labels":[],"label_agreement":null},{"id":"W2768365548","doi":"10.3138/mous.14.3-3","title":"Large-Scale Optical Character Recognition of Ancient Greek","year":2017,"lang":"en","type":"article","venue":"Mouseion Journal of the Classical Association of Canada","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Mount Allison University","funders":"","keywords":"Suite; Optical character recognition; Character (mathematics); Computer science; Scale (ratio); Character recognition; Open source; Natural language processing; Document processing; Sample (material); Artificial intelligence; Information retrieval; Pattern recognition (psychology); Software; Archaeology; History; Mathematics; Geography; Programming language; Cartography","score_opus":0.013366225153928974,"score_gpt":0.2287177835832801,"score_spread":0.21535155842935114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2768365548","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":[0.615796,0.00006099564,0.10112344,0.27408245,0.0035370514,0.00043907558,0.00015133992,0.00004785734,0.004761734],"genre_scores_gemma":[0.9897692,0.000015906637,0.0055402303,0.00076899107,0.00016854696,0.0000029847563,0.0000014658464,0.000009645528,0.0037230174],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9977781,0.00015315312,0.00065816025,0.00011976351,0.0010695155,0.00022130422],"domain_scores_gemma":[0.99586827,0.00018753219,0.0024102875,0.0003785976,0.0010317777,0.0001235186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012039223,0.000096641365,0.00030941737,0.00006687408,0.0002074204,0.00007336849,0.0010469236,0.000098438824,0.0000220479],"category_scores_gemma":[0.0012066133,0.00007057005,0.00019234644,0.00010641233,0.000052546264,0.00045803774,0.00018083687,0.000293724,0.0000013864098],"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":[0.00013169186,0.0010463089,0.009262911,0.00010985316,0.0003285602,0.00005291416,0.00097418664,0.000022647448,0.051525716,0.0034227953,0.8351326,0.09798983],"study_design_scores_gemma":[0.0031751737,0.00065331324,0.15540443,0.0006791976,0.0001541831,0.00013187382,0.00013835136,0.005145827,0.5853385,0.013014642,0.23560463,0.0005599257],"about_ca_topic_score_codex":0.00024104989,"about_ca_topic_score_gemma":0.01617852,"teacher_disagreement_score":0.59952796,"about_ca_system_score_codex":0.00044675847,"about_ca_system_score_gemma":0.00065920607,"threshold_uncertainty_score":0.9027994},"labels":[],"label_agreement":null},{"id":"W2771771851","doi":"","title":"Structure Prétopologique et Applications","year":2011,"lang":"fr","type":"book","venue":"Editions universitaires europeennes eBooks","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Humanities; Political science; Art","score_opus":0.02767497280755143,"score_gpt":0.23774004275782085,"score_spread":0.2100650699502694,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2771771851","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00003429256,0.00016243175,0.31028068,0.0010322082,0.0011147618,0.001313114,0.001533589,0.0012705826,0.68325835],"genre_scores_gemma":[0.029388875,0.00044622176,0.10813704,0.0021451223,0.0030246752,0.00019980769,0.0016395713,0.00027522747,0.8547435],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9958288,0.0008276609,0.0006496842,0.001402736,0.0005105733,0.0007805187],"domain_scores_gemma":[0.9957274,0.0004720478,0.00061919563,0.0016475131,0.0010909266,0.00044287756],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0003076149,0.0009009556,0.00064376224,0.0009715191,0.001167368,0.0003346483,0.0026078275,0.00087869936,0.0015627143],"category_scores_gemma":[0.00006864198,0.0010244965,0.0004499691,0.00035176973,0.0016180713,0.0009882988,0.0013461944,0.0016938432,0.0009683133],"study_design_candidate":"theoretical_or_conceptual","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":[0.000009403965,0.00010616876,0.000010007382,0.00011934635,0.00015375117,0.00031514792,0.00068950467,0.0000024080239,0.00016478803,0.8673741,0.073426954,0.057628408],"study_design_scores_gemma":[0.0003306452,0.00033588623,0.00009982326,0.0003887496,0.0002263979,0.00035278173,0.00012935858,0.00008015981,0.0018405025,0.14621928,0.8489355,0.0010609298],"about_ca_topic_score_codex":0.00012502448,"about_ca_topic_score_gemma":0.0002446255,"teacher_disagreement_score":0.7755085,"about_ca_system_score_codex":0.00043196933,"about_ca_system_score_gemma":0.001514169,"threshold_uncertainty_score":0.99980956},"labels":[],"label_agreement":null},{"id":"W2773624189","doi":"10.1049/iet-ipr.2017.0223","title":"Automatic segmentation and reconstruction of historical manuscripts in gradient domain","year":2017,"lang":"en","type":"article","venue":"IET Image Processing","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"Microsoft Research","keywords":"Computer science; Robustness (evolution); Noise (video); Segmentation; Cluster analysis; Artificial intelligence; Pattern recognition (psychology); Computer vision; Image (mathematics)","score_opus":0.021523635053447177,"score_gpt":0.27367556604509796,"score_spread":0.2521519309916508,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2773624189","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":[0.5278925,0.00016308377,0.47007105,0.0004987094,0.0001399018,0.00015291596,5.7773696e-7,0.000121820995,0.00095944584],"genre_scores_gemma":[0.61871374,0.000011757381,0.38120925,0.000017289784,0.000010766432,0.00001557489,4.1926327e-7,0.0000035908438,0.000017620257],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992712,0.000035889247,0.00024061096,0.00020575694,0.00012969256,0.00011683726],"domain_scores_gemma":[0.9994026,0.000013382858,0.00026574873,0.000210395,0.00007342344,0.00003448737],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030014548,0.00007481293,0.00013128143,0.00014031857,0.00016029175,0.00027181522,0.00024184177,0.00003737764,0.0000041071075],"category_scores_gemma":[0.00006176152,0.000075042764,0.000018172343,0.00007833995,0.0000775092,0.0016199859,0.00008613958,0.00007527929,0.0000015799212],"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":[0.0000016656404,0.000027066462,0.0023573125,0.00012532117,0.0000014163359,0.000007197841,0.0006667766,4.291379e-8,0.020273346,0.00009427395,0.000051999312,0.9763936],"study_design_scores_gemma":[0.0029474506,0.0003744263,0.14605287,0.0026373577,0.000033820615,0.0007927137,0.00063634815,0.12768717,0.4699004,0.247617,0.00026679676,0.0010536498],"about_ca_topic_score_codex":0.000058915208,"about_ca_topic_score_gemma":0.000012192362,"teacher_disagreement_score":0.97533995,"about_ca_system_score_codex":0.00014406141,"about_ca_system_score_gemma":0.000032437834,"threshold_uncertainty_score":0.30601552},"labels":[],"label_agreement":null},{"id":"W2778811706","doi":"10.1007/978-3-319-71607-7_49","title":"Multi-orientation Scene Text Detection Leveraging Background Suppression","year":2017,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Handwritten Text Recognition Techniques","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":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"Ministry of Education of the People's Republic of China; National Natural Science Foundation of China","keywords":"Computer science; Text detection; Artificial intelligence; Pixel; Perspective (graphical); Character (mathematics); Orientation (vector space); Pattern recognition (psychology); Recall rate; Image (mathematics); Convolutional neural network; Computer vision; Natural language processing","score_opus":0.036088437366995636,"score_gpt":0.2907593037137656,"score_spread":0.25467086634677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2778811706","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":[0.0002552479,0.00015080589,0.99315536,0.000233702,0.0034701573,0.0005732693,0.0000044969843,0.00047858665,0.0016783862],"genre_scores_gemma":[0.35420576,0.0000716403,0.6436081,0.0005380728,0.00047589757,0.000029562421,0.000012744569,0.000051480198,0.0010067694],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9957329,0.000063242944,0.00057772675,0.0019193529,0.0010518082,0.00065495673],"domain_scores_gemma":[0.996516,0.00025392283,0.00059611467,0.0019936883,0.00044612173,0.00019415458],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0010864134,0.00058052235,0.00049255404,0.0011098786,0.000855662,0.0015407725,0.0032683774,0.00045155137,0.00003742738],"category_scores_gemma":[0.00012094905,0.0005630881,0.00015687439,0.00027285493,0.00058626255,0.0020155816,0.0013649075,0.00094283314,0.00011139467],"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":[0.0000047701965,0.000027380394,0.000024888735,0.000032289485,0.000006051866,0.000045569104,0.00039389607,0.0003002007,0.0053235525,0.0003391946,0.000014637139,0.9934876],"study_design_scores_gemma":[0.0008833296,0.00028717404,0.0010090087,0.001460268,0.000019247955,0.00022487273,6.606099e-7,0.7122418,0.19327527,0.08596109,0.0030714746,0.0015657992],"about_ca_topic_score_codex":0.00006674775,"about_ca_topic_score_gemma":0.00013083834,"teacher_disagreement_score":0.9919218,"about_ca_system_score_codex":0.000509246,"about_ca_system_score_gemma":0.00034656675,"threshold_uncertainty_score":0.99968207},"labels":[],"label_agreement":null},{"id":"W2784936144","doi":"10.1109/wacv.2018.00028","title":"Generating Handwritten Chinese Characters Using CycleGAN","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":149,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Artificial intelligence; Natural language processing; Speech recognition","score_opus":0.027259316088447876,"score_gpt":0.29449650369999264,"score_spread":0.26723718761154475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2784936144","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":[0.29966223,0.000051267732,0.6943488,0.00036872673,0.0010054461,0.00039577545,0.000008979735,0.001527629,0.002631132],"genre_scores_gemma":[0.379843,0.000028623259,0.61698663,0.0014037519,0.0011875271,0.00006657869,0.000042491018,0.000051837163,0.0003895779],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99710065,0.00015943672,0.0006132688,0.0011485629,0.00046642503,0.00051167246],"domain_scores_gemma":[0.997555,0.000058297977,0.000383815,0.0014533183,0.00035289396,0.0001966501],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00061143824,0.0005248829,0.0005287865,0.00039681696,0.00026388996,0.0011679124,0.002015143,0.0004385687,0.00013644331],"category_scores_gemma":[0.000088265915,0.00045928033,0.00025344026,0.00033549327,0.00009796066,0.00066183915,0.00329013,0.00067180087,0.00014567953],"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":[0.000048272468,0.0011732663,0.015162064,0.0017159516,0.0012918407,0.00066254614,0.009686142,0.0008906046,0.2716711,0.010322833,0.021556908,0.66581845],"study_design_scores_gemma":[0.00043768683,0.00011074011,0.0022221876,0.0006508102,0.000044459368,0.00017425545,0.000019423038,0.91001856,0.05414525,0.029429529,0.0006606797,0.0020864266],"about_ca_topic_score_codex":0.00020082765,"about_ca_topic_score_gemma":0.00002172987,"teacher_disagreement_score":0.90912795,"about_ca_system_score_codex":0.00014284381,"about_ca_system_score_gemma":0.00023026293,"threshold_uncertainty_score":0.999869},"labels":[],"label_agreement":null},{"id":"W2786430557","doi":"10.1109/icdar.2017.267","title":"Pixel.js: Web-Based Pixel Classification Correction Platform for Ground Truth Creation","year":2017,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Pixel; Ground truth; Computer science; Segmentation; Workflow; Artificial intelligence; Image segmentation; Key (lock); Computer vision; Heuristic; Web application; Pattern recognition (psychology); Data mining; Database; World Wide Web","score_opus":0.05350572201523188,"score_gpt":0.31038706010063355,"score_spread":0.2568813380854017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2786430557","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":[0.0074161924,0.000005523262,0.96492755,0.00088460307,0.0011085705,0.0006059979,0.0000059425906,0.00092224986,0.02412334],"genre_scores_gemma":[0.904864,0.000011092005,0.09251705,0.00025458232,0.00014787342,0.00035340356,0.000049688937,0.000016496868,0.0017858214],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99869984,0.000026709458,0.00030422176,0.00046826192,0.00025338403,0.00024758966],"domain_scores_gemma":[0.99807185,0.00023593025,0.00034921404,0.000937513,0.00031772777,0.00008776163],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005102605,0.00016705523,0.00016436656,0.0001911117,0.0007961071,0.00093487056,0.0008032776,0.00015098121,0.000047500856],"category_scores_gemma":[0.00034734467,0.0001566326,0.00010884684,0.00010893494,0.0000779733,0.0018414144,0.000066854234,0.00010705739,0.00008156758],"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":[0.000049711485,0.00018304799,0.0005206685,0.00002838222,0.000016854781,5.610093e-7,0.00010271673,0.0000023538678,0.014593774,0.07330588,0.00759559,0.90360045],"study_design_scores_gemma":[0.0018713244,0.00048148175,0.020742767,0.00008990485,0.000028909872,0.000013629591,0.00008026775,0.8084083,0.10752307,0.031460445,0.028739404,0.0005604575],"about_ca_topic_score_codex":0.000055491186,"about_ca_topic_score_gemma":0.00007383877,"teacher_disagreement_score":0.90304,"about_ca_system_score_codex":0.00014968331,"about_ca_system_score_gemma":0.00013067912,"threshold_uncertainty_score":0.9014978},"labels":[],"label_agreement":null},{"id":"W2787615929","doi":"10.1109/icdar.2017.107","title":"A Comprehensive Survey on Handwriting and Computerized Graphology","year":2017,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"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","keywords":"Handwriting; Computer science; Task (project management); Handwriting recognition; Feature extraction; Feature (linguistics); Artificial intelligence; Natural language processing; Data science; Engineering; Linguistics","score_opus":0.05390015952107252,"score_gpt":0.30864957126379866,"score_spread":0.25474941174272614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2787615929","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":[0.28251427,0.00002660247,0.7074729,0.0011494805,0.00023896183,0.00024976395,0.000009835264,0.0005934001,0.0077447696],"genre_scores_gemma":[0.9444831,0.0000327408,0.05406815,0.0012610864,0.000025695283,0.0000110085975,0.000004868456,0.000007172044,0.000106176674],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99894273,0.00014860516,0.00016743799,0.0003998319,0.0001221195,0.0002192609],"domain_scores_gemma":[0.9986232,0.00028843095,0.00012538378,0.00072885625,0.00014517261,0.000088992885],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030586342,0.00013308972,0.00022104797,0.00011118826,0.0005973029,0.0005794806,0.0007897114,0.000070015616,0.000014670751],"category_scores_gemma":[0.00008842659,0.000118493255,0.000037377926,0.000055189303,0.00016496141,0.00033584243,0.00052289595,0.00012234236,0.000038893053],"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":[0.00009245262,0.00028344028,0.056817424,0.00005848665,0.00010886037,0.0002561596,0.00047307104,7.366159e-7,0.015743976,0.13929372,0.015312299,0.77155936],"study_design_scores_gemma":[0.0011659815,0.00032881694,0.9650544,0.00005650734,0.0000027443707,0.000077219185,0.000009086554,0.0042755413,0.012875307,0.014083512,0.0017140697,0.0003568403],"about_ca_topic_score_codex":0.00036230206,"about_ca_topic_score_gemma":0.000064615146,"teacher_disagreement_score":0.9082369,"about_ca_system_score_codex":0.0000074813047,"about_ca_system_score_gemma":0.000013587257,"threshold_uncertainty_score":0.5587945},"labels":[],"label_agreement":null},{"id":"W2789477730","doi":"10.1016/j.ins.2018.02.004","title":"An HMM framework based on spherical-linear features for online cursive handwriting recognition","year":2018,"lang":"en","type":"article","venue":"Information Sciences","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":20,"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","funders":"","keywords":"Hidden Markov model; Computer science; Pattern recognition (psychology); Artificial intelligence; Speech recognition; Handwriting recognition; Word recognition; Word (group theory); Segmentation; Feature extraction; Handwriting; Mathematics","score_opus":0.0405701509676921,"score_gpt":0.34248694570304106,"score_spread":0.30191679473534894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2789477730","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":[0.009805114,0.0000046363125,0.9845203,0.0013883339,0.0003412787,0.00040079022,0.00005745381,0.00050125684,0.0029808045],"genre_scores_gemma":[0.29617143,0.0000033048761,0.69755256,0.0058662714,0.00026655392,0.000060849143,0.00006680044,0.0000042684555,0.000007945397],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99839497,0.000066515546,0.00038598213,0.00028947892,0.0005443971,0.00031863252],"domain_scores_gemma":[0.9982157,0.00038826777,0.0002700181,0.00031254775,0.0006963278,0.00011718206],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009166403,0.00015277402,0.00014202172,0.00029367078,0.0006445262,0.00065233745,0.00086385134,0.00012255184,0.00006375474],"category_scores_gemma":[0.0007612127,0.00012992122,0.00006729146,0.0009306082,0.00030038692,0.004303298,0.000046878693,0.00015066721,0.00014625002],"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":[0.00003140399,0.00011401276,0.0000808669,0.000019021049,0.0000035993721,4.3257552e-7,0.0010483155,0.00014988423,0.00021670887,0.005660589,0.0020394092,0.99063575],"study_design_scores_gemma":[0.00058806234,0.003186616,0.0014655106,0.00037165964,0.000008382113,0.0000129363925,0.00067076617,0.84934247,0.074607335,0.05765603,0.011514922,0.00057532947],"about_ca_topic_score_codex":0.00001878186,"about_ca_topic_score_gemma":0.000009891404,"teacher_disagreement_score":0.99006045,"about_ca_system_score_codex":0.00004234389,"about_ca_system_score_gemma":0.00013621323,"threshold_uncertainty_score":0.6290505},"labels":[],"label_agreement":null},{"id":"W2791129077","doi":"10.1080/08839514.2018.1448137","title":"Fuzzy String Matching with a Deep Neural Network","year":2018,"lang":"en","type":"article","venue":"Applied Artificial Intelligence","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Artificial intelligence; Character (mathematics); Deep learning; Artificial neural network; Feature (linguistics); Pattern recognition (psychology); Spell; Matching (statistics); Speech recognition; Natural language processing","score_opus":0.03044484937173433,"score_gpt":0.26869993974396217,"score_spread":0.23825509037222783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2791129077","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":[0.024553927,0.00001728248,0.95970243,0.00020242791,0.0002160498,0.00030469097,6.137888e-7,0.00079372316,0.014208877],"genre_scores_gemma":[0.84341604,0.0000036343824,0.15544368,0.00052436965,0.00051937666,0.000058755002,0.0000016514488,0.000018455226,0.0000140386555],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981277,0.000038024773,0.00037925428,0.0005745213,0.00032073644,0.00055978633],"domain_scores_gemma":[0.99892473,0.000120683115,0.0001335199,0.0005518936,0.00013898971,0.00013019881],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003691563,0.00022083461,0.0001992557,0.000100911646,0.00038554822,0.0003750658,0.0009439381,0.000079120924,0.000056246117],"category_scores_gemma":[0.000013186866,0.00019623594,0.000044959346,0.00078848784,0.00021085363,0.00035781797,0.00027427136,0.00024918304,0.00054255174],"study_design_candidate":"theoretical_or_conceptual","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":[0.000019967769,0.000026431551,0.000011189745,0.0000039083775,0.000008377719,0.000008709926,0.00061808777,0.00042389132,0.0018169393,0.48939118,0.00004291834,0.5076284],"study_design_scores_gemma":[0.000026402677,0.00022498849,0.000056568526,0.000038723007,0.000008837265,0.00003227641,0.00022960018,0.027299274,0.19750723,0.77379847,0.00033045156,0.00044720693],"about_ca_topic_score_codex":0.00004065338,"about_ca_topic_score_gemma":0.00017631892,"teacher_disagreement_score":0.8188621,"about_ca_system_score_codex":0.000036047863,"about_ca_system_score_gemma":0.00003378923,"threshold_uncertainty_score":0.800227},"labels":[],"label_agreement":null},{"id":"W2791694245","doi":"10.1109/ipta.2017.8310140","title":"Footnote-based document image classification using 1D convolutional neural networks and histograms","year":2017,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Convolutional neural network; Computer science; Histogram; Historical document; Task (project management); Artificial intelligence; Pattern recognition (psychology); Set (abstract data type); Image (mathematics); Contextual image classification; Data set; Artificial neural network; Data mining; Engineering","score_opus":0.04084644577790833,"score_gpt":0.2979454443406111,"score_spread":0.2570989985627028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2791694245","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":[0.015479115,0.000043906493,0.9808198,0.0015694671,0.00017998109,0.0001949311,0.0000010313097,0.00029231448,0.0014194082],"genre_scores_gemma":[0.81782085,0.0000056641875,0.18168877,0.00032558953,0.00005272066,0.000019133384,0.0000054915995,0.0000062669046,0.00007553187],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990105,0.000050119375,0.00019151783,0.00034410463,0.00019132961,0.00021239968],"domain_scores_gemma":[0.9989514,0.000047002657,0.00017784158,0.00059456384,0.0001327488,0.00009649039],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026587467,0.00012027724,0.00011461576,0.00006916399,0.00053303427,0.00076456426,0.0005347219,0.00007063127,0.000035357916],"category_scores_gemma":[0.000036399604,0.00011295843,0.000048218495,0.00005374769,0.00020162888,0.00087338325,0.00018029576,0.00011225578,0.0000065098648],"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":[0.00003874612,0.0002343707,0.0108482735,0.000049215563,0.000040807565,0.000036054847,0.000107421,0.00029835812,0.021570666,0.1288195,0.0033682354,0.83458835],"study_design_scores_gemma":[0.0003098445,0.00004455092,0.012593758,0.000015722091,0.0000063276216,0.000013683659,0.0000041308085,0.98061395,0.0023302592,0.0033235399,0.0005739844,0.00017026572],"about_ca_topic_score_codex":0.00015604658,"about_ca_topic_score_gemma":0.000017032728,"teacher_disagreement_score":0.98031557,"about_ca_system_score_codex":0.00009726317,"about_ca_system_score_gemma":0.000044788107,"threshold_uncertainty_score":0.7372711},"labels":[],"label_agreement":null},{"id":"W2792001378","doi":"10.1109/icip.2017.8296454","title":"Query-by-example word spotting using multiscale features and classification in the space of representation differences","year":2017,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Spotting; Computer science; Word (group theory); Keyword spotting; Pooling; Artificial intelligence; Pattern recognition (psychology); Representation (politics); Natural language processing; Speech recognition; Mathematics","score_opus":0.079930438856971,"score_gpt":0.3307995693443399,"score_spread":0.2508691304873689,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2792001378","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":[0.7682933,0.000047617716,0.2273606,0.0012003834,0.000044219334,0.00022744705,0.0000014449272,0.00005449028,0.002770447],"genre_scores_gemma":[0.9403076,0.000031907814,0.059432004,0.000034571567,0.000013030635,0.000011933034,0.0000015377459,0.000002696803,0.00016470559],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9992382,0.00010828052,0.00015822261,0.00022815843,0.00016389883,0.00010322601],"domain_scores_gemma":[0.99908054,0.0001761958,0.00020823054,0.00046855758,0.0000477391,0.000018756618],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039440498,0.00006886505,0.000102768994,0.000063877356,0.00020066078,0.0003120991,0.0005142387,0.00004580562,0.0000070520828],"category_scores_gemma":[0.00013021103,0.00004801741,0.000019143688,0.00009119761,0.00009526153,0.00057579245,0.00011415947,0.00008627967,0.000001241519],"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":[0.00001388095,0.00016862967,0.3254565,0.000053545682,0.000014325037,0.000005052697,0.007147953,0.0000010832654,0.17009482,0.018412808,0.0034093054,0.4752221],"study_design_scores_gemma":[0.00020460055,0.000024127583,0.911464,0.000065666856,0.0000043140785,0.000013171879,0.00073069916,0.014763975,0.06640818,0.006131327,0.000069737434,0.00012020928],"about_ca_topic_score_codex":0.0023638709,"about_ca_topic_score_gemma":0.00029209498,"teacher_disagreement_score":0.5860075,"about_ca_system_score_codex":0.000010598082,"about_ca_system_score_gemma":0.00001118349,"threshold_uncertainty_score":0.3573481},"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":"W2803020058","doi":"10.1016/j.patrec.2018.04.025","title":"Convolutional pyramid of bidirectional character sequences for the recognition of handwritten words","year":2018,"lang":"en","type":"article","venue":"Pattern Recognition Letters","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":14,"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":"Character (mathematics); Computer science; Character recognition; Artificial intelligence; Pyramid (geometry); Pattern recognition (psychology); Convolutional neural network; Natural language processing; Speech recognition; Intelligent word recognition; Image (mathematics); Intelligent character recognition; Mathematics","score_opus":0.037446525955641206,"score_gpt":0.2660808310047379,"score_spread":0.22863430504909668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2803020058","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":[0.18070419,0.00004779133,0.8116406,0.005162562,0.00085505896,0.0007305008,0.00043202055,0.00019130144,0.00023592774],"genre_scores_gemma":[0.9684081,0.00006932373,0.02585874,0.0041453615,0.0007549585,0.00045236133,0.0002519201,0.00002657984,0.00003263871],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9979276,0.00014611396,0.000671409,0.00045475928,0.00047497408,0.00032511805],"domain_scores_gemma":[0.9974763,0.00066571566,0.0005428991,0.0003488243,0.0008987272,0.00006752948],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007699434,0.0002244283,0.00029383574,0.00032122651,0.00022091989,0.00007524759,0.0005956458,0.000114667535,0.00040121912],"category_scores_gemma":[0.00013602464,0.00018630375,0.00024130337,0.00043787225,0.0005780104,0.00064564054,0.00009481706,0.00016316662,0.00011017122],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008692148,0.00018264423,0.001963113,0.00013268688,0.0001984607,0.0000020517768,0.00066967495,8.9953215e-7,0.0838845,0.000101697944,0.005046258,0.9077311],"study_design_scores_gemma":[0.0019822544,0.0008214325,0.019882774,0.0007105409,0.00016093839,0.000128066,0.00017187904,0.007262359,0.9469112,0.016466739,0.004628353,0.0008734573],"about_ca_topic_score_codex":0.000095071184,"about_ca_topic_score_gemma":0.00002647032,"teacher_disagreement_score":0.9068576,"about_ca_system_score_codex":0.00005471175,"about_ca_system_score_gemma":0.00007188205,"threshold_uncertainty_score":0.7597247},"labels":[],"label_agreement":null},{"id":"W2803853399","doi":"10.1109/atsip.2018.8364482","title":"Frequent pattern mining for online handwriting recognition","year":2018,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Computer science; Artificial intelligence; Feature extraction; Image segmentation; Handwriting; Pattern recognition (psychology); Image processing; Segmentation; Image (mathematics); Feature (linguistics); Feature detection (computer vision); Representation (politics); Contextual image classification; Computer vision","score_opus":0.05156986853528073,"score_gpt":0.29962292354844544,"score_spread":0.2480530550131647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2803853399","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":[0.042227767,0.00001275333,0.9519243,0.0008455697,0.00020456438,0.0002967024,0.00002490929,0.0008320064,0.0036314223],"genre_scores_gemma":[0.33457547,0.0000065549734,0.66236657,0.0022112704,0.000466306,0.00008683299,0.000049826984,0.000014349907,0.00022284214],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998858,0.00003485639,0.00028224106,0.00037771784,0.00015379362,0.00029341193],"domain_scores_gemma":[0.9990329,0.00013661405,0.00009277477,0.00027490192,0.00038378083,0.00007900176],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033010377,0.0001257465,0.00013224289,0.0001353369,0.00016814165,0.00016436422,0.00039644848,0.00007125446,0.00015295997],"category_scores_gemma":[0.00010892767,0.000119487326,0.00007290419,0.00018569043,0.000047554753,0.00047839643,0.00011519345,0.00006195112,0.000110490415],"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":[0.0000018601639,0.000047487676,0.00009569161,0.000011680491,0.0000068692525,0.0000016684326,0.00015701778,1.6270505e-8,0.0019120831,0.00028275477,0.0025774552,0.9949054],"study_design_scores_gemma":[0.0019269084,0.0017411095,0.0010349448,0.0005498575,0.000030339119,0.000118711025,0.00036937764,0.085262366,0.8309809,0.052757848,0.024025252,0.0012024025],"about_ca_topic_score_codex":0.000036781665,"about_ca_topic_score_gemma":0.00010104592,"teacher_disagreement_score":0.993703,"about_ca_system_score_codex":0.000033426855,"about_ca_system_score_gemma":0.00002975001,"threshold_uncertainty_score":0.4872552},"labels":[],"label_agreement":null},{"id":"W2868811703","doi":"10.5958/2347-7202.2018.00002.6","title":"Multi-Character Recognition using EMNIST","year":2018,"lang":"en","type":"article","venue":"JIMS8I - International Journal of Information Communication and Computing Technology","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Innovation Cluster (Canada)","funders":"","keywords":"Character (mathematics); Character recognition; Computer science; Artificial intelligence; Natural language processing; Pattern recognition (psychology); Psychology; Mathematics; Geometry","score_opus":0.029125900910250826,"score_gpt":0.30924534650680824,"score_spread":0.28011944559655744,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2868811703","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":[0.07187186,0.00008186317,0.9234001,0.0033566253,0.00040268453,0.00009751693,0.0000033332476,0.00021819874,0.00056783954],"genre_scores_gemma":[0.58052605,0.00010979442,0.4185725,0.000708314,0.00006673066,0.0000014036002,0.000008316388,0.0000036915144,0.0000032253104],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985756,0.000084396,0.0008192654,0.00009642238,0.00029048003,0.00013380729],"domain_scores_gemma":[0.99605656,0.00006337465,0.0010899727,0.00034530842,0.0023920767,0.000052717212],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00070898863,0.000118542695,0.00016869958,0.0010790771,0.00021230782,0.00032106784,0.0014692522,0.00013974714,0.000021141306],"category_scores_gemma":[0.00026630628,0.00011619819,0.000058644564,0.00037196826,0.00021032046,0.002215215,0.0005928487,0.00032699434,0.00004475886],"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":[0.000026722473,0.0001039948,0.0007299329,0.000009276834,0.00009101548,0.0000032100231,0.0012944225,0.0000063103594,0.0017319227,0.012962916,0.000426375,0.9826139],"study_design_scores_gemma":[0.005265328,0.00094986125,0.0072084805,0.0014839452,0.000064688924,0.0061233942,0.0017745465,0.78221536,0.055754412,0.070877425,0.067156285,0.0011262998],"about_ca_topic_score_codex":0.0000091235315,"about_ca_topic_score_gemma":0.0000021484914,"teacher_disagreement_score":0.9814876,"about_ca_system_score_codex":0.000095255185,"about_ca_system_score_gemma":0.00007495421,"threshold_uncertainty_score":0.47384247},"labels":[],"label_agreement":null},{"id":"W2884067191","doi":"10.1109/bracis.2018.00044","title":"A Writer-Independent Approach for Offline Signature Verification using Deep Convolutional Neural Networks Features","year":2018,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Computer science; Convolutional neural network; Artificial intelligence; Support vector machine; Classifier (UML); Pattern recognition (psychology); Signature (topology); Deep learning; Machine learning; Mathematics","score_opus":0.026243839138594953,"score_gpt":0.2742199011466865,"score_spread":0.24797606200809152,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2884067191","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":[0.0014963782,0.00015343302,0.9959149,0.00021554157,0.00024919966,0.000560955,0.0000066336956,0.00046271173,0.0009402988],"genre_scores_gemma":[0.5466874,0.0000023177806,0.4520617,0.00058223796,0.000402436,0.00005525922,0.000052586915,0.00001010006,0.00014595989],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99860626,0.00006393506,0.00024486036,0.0005016517,0.00026442448,0.00031888072],"domain_scores_gemma":[0.99888355,0.00006440289,0.00011324195,0.00039965636,0.00044768213,0.00009149038],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032275094,0.0001723622,0.000157187,0.00012723671,0.00024595374,0.00020056611,0.0006186961,0.00020978895,0.00003888086],"category_scores_gemma":[0.000033683125,0.00015325473,0.0000988097,0.00030267754,0.00009388259,0.00048929977,0.0001301227,0.00020144656,0.0000041373405],"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":[0.00043184534,0.0014649421,0.0011309541,0.00019044634,0.00029965563,0.000015001191,0.0013753184,0.00856095,0.046698656,0.28817645,0.041252226,0.61040354],"study_design_scores_gemma":[0.00032830128,0.00012704439,0.0008091975,0.000007730652,0.000010086376,0.00005807166,0.000016360756,0.98914784,0.007095621,0.0018078854,0.00038307154,0.00020878385],"about_ca_topic_score_codex":0.000018975665,"about_ca_topic_score_gemma":0.000009330326,"teacher_disagreement_score":0.9805869,"about_ca_system_score_codex":0.00006935732,"about_ca_system_score_gemma":0.00003916415,"threshold_uncertainty_score":0.62495464},"labels":[],"label_agreement":null},{"id":"W2886227292","doi":"10.1109/aina.2018.00158","title":"Online Signature Verification Using the Information Set Based Models","year":2018,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Signature (topology); Computer science; Data mining; Entropy (arrow of time); Fuzzy set; Fuzzy logic; Set (abstract data type); Membership function; Function (biology); Algorithm; Sample (material); Pattern recognition (psychology); Artificial intelligence; Mathematics","score_opus":0.04422432018254207,"score_gpt":0.287208781442583,"score_spread":0.24298446126004092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2886227292","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":[0.0042554713,0.0000048800866,0.9917668,0.001120718,0.00007679622,0.00016885594,0.000007691997,0.0003824542,0.0022162972],"genre_scores_gemma":[0.7012657,0.0000016058488,0.29561508,0.0030019197,0.000053019892,0.0000069185317,0.000029295783,0.0000026408488,0.000023815845],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99940926,0.000042574506,0.00015483101,0.00010465801,0.00018180258,0.00010684935],"domain_scores_gemma":[0.99920434,0.000030193485,0.00007459194,0.00037881406,0.0002851943,0.000026876705],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022185639,0.00006784688,0.000049267277,0.00008294132,0.00014143152,0.000166199,0.00045096464,0.00006248535,0.00004210216],"category_scores_gemma":[0.000020561425,0.00004526732,0.000025817339,0.000319955,0.000043388267,0.0017659744,0.000057611764,0.000088947876,0.000040185252],"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":[0.00003101399,0.00028413234,0.00005209057,0.000053507443,0.00003622112,0.000001665422,0.0055890153,0.0030743084,0.020755935,0.22253369,0.035032485,0.71255594],"study_design_scores_gemma":[0.000074905714,0.000030496381,0.000049157738,0.0000094551915,0.0000021515905,0.000002698157,0.00003309481,0.94972587,0.03910283,0.008008354,0.002888859,0.000072137846],"about_ca_topic_score_codex":0.000029002787,"about_ca_topic_score_gemma":0.0000074398204,"teacher_disagreement_score":0.9466516,"about_ca_system_score_codex":0.000029470631,"about_ca_system_score_gemma":0.00005948743,"threshold_uncertainty_score":0.18459477},"labels":[],"label_agreement":null},{"id":"W2889064910","doi":"10.1007/s10044-018-0747-7","title":"Gabor filter-based texture for ancient degraded document image binarization","year":2018,"lang":"en","type":"article","venue":"Pattern Analysis and Applications","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":28,"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; McGill University","funders":"Ministère de l'Enseignement Supérieur et de la Recherche","keywords":"Artificial intelligence; Gabor filter; Computer science; Pattern recognition (psychology); Preprocessor; Computer vision; Filter (signal processing); Image (mathematics)","score_opus":0.012818523463252837,"score_gpt":0.2781765914422702,"score_spread":0.26535806797901734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2889064910","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":[0.0020105531,0.000043964046,0.9957403,0.0013574774,0.000012375533,0.0004959494,0.000042082385,0.0001656101,0.00013167906],"genre_scores_gemma":[0.92345375,0.0000117617865,0.07386218,0.0012090118,0.00008930282,0.0011555157,0.00013212675,0.000007753473,0.000078613244],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99900943,0.000028896919,0.00022097111,0.00042681737,0.00014177713,0.00017211647],"domain_scores_gemma":[0.99902296,0.000043468448,0.00012099775,0.0004649233,0.00026151186,0.00008614618],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018004855,0.000115892966,0.0001571154,0.00028137254,0.00025867697,0.0002479608,0.00031018653,0.00004600693,0.00005437628],"category_scores_gemma":[0.000008886224,0.000103195205,0.00011671964,0.0010702292,0.00006694743,0.00016226614,0.00005838905,0.000042338124,0.000028421731],"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":[0.0000042770575,0.0002744178,0.005323446,0.00005079264,0.0002316987,5.810098e-7,0.00028206708,0.0000059980903,0.016528968,0.0056232326,0.0020130044,0.96966153],"study_design_scores_gemma":[0.0014617173,0.00047477783,0.04214451,0.000060982038,0.001220588,0.0000049700648,0.000078810066,0.50602853,0.3199775,0.01759402,0.10979874,0.0011548783],"about_ca_topic_score_codex":0.000035100904,"about_ca_topic_score_gemma":0.00006300864,"teacher_disagreement_score":0.96850663,"about_ca_system_score_codex":0.00002541123,"about_ca_system_score_gemma":0.000021555443,"threshold_uncertainty_score":0.42081782},"labels":[],"label_agreement":null},{"id":"W2896024503","doi":"10.1109/access.2018.2876035","title":"Baidu Meizu Deep Learning Competition: Arithmetic Operation Recognition Using End-to-End Learning OCR Technologies","year":2018,"lang":"en","type":"article","venue":"IEEE Access","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Connectionism; Pipeline (software); Convolutional neural network; Task (project management); Artificial intelligence; Deep learning; End-to-end principle; Recurrent neural network; Pattern recognition (psychology); Artificial neural network; Machine learning","score_opus":0.04740332064415651,"score_gpt":0.3155909041870854,"score_spread":0.2681875835429289,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2896024503","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":[0.11617907,0.000054609405,0.8771185,0.0006476566,0.0004925227,0.00038498547,0.0000024911853,0.0026058725,0.0025142473],"genre_scores_gemma":[0.87591124,0.000057257203,0.12324486,0.0003052015,0.0002710733,0.00008811362,0.000022678103,0.000030088504,0.000069520516],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99759394,0.00027268537,0.00044759634,0.0007407874,0.0004640018,0.00048096842],"domain_scores_gemma":[0.99850273,0.00015638537,0.00022560802,0.00043340577,0.0005827583,0.00009908229],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00066421967,0.00027803832,0.00028836675,0.0006701526,0.0008278946,0.0012908414,0.0012325589,0.0002134229,0.00027764254],"category_scores_gemma":[0.00032783925,0.0002935941,0.00007781356,0.0011795552,0.00018768857,0.0025641692,0.00048260807,0.0005649602,0.0004848022],"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":[0.000014477577,0.000075526164,0.00082773116,0.000037298494,0.000030246527,0.000029410141,0.00069065415,0.00060500647,0.024056772,0.0007124558,0.0001524409,0.972768],"study_design_scores_gemma":[0.00062029465,0.00079447863,0.00089556637,0.0004629883,0.000048384947,0.00023293418,0.00043892622,0.1997035,0.77531105,0.012999937,0.0073773763,0.0011145971],"about_ca_topic_score_codex":0.00011140371,"about_ca_topic_score_gemma":0.00007908509,"teacher_disagreement_score":0.9716534,"about_ca_system_score_codex":0.00015410445,"about_ca_system_score_gemma":0.00006504554,"threshold_uncertainty_score":0.9999516},"labels":[],"label_agreement":null},{"id":"W2897315523","doi":"","title":"Authentification biométrique par dynamique de frappe pour évaluation à distance utilisant SVM à une classe","year":2016,"lang":"fr","type":"article","venue":"Corpus Université Laval (Université Laval)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mathematics; Computer science; Humanities; Art","score_opus":0.01958166400550252,"score_gpt":0.22103106695422053,"score_spread":0.20144940294871802,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2897315523","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":[0.08783279,0.0020037882,0.8380745,0.060421225,0.0010746138,0.0009382211,0.00030221633,0.0010355375,0.008317076],"genre_scores_gemma":[0.87666166,0.011829176,0.015384774,0.00033643618,0.00023285416,0.000013583566,0.000105638246,0.000103561964,0.095332295],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9949072,0.0010073693,0.0005786657,0.0015110953,0.00081457896,0.0011810629],"domain_scores_gemma":[0.9956147,0.00053695374,0.0007495447,0.0013180944,0.0011164809,0.00066421967],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011132774,0.0007203059,0.000625503,0.00086656655,0.0009107551,0.0002638305,0.0019999936,0.0007684047,0.00022073231],"category_scores_gemma":[0.00016794918,0.00076068257,0.00047803973,0.002319384,0.0005925306,0.0024960171,0.00067613553,0.0005291998,0.00034895228],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026484724,0.0005444744,0.0053987736,0.0001531328,0.0002245315,0.0007951569,0.012300106,0.000018775609,0.23895603,0.1542535,0.009138267,0.5779524],"study_design_scores_gemma":[0.005560456,0.0008576296,0.038971417,0.0024490315,0.00073188683,0.0004928883,0.00230289,0.034691434,0.5731507,0.05031015,0.28772765,0.0027538778],"about_ca_topic_score_codex":0.0070557254,"about_ca_topic_score_gemma":0.0067238244,"teacher_disagreement_score":0.8226898,"about_ca_system_score_codex":0.003142534,"about_ca_system_score_gemma":0.0015084635,"threshold_uncertainty_score":0.99955636},"labels":[],"label_agreement":null},{"id":"W2902136541","doi":"10.5430/air.v7n2p43","title":"A Genetic-LVQ neural networks approach for handwritten Arabic character recognition","year":2018,"lang":"en","type":"article","venue":"Artificial Intelligence Research","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Deanship of Scientific Research, King Saud University; King Saud University","keywords":"Learning vector quantization; Computer science; Artificial intelligence; Pattern recognition (psychology); Artificial neural network; Feature selection; Classifier (UML); Speech recognition; Intelligent character recognition; Arabic; Character recognition","score_opus":0.18716098341923487,"score_gpt":0.38721426140435183,"score_spread":0.20005327798511696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2902136541","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":[0.019235041,0.00008079263,0.97645223,0.0008119849,0.00032257062,0.001352627,0.0000105349145,0.00038462805,0.0013495982],"genre_scores_gemma":[0.8418024,0.00006898215,0.15509894,0.00033256994,0.0016520612,0.0008256767,0.000034881163,0.000037550803,0.00014693568],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959907,0.00045065943,0.00063358527,0.0009956631,0.0007291702,0.0012002259],"domain_scores_gemma":[0.9963798,0.00053686515,0.00010920777,0.0008001209,0.0019039913,0.0002700355],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002791906,0.00024556054,0.00027262888,0.0005529329,0.00074277114,0.00079610304,0.0015002699,0.00024268299,0.00014797901],"category_scores_gemma":[0.0004967238,0.00023365684,0.00015865627,0.0014431132,0.0006113778,0.00072639895,0.00039869576,0.00058736565,0.00048776672],"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":[0.00007606958,0.00020730257,0.00004708147,0.000021810394,0.000017657268,0.0000065635486,0.00040854388,0.000028178012,0.0027646185,0.005326482,0.001075347,0.99002033],"study_design_scores_gemma":[0.000046568213,0.0007595291,0.00012837086,0.000032388387,0.0000062307467,0.000029520248,0.00013961774,0.81508875,0.113615744,0.0689316,0.00089246914,0.00032922917],"about_ca_topic_score_codex":0.00008472998,"about_ca_topic_score_gemma":0.000039285173,"teacher_disagreement_score":0.98969114,"about_ca_system_score_codex":0.00009539488,"about_ca_system_score_gemma":0.00009976388,"threshold_uncertainty_score":0.95282495},"labels":[],"label_agreement":null},{"id":"W2905695339","doi":"10.1109/icfhr-2018.2018.00048","title":"Improving Word Spotting System Performance using Ensemble Classifier Combination Methods","year":2018,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Spotting; Computer science; Artificial intelligence; Classifier (UML); Support vector machine; Word (group theory); Keyword spotting; Pattern recognition (psychology); Random subspace method; Lexicon; Linear discriminant analysis; Arabic; Speech recognition; Natural language processing; Mathematics","score_opus":0.04119228170569745,"score_gpt":0.3182822732577243,"score_spread":0.27708999155202685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2905695339","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":[0.08641938,0.000011269617,0.8913524,0.000042656586,0.0004005878,0.00018218062,1.6769475e-7,0.0010709418,0.020520413],"genre_scores_gemma":[0.5021897,8.4001664e-7,0.49745113,0.00007562136,0.00007093309,0.000008488289,3.928295e-7,0.000008053496,0.00019484671],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99855584,0.00018408376,0.00032707854,0.00038632736,0.00022421173,0.0003224853],"domain_scores_gemma":[0.9988737,0.000098217475,0.00018054272,0.00043372638,0.00034000413,0.000073824],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014515023,0.00014495058,0.00017045555,0.00021287752,0.00034337834,0.00027034862,0.00050236296,0.000095472606,0.00002298469],"category_scores_gemma":[0.000061440274,0.00013406288,0.000049560746,0.00052078295,0.000055759778,0.0011083581,0.00026166288,0.00013091086,0.00007528853],"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":[0.0000021124683,0.00001709317,0.00018980111,0.000060600607,0.0000057453494,0.0000017372694,0.00016454,9.870763e-7,0.08669259,0.010055152,0.000062355575,0.9027473],"study_design_scores_gemma":[0.00010832504,0.00005944512,0.00019838549,0.0000788625,0.0000043786868,0.00003996777,0.000051515464,0.56135863,0.4374583,0.0003197518,0.00018180485,0.0001406405],"about_ca_topic_score_codex":0.000053822663,"about_ca_topic_score_gemma":0.000002524706,"teacher_disagreement_score":0.90260667,"about_ca_system_score_codex":0.00017225665,"about_ca_system_score_gemma":0.000065386186,"threshold_uncertainty_score":0.54669255},"labels":[],"label_agreement":null},{"id":"W2905811340","doi":"10.1109/ccst.2018.8585714","title":"A Biometric Attack Case Based on Signature Synthesis","year":2018,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; European Commission","keywords":"Biometrics; Signature (topology); Computer science; Signature recognition; Computer security; Salient; Artificial intelligence; Data mining; Mathematics","score_opus":0.029120396986164462,"score_gpt":0.28633750675013664,"score_spread":0.25721710976397216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2905811340","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":[0.0063964506,0.000013077522,0.95417476,0.0012259929,0.00015267837,0.00019384621,0.0000063347634,0.001233208,0.036603637],"genre_scores_gemma":[0.84126836,0.0000013021221,0.15576306,0.0025310714,0.0000774569,0.000034295732,6.2434225e-7,0.000008931263,0.00031491948],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989239,0.000055137803,0.00014800178,0.00038812743,0.00025154522,0.00023331054],"domain_scores_gemma":[0.9986374,0.00041997497,0.000048760037,0.0006082307,0.00017548092,0.00011015509],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00030314559,0.00013394516,0.00012446089,0.000875607,0.00012932156,0.0001509799,0.00051845325,0.00011241654,0.00072105194],"category_scores_gemma":[0.00025507677,0.000106354775,0.000069767004,0.0021945264,0.00006358448,0.00022506296,0.00008991613,0.00010894365,0.0008885952],"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":[0.000012586457,0.0003130464,0.00007069082,0.000020800091,0.000018118513,0.0014125425,0.000076865144,0.0000016533428,0.0021398044,0.0042637223,0.07962141,0.91204876],"study_design_scores_gemma":[0.00027988598,0.00076892716,0.00015346415,0.00007267166,0.000012164949,0.0006135132,0.00001430224,0.15659639,0.82227993,0.0011600399,0.017525353,0.000523341],"about_ca_topic_score_codex":0.000024899044,"about_ca_topic_score_gemma":0.000010604762,"teacher_disagreement_score":0.9115254,"about_ca_system_score_codex":0.000040415238,"about_ca_system_score_gemma":0.000040587685,"threshold_uncertainty_score":0.9998893},"labels":[],"label_agreement":null},{"id":"W2906214563","doi":"10.16995/dm.67","title":"Automatic Scribe Attribution for Medieval Manuscripts","year":2018,"lang":"en","type":"article","venue":"Digital Medievalist","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Handwriting; Set (abstract data type); Component (thermodynamics); Scripting language; Artificial intelligence; Information retrieval; Pattern recognition (psychology); Natural language processing; Programming language","score_opus":0.032890492331266265,"score_gpt":0.285136165189211,"score_spread":0.2522456728579447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2906214563","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":[0.011101969,0.00006509547,0.9701061,0.0021766932,0.0013770955,0.00072111015,0.00015354663,0.0016469565,0.012651399],"genre_scores_gemma":[0.94616,0.0000059370927,0.050545342,0.0010909487,0.00082005793,0.00020953364,0.00019140175,0.00003168473,0.0009450518],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981266,0.00003399768,0.00039476846,0.00048398462,0.00048658237,0.0004740576],"domain_scores_gemma":[0.9984543,0.00015048565,0.00013295909,0.0005356676,0.00052340294,0.00020319143],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004523951,0.00021495542,0.00024418836,0.00015355661,0.00021330657,0.0006207624,0.0008298301,0.000108275686,0.0000530075],"category_scores_gemma":[0.00054677326,0.00019854985,0.0001329993,0.00034327904,0.0002575839,0.0015766313,0.00021985572,0.00009259451,0.00043545864],"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":[0.000019965264,0.00017184073,0.00014669434,0.000106787076,0.000045307992,0.000014724279,0.00041189344,3.3504634e-8,0.0010821964,0.04398851,0.067635246,0.8863768],"study_design_scores_gemma":[0.0026262554,0.002712842,0.0026296915,0.0005323097,0.0000683813,0.00026040358,0.00011764839,0.066240266,0.15554295,0.20280854,0.56474876,0.0017119447],"about_ca_topic_score_codex":0.000005418704,"about_ca_topic_score_gemma":0.000006484203,"teacher_disagreement_score":0.93505806,"about_ca_system_score_codex":0.000105231884,"about_ca_system_score_gemma":0.00007636876,"threshold_uncertainty_score":0.8096628},"labels":[],"label_agreement":null},{"id":"W2907272786","doi":"10.3166/ts.34.7-20","title":"Ensembling: Model of histogram of oriented gradient based handwritten devanagari character recognition system","year":2017,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Devanagari; Character (mathematics); Histogram; Artificial intelligence; Computer science; Pattern recognition (psychology); Character recognition; Speech recognition; Natural language processing; Image (mathematics); Mathematics","score_opus":0.04167926175246987,"score_gpt":0.2512361175014844,"score_spread":0.2095568557490145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2907272786","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":[0.20369346,0.000017067678,0.7938514,0.00019355671,0.00015370673,0.0005115935,0.000067123925,0.00023671977,0.0012753651],"genre_scores_gemma":[0.9381815,0.0000059396625,0.061491493,0.00008724037,0.000045302317,0.00009354856,0.000043892273,0.000017299826,0.00003378363],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99784076,0.00009453235,0.0007405271,0.00044438333,0.000570706,0.00030910305],"domain_scores_gemma":[0.99764854,0.00006104554,0.0008434245,0.00076602516,0.0005535274,0.00012741871],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00074948696,0.00023000274,0.00040969308,0.00032874208,0.00022794216,0.00011037587,0.0009314755,0.00010747712,0.000041633808],"category_scores_gemma":[0.000043283337,0.00022163978,0.0002055331,0.00013723836,0.00013943804,0.00056279387,0.00014315352,0.00013114836,0.0000133841895],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048176682,0.0027844035,0.002531378,0.0019802535,0.00038203306,0.00006621274,0.0025900009,0.0005746829,0.30875745,0.025935063,0.0015691369,0.6523476],"study_design_scores_gemma":[0.0016481478,0.0004521439,0.0010775101,0.0006416005,0.00007505981,0.000008796151,0.000042640644,0.5939265,0.4003953,0.0010305591,0.00033403895,0.00036772244],"about_ca_topic_score_codex":0.0000620759,"about_ca_topic_score_gemma":0.000008672816,"teacher_disagreement_score":0.734488,"about_ca_system_score_codex":0.000110835186,"about_ca_system_score_gemma":0.00010284496,"threshold_uncertainty_score":0.9038208},"labels":[],"label_agreement":null},{"id":"W2909023102","doi":"10.1109/tifs.2019.2894031","title":"Characterizing and Evaluating Adversarial Examples for Offline Handwritten Signature Verification","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Information Forensics and Security","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"Fonds de recherche du Québec – Nature et technologies; Conselho Nacional de Desenvolvimento Científico e Tecnológico; National Science Foundation","keywords":"Computer science; Signature (topology); Adversarial system; Artificial intelligence; Pattern recognition (psychology); Handwriting recognition; Signature recognition; Feature extraction; Speech recognition; Natural language processing","score_opus":0.01713105310537766,"score_gpt":0.2556298412927902,"score_spread":0.23849878818741255,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2909023102","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":[0.080000244,0.000016713144,0.9180997,0.00038010866,0.00037136322,0.0006770825,0.0000873146,0.00016808818,0.00019938027],"genre_scores_gemma":[0.96619374,0.00008465933,0.033020027,0.00050927507,0.000034524095,0.00007683166,0.00005786778,0.0000066524685,0.00001642958],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990783,0.00003206923,0.00032190658,0.00020075768,0.00020518784,0.0001617817],"domain_scores_gemma":[0.99919015,0.00013399695,0.00015571286,0.00021190653,0.0002395031,0.000068734815],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042712368,0.00014153539,0.00016182597,0.00016868947,0.00024236176,0.0002560989,0.0001244967,0.00013363632,0.000012745995],"category_scores_gemma":[0.000015454487,0.00013903221,0.00005388364,0.00014420414,0.00003759998,0.0020177264,0.000004776942,0.00018593646,0.000010947253],"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":[0.00013594463,0.00004723437,0.000018549115,0.00022107582,0.000044545486,1.8918581e-7,0.006388879,0.000093422685,0.0060564964,0.020051166,0.00014779081,0.9667947],"study_design_scores_gemma":[0.0044058356,0.0014273808,0.0008144086,0.00023894642,0.00007899983,0.00004514612,0.00075442553,0.8112869,0.1254943,0.034290794,0.020231828,0.00093099725],"about_ca_topic_score_codex":0.000014651445,"about_ca_topic_score_gemma":0.00000537239,"teacher_disagreement_score":0.9658637,"about_ca_system_score_codex":0.000028513647,"about_ca_system_score_gemma":0.00003606858,"threshold_uncertainty_score":0.5669569},"labels":[],"label_agreement":null},{"id":"W2911019237","doi":"10.5815/ijigsp.2019.01.03","title":"Recognizing Bangla Handwritten Numeral Utilizing Deep Long Short Term Memory","year":2019,"lang":"en","type":"article","venue":"International Journal of Image Graphics and Signal Processing","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Numeral system; Bengali; Artificial intelligence; Speech recognition; Benchmark (surveying); Scripting language; Task (project management); Artificial neural network; Pattern recognition (psychology); Natural language processing","score_opus":0.014827059975069182,"score_gpt":0.27187528704786,"score_spread":0.25704822707279085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2911019237","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":[0.29129246,0.0015260063,0.7040714,0.0006729516,0.00042646998,0.00012951474,0.0000026366667,0.00008464427,0.0017939232],"genre_scores_gemma":[0.95762116,0.00022789135,0.041332588,0.0005097609,0.00024903714,0.000002840239,0.0000031690624,0.000019024077,0.000034535435],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9979377,0.00006977012,0.00065291993,0.00030315196,0.00078140176,0.00025510244],"domain_scores_gemma":[0.9977822,0.00011010432,0.0004015756,0.00012499881,0.0014357783,0.00014538105],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0009292183,0.00020117243,0.00028720233,0.0006296533,0.00012942783,0.0011027011,0.0009381771,0.000094528055,0.0000503866],"category_scores_gemma":[0.00005047219,0.00018043355,0.00016801714,0.00027064094,0.00009460011,0.0027736241,0.0002197659,0.00048266855,0.0000058994424],"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":[0.000050184157,0.00009093168,0.010695432,0.00006969249,0.00012697185,0.0003872147,0.00079382886,0.0000039999786,0.033244938,0.00054290966,0.000081970924,0.9539119],"study_design_scores_gemma":[0.009539393,0.0022447817,0.07188748,0.011551566,0.00037490405,0.02338736,0.0025583175,0.35361296,0.38416103,0.13403158,0.002040583,0.004610072],"about_ca_topic_score_codex":0.000007613344,"about_ca_topic_score_gemma":0.0000032496043,"teacher_disagreement_score":0.94930184,"about_ca_system_score_codex":0.00004714596,"about_ca_system_score_gemma":0.00012096941,"threshold_uncertainty_score":0.99993426},"labels":[],"label_agreement":null},{"id":"W2911424601","doi":"10.1145/3274658","title":"A Perspective Analysis of Handwritten Signature Technology","year":2019,"lang":"en","type":"review","venue":"ACM Computing Surveys","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":249,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Perspective (graphical); Signature (topology); Artificial intelligence; Natural language processing","score_opus":0.05095119436942392,"score_gpt":0.3541816603901525,"score_spread":0.30323046602072856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2911424601","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000037965772,0.6868256,0.31112796,0.00006686193,0.00021476188,0.00055048364,0.000050159826,0.0006752762,0.0004850956],"genre_scores_gemma":[0.000678742,0.94666314,0.05207967,0.0000455665,0.0000796822,0.000032085456,0.00013356163,0.000066356966,0.00022118595],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9946559,0.0017903808,0.001123816,0.0013720626,0.00050001225,0.0005578079],"domain_scores_gemma":[0.9925381,0.0020037133,0.0012987347,0.0031595682,0.00091231527,0.000087577675],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0032018684,0.0006515728,0.003950426,0.0043596816,0.000113089416,0.00014231607,0.0053592157,0.0010056255,0.000028628849],"category_scores_gemma":[0.0012646598,0.00057716673,0.0014142417,0.0109877465,0.00015750046,0.00018133849,0.0025289308,0.0011214649,0.0000942404],"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":[3.0285062e-7,0.00006415743,0.000044410615,0.0013391898,0.0023157601,0.00001540321,0.00013281206,0.00000610233,8.5164805e-7,0.0028819565,0.00027082508,0.9929282],"study_design_scores_gemma":[0.0012949143,0.0012996815,0.0010175197,0.04244998,0.030904181,0.00033918617,0.00033431302,0.018810654,0.00027934104,0.026133738,0.86915797,0.0079785],"about_ca_topic_score_codex":0.000112544665,"about_ca_topic_score_gemma":0.000022527844,"teacher_disagreement_score":0.9849497,"about_ca_system_score_codex":0.0002836912,"about_ca_system_score_gemma":0.00042391286,"threshold_uncertainty_score":0.999668},"labels":[],"label_agreement":null},{"id":"W2914305639","doi":"10.1145/3573128","title":"Proceedings of the ACM Symposium on Document Engineering 2023","year":2023,"lang":"en","type":"paratext","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science","score_opus":0.014383199818227593,"score_gpt":0.2505038453166223,"score_spread":0.2361206454983947,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2914305639","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006546494,0.000093392235,0.01774779,0.008471639,0.007017443,0.001960157,0.00005539574,0.0018144755,0.9621851],"genre_scores_gemma":[0.0031579991,0.000607779,0.034471925,0.0006339012,0.0004942698,0.00050830445,0.000017012731,0.00011147981,0.95999736],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99826163,0.000009665996,0.00037306658,0.0005061551,0.0005481558,0.000301354],"domain_scores_gemma":[0.9984033,0.00012395608,0.00021205826,0.0010004645,0.00019848316,0.00006173237],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000283713,0.0002867343,0.0003167603,0.00028706866,0.000056002224,0.00019977002,0.004355044,0.00023342622,0.0003499808],"category_scores_gemma":[0.00013015268,0.00019714063,0.00018850093,0.00078391,0.000027487251,0.00019519616,0.0021282115,0.0004093055,0.00525689],"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":[9.973742e-7,0.000016695718,8.475761e-7,0.00016879872,0.000029404651,6.882059e-7,0.00006405452,0.000018404258,0.0026736883,0.007857082,0.9879032,0.001266184],"study_design_scores_gemma":[0.0002303165,0.00029015358,0.000071033624,0.002062858,0.000025763708,0.000013894643,0.000022215603,0.0012274936,0.6250036,0.0045985878,0.36563817,0.0008159349],"about_ca_topic_score_codex":0.0000360497,"about_ca_topic_score_gemma":0.0000011910829,"teacher_disagreement_score":0.6223299,"about_ca_system_score_codex":0.00009989467,"about_ca_system_score_gemma":0.00007138924,"threshold_uncertainty_score":0.9955176},"labels":[],"label_agreement":null},{"id":"W2917150894","doi":"10.1109/icdar.2011.287","title":"ICDAR 2011 - Arabic Handwriting Recognition Competition","year":2011,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":48,"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":"Université de Sfax; University of Jordan; Concordia University; University of Sharjah","keywords":"Arabic; Handwriting; Competition (biology); Handwriting recognition; Computer science; Artificial intelligence; Text recognition; Speech recognition; Natural language processing; Feature extraction; Linguistics; Image (mathematics); Biology","score_opus":0.050161789846536166,"score_gpt":0.23800465704765017,"score_spread":0.187842867201114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2917150894","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":[0.008742184,0.000029798679,0.81242436,0.00016841336,0.00016320603,0.00020423546,0.0000039503448,0.0015201424,0.1767437],"genre_scores_gemma":[0.6217699,0.000047600613,0.37680066,0.00076351233,0.00007639863,0.00006925057,0.000021311494,0.000014983276,0.0004363942],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99869347,0.0000905061,0.0003061261,0.00040087756,0.0002154175,0.00029362566],"domain_scores_gemma":[0.99913776,0.00004656701,0.00010607177,0.00038259738,0.00021645548,0.000110535744],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00038784798,0.00015461067,0.00015287548,0.00021135081,0.00015146297,0.0001085584,0.00048767004,0.000094419214,0.0024566476],"category_scores_gemma":[0.000030360594,0.00014981123,0.000082135215,0.00021034926,0.00005377906,0.0011700717,0.00013529393,0.00015147244,0.002907568],"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":[0.000013777327,0.0003399039,0.00061239576,0.000041756073,0.000028480732,0.000049198738,0.0010186096,6.351725e-8,0.0058303936,0.1252483,0.004593803,0.8622233],"study_design_scores_gemma":[0.0007892781,0.0004553662,0.0053295484,0.00019060787,0.000021440617,0.00023499098,0.00018476043,0.0026652715,0.63878894,0.3473145,0.0030719296,0.00095331855],"about_ca_topic_score_codex":0.00012293128,"about_ca_topic_score_gemma":0.000020506612,"teacher_disagreement_score":0.86127,"about_ca_system_score_codex":0.00003331572,"about_ca_system_score_gemma":0.000029949191,"threshold_uncertainty_score":0.9984552},"labels":[],"label_agreement":null},{"id":"W2922340873","doi":"10.1109/iciscae.2018.8666847","title":"Research on Text Detection in Network Advertisement Picture Based on Depth Learning","year":2018,"lang":"en","type":"article","venue":"","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":"University of Toronto","keywords":"Computer science; Artificial intelligence; Artificial neural network; Deep learning; Order (exchange); Machine learning; Information retrieval; Data mining; Pattern recognition (psychology)","score_opus":0.03868862890194733,"score_gpt":0.3329343014802905,"score_spread":0.29424567257834316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2922340873","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":[0.014942941,0.0000063102134,0.85901815,0.00057763763,0.00014844144,0.00036379637,1.3237015e-7,0.00055012305,0.12439244],"genre_scores_gemma":[0.97487503,0.0000044402013,0.023075683,0.0011144101,0.00020184788,0.00005419406,0.0000011913426,0.00001099388,0.0006621935],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979622,0.00043466175,0.00018539131,0.00044312148,0.00054068747,0.0004339795],"domain_scores_gemma":[0.99909645,0.0002497506,0.00003700918,0.00037252155,0.00016728957,0.000076965815],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013767272,0.00011589945,0.000104398896,0.00042015378,0.00023426888,0.00012304181,0.00042289318,0.000107760075,0.0001933009],"category_scores_gemma":[0.00007220782,0.00009912567,0.000035698475,0.0010881815,0.00005375619,0.00015653296,0.000117437696,0.0005771415,0.00056732993],"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":[0.00006102118,0.00013700007,0.0010617238,0.000008024488,0.0000039429447,0.000013709489,0.00016570417,0.0014946228,0.0007824094,0.0028870625,0.0042173546,0.98916745],"study_design_scores_gemma":[0.0010919941,0.0064909146,0.026721355,0.0004917885,0.000002501791,0.0000051286593,0.00011700563,0.58707416,0.3330535,0.009867529,0.034540396,0.0005437053],"about_ca_topic_score_codex":0.000065980406,"about_ca_topic_score_gemma":0.0005030627,"teacher_disagreement_score":0.98862374,"about_ca_system_score_codex":0.00017834431,"about_ca_system_score_gemma":0.00004374643,"threshold_uncertainty_score":0.7292068},"labels":[],"label_agreement":null},{"id":"W2943378958","doi":"10.5539/cis.v12n2p126","title":"Arabic Hand Written Character Recognition Based on Contour Matching and Neural Network","year":2019,"lang":"en","type":"article","venue":"Computer and Information Science","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Character (mathematics); Artificial intelligence; Pattern recognition (psychology); Artificial neural network; Set (abstract data type); Arabic; Font; Matching (statistics); Intelligent character recognition; Word (group theory); Character recognition; Speech recognition; Natural language processing; Image (mathematics); Mathematics","score_opus":0.01252677328415966,"score_gpt":0.2283319288556304,"score_spread":0.21580515557147073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2943378958","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":[0.3296755,0.000009305775,0.6672936,0.00055225386,0.00039751115,0.00028927324,0.0000030573517,0.00016674788,0.0016127558],"genre_scores_gemma":[0.9527842,0.000015682741,0.039780695,0.0072924793,0.00008586754,0.000013713035,0.000011055637,0.0000034515988,0.000012864469],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99871254,0.00003950835,0.00029436397,0.00028972412,0.00037459919,0.00028927022],"domain_scores_gemma":[0.99912137,0.0001038588,0.00014594577,0.0002747229,0.00022068212,0.00013340206],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0008139084,0.00014282466,0.00015153072,0.00031524623,0.00033861992,0.0015249673,0.00039451238,0.000049719896,0.00001729308],"category_scores_gemma":[0.000016988219,0.00012345941,0.000026372181,0.00048329058,0.00015988055,0.009904249,0.00021176372,0.0001499024,0.000102773294],"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":[0.000014600606,0.000017442439,0.0012506017,0.00004402834,0.0000027630426,0.0000012299021,0.00095617166,0.00033845127,0.00045672824,0.0047533163,0.00033972913,0.9918249],"study_design_scores_gemma":[0.0005926445,0.00028324279,0.03769512,0.00014153468,0.0000024785372,0.000040991363,0.000015927995,0.95458764,0.0016779318,0.002353718,0.0023223748,0.0002864241],"about_ca_topic_score_codex":0.0000054466823,"about_ca_topic_score_gemma":3.6201664e-7,"teacher_disagreement_score":0.9915385,"about_ca_system_score_codex":0.000025911402,"about_ca_system_score_gemma":0.000053149302,"threshold_uncertainty_score":0.99951154},"labels":[],"label_agreement":null},{"id":"W2945538803","doi":"10.1145/3314994.3325080","title":"Poetry Form Checker","year":2019,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Rhyme; Poetry; Sonnet; Haiku; Line (geometry); Literature; Linguistics; Art; Computer science; Philosophy; Mathematics","score_opus":0.010059245827634258,"score_gpt":0.23864319663586647,"score_spread":0.2285839508082322,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2945538803","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":[0.023193903,0.000011363009,0.6415658,0.0005460174,0.00015482455,0.00014531206,3.4403476e-7,0.00087361457,0.33350885],"genre_scores_gemma":[0.7824081,0.0000054780435,0.20106772,0.0018809253,0.00002559519,0.000011836427,0.0000012329202,0.0000060204507,0.014593099],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99943286,0.000008565161,0.00009463974,0.00018427528,0.00013270618,0.00014694528],"domain_scores_gemma":[0.99950457,0.000015353502,0.000022231578,0.00036945104,0.000044294797,0.000044099976],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00011639882,0.000060276183,0.000070279435,0.000062816776,0.000020010233,0.00007513385,0.00043757723,0.000042098713,0.00089169794],"category_scores_gemma":[0.0000067106184,0.000049242357,0.00003956867,0.00016568706,0.000008076912,0.00048532974,0.00014720832,0.00006342269,0.003879801],"study_design_candidate":"theoretical_or_conceptual","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":[0.000001966293,0.00007392908,0.004416534,0.000020773188,0.000013141409,0.0000070050055,0.00024142637,1.4226693e-7,0.0058441516,0.6164451,0.027524889,0.34541094],"study_design_scores_gemma":[0.0007971534,0.0003128844,0.010832431,0.00005019669,0.0000040675095,0.00009065931,0.00006045977,0.018766535,0.6429379,0.12426851,0.20107618,0.00080306083],"about_ca_topic_score_codex":0.000008923429,"about_ca_topic_score_gemma":0.0000014696702,"teacher_disagreement_score":0.7592142,"about_ca_system_score_codex":0.000016334883,"about_ca_system_score_gemma":0.000018593997,"threshold_uncertainty_score":0.9968958},"labels":[],"label_agreement":null},{"id":"W2947932456","doi":"10.1186/s41074-019-0055-1","title":"Symbol spotting for architectural drawings: state-of-the-art and new industry-driven developments","year":2019,"lang":"en","type":"article","venue":"IPSJ Transactions on Computer Vision and Applications","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"Division of Materials Research; Natural Sciences and Engineering Research Council of Canada; Western Canada Research Grid; Compute Canada","keywords":"Spotting; Computer science; Symbol (formal); Categorization; False positive paradox; Clutter; Context (archaeology); Artificial intelligence; Segmentation; Focus (optics); Set (abstract data type); Pattern recognition (psychology); Programming language","score_opus":0.012601125367595722,"score_gpt":0.2605824088380535,"score_spread":0.24798128347045778,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2947932456","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":[0.027534943,0.000010561662,0.97010934,0.0010459401,0.00008340378,0.0009809551,0.00001282393,0.00013464446,0.00008739398],"genre_scores_gemma":[0.71228206,0.000011774504,0.28652266,0.00044774142,0.000027686177,0.00015396375,0.0000036661345,0.000012413524,0.0005380238],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99904203,0.000028334436,0.0002570346,0.00036416546,0.00015004704,0.0001583618],"domain_scores_gemma":[0.99924856,0.0001584883,0.00009674315,0.00031589498,0.000073842646,0.00010644345],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010143759,0.0001380281,0.00015304695,0.0001384894,0.00024450995,0.00012187274,0.0003320765,0.00007774386,0.000008999225],"category_scores_gemma":[0.0000019664922,0.000111511836,0.00006194574,0.00029285118,0.000048772607,0.00019118449,0.000037779933,0.00023378241,0.000014253769],"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":[0.000004930133,0.00005002106,0.00010012628,0.000024816085,0.000014693383,7.860447e-8,0.00024261266,0.00024184202,0.00078127795,0.0008497903,0.00018348583,0.9975063],"study_design_scores_gemma":[0.0068731466,0.0018902817,0.055866033,0.001812819,0.00012915557,0.000383115,0.00015360443,0.5123202,0.15339617,0.056087848,0.20861752,0.0024700598],"about_ca_topic_score_codex":0.0000058960754,"about_ca_topic_score_gemma":0.0000039517436,"teacher_disagreement_score":0.99503624,"about_ca_system_score_codex":0.000018647415,"about_ca_system_score_gemma":0.00006188648,"threshold_uncertainty_score":0.45473206},"labels":[],"label_agreement":null},{"id":"W2950827670","doi":"","title":"Not Gorgythion Struck by an Arrow","year":2012,"lang":"en","type":"article","venue":"Dalhousie review","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Arrow; History; Art; Computer science","score_opus":0.02838053674949871,"score_gpt":0.29434293497653385,"score_spread":0.26596239822703516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950827670","genre_codex":"methods","genre_gemma":"review","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":[0.0047061467,0.2578533,0.70901924,0.005437414,0.0010014822,0.002061461,0.00006135731,0.00378615,0.01607343],"genre_scores_gemma":[0.25871348,0.39024633,0.29075438,0.05609606,0.0011010654,0.0006699344,0.00030631913,0.00018053228,0.001931888],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99843436,0.00020247162,0.00033928262,0.00031352168,0.00030605152,0.00040429545],"domain_scores_gemma":[0.9986744,0.0000409764,0.00014328696,0.0008031401,0.00008007398,0.00025812548],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008407481,0.00018172585,0.00031485604,0.000051208317,0.00008584161,0.000080991806,0.00078855164,0.00007379586,0.00021853035],"category_scores_gemma":[0.00006870668,0.00015827596,0.000095600284,0.0003503312,0.000028776427,0.0013528389,0.00016374457,0.00016344943,0.0006844591],"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":[5.5420986e-7,0.00012833405,0.000097743105,0.0005411773,0.0000075413377,0.0000024339702,0.00010974972,1.3214943e-8,0.0013939184,0.004815355,0.04203478,0.9508684],"study_design_scores_gemma":[0.00011803905,0.00011430236,0.00023697871,0.0012252722,0.00003096464,0.000099731675,0.0000033426597,0.000108905646,0.023296177,0.00061388995,0.97369397,0.00045840666],"about_ca_topic_score_codex":0.000011052374,"about_ca_topic_score_gemma":0.0000016549717,"teacher_disagreement_score":0.95041,"about_ca_system_score_codex":0.000032430355,"about_ca_system_score_gemma":0.000030021434,"threshold_uncertainty_score":0.8797565},"labels":[],"label_agreement":null},{"id":"W2950835523","doi":"10.1142/9789811203527_0004","title":"Handwriting Recognition Systems and Applications","year":2019,"lang":"en","type":"book-chapter","venue":"WORLD SCIENTIFIC eBooks","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","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":"Concordia University","funders":"","keywords":"Handwriting; Computer science; Speech recognition; Artificial intelligence","score_opus":0.031111375738270792,"score_gpt":0.23962296532852562,"score_spread":0.20851158959025481,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950835523","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000064613396,0.0006017569,0.09442051,0.0000493457,0.0008411535,0.0014267951,0.0000782231,0.00073648134,0.90183926],"genre_scores_gemma":[0.0014398432,0.0000075040807,0.0067407154,0.00010874151,0.0002491257,0.0002222555,0.00010324123,0.0000515995,0.99107695],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.997218,0.000041722335,0.0005613765,0.0012451042,0.0005744652,0.0003592982],"domain_scores_gemma":[0.99771214,0.00015771945,0.000406852,0.0011516216,0.0003942843,0.00017741292],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009048474,0.00036962947,0.0004228058,0.0009911611,0.00052810775,0.0018631393,0.0007947198,0.00022119159,0.00006625101],"category_scores_gemma":[0.000007187106,0.0003933348,0.000129199,0.00011159286,0.00032757912,0.00026132792,0.00041714523,0.0004558992,0.0011623768],"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":[0.0000016951501,0.0000108110735,0.000002511578,0.00023258058,0.00003289884,0.000009976823,0.00010910224,2.8793954e-7,0.00041806832,0.6308859,0.012637735,0.35565844],"study_design_scores_gemma":[0.00014730493,0.000022921024,0.000001434082,0.0007816015,0.000031923682,0.000050148617,0.0000080323425,0.0004823947,0.000947425,0.07371525,0.92325884,0.00055269874],"about_ca_topic_score_codex":0.0000041302615,"about_ca_topic_score_gemma":0.00011255062,"teacher_disagreement_score":0.9106211,"about_ca_system_score_codex":0.00009229135,"about_ca_system_score_gemma":0.00017969596,"threshold_uncertainty_score":0.9998519},"labels":[],"label_agreement":null},{"id":"W2951021636","doi":"10.48550/arxiv.1306.4966","title":"Determining Points on Handwritten Mathematical Symbols","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Handwriting; Computer science; Variety (cybernetics); Baseline (sea); Simple (philosophy); Diagram; Scale (ratio); Artificial intelligence; Natural language processing; Pattern recognition (psychology)","score_opus":0.07289076049738406,"score_gpt":0.20769780011144276,"score_spread":0.1348070396140587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951021636","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":[0.19228326,0.000009487006,0.78927124,0.00023017262,0.00027297056,0.0006103178,0.000011695901,0.0011594009,0.01615144],"genre_scores_gemma":[0.97504604,0.00005345043,0.022499979,0.0004418792,0.000083745275,0.000010667389,0.000011646562,0.000036823556,0.0018157825],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997408,0.00020267122,0.00034399747,0.0013471311,0.00018472153,0.00051352114],"domain_scores_gemma":[0.99724394,0.00027048198,0.00029725197,0.0016849162,0.00021615495,0.00028723732],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00034872213,0.00046894766,0.00053585245,0.0004611559,0.00016509967,0.00037575603,0.0024333864,0.00048296977,0.0002850392],"category_scores_gemma":[0.00010275432,0.00050451973,0.00029872762,0.00037630013,0.0001299295,0.0005156186,0.0022522034,0.00086411845,0.00232727],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030099567,0.0006767084,0.0009288314,0.00049058395,0.00028778694,0.0016571115,0.0008747209,0.0012877348,0.0002524302,0.9502553,0.0060392274,0.03721947],"study_design_scores_gemma":[0.00054341933,0.00020167102,0.0004530204,0.0009317145,0.00006800434,0.00003611477,0.000056534565,0.27472612,0.004131817,0.71745276,0.0003496969,0.0010491299],"about_ca_topic_score_codex":0.000016888021,"about_ca_topic_score_gemma":0.000002378351,"teacher_disagreement_score":0.78276277,"about_ca_system_score_codex":0.00020010435,"about_ca_system_score_gemma":0.00012417976,"threshold_uncertainty_score":0.99974066},"labels":[],"label_agreement":null},{"id":"W2951574664","doi":"10.48550/arxiv.1807.10755","title":"A writer-independent approach for offline signature verification using deep convolutional neural networks features","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec","funders":"","keywords":"Convolutional neural network; Computer science; Artificial intelligence; Support vector machine; Classifier (UML); Pattern recognition (psychology); Signature (topology); Machine learning; Mathematics","score_opus":0.06908249157228466,"score_gpt":0.21585726993310458,"score_spread":0.14677477836081992,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951574664","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":[0.015859233,0.00019363791,0.9814946,0.000046000645,0.00053694664,0.000996549,0.00005454446,0.00051235565,0.00030611473],"genre_scores_gemma":[0.88924885,0.000039327886,0.10948502,0.00016757495,0.0004282701,0.000011444862,0.00034309222,0.000029680288,0.00024674044],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974771,0.00018371944,0.00028640937,0.0014326827,0.00016619249,0.0004538655],"domain_scores_gemma":[0.99762315,0.00010134012,0.00041495168,0.0010361074,0.00065455533,0.00016989898],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00039340794,0.0004136336,0.0003790116,0.00034283995,0.0003058805,0.00023509841,0.0017890567,0.0007900679,0.00002006008],"category_scores_gemma":[0.000038941052,0.0004771342,0.00032530146,0.0004759363,0.00017343202,0.00047993095,0.0010688463,0.00084250985,0.000004614192],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003498403,0.00066696404,0.0010720866,0.00039756965,0.0004290991,0.00010611139,0.000336118,0.8919016,0.0005937058,0.0923849,0.0034233632,0.00833861],"study_design_scores_gemma":[0.000480782,0.000077495024,0.00060294557,0.000053664542,0.00008561236,0.0000251437,0.000022052087,0.9844923,0.00037407686,0.013186019,0.00009755287,0.00050234376],"about_ca_topic_score_codex":0.0000488455,"about_ca_topic_score_gemma":0.000011524775,"teacher_disagreement_score":0.8733896,"about_ca_system_score_codex":0.00033770467,"about_ca_system_score_gemma":0.00015065444,"threshold_uncertainty_score":0.999768},"labels":[],"label_agreement":null},{"id":"W2951828725","doi":"10.48550/arxiv.1409.5317","title":"A Bayesian model for recognizing handwritten mathematical expressions","year":2014,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Parsing; Parse tree; Probabilistic logic; Bayesian network; Artificial intelligence; Ambiguity; Tree (set theory); Identification (biology); Pattern recognition (psychology); Natural language processing; Bayesian probability; Machine learning; Mathematics","score_opus":0.09535052164430832,"score_gpt":0.2244525857650222,"score_spread":0.12910206412071387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951828725","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":[0.0032527791,0.000016771517,0.9910195,0.0002354767,0.00016689004,0.0008645005,0.00004593124,0.0010535041,0.0033446513],"genre_scores_gemma":[0.7663836,0.0000438862,0.23109438,0.00022097486,0.00008177883,0.000029152854,0.00002837084,0.000040342784,0.0020775262],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974192,0.00014384695,0.00037510664,0.0013979457,0.00012769307,0.00053620053],"domain_scores_gemma":[0.9972062,0.0003429935,0.00032026222,0.0015076338,0.0003167692,0.0003061532],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000539439,0.00043319882,0.00056769815,0.00038553818,0.00028560948,0.00024807962,0.0021883615,0.0005438748,0.00004063411],"category_scores_gemma":[0.0001715384,0.00047621186,0.0004392809,0.00028761372,0.00010710799,0.00042872078,0.0019504653,0.00060037494,0.00008262365],"study_design_candidate":"theoretical_or_conceptual","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":[0.00013291449,0.0009396863,0.00014534622,0.0018212935,0.00044161317,0.00022138363,0.0022530057,0.12325171,0.0012126385,0.8219054,0.015950385,0.031724654],"study_design_scores_gemma":[0.00025738377,0.000027757915,0.0000021252822,0.00029009933,0.00004616285,0.00000435246,0.000014267623,0.5924052,0.0006442704,0.40581813,0.00014129296,0.00034891078],"about_ca_topic_score_codex":0.000008974644,"about_ca_topic_score_gemma":0.000007719916,"teacher_disagreement_score":0.76313084,"about_ca_system_score_codex":0.00014659713,"about_ca_system_score_gemma":0.00020925347,"threshold_uncertainty_score":0.999769},"labels":[],"label_agreement":null},{"id":"W2954094885","doi":"10.1109/synasc.2018.00023","title":"Real-Time Computation of Legendre-Sobolev Approximations","year":2018,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Legendre polynomials; Legendre function; Associated Legendre polynomials; Mathematics; Legendre wavelet; Series (stratigraphy); Sobolev space; Legendre's equation; Representation (politics); Mathematical analysis; Applied mathematics; Orthogonal polynomials; Computer science; Classical orthogonal polynomials; Wavelet; Wavelet transform; Gegenbauer polynomials","score_opus":0.01792191850684955,"score_gpt":0.27449614808730105,"score_spread":0.2565742295804515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2954094885","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":[0.0050763367,0.0000041561952,0.8822568,0.00023209587,0.000050812963,0.00014019183,0.000002069278,0.0005708372,0.11166672],"genre_scores_gemma":[0.42323098,0.0000067338565,0.57594603,0.000061805054,0.000044005592,0.000011883795,0.0000046814307,0.0000056819877,0.0006881847],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99921435,0.000046273693,0.00023881589,0.00019633787,0.00017947984,0.00012471674],"domain_scores_gemma":[0.99924237,0.00004177349,0.000097948796,0.0002688113,0.00030375653,0.000045364664],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020257528,0.000073533156,0.00011412304,0.00014694933,0.000067776695,0.000045749905,0.00034089587,0.000044259898,0.00012035757],"category_scores_gemma":[0.000019770501,0.00006894199,0.000041246964,0.0003768972,0.00008555062,0.0004063162,0.00010156051,0.000035652673,0.00038246723],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000075640655,0.00034190604,0.00012528076,0.000068280206,0.000044508317,0.0000031032532,0.001975783,0.000011032963,0.16303828,0.40058827,0.034948204,0.3988478],"study_design_scores_gemma":[0.00028980992,0.00032814377,0.0010251085,0.000058164533,0.0000080637565,0.00001940887,0.000033660894,0.20950912,0.738318,0.049130663,0.0010170465,0.0002627733],"about_ca_topic_score_codex":0.00003466266,"about_ca_topic_score_gemma":0.0000036303754,"teacher_disagreement_score":0.5752798,"about_ca_system_score_codex":0.000016461612,"about_ca_system_score_gemma":0.000041309002,"threshold_uncertainty_score":0.491597},"labels":[],"label_agreement":null},{"id":"W295672701","doi":"10.1299/jsmermd.2008._1p1-i23_1","title":"1P1-I23 Simulating Finger Pad Deformation under Line Loading Using Shell Structure Enclosing Fluid-Like Material","year":2008,"lang":"en","type":"article","venue":"The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Stiffness; Deflection (physics); Computer science; Deformation (meteorology); Shell (structure); Materials science; Mechanics; Structural engineering; Physics; Composite material; Classical mechanics; Engineering","score_opus":0.03514795239690291,"score_gpt":0.25948836610149095,"score_spread":0.22434041370458804,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W295672701","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":[0.7460787,0.000059551152,0.25176,0.00085267564,0.00027944183,0.0004643855,0.00003314146,0.00023300685,0.00023902932],"genre_scores_gemma":[0.94093806,0.00017775389,0.058360558,0.0003298838,0.00011142904,0.000005467155,0.000010966168,0.000029018964,0.000036897378],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99785936,0.000027350125,0.00060503895,0.0004709201,0.00050555513,0.00053177756],"domain_scores_gemma":[0.9982022,0.00008165544,0.00048874697,0.00022900145,0.0008707141,0.00012769185],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00049123383,0.00036035423,0.00041978408,0.00025312832,0.0005729067,0.00035014548,0.00070301455,0.00021362375,0.000021375385],"category_scores_gemma":[0.00006507259,0.0002872025,0.00008943168,0.0003648828,0.0001662581,0.0011743695,0.00044484966,0.00038980498,0.000002959201],"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":[0.00012144205,0.00017960244,0.0002054713,0.00037755442,0.00013933338,0.0000044344233,0.0124075115,0.04082914,0.47987083,0.4560745,0.00021756023,0.009572626],"study_design_scores_gemma":[0.0007203484,0.0006571007,0.00006622887,0.00054282683,0.00007153187,0.0001499773,0.0018268256,0.7070555,0.21364878,0.07447292,0.00005018425,0.00073774706],"about_ca_topic_score_codex":0.000030145131,"about_ca_topic_score_gemma":0.0000020800255,"teacher_disagreement_score":0.6662264,"about_ca_system_score_codex":0.00010409899,"about_ca_system_score_gemma":0.00012001771,"threshold_uncertainty_score":0.99995804},"labels":[],"label_agreement":null},{"id":"W2959393087","doi":"10.5539/ach.v11n2p66","title":"Recognition of Variety for $100 Malaya Japanese Invasion Money Pick Number M8a: Capital Block Letter M and Number of Ropes","year":2019,"lang":"en","type":"article","venue":"Asian Culture and History","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Variety (cybernetics); Block (permutation group theory); Capital (architecture); Dimension (graph theory); Economics; Finance; History; Mathematics; Computer science; Artificial intelligence; Ancient history; Combinatorics","score_opus":0.012955822269896777,"score_gpt":0.22332215730692112,"score_spread":0.21036633503702434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2959393087","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":[0.9375036,0.00088453083,0.0038154838,0.00070152123,0.00049916224,0.0010953831,0.000058025067,0.00019250452,0.055249825],"genre_scores_gemma":[0.96497905,0.00011753405,0.03027113,0.0006418183,0.00008350247,0.000040012586,0.000030474397,0.00001737314,0.0038190985],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990836,0.00004355968,0.00025221505,0.00032569055,0.00015149722,0.00014345373],"domain_scores_gemma":[0.9993233,0.00003084683,0.00016851118,0.00022936864,0.00018143219,0.00006653444],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014131122,0.00014695531,0.0002551694,0.000048822923,0.000044572662,0.000020009742,0.00015750383,0.00015909605,0.00012621912],"category_scores_gemma":[0.000016520622,0.00012799088,0.000075791875,0.00007093767,0.00010623798,0.00043383474,0.0000779342,0.00011929979,0.000037283662],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030332175,0.0010839523,0.02229033,0.0029840989,0.00035434976,0.000032179614,0.13048622,7.1376195e-7,0.19022046,0.012077735,0.4750114,0.16515523],"study_design_scores_gemma":[0.008085577,0.002235245,0.022713406,0.0017709576,0.00044607208,0.00093352783,0.003968898,0.0006217619,0.15579253,0.026452273,0.7737441,0.0032356677],"about_ca_topic_score_codex":0.00009704831,"about_ca_topic_score_gemma":0.00002462347,"teacher_disagreement_score":0.29873267,"about_ca_system_score_codex":0.000046005283,"about_ca_system_score_gemma":0.00003262833,"threshold_uncertainty_score":0.52193165},"labels":[],"label_agreement":null},{"id":"W2963047498","doi":"10.1109/tpami.2017.2695539","title":"Drawing and Recognizing Chinese Characters with Recurrent Neural Network","year":2017,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":356,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"National Natural Science Foundation of China","keywords":"Recurrent neural network; Computer science; Discriminative model; Artificial intelligence; Handwriting; Chinese characters; Generative grammar; Handwriting recognition; Convolutional neural network; Deep learning; Intelligent character recognition; Natural language processing; Generative model; Embedding; Task (project management); Pattern recognition (psychology); Machine learning; Speech recognition; Artificial neural network; Feature extraction; Character recognition; Image (mathematics)","score_opus":0.022859438703082557,"score_gpt":0.2794097470582382,"score_spread":0.25655030835515563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963047498","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":[0.08779517,0.00006543513,0.91097325,0.0006558556,0.00016280691,0.00013863906,0.0000108243885,0.00013065491,0.00006733948],"genre_scores_gemma":[0.9947261,0.0005675383,0.004222524,0.0003451156,0.00004079559,0.00003208306,0.0000032369421,0.000013231737,0.00004934517],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985103,0.000074875206,0.00030264896,0.00060743117,0.00021899458,0.00028572744],"domain_scores_gemma":[0.99876213,0.00010801638,0.00021930561,0.0006696469,0.000079133526,0.00016174871],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003030669,0.000266246,0.0003568934,0.00030327783,0.000829989,0.0007106006,0.00051648484,0.00005887709,0.00003336067],"category_scores_gemma":[0.000007708395,0.00020292428,0.00013864908,0.00039160185,0.00012489443,0.0006864777,0.000016520484,0.00033706546,0.000007126956],"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":[0.000012155474,0.000046393754,0.008033604,0.000012393428,0.00022445206,0.000015472559,0.00021500829,0.00044989912,0.00007594974,0.00001212595,0.0000021409649,0.9909004],"study_design_scores_gemma":[0.0006087202,0.0010058727,0.18796074,0.00050083606,0.0013401576,0.00021597487,0.00007781589,0.757223,0.047433484,0.0016936138,0.0001038886,0.0018359009],"about_ca_topic_score_codex":0.00049786153,"about_ca_topic_score_gemma":0.0012845931,"teacher_disagreement_score":0.9890645,"about_ca_system_score_codex":0.000018579072,"about_ca_system_score_gemma":0.000011240588,"threshold_uncertainty_score":0.8275012},"labels":[],"label_agreement":null},{"id":"W2964548271","doi":"10.1109/pria.2019.8786006","title":"Line Segmentation in Persian Handwritten Documents Based on a Novel Projection Histogram Method","year":2019,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Histogram; Artificial intelligence; Skew; Pattern recognition (psychology); Computer science; Image segmentation; Maxima and minima; Balanced histogram thresholding; Histogram matching; Computer vision; Projection (relational algebra); Segmentation; Smoothing; Image (mathematics); Mathematics; Algorithm","score_opus":0.016909799210114273,"score_gpt":0.3020595621330265,"score_spread":0.2851497629229122,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964548271","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":[0.003790252,0.0000034495715,0.97994596,0.00095118984,0.0001705271,0.00082703447,0.00000176976,0.0004275751,0.013882238],"genre_scores_gemma":[0.28395045,0.000001956643,0.7125252,0.0016955105,0.000022190616,0.00013779712,0.00001909339,0.000012424819,0.0016353836],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985986,0.00010459047,0.00025840604,0.0004777402,0.00033470325,0.00022598954],"domain_scores_gemma":[0.9993447,0.00007575441,0.000089551686,0.00035625946,0.000077713434,0.000056021498],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005741202,0.00014999822,0.00016077017,0.0005224456,0.00004451722,0.00013557487,0.00032061152,0.00008807699,0.00017388928],"category_scores_gemma":[0.00002224666,0.00013794197,0.000065993,0.00060633064,0.000010852599,0.00057751726,0.000057412555,0.00015799461,0.0001562523],"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":[0.00011440535,0.0016162979,0.0050702873,0.000101120306,0.00002697428,0.000011198006,0.0013287227,0.00048527165,0.08831127,0.0062319436,0.0016146807,0.89508784],"study_design_scores_gemma":[0.0031506224,0.0011965932,0.0020820622,0.00015270682,0.0000085614265,0.000013926527,0.00016940203,0.8215323,0.16675758,0.0011599916,0.003287599,0.0004886479],"about_ca_topic_score_codex":0.00039528488,"about_ca_topic_score_gemma":0.000045371504,"teacher_disagreement_score":0.8945992,"about_ca_system_score_codex":0.00024912006,"about_ca_system_score_gemma":0.000061643615,"threshold_uncertainty_score":0.562511},"labels":[],"label_agreement":null},{"id":"W2965749646","doi":"10.1109/crv.2019.00013","title":"Rectification of Camera-Captured Document Images with Mixed Contents and Varied Layouts","year":2019,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Perspective distortion; Rectification; Computer science; Distortion (music); Artificial intelligence; Computer vision; Image rectification; Perspective (graphical); Transformation (genetics); Document layout analysis; Readability; Graphics; Computer graphics (images); Geometric transformation; Information retrieval; Pattern recognition (psychology); Image (mathematics); Physics","score_opus":0.010052107007502914,"score_gpt":0.22703160619269486,"score_spread":0.21697949918519194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2965749646","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":[0.27860898,0.00006278368,0.7072056,0.0008265126,0.00012549963,0.00069730723,0.0000038942803,0.0002985667,0.012170848],"genre_scores_gemma":[0.931031,0.000015862583,0.06741119,0.00014633879,0.000004571064,0.000021660639,0.0000035976693,0.000005275037,0.0013604934],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99921644,0.000049373375,0.00016939844,0.00027104453,0.00018183382,0.00011192657],"domain_scores_gemma":[0.99927276,0.000051685296,0.00010874587,0.00034256346,0.00017839608,0.000045819812],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016469098,0.00009080009,0.00014780824,0.000081729166,0.000023975716,0.000075422344,0.00021928619,0.000039838364,0.000050933846],"category_scores_gemma":[0.000013916747,0.00006712832,0.000018268829,0.00015485451,0.000039887003,0.00038748467,0.00006709949,0.000056384593,0.000025460888],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017576906,0.00039886168,0.026095418,0.00020392294,0.00022111526,0.000011505611,0.0027006005,0.000005880484,0.5861295,0.05752638,0.0061285966,0.32040247],"study_design_scores_gemma":[0.00076979684,0.0003083679,0.022210084,0.00005884929,0.000009834084,0.00001924647,0.00011408544,0.0004326529,0.9727666,0.0025407737,0.00057143107,0.00019831794],"about_ca_topic_score_codex":0.00012831987,"about_ca_topic_score_gemma":0.000011267638,"teacher_disagreement_score":0.652422,"about_ca_system_score_codex":0.000015429467,"about_ca_system_score_gemma":0.00001888846,"threshold_uncertainty_score":0.27374136},"labels":[],"label_agreement":null},{"id":"W2969633502","doi":"10.1109/icnas.2019.8807829","title":"An efficient multiple-classifier system for Arabic calligraphy style recognition","year":2019,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Calligraphy; Unavailability; Computer science; Arabic; Classifier (UML); Style (visual arts); Artificial intelligence; Natural language processing; Correctness; Pattern recognition (psychology); Linguistics; Engineering; Programming language","score_opus":0.020537262615843068,"score_gpt":0.24855033070979868,"score_spread":0.2280130680939556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2969633502","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":[0.14604305,0.000013111679,0.8455257,0.000096416225,0.0003823173,0.0011927454,0.000023096072,0.0015111462,0.0052124276],"genre_scores_gemma":[0.85670125,0.0000018944983,0.14252321,0.00019920501,0.000051303647,0.0002659408,0.000032667416,0.000017125487,0.00020738808],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983576,0.00009029926,0.00032243534,0.00061306386,0.0002691184,0.0003474721],"domain_scores_gemma":[0.99855804,0.00020247337,0.00011457468,0.0006676894,0.00030967777,0.00014754462],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048553085,0.00018271341,0.00021799529,0.0002665709,0.00010799577,0.00021497892,0.0005990271,0.00012707859,0.000058475056],"category_scores_gemma":[0.000028637816,0.00015930578,0.00015006072,0.00035079266,0.000024514717,0.0004478914,0.00005900786,0.00010143758,0.0005386584],"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":[0.00017685712,0.0017371328,0.004674308,0.0011274117,0.00016439566,0.000020233125,0.0015337424,0.00022661363,0.11448938,0.0682855,0.0061080414,0.8014564],"study_design_scores_gemma":[0.0016065255,0.00081313046,0.0013692724,0.0002014326,0.000018956593,0.00003528962,0.00037926686,0.7459229,0.24471915,0.0015651647,0.0026249771,0.0007439129],"about_ca_topic_score_codex":0.00003040982,"about_ca_topic_score_gemma":0.000012602795,"teacher_disagreement_score":0.80071247,"about_ca_system_score_codex":0.00007278681,"about_ca_system_score_gemma":0.000038473052,"threshold_uncertainty_score":0.6923544},"labels":[],"label_agreement":null},{"id":"W2970712536","doi":"10.48550/arxiv.1908.11550","title":"Handwritten Chinese Character Recognition by Convolutional Neural Network and Similarity Ranking","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Softmax function; Pattern recognition (psychology); Convolutional neural network; Artificial intelligence; Similarity (geometry); Computer science; Cross entropy; Ranking (information retrieval); Entropy (arrow of time); Euclidean distance; Artificial neural network; Mathematics; Image (mathematics)","score_opus":0.04240639175468045,"score_gpt":0.1921913100682666,"score_spread":0.14978491831358615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2970712536","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":[0.51301783,0.00022360744,0.48322874,0.00032389705,0.00077040883,0.00063876546,0.00014441273,0.0006388532,0.001013501],"genre_scores_gemma":[0.99485034,0.00040199133,0.0029089034,0.0006776363,0.0002507985,0.000005166202,0.00036073208,0.000027584378,0.000516871],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99740165,0.0002851567,0.00030623437,0.0013538678,0.00015891799,0.0004941778],"domain_scores_gemma":[0.9981937,0.00021402772,0.00035696157,0.00075972866,0.00028365047,0.00019195816],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00047887643,0.000459344,0.00050148583,0.00021775598,0.00025761104,0.00030199625,0.0010148158,0.000508689,0.0000841721],"category_scores_gemma":[0.000044850778,0.0005141692,0.00021218193,0.0004424485,0.00015608397,0.00090743613,0.0017752511,0.0009806473,0.000092307724],"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":[0.0015216989,0.0025932782,0.5871199,0.003223608,0.0029463489,0.0023527243,0.002522073,0.04605762,0.0034321586,0.06715313,0.10245856,0.17861892],"study_design_scores_gemma":[0.0017580562,0.00014702523,0.025329838,0.00043400907,0.00013983676,0.00006134352,0.000015888376,0.7921199,0.0002745916,0.17654568,0.0015177368,0.0016560602],"about_ca_topic_score_codex":0.000080584156,"about_ca_topic_score_gemma":0.000017986986,"teacher_disagreement_score":0.74606234,"about_ca_system_score_codex":0.0001475282,"about_ca_system_score_gemma":0.00010667394,"threshold_uncertainty_score":0.999731},"labels":[],"label_agreement":null},{"id":"W2982447515","doi":"10.1109/ccst.2019.8888418","title":"Generating Off-line and On-line Forgeries from On-line Genuine Signatures","year":2019,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Polytechnique Montréal","funders":"","keywords":"Line (geometry); Trajectory; Signature (topology); Computer science; Point (geometry); Kinematics; Artificial intelligence; Set (abstract data type); Line segment; Single line; Computer vision; Pattern recognition (psychology); Data mining; Algorithm; Mathematics; Engineering drawing; Engineering","score_opus":0.02571388835525586,"score_gpt":0.27341823223588735,"score_spread":0.24770434388063148,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2982447515","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":[0.5006444,0.00067944877,0.48917618,0.0031945766,0.000489546,0.0005898417,0.000057703124,0.0011648209,0.004003474],"genre_scores_gemma":[0.82382435,0.00014328938,0.16637035,0.006315071,0.00040497957,0.00003073228,0.00006537138,0.000029544279,0.002816305],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9982414,0.000065568674,0.00036616105,0.00066332053,0.00035292853,0.00031062],"domain_scores_gemma":[0.998663,0.00032547503,0.000120706136,0.0006270886,0.00013847339,0.00012525641],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026390067,0.00027894648,0.00032644108,0.00016862153,0.00011824911,0.00023518805,0.0004886496,0.00014926589,0.00036983832],"category_scores_gemma":[0.00009723094,0.00022076628,0.00007073338,0.0002285283,0.000048350747,0.0003759315,0.00026052998,0.0002910467,0.00023333204],"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":[0.000092024784,0.00037958086,0.00032930897,0.000043263488,0.00009860339,0.000048456826,0.00049496786,0.0020013202,0.08077001,0.030557884,0.009927763,0.87525684],"study_design_scores_gemma":[0.000997658,0.0018173871,0.0001905953,0.00014656574,0.000011457092,0.000010156005,0.000033994453,0.37955534,0.59876776,0.009228928,0.008615237,0.00062492245],"about_ca_topic_score_codex":0.00006543769,"about_ca_topic_score_gemma":0.00004718467,"teacher_disagreement_score":0.8746319,"about_ca_system_score_codex":0.000025437825,"about_ca_system_score_gemma":0.000039607196,"threshold_uncertainty_score":0.9002588},"labels":[],"label_agreement":null},{"id":"W2997702402","doi":"10.1007/978-3-030-37731-1_18","title":"Towards Accurate Panel Detection in Manga: A Combined Effort of CNN and Heuristics","year":2019,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":3,"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":"Computer science; Heuristics; Artificial intelligence; Pattern recognition (psychology); Machine learning; Information retrieval; Operating system","score_opus":0.02211368890219727,"score_gpt":0.25072010165949143,"score_spread":0.22860641275729415,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2997702402","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":[0.0026086618,0.00014869405,0.99416363,0.00017369844,0.00068163424,0.00058967515,0.000006945933,0.0001437518,0.0014833239],"genre_scores_gemma":[0.82596827,0.00013231115,0.17325996,0.00038482438,0.000079298945,0.0000125312135,0.0000042695333,0.00002744223,0.00013107277],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970699,0.000038338872,0.00063805195,0.001080214,0.00072993065,0.00044358158],"domain_scores_gemma":[0.998065,0.00029356236,0.00036687384,0.0008690855,0.00029989224,0.000105603525],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009784162,0.00041295248,0.00062851637,0.0012747046,0.0000774176,0.00025312568,0.0016165626,0.0003623645,0.000008506377],"category_scores_gemma":[0.000115917384,0.00039414078,0.00008363959,0.0006799952,0.00048052048,0.0004920926,0.0011407115,0.0007041074,0.000013597801],"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":[0.0000151084805,0.00003728067,0.00017321222,0.00015184113,0.000008449318,0.000054333203,0.00042343684,0.0004444678,0.0007825054,0.0051807654,0.0000052410064,0.99272335],"study_design_scores_gemma":[0.0011622868,0.0011742343,0.0049881805,0.0015353273,0.000020081383,0.00017706754,6.134464e-7,0.5734873,0.08276393,0.33296856,0.00038931693,0.0013331398],"about_ca_topic_score_codex":0.00006852469,"about_ca_topic_score_gemma":0.00012788028,"teacher_disagreement_score":0.9913902,"about_ca_system_score_codex":0.00019373606,"about_ca_system_score_gemma":0.0003878094,"threshold_uncertainty_score":0.99985105},"labels":[],"label_agreement":null},{"id":"W3001318351","doi":"10.5555/1739839.1739841","title":"An accurate and efficient skew estimation technique for South Indian documents","year":2007,"lang":"en","type":"article","venue":"International Journal of Robotics and Automation","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Skew; Computer science; Estimation; Cluster analysis; Boundary (topology); Optical character recognition; Character (mathematics); Pattern recognition (psychology); Artificial intelligence; k-nearest neighbors algorithm; Mathematics; Image (mathematics); Telecommunications; Engineering; Geometry","score_opus":0.011968992800398818,"score_gpt":0.3095412602110955,"score_spread":0.2975722674106967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3001318351","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":[0.05725451,0.000022649047,0.94177884,0.00046591013,0.0002190871,0.00018557055,0.0000035771754,0.000042311152,0.000027537675],"genre_scores_gemma":[0.6328122,0.000011486346,0.3670492,0.00006588863,0.000046614692,0.0000033585607,0.0000044244393,0.0000036392853,0.0000031657255],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991037,0.000022703827,0.00037811254,0.000114258284,0.0002838723,0.00009730524],"domain_scores_gemma":[0.99889207,0.00007582965,0.000404147,0.00007245062,0.0004755567,0.00007996838],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00092248403,0.000079141195,0.000097961056,0.00034960415,0.00006246353,0.00028575878,0.00026090996,0.000055963697,0.0000016518194],"category_scores_gemma":[0.00008083899,0.00007142005,0.00003103822,0.000079727775,0.000023810033,0.0006525171,0.000041691535,0.00007677409,6.8955666e-7],"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":[0.00007737277,0.00029919323,0.00096760545,0.000067953086,0.00012347898,0.00006063781,0.0037712445,0.012104141,0.0255068,0.06242492,0.000113196096,0.89448345],"study_design_scores_gemma":[0.0013678519,0.0006619721,0.012582654,0.0003514115,0.000028813141,0.0007639004,0.00012735366,0.8299674,0.09512147,0.058565117,0.00015073617,0.00031132085],"about_ca_topic_score_codex":0.000002358092,"about_ca_topic_score_gemma":0.0000011037738,"teacher_disagreement_score":0.89417213,"about_ca_system_score_codex":0.000051258055,"about_ca_system_score_gemma":0.0000353651,"threshold_uncertainty_score":0.29124254},"labels":[],"label_agreement":null},{"id":"W3004017572","doi":"10.1016/j.scijus.2020.01.006","title":"The potential of collaborative learning as a tool for forensic students: Application to signature examination","year":2020,"lang":"en","type":"article","venue":"Science & Justice","topic":"Handwritten Text Recognition Techniques","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":"Université du Québec à Trois-Rivières","funders":"Université de Lausanne","keywords":"Handwriting; Class (philosophy); Computer science; Signature (topology); Population; Vulnerability (computing); Test (biology); Forensic examination; Psychology; Mathematics education; Data science; Artificial intelligence; Computer security; Engineering; Medicine; Forensic engineering; Mathematics","score_opus":0.008718536027226612,"score_gpt":0.2939882336782774,"score_spread":0.2852696976510508,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3004017572","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":[0.038585924,0.000029622166,0.9575996,0.002215589,0.00012872594,0.0010017783,0.0000038922835,0.00013106296,0.00030383767],"genre_scores_gemma":[0.9447409,0.000011148234,0.05402929,0.00090714137,0.00006730614,0.00018581141,0.0000019951249,0.0000051670404,0.000051235715],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99835587,0.000072996234,0.00021056787,0.00041044102,0.0007240547,0.00022609215],"domain_scores_gemma":[0.9980998,0.00023236919,0.00016548083,0.00022098716,0.0011858706,0.00009551111],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013148695,0.0000882482,0.00010022496,0.00008610377,0.0005825819,0.0003329925,0.001407231,0.000039283666,0.0000017865812],"category_scores_gemma":[0.0018812964,0.0000714447,0.000029398927,0.0019863953,0.00018608669,0.0006527348,0.0002874465,0.000117799544,0.000020855166],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004846821,0.000059262416,0.000045777582,0.00006339443,0.000009994664,0.0000016361607,0.0067341845,0.00088436896,0.2857716,0.058069754,0.00094824046,0.6473633],"study_design_scores_gemma":[0.0010106986,0.0029038207,0.0070465454,0.00010836224,0.00014211767,0.000007971581,0.009070644,0.27996516,0.670122,0.019593112,0.00933677,0.0006927915],"about_ca_topic_score_codex":0.0000036285985,"about_ca_topic_score_gemma":0.000002199118,"teacher_disagreement_score":0.906155,"about_ca_system_score_codex":0.00005208662,"about_ca_system_score_gemma":0.00020860817,"threshold_uncertainty_score":0.4480808},"labels":[],"label_agreement":null},{"id":"W3007199277","doi":"10.1007/978-3-030-41258-6_2","title":"The LegendreSobolev Package and Its Applications in Handwriting Recognition","year":2020,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Handwritten Text Recognition Techniques","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":"University of Waterloo","funders":"","keywords":"Handwriting; Computer science; Speech recognition; Natural language processing; Artificial intelligence","score_opus":0.0467617885166808,"score_gpt":0.2857479680374212,"score_spread":0.2389861795207404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3007199277","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":[0.00015405718,0.0038209432,0.71906495,0.0070986804,0.00017166723,0.002388272,0.00006904148,0.00043984634,0.26679257],"genre_scores_gemma":[0.49957314,0.10341672,0.38602975,0.0067759994,0.00027267498,0.0016270858,0.0005952554,0.00008285129,0.0016265298],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99830186,0.000055048728,0.0007388083,0.0003343764,0.00034074453,0.0002291735],"domain_scores_gemma":[0.99758464,0.00056091824,0.00031554844,0.0010915952,0.00033379233,0.00011351907],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011733169,0.0002098238,0.00021458016,0.0006528271,0.0008162543,0.0010258383,0.002323407,0.00012258759,0.0000024451545],"category_scores_gemma":[0.00010358354,0.00018877424,0.00003313182,0.0005878648,0.00057179114,0.004913025,0.0020862517,0.00056863145,0.00005124412],"study_design_candidate":"theoretical_or_conceptual","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":[8.9156634e-7,0.0000065955905,0.000013584072,0.00002271247,0.0000020362274,2.9941666e-7,0.0007372142,0.0000013164312,0.000008788721,0.43655723,0.000052502775,0.5625968],"study_design_scores_gemma":[0.0009737979,0.0001698653,0.002034713,0.0011372346,0.000017312397,0.000107125015,0.00028637293,0.4049899,0.0008573351,0.20532803,0.3827217,0.0013766141],"about_ca_topic_score_codex":0.000006061989,"about_ca_topic_score_gemma":0.000026091673,"teacher_disagreement_score":0.56122017,"about_ca_system_score_codex":0.0000961205,"about_ca_system_score_gemma":0.00016732581,"threshold_uncertainty_score":0.9892183},"labels":[],"label_agreement":null},{"id":"W3012200654","doi":"10.19195/2084-5065.45.2","title":"How to answer the question of error margin in forensic signature examination with a Bayesian approach?","year":2017,"lang":"en","type":"article","venue":"Nowa Kodyfikacja Prawa Karnego","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Margin (machine learning); Signature (topology); Computer science; Bayesian probability; Handwriting; False accusation; Certainty; Forensic examination; Forensic science; Artificial intelligence; Machine learning; Psychology; Mathematics; Engineering; Social psychology; Forensic engineering","score_opus":0.021382696858615987,"score_gpt":0.2725000644968411,"score_spread":0.2511173676382251,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3012200654","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":[0.034057066,0.00009956098,0.94265604,0.0069948398,0.00019564776,0.0015442659,0.00000767727,0.0002549797,0.014189921],"genre_scores_gemma":[0.86999375,0.0000074280065,0.12859268,0.0003124742,0.00007308105,0.00021375786,0.0000093214,0.000022143351,0.0007753297],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99803543,0.00026314598,0.0002701303,0.0005740338,0.0005196175,0.0003376564],"domain_scores_gemma":[0.99771595,0.00008440309,0.00037032977,0.0014035265,0.0003210839,0.00010471279],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001019508,0.0002530399,0.00028981536,0.00031337456,0.0002402974,0.00053159974,0.0015676463,0.0001922244,0.000005809015],"category_scores_gemma":[0.000301514,0.00017604016,0.00006456558,0.00041988073,0.0001759165,0.0012762425,0.00028375292,0.00037911072,0.0000074398426],"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":[0.00007981981,0.0005071276,0.0053641573,0.00016004736,0.00004400772,0.000036309615,0.0033189105,0.00004368864,0.0052545057,0.07296131,0.003737016,0.9084931],"study_design_scores_gemma":[0.005424852,0.003849072,0.6145439,0.0029403314,0.00015410857,0.00039249394,0.0023741496,0.07965589,0.20338854,0.05389362,0.029723072,0.0036599382],"about_ca_topic_score_codex":0.00013898243,"about_ca_topic_score_gemma":0.0005082251,"teacher_disagreement_score":0.90483314,"about_ca_system_score_codex":0.0000790269,"about_ca_system_score_gemma":0.00014331726,"threshold_uncertainty_score":0.71787095},"labels":[],"label_agreement":null},{"id":"W3012666521","doi":"10.1016/j.eswa.2020.113397","title":"A white-box analysis on the writer-independent dichotomy transformation applied to offline handwritten signature verification","year":2020,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":31,"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; Université du Québec à Montréal","funders":"Fundação de Amparo à Ciência e Tecnologia do Estado de Pernambuco; Conselho Nacional de Desenvolvimento Científico e Tecnológico; École de technologie supérieure","keywords":"Computer science; Signature (topology); Context (archaeology); Transformation (genetics); Artificial intelligence; Class (philosophy); Scalability; Machine learning; Natural language processing; Mathematics","score_opus":0.016379702903542973,"score_gpt":0.24341964613745418,"score_spread":0.2270399432339112,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3012666521","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":[0.0005305057,0.000077399745,0.9719253,0.018934462,0.00002563529,0.003446935,0.00003634104,0.0006820606,0.0043413355],"genre_scores_gemma":[0.96898997,0.00001414859,0.015740165,0.0041535585,0.0001819576,0.010691237,0.0001179762,0.000024521114,0.00008644308],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977612,0.00010863829,0.00050190673,0.00070017274,0.0006529345,0.00027513952],"domain_scores_gemma":[0.99810696,0.000107811415,0.00020452663,0.0010710326,0.00024886895,0.00026077477],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033374561,0.00027003285,0.0003350509,0.00029415236,0.00035815095,0.00042622312,0.0011472945,0.00012958678,0.000034179146],"category_scores_gemma":[0.000012647465,0.00018531612,0.00011189529,0.00286515,0.000036056983,0.0002841978,0.000056340203,0.00026588945,0.00025771183],"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":[0.000501815,0.0014821658,0.00072006567,0.00035202576,0.0023828982,0.000014787904,0.08115123,0.010395186,0.07575333,0.6717818,0.05417189,0.101292804],"study_design_scores_gemma":[0.003203424,0.0013725363,0.0043241573,0.00034673596,0.0006299639,0.000052274096,0.0071788435,0.2215876,0.11614883,0.0011422586,0.6406731,0.0033402848],"about_ca_topic_score_codex":0.000030553918,"about_ca_topic_score_gemma":0.0000137374145,"teacher_disagreement_score":0.9684595,"about_ca_system_score_codex":0.00009057776,"about_ca_system_score_gemma":0.000053353822,"threshold_uncertainty_score":0.7556972},"labels":[],"label_agreement":null},{"id":"W3013947068","doi":"10.1109/synasc49474.2019.00036","title":"Handwriting Feature Extraction via Legendre-Sobolev Matrix Representation","year":2019,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Handwriting; Legendre polynomials; Representation (politics); Computer science; Monomial; Feature extraction; Matrix (chemical analysis); Handwriting recognition; Pattern recognition (psychology); Feature (linguistics); Artificial intelligence; Bounding overwatch; Algorithm; Mathematics; Algebra over a field; Pure mathematics; Mathematical analysis","score_opus":0.013473446128900505,"score_gpt":0.29853373855558046,"score_spread":0.28506029242667996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3013947068","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":[0.02039907,0.000072035815,0.94753253,0.0012350398,0.00036918928,0.0003756604,0.0000012287862,0.0011649262,0.028850334],"genre_scores_gemma":[0.8138916,0.000024119552,0.1763159,0.00032238255,0.00011611966,0.00002875911,0.000014068221,0.0000143643665,0.009272695],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986876,0.0000757832,0.0002149291,0.00046460459,0.00031424718,0.00024283589],"domain_scores_gemma":[0.99906385,0.00008744406,0.00011970091,0.0005171612,0.0001404688,0.00007134962],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00027092968,0.00013589898,0.00015467651,0.00017786285,0.00009523358,0.00025435022,0.00039921032,0.00012548717,0.00033482254],"category_scores_gemma":[0.000019466843,0.00013051936,0.00008718876,0.0004180402,0.000013583705,0.0015029776,0.000121766505,0.00021129569,0.0010221268],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019313853,0.00009970555,0.0066905883,0.000080259284,0.000038693594,0.00003746503,0.0004872724,0.000025494692,0.35418028,0.029243166,0.01815365,0.5909441],"study_design_scores_gemma":[0.00063813373,0.0001468503,0.007407033,0.00007502184,0.000011265693,0.00031313876,0.0001722754,0.037551064,0.93445545,0.010448606,0.008236592,0.0005445826],"about_ca_topic_score_codex":0.000047506175,"about_ca_topic_score_gemma":0.000007702718,"teacher_disagreement_score":0.7934925,"about_ca_system_score_codex":0.000049862665,"about_ca_system_score_gemma":0.000025663212,"threshold_uncertainty_score":0.9997557},"labels":[],"label_agreement":null},{"id":"W3019597059","doi":"10.3934/mbe.2020182","title":"Robust table recognition for printed document images","year":2020,"lang":"en","type":"article","venue":"Mathematical Biosciences & Engineering","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; University of Alberta","funders":"","keywords":"Computer science; Artificial intelligence; Robustness (evolution); Table (database); Preprocessor; Pattern recognition (psychology); Distortion (music); Computer vision; Data mining","score_opus":0.038069203800892876,"score_gpt":0.24124769122178588,"score_spread":0.203178487420893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3019597059","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":[0.00189066,0.000023497028,0.9939725,0.0020890532,0.00009024368,0.00042498935,0.000008290995,0.00084603264,0.00065473374],"genre_scores_gemma":[0.16545314,0.000009044725,0.8338722,0.0003698693,0.00006625126,0.00017154617,0.0000032905157,0.000012441245,0.000042206593],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986654,0.000013046255,0.00029302965,0.00040650982,0.0002739218,0.00034807273],"domain_scores_gemma":[0.9992427,0.00023043585,0.000059193735,0.00018702952,0.000092296876,0.00018829803],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037999035,0.00015453507,0.00019414393,0.00008757657,0.00008553614,0.00032408096,0.00066190737,0.000050807426,0.00007546153],"category_scores_gemma":[0.0007553126,0.00013293284,0.00007053547,0.00057509926,0.000044171175,0.00066620274,0.00017027171,0.00009683658,0.00010307548],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002501007,0.0004890276,0.000045182733,0.0019957817,0.00009170393,0.00003831248,0.0033221238,0.002177134,0.42654487,0.3319525,0.008268686,0.22504964],"study_design_scores_gemma":[0.0002068022,0.0002352375,0.000021174777,0.00018904997,0.000011757559,0.000017124745,0.000053652213,0.49358574,0.4760077,0.02676396,0.0024901193,0.00041770475],"about_ca_topic_score_codex":0.0000011739386,"about_ca_topic_score_gemma":9.6510604e-8,"teacher_disagreement_score":0.4914086,"about_ca_system_score_codex":0.000024275321,"about_ca_system_score_gemma":0.000027584596,"threshold_uncertainty_score":0.54208434},"labels":[],"label_agreement":null},{"id":"W3026638717","doi":"10.1109/wacvw50321.2020.9096928","title":"Memory-Efficient Models for Scene Text Recognition via Neural Architecture Search","year":2020,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Architecture; Artificial intelligence; Natural language processing; Pattern recognition (psychology); Computer architecture; Speech recognition","score_opus":0.05419015944619034,"score_gpt":0.27003568489939844,"score_spread":0.2158455254532081,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3026638717","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":[0.0042581833,0.000031509346,0.9817051,0.008612024,0.000089168,0.000904456,0.0000196761,0.0011216155,0.0032582183],"genre_scores_gemma":[0.60691774,0.000004757965,0.38841295,0.0042403904,0.00014607783,0.00013187982,0.000025609717,0.000022019243,0.00009861367],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99823344,0.00009402648,0.0002821947,0.00061736314,0.00035971298,0.00041326843],"domain_scores_gemma":[0.998964,0.00013289938,0.000055308785,0.0003214371,0.0002697622,0.00025659066],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028451424,0.0001941628,0.00020455444,0.00013940955,0.00015454766,0.00018332503,0.0007073958,0.00009444835,0.000107673266],"category_scores_gemma":[0.000044727905,0.00017132096,0.00014488121,0.00047295983,0.000038211892,0.00030106693,0.00024296586,0.00023808453,0.00013240278],"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":[0.00002528227,0.000065462526,6.896745e-7,0.000044293876,0.000009841233,0.000005218912,0.0006828609,0.002249399,0.0042625135,0.0006420199,0.0013327608,0.9906797],"study_design_scores_gemma":[0.00034559384,0.00025081707,0.000005115704,0.000013504828,0.0000053641265,0.00002009651,0.000026578758,0.8144892,0.1718155,0.0126028815,0.0002055882,0.00021975605],"about_ca_topic_score_codex":0.00002032493,"about_ca_topic_score_gemma":0.0000034821194,"teacher_disagreement_score":0.9904599,"about_ca_system_score_codex":0.000033307533,"about_ca_system_score_gemma":0.00005404558,"threshold_uncertainty_score":0.69862664},"labels":[],"label_agreement":null},{"id":"W3027907503","doi":"10.1007/s42979-020-00186-z","title":"KuroNet: Regularized Residual U-Nets for End-to-End Kuzushiji Character Recognition","year":2020,"lang":"en","type":"article","venue":"SN Computer Science","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Cursive; Residual; Architecture; Artificial intelligence; Optical character recognition; Curriculum; Regularization (linguistics); Metadata; World Wide Web; Visual arts; Art; Algorithm","score_opus":0.04045883570007657,"score_gpt":0.2671012331396064,"score_spread":0.2266423974395298,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3027907503","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":[0.017148694,0.0000143162915,0.9638649,0.01564953,0.00077158253,0.001016506,0.000039021445,0.00097436545,0.0005210796],"genre_scores_gemma":[0.18251021,0.000006558041,0.80080855,0.015682317,0.0007069408,0.00016670767,0.000027918984,0.00002647687,0.00006431376],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9960635,0.00011137266,0.0005194976,0.001540597,0.0009373022,0.00082778203],"domain_scores_gemma":[0.9975784,0.00020506501,0.00019637824,0.00079604966,0.0005930711,0.0006310817],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001307363,0.0003180466,0.00035676986,0.00042109462,0.00047309106,0.0010170556,0.0027979868,0.000107098465,0.00007024733],"category_scores_gemma":[0.00021886814,0.00031653084,0.00012900685,0.0019180151,0.00029440082,0.0019960054,0.0010770628,0.00024246462,0.0004375798],"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":[0.000041847972,0.00007847808,0.00002993572,0.000033383094,0.000013182196,0.000022455202,0.0016451782,0.000009791934,0.050373264,0.0033116883,0.009960965,0.93447983],"study_design_scores_gemma":[0.0023525583,0.002788071,0.005094443,0.00026448123,0.000031995063,0.00014092578,0.000024538069,0.26669952,0.63171256,0.026977828,0.06185184,0.0020612339],"about_ca_topic_score_codex":0.000011010254,"about_ca_topic_score_gemma":0.0000036005933,"teacher_disagreement_score":0.9324186,"about_ca_system_score_codex":0.00009481359,"about_ca_system_score_gemma":0.00033983545,"threshold_uncertainty_score":0.99992865},"labels":[],"label_agreement":null},{"id":"W3033633564","doi":"10.48550/arxiv.2006.04305","title":"Text Detection and Recognition in the Wild: A Review","year":2020,"lang":"en","type":"review","venue":"arXiv (Cornell University)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Artificial intelligence","score_opus":0.11040904182149343,"score_gpt":0.22838566859597423,"score_spread":0.1179766267744808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3033633564","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000034606621,0.9121966,0.0854798,0.00009809369,0.000053017186,0.0009805751,0.0000075562048,0.0002027851,0.0009781052],"genre_scores_gemma":[0.00045076088,0.9984938,0.00039513886,0.0005338446,0.000037103277,0.000013720845,0.000012868549,0.000014267047,0.00004850873],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980726,0.00063315843,0.0002939092,0.0007201349,0.000079705154,0.0002004936],"domain_scores_gemma":[0.99887156,0.00023522887,0.0002638706,0.0004945011,0.000057344485,0.00007749913],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050694426,0.00028261004,0.0006957125,0.00026209533,0.00009315708,0.000089522604,0.00093371555,0.00018030635,0.000017724664],"category_scores_gemma":[0.00009334527,0.00023260877,0.00022514192,0.0019517274,0.000059283087,0.0004718109,0.00023078345,0.0005144296,0.00020777798],"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":[8.164274e-7,0.000016395932,3.9785365e-7,0.0039137453,0.000013187743,0.0001413316,0.000027330812,6.124109e-8,8.014746e-8,0.0007758934,0.00017799038,0.9949328],"study_design_scores_gemma":[0.00012658228,0.00009027635,0.0000021762228,0.018772688,0.00029036932,0.00018283281,0.000013065744,0.00078341196,0.00000191796,0.005945742,0.9733958,0.00039510746],"about_ca_topic_score_codex":0.000025017687,"about_ca_topic_score_gemma":0.000027332224,"teacher_disagreement_score":0.99453765,"about_ca_system_score_codex":0.00010786364,"about_ca_system_score_gemma":0.000086842745,"threshold_uncertainty_score":0.948551},"labels":[],"label_agreement":null},{"id":"W3084112228","doi":"","title":"Interpreting images of line drawings: a tutorial presented at the 16th International conference on pattern recognition (ICPR), Quebec city, Canada, 11th August 2002","year":2002,"lang":"en","type":"article","venue":"Digital Library of the Belarusian State University (Belarusian State University)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Line drawings; Line (geometry); Geography; Artificial intelligence; Cartography; Library science; Computer science; History; Computer graphics (images); Visual arts; Engineering drawing; Mathematics; Engineering; Art; Geometry","score_opus":0.0143535406384368,"score_gpt":0.18019198027279798,"score_spread":0.16583843963436118,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3084112228","genre_codex":"other","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":[0.44735655,0.000085834494,0.05763488,0.017583475,0.0019820533,0.0024055685,0.019904299,0.0010902816,0.45195708],"genre_scores_gemma":[0.92346805,0.00021651904,0.0006842696,0.00029871767,0.000057771766,5.912958e-7,0.00020799626,0.000038429633,0.07502767],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99746007,0.00030206444,0.00041895796,0.00062197127,0.0007368328,0.00046012114],"domain_scores_gemma":[0.9978924,0.00021320673,0.0006822953,0.0007205384,0.00028471285,0.00020687025],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00012325778,0.00037738078,0.00038060884,0.00051807467,0.00041967505,0.0002771519,0.0028425246,0.00010922262,0.0007912772],"category_scores_gemma":[0.00004978646,0.0003364901,0.00027642626,0.0010802579,0.00051966315,0.0034176675,0.0024084614,0.00044855385,0.000031490225],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002336131,0.0022533422,0.017969131,0.00037375605,0.002150139,0.0032815284,0.011421863,0.0002945532,0.0015087967,0.0067709866,0.19163586,0.7600039],"study_design_scores_gemma":[0.013168264,0.0021492946,0.011050619,0.0044495463,0.0004968604,0.00031470432,0.010858147,0.024758263,0.11301466,0.0062608286,0.80806416,0.0054146303],"about_ca_topic_score_codex":0.025235172,"about_ca_topic_score_gemma":0.027654001,"teacher_disagreement_score":0.75458926,"about_ca_system_score_codex":0.00044669962,"about_ca_system_score_gemma":0.00036679555,"threshold_uncertainty_score":0.9999087},"labels":[],"label_agreement":null},{"id":"W3089017776","doi":"10.1145/3395027.3419598","title":"Automatic Generation of Electrical Plan Documents from Architectural Data","year":2020,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Plan (archaeology); Floor plan; Computer science; Process (computing); Architectural plan; Code (set theory); Stack (abstract data type); Software engineering; Task (project management); Architectural engineering; Electrical equipment; Systems engineering; Architecture; Engineering drawing; Engineering; Electrical engineering; Programming language; Set (abstract data type)","score_opus":0.08344102083516063,"score_gpt":0.29102815249640235,"score_spread":0.2075871316612417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3089017776","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":[0.12049634,0.000021797538,0.8769836,0.0013396762,0.00003494716,0.00012957813,0.000020211106,0.00041240052,0.0005614686],"genre_scores_gemma":[0.7031706,0.0000028304482,0.2958014,0.0008246592,0.00006647749,0.000004311171,0.000115999545,0.000003367753,0.000010344583],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999082,0.00006109859,0.0002218608,0.00030162913,0.00022336545,0.00011003776],"domain_scores_gemma":[0.9993049,0.000058880385,0.00006442155,0.000469288,0.000027011867,0.00007548222],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007835835,0.00007374966,0.00012240898,0.00004265267,0.000025080923,0.00007406705,0.001078156,0.000031591608,0.00019824409],"category_scores_gemma":[0.00007195451,0.000061418075,0.00002099817,0.00021579073,0.000013970777,0.00039824023,0.00037152146,0.00007663434,0.000057904428],"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":[0.0000034029122,0.00004685285,0.00035747947,0.000010271731,0.000033369943,0.0000069185317,0.0005765659,0.0000027348178,0.048733216,0.0020743671,0.017311985,0.9308428],"study_design_scores_gemma":[0.00014976828,0.00008899807,0.00042545146,0.000005772077,0.0000050834774,0.0000036487888,0.0000024984786,0.8611615,0.13573503,0.0020435061,0.00028845324,0.00009028555],"about_ca_topic_score_codex":0.00008594353,"about_ca_topic_score_gemma":0.000008718309,"teacher_disagreement_score":0.9307526,"about_ca_system_score_codex":0.000009308464,"about_ca_system_score_gemma":0.00003414623,"threshold_uncertainty_score":0.25045565},"labels":[],"label_agreement":null},{"id":"W3091933531","doi":"10.1007/978-3-030-59830-3_11","title":"Comparison of Persian Handwritten Digit Recognition in Three Color Modalities Using Deep Neural Networks","year":2020,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":3,"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":"Computer science; Convolutional neural network; Numerical digit; Artificial intelligence; Modalities; Pattern recognition (psychology); Digit recognition; Set (abstract data type); Speech recognition; Artificial neural network; Deep learning; Handwriting recognition; Feature extraction; Arithmetic; Mathematics","score_opus":0.04831912484570828,"score_gpt":0.28412145579972703,"score_spread":0.23580233095401876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3091933531","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":[0.0022157037,0.00037487558,0.99449205,0.00047167347,0.00062559184,0.00068262994,0.000012639972,0.00024245205,0.0008824006],"genre_scores_gemma":[0.7801415,0.000018357303,0.21890013,0.0006107557,0.0002481763,0.000015349713,0.000019282015,0.000039034298,0.000007451719],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99580765,0.000080000136,0.001071296,0.0014330266,0.00091955846,0.0006884685],"domain_scores_gemma":[0.99759305,0.00047017378,0.000588585,0.0007934389,0.0003597945,0.00019496509],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005545152,0.0006024156,0.0010619566,0.0011069776,0.00018221288,0.0004998727,0.00247287,0.00048684137,0.000023424152],"category_scores_gemma":[0.00010820021,0.00061950623,0.00020544004,0.0010166749,0.00083105924,0.0010253077,0.0011646096,0.0011578813,0.000008010181],"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":[0.000026512429,0.00007078655,0.00089997554,0.000102341444,0.000017436118,0.000079692654,0.001578698,0.060954604,0.00018185173,0.0016223879,0.000005578988,0.93446016],"study_design_scores_gemma":[0.00028200084,0.00028902284,0.00012986347,0.0005326849,0.000013054098,0.000038936687,0.000002244924,0.9001858,0.0028740547,0.09503928,0.000020211493,0.0005927934],"about_ca_topic_score_codex":0.00009757241,"about_ca_topic_score_gemma":0.00054892316,"teacher_disagreement_score":0.93386734,"about_ca_system_score_codex":0.00037130364,"about_ca_system_score_gemma":0.00025131917,"threshold_uncertainty_score":0.9996256},"labels":[],"label_agreement":null},{"id":"W3092344991","doi":"10.1007/978-3-030-59830-3_1","title":"Gender Detection from Handwritten Documents Using Concept of Transfer-Learning","year":2020,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":16,"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":"Computer science; Artificial intelligence; Convolutional neural network; Transfer of learning; Support vector machine; Arabic; Pattern recognition (psychology); Natural language processing; Task (project management); Convolution (computer science); Set (abstract data type); Data set; Feature (linguistics); Artificial neural network","score_opus":0.025633938871819147,"score_gpt":0.2571517025986135,"score_spread":0.23151776372679433,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092344991","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":[0.00094537507,0.00031150604,0.9962672,0.000093217604,0.0006675563,0.00040648403,0.000015782942,0.00031777687,0.0009751228],"genre_scores_gemma":[0.68755937,0.000029517416,0.31162065,0.00045232783,0.00026352756,0.0000060465222,0.000010990008,0.000037237092,0.000020342475],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962296,0.00009091727,0.0007089784,0.0014632189,0.0010475422,0.0004597583],"domain_scores_gemma":[0.99822026,0.00031548442,0.00027567195,0.0007055107,0.00029888962,0.00018416718],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00043204005,0.00050618296,0.00067679025,0.00065266405,0.00021722261,0.00035052918,0.0020801981,0.00039542376,0.00005869888],"category_scores_gemma":[0.0000731506,0.00051407906,0.00019918765,0.0006210131,0.0005369391,0.0008021928,0.0006788609,0.0010381109,0.000014222939],"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":[0.000012006725,0.000020859874,0.000039993185,0.00004688716,0.000041172058,0.000058546902,0.0022037793,0.008361666,0.014765847,0.0013539835,0.000002741052,0.9730925],"study_design_scores_gemma":[0.00055599125,0.00033878032,0.000054914366,0.00058613345,0.000037096255,0.000042935117,9.966601e-7,0.52606404,0.33829775,0.1325942,0.0004944695,0.0009326936],"about_ca_topic_score_codex":0.00012032818,"about_ca_topic_score_gemma":0.000027678412,"teacher_disagreement_score":0.9721598,"about_ca_system_score_codex":0.0002506758,"about_ca_system_score_gemma":0.00034664193,"threshold_uncertainty_score":0.99973106},"labels":[],"label_agreement":null},{"id":"W3095237147","doi":"10.1016/j.eswa.2020.114196","title":"A comprehensive comparison of end-to-end approaches for handwritten digit string recognition","year":2020,"lang":"en","type":"preprint","venue":"Expert Systems with Applications","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","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":"École de Technologie Supérieure","funders":"Fundação Araucária; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; Fondo Nacional de Desarrollo Científico y Tecnológico; Nvidia","keywords":"Segmentation; Computer science; Heuristics; String (physics); End-to-end principle; Artificial intelligence; Pipeline (software); Sequence (biology); NIST; Pattern recognition (psychology); Benchmark (surveying); Representation (politics); Machine learning; Speech recognition; Mathematics","score_opus":0.1278187303993129,"score_gpt":0.3236232059702125,"score_spread":0.19580447557089958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3095237147","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":[0.0007074093,0.000860943,0.98713225,0.0011020295,0.00014583788,0.007845426,0.00049678213,0.00081425137,0.00089508865],"genre_scores_gemma":[0.6917082,0.000032744785,0.277005,0.0001534175,0.0003523644,0.02988261,0.00075275917,0.00006629454,0.000046641217],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.996626,0.000118275886,0.0010333754,0.0012974347,0.00054207584,0.0003828196],"domain_scores_gemma":[0.9964671,0.00036254054,0.0008230472,0.0012983799,0.00075757393,0.00029135734],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00017444488,0.0004895596,0.0010339882,0.00036207386,0.00022404209,0.00040807403,0.0014571279,0.0003114216,0.0000054390475],"category_scores_gemma":[0.000032673408,0.00046812822,0.0002025663,0.0005882873,0.00010405928,0.000240221,0.0007379713,0.0004127158,0.00004311916],"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":[0.00022546532,0.0015807294,0.00035245958,0.006286875,0.0012017003,0.0000061563724,0.018071584,0.0020580136,0.009275895,0.04072837,0.021443097,0.8987697],"study_design_scores_gemma":[0.0040328535,0.0024123157,0.000466462,0.0073373043,0.00041433936,0.00014025766,0.009490154,0.2080252,0.29584846,0.032460947,0.43326047,0.006111236],"about_ca_topic_score_codex":0.0002028515,"about_ca_topic_score_gemma":0.0000135169685,"teacher_disagreement_score":0.8926584,"about_ca_system_score_codex":0.0001457787,"about_ca_system_score_gemma":0.00023675985,"threshold_uncertainty_score":0.999777},"labels":[],"label_agreement":null},{"id":"W3096989855","doi":"10.18280/ts.370416","title":"Handwritten Gurmukhi Digit Recognition System for Small Datasets","year":2020,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Pattern recognition (psychology); Artificial intelligence; Overfitting; Support vector machine; Convolutional neural network; Transformation (genetics); Discrete cosine transform; Digit recognition; MNIST database; Kernel (algebra); Speech recognition; Artificial neural network; Image (mathematics); Mathematics","score_opus":0.04981814569558502,"score_gpt":0.24361643341382802,"score_spread":0.193798287718243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3096989855","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":[0.00706491,0.000036659374,0.98632437,0.002299741,0.00012780282,0.001150029,0.00089450495,0.0012753989,0.00082657667],"genre_scores_gemma":[0.8841702,0.00001234816,0.109541915,0.0034431797,0.00057326286,0.00067304587,0.0015177446,0.00004088995,0.000027453194],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99809736,0.000081706305,0.00049126823,0.00062718,0.0003139612,0.00038849722],"domain_scores_gemma":[0.9989874,0.00013407673,0.00016681575,0.0002934035,0.00015860643,0.00025973172],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003349412,0.00024179315,0.00027576328,0.00010276686,0.00016564773,0.0003684795,0.00083903986,0.000087491026,0.00010015459],"category_scores_gemma":[0.000043008356,0.00023785693,0.00014124332,0.00027805803,0.00003389756,0.0006373314,0.00016945285,0.00012149209,0.0002219495],"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":[0.0001462746,0.00026943162,0.000087443725,0.0006807976,0.00014122677,0.00007025843,0.00085594336,0.000014634419,0.017048566,0.004145617,0.04918695,0.92735285],"study_design_scores_gemma":[0.0057502016,0.0024907298,0.00025947267,0.00060688215,0.00016933701,0.00011187386,0.00033359876,0.07782595,0.75646985,0.005470535,0.14872113,0.0017904316],"about_ca_topic_score_codex":0.000009452178,"about_ca_topic_score_gemma":0.000003138431,"teacher_disagreement_score":0.92556244,"about_ca_system_score_codex":0.000069089765,"about_ca_system_score_gemma":0.000055386365,"threshold_uncertainty_score":0.9699524},"labels":[],"label_agreement":null},{"id":"W3097680986","doi":"10.48550/arxiv.2011.00380","title":"Real-Time Text Detection and Recognition","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Text detection; Computer science; Session (web analytics); Distortion (music); Artificial intelligence; Image (mathematics); Text recognition; Computer vision; Pattern recognition (psychology); Machine learning; Speech recognition","score_opus":0.06017547374233711,"score_gpt":0.18943577479967424,"score_spread":0.12926030105733713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3097680986","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":[0.21599221,0.000016139551,0.77408075,0.00019107769,0.00020270611,0.00045225833,0.000026512265,0.0016466663,0.0073916763],"genre_scores_gemma":[0.98925203,0.000705565,0.009314485,0.00010681037,0.00008808017,0.0000035887151,0.00003015101,0.000022837983,0.00047646268],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981576,0.00017944783,0.00019390506,0.0011454955,0.00008385305,0.00023967394],"domain_scores_gemma":[0.9987157,0.000090178655,0.00022847891,0.00058355107,0.0001794345,0.00020265444],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00019667238,0.00028250468,0.00029536075,0.0002873318,0.00013960434,0.00018840811,0.0006928744,0.00034792465,0.00006467974],"category_scores_gemma":[0.00005024424,0.00035685822,0.00013011108,0.0004902096,0.00008711217,0.00051441917,0.0013137796,0.0005092079,0.0004688697],"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":[0.00034948648,0.0005539092,0.0006633185,0.0011655067,0.0006810866,0.0022808562,0.0022455347,0.0008857502,0.07657548,0.034465797,0.003918538,0.87621474],"study_design_scores_gemma":[0.00073868275,0.00031497978,0.0011682529,0.00029732843,0.00015656541,0.00004918453,0.000053484757,0.4299896,0.0324466,0.53287834,0.00060703134,0.0012999334],"about_ca_topic_score_codex":0.00018406348,"about_ca_topic_score_gemma":0.000017686012,"teacher_disagreement_score":0.8749148,"about_ca_system_score_codex":0.0001426752,"about_ca_system_score_gemma":0.000083035775,"threshold_uncertainty_score":0.99988836},"labels":[],"label_agreement":null},{"id":"W3102713119","doi":"","title":"Fixed-sized representation learning from offline handwritten signatures of different sizes","year":2018,"lang":"en","type":"article","venue":"Espace ÉTS (ETS)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":75,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","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":"Computer science; Representation (politics); Offline learning; Feature learning; Artificial intelligence; Pattern recognition (psychology); Online learning; World Wide Web","score_opus":0.016541865178639686,"score_gpt":0.27246875146980326,"score_spread":0.25592688629116356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3102713119","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":[0.531148,0.00027403596,0.46166056,0.002262151,0.00045950737,0.000457889,0.000012485614,0.0009153906,0.0028099779],"genre_scores_gemma":[0.9682613,0.0000636372,0.029772371,0.0002031418,0.0002880465,0.000033241617,0.000033564153,0.000022888036,0.0013218357],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9979422,0.0002895279,0.0003860757,0.0005835103,0.0004922223,0.00030645286],"domain_scores_gemma":[0.9981374,0.00047235342,0.0003145601,0.0006351675,0.00032624873,0.000114240094],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026702488,0.00023654333,0.0003907329,0.00021517207,0.00016198544,0.0001541155,0.00071651296,0.00016475563,0.00033932447],"category_scores_gemma":[0.00047511715,0.00020677899,0.0001350638,0.00042116342,0.00015597732,0.00044762646,0.00034339252,0.0003030541,0.00010437327],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037530708,0.0006011886,0.013845151,0.00007485453,0.00028824707,0.00004597094,0.010048576,0.000059514998,0.70194614,0.0072664674,0.021744195,0.24370442],"study_design_scores_gemma":[0.0012053858,0.00045240676,0.021907585,0.00018959433,0.000033328794,0.000004321897,0.00020021186,0.0148588875,0.9483064,0.008949344,0.003470899,0.0004216305],"about_ca_topic_score_codex":0.00018099889,"about_ca_topic_score_gemma":0.00012760267,"teacher_disagreement_score":0.43711329,"about_ca_system_score_codex":0.000038870596,"about_ca_system_score_gemma":0.00004349073,"threshold_uncertainty_score":0.84322023},"labels":[],"label_agreement":null},{"id":"W3105826996","doi":"","title":"Persian Heritage Image Binarization Competition (PHIBC 2012)","year":2016,"lang":"en","type":"preprint","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Persian; Computer science; Competition (biology); Artificial intelligence; Image (mathematics); Pattern recognition (psychology); Conjunction (astronomy); Computer vision; Linguistics","score_opus":0.013900173078229744,"score_gpt":0.25032242772626795,"score_spread":0.2364222546480382,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3105826996","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":[0.00031400003,0.00007701074,0.9289061,0.0053243963,0.0005839448,0.00052414654,0.000033765613,0.0021295892,0.06210704],"genre_scores_gemma":[0.52399105,0.00035663362,0.46659583,0.0010958968,0.00055644696,0.0003252913,0.00024349084,0.000084639454,0.006750737],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99782854,0.00016023358,0.0004011344,0.00086353003,0.00039983095,0.000346745],"domain_scores_gemma":[0.99812144,0.000042051393,0.00024763384,0.0011024728,0.0003428668,0.00014350959],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00033434248,0.0003468329,0.0003195637,0.00036322136,0.00013234065,0.00055452593,0.0013352247,0.00038915136,0.0008439468],"category_scores_gemma":[0.000028591783,0.00029685465,0.00019178068,0.00020084807,0.00015070559,0.0011480774,0.0015785428,0.00038237125,0.00089194573],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017099992,0.00051483937,0.00017874449,0.00065872644,0.00013485273,0.00010932905,0.0018051266,0.0000031375353,0.030667042,0.75806713,0.038706977,0.16913702],"study_design_scores_gemma":[0.0015770465,0.00048459208,0.0013476787,0.0031211851,0.00008270387,0.0001513389,0.00028913972,0.019243948,0.11993008,0.8118706,0.03782551,0.0040762224],"about_ca_topic_score_codex":0.00005454789,"about_ca_topic_score_gemma":0.00002491346,"teacher_disagreement_score":0.52367705,"about_ca_system_score_codex":0.00015762208,"about_ca_system_score_gemma":0.00012935638,"threshold_uncertainty_score":0.9999484},"labels":[],"label_agreement":null},{"id":"W3107374013","doi":"10.20870/ijvr.2020...3316","title":"Interaction by gesture recognition: a tool to virtually revive the automata of the Antiquity","year":2020,"lang":"en","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Agence Nationale de la Recherche","keywords":"Automaton; Gesture; Computer science; Greeks; Human–computer interaction; Gesture recognition; Artificial intelligence; Art","score_opus":0.01677477667176162,"score_gpt":0.2352361805783981,"score_spread":0.2184614039066365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3107374013","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":[0.0626508,0.00013590184,0.77326727,0.14976889,0.00015509452,0.00084641867,0.00006603818,0.00051737885,0.012592185],"genre_scores_gemma":[0.93285406,0.00016188125,0.061833184,0.004120026,0.000026799025,0.00008749864,0.000041991258,0.000020784011,0.0008537825],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9957889,0.0027523695,0.0004062128,0.00044517338,0.00041080549,0.00019655422],"domain_scores_gemma":[0.99606776,0.00079096045,0.00033345437,0.0013796346,0.0013182004,0.0001099837],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024205185,0.00016408839,0.00018761704,0.000050451643,0.00031423892,0.00028731435,0.0021770203,0.00008499723,0.00007568275],"category_scores_gemma":[0.0021161197,0.00011790319,0.0001376424,0.0009295266,0.00012603846,0.0004219145,0.000994828,0.00033227398,0.00007424012],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023167056,0.0004399659,0.00034880952,0.00008807126,0.00006163531,0.000002382777,0.020845296,0.000004051231,0.057534937,0.02976974,0.06613544,0.8247465],"study_design_scores_gemma":[0.00046617136,0.0000051294396,0.0027209702,0.0010673108,0.00003137433,0.00002804025,0.00022740012,0.011422317,0.881493,0.0034655386,0.098645546,0.00042726283],"about_ca_topic_score_codex":0.00010703064,"about_ca_topic_score_gemma":0.000093689654,"teacher_disagreement_score":0.87020326,"about_ca_system_score_codex":0.000043987475,"about_ca_system_score_gemma":0.00010006561,"threshold_uncertainty_score":0.48079523},"labels":[],"label_agreement":null},{"id":"W3108615237","doi":"10.1504/ijapr.2020.10033768","title":"Arabic literal amount sub-word recognition using multiple features and classifiers","year":2020,"lang":"en","type":"article","venue":"International Journal of Applied Pattern Recognition","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Fuels Association","funders":"","keywords":"Computer science; Artificial intelligence; Literal (mathematical logic); Arabic; Support vector machine; Decision tree; Classifier (UML); Pattern recognition (psychology); Word (group theory); Natural language processing; Arabic numerals; Artificial neural network; Speech recognition; Mathematics","score_opus":0.041253202461521796,"score_gpt":0.2661508901359665,"score_spread":0.22489768767444468,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3108615237","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":[0.51301444,0.000054696524,0.48402518,0.0017443158,0.000512167,0.00020387156,0.000052123873,0.00010636449,0.00028685815],"genre_scores_gemma":[0.9525568,0.00016813261,0.042633407,0.0038563432,0.000673661,0.000014273097,0.00007109205,0.0000243883,0.0000019135732],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.997937,0.000084729734,0.0006983713,0.00037356935,0.000675195,0.00023109924],"domain_scores_gemma":[0.9979954,0.00015847925,0.00070232106,0.00011540675,0.0007971956,0.00023122114],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035261878,0.00024149525,0.00029027017,0.0003898386,0.00008404532,0.00046659095,0.0006030476,0.00014572935,0.00005252695],"category_scores_gemma":[0.000105665174,0.00023728969,0.00014769717,0.00022524175,0.000069700465,0.0011028985,0.00015776377,0.0004695403,0.000046689467],"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":[0.00017688527,0.00007340224,0.00055009936,0.00002249492,0.000113881,0.00008680839,0.00081208517,0.000008761882,0.020546205,0.000022461172,0.00058082375,0.9770061],"study_design_scores_gemma":[0.015438217,0.0017675536,0.023337321,0.0025223093,0.0004053805,0.0068852287,0.0011768398,0.096767515,0.7611282,0.081062905,0.005981831,0.003526702],"about_ca_topic_score_codex":0.000019520068,"about_ca_topic_score_gemma":0.0000076386505,"teacher_disagreement_score":0.9734794,"about_ca_system_score_codex":0.00012990716,"about_ca_system_score_gemma":0.00006936298,"threshold_uncertainty_score":0.96763927},"labels":[],"label_agreement":null},{"id":"W3122447812","doi":"10.15353/jcvis.v6i1.3533","title":"2D Positional Embedding-based Transformer for Scene Text Recognition","year":2021,"lang":"en","type":"article","venue":"Journal of Computational Vision and Imaging Systems","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"ATS Automation Tooling Systems (Canada); University of Waterloo","funders":"Ontario Centres of Excellence","keywords":"Computer science; Transformer; Artificial intelligence; Encoder; Embedding; Leverage (statistics); Architecture; Pattern recognition (psychology); Text recognition; Computer vision; Image (mathematics); Engineering; Geography","score_opus":0.015430532486448805,"score_gpt":0.2989395937905886,"score_spread":0.2835090613041398,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3122447812","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":[0.006878939,0.00071502104,0.9880996,0.003400045,0.00046520992,0.00016254923,0.00002549962,0.000051245148,0.00020194125],"genre_scores_gemma":[0.7549889,0.000019854739,0.2438898,0.0008173902,0.00018237968,0.000010630383,0.0000468937,0.00001197907,0.00003218921],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99843925,0.00012340002,0.0006196708,0.00018209188,0.00048251447,0.00015308909],"domain_scores_gemma":[0.9973063,0.00042643616,0.00034190255,0.000082415456,0.001722277,0.00012065738],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006672548,0.00013225025,0.00025378744,0.00028934164,0.00017088882,0.00047909538,0.00016532066,0.000042856565,0.000018703708],"category_scores_gemma":[0.00006621631,0.00011781531,0.00015920271,0.00021708666,0.0000376374,0.00089388725,0.000015718218,0.00013016748,0.000006131904],"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":[0.00020864798,0.0008273895,0.00050649064,0.00062216655,0.00020040582,0.00017114595,0.00072737166,0.01470509,0.017311126,0.01139956,0.02654272,0.9267779],"study_design_scores_gemma":[0.0024204778,0.0003178402,0.001883473,0.0011329494,0.000038836384,0.0024743986,0.00015073865,0.94505835,0.006811094,0.033204038,0.0061896876,0.00031814608],"about_ca_topic_score_codex":0.0000020005405,"about_ca_topic_score_gemma":2.1656804e-7,"teacher_disagreement_score":0.9303532,"about_ca_system_score_codex":0.00005608507,"about_ca_system_score_gemma":0.0002842851,"threshold_uncertainty_score":0.48043692},"labels":[],"label_agreement":null},{"id":"W3127551618","doi":"10.15353/jcvis.v6i1.3543","title":"Challenges of Deep Learning-based Text Detection in the Wild","year":2021,"lang":"en","type":"article","venue":"Journal of Computational Vision and Imaging Systems","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"ATS Automation Tooling Systems (Canada); University of Waterloo","funders":"","keywords":"Benchmark (surveying); Computer science; Artificial intelligence; Distortion (music); Deep learning; Perspective (graphical); Machine learning; Text detection; Function (biology); Pattern recognition (psychology); Image (mathematics)","score_opus":0.01399929453120768,"score_gpt":0.2751410523217244,"score_spread":0.26114175779051674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3127551618","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":[0.017328685,0.0042823222,0.97538924,0.0023853835,0.00018242173,0.000065326385,2.578555e-7,0.000018624984,0.00034774732],"genre_scores_gemma":[0.9935632,0.00009392055,0.0061540054,0.00013388542,0.000044963952,0.0000018711482,5.9059784e-7,0.000003902671,0.0000036567014],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985575,0.0004069587,0.00043844688,0.0001008111,0.00041846806,0.00007778403],"domain_scores_gemma":[0.99855155,0.0004528792,0.0003669959,0.00008466052,0.00051238894,0.00003153274],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011019484,0.00007195642,0.00017556353,0.00023542266,0.000059655533,0.00013727765,0.0001936177,0.000024538427,0.00000194426],"category_scores_gemma":[0.00011456519,0.00005119247,0.00006101854,0.00024228569,0.000030253323,0.00033460942,0.00002879991,0.00019312507,0.0000011782556],"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":[0.000016015565,0.00017568372,0.0009732041,0.00012937741,0.000018616875,0.00007498001,0.0016019263,0.025202483,0.0011591052,0.0043894094,0.00010368698,0.9661555],"study_design_scores_gemma":[0.00079811894,0.00025209636,0.032748714,0.00057848264,0.0000086156315,0.0014454677,0.00140927,0.9527334,0.0017123362,0.0065393737,0.0016511629,0.00012294529],"about_ca_topic_score_codex":0.000004727756,"about_ca_topic_score_gemma":0.0000027755214,"teacher_disagreement_score":0.9762345,"about_ca_system_score_codex":0.000021998318,"about_ca_system_score_gemma":0.00005826175,"threshold_uncertainty_score":0.20875683},"labels":[],"label_agreement":null},{"id":"W3131584316","doi":"10.1007/978-3-030-68787-8_20","title":"Simultaneous Detection of Regular Patterns in Ancient Manuscripts Using GAN-Based Deep Unsupervised Segmentation","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Handwritten Text Recognition Techniques","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":"École de Technologie Supérieure","funders":"","keywords":"Computer science; Segmentation; Artificial intelligence; Ornaments; Task (project management); Deep learning; Market segmentation; Pattern recognition (psychology); Noise (video); Architecture; Unsupervised learning; Image (mathematics); Archaeology","score_opus":0.020694113141351483,"score_gpt":0.24898078988582437,"score_spread":0.2282866767444729,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3131584316","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":[0.015979083,0.00024625807,0.9822134,0.0000673217,0.000684798,0.0005782124,0.000009200113,0.00013576604,0.00008600162],"genre_scores_gemma":[0.70522606,0.00002276772,0.29410937,0.000507048,0.000070227026,0.000011459865,0.000013561373,0.000026202146,0.000013272855],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961626,0.000109157125,0.0007809353,0.0013580896,0.0010633066,0.00052589626],"domain_scores_gemma":[0.99760336,0.00038754643,0.0004051187,0.0010075322,0.0004960824,0.00010036286],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006733005,0.00045741026,0.0005544027,0.001476124,0.00012817202,0.00027848413,0.0013922141,0.00033913396,0.000020797695],"category_scores_gemma":[0.00010764432,0.00048897613,0.00014607134,0.0010258515,0.00028356924,0.0004727984,0.0002839021,0.0005462387,0.000003683065],"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":[0.000008115507,0.000065173175,0.00010729206,0.000119144606,0.0000063252655,0.00024925917,0.00036525974,0.12762658,0.06260722,0.00014359216,2.2606271e-7,0.8087018],"study_design_scores_gemma":[0.00026910673,0.00012276288,0.000074567484,0.0006518641,0.000006818126,0.00004006366,8.884697e-7,0.66272867,0.3315143,0.0042253053,0.000016163853,0.00034946558],"about_ca_topic_score_codex":0.00014123767,"about_ca_topic_score_gemma":0.0006239988,"teacher_disagreement_score":0.80835235,"about_ca_system_score_codex":0.0007238474,"about_ca_system_score_gemma":0.0004042103,"threshold_uncertainty_score":0.9997562},"labels":[],"label_agreement":null},{"id":"W3132571997","doi":"10.1007/978-3-030-68787-8_21","title":"A Two-Stage Unsupervised Deep Learning Framework for Degradation Removal in Ancient Documents","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Handwritten Text Recognition 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":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Computer science; Artificial intelligence; Deep learning; Task (project management); Generative grammar; Stage (stratigraphy); Degradation (telecommunications); Generative adversarial network; Machine learning; Artificial neural network; State (computer science); Pattern recognition (psychology); Engineering; Algorithm","score_opus":0.021642343373121195,"score_gpt":0.28469750886643447,"score_spread":0.26305516549331326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3132571997","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":[0.00050625985,0.0006135508,0.9951481,0.00036297273,0.0009323444,0.00088482833,0.000004933607,0.00029045792,0.0012565062],"genre_scores_gemma":[0.02270904,0.00009382273,0.9748286,0.0014349325,0.00022626255,0.0000738717,0.000033344142,0.000045353234,0.00055478985],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9954215,0.000101210695,0.0007323661,0.0018893742,0.0010305593,0.00082495395],"domain_scores_gemma":[0.99713063,0.0008739666,0.0003512797,0.0010480365,0.00042335634,0.00017272138],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015400329,0.00054006116,0.00061100564,0.0011952375,0.0002798017,0.000894014,0.0022928196,0.00042271297,0.000051341976],"category_scores_gemma":[0.0005053417,0.00056045747,0.0001865761,0.0011414293,0.00027701314,0.0008674236,0.0010424705,0.0012450642,0.000017400038],"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":[0.000009387986,0.000047208105,0.00009254003,0.000070991104,0.000008886178,0.00018760956,0.0007190118,0.006555022,0.00042597626,0.057931073,0.000004097067,0.9339482],"study_design_scores_gemma":[0.0008525052,0.00029357406,0.00010637677,0.0017139904,0.000010464801,0.000106216634,0.0000021738335,0.659748,0.010198644,0.3217754,0.0040545147,0.0011381209],"about_ca_topic_score_codex":0.00003556372,"about_ca_topic_score_gemma":0.00018361617,"teacher_disagreement_score":0.93281007,"about_ca_system_score_codex":0.0006187669,"about_ca_system_score_gemma":0.0005069316,"threshold_uncertainty_score":0.9996847},"labels":[],"label_agreement":null},{"id":"W3132698244","doi":"10.3390/s22103617","title":"SCD: A Stacked Carton Dataset for Detection and Segmentation","year":2022,"lang":"en","type":"article","venue":"Sensors","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Carton; Computer science; Classifier (UML); Artificial intelligence; Segmentation; Computer vision; Engineering","score_opus":0.018622672787664,"score_gpt":0.27118897448788987,"score_spread":0.25256630170022587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3132698244","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":[0.56507665,0.000035021025,0.43152848,0.00058525504,0.00026441205,0.0008686285,0.0011805508,0.00036376505,0.000097245254],"genre_scores_gemma":[0.9546794,0.000010497501,0.043858517,0.00044575526,0.00003536876,0.00030220544,0.0005376417,0.000010982831,0.00011958279],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99936366,0.0000708756,0.00009992853,0.00022047696,0.00013365467,0.000111380614],"domain_scores_gemma":[0.999668,0.000051778177,0.00004957346,0.0001693784,0.000028143662,0.000033125605],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022463348,0.000058392805,0.00006107823,0.000096791286,0.00024453056,0.000059955928,0.00012447646,0.000015670275,0.000017992306],"category_scores_gemma":[0.000018712675,0.00006467133,0.000017754488,0.00014771413,0.000014937191,0.00017831825,0.00011690023,0.00006153652,0.0000040875548],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007310279,0.00010739543,0.00011426988,0.00006674709,0.00003640499,0.00001688524,0.0023441617,0.00014571639,0.14245275,0.0018599157,0.014660464,0.8381222],"study_design_scores_gemma":[0.0014150877,0.0010122099,0.00048176272,0.000009603141,0.00002706656,0.00015600788,0.0010255881,0.11731214,0.73386806,0.010369409,0.13382632,0.0004967427],"about_ca_topic_score_codex":0.00003556357,"about_ca_topic_score_gemma":0.000015851227,"teacher_disagreement_score":0.83762544,"about_ca_system_score_codex":0.000048069218,"about_ca_system_score_gemma":0.000012537622,"threshold_uncertainty_score":0.26372203},"labels":[],"label_agreement":null},{"id":"W3136599387","doi":"10.1109/access.2021.3096823","title":"uTHCD: A New Benchmarking for Tamil Handwritten OCR","year":2021,"lang":"en","type":"preprint","venue":"IEEE Access","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":4,"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":"Trent University; Nottingham Trent University","keywords":"Computer science; Tamil; Database; Grid; Benchmark (surveying); Benchmarking; Font; Optical character recognition; Artificial intelligence; Scripting language; Metadata; Field (mathematics); Information retrieval; Natural language processing; Pattern recognition (psychology); World Wide Web; Image (mathematics)","score_opus":0.06194948546271989,"score_gpt":0.33909676462188854,"score_spread":0.27714727915916865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3136599387","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":[0.005868091,0.0005893893,0.9848798,0.0012394426,0.0034566557,0.0011389408,0.000038695143,0.0010058612,0.0017831346],"genre_scores_gemma":[0.33877146,0.00064553786,0.6488537,0.0039724363,0.0037838367,0.00155889,0.00031787972,0.00014742924,0.0019488184],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99656206,0.00011634112,0.0006559825,0.001500093,0.00053397176,0.0006315309],"domain_scores_gemma":[0.99684817,0.00026355952,0.00044138293,0.0016501097,0.00051930186,0.00027750226],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005211202,0.0005120614,0.00069451355,0.000382943,0.0002034274,0.0035342232,0.0046842513,0.00055322156,0.00011329221],"category_scores_gemma":[0.00012033509,0.00054840086,0.00045142803,0.00047371097,0.000049645296,0.0012403084,0.0029629061,0.0007337037,0.00001930772],"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":[0.000019231442,0.00018693492,0.00037103487,0.00078841567,0.00024578124,0.00012059869,0.0010939043,0.00013856965,0.0014522529,0.0012846714,0.118389726,0.87590885],"study_design_scores_gemma":[0.0034219525,0.0004521169,0.0023758798,0.006034564,0.00037997993,0.00021868727,0.000101403006,0.08483793,0.51970905,0.29376516,0.082580805,0.0061224946],"about_ca_topic_score_codex":0.00059645606,"about_ca_topic_score_gemma":0.00017081044,"teacher_disagreement_score":0.8697864,"about_ca_system_score_codex":0.00014794066,"about_ca_system_score_gemma":0.0010112214,"threshold_uncertainty_score":0.99969673},"labels":[],"label_agreement":null},{"id":"W3142983592","doi":"","title":"2 - Utilisation de la transformée de Fourier-Mellin pour la reconnaissance de formes multi-orientées et multi-échelles : application à l'analyse automatique de documents techniques","year":2001,"lang":"fr","type":"article","venue":"Traitement du signal","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Artificial intelligence; Pattern recognition (psychology); Fourier transform; Invariant (physics); Set (abstract data type); Mathematics","score_opus":0.03040789133369996,"score_gpt":0.3244224327595335,"score_spread":0.2940145414258335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3142983592","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":[0.07071477,0.00071329315,0.92084855,0.003922706,0.00004706712,0.0012757136,0.000048790058,0.0009823749,0.0014467274],"genre_scores_gemma":[0.51704293,0.0019267738,0.4786509,0.000713117,0.00011425405,0.0008323488,0.000040802894,0.000048976446,0.0006298984],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9949169,0.0017286086,0.0009965834,0.00078958296,0.00047585316,0.0010924413],"domain_scores_gemma":[0.99773675,0.00065719464,0.0004577399,0.00045753727,0.00027308302,0.00041770737],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00557357,0.00056921336,0.00046391395,0.00037319772,0.00035311395,0.0005877266,0.000874135,0.0005792473,0.000300821],"category_scores_gemma":[0.00014284486,0.00063922745,0.00031593334,0.00055565377,0.00036797367,0.0015680727,0.00008713697,0.0006185571,0.000036456506],"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":[0.00011806641,0.0026606082,0.013435417,0.00046324954,0.00032418917,0.00013233209,0.020839566,0.0006330599,0.07745266,0.01737693,0.0022957579,0.8642682],"study_design_scores_gemma":[0.001584968,0.00020998977,0.0062825177,0.0005963951,0.00018478351,0.00036761133,0.00041027102,0.5882608,0.35369092,0.02098133,0.026711464,0.0007188939],"about_ca_topic_score_codex":0.0010516942,"about_ca_topic_score_gemma":0.00024263107,"teacher_disagreement_score":0.8635493,"about_ca_system_score_codex":0.0009226833,"about_ca_system_score_gemma":0.0008678654,"threshold_uncertainty_score":0.9996059},"labels":[],"label_agreement":null},{"id":"W3146762582","doi":"10.18653/v1/2022.nlpcss-1.19","title":"OLALA: Object-Level Active Learning for Efficient Document Layout Annotation","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Harvard Data Science Initiative, Harvard University; Harvard Catalyst; National Science Foundation","keywords":"Annotation; Computer science; Automatic image annotation; Artificial intelligence; Object (grammar); Information retrieval; Process (computing); Active learning (machine learning); Image retrieval; Machine learning; Image (mathematics); Pattern recognition (psychology)","score_opus":0.0334919703407659,"score_gpt":0.30541292926826225,"score_spread":0.27192095892749635,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3146762582","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":[0.006646287,0.000045829398,0.9800655,0.0005780223,0.00074601336,0.0017648084,0.000045789267,0.0013278491,0.008779899],"genre_scores_gemma":[0.5636327,0.000041104508,0.4243805,0.0005252004,0.0001850668,0.0041262694,0.00044479466,0.00006218256,0.0066021364],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972406,0.0002347946,0.00045525687,0.0010699801,0.0005976647,0.00040172433],"domain_scores_gemma":[0.9982009,0.00030258275,0.00039611253,0.00064720237,0.00035428556,0.00009894966],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00082819146,0.00034128918,0.00036338216,0.00038855366,0.00037561814,0.0004169062,0.0011678559,0.00019624246,0.00035052196],"category_scores_gemma":[0.00017077374,0.000349606,0.0002673744,0.00027979165,0.000030884283,0.00020108144,0.0024535696,0.0008897526,0.000041186413],"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":[0.0000969328,0.00051820657,0.00010411927,0.0004692452,0.0003121848,0.00002504812,0.011202546,0.05268479,0.0009761363,0.051077876,0.007609104,0.8749238],"study_design_scores_gemma":[0.002914045,0.0016421935,0.0029040144,0.00048732644,0.00016946712,0.000041728686,0.0023649093,0.6538634,0.15234756,0.11132355,0.06816313,0.0037787165],"about_ca_topic_score_codex":0.00011023544,"about_ca_topic_score_gemma":0.000009736071,"teacher_disagreement_score":0.87114507,"about_ca_system_score_codex":0.00050994544,"about_ca_system_score_gemma":0.0003039617,"threshold_uncertainty_score":0.9998956},"labels":[],"label_agreement":null},{"id":"W3146905089","doi":"10.23977/jaip.2020.040101","title":"The Recognition of Tibetan Handwritten Numbers Based on Federated Learning","year":2021,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Practice","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Numeral system; Computer science; Identification (biology); Process (computing); Artificial intelligence; Pattern recognition (psychology); Speech recognition","score_opus":0.04480459474651922,"score_gpt":0.32261531270985916,"score_spread":0.27781071796333995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3146905089","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":[0.004992942,0.00014654346,0.97827864,0.009837466,0.00057167985,0.000113597016,0.0000014509124,0.000058853035,0.005998852],"genre_scores_gemma":[0.90097046,0.00045541726,0.097210355,0.0010331046,0.00019886931,0.0000056047456,0.0000028096722,0.000017654065,0.000105737985],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99705005,0.0008663886,0.0009555152,0.00021165282,0.0006870737,0.00022931324],"domain_scores_gemma":[0.99254644,0.0031598278,0.0012429871,0.00025002775,0.0026977279,0.00010298276],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028836003,0.00013831479,0.00023813927,0.00015771735,0.00037336836,0.0005268007,0.0004903529,0.000091552785,0.00007374194],"category_scores_gemma":[0.0077297552,0.000107980544,0.00017035859,0.00076796993,0.000095779345,0.0011418132,0.00006452305,0.0007362124,0.00007446558],"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":[0.00026511974,0.0003723188,0.00001879297,0.000011963198,0.00006206975,0.00018158091,0.00041537156,0.0005572816,0.010619025,0.002997717,0.00038130634,0.98411745],"study_design_scores_gemma":[0.0000829138,0.0008853311,0.000020996276,0.00025875607,0.000059520946,0.0003881822,0.0023613537,0.050161492,0.91610545,0.018818604,0.010651943,0.00020544614],"about_ca_topic_score_codex":0.000018540193,"about_ca_topic_score_gemma":0.000020560514,"teacher_disagreement_score":0.983912,"about_ca_system_score_codex":0.00007216715,"about_ca_system_score_gemma":0.00039530668,"threshold_uncertainty_score":0.92537975},"labels":[],"label_agreement":null},{"id":"W3157531239","doi":"10.3934/mbe.2021189","title":"Defect detection in code characters with complex backgrounds based on BBE","year":2021,"lang":"en","type":"article","venue":"Mathematical Biosciences & Engineering","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"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; Robustness (evolution); Code (set theory); Artificial intelligence; Set (abstract data type); Source code; Transferability; Object detection; Process (computing); Computer engineering; Pattern recognition (psychology); Data mining; Computer vision; Machine learning; Programming language","score_opus":0.0207169744252643,"score_gpt":0.23825333884602365,"score_spread":0.21753636442075935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3157531239","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":[0.09684775,0.000005670966,0.9011704,0.00061362947,0.00006485997,0.00012814242,0.0000015975901,0.0003613575,0.00080659497],"genre_scores_gemma":[0.8844015,0.0000017211652,0.115039274,0.00048674466,0.000010112968,0.00003834594,0.0000015619011,0.000009094386,0.000011637469],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985653,0.00003863063,0.00023665823,0.00041564615,0.00041752256,0.00032623115],"domain_scores_gemma":[0.9992103,0.00025665114,0.00004639378,0.00033224226,0.000051955012,0.00010244959],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043567322,0.00016161732,0.00020998616,0.0002342272,0.00006370903,0.00023521455,0.0003967479,0.000049407936,0.000036547248],"category_scores_gemma":[0.00015495841,0.0001310379,0.000062681975,0.0011104677,0.000055847606,0.000344719,0.00006771492,0.00017163303,0.000040142877],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038180442,0.0014737376,0.0007420698,0.0005588881,0.0000433031,0.0005754543,0.0010505718,0.007057408,0.77815074,0.12223192,0.00011051979,0.08796721],"study_design_scores_gemma":[0.00023625187,0.0001963012,0.0028201633,0.00024057836,0.0000037403008,0.00004695104,0.0000256854,0.8277414,0.16708417,0.0010010471,0.00032834263,0.0002753941],"about_ca_topic_score_codex":0.0000027471947,"about_ca_topic_score_gemma":0.000010985794,"teacher_disagreement_score":0.82068396,"about_ca_system_score_codex":0.000083403014,"about_ca_system_score_gemma":0.00005167197,"threshold_uncertainty_score":0.5343571},"labels":[],"label_agreement":null},{"id":"W3161193347","doi":"10.1142/s0219467822500152","title":"Histogram of Marked Background (HMB) Feature Extraction Method for Arabic Handwriting Recognition","year":2021,"lang":"en","type":"article","venue":"International Journal of Image and Graphics","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Handwriting; Histogram; Computer science; Artificial intelligence; Pattern recognition (psychology); Hidden Markov model; Handwriting recognition; Pixel; Feature extraction; Feature (linguistics); Arabic; Image (mathematics); Linguistics","score_opus":0.026623481588054023,"score_gpt":0.3361669086376732,"score_spread":0.3095434270496192,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3161193347","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":[0.01567921,0.00047465414,0.9802429,0.0026791953,0.00046346197,0.00007883757,0.000024030493,0.000023417004,0.00033428697],"genre_scores_gemma":[0.09031337,0.0009108828,0.9078467,0.00052398985,0.0002638272,0.000008011814,0.000026835434,0.000011148691,0.00009526759],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99880326,0.000113599046,0.00043704975,0.000170906,0.0003672823,0.00010792613],"domain_scores_gemma":[0.99603957,0.00040292676,0.00054696016,0.00010354353,0.0028457704,0.00006121987],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00087694905,0.00010202847,0.00019964227,0.00035156208,0.00005883045,0.00020240455,0.0002882778,0.000092008355,0.000018301951],"category_scores_gemma":[0.00032487838,0.00009884396,0.00020549717,0.00021803426,0.000047735437,0.00099694,0.000058260997,0.00024140073,5.9331364e-7],"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":[0.00013367838,0.00024986736,0.00025383453,0.000086494954,0.00027567716,0.00018255314,0.00023233112,7.5556966e-7,0.120426476,0.0045968317,0.0038776007,0.8696839],"study_design_scores_gemma":[0.00439201,0.00083034637,0.00657728,0.0014485184,0.00023542102,0.009732521,0.0006421556,0.010572327,0.68014526,0.24726717,0.0374486,0.00070837187],"about_ca_topic_score_codex":0.000006797891,"about_ca_topic_score_gemma":0.000010820968,"teacher_disagreement_score":0.8689755,"about_ca_system_score_codex":0.000034224828,"about_ca_system_score_gemma":0.00008852955,"threshold_uncertainty_score":0.40307397},"labels":[],"label_agreement":null},{"id":"W3164449140","doi":"10.18280/ria.350206","title":"AksharaNet: A GPU Accelerated Modified Depth-Wise Separable Convolution for Kannada Text Classification","year":2021,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Artificial intelligence; Convolutional neural network; Grayscale; Convolution (computer science); Character (mathematics); Pattern recognition (psychology); Kannada; Search engine indexing; Deep learning; Scale (ratio); Key (lock); Artificial neural network; Image (mathematics); Mathematics","score_opus":0.10110669477023192,"score_gpt":0.3153051932894518,"score_spread":0.21419849851921985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3164449140","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":[0.006256302,0.00049754407,0.9836144,0.0014695657,0.00038344797,0.00071538216,0.000021123553,0.0005555578,0.006486718],"genre_scores_gemma":[0.9583895,0.00022264186,0.035259616,0.00045764452,0.000104381055,0.00042965802,0.00013366989,0.000030163948,0.0049727294],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975709,0.00012997344,0.00067401025,0.0008620706,0.0002473647,0.0005157082],"domain_scores_gemma":[0.99756867,0.0002678766,0.00022248439,0.0009357785,0.00084901205,0.00015615424],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005050697,0.00024804063,0.0003028929,0.00016926926,0.00033697372,0.00036651458,0.00068351114,0.00018894626,0.0002145988],"category_scores_gemma":[0.00028213157,0.00027609416,0.00017060862,0.0010804555,0.000078637175,0.0006851437,0.00013295612,0.00021299573,0.0004974702],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000078436045,0.0008305363,0.00014109592,0.00029997894,0.00008455156,0.000060190872,0.0016065249,0.0067668334,0.24636833,0.13504273,0.01900512,0.58971566],"study_design_scores_gemma":[0.000075853175,0.00006258115,0.00006587786,0.000070056194,0.000010512253,0.000038531372,0.00013498236,0.57046324,0.40685642,0.009223667,0.012744162,0.00025414853],"about_ca_topic_score_codex":0.000040693507,"about_ca_topic_score_gemma":0.000054420256,"teacher_disagreement_score":0.9521332,"about_ca_system_score_codex":0.00013433631,"about_ca_system_score_gemma":0.00023736655,"threshold_uncertainty_score":0.9999691},"labels":[],"label_agreement":null},{"id":"W3166167994","doi":"10.21742/ijhit.2021.14.1.05","title":"The Study of Handwriting Recognition Algorithms Based on Neural Networks","year":2021,"lang":"en","type":"article","venue":"International Journal of Hybrid Information Technology","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Athabasca University","funders":"","keywords":"Computer science; Convolutional neural network; Intelligent character recognition; Artificial intelligence; Handwriting recognition; Pattern recognition (psychology); Handwriting; Classifier (UML); Feature (linguistics); Graph; Speech recognition; Feature extraction; Image (mathematics); Character recognition","score_opus":0.012029196630704229,"score_gpt":0.25844025487217603,"score_spread":0.2464110582414718,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3166167994","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":[0.10220819,0.00006204654,0.8918784,0.003907715,0.0011179178,0.0001727271,0.000007638218,0.00012407708,0.0005212875],"genre_scores_gemma":[0.98664886,0.00006137363,0.012672497,0.0005006727,0.00008140561,0.000014400777,0.000011428667,0.0000047524186,0.0000046069176],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99803394,0.000094946474,0.0009822318,0.0000983036,0.0006411266,0.00014944171],"domain_scores_gemma":[0.99575263,0.00025266295,0.0010265324,0.00026057794,0.0026723794,0.00003519026],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006625176,0.00010969164,0.00017372706,0.0006965766,0.000117279604,0.00022343831,0.0011334078,0.000050898117,0.000015110833],"category_scores_gemma":[0.0006006367,0.000086946624,0.00009744243,0.00041891827,0.00006354838,0.0012519789,0.00016977626,0.00038002548,0.0000075192165],"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":[0.00004212945,0.00022224332,0.00026700526,0.000003395099,0.000071924194,0.00009865802,0.00008342999,0.0024700055,0.000058571095,0.0011593705,0.0005301456,0.99499315],"study_design_scores_gemma":[0.0028827386,0.001673032,0.0004672172,0.00019574272,0.000023029612,0.0021122412,0.001541488,0.87353903,0.10354531,0.010417748,0.0033507526,0.0002517025],"about_ca_topic_score_codex":0.0000029484893,"about_ca_topic_score_gemma":0.0000021430976,"teacher_disagreement_score":0.99474144,"about_ca_system_score_codex":0.000078096404,"about_ca_system_score_gemma":0.00009760603,"threshold_uncertainty_score":0.35455805},"labels":[],"label_agreement":null},{"id":"W3167290312","doi":"10.1109/cvpr46437.2021.01342","title":"House-GAN++: Generative Adversarial Layout Refinement Network towards Intelligent Computational Agent for Professional Architects","year":2021,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":130,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Floorplan; Iterative refinement; Iterative and incremental development; Generator (circuit theory); Metric (unit); Constraint (computer-aided design); Generative grammar; Computer engineering; Graph; Process (computing); Iterative method; Generative adversarial network; Ground truth; Theoretical computer science; Artificial intelligence; Deep learning; Software engineering; Algorithm; Programming language; Embedded system","score_opus":0.03557646882454432,"score_gpt":0.3029209010096701,"score_spread":0.2673444321851258,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3167290312","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":[0.0014483469,0.00009318927,0.99011743,0.003804797,0.0012921585,0.0006592413,0.000021521173,0.000664227,0.0018990588],"genre_scores_gemma":[0.095025286,0.000019872321,0.89708006,0.004593993,0.00067236205,0.00037132096,0.00010608357,0.00003055336,0.0021004805],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978185,0.0001796366,0.00044770405,0.00061283173,0.0005244853,0.0004168304],"domain_scores_gemma":[0.9986893,0.0002035527,0.00012802213,0.0003341954,0.00051138573,0.00013352507],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043519356,0.00022162325,0.00025187252,0.000087914406,0.0002761155,0.0001667939,0.0004635698,0.00009146422,0.00025741392],"category_scores_gemma":[0.00008512812,0.00019621052,0.00017297041,0.00033548687,0.000046540594,0.00018024663,0.00038406,0.00017288368,0.000060598806],"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":[0.00011341486,0.0009858585,0.0001233935,0.00010140604,0.00031854011,0.00009589243,0.002580433,0.04133663,0.0008991679,0.21875294,0.21711282,0.5175795],"study_design_scores_gemma":[0.0027787616,0.0008913065,0.0011607686,0.00032175428,0.000056271514,0.00011303769,0.0002953961,0.49257714,0.16131824,0.20297295,0.13612688,0.0013874952],"about_ca_topic_score_codex":0.000012744598,"about_ca_topic_score_gemma":0.000039498336,"teacher_disagreement_score":0.516192,"about_ca_system_score_codex":0.00013279637,"about_ca_system_score_gemma":0.000623857,"threshold_uncertainty_score":0.8001232},"labels":[],"label_agreement":null},{"id":"W3178965751","doi":"10.1142/s0219467822500358","title":"Spatial Distribution of Ink at Keypoints (SDIK): A Novel Feature for Word Spotting in Arabic Documents","year":2021,"lang":"en","type":"article","venue":"International Journal of Image and Graphics","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"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; Handwriting; Spotting; Artificial intelligence; Feature (linguistics); Word (group theory); Task (project management); Arabic; Handwriting recognition; Inkwell; Matching (statistics); Natural language processing; Pattern recognition (psychology); Pixel; Feature extraction; Speech recognition; Mathematics; Linguistics","score_opus":0.010769024176913864,"score_gpt":0.2792518819922136,"score_spread":0.26848285781529974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3178965751","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":[0.34043586,0.00016486933,0.6565671,0.0023490477,0.0002981419,0.000074156495,0.000053206342,0.000009259955,0.000048377347],"genre_scores_gemma":[0.9556839,0.00027035348,0.04364581,0.00021597043,0.000101820406,0.000003810604,0.000031753956,0.0000049686028,0.000041653362],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99898165,0.000031903666,0.00038795726,0.00013760137,0.00035398724,0.00010687824],"domain_scores_gemma":[0.9982746,0.0001289721,0.0003618943,0.00008534533,0.0011022347,0.000046935907],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004054652,0.0000836798,0.00016301533,0.0002115984,0.000032928718,0.000101637794,0.00031984656,0.00006269385,0.000006338467],"category_scores_gemma":[0.00030116338,0.00007835068,0.000113746304,0.00020182673,0.0000448942,0.00055706355,0.000152024,0.0001757852,3.719319e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00089633965,0.0017991237,0.08669817,0.00027062898,0.00079197565,0.0012439425,0.0022178746,0.000018448254,0.25105023,0.040076766,0.0074459054,0.6074906],"study_design_scores_gemma":[0.009925978,0.0006169995,0.35561526,0.0022836954,0.000080835765,0.0034790626,0.00017680154,0.012193349,0.49524376,0.1083507,0.011302814,0.0007307458],"about_ca_topic_score_codex":0.000018048962,"about_ca_topic_score_gemma":0.000051576848,"teacher_disagreement_score":0.61524796,"about_ca_system_score_codex":0.000060876206,"about_ca_system_score_gemma":0.00007252245,"threshold_uncertainty_score":0.3195048},"labels":[],"label_agreement":null},{"id":"W318724287","doi":"10.1007/978-0-85729-859-1_30","title":"Online Signature Verification","year":2014,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Signature (topology); Computer science; The Internet; World Wide Web; Mathematics","score_opus":0.012963940899010044,"score_gpt":0.2499117108024928,"score_spread":0.23694776990348276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W318724287","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":[0.0016672909,0.000009761372,0.9770042,0.0014986754,0.00006419074,0.000055773162,6.473042e-7,0.0007820387,0.018917428],"genre_scores_gemma":[0.6564411,0.0000056250024,0.34119466,0.0015208737,0.00005513615,0.0000069174007,0.000008831828,0.0000034037723,0.0007634653],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99953026,0.000032516124,0.0000843251,0.00016563816,0.000101939986,0.00008532956],"domain_scores_gemma":[0.99952537,0.000032168376,0.000026349404,0.00031510825,0.00006443917,0.000036557805],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013284167,0.000049375154,0.000050556308,0.000050815284,0.00003242514,0.000054020984,0.00037382243,0.000047756155,0.00006191167],"category_scores_gemma":[0.000038346618,0.000041511998,0.000021749449,0.00015523133,0.000010667036,0.00022916029,0.000048757312,0.00007177131,0.00014719936],"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":[5.1750345e-7,0.0000809729,0.000036146586,0.0000038587023,0.0000022948363,4.7881485e-7,0.000048564798,8.173227e-7,0.008312645,0.23280212,0.009623455,0.7490881],"study_design_scores_gemma":[0.00042631215,0.00025147872,0.0088033145,0.00003225373,0.0000052696655,0.000022253793,0.000018215835,0.13500962,0.38627183,0.14336866,0.32524547,0.00054532924],"about_ca_topic_score_codex":0.000004461279,"about_ca_topic_score_gemma":0.0000034573752,"teacher_disagreement_score":0.7485428,"about_ca_system_score_codex":0.000008700672,"about_ca_system_score_gemma":0.000008852772,"threshold_uncertainty_score":0.18919991},"labels":[],"label_agreement":null},{"id":"W3196382033","doi":"10.1007/978-3-030-86198-8_23","title":"Improving Handwritten Arabic Text Recognition Using an Adaptive Data-Augmentation Algorithm","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","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":"Cambrian College","funders":"","keywords":"Computer science; Lexicon; Word (group theory); Artificial intelligence; Arabic; Natural language processing; Task (project management); Pattern recognition (psychology); Handwriting recognition; Speech recognition; Feature extraction; Mathematics","score_opus":0.06282409887958935,"score_gpt":0.29128631287973106,"score_spread":0.22846221400014172,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3196382033","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":[0.00010706769,0.00038353557,0.9965995,0.00013198676,0.0011144414,0.0006621979,0.000093803515,0.000435297,0.00047217146],"genre_scores_gemma":[0.0052124853,0.00006527121,0.99248785,0.0010273015,0.000690711,0.00001918401,0.00034530426,0.00006310676,0.00008877905],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99406993,0.00015194256,0.00081923616,0.002937907,0.0012713387,0.00074963784],"domain_scores_gemma":[0.9954904,0.00032349495,0.00061607285,0.0024904136,0.00081830926,0.00026131095],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0015769324,0.0006903521,0.0006713737,0.0011708809,0.00046088157,0.0014564886,0.003918973,0.00047473557,0.00008789829],"category_scores_gemma":[0.00012635902,0.0007215475,0.00012371915,0.00089853536,0.00051953166,0.004215309,0.0024942204,0.0010117823,0.00004497097],"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":[0.000004140428,0.000052308093,0.0000017725858,0.00002325901,0.000014775899,0.00011427094,0.0001915862,0.00038415796,0.00092644215,0.00021594907,0.000005221375,0.9980661],"study_design_scores_gemma":[0.00032192637,0.00031206055,0.000011303195,0.0006381971,0.00003597095,0.00026612188,0.0000016348762,0.9307927,0.013951863,0.05262372,0.00010142037,0.00094311545],"about_ca_topic_score_codex":0.00018157654,"about_ca_topic_score_gemma":0.0001581279,"teacher_disagreement_score":0.997123,"about_ca_system_score_codex":0.0005937836,"about_ca_system_score_gemma":0.0010250569,"threshold_uncertainty_score":0.9995801},"labels":[],"label_agreement":null},{"id":"W3199808029","doi":"10.36227/techrxiv.16569420.v1","title":"Soft Computing Approaches for tagging Arabic text","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Association of Canadian Archivists","funders":"","keywords":"Computer science; Artificial intelligence; Arabic; Support vector machine; Hindi; Natural language processing; Artificial neural network; Process (computing); Multilayer perceptron; Perceptron; Part of speech; Machine learning; Speech recognition; Linguistics","score_opus":0.06861444804767225,"score_gpt":0.28092561340744,"score_spread":0.21231116535976774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3199808029","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":[0.0012063675,0.00027065966,0.98483574,0.0012877474,0.00053778343,0.0008630952,0.000006054121,0.00197201,0.009020533],"genre_scores_gemma":[0.29787835,0.000014716285,0.7003844,0.00079829496,0.0002029536,0.00017993352,0.000069186346,0.00003114212,0.00044102938],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99737644,0.00010286944,0.0005145177,0.0012243626,0.000304903,0.00047688285],"domain_scores_gemma":[0.9979353,0.00032563912,0.00027899162,0.0010702468,0.00027286066,0.0001169829],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00074751617,0.00037685136,0.0005179472,0.0002373842,0.00019171,0.0011622991,0.0016298012,0.00035038075,0.000038771876],"category_scores_gemma":[0.00014474572,0.00037659897,0.00035877034,0.00023306742,0.00005073472,0.0003013712,0.0030029688,0.0005778217,0.000020285963],"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":[0.0000018423808,0.000118799166,0.00004918643,0.00054562825,0.00008519043,0.000012643983,0.0008720876,0.00043265635,0.00013898713,0.022167156,0.0032886604,0.9722872],"study_design_scores_gemma":[0.0002859923,0.000050550458,0.000114858216,0.0006412054,0.000030710253,0.000047761732,0.00023212704,0.9319678,0.025551684,0.036458142,0.0035681487,0.0010509988],"about_ca_topic_score_codex":0.000030457313,"about_ca_topic_score_gemma":0.000009271869,"teacher_disagreement_score":0.97123617,"about_ca_system_score_codex":0.00009382009,"about_ca_system_score_gemma":0.00027138783,"threshold_uncertainty_score":0.9998746},"labels":[],"label_agreement":null},{"id":"W3202466114","doi":"10.1007/978-3-030-86549-8_9","title":"LayoutParser: A Unified Toolkit for Deep Learning Based Document Image Analysis","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":117,"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":"Computer science; Parsing; Digitization; Set (abstract data type); Reuse; Reusability; Extensibility; Artificial intelligence; Software engineering; World Wide Web; Programming language; Software; Computer vision","score_opus":0.01471688984861719,"score_gpt":0.2596056761146642,"score_spread":0.244888786266047,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3202466114","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":[0.00003157362,0.00026874733,0.9955791,0.00083617563,0.00044583756,0.00066420133,0.000008845686,0.00047722858,0.0016882501],"genre_scores_gemma":[0.039968617,0.000042184267,0.95707124,0.0016769242,0.00023335293,0.00008731497,0.00007309002,0.000046849316,0.00080041884],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9952019,0.00009837569,0.00073349004,0.0021019897,0.0010579723,0.0008062756],"domain_scores_gemma":[0.996054,0.0009777276,0.00043600678,0.0014983821,0.00081078475,0.0002230939],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0015102312,0.0006307516,0.0009142048,0.0019403836,0.0003830936,0.0014783205,0.0029234483,0.0003814556,0.00013682489],"category_scores_gemma":[0.00026151034,0.0006277391,0.0005568049,0.0019467054,0.00041046814,0.00073301024,0.0010041263,0.0008670398,0.000025953583],"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":[0.000013469525,0.00005917499,0.000060197144,0.00010502237,0.00017282902,0.00017147488,0.00044910706,0.03678847,0.00042087302,0.012401798,0.000024903302,0.94933265],"study_design_scores_gemma":[0.00047578698,0.00029198555,0.000056082274,0.0003075694,0.00016182051,0.000020696152,5.4237955e-7,0.9143375,0.01386668,0.06526912,0.0041229553,0.0010892735],"about_ca_topic_score_codex":0.000024362129,"about_ca_topic_score_gemma":0.00014815938,"teacher_disagreement_score":0.9482434,"about_ca_system_score_codex":0.00042251646,"about_ca_system_score_gemma":0.00061026815,"threshold_uncertainty_score":0.9996174},"labels":[],"label_agreement":null},{"id":"W3203851352","doi":"10.1016/j.neucom.2022.09.094","title":"On cropped versus uncropped training sets in tabular structure detection","year":2022,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","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":"Gnowit (Canada); University of Ottawa","funders":"","keywords":"Table (database); Intersection (aeronautics); Set (abstract data type); Computer science; Artificial intelligence; Precision and recall; Training set; Data mining; Machine learning; Geography; Cartography","score_opus":0.027063630919426603,"score_gpt":0.2630589935034269,"score_spread":0.23599536258400028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3203851352","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":[0.8571586,0.000011431404,0.13994958,0.00024763463,0.00093784067,0.00031857574,0.0000043126092,0.0007463921,0.00062567124],"genre_scores_gemma":[0.9880496,7.3240517e-7,0.011213719,0.00061886664,0.00005409522,0.000027190157,0.0000041413873,0.000022485117,0.0000091217635],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99798435,0.00032997745,0.00029237222,0.0005827592,0.00041682212,0.0003937461],"domain_scores_gemma":[0.9991477,0.00027475104,0.00013780655,0.00033937406,0.000035888377,0.000064479296],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030532776,0.00018016563,0.00018361572,0.0003630023,0.00042844276,0.00012378,0.00064351334,0.00005041239,0.000045403667],"category_scores_gemma":[0.00010890892,0.00020911577,0.00006294975,0.00087154406,0.00001759,0.00017831585,0.00046014902,0.000706836,0.0000081632925],"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":[0.00008557156,0.000067180765,0.00008837117,0.000013533253,0.000009438985,0.00020731176,0.0017140203,0.010567084,0.033447906,0.0015043974,0.00013207774,0.9521631],"study_design_scores_gemma":[0.0057977885,0.0023729235,0.0043291096,0.00009677696,0.000014534536,0.0002880063,0.00056692865,0.844107,0.1138404,0.022173865,0.0050596613,0.0013530548],"about_ca_topic_score_codex":0.000022408924,"about_ca_topic_score_gemma":0.000024087958,"teacher_disagreement_score":0.9508101,"about_ca_system_score_codex":0.00015284719,"about_ca_system_score_gemma":0.000051950537,"threshold_uncertainty_score":0.85274935},"labels":[],"label_agreement":null},{"id":"W3208625967","doi":"10.1162/tacl_a_00427","title":"Lexically Aware Semi-Supervised Learning for OCR Post-Correction","year":2021,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Government of Canada; National Endowment for the Humanities; National Science Foundation","keywords":"Computer science; Decoding methods; Optical character recognition; Consistency (knowledge bases); Artificial intelligence; Natural language processing; Language model; Raw data; Vocabulary; Error detection and correction; Machine learning; Speech recognition; Image (mathematics); Algorithm","score_opus":0.013893598658533842,"score_gpt":0.26406367339091125,"score_spread":0.2501700747323774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3208625967","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":[0.00040821152,0.000013786834,0.99571127,0.0009731967,0.0016613659,0.0003858138,0.00012517834,0.00020720603,0.0005139672],"genre_scores_gemma":[0.83721393,0.0000064739684,0.15934196,0.0002586471,0.00020134746,0.0000968961,0.00017064992,0.00001939862,0.002690698],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99867094,0.00010210448,0.00041256085,0.00025090147,0.00038041154,0.0001830935],"domain_scores_gemma":[0.99292195,0.0015562979,0.00032976718,0.00017681456,0.004972375,0.000042768123],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039212845,0.00011814063,0.00018509952,0.00009061831,0.00049648405,0.00009705746,0.00031175118,0.00012298273,0.0000114245595],"category_scores_gemma":[0.0032474082,0.00011947422,0.00031616757,0.0003858344,0.000020755475,0.00009304576,0.000019968249,0.00018511302,0.0000036668837],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015130715,0.0013042832,0.003183178,0.00048483853,0.000916824,0.0000018203394,0.002003108,0.75785506,0.003335119,0.14976783,0.009348501,0.07164813],"study_design_scores_gemma":[0.001000422,0.00020575478,0.0018082509,0.00008038197,0.0001307388,0.0000072471585,0.00010044781,0.91441816,0.023360994,0.04334361,0.015268068,0.00027591095],"about_ca_topic_score_codex":0.000010908791,"about_ca_topic_score_gemma":0.000015734386,"teacher_disagreement_score":0.8368057,"about_ca_system_score_codex":0.00021645369,"about_ca_system_score_gemma":0.00034385305,"threshold_uncertainty_score":0.48720172},"labels":[],"label_agreement":null},{"id":"W3209859250","doi":"10.5220/0010648300003063","title":"A Hybrid Evolutionary Algorithm, Utilizing Novelty Search and Local Optimization, Used to Design Convolutional Neural Networks for Handwritten Digit Recognition","year":2021,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","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":"Concordia University","funders":"","keywords":"Computer science; Convolutional neural network; Novelty; Numerical digit; Artificial intelligence; Pattern recognition (psychology); Digit recognition; Speech recognition; Artificial neural network; Arithmetic; Mathematics","score_opus":0.05327061762621739,"score_gpt":0.27542095899270963,"score_spread":0.22215034136649225,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3209859250","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":[0.0005607429,0.00015649176,0.99601865,0.0015425348,0.00017016864,0.00083604315,0.00006953114,0.000523095,0.0001227203],"genre_scores_gemma":[0.14376163,0.000032548123,0.8541095,0.001213579,0.00014358458,0.0002595812,0.0002826922,0.000026161793,0.00017071891],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99766684,0.00019100647,0.0004237203,0.0008035572,0.00039116637,0.0005236938],"domain_scores_gemma":[0.9977031,0.00048880896,0.000056397323,0.0003144479,0.0011451405,0.00029212277],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00047487256,0.00024205228,0.00026978127,0.00021215313,0.0003822616,0.00040417074,0.0003321978,0.00011613342,0.00008651931],"category_scores_gemma":[0.00014691803,0.00025977628,0.000097272925,0.00053732574,0.000113412905,0.0009646824,0.00034101598,0.00018747679,0.000013341124],"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":[0.000069196234,0.00026525964,0.00008761039,0.000039900413,0.00007680554,0.00005724126,0.00015478791,0.09052404,0.0003944515,0.0021096228,0.008781689,0.8974394],"study_design_scores_gemma":[0.00073546876,0.00018958744,0.00015580165,0.0000518024,0.0000136137505,0.00028837266,0.000056271445,0.9821827,0.012651069,0.00302096,0.00030098637,0.00035337132],"about_ca_topic_score_codex":0.000025407964,"about_ca_topic_score_gemma":0.0000069179227,"teacher_disagreement_score":0.897086,"about_ca_system_score_codex":0.00013782021,"about_ca_system_score_gemma":0.00024027494,"threshold_uncertainty_score":0.99998546},"labels":[],"label_agreement":null},{"id":"W3211361940","doi":"10.18280/ria.350504","title":"ETDR: An Exploratory View of Text Detection and Recognition in Images and Videos","year":2021,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Identification (biology); Information retrieval; Process (computing); Artificial intelligence; Focus (optics); Deep learning","score_opus":0.044916571861431824,"score_gpt":0.277149942805904,"score_spread":0.23223337094447216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3211361940","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":[0.34863973,0.0016243221,0.64849913,0.00023077868,0.00008994544,0.00022037096,0.000004938537,0.00012387644,0.0005669321],"genre_scores_gemma":[0.9830349,0.0018124,0.01492473,0.000101675,0.00002023952,0.00004169134,0.0000038104224,0.000009436978,0.000051107418],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99873966,0.00017574045,0.0003850877,0.000432069,0.00010346048,0.00016397047],"domain_scores_gemma":[0.99917144,0.00012968629,0.00009865347,0.00032965056,0.00019572405,0.00007485088],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005063997,0.00011507835,0.00019375318,0.00017582338,0.00006204061,0.000091706286,0.00015564135,0.000077077326,0.000045112785],"category_scores_gemma":[0.00013766422,0.00012747916,0.000029861398,0.00052053,0.00009030552,0.0007941313,0.0001305126,0.00014038362,0.000027143307],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004068301,0.000083475556,0.000118261785,0.00008363517,0.000002852308,0.00001713933,0.0012866949,0.000010006584,0.09144808,0.00030270583,0.00000827059,0.9066348],"study_design_scores_gemma":[0.000040547755,0.00013373604,0.00026199655,0.00022034919,0.000004609317,0.00008301674,0.0008586211,0.025586743,0.9569424,0.01540337,0.00030235085,0.0001622548],"about_ca_topic_score_codex":0.000027012838,"about_ca_topic_score_gemma":0.00012386862,"teacher_disagreement_score":0.90647256,"about_ca_system_score_codex":0.000020605621,"about_ca_system_score_gemma":0.000032651165,"threshold_uncertainty_score":0.5198449},"labels":[],"label_agreement":null},{"id":"W3214202479","doi":"10.1007/978-981-16-7069-5","title":"Cognitively Inspired Video Text Processing","year":2021,"lang":"en","type":"book","venue":"Cognitive intelligence and robotics","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","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":"University of Alberta","funders":"","keywords":"Computer science; Psychology","score_opus":0.03984596163690346,"score_gpt":0.28424097996649167,"score_spread":0.2443950183295882,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3214202479","genre_codex":"methods","genre_gemma":"other","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":[0.0000044930066,0.005238547,0.8412099,0.0002716942,0.0003106234,0.0005833299,0.000053070682,0.00049124117,0.15183713],"genre_scores_gemma":[0.027742153,0.01897492,0.22547235,0.009375843,0.0027232503,0.00042670366,0.0010525597,0.00048456085,0.7137477],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9964766,0.00014228161,0.0007802108,0.0013846844,0.00060742686,0.00060881674],"domain_scores_gemma":[0.9953114,0.00068655924,0.00048441335,0.00041266944,0.0028065138,0.0002984463],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003574205,0.000730804,0.0008188152,0.00044801834,0.00037880705,0.00078974344,0.00084183394,0.0006934774,0.00010627984],"category_scores_gemma":[0.0005332809,0.00074378663,0.00021770694,0.0004758841,0.0005963867,0.0007447419,0.000903087,0.0010406931,0.0003056619],"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":[0.0000098097835,0.00010539721,0.000011929423,0.0003123847,0.00010283214,0.0003390139,0.0006449688,0.000005785669,0.000020388105,0.008038675,0.003301254,0.9871076],"study_design_scores_gemma":[0.001769137,0.002929068,0.00038211074,0.05865854,0.0019755806,0.0022188956,0.0028855738,0.03896637,0.111500144,0.6461846,0.119528614,0.0130013665],"about_ca_topic_score_codex":0.0000044056073,"about_ca_topic_score_gemma":0.000008982653,"teacher_disagreement_score":0.9741062,"about_ca_system_score_codex":0.00013499918,"about_ca_system_score_gemma":0.001313459,"threshold_uncertainty_score":0.9995013},"labels":[],"label_agreement":null},{"id":"W3217430695","doi":"10.1142/9789811239014_0007","title":"Gender Detection from Handwritten Documents Using Transfer Learning Method","year":2021,"lang":"en","type":"book-chapter","venue":"Series on language processing, pattern recognition, and intelligent systems","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":5,"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":"Computer science; Transfer of learning; Transfer (computing); Artificial intelligence; Natural language processing; Speech recognition","score_opus":0.042310516388248585,"score_gpt":0.2810272819976789,"score_spread":0.2387167656094303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3217430695","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":[0.0020209283,0.009123338,0.9708169,0.000024650704,0.00074054225,0.0007035017,0.00017247158,0.0006788719,0.015718779],"genre_scores_gemma":[0.61307997,0.017117923,0.07579399,0.0036248618,0.006609345,0.001143677,0.0074232332,0.0015852312,0.27362177],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9961961,0.00029394982,0.00096940104,0.0013781507,0.000697363,0.00046505727],"domain_scores_gemma":[0.99816203,0.000113156115,0.00044913872,0.0004789164,0.00057780545,0.00021894941],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005095832,0.00078443123,0.000842285,0.00047559288,0.00046941068,0.0013320216,0.00044046505,0.00064160704,0.0005602898],"category_scores_gemma":[0.000036693353,0.00077816227,0.0002342394,0.00013354476,0.00009770392,0.0009866586,0.00014785465,0.0008695448,0.00014097402],"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":[0.000029806246,0.00004912876,0.000022205688,0.0008144305,0.00024689513,0.00014410159,0.0045326794,0.000012130677,0.0014572431,0.00014134972,0.000039902545,0.99251014],"study_design_scores_gemma":[0.0046611708,0.0037110099,0.00009219903,0.052367426,0.0027210175,0.00515153,0.021305252,0.0783939,0.5672018,0.041494243,0.206129,0.016771466],"about_ca_topic_score_codex":0.0005566388,"about_ca_topic_score_gemma":0.000109125,"teacher_disagreement_score":0.97573864,"about_ca_system_score_codex":0.0001836604,"about_ca_system_score_gemma":0.00011744145,"threshold_uncertainty_score":0.9997047},"labels":[],"label_agreement":null},{"id":"W373300525","doi":"","title":"Document analysis using image processing techniques.","year":2003,"lang":"en","type":"article","venue":"Scholarship at UWindsor (University of Windsor)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Image processing; Computer science; Computer vision; Artificial intelligence; Image (mathematics); Computer graphics (images)","score_opus":0.01941819093938934,"score_gpt":0.25326991231753604,"score_spread":0.2338517213781467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W373300525","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":[0.4108002,0.00011969751,0.5813229,0.00018656951,0.000049391616,0.00032751693,0.000009336101,0.0005719602,0.0066124024],"genre_scores_gemma":[0.63828754,0.000016280339,0.36109444,0.00007794105,0.000011416815,7.853199e-7,0.0000063044363,0.000014281688,0.00049099297],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9974973,0.00034347805,0.0003023371,0.0007296251,0.0006419588,0.00048528402],"domain_scores_gemma":[0.99804974,0.000055074175,0.00039250913,0.0008391491,0.00043234706,0.00023117664],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012831532,0.00027651113,0.00047944952,0.0011049727,0.00061571115,0.00018520276,0.0013153392,0.0002363779,0.00042375232],"category_scores_gemma":[0.0000863331,0.0003456151,0.00038555247,0.002810543,0.00021862314,0.0028551628,0.0004421685,0.00038485715,0.00005699523],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002483904,0.0016616903,0.1719067,0.0007363842,0.0028934365,0.0010148832,0.012818745,0.00011880193,0.55209005,0.028640341,0.0009865037,0.22688408],"study_design_scores_gemma":[0.0019368037,0.00035471166,0.03683841,0.00038193222,0.0014951805,0.00019058255,0.0013147567,0.0036937825,0.9205926,0.021484034,0.009452751,0.0022644273],"about_ca_topic_score_codex":0.0000574591,"about_ca_topic_score_gemma":0.00004472354,"teacher_disagreement_score":0.3685026,"about_ca_system_score_codex":0.00030201336,"about_ca_system_score_gemma":0.00018343942,"threshold_uncertainty_score":0.99989957},"labels":[],"label_agreement":null},{"id":"W39555859","doi":"10.1167/7.9.513","title":"","year":2010,"lang":"en","type":"article","venue":"Journal of Vision","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut Universitaire de Gériatrie de Montréal; University of Victoria; Université de Montréal","funders":"","keywords":"Identification (biology); Font; Sentence; Computer science; Word (group theory); Contrast (vision); Natural language processing; Artificial intelligence; Confusion; Speech recognition; Pattern recognition (psychology); Linguistics; Psychology","score_opus":0.010405395160339104,"score_gpt":0.2915403447364336,"score_spread":0.2811349495760945,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W39555859","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":[0.5362669,0.0000228527,0.45995343,0.0029150073,0.00062312477,0.000050022783,1.721157e-7,0.00007166003,0.00009683932],"genre_scores_gemma":[0.6692192,0.00002678529,0.3301939,0.00036565846,0.0001822004,8.2828126e-7,7.7735535e-8,0.0000048756256,0.000006458511],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998074,0.00009159301,0.00074238307,0.00017333662,0.0006933566,0.00022531161],"domain_scores_gemma":[0.99752027,0.00018809261,0.0007359652,0.0004526313,0.00085227046,0.00025075013],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019762688,0.00012793396,0.00026032966,0.00044852693,0.000120820536,0.00032831135,0.0016404872,0.00011516228,0.000014375056],"category_scores_gemma":[0.00036999502,0.000095371055,0.00020651142,0.00041465633,0.000050845774,0.0031421748,0.00022816645,0.00083660666,0.0000066162997],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016184116,0.0001569671,0.00065561867,0.000003916644,0.0000073861866,0.00010284183,0.00024791484,0.0000011119322,0.61976236,0.0033177675,0.00081815856,0.37490976],"study_design_scores_gemma":[0.0019507695,0.0035021328,0.14093584,0.00024304191,0.000017419447,0.0060950317,0.000047789144,0.004177745,0.7295398,0.10334402,0.009718976,0.00042744193],"about_ca_topic_score_codex":0.0000034885477,"about_ca_topic_score_gemma":0.000006587111,"teacher_disagreement_score":0.37448233,"about_ca_system_score_codex":0.000021035057,"about_ca_system_score_gemma":0.000099849305,"threshold_uncertainty_score":0.38891187},"labels":[],"label_agreement":null},{"id":"W4200356778","doi":"10.16995/dscn.8094","title":"Advances and Limitations in Open Source Arabic-Script OCR: A Case Study","year":2021,"lang":"en","type":"article","venue":"Digital Studies / Le champ numérique","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Endowment for the Humanities","keywords":"Typeface; Arabic; Open source; Humanities; Natural language processing; Artificial intelligence; Computer science; Linguistics; Art; Philosophy; Programming language; Software","score_opus":0.07025261429829413,"score_gpt":0.310846118016601,"score_spread":0.24059350371830687,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200356778","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":[0.8913772,0.0062214667,0.07155329,0.0026003025,0.00019612799,0.0013468434,0.000018160808,0.0004578011,0.026228819],"genre_scores_gemma":[0.99631774,0.0011189936,0.0010225751,0.00027032,0.000029070123,0.00039447565,0.000005052597,0.000016945865,0.0008247938],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9983631,0.0001390549,0.0003714867,0.00065856957,0.00017434263,0.00029348602],"domain_scores_gemma":[0.99866897,0.0004175177,0.00009713049,0.00041124836,0.0003118722,0.000093255236],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029634402,0.00022026068,0.00038237133,0.000121741934,0.00025573155,0.0008799527,0.000471314,0.000046774014,0.0000014870168],"category_scores_gemma":[0.0006098588,0.00021379348,0.000048939375,0.0006247026,0.000108980494,0.002591141,0.0016736283,0.00017696385,0.000009259869],"study_design_candidate":"qualitative","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":[0.00001235552,0.0014634317,0.010642311,0.00009850047,0.0001337609,0.0081049595,0.40433866,0.0000143535,0.00004154263,0.0004675681,0.00079354295,0.573889],"study_design_scores_gemma":[0.001007981,0.00032296253,0.0004488518,0.00010803009,3.0301672e-7,0.001967547,0.95137066,0.00025420394,0.0009360005,0.02412192,0.019002575,0.00045896223],"about_ca_topic_score_codex":0.00011949213,"about_ca_topic_score_gemma":0.0046849493,"teacher_disagreement_score":0.57343006,"about_ca_system_score_codex":0.00006227653,"about_ca_system_score_gemma":0.00010132392,"threshold_uncertainty_score":0.8718245},"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":"W4206503538","doi":"10.17762/de.v2021i3.7789","title":"Optical Character Recognition of Indian Language Manuscripts using Convolutional Neural Networks","year":2021,"lang":"en","type":"article","venue":"Design Engineering","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Sanskrit; Optical character recognition; Character (mathematics); Computer science; Scripting language; Convolutional neural network; Artificial intelligence; Focus (optics); Natural language processing; Character recognition; Writing system; Artificial neural network; Speech recognition; Image (mathematics); Linguistics; Mathematics; Programming language","score_opus":0.03335090864372424,"score_gpt":0.23308815863826726,"score_spread":0.199737249994543,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206503538","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":[0.097540215,0.00010524971,0.9017609,0.000037076716,0.00022111516,0.000089702684,0.0000031821637,0.00019522647,0.000047385638],"genre_scores_gemma":[0.7359097,0.000007154156,0.26386818,0.00007363662,0.00009224429,0.0000101355445,0.000019611927,0.000011509453,0.000007851517],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991205,0.000048722886,0.00022175034,0.0002169025,0.00016166746,0.00023048578],"domain_scores_gemma":[0.9994821,0.00009091535,0.000051872237,0.00019449473,0.000118438875,0.00006220955],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020136361,0.00011534289,0.00015106407,0.00012926193,0.000031582786,0.00006216428,0.00018407595,0.00008785848,0.000029711773],"category_scores_gemma":[0.000059718175,0.0001325622,0.00006103837,0.00030023,0.000016778018,0.00037318686,0.000063594656,0.00017160985,0.0000066795455],"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":[0.000021932165,0.00030152022,0.00023508513,0.00022172504,0.00015094847,0.0014129442,0.0013038495,0.10317677,0.6920728,0.004591681,0.0002608454,0.19624992],"study_design_scores_gemma":[0.00012434862,0.000021018348,0.00083688524,0.000067201836,0.000006247582,0.00019733868,0.0000075312287,0.7988115,0.1996614,0.000104932136,0.000013448994,0.00014812525],"about_ca_topic_score_codex":0.0000055798178,"about_ca_topic_score_gemma":4.0698603e-7,"teacher_disagreement_score":0.6956347,"about_ca_system_score_codex":0.000043166165,"about_ca_system_score_gemma":0.00003538229,"threshold_uncertainty_score":0.54057294},"labels":[],"label_agreement":null},{"id":"W4210353672","doi":"10.7717/peerj-cs.861","title":"Generative adversarial network based adaptive data augmentation for handwritten Arabic text recognition","year":2022,"lang":"en","type":"article","venue":"PeerJ Computer Science","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cambrian College","funders":"King Fahd University of Petroleum and Minerals","keywords":"Computer science; Artificial intelligence; Generative grammar; Arabic; Domain (mathematical analysis); Class (philosophy); Pattern recognition (psychology); Natural language processing; Machine learning; Speech recognition","score_opus":0.06651338339506535,"score_gpt":0.29177673246947916,"score_spread":0.2252633490744138,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210353672","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":[0.0011816267,0.00004036014,0.993127,0.0017441688,0.0019058278,0.0010939855,0.00020201915,0.0004989452,0.00020608355],"genre_scores_gemma":[0.14031433,0.0000030847357,0.8553906,0.0027120928,0.0006446063,0.00049143494,0.00037857523,0.000017446138,0.000047836922],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960083,0.0002805478,0.0004273855,0.0015146433,0.0011121503,0.00065697276],"domain_scores_gemma":[0.99739003,0.0003485466,0.00029041173,0.0012422295,0.0005511906,0.00017758396],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0029717102,0.00025275827,0.00026370076,0.0003684984,0.0018295593,0.00061298744,0.0039618663,0.000045327513,0.00007545162],"category_scores_gemma":[0.00008701237,0.00026983078,0.000090066125,0.0018243988,0.00026665203,0.002534024,0.00235208,0.00025701773,0.000030326384],"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":[0.00013327008,0.0002962555,0.000063027765,0.000017253547,0.000036209654,0.000017597196,0.00086622144,0.013096379,0.0019730711,0.00534327,0.04549721,0.9326602],"study_design_scores_gemma":[0.0010283616,0.0007215282,0.00024309871,0.000022070779,0.000017197153,0.000024464292,0.000029889874,0.9744828,0.0053311368,0.013685856,0.0040116566,0.0004019679],"about_ca_topic_score_codex":0.00003745611,"about_ca_topic_score_gemma":0.000013380868,"teacher_disagreement_score":0.9613864,"about_ca_system_score_codex":0.00031674432,"about_ca_system_score_gemma":0.00069019396,"threshold_uncertainty_score":0.9999754},"labels":[],"label_agreement":null},{"id":"W4210988543","doi":"10.1007/978-0-85729-859-1_30","title":"Online Signature Verification","year":2014,"lang":"en","type":"book-chapter","venue":"CINECA IRIS Institutional Research Information System (University of Bari Aldo Moro)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Signature (topology); Computer science; Principal (computer security); Identity (music); Data science; The Internet; Computer security; World Wide Web; Mathematics; Physics","score_opus":0.04982871208300459,"score_gpt":0.26829064992596197,"score_spread":0.21846193784295737,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210988543","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":[0.0000784507,0.00011142152,0.61194986,0.00069564086,0.00020125795,0.0006521801,0.00031601737,0.0003598181,0.38563532],"genre_scores_gemma":[0.7096793,0.0009811438,0.12648149,0.00051359663,0.000728267,0.000021056243,0.0063401554,0.00007818509,0.15517683],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964163,0.0001394483,0.0006279863,0.000421287,0.0020486119,0.00034641245],"domain_scores_gemma":[0.9946641,0.00018681535,0.0006545906,0.00096121145,0.0032917978,0.00024154111],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0017883178,0.00029795547,0.0005026732,0.0017732187,0.0007289844,0.00014250181,0.0017234056,0.0006838574,0.0002520438],"category_scores_gemma":[0.00014910886,0.00035086813,0.00023332081,0.00037722266,0.00053660077,0.0023352217,0.0006150034,0.0010109035,0.0011963205],"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":[0.000030304973,0.000021099344,0.0000017876256,0.00052613986,0.00005458083,0.000019737725,0.0003528485,0.0000685143,0.000045092816,0.9364107,0.025194783,0.03727441],"study_design_scores_gemma":[0.0008451168,0.00019952409,0.00031710626,0.0015097272,0.00002872497,0.00011629565,0.00050027465,0.017330492,0.00013907495,0.0033847773,0.9751065,0.00052241865],"about_ca_topic_score_codex":0.00012724081,"about_ca_topic_score_gemma":0.00001750387,"teacher_disagreement_score":0.9499117,"about_ca_system_score_codex":0.0008670015,"about_ca_system_score_gemma":0.0009896216,"threshold_uncertainty_score":0.9998943},"labels":[],"label_agreement":null},{"id":"W4229455692","doi":"10.18280/ts.390218","title":"A Hybrid System for Handwritten Character Recognition with High Robustness","year":2022,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Bundesinstitut für Bau- Stadt- und Raumforschung","keywords":"Computer science; Pattern recognition (psychology); Artificial intelligence; Character (mathematics); Numeral system; Robustness (evolution); Speech recognition; Benchmark (surveying); Bengali; Feature (linguistics); Feature extraction; Support vector machine; Mathematics","score_opus":0.017640627957609647,"score_gpt":0.21307073358620487,"score_spread":0.19543010562859522,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4229455692","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":[0.1513216,0.000015334575,0.84538794,0.0006922016,0.00020817215,0.0011809361,0.0001993494,0.0007810539,0.00021343345],"genre_scores_gemma":[0.94812304,0.000001833202,0.047713622,0.00048797514,0.00019348682,0.0030785676,0.00026163776,0.000031301064,0.00010853351],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9979934,0.00015212444,0.0003679049,0.0005519802,0.00054342236,0.0003911575],"domain_scores_gemma":[0.99909246,0.00009632903,0.00020443897,0.00029509058,0.00020751273,0.00010419733],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067963643,0.00022336165,0.0002618481,0.00022503237,0.00047767177,0.00020615844,0.0006472221,0.00002881483,0.00036147656],"category_scores_gemma":[0.000004795212,0.00020621646,0.00010111457,0.00025008293,0.000032555014,0.000529581,0.00017201791,0.00017401448,0.000019438716],"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":[0.0015665359,0.0023429892,0.00032652973,0.0011338888,0.00066240004,0.00063032156,0.0017379189,0.0020738067,0.023665465,0.024121761,0.024408579,0.9173298],"study_design_scores_gemma":[0.021515185,0.012468202,0.002038371,0.0009986396,0.0004878517,0.0032831558,0.001353467,0.35899684,0.5346113,0.008748249,0.050714426,0.0047843354],"about_ca_topic_score_codex":0.000018457975,"about_ca_topic_score_gemma":0.0000018887729,"teacher_disagreement_score":0.91254544,"about_ca_system_score_codex":0.00021134874,"about_ca_system_score_gemma":0.00007912885,"threshold_uncertainty_score":0.8409263},"labels":[],"label_agreement":null},{"id":"W4235009179","doi":"10.1002/9780470176535.index","title":"Index","year":2007,"lang":"en","type":"paratext","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; École de Technologie Supérieure; Université du Québec à Montréal","funders":"","keywords":"Beijing; Chinese academy of sciences; Library science; Index (typography); China; Citation; History; Computer science; Archaeology; World Wide Web","score_opus":0.02035919828287254,"score_gpt":0.2899571145881347,"score_spread":0.2695979163052622,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4235009179","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[7.108238e-7,0.00013693862,0.51033014,0.00010154038,0.0007483361,0.00010302061,0.000003084734,0.0003396181,0.4882366],"genre_scores_gemma":[0.00086808536,0.00025729876,0.11199274,0.002696711,0.0004069264,0.000036524973,0.00004612587,0.000028590232,0.883667],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984733,0.000034740147,0.00029430803,0.000499657,0.000357851,0.0003401524],"domain_scores_gemma":[0.9987803,0.00006908909,0.00012029827,0.0007599354,0.00015544487,0.00011491643],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0002843883,0.00024279693,0.00026735658,0.00045205947,0.00005449836,0.00023066344,0.0014984248,0.00046956906,0.008217002],"category_scores_gemma":[0.000012465239,0.0002177248,0.00011607845,0.00041801325,0.000036206417,0.00025889548,0.00039481034,0.00044008697,0.063292086],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.4472196e-7,0.000014890588,0.0000010623254,0.000013486107,0.00000826751,0.000008691609,0.00001129332,1.3452569e-7,0.000009796858,0.0027056278,0.8556535,0.14157277],"study_design_scores_gemma":[0.0000725214,0.00003456231,0.000010558339,0.000050005092,0.0000019045451,0.000023870463,0.0000017204742,0.0002818604,0.008867097,0.0019664406,0.9883461,0.00034336484],"about_ca_topic_score_codex":0.000051879513,"about_ca_topic_score_gemma":0.000008254769,"teacher_disagreement_score":0.3983374,"about_ca_system_score_codex":0.000061848536,"about_ca_system_score_gemma":0.00013620402,"threshold_uncertainty_score":0.9926896},"labels":[],"label_agreement":null},{"id":"W4239257072","doi":"10.1109/icdar.2019.00004","title":"Table of Contents","year":2019,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Informatics; National Laboratory of Pattern Recognition; Aston University; Baidu; Université de Montréal; University of Chinese Academy of Sciences; Chinese Academy of Sciences","keywords":"Table (database); Computer science; Database","score_opus":0.01690827792960963,"score_gpt":0.2428886422873695,"score_spread":0.22598036435775987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4239257072","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":[0.044344675,0.000019549481,0.73499554,0.0001999455,0.00012525836,0.00016864079,0.0000010438116,0.00030380953,0.21984151],"genre_scores_gemma":[0.93392724,0.0000034863315,0.060152058,0.00024058389,0.0000033071374,0.0000034989164,4.3258768e-7,0.0000019261718,0.005667452],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99962246,0.000009854851,0.000092887545,0.00010201359,0.00009712412,0.00007568491],"domain_scores_gemma":[0.9996148,0.00001987253,0.0000317249,0.00023803672,0.000074969386,0.000020613938],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000073413015,0.00003259325,0.000072485134,0.000040438434,0.0000064725737,0.000016249336,0.00031099623,0.000019689242,0.00038703278],"category_scores_gemma":[0.00000776314,0.00002692176,0.00002032503,0.00012872402,0.000008046499,0.00023677365,0.00008428333,0.000024618943,0.0003772632],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006056461,0.0002177825,0.0237035,0.00006615975,0.000032287015,0.0000041688872,0.00023683792,0.0000014883008,0.18782438,0.5725957,0.025631262,0.18968038],"study_design_scores_gemma":[0.0002696027,0.00011467448,0.0019442996,0.000023520344,0.0000010218874,0.000005056144,0.000014341617,0.0031292061,0.9738383,0.0099794315,0.0105774,0.00010309668],"about_ca_topic_score_codex":0.000029656232,"about_ca_topic_score_gemma":0.00000110912,"teacher_disagreement_score":0.8895826,"about_ca_system_score_codex":0.000003404703,"about_ca_system_score_gemma":0.000010080176,"threshold_uncertainty_score":0.4849081},"labels":[],"label_agreement":null},{"id":"W4246412339","doi":"10.1007/bf02683995","title":"Feature dimensionality reduction for the verification of handwritten numerals","year":2004,"lang":"en","type":"article","venue":"Pattern Analysis and Applications","topic":"Handwritten Text Recognition Techniques","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":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Pattern recognition (psychology); Artificial intelligence; Dimensionality reduction; Computer science; Linear discriminant analysis; Feature extraction; Principal component analysis; Classifier (UML); Curse of dimensionality; Discriminant; Artificial neural network","score_opus":0.015898302070796747,"score_gpt":0.2761278753260146,"score_spread":0.2602295732552179,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4246412339","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":[0.003058822,0.00017789277,0.98782086,0.008389909,0.000010956371,0.00042029683,0.00002794319,0.000055862492,0.00003747069],"genre_scores_gemma":[0.9779797,0.00012839737,0.020945627,0.0001395474,0.000045870813,0.0006380694,0.000056204623,0.0000038036271,0.00006277806],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993561,0.000020849619,0.00016314437,0.0002550841,0.000121530094,0.00008332966],"domain_scores_gemma":[0.99914443,0.000065343,0.00014143653,0.00044137886,0.00017438894,0.000033023956],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024365527,0.000072109935,0.00013633422,0.000104350496,0.00022530518,0.000059031907,0.0002471161,0.00004119085,0.00000516431],"category_scores_gemma":[0.000007713475,0.000052471507,0.00012235394,0.0006758588,0.00005393073,0.000117836455,0.000039630948,0.000051671974,0.000002981738],"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":[0.000005486295,0.00025019323,0.001777284,0.000047412403,0.0006820756,1.0666234e-7,0.00036487047,0.00025057988,0.030892689,0.076319866,0.0007700649,0.8886394],"study_design_scores_gemma":[0.0016882187,0.00018221326,0.18006907,0.000075988275,0.0029878085,0.000031816864,0.00043949025,0.031301547,0.5536984,0.18346389,0.04510172,0.00095980027],"about_ca_topic_score_codex":0.00010739252,"about_ca_topic_score_gemma":0.000023063714,"teacher_disagreement_score":0.97492087,"about_ca_system_score_codex":0.000016166889,"about_ca_system_score_gemma":0.000015841042,"threshold_uncertainty_score":0.2139726},"labels":[],"label_agreement":null},{"id":"W4246775156","doi":"10.31227/osf.io/zdtkr","title":"Model Vancouover, Easy For Making Manuscript","year":2019,"lang":"id","type":"preprint","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Humanities; Philosophy","score_opus":0.07136667630312199,"score_gpt":0.3075424548832839,"score_spread":0.23617577858016192,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4246775156","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":[0.00009513313,0.0002322939,0.8752486,0.0005754622,0.0030948862,0.0030841865,0.00011473149,0.0012593522,0.11629533],"genre_scores_gemma":[0.0894106,0.00026428758,0.7695228,0.003686311,0.0003957013,0.0008451657,0.00006846319,0.00013080704,0.13567589],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99456125,0.00012327728,0.0011057121,0.0022956314,0.0008161232,0.0010979732],"domain_scores_gemma":[0.9954273,0.00026952891,0.0006822338,0.0025348186,0.0008760004,0.00021007954],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010902812,0.0009116364,0.0010492216,0.00046279895,0.00024769356,0.0010925607,0.0033564693,0.0009438504,0.00029153368],"category_scores_gemma":[0.00012988805,0.00094675267,0.00084366207,0.00025873503,0.00009741062,0.0008364667,0.0035251104,0.0009707063,0.0010341045],"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":[0.00016940427,0.0009309145,0.00018723114,0.0046718,0.0005333197,0.00003505255,0.0014943718,0.009648311,0.0021711474,0.22107065,0.2871175,0.47197032],"study_design_scores_gemma":[0.0005640212,0.00015516732,0.000022322463,0.0008028365,0.000063927044,0.000017165223,0.000021676091,0.83697873,0.006927635,0.11401633,0.039284494,0.0011457038],"about_ca_topic_score_codex":0.000039121263,"about_ca_topic_score_gemma":0.00004643635,"teacher_disagreement_score":0.8273304,"about_ca_system_score_codex":0.00036364995,"about_ca_system_score_gemma":0.0006879662,"threshold_uncertainty_score":0.9999444},"labels":[],"label_agreement":null},{"id":"W4247646242","doi":"10.1145/3495018.3501199","title":"Handwritten character recognition based on CNN","year":2021,"lang":"en","type":"article","venue":"2021 3rd International Conference on Artificial Intelligence and Advanced Manufacture","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Character recognition; Computer science; Character (mathematics); Artificial intelligence; Speech recognition; Pattern recognition (psychology); Feature extraction; Intelligent word recognition; Natural language processing; Intelligent character recognition; Mathematics; Image (mathematics)","score_opus":0.06041791743990403,"score_gpt":0.3071205096829152,"score_spread":0.24670259224301117,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4247646242","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":[0.012204145,0.00004317834,0.92912793,0.0284566,0.0016578936,0.00041708775,0.00011829422,0.00033874263,0.027636142],"genre_scores_gemma":[0.9694515,0.00040652277,0.022198543,0.0064175627,0.00028179493,0.00009096026,0.00025130375,0.000021145943,0.0008806694],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99779564,0.00009998653,0.00042470585,0.0008431945,0.00052547205,0.0003109911],"domain_scores_gemma":[0.99850905,0.00015784714,0.00016340506,0.00044543878,0.0005727933,0.00015147764],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00018472211,0.0003058191,0.00025328086,0.00025461742,0.0001741684,0.0005592623,0.0005518089,0.00015989448,0.0027857367],"category_scores_gemma":[0.00018610069,0.00029036315,0.000115655785,0.00023717448,0.00008428484,0.0006388138,0.00013296993,0.0004567889,0.0006226587],"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":[0.00007979281,0.00022064574,0.0000068425757,0.000009711527,0.000019961051,0.00009140643,0.0001089345,0.00007659608,0.01333479,0.075217865,0.00017552573,0.91065794],"study_design_scores_gemma":[0.00011810673,0.0002829277,0.00012919054,0.000309164,0.000008204922,0.000019287994,0.00020922857,0.048900496,0.77037764,0.17170882,0.0074667423,0.00047020082],"about_ca_topic_score_codex":0.0000054798465,"about_ca_topic_score_gemma":0.000022651338,"teacher_disagreement_score":0.9572474,"about_ca_system_score_codex":0.00006855266,"about_ca_system_score_gemma":0.00011619031,"threshold_uncertainty_score":0.9999549},"labels":[],"label_agreement":null},{"id":"W4249709004","doi":"10.1109/icdar.2013.5","title":"Welcome from the Executive Chairs","year":2013,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Executive summary; Business; Finance","score_opus":0.015658270100521836,"score_gpt":0.23259325819784749,"score_spread":0.21693498809732564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4249709004","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":[0.006776101,0.00004551193,0.88644385,0.013159183,0.00022560211,0.00034579088,0.0000025892616,0.0009434055,0.092057966],"genre_scores_gemma":[0.8846353,0.00002068699,0.10604727,0.0058152108,0.00014722711,0.00016268725,0.0000032991225,0.000007997818,0.0031603053],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.999321,0.000049562488,0.000113890295,0.00020824022,0.00015068184,0.00015666094],"domain_scores_gemma":[0.99919564,0.00018057575,0.00003291425,0.00046188428,0.00007788603,0.000051079372],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000094409195,0.0000793516,0.000074624266,0.00002570921,0.000086874454,0.00021476179,0.0008930682,0.000036727353,0.0009780019],"category_scores_gemma":[0.000023257922,0.000046037207,0.0000430663,0.00016498796,0.000042444575,0.000491839,0.00023650331,0.00009399752,0.0023254748],"study_design_candidate":"theoretical_or_conceptual","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":[9.0928677e-7,0.00006251421,0.001135343,0.0000015799598,0.000033022727,0.0000052504583,0.0014929237,2.3562963e-7,0.0020316616,0.1256758,0.43879494,0.4307658],"study_design_scores_gemma":[0.00050898385,0.00015481982,0.054942667,0.0000520242,0.00000834032,0.000019871635,0.00064091734,0.014855995,0.15420197,0.67039734,0.103474356,0.00074272737],"about_ca_topic_score_codex":0.0010543495,"about_ca_topic_score_gemma":0.000020144294,"teacher_disagreement_score":0.87785923,"about_ca_system_score_codex":0.000014088793,"about_ca_system_score_gemma":0.000014857937,"threshold_uncertainty_score":0.9999352},"labels":[],"label_agreement":null},{"id":"W4253789545","doi":"10.1017/s002555720017874x","title":"Advanced maths: AS core for OCR","year":2005,"lang":"en","type":"article","venue":"The Mathematical Gazette","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Saint Paul University","funders":"","keywords":"Mathematics; Core (optical fiber); Engineering; Telecommunications","score_opus":0.028110734641827857,"score_gpt":0.3036201623144602,"score_spread":0.27550942767263237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4253789545","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":[0.0069869375,0.00005012341,0.9568245,0.012708767,0.000054034812,0.00073764334,0.0000041428316,0.00071487646,0.021918995],"genre_scores_gemma":[0.16969903,0.000015956444,0.81831425,0.006518693,0.00022582781,0.0005305779,0.0000030247022,0.000035593224,0.004657023],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99881834,0.000031323467,0.00029877582,0.0002607417,0.0002626723,0.00032813236],"domain_scores_gemma":[0.99853957,0.0005069977,0.00008568437,0.00069216994,0.000086776454,0.00008878654],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005115843,0.00015528013,0.0002059319,0.000046700963,0.0001398874,0.00011916619,0.0010338802,0.00006048142,0.00019524635],"category_scores_gemma":[0.0002531793,0.00010022465,0.000121686935,0.0001675731,0.000085913256,0.0002726876,0.00018552742,0.00013508587,0.0016180164],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009170423,0.000101928585,6.824324e-7,0.0000496625,0.000015218095,0.000002607191,0.0006260592,0.0000035994483,0.0018113521,0.7669021,0.0098670125,0.2206106],"study_design_scores_gemma":[0.00034053804,0.000115394854,0.000010508817,0.00007712498,0.00001465809,0.00008377068,0.000029557292,0.028412392,0.031180281,0.8971604,0.04235707,0.00021826568],"about_ca_topic_score_codex":5.0170235e-7,"about_ca_topic_score_gemma":6.8317803e-7,"teacher_disagreement_score":0.22039235,"about_ca_system_score_codex":0.000031590032,"about_ca_system_score_gemma":0.000024863899,"threshold_uncertainty_score":0.99915934},"labels":[],"label_agreement":null},{"id":"W4256140860","doi":"10.1109/icosc.2007.4338404","title":"Robust Invariant Descriptor for Symbol-Based Image Recognition and Retrieval","year":2007,"lang":"en","type":"article","venue":"International Conference on Semantic Computing (ICSC 2007)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Artificial intelligence; Invariant (physics); Pattern recognition (psychology); Computer vision; Computer science; Image retrieval; Symbol (formal); Mathematics; Image (mathematics)","score_opus":0.09667433081708071,"score_gpt":0.30324328585353366,"score_spread":0.20656895503645295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4256140860","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":[0.046703376,0.000013558588,0.9463049,0.0015117711,0.00095093827,0.00046679098,0.00003190226,0.00040231962,0.0036144033],"genre_scores_gemma":[0.77925044,0.000011443894,0.21921477,0.001046598,0.00028251373,0.000007515731,0.0000662671,0.000020597678,0.00009986552],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99778664,0.000065806504,0.0005647434,0.00065541005,0.0005114508,0.00041595002],"domain_scores_gemma":[0.9976741,0.00056471874,0.0002825474,0.00030764617,0.0010128496,0.00015811018],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0016295403,0.0002576806,0.00025306473,0.00043118896,0.00019468665,0.0005565382,0.00073360215,0.00013533476,0.00011320138],"category_scores_gemma":[0.0004566558,0.0002695817,0.00010049706,0.00023298357,0.000104027094,0.0003752246,0.00017822118,0.00027173536,0.000070415095],"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":[0.0013360874,0.0016431375,0.0020561367,0.00045164695,0.00040581435,0.00044088034,0.0021458035,0.00012800428,0.09935491,0.24817006,0.009563301,0.6343042],"study_design_scores_gemma":[0.0027778065,0.0007559652,0.0032965199,0.0011354266,0.00003967928,0.00015143429,0.00020144429,0.81722,0.11970508,0.052561615,0.0010906227,0.0010644213],"about_ca_topic_score_codex":0.00003400894,"about_ca_topic_score_gemma":0.000012234151,"teacher_disagreement_score":0.817092,"about_ca_system_score_codex":0.00012832345,"about_ca_system_score_gemma":0.00013714175,"threshold_uncertainty_score":0.9999756},"labels":[],"label_agreement":null},{"id":"W4280578488","doi":"10.18280/ria.360219","title":"Hand-Written Text Recognition Methods: Review Study","year":2022,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Process (computing); Software; Text recognition; Natural language processing; Artificial intelligence; Programming language","score_opus":0.08111015767341702,"score_gpt":0.35045165431221176,"score_spread":0.26934149663879475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4280578488","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":[0.0012216384,0.00472935,0.9822578,0.0023043926,0.0004970024,0.0017242267,0.00001391838,0.0006511564,0.0066005313],"genre_scores_gemma":[0.6126434,0.004392534,0.36262825,0.009084691,0.0002901685,0.0051433695,0.00010074,0.00013061301,0.0055862367],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9961863,0.0011658499,0.00085272134,0.00088719744,0.0004600195,0.00044787434],"domain_scores_gemma":[0.9977521,0.00036505732,0.0002823239,0.001207438,0.00025401887,0.00013910803],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.003557504,0.0002592211,0.00042801432,0.0002854216,0.0008060287,0.00020689864,0.0016411379,0.000045564055,0.0024793583],"category_scores_gemma":[0.00033558637,0.0002766604,0.0001992548,0.0017239081,0.00007605551,0.00047290197,0.00092429394,0.0005173255,0.0010676903],"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":[0.0000060586003,0.0006860331,0.00003695389,0.00013662258,0.000024362342,0.000048626756,0.001364349,0.00007387585,0.0014217461,0.0009919793,0.0049577956,0.9902516],"study_design_scores_gemma":[0.0003973119,0.0043514683,0.00008762533,0.0017015823,0.00024344097,0.0011332054,0.008375319,0.1678836,0.39590457,0.103358515,0.31362832,0.0029350442],"about_ca_topic_score_codex":0.000050964263,"about_ca_topic_score_gemma":0.000006195107,"teacher_disagreement_score":0.98731655,"about_ca_system_score_codex":0.00013807842,"about_ca_system_score_gemma":0.00006781547,"threshold_uncertainty_score":0.9999685},"labels":[],"label_agreement":null},{"id":"W4281671095","doi":"10.21203/rs.3.rs-1717367/v1","title":"Refocus attention span networks for handwriting line recognition","year":2022,"lang":"en","type":"preprint","venue":"Research Square","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Handwriting; Transformer; Speech recognition; Artificial intelligence; Encoder; Robustness (evolution); Lexicon; Benchmark (surveying); Natural language processing; Pattern recognition (psychology)","score_opus":0.11089152384804617,"score_gpt":0.3995111500210831,"score_spread":0.28861962617303694,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281671095","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":[0.0035777257,0.000883474,0.9851294,0.0017688579,0.0006845334,0.0036546695,0.00026716047,0.0012415802,0.0027925628],"genre_scores_gemma":[0.7280855,0.0030528244,0.23644502,0.00032867142,0.0035745248,0.01843012,0.0065112803,0.0002833576,0.0032886881],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99392,0.001219941,0.0007186517,0.001510203,0.0015085944,0.0011226018],"domain_scores_gemma":[0.99533236,0.0008979715,0.00030480753,0.0013874036,0.001822194,0.00025525404],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0065900786,0.00037033233,0.00047900894,0.0010745465,0.0010449217,0.0010358671,0.0019882752,0.00051277614,0.00031763743],"category_scores_gemma":[0.00084566395,0.0004095926,0.00042969492,0.0010225382,0.00011388022,0.00044557443,0.0045414777,0.0029090557,0.00006381642],"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":[0.000073468,0.0003025203,0.00019279572,0.0012301069,0.00007633332,0.000060771585,0.00021483902,0.00031307506,0.0002818271,0.0020050523,0.008804514,0.9864447],"study_design_scores_gemma":[0.002692815,0.0034752917,0.0014385805,0.006618608,0.00008343122,0.00009070577,0.00097371335,0.56528586,0.010156049,0.3497178,0.05654592,0.0029212094],"about_ca_topic_score_codex":0.0001674414,"about_ca_topic_score_gemma":0.000043860466,"teacher_disagreement_score":0.9835235,"about_ca_system_score_codex":0.00067336374,"about_ca_system_score_gemma":0.00036666606,"threshold_uncertainty_score":0.9998356},"labels":[],"label_agreement":null},{"id":"W4283790221","doi":"10.1609/aaai.v36i10.21369","title":"Post-OCR Document Correction with Large Ensembles of Character Sequence-to-Sequence Models","year":2022,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Dalhousie University; Consejo de Investigación, Universidad Nacional de Salta; Consejo Nacional de Investigaciones Científicas y Técnicas; Compute Canada","keywords":"Sequence (biology); Computer science; Optical character recognition; Character (mathematics); Artificial intelligence; Code (set theory); Natural language processing; Task (project management); Process (computing); Pattern recognition (psychology); Speech recognition; Image (mathematics); Mathematics; Programming language","score_opus":0.07268029614619377,"score_gpt":0.29639702582878513,"score_spread":0.22371672968259138,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283790221","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":[0.7295202,0.000018249997,0.24765904,0.01017467,0.0010978379,0.0024297251,0.00012870146,0.00050844805,0.008463114],"genre_scores_gemma":[0.9914952,0.000022145075,0.007042742,0.00088333676,0.000027910617,0.00024810043,0.0000025741624,0.000017852793,0.00026014395],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9972713,0.000051136853,0.00065123435,0.0006342041,0.00096520234,0.00042692557],"domain_scores_gemma":[0.9974739,0.00008510643,0.00059721945,0.0004060964,0.0013240328,0.000113645714],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00082820735,0.0002664317,0.00034197516,0.00031264787,0.00035337554,0.00016507416,0.0021805274,0.00005974948,0.00015536493],"category_scores_gemma":[0.00014597642,0.00020824069,0.00011639519,0.001081813,0.00017680948,0.0008207054,0.0007987957,0.00042121945,0.00002482264],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023758458,0.0003363712,0.00008354571,0.000048880254,0.000026101607,0.0000023817522,0.0039969846,0.00026642779,0.31163204,0.60317075,0.00022522948,0.079973705],"study_design_scores_gemma":[0.000042047523,0.0011258704,0.000055438326,0.00024255415,0.000013707657,0.000035588797,0.0012813882,0.037465245,0.85989004,0.09938884,0.00016069114,0.00029858237],"about_ca_topic_score_codex":0.00014281884,"about_ca_topic_score_gemma":0.000020070722,"teacher_disagreement_score":0.548258,"about_ca_system_score_codex":0.00014993286,"about_ca_system_score_gemma":0.00017872325,"threshold_uncertainty_score":0.8491809},"labels":[],"label_agreement":null},{"id":"W4285113967","doi":"10.1007/978-3-031-09037-0_25","title":"Using Convolutional Neural Network to Handle Word Shape Similarities in Handwritten Cursive Arabic Scripts of Pashto Language","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Handwritten Text Recognition Techniques","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":"Concordia University","funders":"","keywords":"Cursive; Computer science; Artificial intelligence; Scripting language; Convolutional neural network; Word (group theory); Natural language processing; Speech recognition; Set (abstract data type); Class (philosophy); Pattern recognition (psychology); Mathematics","score_opus":0.03087748646269007,"score_gpt":0.27256729797719026,"score_spread":0.2416898115145002,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285113967","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":[0.0044206074,0.0013101583,0.9904845,0.0007004907,0.0013114548,0.0007765067,0.000047509136,0.00018188212,0.00076693716],"genre_scores_gemma":[0.39262393,0.000057053017,0.6012641,0.0050024255,0.0006618272,0.000070442344,0.000034566136,0.000072174036,0.00021344032],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99561906,0.00011881029,0.000795639,0.0013923314,0.0012103232,0.000863843],"domain_scores_gemma":[0.99778265,0.00046314317,0.0003533545,0.0009084424,0.00030369492,0.00018874453],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001039631,0.0005354933,0.0007794257,0.0014127743,0.00029117783,0.00029764167,0.0028185262,0.0002572024,0.00018479368],"category_scores_gemma":[0.000121774436,0.000566916,0.00017461319,0.0014033671,0.0006030455,0.0007711895,0.00216396,0.0010238024,0.000007912383],"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":[0.0000752475,0.00017556058,0.0011703509,0.00019343944,0.00004603342,0.0006443601,0.0067805746,0.19817975,0.0019905262,0.018395673,0.00047693483,0.77187157],"study_design_scores_gemma":[0.00070646545,0.0005358473,0.0009837501,0.0016389554,0.000021115513,0.00021675939,0.0000066991206,0.8807455,0.0038900513,0.10788403,0.0018236531,0.0015472203],"about_ca_topic_score_codex":0.00017081515,"about_ca_topic_score_gemma":0.00034145304,"teacher_disagreement_score":0.77032435,"about_ca_system_score_codex":0.00054976007,"about_ca_system_score_gemma":0.00057771645,"threshold_uncertainty_score":0.99967825},"labels":[],"label_agreement":null},{"id":"W4285185775","doi":"10.2139/ssrn.4113859","title":"Handwriting Word Spotting in the Space of Difference between Representations Using Vision Transformers","year":2022,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","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":"École de Technologie Supérieure","funders":"","keywords":"Spotting; Handwriting; Transformer; Speech recognition; Computer science; Artificial intelligence; Natural language processing; Engineering; Electrical engineering; Voltage","score_opus":0.020249917411994316,"score_gpt":0.2960863946074617,"score_spread":0.2758364771954674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285185775","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":[0.49042994,0.00025500526,0.50793886,0.00092006515,0.00004030126,0.00014029579,0.0000017241673,0.000029759773,0.00024404911],"genre_scores_gemma":[0.9946862,0.00018687332,0.004967444,0.00004431061,0.00005607814,0.000012466785,0.0000018373084,0.000008822288,0.000036007044],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9974223,0.0004467928,0.00041617974,0.00020990975,0.00051414955,0.0009907022],"domain_scores_gemma":[0.99922556,0.00025394914,0.000243235,0.00018792758,0.00005699397,0.000032323333],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036547773,0.00010554152,0.00016908172,0.00029029005,0.00055314467,0.000098807555,0.0008829485,0.000027698514,0.000010618538],"category_scores_gemma":[0.00005841218,0.000089215406,0.00010158563,0.0008717796,0.000040046016,0.0003695236,0.00011903873,0.0016824539,5.6995526e-7],"study_design_candidate":"theoretical_or_conceptual","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":[0.000024008266,0.00018086513,0.023229718,0.000020123123,0.00007141041,0.000021334281,0.006804333,0.0003449264,0.015461616,0.07141853,0.000025547006,0.8823976],"study_design_scores_gemma":[0.002539504,0.0015844817,0.03220299,0.0003478085,0.000101264915,0.0028775304,0.048725888,0.02931548,0.018205471,0.8627745,0.00040215644,0.00092294265],"about_ca_topic_score_codex":0.00015312863,"about_ca_topic_score_gemma":0.000111951864,"teacher_disagreement_score":0.8814747,"about_ca_system_score_codex":0.00043739396,"about_ca_system_score_gemma":0.00067304366,"threshold_uncertainty_score":0.73095185},"labels":[],"label_agreement":null},{"id":"W4285194696","doi":"10.1007/978-981-19-1559-8_42","title":"Novel Approach for Character Recognition Using Chi-Square","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"Handwritten Text Recognition Techniques","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":"University of Windsor","funders":"","keywords":"Devanagari; Shadow (psychology); Optical character recognition; Character (mathematics); Computer science; Artificial intelligence; Diagonal; Key (lock); Set (abstract data type); Pattern recognition (psychology); Feature (linguistics); Benchmark (surveying); Typeface; Intelligent word recognition; Font; Feature extraction; License; Intelligent character recognition; Document processing; Test set; Character recognition; Image (mathematics); Geography; Mathematics; Linguistics; Cartography; Geometry","score_opus":0.04913529121293274,"score_gpt":0.2506793279646557,"score_spread":0.20154403675172294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285194696","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":[0.000016771297,0.0024158668,0.9878793,0.00003918774,0.0008209999,0.0016479687,0.00010162968,0.00020735664,0.006870972],"genre_scores_gemma":[0.22215864,0.0030242729,0.7426671,0.0032395513,0.011535522,0.0036773311,0.005536244,0.00088369864,0.007277674],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99784917,0.00006136928,0.0005789201,0.0008441157,0.00028304948,0.00038337658],"domain_scores_gemma":[0.9986579,0.0002791521,0.00040506985,0.00044904262,0.0001273782,0.000081475686],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00059938745,0.0004453829,0.0006550402,0.00032782208,0.00022006636,0.0003215031,0.00042260805,0.0006367469,0.000030686097],"category_scores_gemma":[0.000030514331,0.00042661285,0.00016816663,0.00012293889,0.00004387794,0.0002365145,0.0002147843,0.0007674188,0.0000011117114],"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":[0.0001095853,0.0001967134,0.00008042096,0.001967748,0.00032531776,0.0000498789,0.00089153723,0.03343526,0.00025005374,0.039545607,0.00054459536,0.9226033],"study_design_scores_gemma":[0.00050564023,0.00016327469,0.00000770224,0.0008201032,0.000047490306,0.00029409942,0.0000038084515,0.96901786,0.000025129266,0.007019376,0.021242483,0.00085305027],"about_ca_topic_score_codex":0.000059231665,"about_ca_topic_score_gemma":0.000012798695,"teacher_disagreement_score":0.9355826,"about_ca_system_score_codex":0.00015221238,"about_ca_system_score_gemma":0.000048033333,"threshold_uncertainty_score":0.99981856},"labels":[],"label_agreement":null},{"id":"W4285274205","doi":"10.54364/aaiml.2022.1126","title":"Transfer Learning to Detect Age From Handwriting","year":2022,"lang":"en","type":"article","venue":"Advances in Artificial Intelligence and Machine Learning","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"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","keywords":"Handwriting; Computer science; Artificial intelligence; Feature extraction; Feature (linguistics); Pattern recognition (psychology); Natural language processing; Speech recognition; Linguistics","score_opus":0.02940891262589089,"score_gpt":0.29581945442232205,"score_spread":0.26641054179643114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285274205","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":[0.08347118,0.0018962518,0.9126224,0.00040449365,0.00016201973,0.00022149889,0.0000040239906,0.00038086355,0.00083725847],"genre_scores_gemma":[0.96907127,0.0005274731,0.029633375,0.00047552286,0.00006019374,0.00012229652,0.000011912367,0.000019322595,0.00007860666],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979395,0.0003481587,0.00043187191,0.0005982032,0.0002971599,0.00038505768],"domain_scores_gemma":[0.9992728,0.00036075126,0.0000575629,0.00017400473,0.00003234025,0.00010249699],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007311525,0.00018710677,0.00024542483,0.0003108803,0.00063465297,0.00018086727,0.0005193425,0.000039137973,0.00016408782],"category_scores_gemma":[0.00023777096,0.00020889628,0.00005546055,0.0007315232,0.000049771646,0.0008175897,0.00041893916,0.0009818228,0.000026819856],"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":[0.000023453182,0.000020909092,0.0005425308,0.0000065574536,0.0000034669733,0.0000705817,0.002425201,0.031412635,0.005598285,0.0061585037,0.0000010624219,0.95373684],"study_design_scores_gemma":[0.0002295088,0.0019005834,0.0002657167,0.00024410056,0.000019040579,0.00007208205,0.0066709714,0.3093504,0.28455222,0.2613286,0.13375336,0.0016134017],"about_ca_topic_score_codex":0.00036914356,"about_ca_topic_score_gemma":0.00041450473,"teacher_disagreement_score":0.9521234,"about_ca_system_score_codex":0.000056207602,"about_ca_system_score_gemma":0.000019593017,"threshold_uncertainty_score":0.85185426},"labels":[],"label_agreement":null},{"id":"W4293072781","doi":"10.16995/dm.8073","title":"Illumination Detection in IIIF Medieval Manuscripts Using Deep Learning","year":2022,"lang":"en","type":"article","venue":"Digital Medievalist","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Institut National de Physique Nucléaire et de Physique des Particules; Centre National de la Recherche Scientifique","keywords":"Computer science; Interoperability; Domain (mathematical analysis); Transfer of learning; Deep learning; Information retrieval; World Wide Web; Artificial intelligence; Mathematics","score_opus":0.02112968539749353,"score_gpt":0.2525656625109896,"score_spread":0.2314359771134961,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293072781","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":[0.46430987,0.00021078283,0.51898295,0.00043231447,0.0014304643,0.00058460166,0.000015531683,0.0010525231,0.012980952],"genre_scores_gemma":[0.99666476,0.000007905298,0.0028010285,0.00012722473,0.00007282569,0.00007820267,0.000035250985,0.000019243274,0.00019352898],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99804467,0.00016699516,0.00034321778,0.00043014216,0.00069063634,0.00032433984],"domain_scores_gemma":[0.9993529,0.00009671406,0.0001465224,0.00023673107,0.000095136085,0.000072017865],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006050322,0.00015776495,0.00017363665,0.00043874801,0.0003163416,0.00028810045,0.00051264896,0.00005154988,0.000037849684],"category_scores_gemma":[0.00029086892,0.00018371412,0.00007310151,0.0008071437,0.00006170423,0.0013993132,0.00047269784,0.00040899063,0.000020358611],"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":[0.000023105293,0.0001615294,0.0007560249,0.000024908699,0.000012324667,0.00013489183,0.0016722082,0.0004138156,0.00545508,0.0011232177,0.000050544953,0.9901723],"study_design_scores_gemma":[0.0019775177,0.0010983116,0.0046682996,0.00012138797,0.000025136149,0.0008019564,0.0026817264,0.8680451,0.052847102,0.021578124,0.044650197,0.0015051309],"about_ca_topic_score_codex":0.00005331105,"about_ca_topic_score_gemma":0.000040336254,"teacher_disagreement_score":0.9886672,"about_ca_system_score_codex":0.00044250756,"about_ca_system_score_gemma":0.00003874193,"threshold_uncertainty_score":0.7491644},"labels":[],"label_agreement":null},{"id":"W4293223870","doi":"10.11159/cist22.131","title":"Archival Handwritten Digits Identification Through Deep Learning Models Johnson","year":2022,"lang":"en","type":"article","venue":"Proceedings of the World Congress on Electrical Engineering and Computer Systems and Science","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Identification (biology); Deep learning; Artificial intelligence; Speech recognition; Natural language processing","score_opus":0.012155460501167375,"score_gpt":0.21317511919441004,"score_spread":0.20101965869324268,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293223870","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":[0.3533448,0.001557667,0.6373133,0.0009544968,0.002456689,0.0010944844,0.0000039329057,0.0009166651,0.00235798],"genre_scores_gemma":[0.9966005,0.000043073418,0.0028851277,0.000049888175,0.00005582763,0.000065207576,1.9731269e-7,0.000008650045,0.0002915394],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99831116,0.000018163615,0.00028658254,0.00048106027,0.000597359,0.000305675],"domain_scores_gemma":[0.9993625,0.00009125852,0.00017256707,0.00013974577,0.00014946787,0.00008444098],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006540205,0.00014803649,0.00020796036,0.0003145054,0.00057355216,0.0005745771,0.0009894262,0.000017374896,2.8407126e-7],"category_scores_gemma":[0.00003585404,0.000118565586,0.000041787403,0.001358941,0.00011037758,0.00069977564,0.00064876524,0.00035255772,2.7420285e-7],"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":[0.000020063506,0.00011844179,0.0004863252,0.00018642364,0.000032739135,0.0000028571817,0.0010053732,0.032225378,0.014582534,0.7954073,0.00051638926,0.15541619],"study_design_scores_gemma":[0.00012460475,0.00014310819,0.00068384147,0.00008196798,0.000004375446,0.00006261269,0.000009552354,0.9909233,0.0051215016,0.0015524452,0.0011349277,0.00015778723],"about_ca_topic_score_codex":0.000013252104,"about_ca_topic_score_gemma":1.7147497e-7,"teacher_disagreement_score":0.9586979,"about_ca_system_score_codex":0.00005492919,"about_ca_system_score_gemma":0.000024414167,"threshold_uncertainty_score":0.554066},"labels":[],"label_agreement":null},{"id":"W4293863308","doi":"10.1109/siu55565.2022.9864951","title":"Text Spotting for Low-Resolution Price Tag Images","year":2022,"lang":"en","type":"article","venue":"2022 30th Signal Processing and Communications Applications Conference (SIU)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Stantec (Canada)","funders":"","keywords":"Computer science; Barcode; Convolutional neural network; Spotting; Artificial intelligence; Feature (linguistics); Pattern recognition (psychology); Similarity (geometry); Product (mathematics); Extractor; Image (mathematics); Information retrieval; Mathematics","score_opus":0.02839450345604256,"score_gpt":0.28594508132841745,"score_spread":0.2575505778723749,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293863308","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":[0.00039482032,0.0018270895,0.98694956,0.003974715,0.000016275453,0.0011098392,0.00008175028,0.0006040588,0.0050418745],"genre_scores_gemma":[0.8072677,0.00036358746,0.18342245,0.00039296813,0.00003329443,0.007958889,0.00016405983,0.0000217249,0.0003753248],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998066,0.00020514234,0.0004779605,0.00058224454,0.00032295872,0.00034570115],"domain_scores_gemma":[0.9973044,0.00033909548,0.00037800107,0.0013467683,0.00051630003,0.00011544973],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00090426987,0.00021113743,0.00022216293,0.00026767736,0.0033908056,0.00051205175,0.0024726866,0.00006266208,0.00006831722],"category_scores_gemma":[0.000030921878,0.00024250112,0.00007119215,0.0010428573,0.0002447633,0.000619294,0.0014388704,0.0004668536,0.000012960921],"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":[0.000008413405,0.00030501687,0.000042135038,0.00009536823,0.000016026785,2.653877e-7,0.00090389425,0.000036996604,0.0063557164,0.12285315,0.0009980958,0.8683849],"study_design_scores_gemma":[0.00085952994,0.00026061217,0.0003134738,0.0001458809,0.000071692484,0.00007254474,0.0031834194,0.68340224,0.005977819,0.12050836,0.18415153,0.0010529201],"about_ca_topic_score_codex":0.000027330263,"about_ca_topic_score_gemma":0.000004939758,"teacher_disagreement_score":0.867332,"about_ca_system_score_codex":0.0001174423,"about_ca_system_score_gemma":0.00038378127,"threshold_uncertainty_score":0.9979066},"labels":[],"label_agreement":null},{"id":"W4293863327","doi":"10.1109/siu55565.2022.9864878","title":"Neural Machine Translation Approaches for Post-OCR Text Processing","year":2022,"lang":"en","type":"article","venue":"2022 30th Signal Processing and Communications Applications Conference (SIU)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Stantec (Canada)","funders":"","keywords":"Automatic summarization; Computer science; Optical character recognition; Machine translation; Artificial intelligence; Natural language processing; Text recognition; Process (computing); Speech recognition; Document processing; Error detection and correction; Translation (biology); Intelligent word recognition; Pattern recognition (psychology); Information extraction; Character recognition; Image (mathematics); Intelligent character recognition","score_opus":0.07876931332849635,"score_gpt":0.2935847599729343,"score_spread":0.21481544664443797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293863327","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":[0.0003227727,0.007717294,0.9791592,0.008343659,0.000012865282,0.0015083939,0.00011963713,0.000612997,0.0022031977],"genre_scores_gemma":[0.853827,0.00012434323,0.13695006,0.00041688458,0.00002695013,0.008004448,0.0004463873,0.000028142147,0.00017579165],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979052,0.00022436844,0.0005296975,0.00065300806,0.00034806863,0.00033964976],"domain_scores_gemma":[0.9977339,0.00022381515,0.00035258537,0.0011309966,0.00043490907,0.00012379968],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0006844807,0.00026331525,0.0002645277,0.00030472464,0.00324047,0.00061178964,0.0022936491,0.00007519637,0.000056687604],"category_scores_gemma":[0.000013923126,0.00028681132,0.000085719475,0.0010331165,0.00025640914,0.0008206125,0.0007153061,0.0005366689,0.0000046228056],"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":[0.000011909146,0.00022439296,0.00003248926,0.00008225908,0.000009794846,1.6310257e-7,0.0011425371,0.00004662665,0.0010749083,0.01878958,0.0000609473,0.9785244],"study_design_scores_gemma":[0.00040637003,0.0001527701,0.000098019635,0.000031176012,0.00004294089,0.000046154353,0.00115883,0.95099956,0.0003782321,0.016050521,0.030213138,0.0004223062],"about_ca_topic_score_codex":0.000030472453,"about_ca_topic_score_gemma":0.000024559395,"teacher_disagreement_score":0.9781021,"about_ca_system_score_codex":0.00007474861,"about_ca_system_score_gemma":0.00038199365,"threshold_uncertainty_score":0.9999584},"labels":[],"label_agreement":null},{"id":"W4293868178","doi":"10.1109/crv55824.2022.00027","title":"Classification of handwritten annotations in mixed-media documents","year":2022,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"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; Artificial intelligence; Segmentation; Pattern recognition (psychology); Intersection (aeronautics); Information loss; Probabilistic logic; Ground truth; Function (biology)","score_opus":0.020083032007895955,"score_gpt":0.26907229871704086,"score_spread":0.2489892667091449,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293868178","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":[0.29548362,0.0000845668,0.6688565,0.0032390978,0.0004823495,0.0006626451,0.000036416077,0.0006168315,0.030537974],"genre_scores_gemma":[0.96436083,0.000007817633,0.034993485,0.00016913922,0.0000076780625,0.00018789766,0.000022926904,0.0000045123948,0.0002456904],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99895614,0.00011850788,0.000284575,0.000215232,0.00029561398,0.00012994584],"domain_scores_gemma":[0.9994096,0.000098571785,0.00009402736,0.00029582696,0.00006828635,0.0000336591],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036206518,0.000062782354,0.00010211358,0.0003248529,0.00007706474,0.000031164487,0.000537474,0.000021534092,0.0002875065],"category_scores_gemma":[0.000041165276,0.000066930545,0.000034216428,0.00076822523,0.000025054305,0.000359948,0.00023376766,0.00011409055,0.000019949297],"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":[0.000016599945,0.0010476207,0.02467354,0.00003262839,0.000024942014,0.000020980593,0.004512059,0.00006390044,0.038229335,0.29262716,0.021031434,0.6177198],"study_design_scores_gemma":[0.0024292616,0.000487668,0.66780955,0.00005252414,0.000014577639,0.000049823506,0.00338473,0.051806614,0.082887925,0.1690711,0.021134915,0.0008713171],"about_ca_topic_score_codex":0.0000631754,"about_ca_topic_score_gemma":0.000054364256,"teacher_disagreement_score":0.66887724,"about_ca_system_score_codex":0.00006734669,"about_ca_system_score_gemma":0.000053759584,"threshold_uncertainty_score":0.31479943},"labels":[],"label_agreement":null},{"id":"W4293868248","doi":"10.1109/crv55824.2022.00026","title":"Occluded Text Detection and Recognition in the Wild","year":2022,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Ontario Centres of Excellence","keywords":"Spotting; Computer science; Artificial intelligence; Text recognition; Text detection; Robustness (evolution); Convolutional neural network; Deep learning; Pattern recognition (psychology); Feature extraction; Speech recognition; Natural language processing; Computer vision; Image (mathematics)","score_opus":0.020484687260084577,"score_gpt":0.23853559459111434,"score_spread":0.21805090733102978,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293868248","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":[0.32764027,0.000077297474,0.64518857,0.003627653,0.00019868679,0.00070880563,0.0000046022415,0.0006830666,0.021871066],"genre_scores_gemma":[0.9914474,0.000013378148,0.0064124586,0.0018331412,0.0000143483885,0.00018838572,0.0000022975994,0.0000032093467,0.00008537928],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991963,0.00020414389,0.000117369076,0.00019262683,0.00018066229,0.00010890576],"domain_scores_gemma":[0.9996668,0.00008832602,0.000032779077,0.00017555624,0.000019473375,0.0000170762],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00062398217,0.00005596107,0.000053228076,0.00013749425,0.00018831703,0.000093291455,0.0002967852,0.000018796412,0.000109897745],"category_scores_gemma":[0.000022381644,0.000044101802,0.000018536992,0.00045089785,0.000016982829,0.0002773575,0.00016846968,0.0001753193,0.000018213852],"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":[0.0000039357437,0.000048292906,0.00010020001,0.0000027206902,0.0000016877018,0.000008128367,0.0007984762,6.069298e-7,0.0017341754,0.0009776611,0.0006259119,0.9956982],"study_design_scores_gemma":[0.0030781438,0.002488443,0.03343716,0.00005472852,0.000027265625,0.0025550302,0.005885849,0.08363946,0.16417418,0.6343574,0.068637244,0.0016650856],"about_ca_topic_score_codex":0.00009805621,"about_ca_topic_score_gemma":0.00008046832,"teacher_disagreement_score":0.9940331,"about_ca_system_score_codex":0.00003202953,"about_ca_system_score_gemma":0.000010765279,"threshold_uncertainty_score":0.17984192},"labels":[],"label_agreement":null},{"id":"W4294312962","doi":"10.16995/dscn.8096","title":"Exploring Medieval Manuscripts Writer Predictability: A Study on Scribe and Letter Identification","year":2022,"lang":"en","type":"article","venue":"Digital Studies / Le champ numérique","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Handwriting; Palaeography; Character (mathematics); Art; Identification (biology); Literature; Humanities; Medieval literature; Middle Ages; Digital humanities; History; Computer science; Artificial intelligence; Archaeology","score_opus":0.11702025945853227,"score_gpt":0.28119095408289313,"score_spread":0.16417069462436085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4294312962","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":[0.977197,0.00022677095,0.014915267,0.0043320637,0.0005740349,0.0009962964,0.00004550239,0.00064894435,0.0010641104],"genre_scores_gemma":[0.9967876,0.000054649983,0.00006359207,0.0007963387,0.00012874162,0.0018905288,0.000015703596,0.000023741726,0.0002390984],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99756813,0.00020992415,0.00045527858,0.0008174167,0.0006152395,0.00033399294],"domain_scores_gemma":[0.9988405,0.00016437602,0.00013099996,0.0006183749,0.00015697518,0.0000887769],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00078943564,0.00025906164,0.0003131665,0.0002115993,0.0005779568,0.00043515678,0.00057359884,0.000026854705,0.000006048037],"category_scores_gemma":[0.0001743026,0.00025536804,0.00007863535,0.00036879262,0.00011948435,0.001754712,0.0014333979,0.0003148494,0.000017680037],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015103091,0.0038310725,0.020388843,0.00020893768,0.00066233467,0.0003759698,0.80588436,0.000014391979,0.0014834459,0.0008635296,0.018241495,0.14789456],"study_design_scores_gemma":[0.003049995,0.0041979332,0.051406316,0.00018180089,0.0000025813358,0.00018488624,0.857299,0.0005795633,0.013075951,0.030504633,0.03750114,0.002016247],"about_ca_topic_score_codex":0.000015712652,"about_ca_topic_score_gemma":0.000011582381,"teacher_disagreement_score":0.14587831,"about_ca_system_score_codex":0.00017219454,"about_ca_system_score_gemma":0.000026727905,"threshold_uncertainty_score":0.99998987},"labels":[],"label_agreement":null},{"id":"W4295011752","doi":"10.1016/j.patrec.2022.08.016","title":"Novel features to detect gender from handwritten documents","year":2022,"lang":"en","type":"article","venue":"Pattern Recognition Letters","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":18,"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; Concordia University","keywords":"Handwriting; Computer science; Support vector machine; Artificial intelligence; Pattern recognition (psychology); Set (abstract data type); Task (project management); Similarity (geometry); Data set; Handwriting recognition; Speech recognition; Natural language processing; Feature extraction; Image (mathematics)","score_opus":0.026644853902571597,"score_gpt":0.2527431218860396,"score_spread":0.226098267983468,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4295011752","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":[0.10528579,0.00003798286,0.8850553,0.006551635,0.0007335781,0.0006077405,0.00038280216,0.000781692,0.0005634983],"genre_scores_gemma":[0.761216,0.000011043315,0.13394818,0.10246349,0.00035000738,0.001410466,0.00042462046,0.00007140027,0.000104818595],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99717087,0.00022482088,0.00039721472,0.00089677307,0.00078282977,0.00052751554],"domain_scores_gemma":[0.99876374,0.0001435387,0.00016298675,0.0006158042,0.00008805509,0.00022584976],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00035722964,0.00030874903,0.00026197516,0.0004576485,0.00044974955,0.00036251327,0.0011869948,0.00006118397,0.0013918333],"category_scores_gemma":[0.00003622874,0.00034810213,0.00016637777,0.0005588451,0.000029681121,0.0005792533,0.00083144306,0.000455874,0.00067764707],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023627388,0.00011651281,0.0005386045,0.0000129325235,0.00009581027,0.000081007005,0.0010514993,0.000022143384,0.125347,0.000007876966,0.048239626,0.82446337],"study_design_scores_gemma":[0.011251496,0.0015816396,0.09777474,0.0004142568,0.0003197242,0.001373764,0.00094966375,0.0028676083,0.724909,0.034086592,0.116073035,0.008398472],"about_ca_topic_score_codex":0.00046826675,"about_ca_topic_score_gemma":0.000028175147,"teacher_disagreement_score":0.8160649,"about_ca_system_score_codex":0.00021596778,"about_ca_system_score_gemma":0.000029452183,"threshold_uncertainty_score":0.9998971},"labels":[],"label_agreement":null},{"id":"W4298854907","doi":"","title":"Error handling approach using characterization and correction steps for handwritten document analysis","year":2012,"lang":"en","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Handwritten Text Recognition Techniques","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":"École de Technologie Supérieure","funders":"","keywords":"Computer science; Natural language processing; Characterization (materials science); Artificial intelligence; Error analysis; Information retrieval; Pattern recognition (psychology); Mathematics; Materials science","score_opus":0.020048214097793365,"score_gpt":0.24896423132796225,"score_spread":0.22891601723016888,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4298854907","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":[0.07513985,0.00015984829,0.9220906,0.0005684007,0.00015266122,0.00042483577,0.00001155003,0.00028652203,0.0011657528],"genre_scores_gemma":[0.6839437,0.000063407264,0.31435332,0.00007196752,0.000028050428,0.00008839647,0.00024660968,0.00001689112,0.0011877035],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969654,0.0015900076,0.00036926134,0.00046890206,0.00025528914,0.00035114778],"domain_scores_gemma":[0.99734807,0.0005671746,0.00030895113,0.00072854426,0.0008735124,0.0001737359],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0049535083,0.00019030449,0.0002658619,0.00037934515,0.00047374325,0.00049646205,0.00045851135,0.00012475911,0.000017155648],"category_scores_gemma":[0.00039844876,0.00019925648,0.00012345596,0.00090228807,0.000075985474,0.0010520882,0.0002582395,0.0001427986,0.0000039601014],"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":[0.00003068049,0.001295142,0.022330642,0.00020117711,0.0006208332,9.4735094e-7,0.024004215,0.00009315638,0.09142005,0.07375126,0.00028598594,0.7859659],"study_design_scores_gemma":[0.0005997916,0.0000013366883,0.011049343,0.00020901,0.00024595586,0.000026385418,0.00015467982,0.8181095,0.164403,0.0005285032,0.004184757,0.0004877176],"about_ca_topic_score_codex":0.00015764376,"about_ca_topic_score_gemma":0.000051046078,"teacher_disagreement_score":0.81801635,"about_ca_system_score_codex":0.00008779299,"about_ca_system_score_gemma":0.000045937224,"threshold_uncertainty_score":0.81254435},"labels":[],"label_agreement":null},{"id":"W4301427922","doi":"10.48550/arxiv.1502.07058","title":"Evaluation of Deep Convolutional Nets for Document Image Classification\\n and Retrieval","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Convolutional neural network; Computer science; Artificial intelligence; Abstraction; Pattern recognition (psychology); Representation (politics); Feature (linguistics); Variety (cybernetics); Document classification; Object (grammar); Deep learning; Feature learning; Contextual image classification; Image (mathematics); Information retrieval","score_opus":0.14221173661594697,"score_gpt":0.2585576023917633,"score_spread":0.11634586577581632,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4301427922","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":[0.07042947,0.00013910617,0.9265201,0.00016715591,0.00020031286,0.00092606957,0.000040146224,0.00013698825,0.0014406518],"genre_scores_gemma":[0.9755578,0.000080905156,0.024103371,0.000029465047,0.000035336445,0.0000069983084,0.000067451314,0.000009544957,0.00010912474],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99833125,0.0002511815,0.00024897058,0.0006941421,0.00030377237,0.00017071063],"domain_scores_gemma":[0.99611145,0.00012432203,0.00037909485,0.000583702,0.0026828747,0.00011857582],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022058357,0.00017802573,0.00023536138,0.00024106269,0.00007732909,0.00007723563,0.0006475855,0.00022084794,0.000026392858],"category_scores_gemma":[0.00025243338,0.00021421403,0.0001010936,0.00025505238,0.00015988549,0.0004207232,0.0006248838,0.00018728225,0.000009068323],"study_design_candidate":"theoretical_or_conceptual","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":[0.00027928728,0.000492649,0.0012557622,0.00048099033,0.00056483864,0.000020383617,0.0010260455,0.009881179,0.002617731,0.93117255,0.0050484063,0.047160204],"study_design_scores_gemma":[0.00062877237,0.000061611565,0.0009334942,0.00003606083,0.00013409743,0.00000223091,0.000034856406,0.6109256,0.0011228103,0.3858046,0.00013955402,0.0001762902],"about_ca_topic_score_codex":0.000018838677,"about_ca_topic_score_gemma":0.000009847144,"teacher_disagreement_score":0.90512836,"about_ca_system_score_codex":0.0004259348,"about_ca_system_score_gemma":0.00055762095,"threshold_uncertainty_score":0.87353945},"labels":[],"label_agreement":null},{"id":"W4309355783","doi":"10.1002/9781119861850.ch10","title":"Smart Text Reader System for People who are Blind Using Machine and Deep Learning","year":2022,"lang":"en","type":"other","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Variety (cybernetics); Artificial intelligence; Sight; Computer science; Field (mathematics); Parsing; Deep learning; Data science; Population; Automation; Benchmark (surveying); Everyday life; Machine learning; Human–computer interaction; Engineering; Cartography; Geography; Medicine","score_opus":0.022089160079882052,"score_gpt":0.26079673309805135,"score_spread":0.2387075730181693,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309355783","genre_codex":"methods","genre_gemma":"other","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":[0.00004206381,0.0014816753,0.8367587,0.00011058755,0.00022644558,0.00093639427,0.000028608401,0.0019194564,0.15849613],"genre_scores_gemma":[0.0030858489,0.00022757267,0.32879466,0.00036375027,0.00034535397,0.00042643465,0.00010607583,0.0006604161,0.6659899],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984434,0.00012364617,0.00024734548,0.0006375783,0.0002580094,0.00028998285],"domain_scores_gemma":[0.9990276,0.000103632214,0.00031153654,0.0004099537,0.000057377325,0.00008990157],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00033611828,0.00028228623,0.0005278357,0.00045048018,0.00023193382,0.00023466567,0.00048603915,0.0002046595,0.0015058385],"category_scores_gemma":[0.000037789276,0.00026766263,0.00009119107,0.00029070443,0.000025038984,0.00012909003,0.00044644048,0.0003112297,0.000020953481],"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":[0.00009896911,0.00035794254,0.012653887,0.010854318,0.00093187345,0.00018875711,0.0047343452,0.00003908639,0.00042246532,0.025078336,0.44297335,0.50166667],"study_design_scores_gemma":[0.0013581302,0.00023038831,0.00010392436,0.0012538714,0.00009677358,0.00030844615,0.0011978671,0.13794214,0.0004918965,0.00023846829,0.8554756,0.0013024712],"about_ca_topic_score_codex":0.00048659093,"about_ca_topic_score_gemma":0.0005832173,"teacher_disagreement_score":0.507964,"about_ca_system_score_codex":0.00010119129,"about_ca_system_score_gemma":0.000036528425,"threshold_uncertainty_score":0.9999775},"labels":[],"label_agreement":null},{"id":"W4309788759","doi":"10.3390/app122211760","title":"Persian Optical Character Recognition Using Deep Bidirectional Long Short-Term Memory","year":2022,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Persian; Computer science; Artificial intelligence; Natural language processing; Optical character recognition; Context (archaeology); Character (mathematics); Convolutional neural network; Arabic; Deep learning; Term (time); Speech recognition; Linguistics; Image (mathematics); Mathematics; History","score_opus":0.046375180538908364,"score_gpt":0.27691000945899674,"score_spread":0.23053482892008836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309788759","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":[0.6420251,0.00005320459,0.3295692,0.0006309944,0.00071521354,0.00046853727,0.0000088139095,0.0007014802,0.025827454],"genre_scores_gemma":[0.9239829,0.0000046356604,0.07514443,0.0005301143,0.00013314592,0.00014684566,0.0000123832,0.000009175637,0.000036354442],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9977912,0.000081226186,0.0002561087,0.00066842063,0.00080618594,0.00039689985],"domain_scores_gemma":[0.99941367,0.000095045616,0.000080626174,0.00023655908,0.000057988396,0.000116137766],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010388073,0.00015554359,0.00015720152,0.0003468367,0.0012859766,0.00030484394,0.00095022836,0.000047872698,0.0005335578],"category_scores_gemma":[0.000014789018,0.00015786274,0.00007833256,0.0009902572,0.000393999,0.00063789025,0.0004986277,0.00026934236,0.00006594756],"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":[0.000017966522,0.00029727112,0.0013275323,0.0000165815,0.000027909724,0.000056881865,0.0014238587,0.000120486846,0.061665963,0.010598938,0.00024342586,0.92420316],"study_design_scores_gemma":[0.0016185628,0.0014017647,0.025308797,0.000121736855,0.00013939134,0.0033124317,0.006699623,0.23636979,0.6625612,0.055621468,0.002218554,0.0046266937],"about_ca_topic_score_codex":0.000013767694,"about_ca_topic_score_gemma":0.000008754726,"teacher_disagreement_score":0.91957647,"about_ca_system_score_codex":0.0001398731,"about_ca_system_score_gemma":0.00013527159,"threshold_uncertainty_score":0.9890823},"labels":[],"label_agreement":null},{"id":"W4309951107","doi":"10.1007/s42979-022-01494-2","title":"Introducing a New High-Resolution Handwritten Digits Data Set with Writer Characteristics","year":2022,"lang":"en","type":"article","venue":"SN Computer Science","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":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Engineering and Physical Sciences Research Council; University of Toronto; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Set (abstract data type); Data set; Computer science; High resolution; Natural language processing; Resolution (logic); Artificial intelligence; Speech recognition; History; Programming language; Archaeology","score_opus":0.027616977552786654,"score_gpt":0.2553996096001099,"score_spread":0.2277826320473232,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309951107","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":[0.014895464,0.000032094093,0.9803986,0.0025649478,0.00088971463,0.00032536194,0.00007515,0.0006790303,0.00013962704],"genre_scores_gemma":[0.41028488,0.0000070157116,0.5872258,0.0016522468,0.0005053807,0.000032078293,0.000106880914,0.000018851224,0.00016685594],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958332,0.00012742488,0.00039411167,0.0016202776,0.001322663,0.000702301],"domain_scores_gemma":[0.99641746,0.00008806485,0.00022882801,0.0027319638,0.00023652842,0.00029715287],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0015081639,0.0002617628,0.00028502388,0.0004919061,0.0010546027,0.0013868369,0.006785116,0.000034950674,0.000058719143],"category_scores_gemma":[0.00005519655,0.0002404951,0.000034409983,0.0023777124,0.00029026705,0.0031864787,0.007382044,0.00040584907,0.000049656763],"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":[0.000032558943,0.00020110069,0.00086919847,0.000025707159,0.00002845184,0.00015414557,0.0016717233,0.00057156,0.002194109,0.009802384,0.038463544,0.9459855],"study_design_scores_gemma":[0.0010826132,0.0011652699,0.0072098873,0.00011647705,0.000023188728,0.00088700553,0.000032653767,0.9361882,0.004584702,0.0046442472,0.042886354,0.0011793536],"about_ca_topic_score_codex":0.0001392214,"about_ca_topic_score_gemma":0.000009784728,"teacher_disagreement_score":0.94480616,"about_ca_system_score_codex":0.00020366987,"about_ca_system_score_gemma":0.0007660303,"threshold_uncertainty_score":0.9996498},"labels":[],"label_agreement":null},{"id":"W4312108337","doi":"10.48550/arxiv.2212.11146","title":"The Challenges of HTR Model Training: Feedback from the Project Donner le gout de l'archive a l'ere numerique","year":2022,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Rimouski; Université de Montréal","funders":"","keywords":"Computer science; Handwriting; Process (computing); Handwriting recognition; Base (topology); Scale (ratio); Language model; Character (mathematics); Natural language processing; Word error rate; Data science; Artificial intelligence; Speech recognition; Feature extraction; Programming language; Cartography","score_opus":0.12012162176980765,"score_gpt":0.21708516363452854,"score_spread":0.09696354186472089,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312108337","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":[0.04353579,0.00055422506,0.9365607,0.0024289945,0.0001913976,0.0009869362,0.00020385045,0.00047548505,0.015062637],"genre_scores_gemma":[0.9872814,0.0020840345,0.009763203,0.00014071756,0.00005939701,0.0000284202,0.000019176765,0.000030230605,0.0005934341],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975222,0.00069660967,0.0002695576,0.0009380222,0.00016695255,0.00040665863],"domain_scores_gemma":[0.9970686,0.0007210663,0.0004020805,0.0015930206,0.0001309762,0.00008429564],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00072344847,0.00032256026,0.0003602302,0.00013582679,0.00047596777,0.00012465403,0.0040191547,0.00019729623,0.0000181364],"category_scores_gemma":[0.00007578164,0.00025454475,0.00033384,0.00034196975,0.00029839124,0.00022911107,0.0031272538,0.0010499354,0.0000066846324],"study_design_candidate":"theoretical_or_conceptual","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":[0.000113942,0.00024849802,0.0001905786,0.000089667425,0.00044189245,0.0001290088,0.033382874,0.04961635,0.00023288521,0.8954719,0.002347864,0.017734557],"study_design_scores_gemma":[0.00032876682,0.000073016294,0.00018819979,0.00012040084,0.000049475293,0.0000059356885,0.0047123996,0.5016955,0.00051281974,0.49009025,0.001833373,0.0003898715],"about_ca_topic_score_codex":0.0015546073,"about_ca_topic_score_gemma":0.00059764675,"teacher_disagreement_score":0.9437456,"about_ca_system_score_codex":0.00016738383,"about_ca_system_score_gemma":0.0011910292,"threshold_uncertainty_score":0.9999907},"labels":[],"label_agreement":null},{"id":"W4312371981","doi":"10.1109/icpr56361.2022.9956534","title":"Frank-Wolfe-based Multi-task Learning for Historical Document Restoration","year":2022,"lang":"en","type":"article","venue":"2022 26th International Conference on Pattern Recognition (ICPR)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"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; Artificial intelligence; Task (project management); Machine learning; Inference; Supervised learning; Deep learning; Artificial neural network","score_opus":0.07621091900896396,"score_gpt":0.3065656147011682,"score_spread":0.23035469569220426,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312371981","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":[0.0050178175,0.000031575455,0.9812007,0.0066270404,0.0026365514,0.00089425285,0.00019899139,0.00065111666,0.0027419678],"genre_scores_gemma":[0.9749277,0.000034134016,0.014990415,0.0034599141,0.00029031886,0.002832504,0.0015115386,0.000046188634,0.0019072851],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965303,0.00041510927,0.0006652395,0.0008879235,0.0011250508,0.0003763813],"domain_scores_gemma":[0.99806243,0.00023742243,0.00048060445,0.00037407855,0.00069850404,0.00014697165],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008635087,0.00031385777,0.00028267349,0.0006329161,0.0006496361,0.00034946887,0.001117321,0.000089671346,0.0029992464],"category_scores_gemma":[0.00019221903,0.0003634007,0.0002251461,0.00032410567,0.00003704699,0.0005603575,0.00029152885,0.0007029879,0.00022358797],"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":[0.00042155237,0.0013963442,0.00096171093,0.000074831696,0.00015144203,0.00008478131,0.00086028373,0.0006975876,0.006156467,0.007830201,0.024046501,0.9573183],"study_design_scores_gemma":[0.008613109,0.0047388608,0.0019964078,0.0003400949,0.00008435871,0.00010766654,0.0005662705,0.6661914,0.026558563,0.038476016,0.24968214,0.002645123],"about_ca_topic_score_codex":0.000117955344,"about_ca_topic_score_gemma":0.000031717926,"teacher_disagreement_score":0.9699099,"about_ca_system_score_codex":0.0014156238,"about_ca_system_score_gemma":0.00023008233,"threshold_uncertainty_score":0.9998818},"labels":[],"label_agreement":null},{"id":"W4312403814","doi":"10.1109/icpr56361.2022.9956488","title":"Arbitrary Shape Text Detection using Transformers","year":2022,"lang":"en","type":"article","venue":"2022 26th International Conference on Pattern Recognition (ICPR)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Bézier curve; Minimum bounding box; Artificial intelligence; Bounding overwatch; Intersection (aeronautics); Transformer; Function (biology); Pattern recognition (psychology); Representation (politics); Algorithm; Image (mathematics); Mathematics; Geometry","score_opus":0.0700658564829681,"score_gpt":0.29155630256633913,"score_spread":0.22149044608337104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312403814","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":[0.22759649,0.000028403821,0.7328043,0.002809008,0.0027874045,0.0008181731,0.0005924293,0.0009615416,0.03160228],"genre_scores_gemma":[0.99248165,0.00006782474,0.002642893,0.0035807595,0.00017707529,0.0004353367,0.00031419517,0.00003929736,0.0002609713],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99664396,0.00029994835,0.00060447044,0.00084715034,0.0011855573,0.00041890636],"domain_scores_gemma":[0.998744,0.0000896641,0.0003169401,0.00032758,0.00036528017,0.0001565491],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005433591,0.0003370454,0.00026062608,0.0007851658,0.00054248277,0.00033934397,0.0011634132,0.00010248362,0.015158724],"category_scores_gemma":[0.000034638648,0.00039215488,0.00022300995,0.00053689466,0.000065586646,0.000973516,0.0003137373,0.00081360084,0.00036999665],"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":[0.000060608003,0.0002742271,0.00018416894,0.000015960137,0.000076575234,0.000058604473,0.00029754438,0.000015950805,0.012173979,0.0012340192,0.00029089747,0.98531747],"study_design_scores_gemma":[0.002947565,0.0017790481,0.002148502,0.00028784107,0.00007472316,0.00091841037,0.0013880657,0.8118262,0.10645246,0.058259062,0.011624585,0.002293539],"about_ca_topic_score_codex":0.00010855841,"about_ca_topic_score_gemma":0.0000316794,"teacher_disagreement_score":0.98302394,"about_ca_system_score_codex":0.0004450031,"about_ca_system_score_gemma":0.0001716631,"threshold_uncertainty_score":0.999853},"labels":[],"label_agreement":null},{"id":"W4312717468","doi":"10.1109/cvpr52688.2022.01145","title":"GAT-CADNet: Graph Attention Network for Panoptic Symbol Spotting in CAD Drawings","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Adjacency list; CAD; Adjacency matrix; Graph; Vertex (graph theory); Theoretical computer science; Symbol (formal); Spotting; Raster graphics; Artificial intelligence; Pattern recognition (psychology); Algorithm; Engineering drawing","score_opus":0.03216264739353678,"score_gpt":0.27145013738135443,"score_spread":0.23928748998781765,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312717468","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":[0.2696314,0.000047758167,0.7249325,0.0012984119,0.0015063292,0.0012876043,0.000115967334,0.0004934867,0.0006865587],"genre_scores_gemma":[0.9784631,0.00014586703,0.01638052,0.003464575,0.000342208,0.00076775585,0.0002599268,0.0000500983,0.00012591999],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99588764,0.0005517519,0.00083906023,0.0012395435,0.000762445,0.00071956095],"domain_scores_gemma":[0.9981733,0.0003809273,0.00040575562,0.0004905299,0.00033249945,0.00021696914],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001491928,0.0004654638,0.0005607063,0.0006763001,0.0007311678,0.0006018544,0.0007668111,0.00015880517,0.00040196723],"category_scores_gemma":[0.000025894476,0.0004995126,0.0002237671,0.00079506764,0.00007337367,0.00066489447,0.0004662261,0.0007143771,0.00007364344],"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":[0.00007329542,0.00029635915,0.0018037725,0.00010220547,0.000033074084,0.00004803425,0.0006079914,0.000096921234,0.0018437332,0.00055350334,0.0043658805,0.99017525],"study_design_scores_gemma":[0.007832041,0.006859628,0.028833518,0.0024817162,0.00010461338,0.00048739664,0.0006751769,0.8581124,0.004506378,0.08123181,0.0053159897,0.0035593228],"about_ca_topic_score_codex":0.000079833444,"about_ca_topic_score_gemma":0.000053325577,"teacher_disagreement_score":0.9866159,"about_ca_system_score_codex":0.00014305266,"about_ca_system_score_gemma":0.00010055488,"threshold_uncertainty_score":0.99974567},"labels":[],"label_agreement":null},{"id":"W4313040688","doi":"10.1007/978-3-031-19745-1_11","title":"Novel Feature Extraction Methods to Detect Age from Handwriting","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","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":"Concordia University","funders":"","keywords":"Handwriting; Feature extraction; Computer science; Artificial intelligence; Pattern recognition (psychology); Extraction (chemistry); Chromatography; Chemistry","score_opus":0.031047056089029416,"score_gpt":0.31687526766023316,"score_spread":0.28582821157120375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313040688","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":[0.000021344376,0.00038969886,0.99107456,0.0011217775,0.0019559178,0.00069646764,0.00003459902,0.000721657,0.0039839856],"genre_scores_gemma":[0.0029165163,0.00003363095,0.9928678,0.003031665,0.0005810216,0.00007068527,0.000021916743,0.00006168643,0.0004150465],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9948273,0.00013177472,0.00060636597,0.0023735722,0.0012777869,0.00078324],"domain_scores_gemma":[0.9960984,0.0013271262,0.00037996337,0.0016489837,0.00024785075,0.00029770398],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0019965111,0.00068613177,0.00071498484,0.0014685664,0.00056553714,0.0010518404,0.004027377,0.00045621826,0.0001942526],"category_scores_gemma":[0.00033257346,0.0007099293,0.00023149334,0.0011952721,0.00027075873,0.0009812295,0.002708983,0.0019689745,0.000043943553],"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":[0.0000057636785,0.00001722412,0.0000017935482,0.000012576927,0.00001153638,0.0001356224,0.00042177955,0.00093527226,0.020436028,0.0016299414,0.00007475169,0.9763177],"study_design_scores_gemma":[0.00089342805,0.00088415155,0.0002845183,0.0013731306,0.000055674605,0.0006845524,0.0000016216449,0.15131387,0.2506444,0.4776451,0.11235076,0.003868801],"about_ca_topic_score_codex":0.00016259633,"about_ca_topic_score_gemma":0.00016378237,"teacher_disagreement_score":0.9724489,"about_ca_system_score_codex":0.0007080697,"about_ca_system_score_gemma":0.00037805914,"threshold_uncertainty_score":0.99998516},"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":"W4313343284","doi":"10.1007/978-3-031-23028-8_6","title":"Review of Handwriting Analysis for Predicting Personality Traits","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":8,"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":"Handwriting; Computer science; Point (geometry); Process (computing); Data science; Artificial intelligence; Artificial neural network; Data mining; Machine learning; Information retrieval","score_opus":0.030487248102765208,"score_gpt":0.2855566614293807,"score_spread":0.2550694133266155,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313343284","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":[0.000019441537,0.0072789877,0.98854065,0.00059646956,0.00023881104,0.0008291451,0.000071751136,0.00020809291,0.0022166374],"genre_scores_gemma":[0.03188359,0.0027288985,0.9600025,0.0046621826,0.00033087604,0.00016032744,0.000057354737,0.000047708567,0.00012658245],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960472,0.00007811577,0.00093248405,0.0014016612,0.0010425501,0.0004980155],"domain_scores_gemma":[0.9967257,0.0010018371,0.0007315679,0.00085699884,0.00056419877,0.00011971015],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0032185956,0.00040234617,0.000996802,0.0011764033,0.0003156986,0.00016242145,0.0027779595,0.00016622391,0.00016287158],"category_scores_gemma":[0.0004280246,0.00040396952,0.000567062,0.001761656,0.00036008196,0.0005086623,0.0010370641,0.0006146773,0.0000014983481],"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":[0.00000418737,0.000040264094,0.00014966972,0.0028729811,0.00013017743,0.000012526377,0.00048572713,0.00077860913,0.00009964446,0.008149047,0.00005157528,0.9872256],"study_design_scores_gemma":[0.0009142799,0.001135416,0.0006465909,0.028180849,0.0008404081,0.00016207749,0.0000013868744,0.7613172,0.009170051,0.17909223,0.015669374,0.0028701283],"about_ca_topic_score_codex":0.000035601723,"about_ca_topic_score_gemma":0.00004361717,"teacher_disagreement_score":0.98435545,"about_ca_system_score_codex":0.0002571483,"about_ca_system_score_gemma":0.00046404928,"threshold_uncertainty_score":0.9998412},"labels":[],"label_agreement":null},{"id":"W4316924994","doi":"10.1109/ijcb54206.2022.10007945","title":"Kinematic Synthesis for 3D Signatures","year":2022,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; European Commission","keywords":"Kinematics; Signature (topology); Computer science; Novelty; Artificial intelligence; Data mining; Pattern recognition (psychology); Mathematics","score_opus":0.016081108754314358,"score_gpt":0.2511296400161193,"score_spread":0.23504853126180497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4316924994","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":[0.0002207471,0.000036335023,0.9880546,0.0012662658,0.000101285754,0.0003253611,0.0000074677537,0.0006792516,0.00930869],"genre_scores_gemma":[0.23427825,0.0000018731312,0.7617117,0.0014228033,0.000024134604,0.0014013614,0.000002219495,0.000008536492,0.001149124],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99927515,0.000054666038,0.00012866054,0.00020509018,0.00018867588,0.00014775395],"domain_scores_gemma":[0.9992289,0.00037799543,0.000042465068,0.00027706064,0.000040531206,0.000033073047],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031467868,0.00006797494,0.00009947626,0.00010897747,0.00020290403,0.00006398401,0.0006454104,0.000018729053,0.0008120124],"category_scores_gemma":[0.00010353587,0.00006136834,0.00006388394,0.0002031736,0.000010322194,0.00014637507,0.00025833858,0.00007460462,0.00001875651],"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":[0.000008292262,0.00020204831,0.000013744233,0.00007842025,0.00003507899,0.000010944324,0.00032601936,0.00006647472,0.00436178,0.19420835,0.1207734,0.6799154],"study_design_scores_gemma":[0.00056127505,0.00062980613,0.00015370159,0.00003973805,0.00003830376,0.00007753637,0.00022035465,0.36591294,0.20584154,0.20973574,0.21579957,0.0009894791],"about_ca_topic_score_codex":0.000005697296,"about_ca_topic_score_gemma":0.000001320241,"teacher_disagreement_score":0.678926,"about_ca_system_score_codex":0.000029129225,"about_ca_system_score_gemma":0.000025925054,"threshold_uncertainty_score":0.8890967},"labels":[],"label_agreement":null},{"id":"W4318147587","doi":"10.1109/bigdata55660.2022.10021025","title":"Handwritten Word Recognition using Deep Learning Approach: A Novel Way of Generating Handwritten Words","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Word (group theory); Artificial intelligence; Word error rate; Bengali; Natural language processing; Process (computing); Speech recognition; Recall rate; Deep learning; Precision and recall; Language model; Pattern recognition (psychology); Mathematics","score_opus":0.3210273366955822,"score_gpt":0.3386155405561522,"score_spread":0.017588203860569973,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318147587","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":[0.017977089,0.000077241064,0.9692883,0.0004839903,0.00259555,0.00047509337,0.00595841,0.00032548176,0.0028188794],"genre_scores_gemma":[0.78284115,0.00022005041,0.18569271,0.0006767326,0.0012735218,0.0001982605,0.028703185,0.00007180277,0.0003225667],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99457866,0.00043928224,0.00094446196,0.0017704908,0.0017569824,0.0005101204],"domain_scores_gemma":[0.99579805,0.00021047653,0.00077993097,0.0025933404,0.00045850326,0.000159685],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0021849584,0.00041393537,0.00047859247,0.0007383843,0.0006436945,0.0006165558,0.008187549,0.00012451972,0.00038981935],"category_scores_gemma":[0.00044954874,0.00046137,0.00009369228,0.0008790128,0.0001407304,0.0018494864,0.0063461554,0.0010970846,0.00003311],"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":[0.000088542176,0.0005659429,0.00011499001,0.000039054863,0.0001829366,0.000031722302,0.0005101248,0.00051514676,0.038859714,0.0010006159,0.0021043292,0.95598686],"study_design_scores_gemma":[0.0010926047,0.00020651998,0.00006872723,0.00017087728,0.0000493118,0.00018254553,0.0007388224,0.9826981,0.0046986677,0.0009649312,0.008440451,0.00068842986],"about_ca_topic_score_codex":0.0003411322,"about_ca_topic_score_gemma":0.00010726845,"teacher_disagreement_score":0.982183,"about_ca_system_score_codex":0.00022422704,"about_ca_system_score_gemma":0.00031420184,"threshold_uncertainty_score":0.9997838},"labels":[],"label_agreement":null},{"id":"W4319026190","doi":"10.21203/rs.3.rs-2533077/v1","title":"Signature Verification by Multi-Size Assembled-Attention with the Backbone of Swin-Transformer","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"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; Handwriting; Artificial intelligence; Transformer; Signature (topology); Pattern recognition (psychology); Biometrics; Convolutional neural network; Feature extraction; Handwriting recognition; Block (permutation group theory); Data mining; Engineering","score_opus":0.06749547708586436,"score_gpt":0.374124492904705,"score_spread":0.30662901581884067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319026190","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":[0.023355141,0.00077690475,0.958978,0.010828713,0.00021306454,0.003774385,0.00020121047,0.0009345606,0.00093801157],"genre_scores_gemma":[0.97200245,0.0008877859,0.022908235,0.00005649368,0.000090025285,0.0011127361,0.00022879154,0.00007423375,0.0026392732],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99546415,0.0007732047,0.00041615564,0.00089801714,0.0018715843,0.0005769194],"domain_scores_gemma":[0.9957845,0.0007666264,0.00022218612,0.0014938808,0.001606008,0.00012678395],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030726441,0.0002890503,0.00035209404,0.00036931003,0.00027364187,0.0003705141,0.0020757848,0.0004851947,0.000045642217],"category_scores_gemma":[0.0002548505,0.00019961587,0.00018152532,0.0012924824,0.00019176463,0.00032822727,0.0005719183,0.0020811849,0.00012861438],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026647252,0.0018290117,0.0019154345,0.0062929047,0.0006982782,0.00008727111,0.004778889,0.00015830349,0.64747477,0.007064758,0.18895969,0.14047422],"study_design_scores_gemma":[0.003790668,0.0024427108,0.09592707,0.009302272,0.00014774762,0.00003680503,0.0027166242,0.033884786,0.8081192,0.020556567,0.020219304,0.0028562522],"about_ca_topic_score_codex":0.000252666,"about_ca_topic_score_gemma":0.000095707066,"teacher_disagreement_score":0.94864726,"about_ca_system_score_codex":0.00016283765,"about_ca_system_score_gemma":0.00037467215,"threshold_uncertainty_score":0.90418285},"labels":[],"label_agreement":null},{"id":"W4319073283","doi":"10.1016/j.patrec.2023.02.001","title":"Age detection from handwriting using different feature classification models","year":2023,"lang":"en","type":"article","venue":"Pattern Recognition Letters","topic":"Handwritten Text Recognition Techniques","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":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Support vector machine; Handwriting; Pattern recognition (psychology); Artificial intelligence; Computer science; Artificial neural network; Field (mathematics); Feature (linguistics); Feature extraction; Similarity (geometry); Handwriting recognition; Set (abstract data type); Machine learning; Image (mathematics); Mathematics","score_opus":0.07734622065577988,"score_gpt":0.2713761186785971,"score_spread":0.19402989802281723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319073283","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":[0.4261492,0.000008304228,0.5706748,0.0013420801,0.00028733164,0.00023068277,0.000042026797,0.0011821869,0.00008343434],"genre_scores_gemma":[0.9847526,0.00004110544,0.011604285,0.0026142953,0.00033139525,0.00015529002,0.0004414158,0.00004223927,0.000017385868],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978153,0.00022197285,0.0003646464,0.0007237309,0.00043695074,0.0004373588],"domain_scores_gemma":[0.9989287,0.00016820843,0.00022581496,0.00044669368,0.00010936007,0.00012119483],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00025306502,0.000282483,0.00024544128,0.00048617512,0.00029121974,0.00044341607,0.00044603564,0.00016727991,0.000038541762],"category_scores_gemma":[0.000033463348,0.00029434968,0.00015188292,0.00064099755,0.000046065386,0.0010955905,0.00015976702,0.00034499637,0.00032972553],"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":[0.0000049354376,0.000032355438,0.00026675186,0.000023950082,0.000029726098,0.0000526485,0.00035356305,0.000041909272,0.32490867,0.000007859072,0.0007065689,0.67357105],"study_design_scores_gemma":[0.0007805509,0.000047880887,0.009819778,0.00037172643,0.000049595026,0.000035837988,0.00015735197,0.75335586,0.22096495,0.013426162,0.00016479043,0.0008255324],"about_ca_topic_score_codex":0.0001344853,"about_ca_topic_score_gemma":0.00004610614,"teacher_disagreement_score":0.75331396,"about_ca_system_score_codex":0.00015977725,"about_ca_system_score_gemma":0.000012034747,"threshold_uncertainty_score":0.9999509},"labels":[],"label_agreement":null},{"id":"W4320169013","doi":"10.1016/j.eswa.2023.119589","title":"A multi-task approach for contrastive learning of handwritten signature feature representations","year":2023,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":23,"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; Feature (linguistics); Signature (topology); Artificial intelligence; Task (project management); Feature learning; Feature vector; Pattern recognition (psychology); Class (philosophy); Natural language processing; Mathematics","score_opus":0.02154042704118518,"score_gpt":0.2913953367677581,"score_spread":0.2698549097265729,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4320169013","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":[0.000059842005,0.0004949109,0.994161,0.00044338574,0.000038113918,0.0029889967,0.00006007605,0.0010046888,0.0007489537],"genre_scores_gemma":[0.45221046,0.000050815892,0.52009344,0.000079944584,0.00016507096,0.02400238,0.00038842406,0.000044642115,0.002964812],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985111,0.000091562666,0.00029477407,0.00055840303,0.00026640922,0.00027777764],"domain_scores_gemma":[0.99829763,0.00029834438,0.0002479928,0.00055556674,0.00050014124,0.000100328194],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029113237,0.00017999583,0.0002941999,0.00025172965,0.00032601805,0.00011506783,0.0005651374,0.00014820849,0.0000013415112],"category_scores_gemma":[0.00006286416,0.00014992814,0.00008709138,0.0012015213,0.00008122001,0.0002597263,0.00007971079,0.00020796493,0.0000143728885],"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":[0.00023684252,0.0024674882,0.0034069738,0.0018597065,0.0015298376,0.00002434328,0.0414772,0.013843403,0.39751095,0.22489315,0.23353268,0.07921743],"study_design_scores_gemma":[0.0033402243,0.0004677033,0.0016778833,0.00034993314,0.00006380101,0.00010616835,0.008402649,0.8526298,0.027308097,0.0006742399,0.10386171,0.0011178334],"about_ca_topic_score_codex":0.00005531919,"about_ca_topic_score_gemma":0.000003055631,"teacher_disagreement_score":0.83878636,"about_ca_system_score_codex":0.000037067002,"about_ca_system_score_gemma":0.00007650384,"threshold_uncertainty_score":0.6113892},"labels":[],"label_agreement":null},{"id":"W4321205073","doi":"10.1016/j.knosys.2023.110365","title":"Synthesis of 3D on-air signatures with the Sigma–Lognormal model","year":2023,"lang":"en","type":"article","venue":"Knowledge-Based Systems","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Ministerio de Asuntos Económicos y Transformación Digital, Gobierno de España; European Commission; Fundación CajaCanarias","keywords":"Signature (topology); Handwriting; Computer science; Trajectory; Artificial intelligence; Pattern recognition (psychology); Algorithm; Data mining; Mathematics","score_opus":0.019518612986224485,"score_gpt":0.2481928081131983,"score_spread":0.22867419512697382,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321205073","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":[0.0069317752,0.00028415569,0.97192055,0.0007273487,0.00029779557,0.0008112514,0.00003914805,0.001517972,0.017469987],"genre_scores_gemma":[0.9961071,0.0000046768373,0.002427015,0.00012260926,0.00008929834,0.0004885947,0.0000050760796,0.00003103637,0.00072457566],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979935,0.00033531824,0.00035432825,0.00044986125,0.00048222847,0.0003847623],"domain_scores_gemma":[0.9972147,0.0012141927,0.00020292435,0.0009281313,0.00034683623,0.0000932398],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010352632,0.00025573745,0.0003636574,0.00039210945,0.00020014084,0.00009647726,0.0012396884,0.00014430581,0.0000059943327],"category_scores_gemma":[0.00010982075,0.00015778118,0.00011449029,0.0011702353,0.00013675123,0.00018002623,0.00012128443,0.00024097301,0.00007170008],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024388477,0.0010920488,0.00049484737,0.0018659413,0.0003920356,0.0001256088,0.0037811848,0.6775965,0.008167845,0.05745445,0.13812628,0.11065937],"study_design_scores_gemma":[0.00027285892,0.00021346436,0.00007233138,0.00049432187,0.000020763115,0.0000047875915,0.000082902196,0.9174084,0.07928635,0.00018153836,0.0016852239,0.00027704771],"about_ca_topic_score_codex":0.000024508658,"about_ca_topic_score_gemma":0.00002672642,"teacher_disagreement_score":0.9891753,"about_ca_system_score_codex":0.00005683008,"about_ca_system_score_gemma":0.00027103614,"threshold_uncertainty_score":0.64341295},"labels":[],"label_agreement":null},{"id":"W4321504878","doi":"10.1007/978-3-031-26284-5_35","title":"CCLSL: Combination of Contrastive Learning and Supervised Learning for Handwritten Mathematical Expression Recognition","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Handwritten Text Recognition Techniques","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":"Concordia University","funders":"","keywords":"Computer science; Artificial intelligence; Handwriting; Benchmark (surveying); Speech recognition; Pattern recognition (psychology); Robustness (evolution); Handwriting recognition; Deep learning; Feature extraction","score_opus":0.024780742021328704,"score_gpt":0.2660661685124395,"score_spread":0.24128542649111082,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321504878","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":[0.00059957546,0.000078659396,0.9969976,0.00021640155,0.00023804583,0.0008133671,0.000006774613,0.00040058303,0.00064901257],"genre_scores_gemma":[0.3250813,0.00020807706,0.6734229,0.00016967647,0.00019485793,0.00013199456,0.000074799675,0.000092006274,0.000624448],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99722636,0.00008770031,0.00060779444,0.0010088672,0.0006508047,0.0004184957],"domain_scores_gemma":[0.9965937,0.0019807445,0.0004050871,0.00029404834,0.0006108108,0.000115586605],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014493787,0.0003711275,0.0005960293,0.0008813412,0.00028951865,0.00028381697,0.0007412766,0.0003545794,0.00001560908],"category_scores_gemma":[0.00077497185,0.0003561524,0.000116576106,0.0003852628,0.00047230546,0.0005554433,0.00058667763,0.00072687556,0.000015139483],"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":[0.000020992135,0.000044098677,0.00004927264,0.00026370853,0.00001346841,0.000011523789,0.0011559927,0.00032444985,0.0049773697,0.0047374736,0.000009076704,0.9883926],"study_design_scores_gemma":[0.0007634997,0.0006378684,0.00005813952,0.0020646749,0.000016843389,0.000028323911,0.0000027553822,0.45998585,0.050531656,0.48534104,0.000080436366,0.00048889156],"about_ca_topic_score_codex":0.0000038127246,"about_ca_topic_score_gemma":0.000003723838,"teacher_disagreement_score":0.98790365,"about_ca_system_score_codex":0.00009673321,"about_ca_system_score_gemma":0.00014326499,"threshold_uncertainty_score":0.999889},"labels":[],"label_agreement":null},{"id":"W4323556845","doi":"10.3390/jimaging9030062","title":"DCTable: A Dilated CNN with Optimizing Anchors for Accurate Table Detection","year":2023,"lang":"en","type":"article","venue":"Journal of Imaging","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Discriminative model; Pooling; Table (database); Bilinear interpolation; Intersection (aeronautics); Pattern recognition (psychology); Field (mathematics); Region of interest; Interpolation (computer graphics); Computer vision; Machine learning; Data mining; Image (mathematics); Mathematics","score_opus":0.015259225514454557,"score_gpt":0.26511473710866784,"score_spread":0.2498555115942133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4323556845","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":[0.013346648,0.00007764238,0.98482466,0.000744418,0.00023911851,0.00014740578,0.0000014719162,0.0002799083,0.00033872513],"genre_scores_gemma":[0.731861,0.0000752135,0.26737168,0.00023519369,0.00016794889,0.000022707873,0.0000014331998,0.000026578504,0.00023827546],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99896026,0.00003519602,0.00033272186,0.00015767943,0.00023036716,0.000283783],"domain_scores_gemma":[0.99878824,0.00011845159,0.00037309332,0.00014979576,0.0004880183,0.00008242823],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00078298413,0.00010807012,0.00018427339,0.0004297282,0.00016022,0.00031640107,0.00035871193,0.00002621091,0.000005778149],"category_scores_gemma":[0.00011613872,0.000086626955,0.00006481546,0.0010336505,0.000020230753,0.0017453388,0.00006323436,0.00019023247,0.0000070283922],"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":[0.00015794346,0.00009141325,0.0009931828,0.00012932134,0.00016072478,0.00038079705,0.0010794874,0.003492919,0.19947806,0.00024805692,0.016164195,0.7776239],"study_design_scores_gemma":[0.0017799669,0.00045498545,0.0006208832,0.00064818654,0.00005343888,0.001207413,0.00029027945,0.49520212,0.4842923,0.004126535,0.01089089,0.00043299762],"about_ca_topic_score_codex":0.0000068104164,"about_ca_topic_score_gemma":0.0000019370004,"teacher_disagreement_score":0.7771909,"about_ca_system_score_codex":0.00006786976,"about_ca_system_score_gemma":0.0000961429,"threshold_uncertainty_score":0.35325447},"labels":[],"label_agreement":null},{"id":"W4353100306","doi":"10.18280/ts.400132","title":"Enhancing Marathi Handwritten Character Recognition Using Ensemble Learning","year":2023,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Marathi; Character recognition; Character (mathematics); Computer science; Artificial intelligence; Pattern recognition (psychology); Speech recognition; Natural language processing; Mathematics; Linguistics; Image (mathematics)","score_opus":0.038275313134606206,"score_gpt":0.2649709031932447,"score_spread":0.22669559005863849,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353100306","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":[0.35111475,0.000021107611,0.6453129,0.00032411,0.00019102651,0.00032375555,0.000004456242,0.0016388713,0.0010689821],"genre_scores_gemma":[0.955543,0.00004646881,0.0428991,0.0005556089,0.00036412277,0.000102539656,0.00008466188,0.000037936596,0.0003665889],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99781185,0.00019393807,0.00045840954,0.00052487163,0.00046888483,0.0005420693],"domain_scores_gemma":[0.99917245,0.00013598961,0.00017136359,0.00022293089,0.00016851944,0.00012877016],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010650095,0.0002326172,0.00023859955,0.00042443423,0.00033698184,0.00033775513,0.0004136155,0.00010906284,0.0003579119],"category_scores_gemma":[0.000042937514,0.00024316051,0.00012291054,0.0007820313,0.000033421882,0.0009484204,0.00019336844,0.000294874,0.000910114],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018591874,0.000090322,0.00033971525,0.000061728984,0.000049033642,0.000107237036,0.0012866607,0.000076312484,0.6032667,0.00039827335,0.0008813356,0.3934241],"study_design_scores_gemma":[0.0011621037,0.00041703533,0.0018974139,0.00045815328,0.000045975507,0.00011745849,0.00024082328,0.19669743,0.78496534,0.0074902396,0.0055186427,0.0009893957],"about_ca_topic_score_codex":0.00002080441,"about_ca_topic_score_gemma":0.0000055228707,"teacher_disagreement_score":0.60442823,"about_ca_system_score_codex":0.00009090507,"about_ca_system_score_gemma":0.0000627407,"threshold_uncertainty_score":0.9998678},"labels":[],"label_agreement":null},{"id":"W4360989194","doi":"10.18280/ria.370127","title":"Fusion of RNCNN-BRHA for Recognition of Telugu Word from Handwritten Text","year":2023,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Telugu; Natural language processing; Word (group theory); Computer science; Artificial intelligence; Speech recognition; Linguistics","score_opus":0.057490079880452793,"score_gpt":0.2890280730400477,"score_spread":0.2315379931595949,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4360989194","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":[0.16590856,0.00015601865,0.8305624,0.0005629333,0.00034258005,0.000692137,0.00012241055,0.00043050785,0.0012224569],"genre_scores_gemma":[0.9387633,0.00036841817,0.05962894,0.0000783816,0.00010209736,0.0001562007,0.00012212337,0.000027975371,0.0007525374],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99800277,0.000073455594,0.0008146545,0.000518446,0.00025992823,0.0003307322],"domain_scores_gemma":[0.997735,0.00069146545,0.0003466193,0.0006887562,0.00045405558,0.000084082676],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067498465,0.00018172285,0.0003742803,0.00039062076,0.00010533204,0.000047767684,0.00080119574,0.00014530765,0.00021065971],"category_scores_gemma":[0.00030440182,0.0001860092,0.00021638001,0.0012753897,0.00011421408,0.000330398,0.00022993553,0.00012682227,0.0004035478],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035052843,0.00014765958,0.000108638356,0.00012907232,0.000022503073,0.0000040218974,0.0012709104,0.00013017177,0.10518967,0.0012215952,0.0024587726,0.8892819],"study_design_scores_gemma":[0.00007959886,0.0002020995,0.00014369574,0.00035060814,0.000014940108,0.0000032499477,0.0003914091,0.10031235,0.8486221,0.04725814,0.0024142931,0.00020753563],"about_ca_topic_score_codex":0.00010063027,"about_ca_topic_score_gemma":0.00001732576,"teacher_disagreement_score":0.8890744,"about_ca_system_score_codex":0.00002803784,"about_ca_system_score_gemma":0.00005428059,"threshold_uncertainty_score":0.75852346},"labels":[],"label_agreement":null},{"id":"W4362513310","doi":"10.22215/etd/2023-15368","title":"Using Bipartite Matching and Detection Transformers for Document Layout Analysis Transfer Learning","year":2023,"lang":"en","type":"dissertation","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Transformer; Bipartite graph; Encoder; Artificial intelligence; Natural language processing; Task (project management); Information retrieval; Machine learning; Data mining; Engineering; Theoretical computer science","score_opus":0.02616294349052464,"score_gpt":0.31199102156919906,"score_spread":0.28582807807867444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362513310","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":[0.18978874,0.000037003636,0.80849016,0.00002389194,0.00017103564,0.0004592056,0.000003940423,0.00067431404,0.00035173676],"genre_scores_gemma":[0.961117,0.00018675602,0.03434704,0.00004449035,0.000051138657,0.0002633067,0.00027385226,0.00006028322,0.003656135],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983921,0.00006549293,0.00040353026,0.000570661,0.00026873153,0.0002994938],"domain_scores_gemma":[0.99948204,0.00010595624,0.000077910445,0.00012318016,0.00012478908,0.00008610761],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00049098546,0.00026048595,0.00038803968,0.000994026,0.0003083412,0.00037218095,0.0001811259,0.00024051718,0.000023982559],"category_scores_gemma":[0.000014141687,0.00025901012,0.00031197976,0.001014531,0.000012096316,0.0005105958,0.000012223756,0.00026477207,0.0000066072616],"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":[0.00007403139,0.000033328983,0.000079346966,0.0006725323,0.0015211337,0.000006166494,0.00995084,0.0013445151,0.034820322,0.0013618211,0.000011125685,0.95012486],"study_design_scores_gemma":[0.00140328,0.0006161957,0.0015208266,0.00063622795,0.0042623137,0.000016824257,0.0071094045,0.4514222,0.50677365,0.022509167,0.001186998,0.0025428897],"about_ca_topic_score_codex":0.00041395047,"about_ca_topic_score_gemma":0.0022748448,"teacher_disagreement_score":0.94758195,"about_ca_system_score_codex":0.000070585724,"about_ca_system_score_gemma":0.00004329365,"threshold_uncertainty_score":0.99998623},"labels":[],"label_agreement":null},{"id":"W4365790733","doi":"10.1007/978-981-99-1645-0_2","title":"ScriptNet: A Two Stream CNN for Script Identification in Camera-Based Document Images","year":2023,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","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":"Concordia University","funders":"","keywords":"Computer science; Scripting language; Artificial intelligence; Computer vision; Identification (biology); Perspective (graphical); Image (mathematics); Pattern recognition (psychology)","score_opus":0.04299313466075153,"score_gpt":0.3224235304960374,"score_spread":0.27943039583528584,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4365790733","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":[0.000035423116,0.0001721224,0.9643437,0.0021658824,0.00041171155,0.0014945611,0.00006200071,0.0003883324,0.03092623],"genre_scores_gemma":[0.10721684,0.0035535882,0.8758297,0.0040783607,0.00010857457,0.0016921653,0.0008346507,0.00006604403,0.0066200835],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99751705,0.000052970146,0.0011192902,0.0004594594,0.00052067125,0.00033057795],"domain_scores_gemma":[0.9962893,0.00033395176,0.0004922242,0.002130753,0.00065239245,0.00010136677],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002269477,0.0002743839,0.00031099716,0.0024288837,0.00039305762,0.0012171835,0.0034077289,0.0001269022,0.0000051378447],"category_scores_gemma":[0.00010443262,0.00029840367,0.00007326404,0.00083468395,0.000640025,0.00688125,0.0012403623,0.00037538513,0.00008644392],"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":[0.000004101661,0.000033733668,0.000038012677,0.000071917486,0.0000052195023,6.251363e-7,0.00089280226,0.0002058555,0.000035123878,0.39163175,0.0013070751,0.6057738],"study_design_scores_gemma":[0.0016139711,0.00018363567,0.0019116087,0.0010733391,0.000014881529,0.000013409547,0.000060746523,0.77985966,0.0014608869,0.13934503,0.07345845,0.0010043954],"about_ca_topic_score_codex":0.00005972996,"about_ca_topic_score_gemma":0.00006632105,"teacher_disagreement_score":0.7796538,"about_ca_system_score_codex":0.00030516903,"about_ca_system_score_gemma":0.000419252,"threshold_uncertainty_score":0.99994683},"labels":[],"label_agreement":null},{"id":"W4377927260","doi":"10.2352/issn.2168-3204.2005.2.1.art00037","title":"Joint Compression and Restoration of Documents with Bleed-through","year":2005,"lang":"en","type":"article","venue":"Archiving Conference","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"University of Ottawa","keywords":"Computer science; Bleed; Compression (physics); Joint (building); Segmentation; Inpainting; Artificial intelligence; Computer vision; Image (mathematics); Engineering; Medicine","score_opus":0.02762871088630275,"score_gpt":0.26340661916365643,"score_spread":0.23577790827735368,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4377927260","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":[0.16816789,0.000025006117,0.82459176,0.0007147567,0.000017270924,0.00013051857,0.0000012913287,0.00013280423,0.0062186974],"genre_scores_gemma":[0.7804348,0.000044659715,0.21935262,0.00007582755,0.000012324787,0.000009751488,0.000001786264,0.0000036001566,0.000064622625],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992291,0.00006391975,0.00018524603,0.00019883875,0.00019274709,0.00013015508],"domain_scores_gemma":[0.99941856,0.000058438305,0.00012087351,0.0002732751,0.000084821906,0.000044059878],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012927022,0.00009032362,0.00012831241,0.00006857439,0.00006996821,0.00008294941,0.00025251476,0.000021715296,0.000014170283],"category_scores_gemma":[0.000020625976,0.0000737153,0.000013936336,0.00009886266,0.000087522414,0.0007616013,0.00018507245,0.00009172766,0.0000068299823],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026096326,0.00016685024,0.0038806503,0.00009771501,0.000030378495,0.0000060210095,0.008864161,0.00002725292,0.11594183,0.1495287,0.00069020555,0.72074014],"study_design_scores_gemma":[0.001471281,0.0010013122,0.07664423,0.0020881684,0.000026618189,0.00010403348,0.0001497026,0.061808288,0.76981056,0.080546945,0.0055440017,0.00080486515],"about_ca_topic_score_codex":0.000056644265,"about_ca_topic_score_gemma":0.00002957695,"teacher_disagreement_score":0.7199353,"about_ca_system_score_codex":0.000012133488,"about_ca_system_score_gemma":0.000048790687,"threshold_uncertainty_score":0.3006023},"labels":[],"label_agreement":null},{"id":"W4378946015","doi":"10.48550/arxiv.2305.19181","title":"Table Detection for Visually Rich Document Images","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Mitacs","keywords":"Computer science; Information loss; Intersection (aeronautics); Artificial intelligence; Ground truth; Task (project management); Image (mathematics); Data mining; Table (database); Term (time); Pattern recognition (psychology)","score_opus":0.0660151355830532,"score_gpt":0.22560428153681067,"score_spread":0.15958914595375745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378946015","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":[0.017613081,0.000020646627,0.97800136,0.000119175726,0.00069981127,0.0008316864,0.000035599653,0.0018664487,0.0008121674],"genre_scores_gemma":[0.97638,0.00023508196,0.015500667,0.00008679225,0.00011365063,0.000032047254,0.000034272718,0.000039811126,0.0075776866],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99795735,0.000100230725,0.0002324802,0.0011930435,0.000109917695,0.00040698328],"domain_scores_gemma":[0.9981718,0.00017633164,0.0002556562,0.00090066734,0.00036715902,0.00012837187],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00047090708,0.00030073244,0.0003046046,0.00045404196,0.00022105801,0.0002773823,0.0014297261,0.00030131623,0.00002248066],"category_scores_gemma":[0.000071397655,0.00036577458,0.00020991817,0.00072489376,0.000056126322,0.00056889205,0.0016212256,0.00037421694,0.00019019774],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00070617633,0.0021075828,0.0056468705,0.004951077,0.002889802,0.0024789204,0.002303703,0.10241225,0.025350653,0.5447766,0.07296046,0.2334159],"study_design_scores_gemma":[0.0010496767,0.00042471656,0.0008573231,0.00028292992,0.00017024446,0.0000106389225,0.000083883344,0.20904188,0.1264472,0.65574443,0.004466816,0.0014202772],"about_ca_topic_score_codex":0.0001393238,"about_ca_topic_score_gemma":0.000061176484,"teacher_disagreement_score":0.9625007,"about_ca_system_score_codex":0.00023816281,"about_ca_system_score_gemma":0.0001580357,"threshold_uncertainty_score":0.9998794},"labels":[],"label_agreement":null},{"id":"W4379417306","doi":"10.14209/sbrt.2000.5250251","title":"Handwritten Numerical Characters Recognition Using Biorthogonal Spline Wavelets","year":2000,"lang":"pt","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Biorthogonal system; Wavelet; Spline (mechanical); Computer science; Artificial intelligence; Pattern recognition (psychology); Speech recognition; Wavelet transform; Structural engineering; Engineering","score_opus":0.04354780646438492,"score_gpt":0.2800802056233127,"score_spread":0.2365323991589278,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379417306","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":[0.49224323,0.00041130855,0.47972336,0.00436022,0.0012053021,0.0020447732,0.00021501447,0.0018485566,0.017948225],"genre_scores_gemma":[0.8674515,0.0004789417,0.11763776,0.005774887,0.0011164977,0.00011785888,0.0003584057,0.00013164479,0.006932494],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99489325,0.00044204746,0.0010773762,0.0013958794,0.0011072678,0.0010841775],"domain_scores_gemma":[0.99767965,0.00012831196,0.0002792465,0.00083522534,0.00054562517,0.0005319225],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0010584529,0.00065816334,0.0006689123,0.00045156028,0.00043273013,0.0006686325,0.0009233144,0.0004538555,0.023871148],"category_scores_gemma":[0.00006166256,0.0006681329,0.00039044203,0.001259305,0.00018305644,0.0015396759,0.00022544258,0.0006528439,0.0041194935],"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":[0.00005685502,0.0004317133,0.00016825598,0.00003540127,0.000074288866,0.000101326565,0.00025887342,0.0000044309254,0.0015019291,0.00005462119,0.0020975685,0.99521476],"study_design_scores_gemma":[0.0037450818,0.0010105637,0.0081802495,0.0012788512,0.00047211192,0.0019531928,0.00014122493,0.9009476,0.05394381,0.0038154994,0.02057875,0.003933078],"about_ca_topic_score_codex":0.00020292526,"about_ca_topic_score_gemma":0.000011460225,"teacher_disagreement_score":0.9912816,"about_ca_system_score_codex":0.00025554726,"about_ca_system_score_gemma":0.00033085523,"threshold_uncertainty_score":0.999577},"labels":[],"label_agreement":null},{"id":"W4381325436","doi":"10.1016/j.array.2023.100300","title":"ResneSt-Transformer: Joint attention segmentation-free for end-to-end handwriting paragraph recognition model","year":2023,"lang":"en","type":"article","venue":"Array","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Segmentation; Artificial intelligence; Transformer; End-to-end principle; Encoder; Paragraph; Speech recognition; Pattern recognition (psychology); Pipeline (software); Computer vision; Engineering","score_opus":0.04780665872640486,"score_gpt":0.28543027570357854,"score_spread":0.23762361697717369,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381325436","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":[0.039587766,0.000013931711,0.9535091,0.0025470366,0.00020929646,0.0010291032,0.000112142014,0.0013186599,0.0016729593],"genre_scores_gemma":[0.5202443,0.000101528356,0.4757597,0.0011233556,0.00015702272,0.0016016534,0.00042929233,0.000049069,0.0005340787],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99801147,0.00006141504,0.00047218322,0.00057912164,0.00039866465,0.00047716653],"domain_scores_gemma":[0.9988216,0.00014993675,0.0001212016,0.00048742868,0.00026676667,0.00015305172],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00089724653,0.0002043415,0.00021172802,0.00052967825,0.00034865987,0.00023365629,0.0005160399,0.00010075301,0.000032812648],"category_scores_gemma":[0.00015112672,0.0002162521,0.00019115883,0.00090447447,0.00003675311,0.0008996633,0.00006116915,0.00012737815,0.00027468053],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029207164,0.000094288174,0.00021899903,0.00013291895,0.000050984316,0.0000081272565,0.0015936238,0.00013156264,0.41578713,0.0034268731,0.013453503,0.5650728],"study_design_scores_gemma":[0.0016428672,0.00036959132,0.0012964312,0.00033158553,0.000046632238,0.000027710188,0.00043352472,0.05482692,0.6896188,0.24923371,0.0013619952,0.00081021315],"about_ca_topic_score_codex":0.00002736013,"about_ca_topic_score_gemma":0.00006013066,"teacher_disagreement_score":0.56426257,"about_ca_system_score_codex":0.000060934217,"about_ca_system_score_gemma":0.000058547073,"threshold_uncertainty_score":0.8818505},"labels":[],"label_agreement":null},{"id":"W4381512791","doi":"10.21203/rs.3.rs-3074040/v1","title":"Unpaired Document Image Denoising for OCR using BiLSTM enhanced CycleGAN","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"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; Artificial intelligence; Ground truth; Discriminator; Optical character recognition; Pattern recognition (psychology); Feature (linguistics); Image (mathematics); Deep learning; Noise (video); Focus (optics); Feature extraction; Noise reduction; Historical document","score_opus":0.13995329170356266,"score_gpt":0.4447921253720211,"score_spread":0.30483883366845843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381512791","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":[0.025885182,0.00019412048,0.9657147,0.0015035173,0.00053757295,0.0036310307,0.00009325225,0.0019506491,0.0004900026],"genre_scores_gemma":[0.5199343,0.00032607783,0.47497755,0.00008568206,0.00071327074,0.0022083607,0.00018038468,0.00020808479,0.0013663295],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.993758,0.00074201985,0.0006815551,0.0016525417,0.0017520542,0.0014138101],"domain_scores_gemma":[0.99490947,0.0009754283,0.00023079179,0.0018943211,0.0016543685,0.00033563233],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.004452779,0.00043363596,0.0005639119,0.001445458,0.0006569305,0.001958355,0.0026209939,0.000451046,0.000042699554],"category_scores_gemma":[0.00095206435,0.0004475178,0.00039018213,0.0011262111,0.00021015553,0.0006718519,0.0048391884,0.001403636,0.00016830006],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028380973,0.0009882961,0.00023237168,0.016019372,0.0007707805,0.00080614956,0.008965827,0.00092201825,0.45321757,0.01869612,0.03817338,0.4609243],"study_design_scores_gemma":[0.0007504065,0.00039706676,0.00023671235,0.004441256,0.000025776864,0.000014473119,0.00037076641,0.06854048,0.6366265,0.28547892,0.0019504224,0.0011672545],"about_ca_topic_score_codex":0.00046177398,"about_ca_topic_score_gemma":0.00005836444,"teacher_disagreement_score":0.4940491,"about_ca_system_score_codex":0.0009445296,"about_ca_system_score_gemma":0.00097250915,"threshold_uncertainty_score":0.99979764},"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":"W4385570873","doi":"10.18653/v1/2023.cawl-1.11","title":"Learning the Character Inventories of Undeciphered Scripts Using Unsupervised Deep Clustering","year":2023,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Scripting language; Computer science; Cluster analysis; Character (mathematics); Artificial intelligence; Exploit; Task (project management); Natural language processing; Set (abstract data type); Process (computing); Programming language","score_opus":0.05054510033694829,"score_gpt":0.2796570827119955,"score_spread":0.22911198237504724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385570873","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":[0.20993558,0.000025181042,0.78562576,0.0005678195,0.00029527053,0.00020008307,6.3841e-7,0.0010164786,0.0023331838],"genre_scores_gemma":[0.9670555,0.000026855905,0.031799592,0.0002735715,0.000060782022,0.000016840047,0.000003518652,0.000015820007,0.0007475133],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989062,0.00012131906,0.0002566277,0.00021787552,0.00025738,0.00024058681],"domain_scores_gemma":[0.9993007,0.00010928462,0.00009134813,0.00033448974,0.00011991154,0.000044225802],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048818343,0.000107361186,0.00014504971,0.00014068668,0.00017691351,0.00014867749,0.0006097225,0.000051968178,0.000075671276],"category_scores_gemma":[0.00008195469,0.00007819576,0.00006768367,0.00081472704,0.00006048529,0.0004715643,0.0004481676,0.00014248112,0.00005382967],"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":[0.000037691425,0.00014690364,0.014808565,0.00031345707,0.00021714054,0.00006730767,0.02648681,0.0020530547,0.25087517,0.030377436,0.001628267,0.6729882],"study_design_scores_gemma":[0.0002992024,0.00009193498,0.0041404227,0.00010667958,0.000010128548,0.00001840229,0.0009815263,0.9230104,0.0631175,0.005723071,0.002236048,0.00026464954],"about_ca_topic_score_codex":0.00007583745,"about_ca_topic_score_gemma":0.000029923223,"teacher_disagreement_score":0.9209574,"about_ca_system_score_codex":0.000029720446,"about_ca_system_score_gemma":0.000033938206,"threshold_uncertainty_score":0.31887302},"labels":[],"label_agreement":null},{"id":"W4385573344","doi":"10.18653/v1/2022.findings-emnlp.78","title":"Evaluating Token-Level and Passage-Level Dense Retrieval Models for Math Information Retrieval","year":2022,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":14,"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":"Natural Sciences and Engineering Research Council of Canada; Canada First Research Excellence Fund; Compute Canada","keywords":"Computer science; Encoder; Security token; Information retrieval; Domain (mathematical analysis); Human–computer information retrieval; Search engine; Data mining; Artificial intelligence; Mathematics","score_opus":0.10919309069085827,"score_gpt":0.3200185522246476,"score_spread":0.21082546153378934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385573344","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":[0.031163303,0.000032321066,0.9647413,0.0008184343,0.00017639852,0.00085851364,0.0001299807,0.00053533853,0.0015444151],"genre_scores_gemma":[0.4285254,0.000016587284,0.56867695,0.0016269273,0.000043198022,0.00012914602,0.000060925453,0.000016354707,0.0009045327],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979162,0.00013594833,0.000499186,0.0003474543,0.0007620888,0.00033908302],"domain_scores_gemma":[0.9986357,0.00028298647,0.00020951459,0.00039681725,0.00036702305,0.000107946435],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023481194,0.00017815192,0.00020231634,0.0002521288,0.0005634533,0.00034262292,0.000562309,0.000073685704,0.00005969408],"category_scores_gemma":[0.0003273138,0.00017944045,0.00007694145,0.0004863864,0.00003268014,0.0024112547,0.00073564984,0.00023063531,0.000012456887],"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":[0.0005622289,0.00019159883,0.000053707205,0.00020724349,0.00008562205,0.000010901982,0.005706125,0.0011650145,0.006332105,0.33382943,0.01411013,0.6377459],"study_design_scores_gemma":[0.000990193,0.00052629766,0.00012536261,0.000013530308,0.000014670192,0.000088512934,0.00022053329,0.91033983,0.011668026,0.07417664,0.001520972,0.00031541855],"about_ca_topic_score_codex":0.000017929804,"about_ca_topic_score_gemma":0.0000017562118,"teacher_disagreement_score":0.9091748,"about_ca_system_score_codex":0.0001488462,"about_ca_system_score_gemma":0.00017630451,"threshold_uncertainty_score":0.7317369},"labels":[],"label_agreement":null},{"id":"W4385595405","doi":"10.1145/3573128.3604901","title":"WEATHERGOV+","year":2023,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Automatic summarization; Computer science; Pipeline (software); Table (database); Information retrieval; Segmentation; Row; Information extraction; Artificial intelligence; Data mining; Natural language processing; Database","score_opus":0.021095614276608943,"score_gpt":0.2653373836700727,"score_spread":0.24424176939346376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385595405","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":[0.0020240955,0.0000045082047,0.8666742,0.0017355504,0.00008439782,0.000052950534,3.083557e-7,0.00478643,0.12463758],"genre_scores_gemma":[0.7328254,0.00006321378,0.22458623,0.00212841,0.00008308945,0.00007701018,0.0000039412525,0.000014916415,0.040217813],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995832,0.000012431975,0.000060193546,0.00012770154,0.00009731941,0.00011916553],"domain_scores_gemma":[0.99967855,0.000029343468,0.000009612449,0.00022630948,0.000023379363,0.00003281086],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00013326925,0.00003704294,0.00003867674,0.0000925083,0.00003290142,0.00005562674,0.00035407874,0.000020548994,0.00013497537],"category_scores_gemma":[0.000013788902,0.000031024232,0.000024315706,0.000507411,0.000008255032,0.00018836545,0.00012329356,0.000030274696,0.0044443496],"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":[3.0351194e-7,0.000014630438,0.00015193842,0.000003308709,0.0000046608043,0.000024802144,0.00015873867,7.6857685e-7,0.0025326833,0.24283001,0.13462551,0.6196526],"study_design_scores_gemma":[0.00035153763,0.00015256293,0.006043531,0.000025756173,0.00000255429,0.00004313753,0.00006721437,0.0542824,0.30462918,0.31662965,0.31720787,0.00056461873],"about_ca_topic_score_codex":0.0000054414404,"about_ca_topic_score_gemma":0.0000015536611,"teacher_disagreement_score":0.7308013,"about_ca_system_score_codex":0.000006015268,"about_ca_system_score_gemma":0.000010605306,"threshold_uncertainty_score":0.9963308},"labels":[],"label_agreement":null},{"id":"W4386067006","doi":"10.23919/mva57639.2023.10216107","title":"Outline Generation Transformer for Bilingual Scene Text Recognition","year":2023,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Transformer; Computer science; Natural language processing; Artificial intelligence; Benchmark (surveying); Speech recognition; Engineering","score_opus":0.07530413011409365,"score_gpt":0.30939131716321455,"score_spread":0.2340871870491209,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386067006","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":[0.023217611,0.000010729827,0.9697141,0.0020769325,0.00028221752,0.0005744975,0.000021507405,0.001933501,0.0021689073],"genre_scores_gemma":[0.3908196,0.00014693309,0.6012333,0.0018018263,0.0007438797,0.00052718126,0.00064925564,0.00004371796,0.004034312],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998917,0.0000307798,0.0002686667,0.00035137794,0.00017600834,0.00025619534],"domain_scores_gemma":[0.9993646,0.000084489555,0.000042375108,0.00021587963,0.00022742916,0.00006523582],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005035706,0.00011590747,0.00012038349,0.0002585037,0.0001348888,0.00013077627,0.00024609582,0.0000847607,0.00009560075],"category_scores_gemma":[0.000067185734,0.00010476971,0.000091422415,0.00057073904,0.000018725028,0.00050327403,0.00002180613,0.000063010964,0.00050331175],"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":[0.000004120922,0.00003577355,0.000007023493,0.0000140791535,0.000007782973,0.0000016083169,0.00017379793,0.0000024476074,0.038183004,0.0020097124,0.009233873,0.9503268],"study_design_scores_gemma":[0.00059391983,0.00023721083,0.00006234019,0.000019255605,0.000009486888,0.00001031688,0.00003798845,0.15827659,0.8110057,0.018742176,0.010709575,0.00029540178],"about_ca_topic_score_codex":0.000011426994,"about_ca_topic_score_gemma":0.000046988633,"teacher_disagreement_score":0.9500314,"about_ca_system_score_codex":0.000025775556,"about_ca_system_score_gemma":0.00007177134,"threshold_uncertainty_score":0.6469222},"labels":[],"label_agreement":null},{"id":"W4386102201","doi":"10.1016/j.patrec.2023.08.008","title":"Handwriting word spotting in the space of difference between representations using vision transformers","year":2023,"lang":"en","type":"article","venue":"Pattern Recognition Letters","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":3,"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":"Spotting; Computer science; Artificial intelligence; Word (group theory); Natural language processing; Handwriting; Keyword spotting; Vocabulary; Speech recognition; Transformer; Pattern recognition (psychology); Binary number; Representation (politics); Arithmetic; Mathematics; Linguistics","score_opus":0.057028123163070724,"score_gpt":0.316081109954259,"score_spread":0.25905298679118827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386102201","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":[0.58973193,0.0000050967956,0.40624386,0.00334976,0.00007016565,0.00028066558,0.000018783574,0.00017767167,0.00012207996],"genre_scores_gemma":[0.99022526,0.000026160871,0.0086172065,0.00088901125,0.00008944887,0.000062957595,0.00006849704,0.000017008475,0.000004429401],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99787974,0.00033365586,0.00053850166,0.00041418558,0.00045089284,0.00038301383],"domain_scores_gemma":[0.9986651,0.000697413,0.00021710488,0.0002926409,0.0000777845,0.00004995072],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009842163,0.00017482035,0.00023133328,0.0005765599,0.00017510969,0.00015685117,0.00054997165,0.0000679087,0.0000195195],"category_scores_gemma":[0.00009051304,0.00015562342,0.00011785582,0.0014618371,0.000083710314,0.00056667597,0.00008772562,0.00027762767,0.000046017245],"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":[0.0000035770324,0.000039468956,0.03644515,0.000088277935,0.000017691704,0.000036122023,0.0032541354,0.000022119099,0.044912536,0.000011835702,0.0002421146,0.91492695],"study_design_scores_gemma":[0.0026900496,0.000234047,0.6892096,0.0033272288,0.000122050544,0.000113744216,0.00495334,0.06014696,0.22962148,0.0077692396,0.00017235715,0.0016398942],"about_ca_topic_score_codex":0.00021832717,"about_ca_topic_score_gemma":0.000028089995,"teacher_disagreement_score":0.9132871,"about_ca_system_score_codex":0.000043609012,"about_ca_system_score_gemma":0.000020940051,"threshold_uncertainty_score":0.63461393},"labels":[],"label_agreement":null},{"id":"W4386175688","doi":"10.2139/ssrn.4552239","title":"Cclsl: Combination of Contrastive Learning and Supervised Learning for Handwritten Mathematical Expression Recognition","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":3,"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; Computer science; Natural language processing; Pattern recognition (psychology)","score_opus":0.02463675807018716,"score_gpt":0.280367409489311,"score_spread":0.2557306514191238,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386175688","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":[0.044529308,0.0005337974,0.95309037,0.0004800817,0.0001632803,0.00071052153,0.0000064823216,0.000376615,0.000109518405],"genre_scores_gemma":[0.9651918,0.005225197,0.028345322,0.000020197023,0.00017317594,0.00021450999,0.00011393279,0.00007603128,0.0006398492],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99665207,0.00042341693,0.0007150349,0.0005354276,0.00044340047,0.0012306607],"domain_scores_gemma":[0.997638,0.00068313046,0.00073971687,0.00017293505,0.0006602257,0.00010599803],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0037897397,0.00031137298,0.0005645543,0.00046421867,0.00033907333,0.0002636458,0.000501535,0.0003705286,0.0000107516835],"category_scores_gemma":[0.000969177,0.0003028728,0.0002244685,0.00018707143,0.000078507066,0.00038409393,0.000466916,0.0037377118,0.000011036979],"study_design_candidate":"theoretical_or_conceptual","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":[0.00031230916,0.000534436,0.0010041043,0.001261731,0.0006887774,0.000014408425,0.003590058,0.00016729673,0.021692231,0.05921913,0.00019679722,0.9113187],"study_design_scores_gemma":[0.0013969399,0.0009167537,0.00010436182,0.0012129261,0.00007339995,0.00014507835,0.00095723005,0.03856756,0.014169012,0.9420337,0.000049613805,0.0003734294],"about_ca_topic_score_codex":0.000010628346,"about_ca_topic_score_gemma":0.000010265436,"teacher_disagreement_score":0.9247451,"about_ca_system_score_codex":0.0003614024,"about_ca_system_score_gemma":0.0008195387,"threshold_uncertainty_score":0.99994236},"labels":[],"label_agreement":null},{"id":"W4386426921","doi":"10.1109/iccp56744.2023.10233729","title":"Message from the Chairs","year":2023,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Impartiality; Computer science; Graphics; Conflict of interest; Process (computing); Selection (genetic algorithm); Operations research; Computer graphics (images); Artificial intelligence","score_opus":0.022969384986272313,"score_gpt":0.2559919398220392,"score_spread":0.2330225548357669,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386426921","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":[0.010429699,0.000040292492,0.84887946,0.02117158,0.00029106537,0.00020880674,0.000011387922,0.0056858705,0.11328185],"genre_scores_gemma":[0.95036536,0.000085956955,0.034535803,0.0051103327,0.00015041165,0.00008414038,0.000014351742,0.000012662928,0.009640995],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9994375,0.000036948346,0.000079651785,0.00016792765,0.00014693364,0.00013100127],"domain_scores_gemma":[0.9993337,0.0001942589,0.000017281318,0.00040194727,0.00002363036,0.000029230154],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00021314489,0.00005153457,0.000050340444,0.000031574833,0.00008306863,0.00011262212,0.0007552086,0.000026050677,0.0002658717],"category_scores_gemma":[0.000029561312,0.000031146355,0.000034661636,0.00038632014,0.000021274684,0.00013344879,0.00025215873,0.000063059175,0.0016571381],"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":[7.009653e-7,0.000015418775,0.00043770336,0.00000153142,0.000013642948,0.000024931107,0.00086181593,7.3530543e-7,0.0015459365,0.0937572,0.50574684,0.39759356],"study_design_scores_gemma":[0.00041698347,0.00007543918,0.03275192,0.00004790703,0.000008142023,0.000010042249,0.00038320236,0.031167435,0.17273803,0.46273103,0.29910845,0.00056139973],"about_ca_topic_score_codex":0.00010387944,"about_ca_topic_score_gemma":0.000028103856,"teacher_disagreement_score":0.9399356,"about_ca_system_score_codex":0.0000064294513,"about_ca_system_score_gemma":0.000012723973,"threshold_uncertainty_score":0.9991202},"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":"W4386796870","doi":"10.23977/jeis.2023.080306","title":"Research on Residual Convolutional Neural Network for Handwritten Digit Recognition","year":2023,"lang":"en","type":"article","venue":"Journal of Electronics and Information Science","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Overfitting; Residual; Normalization (sociology); Convolutional neural network; Computer science; Pattern recognition (psychology); Artificial intelligence; Dropout (neural networks); Digit recognition; Artificial neural network; Generalization; Feature extraction; Neocognitron; Speech recognition; Deep learning; Time delay neural network; Machine learning; Algorithm; Mathematics","score_opus":0.057858371528431846,"score_gpt":0.3442764071075387,"score_spread":0.28641803557910683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386796870","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":[0.6706944,0.0003945342,0.30197513,0.016530598,0.0012956413,0.0012405608,0.00004834944,0.00037726713,0.007443506],"genre_scores_gemma":[0.98173416,0.0010278993,0.015638644,0.0011239719,0.00035162433,0.00003519872,0.000019981064,0.0000066034445,0.000061910076],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978352,0.000053180276,0.00048283252,0.00013393878,0.0009916999,0.00050310144],"domain_scores_gemma":[0.9971823,0.00039285675,0.00028626813,0.00014140151,0.001868886,0.00012826265],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0057441234,0.00007965123,0.00012640336,0.0010023536,0.00059582,0.00067065354,0.0006008265,0.00005147967,0.0000038713592],"category_scores_gemma":[0.000505772,0.00006677135,0.00004775776,0.0021349248,0.00019893062,0.0075280187,0.00011668241,0.00032765724,0.000028423465],"study_design_candidate":"theoretical_or_conceptual","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":[0.00016541222,0.00004955143,0.00010042817,0.000039051716,0.00001715425,0.0000036390843,0.0006209259,0.0011308338,0.0014729081,0.2786052,0.05866155,0.6591334],"study_design_scores_gemma":[0.0029123263,0.008254508,0.012701661,0.00037905967,0.000017355533,0.00053231465,0.00052688114,0.31586838,0.043491937,0.40456232,0.21002409,0.000729144],"about_ca_topic_score_codex":0.0000011435453,"about_ca_topic_score_gemma":9.2128e-7,"teacher_disagreement_score":0.65840423,"about_ca_system_score_codex":0.00012810841,"about_ca_system_score_gemma":0.0005889846,"threshold_uncertainty_score":0.6467127},"labels":[],"label_agreement":null},{"id":"W4386919255","doi":"10.1007/978-3-031-43849-3_28","title":"Detection of Redacted Text in Legal Documents","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"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":"Computer science; Redaction; Optical character recognition; Artificial intelligence; Discriminator; Segmentation; Character (mathematics); Grayscale; Task (project management); Pattern recognition (psychology); Image (mathematics); Natural language processing; Detector; Mathematics","score_opus":0.015662233439057552,"score_gpt":0.25739749116169647,"score_spread":0.24173525772263893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386919255","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":[0.0004484316,0.00006180276,0.99391514,0.00022396546,0.0010474365,0.0004540709,0.000006162853,0.00039621672,0.003446794],"genre_scores_gemma":[0.78957164,0.0001206116,0.20827949,0.0004939013,0.00024004577,0.000043304335,0.000008742227,0.00006832039,0.0011739217],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9964708,0.0000533164,0.0007418029,0.001225839,0.00097407267,0.00053413527],"domain_scores_gemma":[0.99787766,0.00035235623,0.00036778266,0.0010206915,0.00027723805,0.00010427462],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010540074,0.00039801517,0.0005308073,0.0022092953,0.00009082896,0.00029636195,0.002384204,0.000379371,0.000016584621],"category_scores_gemma":[0.00016128556,0.00039826546,0.000120104785,0.0015711429,0.00041741182,0.0009360622,0.0010603953,0.00081672927,0.000053433854],"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":[0.000006366131,0.000028840992,0.000035073554,0.000043176795,0.000006842232,0.00008871326,0.00022124442,0.00051209045,0.003351016,0.0041624154,0.000010873093,0.99153334],"study_design_scores_gemma":[0.00093178323,0.0007289239,0.001584632,0.0022870747,0.000013567249,0.00015148237,5.113486e-7,0.22954243,0.2293874,0.5319121,0.0018255903,0.001634546],"about_ca_topic_score_codex":0.00016032731,"about_ca_topic_score_gemma":0.00042436225,"teacher_disagreement_score":0.9898988,"about_ca_system_score_codex":0.00034134963,"about_ca_system_score_gemma":0.0003492032,"threshold_uncertainty_score":0.99984694},"labels":[],"label_agreement":null},{"id":"W4388195444","doi":"10.1016/j.knosys.2023.111080","title":"Table detection for visually rich document images","year":2023,"lang":"en","type":"article","venue":"Knowledge-Based Systems","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":12,"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 Ottawa","funders":"Mitacs","keywords":"Computer science; Information loss; Intersection (aeronautics); Artificial intelligence; Task (project management); Ground truth; Image (mathematics); Table (database); Data mining; Term (time); Pattern recognition (psychology)","score_opus":0.02134654737885951,"score_gpt":0.2956310126386067,"score_spread":0.2742844652597472,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388195444","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":[0.0032032793,0.00033725076,0.98745733,0.00014860061,0.0016385401,0.0012931179,0.0000189904,0.002923953,0.0029789142],"genre_scores_gemma":[0.98568255,0.0000116616075,0.006666718,0.000053524676,0.00034013926,0.002162946,0.000030480436,0.000041728283,0.005010253],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9980622,0.00018917894,0.00043279,0.00055709085,0.00027632993,0.00048244162],"domain_scores_gemma":[0.99826306,0.0003787233,0.00015245669,0.00055974745,0.0005190432,0.00012699295],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0013404208,0.00021878866,0.00028394215,0.0004920104,0.0002811883,0.0004445513,0.0006385573,0.00012671611,0.000010357048],"category_scores_gemma":[0.00013085309,0.00020990706,0.00011737824,0.0013913854,0.000031586966,0.00042887396,0.00011276759,0.00010876142,0.0008954201],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000110982146,0.0008898899,0.0009782126,0.0039846725,0.00026252313,0.00006520704,0.0018075507,0.00080023904,0.2678422,0.017481811,0.22338101,0.48239568],"study_design_scores_gemma":[0.0012873363,0.0005871277,0.00026166733,0.0003297681,0.000024445637,0.000014918546,0.00009080258,0.1708526,0.71634805,0.0023864508,0.107179284,0.0006375592],"about_ca_topic_score_codex":0.000039761704,"about_ca_topic_score_gemma":0.000026102785,"teacher_disagreement_score":0.9824793,"about_ca_system_score_codex":0.00014501589,"about_ca_system_score_gemma":0.00017862787,"threshold_uncertainty_score":0.9998825},"labels":[],"label_agreement":null},{"id":"W4389326172","doi":"10.48550/arxiv.2312.00699","title":"Rethinking Detection Based Table Structure Recognition for Visually Rich Document Images","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","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":"Mitacs","keywords":"Computer science; Cascade; Table (database); Artificial intelligence; Data mining; Pattern recognition (psychology); Task (project management); Limiting; Graph; Machine learning; Theoretical computer science","score_opus":0.07789674347453357,"score_gpt":0.22313215811789494,"score_spread":0.14523541464336137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389326172","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":[0.053740777,0.000014000335,0.94205487,0.00013198303,0.00079450087,0.0010442871,0.00015206206,0.001873511,0.00019401262],"genre_scores_gemma":[0.95258296,0.00007093441,0.04607049,0.00017188609,0.0001345178,0.000023411263,0.00023070314,0.00005050948,0.00066461915],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9974551,0.00020415754,0.0003093464,0.0014168785,0.00016944027,0.00044502868],"domain_scores_gemma":[0.99766326,0.000299432,0.00042931296,0.00086593354,0.0006128039,0.00012927229],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00059301476,0.00039109582,0.0003581325,0.00064177834,0.00034273748,0.00038239537,0.0011997749,0.000534824,0.000047776877],"category_scores_gemma":[0.00014942794,0.00047529244,0.00022878138,0.0008888745,0.00006260375,0.000711485,0.00086193625,0.0006731048,0.00004684857],"study_design_candidate":"theoretical_or_conceptual","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":[0.0016743927,0.0015393441,0.0040160427,0.008512159,0.002740549,0.0023195827,0.0049104732,0.24715519,0.064543806,0.054371703,0.02373191,0.5844849],"study_design_scores_gemma":[0.00063306245,0.0001744777,0.00019333293,0.00032103324,0.00011354997,0.0000044960298,0.000028331,0.21210109,0.1255027,0.6599958,0.00022982454,0.0007023055],"about_ca_topic_score_codex":0.000121774785,"about_ca_topic_score_gemma":0.00011726043,"teacher_disagreement_score":0.89884216,"about_ca_system_score_codex":0.0003519016,"about_ca_system_score_gemma":0.00023968668,"threshold_uncertainty_score":0.99976987},"labels":[],"label_agreement":null},{"id":"W4390431099","doi":"10.18280/ts.400623","title":"Offline Handwriting Signature Verification: A Transfer Learning and Feature Selection Approach","year":2023,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Signature (topology); Handwriting; Computer science; Feature selection; Transfer of learning; Artificial intelligence; Selection (genetic algorithm); Pattern recognition (psychology); Transfer (computing); Feature (linguistics); Speech recognition; Machine learning; Mathematics","score_opus":0.015335598063427066,"score_gpt":0.24243956707927725,"score_spread":0.22710396901585017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390431099","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":[0.04303976,0.00015273284,0.9515606,0.0013332139,0.000049322836,0.0004457997,0.000005101392,0.0018118162,0.0016016535],"genre_scores_gemma":[0.96831733,0.00007785606,0.030477036,0.0001896137,0.00018237902,0.0001263348,0.00007290878,0.000019139574,0.0005374105],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99856687,0.00012273357,0.00021313108,0.0004739313,0.00032893475,0.00029438228],"domain_scores_gemma":[0.9995802,0.00006974639,0.000043091048,0.00010407481,0.0001129919,0.000089885216],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005825079,0.00017747174,0.00016601305,0.00022972222,0.00029983703,0.00023440199,0.00023580906,0.00013655628,0.00005803642],"category_scores_gemma":[0.00001807389,0.00017288141,0.000060357157,0.00087995245,0.000037564536,0.0004166544,0.000051237974,0.00039686947,0.000020923453],"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":[0.00008359795,0.00036087722,0.0022836966,0.00039150324,0.00016544954,0.000041351763,0.0054034935,0.0011470317,0.28428736,0.02527605,0.011674108,0.66888547],"study_design_scores_gemma":[0.0024382207,0.0007767536,0.007606182,0.00021433928,0.000065299384,0.00020159436,0.00067624723,0.83442223,0.10753052,0.0022934226,0.042636734,0.0011384579],"about_ca_topic_score_codex":0.0000032226367,"about_ca_topic_score_gemma":0.0000013004384,"teacher_disagreement_score":0.92527753,"about_ca_system_score_codex":0.000032058084,"about_ca_system_score_gemma":0.00003043958,"threshold_uncertainty_score":0.7049899},"labels":[],"label_agreement":null},{"id":"W4390497405","doi":"10.36227/techrxiv.170422019.94163857/v1","title":"Handwritten Grapheme Classification in Bengali Language Using MobileNet","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Bengali; Grapheme; Natural language processing; Computer science; Artificial intelligence; Physics","score_opus":0.04186375217723469,"score_gpt":0.3187987265808951,"score_spread":0.2769349744036604,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390497405","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":[0.21737777,0.0029974156,0.74822,0.00159594,0.0014195116,0.0017588353,0.00006661585,0.003975501,0.022588415],"genre_scores_gemma":[0.8701391,0.00013541746,0.12856574,0.00025056666,0.00013483912,0.00025118218,0.000060704024,0.00004003378,0.00042239542],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99752575,0.00015175753,0.00056193525,0.0010409757,0.00037039767,0.0003491655],"domain_scores_gemma":[0.9984837,0.00006096217,0.00014829836,0.0011091743,0.000106057014,0.000091808],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005660742,0.0003417157,0.00036638812,0.0008962579,0.000047133304,0.0005809823,0.0012397239,0.00043640233,0.00008936135],"category_scores_gemma":[0.00003158278,0.00033115776,0.00017955247,0.0006712963,0.000052359283,0.0002130449,0.0021609298,0.001028873,0.00012287332],"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":[0.000014662655,0.0006527654,0.0018859714,0.0020666588,0.00023267318,0.0005784446,0.009015714,0.00022538038,0.07068294,0.13089249,0.011931141,0.77182114],"study_design_scores_gemma":[0.0004720614,0.00008682399,0.0031896136,0.0021791055,0.00007094879,0.0000796535,0.0006802749,0.5292248,0.08850217,0.37231082,0.0012556054,0.0019481115],"about_ca_topic_score_codex":0.00069593533,"about_ca_topic_score_gemma":0.00019222904,"teacher_disagreement_score":0.7698731,"about_ca_system_score_codex":0.00020559944,"about_ca_system_score_gemma":0.00016485514,"threshold_uncertainty_score":0.99991405},"labels":[],"label_agreement":null},{"id":"W4390576731","doi":"10.1109/access.2024.3349951","title":"Endmember Analysis of Overlapping Handwritten Text in Hyperspectral Document Images","year":2024,"lang":"en","type":"article","venue":"IEEE Access","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; Lakehead University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hyperspectral imaging; Endmember; Computer science; Artificial intelligence; Pattern recognition (psychology)","score_opus":0.02025845693047603,"score_gpt":0.31893351035305173,"score_spread":0.2986750534225757,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390576731","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":[0.41072598,0.0013812875,0.56557405,0.0014209779,0.0005503362,0.00043414612,0.000029416584,0.0009039069,0.018979914],"genre_scores_gemma":[0.9921812,0.00013172947,0.007206495,0.00015018001,0.000048114394,0.00004614567,0.0000043360437,0.000010328652,0.0002215079],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984761,0.000066703884,0.0003819016,0.00047844232,0.00032034455,0.00027649014],"domain_scores_gemma":[0.999214,0.00015245703,0.00006810128,0.00043140553,0.00007560896,0.000058433176],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038425485,0.00015122659,0.0003320096,0.0012597338,0.000031677057,0.00060001074,0.0010266008,0.00006702795,0.00017504019],"category_scores_gemma":[0.000020270016,0.00013913108,0.00019774144,0.0030260466,0.000049248796,0.001584791,0.00019371456,0.00017051173,0.000027622791],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003866867,0.00063059956,0.02244785,0.0006529106,0.0033999642,0.0010396462,0.0055228653,0.0013606435,0.1756431,0.049948853,0.017195346,0.72211957],"study_design_scores_gemma":[0.0005451056,0.000121136654,0.046054944,0.0005603753,0.00050737127,0.000030678864,0.00014144392,0.056159638,0.871323,0.021352174,0.0022754346,0.0009286976],"about_ca_topic_score_codex":0.00043394917,"about_ca_topic_score_gemma":0.00011532664,"teacher_disagreement_score":0.72119087,"about_ca_system_score_codex":0.00009871738,"about_ca_system_score_gemma":0.0000597134,"threshold_uncertainty_score":0.57859176},"labels":[],"label_agreement":null},{"id":"W4390666687","doi":"10.1007/s11042-023-17986-z","title":"Adaptive feature fusion for scene text script identification","year":2024,"lang":"en","type":"article","venue":"Multimedia Tools and Applications","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":5,"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 Natural Science Foundation of China","keywords":"Computer science; Pattern recognition (psychology); Pooling; Artificial intelligence; Scripting language; Channel (broadcasting); Identification (biology); Convolutional neural network; Feature (linguistics)","score_opus":0.028925940644272737,"score_gpt":0.28381885320641814,"score_spread":0.2548929125621454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390666687","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":[0.00018032447,0.0009993836,0.99339986,0.002704421,0.000121805795,0.0012468053,0.00015689273,0.0006304761,0.0005600272],"genre_scores_gemma":[0.2829027,0.00055189413,0.7049893,0.00044643818,0.00055744324,0.007298313,0.00035781454,0.000037005935,0.0028590837],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99907124,0.000017090064,0.00017312187,0.00045598432,0.00012431598,0.00015822107],"domain_scores_gemma":[0.9992243,0.0001993366,0.00004513406,0.00031337503,0.00013378977,0.00008403239],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019420926,0.000115649746,0.000102944454,0.00011539846,0.0002111207,0.0005115304,0.0002843966,0.00009146493,0.000011191005],"category_scores_gemma":[0.000026515694,0.000105139465,0.000056020603,0.00035043387,0.00005202555,0.000534158,0.0000828488,0.0001133085,0.00009926841],"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":[0.0000015906583,0.000028343948,0.0000046401924,0.00002925932,0.000008007667,4.1808423e-7,0.0001541674,3.57545e-7,0.012968196,0.025887944,0.008626506,0.9522906],"study_design_scores_gemma":[0.00035899645,0.00009066738,0.0020210443,0.00013940698,0.000043928972,0.000022949773,0.00010024933,0.37483826,0.06333608,0.04421978,0.5143711,0.00045751416],"about_ca_topic_score_codex":0.000005550487,"about_ca_topic_score_gemma":0.0000036079055,"teacher_disagreement_score":0.95183307,"about_ca_system_score_codex":0.000029550307,"about_ca_system_score_gemma":0.00004117813,"threshold_uncertainty_score":0.49326992},"labels":[],"label_agreement":null},{"id":"W4390872168","doi":"10.1109/iccv51070.2023.00060","title":"Handwritten and Printed Text Segmentation: A Signature Case Study","year":2023,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Thomson Reuters (Canada)","funders":"","keywords":"Computer science; Artificial intelligence; Segmentation; Digitization; Optical character recognition; Task (project management); Pattern recognition (psychology); Class (philosophy); Pixel; Natural language processing; Image segmentation; Process (computing); Image (mathematics); Computer vision","score_opus":0.0222050191988271,"score_gpt":0.29176005706374986,"score_spread":0.26955503786492274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390872168","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":[0.74326646,0.00004055442,0.24817209,0.0014231335,0.00012645515,0.0011393433,0.0000031734276,0.003427313,0.002401498],"genre_scores_gemma":[0.9743207,0.000011546711,0.023488726,0.0003523091,0.000026254282,0.00011851342,0.0000031946483,0.000009178828,0.0016695533],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989793,0.00007971592,0.0001772905,0.00037909838,0.00019850608,0.0001860913],"domain_scores_gemma":[0.9993782,0.00009434027,0.000038364098,0.00030621426,0.000093326686,0.000089554385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032088617,0.000119427976,0.00012089417,0.00022199616,0.0001529498,0.00023757515,0.00024266174,0.000053733504,0.00006882489],"category_scores_gemma":[0.000025875159,0.00010047633,0.000026292968,0.0007951109,0.0000266115,0.00040073667,0.00032111772,0.00012702047,0.00012893253],"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":[0.00001007704,0.00058693386,0.011907299,0.000059955404,0.00014231828,0.020279033,0.015914943,0.0000031369052,0.0067886272,0.0044446066,0.02783982,0.91202325],"study_design_scores_gemma":[0.02315441,0.0105031105,0.09196598,0.0005011155,0.00034382124,0.07213531,0.17937629,0.18253571,0.3613719,0.049737044,0.020121563,0.008253749],"about_ca_topic_score_codex":0.00009060317,"about_ca_topic_score_gemma":0.00008744019,"teacher_disagreement_score":0.9037695,"about_ca_system_score_codex":0.000016315413,"about_ca_system_score_gemma":0.000021454684,"threshold_uncertainty_score":0.40973058},"labels":[],"label_agreement":null},{"id":"W4391719216","doi":"10.21608/jocc.2024.339920","title":"Handwritten Arabic Bills Reader and Recognizer","year":2024,"lang":"en","type":"article","venue":"Journal of Computing and Communication","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Arabic; Computer science; Natural language processing; Speech recognition; Artificial intelligence; Linguistics; Philosophy","score_opus":0.017203293472413644,"score_gpt":0.282319251128827,"score_spread":0.2651159576564134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391719216","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":[0.26696503,0.020133434,0.7006154,0.009754895,0.00025270498,0.0001297888,8.149765e-7,0.00028433,0.0018636019],"genre_scores_gemma":[0.89470375,0.0022448362,0.10272108,0.00020995112,0.000060365914,8.5545497e-7,7.356405e-7,0.0000068889817,0.000051544852],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99909556,0.00016847799,0.00035947197,0.00012602453,0.00014730725,0.00010315837],"domain_scores_gemma":[0.9989322,0.000375735,0.00016251231,0.00027600047,0.0001862849,0.00006728626],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001118946,0.000086394284,0.00016066158,0.00021396142,0.0001295809,0.0004340113,0.0003927999,0.00005620657,0.0000030307249],"category_scores_gemma":[0.00006326967,0.00006929799,0.00004511684,0.00021821423,0.00006184983,0.0005184807,0.00021910587,0.00031242662,0.000004122754],"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":[0.000003531887,0.000025726704,0.00024926846,0.000045108885,0.000035652305,0.000008876251,0.0017959637,0.0000020422476,0.00073683367,0.0052845003,0.001779226,0.99003327],"study_design_scores_gemma":[0.0026530745,0.0017947453,0.039916337,0.011684291,0.0002838229,0.011880819,0.0014027657,0.4054271,0.02335966,0.39989567,0.099967524,0.0017341629],"about_ca_topic_score_codex":0.000006684993,"about_ca_topic_score_gemma":9.3881266e-7,"teacher_disagreement_score":0.98829913,"about_ca_system_score_codex":0.000018951487,"about_ca_system_score_gemma":0.000039672603,"threshold_uncertainty_score":0.4185181},"labels":[],"label_agreement":null},{"id":"W4391767333","doi":"10.1007/978-3-031-70543-4_11","title":"CATMuS Medieval: A Multilingual Large-Scale Cross-Century Dataset in Latin Script for Handwritten Text Recognition and Beyond","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Handwritten Text Recognition 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":"Canada Research Chairs; University of Toronto; Université de Montréal","funders":"","keywords":"Computer science; Natural language processing; Scale (ratio); Artificial intelligence; Speech recognition; Linguistics; Geography; Cartography; Philosophy","score_opus":0.02611180828481044,"score_gpt":0.294718516514478,"score_spread":0.2686067082296676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391767333","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":[0.0012441382,0.0017471083,0.990092,0.0006003507,0.0017374998,0.0014347499,0.002046551,0.00038625865,0.0007113343],"genre_scores_gemma":[0.06405623,0.00064068596,0.92566526,0.005287315,0.0011981779,0.00029951645,0.002222997,0.00018419047,0.00044563864],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9950483,0.0000438229,0.00086192304,0.0023212195,0.00080428383,0.00092044374],"domain_scores_gemma":[0.9975008,0.0006594488,0.0002596425,0.0010020403,0.00034177015,0.00023633847],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0018942846,0.0006666366,0.00069038244,0.0014097956,0.0002595646,0.0012802151,0.0018014032,0.00056163303,0.000027602133],"category_scores_gemma":[0.00023024438,0.0006397248,0.00013201019,0.0006695082,0.0007499844,0.0010046824,0.0015132622,0.0010714872,0.000064979955],"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":[0.000030149666,0.000096280746,0.0000834427,0.00030086015,0.000017957056,0.00015886125,0.0033401982,0.00006341883,0.0003252033,0.0010628868,0.0002706199,0.9942501],"study_design_scores_gemma":[0.00243153,0.0007074232,0.00024043082,0.002659553,0.000056458914,0.0002823597,0.000007714535,0.40127403,0.012135823,0.549844,0.028022846,0.002337826],"about_ca_topic_score_codex":0.000052742995,"about_ca_topic_score_gemma":0.00081724866,"teacher_disagreement_score":0.9919123,"about_ca_system_score_codex":0.00027195798,"about_ca_system_score_gemma":0.00038687678,"threshold_uncertainty_score":0.9997566},"labels":[],"label_agreement":null},{"id":"W4391767348","doi":"","title":"Do (colored) backgrounds matter? An experiment on artificially augmented ground truth for handwritten text recognition applied to historical manuscripts","year":2024,"lang":"en","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Colored; Ground truth; Computer science; Artificial intelligence; Natural language processing; Speech recognition; Pattern recognition (psychology); Sociology","score_opus":0.034066237190934406,"score_gpt":0.25908682834882174,"score_spread":0.22502059115788733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391767348","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":[0.04173371,0.00019608588,0.9212987,0.010369571,0.0006323973,0.0012085307,0.000043043252,0.0012185941,0.023299366],"genre_scores_gemma":[0.750468,0.000037401005,0.24256809,0.00089087605,0.00007950419,0.001209708,0.0003119383,0.00008141671,0.004353022],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9958003,0.0012114214,0.00063617027,0.0012844005,0.00054336706,0.0005243251],"domain_scores_gemma":[0.9960969,0.0009960664,0.00016280884,0.0014940356,0.0008958191,0.00035436964],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0032331517,0.0003690694,0.00034453976,0.0005156825,0.00044554024,0.0016897337,0.0013055402,0.00018723182,0.00020155958],"category_scores_gemma":[0.00022745162,0.0003856118,0.00018481725,0.00078943395,0.00007700463,0.0006222929,0.0003358661,0.0002756626,0.000529828],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000104623134,0.0014853087,0.00002203031,0.0001353067,0.00007939791,0.000014399466,0.008114287,0.000004419658,0.046292696,0.24682204,0.021244146,0.67568135],"study_design_scores_gemma":[0.0017602684,0.000059445276,0.0012163611,0.0023800964,0.00009369673,0.000057207693,0.00051189907,0.023310252,0.7375988,0.075360835,0.15560944,0.0020417348],"about_ca_topic_score_codex":0.00017801025,"about_ca_topic_score_gemma":0.00013685375,"teacher_disagreement_score":0.70873433,"about_ca_system_score_codex":0.00075853197,"about_ca_system_score_gemma":0.0001369314,"threshold_uncertainty_score":0.9998596},"labels":[],"label_agreement":null},{"id":"W4392200088","doi":"10.18280/isi.290102","title":"An Arabic OCR Approach Using Levenshtein Distance and CNNs","year":2024,"lang":"fr","type":"article","venue":"Ingénierie des systèmes d information","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Levenshtein distance; Arabic; Computer science; Natural language processing; Artificial intelligence; Edit distance; Pattern recognition (psychology); Information retrieval; Linguistics","score_opus":0.03419965796406964,"score_gpt":0.27121575923458624,"score_spread":0.2370161012705166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392200088","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":[0.02934629,0.006377574,0.9549117,0.00019182185,0.0009765766,0.0004922703,0.000090991445,0.00085054094,0.0067621986],"genre_scores_gemma":[0.85082084,0.0003076898,0.14796773,0.00020286451,0.00021067588,0.000056334175,0.00008660689,0.000025950987,0.0003213373],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976898,0.00024338145,0.0007770134,0.00038914435,0.00038112307,0.00051953766],"domain_scores_gemma":[0.998708,0.00009203769,0.0002094629,0.00046680408,0.00031322063,0.00021047571],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0011399331,0.0003400008,0.00030425118,0.00044456104,0.00040184753,0.0033980745,0.0004203674,0.00027010482,0.000038520775],"category_scores_gemma":[0.00011478075,0.00036246347,0.00009057855,0.00096895674,0.00043980067,0.018154163,0.00015060126,0.00035145204,0.00011103366],"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":[0.0000078694275,0.000046626155,0.00011193005,0.0023473646,0.000039957664,0.000018286713,0.016568158,0.0002729164,0.00030745837,0.11331688,0.0004989797,0.8664636],"study_design_scores_gemma":[0.00014371272,0.00015148107,0.00035668377,0.0015456903,0.000041668296,0.00067711074,0.0007359341,0.94426924,0.0018331902,0.032555148,0.017184958,0.0005051552],"about_ca_topic_score_codex":0.00023723586,"about_ca_topic_score_gemma":0.000010511305,"teacher_disagreement_score":0.94399637,"about_ca_system_score_codex":0.00048664588,"about_ca_system_score_gemma":0.00026237694,"threshold_uncertainty_score":0.99988276},"labels":[],"label_agreement":null},{"id":"W4392349752","doi":"10.18280/ts.410136","title":"Multiscale Residual Network for Recognizing Handwritten Malayalam Characters","year":2024,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Malayalam; Residual; Computer science; Artificial intelligence; Speech recognition; Pattern recognition (psychology); Natural language processing; Algorithm","score_opus":0.02190175803313322,"score_gpt":0.2589538386356497,"score_spread":0.23705208060251648,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392349752","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":[0.02026404,0.00043665053,0.9716314,0.0031749266,0.0007931463,0.001051288,0.00005071771,0.0017888627,0.0008089849],"genre_scores_gemma":[0.73437655,0.000086655426,0.25942785,0.0015513141,0.0021886548,0.0009210312,0.00013484356,0.00007737988,0.0012357151],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99783105,0.00008498523,0.00046752882,0.0006736408,0.00034472416,0.00059807504],"domain_scores_gemma":[0.9990704,0.0003281135,0.000076033764,0.00027318645,0.00010780604,0.00014445694],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00093999656,0.00025747434,0.0002492449,0.00018571677,0.00021262305,0.0006391206,0.00061518385,0.00011018931,0.00018068517],"category_scores_gemma":[0.000021270158,0.00024470355,0.00018278652,0.00037044872,0.00004969085,0.0007747978,0.00013799743,0.00020554084,0.00012674219],"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":[0.00005877187,0.00016121737,0.00038559036,0.00027170943,0.00020400142,0.0001038603,0.0011504156,0.00007898109,0.010459942,0.018356167,0.10010246,0.8686669],"study_design_scores_gemma":[0.0040458217,0.0022877262,0.00850207,0.0028791719,0.00028087696,0.00026361458,0.00016936618,0.4828316,0.12742585,0.057750676,0.31037587,0.0031873642],"about_ca_topic_score_codex":0.0000087711915,"about_ca_topic_score_gemma":0.0000068140253,"teacher_disagreement_score":0.8654795,"about_ca_system_score_codex":0.00007640749,"about_ca_system_score_gemma":0.000072104274,"threshold_uncertainty_score":0.9978721},"labels":[],"label_agreement":null},{"id":"W4392354286","doi":"10.18280/ria.380112","title":"Geometric Deep Learning for Enhancing Irregular Scene Text Detection","year":2024,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Artificial intelligence; Computer science; Deep learning; Computer vision; Pattern recognition (psychology)","score_opus":0.026521181951322394,"score_gpt":0.2749868986196983,"score_spread":0.24846571666837589,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392354286","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":[0.002582605,0.0018946736,0.99175763,0.00028690943,0.0006933074,0.0004301959,0.0000010113105,0.0012521709,0.0011014914],"genre_scores_gemma":[0.96090573,0.00020488158,0.03628967,0.00006272653,0.00020253449,0.00017829872,0.000005138211,0.000032731154,0.0021182664],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99810445,0.000068139685,0.00047574716,0.000694839,0.00020890584,0.000447907],"domain_scores_gemma":[0.9986763,0.0005123953,0.00008209728,0.00042759738,0.00019599251,0.00010559848],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00093333714,0.00019712762,0.00020550944,0.0007279847,0.00030711514,0.0005110421,0.00056685385,0.00012497015,0.000111763205],"category_scores_gemma":[0.00035487924,0.00020488659,0.00019269212,0.0021552672,0.00004706432,0.000608288,0.00013810887,0.00030714006,0.00080454635],"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":[0.0000030052463,0.000029113464,0.0000050390886,0.00013859356,0.000013298502,0.000010498569,0.0004437004,0.0017267717,0.03453856,0.0027247006,0.00007587678,0.96029085],"study_design_scores_gemma":[0.000010623032,0.00011875354,0.0000043352197,0.00011331481,0.0000071213913,0.00003602814,0.00009364428,0.49586418,0.48604137,0.003811233,0.013744656,0.00015472421],"about_ca_topic_score_codex":0.000013182695,"about_ca_topic_score_gemma":0.000025010282,"teacher_disagreement_score":0.9601361,"about_ca_system_score_codex":0.00012665841,"about_ca_system_score_gemma":0.00004157705,"threshold_uncertainty_score":0.9999734},"labels":[],"label_agreement":null},{"id":"W4392354806","doi":"10.18280/ria.380101","title":"Data Augmentation for Offline Arabic Handwritten Text Recognition Using Moving Least Squares","year":2024,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Handwriting; Artificial intelligence; Convolutional neural network; Task (project management); Deep learning; Handwriting recognition; Arabic; Generative grammar; Natural language processing; Artificial neural network; Speech recognition; Pattern recognition (psychology); Feature extraction; Linguistics","score_opus":0.13706602658994801,"score_gpt":0.34783476943274905,"score_spread":0.21076874284280103,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392354806","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":[0.0071677226,0.0008262543,0.98832417,0.00093997025,0.0006291625,0.00069289113,0.00017694829,0.0007493969,0.00049346517],"genre_scores_gemma":[0.6880793,0.00019612083,0.30944124,0.00029772214,0.00053721794,0.00016790003,0.00050957344,0.00006321055,0.00070768717],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99767786,0.00008108677,0.0006358535,0.0009644854,0.0002384463,0.00040229416],"domain_scores_gemma":[0.998172,0.00038616013,0.00012541826,0.0009741662,0.00024092449,0.00010131919],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00097259035,0.00023115415,0.00022887252,0.00035623257,0.0002742744,0.0006954953,0.0010998313,0.00011386993,0.00015119789],"category_scores_gemma":[0.00023698097,0.0002385077,0.000115946386,0.0007955873,0.00007422363,0.0013704101,0.00034453196,0.00020320473,0.00043376413],"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":[0.000014127932,0.00009629159,0.000011645563,0.00030747263,0.00003199192,0.000017794788,0.00065044966,0.0013075802,0.02049959,0.002366761,0.0018940239,0.9728023],"study_design_scores_gemma":[0.000040986837,0.00010163972,0.0000039397114,0.0005743853,0.000031031977,0.00006740992,0.00027489365,0.8839585,0.095112585,0.014100085,0.0054452578,0.00028926902],"about_ca_topic_score_codex":0.000048443588,"about_ca_topic_score_gemma":0.000026560641,"teacher_disagreement_score":0.972513,"about_ca_system_score_codex":0.00011225156,"about_ca_system_score_gemma":0.000109216395,"threshold_uncertainty_score":0.9726062},"labels":[],"label_agreement":null},{"id":"W4393154888","doi":"10.1609/aaai.v38i3.28021","title":"Rethinking Peculiar Images by Diffusion Models: Revealing Local Minima’s Role","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Korea Coast Guard; Korea Aerospace Industries; Korea Institute of Marine Science and Technology promotion","keywords":"Maxima and minima; Diffusion; Economic geography; Geography; Sociology; Physics; Mathematics; Mathematical analysis","score_opus":0.055439251804349,"score_gpt":0.28461566781915015,"score_spread":0.22917641601480115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393154888","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":[0.02970715,0.0004659916,0.93648297,0.006499167,0.0005261798,0.00059719355,0.000021577063,0.0009941818,0.024705572],"genre_scores_gemma":[0.98588794,0.00024034156,0.0130207455,0.0002629978,0.00007044265,0.0000464777,0.0000014681233,0.000025103407,0.00044450705],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9974411,0.000030744584,0.0006519598,0.00076230697,0.0007020099,0.00041184574],"domain_scores_gemma":[0.9986577,0.00013467642,0.00022472744,0.00032176464,0.00055279036,0.000108325105],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00080765865,0.00029613162,0.00029186328,0.00020362253,0.00024178109,0.0007788812,0.0020859253,0.00016337661,0.00005481941],"category_scores_gemma":[0.00018172472,0.00022710532,0.0001787369,0.00075457955,0.0003227441,0.0010782516,0.0006038226,0.00056586514,0.00009509661],"study_design_candidate":"theoretical_or_conceptual","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":[0.000016202073,0.000076597804,0.0000031696027,0.00008718601,0.0000125842635,0.0000017013746,0.0026297544,0.0000131177585,0.17500079,0.53008026,0.0017512132,0.2903274],"study_design_scores_gemma":[0.0000066310226,0.00006496165,0.0000011131946,0.0005482503,0.0000073111933,0.000005875055,0.0002662092,0.18477106,0.4364805,0.3775614,0.000143399,0.00014328498],"about_ca_topic_score_codex":0.00008308016,"about_ca_topic_score_gemma":0.0000042416723,"teacher_disagreement_score":0.95618075,"about_ca_system_score_codex":0.000090345064,"about_ca_system_score_gemma":0.00010956759,"threshold_uncertainty_score":0.9261086},"labels":[],"label_agreement":null},{"id":"W4394625706","doi":"10.1109/wacv57701.2024.00571","title":"TriCoLo: Trimodal Contrastive Loss for Text to Shape Retrieval","year":2024,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Natural language processing; Artificial intelligence; Information retrieval","score_opus":0.019878319967167806,"score_gpt":0.2940205061168919,"score_spread":0.2741421861497241,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394625706","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":[0.006014425,0.00010951883,0.9794732,0.0041505266,0.00042443987,0.000946657,0.000028773426,0.00159734,0.007255129],"genre_scores_gemma":[0.8405096,0.000011624276,0.15261681,0.0021604407,0.00021938584,0.00018428956,0.000005436899,0.000022320703,0.004270086],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998628,0.00003381224,0.00025232128,0.000530804,0.00022510748,0.0003299385],"domain_scores_gemma":[0.9988639,0.0005206241,0.000023452187,0.00023893072,0.00018997601,0.0001631409],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000440078,0.00015037094,0.0001931482,0.00027114572,0.00007677042,0.00043676462,0.00056657987,0.00009384749,0.00023101411],"category_scores_gemma":[0.00021502757,0.00012663403,0.00012931284,0.0008403217,0.000029930286,0.0004419542,0.00014432103,0.00011991731,0.00044880083],"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":[0.00011424722,0.00009759128,0.000012956637,0.000059790116,0.000050677572,0.00006426952,0.00050874613,9.716583e-7,0.007167829,0.1805132,0.076614045,0.7347957],"study_design_scores_gemma":[0.0015886186,0.002552345,0.00052179676,0.0002134474,0.000045488203,0.00012644324,0.00007189687,0.17114598,0.49904445,0.0769971,0.24660382,0.0010886226],"about_ca_topic_score_codex":0.0000065308027,"about_ca_topic_score_gemma":0.0000026972712,"teacher_disagreement_score":0.8344952,"about_ca_system_score_codex":0.00008770447,"about_ca_system_score_gemma":0.00015433518,"threshold_uncertainty_score":0.5768576},"labels":[],"label_agreement":null},{"id":"W4394725498","doi":"","title":"Manu McFrench, from zero to hero: impact of using a generic handwriting recognition model for smaller datasets","year":2023,"lang":"en","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Manu; HERO; Handwriting; Zero (linguistics); Computer science; Artificial intelligence; Speech recognition; Pattern recognition (psychology); Philosophy; Linguistics","score_opus":0.05508476712345512,"score_gpt":0.28675620901081617,"score_spread":0.23167144188736105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394725498","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":[0.23023783,0.00004782352,0.76703924,0.0006370777,0.000040703326,0.00041012323,0.00068805827,0.0003811071,0.00051805476],"genre_scores_gemma":[0.46103373,0.00005361414,0.5371878,0.00009534349,0.000013094786,0.000093520204,0.0012168293,0.000027982174,0.00027805867],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971874,0.00094508525,0.0005077438,0.00064125156,0.0003181675,0.00040038882],"domain_scores_gemma":[0.9960242,0.0009242203,0.00030569712,0.0012855771,0.0012667878,0.00019350229],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027169266,0.00022221351,0.00029042794,0.0003703685,0.0002759253,0.0002753757,0.0011544826,0.00011427277,0.000036523154],"category_scores_gemma":[0.0008563203,0.00023527481,0.00020272574,0.0010446043,0.00006609122,0.00050251366,0.0006431047,0.00013628422,0.000046420555],"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":[0.000041688738,0.000655462,0.00076311274,0.00013989594,0.00018493344,0.000009705559,0.011039711,0.0019805233,0.22023895,0.004973902,0.016748628,0.7432235],"study_design_scores_gemma":[0.00043766372,0.0000017234312,0.0005553731,0.00056404824,0.000018624169,0.0000050659132,0.000027451804,0.8148984,0.17049943,0.012453025,0.00024766463,0.00029158677],"about_ca_topic_score_codex":0.0012406383,"about_ca_topic_score_gemma":0.00033745202,"teacher_disagreement_score":0.8129178,"about_ca_system_score_codex":0.000109110675,"about_ca_system_score_gemma":0.00017171918,"threshold_uncertainty_score":0.9594228},"labels":[],"label_agreement":null},{"id":"W4394938787","doi":"10.5267/j.ijdns.2024.3.015","title":"Integrated multi-layer perceptron neural network and novel feature extraction for handwritten Arabic recognition","year":2024,"lang":"en","type":"article","venue":"International Journal of Data and Network Science","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Arabic; Artificial intelligence; Pattern recognition (psychology); Artificial neural network; Feature extraction; Perceptron; Layer (electronics); Feature (linguistics); Multilayer perceptron; Speech recognition; Natural language processing; Chemistry; Linguistics","score_opus":0.06953866044816313,"score_gpt":0.35132997630949425,"score_spread":0.2817913158613311,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394938787","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":[0.023177803,0.0013448416,0.97034204,0.0025613133,0.0022027686,0.00016943636,0.00008658333,0.00007650606,0.000038736365],"genre_scores_gemma":[0.51763207,0.0008740965,0.47939768,0.00049015856,0.0014430614,0.000008519457,0.00007147248,0.000011890886,0.000071016984],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99840164,0.000037383783,0.00034724316,0.0004666721,0.0004793381,0.00026770573],"domain_scores_gemma":[0.99854565,0.00024735695,0.00019433648,0.00021446103,0.00066543894,0.00013274068],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0017835471,0.00014535009,0.00016762319,0.00025846856,0.00020515178,0.0012685134,0.0013605492,0.000072748495,0.0000088578045],"category_scores_gemma":[0.00015324367,0.000114886774,0.000048166567,0.0004921102,0.00020098778,0.004824312,0.00040700316,0.00033873253,0.0000022787674],"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":[0.0000663333,0.000054287997,0.00026490382,0.000015837775,0.000058466056,0.000029954354,0.00015979611,0.00010314809,0.010201466,0.001007837,0.0138511155,0.97418684],"study_design_scores_gemma":[0.0007391282,0.00027951715,0.0045380606,0.00073679484,0.0000469137,0.0021403607,0.000067737965,0.9573744,0.00092902756,0.007032848,0.025827736,0.00028748353],"about_ca_topic_score_codex":0.000007760889,"about_ca_topic_score_gemma":0.000016494085,"teacher_disagreement_score":0.97389936,"about_ca_system_score_codex":0.00006409904,"about_ca_system_score_gemma":0.0001589115,"threshold_uncertainty_score":0.99976826},"labels":[],"label_agreement":null},{"id":"W4395111826","doi":"10.18280/ria.380215","title":"Decoded-ViT: A Vision Transformer Framework for Handwritten Digit String Recognition","year":2024,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Numerical digit; Transformer; Digit recognition; Computer science; Speech recognition; String (physics); Pattern recognition (psychology); Artificial intelligence; Arithmetic; Engineering; Electrical engineering; Voltage; Mathematics; Artificial neural network","score_opus":0.04628354131278729,"score_gpt":0.31820659161874615,"score_spread":0.27192305030595887,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395111826","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":[0.0028978428,0.0006200903,0.989725,0.0018755614,0.0006791578,0.00078765175,0.000038069273,0.0012167676,0.002159869],"genre_scores_gemma":[0.74903184,0.0005054482,0.24827643,0.00034769654,0.00032441414,0.00043190576,0.00004661821,0.00006155963,0.0009740613],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9976927,0.000048955717,0.0006299,0.0008437173,0.00025185887,0.0005328597],"domain_scores_gemma":[0.99827075,0.00074368727,0.00007579662,0.00055575557,0.00019846545,0.00015556217],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00058603886,0.00027096612,0.00027257454,0.00035186965,0.00025236612,0.000901461,0.00071691757,0.00022297121,0.00019628963],"category_scores_gemma":[0.00019657792,0.0002661154,0.0002931336,0.0009179929,0.000071776914,0.001219978,0.00007215433,0.00035341448,0.0009310281],"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":[0.000012505179,0.00008047395,0.0000038480093,0.00020304181,0.000021889562,0.000016097902,0.0009226763,0.0000699734,0.0032519652,0.047595426,0.0009367423,0.94688535],"study_design_scores_gemma":[0.00003411454,0.00026644816,0.0000027125793,0.0011186465,0.000019549372,0.00005118858,0.00012840376,0.16388625,0.4896695,0.32072884,0.023724182,0.00037018457],"about_ca_topic_score_codex":0.0000108325885,"about_ca_topic_score_gemma":0.000008954745,"teacher_disagreement_score":0.9465152,"about_ca_system_score_codex":0.00009416851,"about_ca_system_score_gemma":0.00007410409,"threshold_uncertainty_score":0.9999791},"labels":[],"label_agreement":null},{"id":"W4395463230","doi":"10.18280/isi.290223","title":"Automatic Hindi OCR Error Correction Using MLM-BERT","year":2024,"lang":"fr","type":"article","venue":"Ingénierie des systèmes d information","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Hindi; Computer science; Natural language processing; Artificial intelligence; Error detection and correction; Speech recognition; Algorithm","score_opus":0.03190194894866177,"score_gpt":0.2796448416792766,"score_spread":0.24774289273061484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395463230","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":[0.044074044,0.00290545,0.9175894,0.0006378423,0.016082035,0.00088794524,0.00005046299,0.0029696964,0.014803124],"genre_scores_gemma":[0.9133214,0.00024230157,0.081346765,0.00064641406,0.0006093681,0.00014995475,0.00011027841,0.00006330856,0.0035102563],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99675363,0.0002509498,0.0012938958,0.00037487014,0.00062742643,0.00069920975],"domain_scores_gemma":[0.9980889,0.0002600425,0.00040497788,0.0005070292,0.00053790474,0.0002011674],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0011665737,0.00044524166,0.00039840725,0.000953974,0.00054147333,0.0034332683,0.00052837713,0.00042384624,0.0006139953],"category_scores_gemma":[0.0004570203,0.00048605746,0.00023476036,0.0017971591,0.0002978144,0.018053219,0.00023693986,0.00052152865,0.0021980105],"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":[0.000005167451,0.00003680101,0.00005521537,0.0019793417,0.00007934819,0.000031283573,0.014822464,0.0002179181,0.00018546372,0.0074882437,0.012213752,0.962885],"study_design_scores_gemma":[0.00016715076,0.00017065897,0.00042358052,0.004462497,0.000084830855,0.0013569129,0.0005131741,0.934254,0.0051754545,0.0151254395,0.037707835,0.0005584824],"about_ca_topic_score_codex":0.0007523104,"about_ca_topic_score_gemma":0.000029214889,"teacher_disagreement_score":0.9623265,"about_ca_system_score_codex":0.0016012149,"about_ca_system_score_gemma":0.0006389933,"threshold_uncertainty_score":0.99975914},"labels":[],"label_agreement":null},{"id":"W4398407432","doi":"10.7910/dvn/fmzyfp/wultea","title":"trainset.tab","year":2018,"lang":"en","type":"dataset","venue":"Harvard Dataverse","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Library science; Engineering; Computer science","score_opus":0.01938621640855836,"score_gpt":0.25600003960638107,"score_spread":0.2366138231978227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398407432","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[7.8760223e-7,7.938202e-7,0.027468378,0.000014439253,0.0009860094,0.00032316352,0.9700757,0.0006116602,0.0005190257],"genre_scores_gemma":[0.0000013056991,0.00024554026,0.024746029,0.0012806285,0.0006843945,0.00006904408,0.97269636,0.000021352249,0.00025537045],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973466,0.00015386743,0.0004403054,0.00096781045,0.000579154,0.00051228056],"domain_scores_gemma":[0.99584734,0.00009004625,0.00027104063,0.0033745826,0.00018281155,0.00023415075],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005081531,0.00043860805,0.00043116722,0.00040339178,0.0001671084,0.0004637752,0.0039138934,0.00043588787,0.012863181],"category_scores_gemma":[0.00021407692,0.00043620504,0.00017153057,0.00039384392,0.00018198624,0.00097061816,0.0014408046,0.0004904377,0.24154136],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000037898712,0.000066280016,1.4346561e-7,0.000048466565,0.000031837353,0.00012740713,0.000015891985,1.4965924e-8,0.00001117235,0.00011739897,0.9953531,0.004224467],"study_design_scores_gemma":[0.00023136513,0.000111772664,0.0000033102826,0.00010837112,0.000035755205,0.00007895774,0.0000034368175,0.000056641402,0.00041503238,0.00076738535,0.9976652,0.00052275206],"about_ca_topic_score_codex":0.00016919896,"about_ca_topic_score_gemma":0.000092773225,"teacher_disagreement_score":0.22867818,"about_ca_system_score_codex":0.000093485534,"about_ca_system_score_gemma":0.00026951174,"threshold_uncertainty_score":0.99980897},"labels":[],"label_agreement":null},{"id":"W4399076880","doi":"10.2139/ssrn.4845684","title":"Detection of Title Blocks in Construction Documents Using Faster R-Cnn","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","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":"University of Alberta","funders":"","keywords":"Computer science; Information retrieval; Natural language processing; Artificial intelligence","score_opus":0.011166445719621278,"score_gpt":0.2669961562554379,"score_spread":0.2558297105358166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399076880","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":[0.10351514,0.0019456422,0.88712597,0.00010224332,0.0015657938,0.00020506654,0.0000024215,0.00013016988,0.005407542],"genre_scores_gemma":[0.99261457,0.00074371364,0.005964048,0.000010882597,0.00013738514,0.0000048261336,9.363039e-7,0.000013516798,0.00051015173],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988188,0.000053952153,0.0002740989,0.00019691189,0.00017909924,0.00047714205],"domain_scores_gemma":[0.99957335,0.000008916874,0.00016743298,0.00016096975,0.00006676632,0.000022547341],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058854907,0.00010799066,0.00014559863,0.00037540632,0.000025479763,0.0000898942,0.000279484,0.00014462201,0.000035408226],"category_scores_gemma":[0.000010146149,0.00010574063,0.00008528579,0.00017036476,0.000022978842,0.00009671783,0.00026886916,0.0019457716,0.000038864528],"study_design_candidate":"theoretical_or_conceptual","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":[0.000008145147,0.000040091865,0.00012281432,0.00008194247,0.00013533198,0.000010528138,0.00016197188,0.000048428752,0.0063265036,0.018475005,0.000062212675,0.974527],"study_design_scores_gemma":[0.0001204727,0.00006414816,0.000014911055,0.00028361002,0.000022632554,0.000554898,0.000051629442,0.0053138956,0.018481314,0.9745958,0.0003418528,0.00015487295],"about_ca_topic_score_codex":0.000054378692,"about_ca_topic_score_gemma":0.00006858553,"teacher_disagreement_score":0.97437215,"about_ca_system_score_codex":0.000703038,"about_ca_system_score_gemma":0.0009371631,"threshold_uncertainty_score":0.84535176},"labels":[],"label_agreement":null},{"id":"W4399691237","doi":"10.36948/ijfmr.2024.v06i03.22574","title":"Bangla Handwritten Character Recognition Using Deep Learning Approaches and its Explainability With AI","year":2024,"lang":"en","type":"article","venue":"International Journal For Multidisciplinary Research","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Bengali; Computer science; Artificial intelligence; Character (mathematics); Character recognition; Natural language processing; Deep learning; Speech recognition; Task (project management); Optical character recognition; Pattern recognition (psychology); Identification (biology); Intelligent word recognition; Intelligent character recognition; Image (mathematics); Mathematics","score_opus":0.16687900536806075,"score_gpt":0.4156233720436505,"score_spread":0.24874436667558977,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399691237","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":[0.43248266,0.0009580915,0.55633634,0.008051299,0.00070721324,0.00080651895,0.000027615315,0.00028797355,0.00034226847],"genre_scores_gemma":[0.959125,0.00018358688,0.039243832,0.00003772106,0.00070071,0.00017246853,0.000039015416,0.000037574446,0.00046009966],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99730366,0.00034066907,0.0003621195,0.0005743368,0.0009640898,0.00045514366],"domain_scores_gemma":[0.9974176,0.0006089242,0.00007920849,0.00014732791,0.0015509084,0.00019602281],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0031027873,0.00018476031,0.0001766599,0.0008444399,0.0007239824,0.0016772129,0.000725312,0.0001132544,0.000036300095],"category_scores_gemma":[0.00026605086,0.00014754757,0.00010663455,0.00038347204,0.00012522315,0.00236639,0.0005256261,0.0011302478,0.00002453895],"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":[0.00068380893,0.00041878814,0.002001771,0.0003536661,0.00043928402,0.00090404623,0.007031966,0.00016591646,0.00947975,0.0038406136,0.00042723567,0.9742532],"study_design_scores_gemma":[0.0008886208,0.0007960493,0.0014049939,0.0008580748,0.000019176176,0.0031941007,0.0007714563,0.94947577,0.010752918,0.027943874,0.0034959516,0.00039903546],"about_ca_topic_score_codex":0.000008782871,"about_ca_topic_score_gemma":0.000007813813,"teacher_disagreement_score":0.9738541,"about_ca_system_score_codex":0.0003122219,"about_ca_system_score_gemma":0.00022453384,"threshold_uncertainty_score":0.99935913},"labels":[],"label_agreement":null},{"id":"W4401108511","doi":"10.1007/s11263-024-02189-2","title":"Equiangular Basis Vectors: A Novel Paradigm for Classification Tasks","year":2024,"lang":"en","type":"article","venue":"International Journal of Computer Vision","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":3,"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 Toronto","funders":"","keywords":"Basis (linear algebra); Pattern recognition (psychology); Artificial intelligence; Equiangular polygon; Computer science; Mathematics; Algorithm; Geometry","score_opus":0.03135268334370116,"score_gpt":0.33596852755806383,"score_spread":0.30461584421436266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401108511","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":[0.0026504318,0.00027096845,0.9866129,0.0066211545,0.0034181285,0.00014470002,0.000013880309,0.0001571622,0.000110631176],"genre_scores_gemma":[0.646295,0.000057141107,0.35167181,0.00049295457,0.001405674,0.000011546434,0.000011462973,0.000016402886,0.00003800779],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99835545,0.000039413288,0.0005682559,0.0002572927,0.00063058495,0.00014899466],"domain_scores_gemma":[0.9985491,0.00028581292,0.00024322826,0.00019274828,0.0006404135,0.00008869967],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006354481,0.00013554792,0.00017424132,0.0005972832,0.00004374733,0.0007826297,0.0012267235,0.00007808799,0.000019617619],"category_scores_gemma":[0.00004056451,0.0001155303,0.00026258882,0.00021507355,0.000027939903,0.0012900257,0.00015078805,0.00018058342,0.000025550962],"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":[0.000044873887,0.00019319187,0.00001858503,0.00002949834,0.00019185073,0.00008817569,0.00032169634,0.00006093433,0.018232442,0.080602564,0.017958207,0.882258],"study_design_scores_gemma":[0.0008750088,0.00095302076,0.0013464658,0.0010066406,0.000029434816,0.0011046282,0.000007776416,0.7544744,0.016889628,0.04300895,0.18000533,0.0002987191],"about_ca_topic_score_codex":0.0000024411088,"about_ca_topic_score_gemma":4.7016556e-7,"teacher_disagreement_score":0.88195926,"about_ca_system_score_codex":0.0001575037,"about_ca_system_score_gemma":0.00012849875,"threshold_uncertainty_score":0.7546916},"labels":[],"label_agreement":null},{"id":"W4401143497","doi":"10.18280/mmep.110706","title":"Modified ResUNet Architecture for Binarization in Degraded Javanese Ancient Manuscript","year":2024,"lang":"en","type":"article","venue":"Mathematical Modelling and Engineering Problems","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Architecture; Computer science; Artificial intelligence; Art; Natural language processing; History; Visual arts","score_opus":0.03362391758525728,"score_gpt":0.23389325049861767,"score_spread":0.20026933291336038,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401143497","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":[0.0082099885,0.00053557777,0.98961186,0.00043626514,0.0000784245,0.00039541913,0.0000023908765,0.00064726453,0.0000828161],"genre_scores_gemma":[0.63927567,0.000030417461,0.36037531,0.00002283366,0.000021440157,0.0001922979,0.000004408683,0.000020054487,0.000057555397],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990164,0.00001130567,0.00026588986,0.0003224312,0.00012897479,0.00025497147],"domain_scores_gemma":[0.99960196,0.00011568737,0.00001617694,0.00017219706,0.000024871752,0.00006909283],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038452033,0.00014371314,0.0001664562,0.00024826673,0.000033408665,0.00022919623,0.00016820185,0.00008480686,6.9884845e-7],"category_scores_gemma":[0.000033754648,0.00012351105,0.000041636882,0.00027322094,0.000013512505,0.00016093958,0.000046764304,0.00016411392,0.0000037474358],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000031989057,0.0000520085,7.2928395e-7,0.0021759667,0.000011532782,0.000008615713,0.002649506,0.7775568,0.0029129474,0.20500675,0.000054073716,0.0095679015],"study_design_scores_gemma":[0.00009094442,0.000035499874,0.0000013175788,0.000596622,0.0000039154456,0.000016837777,0.0000028364163,0.82426554,0.00045935923,0.17393243,0.00046565608,0.00012902168],"about_ca_topic_score_codex":0.000004215955,"about_ca_topic_score_gemma":5.1315226e-7,"teacher_disagreement_score":0.63106567,"about_ca_system_score_codex":0.000027841423,"about_ca_system_score_gemma":0.000012184053,"threshold_uncertainty_score":0.5036634},"labels":[],"label_agreement":null},{"id":"W4401387595","doi":"10.1109/ickecs61492.2024.10617274","title":"Automated Text Extraction and Classification from Images using Multi-Layer Perceptron(MLP)","year":2024,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Horizon College and Seminary","funders":"","keywords":"Computer science; Perceptron; Artificial intelligence; Layer (electronics); Extraction (chemistry); Pattern recognition (psychology); Feature extraction; Multilayer perceptron; Artificial neural network; Chromatography; Materials science; Chemistry","score_opus":0.0646416139702009,"score_gpt":0.34702969670619344,"score_spread":0.28238808273599253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401387595","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":[0.06723317,0.0002537662,0.9259516,0.0004545238,0.00020430051,0.00015635788,0.00000768638,0.00463588,0.001102737],"genre_scores_gemma":[0.60995287,0.00004804259,0.3895321,0.00007733908,0.00004129657,0.00001276825,0.000008555594,0.00001051711,0.00031651874],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99895746,0.0000655506,0.0002014106,0.00046406555,0.00015519376,0.00015632529],"domain_scores_gemma":[0.99947923,0.000091716516,0.00003867025,0.00025200917,0.00007237364,0.00006597907],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016386899,0.00012993538,0.00010438332,0.0001794465,0.00010089502,0.00065653375,0.0001823182,0.00009772714,0.00018943092],"category_scores_gemma":[0.000020545598,0.00011524779,0.000039047765,0.00025367492,0.000041894746,0.0013527271,0.00008472589,0.00013896213,0.00022779978],"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":[0.0000014804278,0.000043312713,0.00018713014,0.000016847143,0.000017456656,0.000012238025,0.00032132812,0.0000012209213,0.7043439,0.0014292687,0.0024532408,0.29117256],"study_design_scores_gemma":[0.00009574006,0.000017114444,0.024754925,0.000056753535,0.000013067742,0.000034149125,0.00006313453,0.91939366,0.05318277,0.0011021269,0.0011134151,0.00017314928],"about_ca_topic_score_codex":0.00020831011,"about_ca_topic_score_gemma":0.00001215198,"teacher_disagreement_score":0.9193924,"about_ca_system_score_codex":0.000076169774,"about_ca_system_score_gemma":0.00004083163,"threshold_uncertainty_score":0.63309705},"labels":[],"label_agreement":null},{"id":"W4402135519","doi":"10.1007/978-3-031-70536-6_14","title":"Robust Handwritten Signature Representation with Continual Learning of Synthetic Data over Predefined Real Feature Space","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","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":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"","keywords":"Computer science; Artificial intelligence; Representation (politics); Pattern recognition (psychology); Signature (topology); Feature vector; Feature (linguistics); Feature learning; Space (punctuation); Speech recognition; Machine learning","score_opus":0.024408456933704168,"score_gpt":0.2628783702655003,"score_spread":0.23846991333179615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402135519","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":[0.00013322254,0.00057299115,0.9877276,0.001197611,0.00052242115,0.0006512257,0.000055175835,0.0005121984,0.008627561],"genre_scores_gemma":[0.2334426,0.00032170158,0.7577467,0.00034118403,0.0006183876,0.000030206109,0.0002048591,0.00014467062,0.0071497113],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9949034,0.000080105354,0.0005365265,0.0024890283,0.0014172792,0.0005736729],"domain_scores_gemma":[0.9958155,0.00064709596,0.0005005482,0.002457984,0.00043020822,0.00014862235],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001031994,0.0006314541,0.00075974315,0.000974093,0.00018056027,0.00079224404,0.004006535,0.0005835215,0.0000457663],"category_scores_gemma":[0.00019313536,0.0005179007,0.00011790731,0.0010706239,0.00078152015,0.0011790543,0.0025572302,0.0018617846,0.00001529214],"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":[0.0001842297,0.00017730489,0.0005297336,0.00088782195,0.00028714436,0.0013337535,0.0043516327,0.02940264,0.005838529,0.059869647,0.0033628454,0.89377475],"study_design_scores_gemma":[0.00080086617,0.00095574325,0.00035188047,0.0052708834,0.0001353037,0.00048429027,0.000003461704,0.89839584,0.019783063,0.069666654,0.0024530827,0.001698947],"about_ca_topic_score_codex":0.000073322444,"about_ca_topic_score_gemma":0.0001657491,"teacher_disagreement_score":0.8920758,"about_ca_system_score_codex":0.00018035961,"about_ca_system_score_gemma":0.00052796485,"threshold_uncertainty_score":0.99972725},"labels":[],"label_agreement":null},{"id":"W4402307317","doi":"10.18280/ts.410449","title":"Advancing Ancient Arabic Manuscript Restoration with Optimized Deep Learning and Image Enhancement Techniques","year":2024,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Arabic; Artificial intelligence; Image (mathematics); Computer science; Deep learning; Natural language processing; Linguistics; Philosophy","score_opus":0.008644484244156198,"score_gpt":0.24425985897465596,"score_spread":0.23561537473049976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402307317","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":[0.013761235,0.0006227306,0.98181087,0.000585593,0.00007276257,0.0005652893,0.0000013114999,0.0012551616,0.0013250583],"genre_scores_gemma":[0.46880698,0.0001930004,0.5301536,0.00025279983,0.00007818624,0.00030412478,0.000013588002,0.000022625514,0.00017513981],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99822253,0.00011176734,0.00032903274,0.0005659362,0.00042407602,0.00034665153],"domain_scores_gemma":[0.99944526,0.000065758,0.00008576235,0.00016894523,0.00012327444,0.00011102597],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007603454,0.00022413177,0.00019252041,0.00027208822,0.0001834012,0.00059054495,0.0002305361,0.000050885465,0.0001480155],"category_scores_gemma":[0.000013941451,0.00018869551,0.00004621722,0.00033830735,0.00006978326,0.0011560254,0.000112084,0.00023311256,0.00002139079],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057659483,0.00015625145,0.0000820292,0.00023319639,0.00006663637,0.00017401531,0.001888458,0.00007743979,0.24896583,0.0043382645,0.0016136523,0.7423466],"study_design_scores_gemma":[0.0008260209,0.002060776,0.00018558052,0.0008907379,0.000060195358,0.00013847263,0.0002371428,0.24630909,0.70411325,0.0019523118,0.042402152,0.0008242757],"about_ca_topic_score_codex":0.000008910061,"about_ca_topic_score_gemma":0.0000052361856,"teacher_disagreement_score":0.7415223,"about_ca_system_score_codex":0.00015384036,"about_ca_system_score_gemma":0.000054220764,"threshold_uncertainty_score":0.769478},"labels":[],"label_agreement":null},{"id":"W4402426001","doi":"10.1142/9789811289125_0008","title":"An Encoder–Decoder Approach to Offline Handwritten Mathematical Expression Recognition with Residual Attention","year":2024,"lang":"en","type":"book-chapter","venue":"Series on language processing, pattern recognition, and intelligent systems","topic":"Handwritten Text Recognition Techniques","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":"Concordia University","funders":"","keywords":"Computer science; Speech recognition; Encoder; Residual; Artificial intelligence; Pattern recognition (psychology); Expression (computer science); Algorithm; Programming language","score_opus":0.03051297855439314,"score_gpt":0.26037560981552166,"score_spread":0.22986263126112852,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402426001","genre_codex":"methods","genre_gemma":"other","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":[0.0022970268,0.0028030036,0.8796311,0.00024197191,0.00048009536,0.0027017442,0.00069457974,0.0019251549,0.1092253],"genre_scores_gemma":[0.25234002,0.0041465308,0.19216256,0.0048284666,0.008431445,0.0066897585,0.021842053,0.0023686136,0.5071906],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99519444,0.00013908846,0.001189821,0.0018639485,0.0010297775,0.0005829376],"domain_scores_gemma":[0.9973161,0.00007248254,0.0005742969,0.00084276707,0.0007511883,0.0004431605],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007108685,0.0010032201,0.0009298737,0.0008916216,0.00034834552,0.0017531586,0.00068631617,0.00065625703,0.00022019379],"category_scores_gemma":[0.000032526725,0.0008078955,0.00014421216,0.0002042758,0.00018510563,0.0013303902,0.00019472853,0.00076964474,0.0010399119],"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":[0.00029519812,0.00071242556,0.000014802,0.008011276,0.00027739702,0.00025810953,0.011711713,0.000008707928,0.0011794395,0.0021927638,0.0030559832,0.9722822],"study_design_scores_gemma":[0.0063643064,0.028911285,0.00008787102,0.25871465,0.0034224393,0.01557288,0.034702964,0.047710337,0.17372584,0.33034182,0.071224764,0.029220857],"about_ca_topic_score_codex":0.000039846054,"about_ca_topic_score_gemma":0.000035226032,"teacher_disagreement_score":0.94306135,"about_ca_system_score_codex":0.00014317574,"about_ca_system_score_gemma":0.00011281065,"threshold_uncertainty_score":0.9997379},"labels":[],"label_agreement":null},{"id":"W4402572597","doi":"10.1109/newcas58973.2024.10666299","title":"Recognition of Electronic Component Orientations from Hand-Drawn Circuit Schematics through a Two Stage Machine Learning System","year":2024,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Schematic; Component (thermodynamics); Computer science; Stage (stratigraphy); Artificial intelligence; Engineering drawing; Pattern recognition (psychology); Electrical engineering; Engineering; Physics","score_opus":0.03171560612849066,"score_gpt":0.28088490244471487,"score_spread":0.2491692963162242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402572597","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":[0.056031566,0.00049822754,0.93713224,0.000098462275,0.00017274523,0.00034126046,0.00006195875,0.0013754824,0.0042880573],"genre_scores_gemma":[0.9198198,0.000045001852,0.079423174,0.000049195576,0.000046217938,0.000072970826,0.00017423356,0.000021710239,0.0003477488],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9982142,0.00015848008,0.00052059215,0.00043093038,0.0003793688,0.0002964262],"domain_scores_gemma":[0.9989945,0.00028996365,0.0001475688,0.00033196286,0.00017764974,0.000058352325],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036900392,0.00018229816,0.00027118935,0.00018655328,0.00021488675,0.00051861303,0.00037599387,0.000068011635,0.00024267453],"category_scores_gemma":[0.00003989638,0.00016921203,0.00011597929,0.0006327248,0.00007707209,0.0007397904,0.00012945369,0.000340712,0.00021974536],"study_design_candidate":"theoretical_or_conceptual","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":[0.00001671993,0.0003172874,0.00020813235,0.0012275669,0.0004085802,0.00007195589,0.008991458,0.00008855231,0.076845855,0.77778983,0.000448458,0.13358559],"study_design_scores_gemma":[0.0008248489,0.00047554777,0.0000330206,0.0014327816,0.00010295289,0.00006459845,0.0007728261,0.4240589,0.49571535,0.07088581,0.0050534313,0.0005799081],"about_ca_topic_score_codex":0.00078208256,"about_ca_topic_score_gemma":0.00010676753,"teacher_disagreement_score":0.8637882,"about_ca_system_score_codex":0.00019904626,"about_ca_system_score_gemma":0.00018397918,"threshold_uncertainty_score":0.69002664},"labels":[],"label_agreement":null},{"id":"W4402631940","doi":"10.1007/978-3-031-71602-7_19","title":"Deep Multi-label Classification of Personality with Handwriting Analysis","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","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":"Concordia University","funders":"","keywords":"Computer science; Handwriting; Artificial intelligence; Personality; Pattern recognition (psychology); Speech recognition; Natural language processing; Psychology","score_opus":0.034074935504077274,"score_gpt":0.28350340663452234,"score_spread":0.24942847113044506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402631940","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":[0.00019466213,0.0004647491,0.995602,0.00035530137,0.00018906136,0.0003331406,0.00001024369,0.0003111534,0.0025396612],"genre_scores_gemma":[0.25854686,0.00002880316,0.7408141,0.00019875822,0.000095207295,0.000017458757,0.000012360409,0.000025709445,0.00026076956],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99629265,0.000039039718,0.0006301232,0.0015609107,0.001042979,0.0004343234],"domain_scores_gemma":[0.9974157,0.00033180218,0.00041129143,0.0011278547,0.00058332336,0.00013000007],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010562018,0.0004453905,0.0006728193,0.001815082,0.00015490424,0.0004688646,0.0020383021,0.0002843739,0.000026799633],"category_scores_gemma":[0.000057086312,0.0003745792,0.0001981505,0.0022424841,0.0007865216,0.0005241394,0.0006176255,0.00070377043,0.000021422797],"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":[0.0000073615784,0.00008817893,0.00041172584,0.00018239027,0.00019648692,0.00006521551,0.0012163286,0.0015050643,0.00084449566,0.029082863,0.000003437463,0.96639645],"study_design_scores_gemma":[0.00018723436,0.00013873128,0.00050186063,0.00048569657,0.00012433497,0.000030125544,7.1013176e-7,0.9609515,0.0036558036,0.033401128,0.000049207727,0.00047367573],"about_ca_topic_score_codex":0.000048402304,"about_ca_topic_score_gemma":0.00039428473,"teacher_disagreement_score":0.9659228,"about_ca_system_score_codex":0.00025462083,"about_ca_system_score_gemma":0.0003190806,"threshold_uncertainty_score":0.9998706},"labels":[],"label_agreement":null},{"id":"W4402671279","doi":"10.18653/v1/2024.arabicnlp-1.19","title":"Qalam: A Multimodal LLM for Arabic Optical Character and Handwriting Recognition","year":2024,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":9,"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":"Alliance de recherche numérique du Canada; Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Computer science; Character (mathematics); Arabic; Handwriting; Optical character recognition; Intelligent character recognition; Character recognition; Handwriting recognition; Speech recognition; Natural language processing; Artificial intelligence; Feature extraction; Linguistics; Image (mathematics); Mathematics","score_opus":0.023402467897280118,"score_gpt":0.27428927077269494,"score_spread":0.2508868028754148,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402671279","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":[0.03320898,0.00012444418,0.95891553,0.00197416,0.00020985959,0.00045667824,0.000013201631,0.0013442728,0.003752874],"genre_scores_gemma":[0.578208,0.000048086727,0.4200276,0.0006057155,0.00023365735,0.00027725546,0.000023913286,0.000020117264,0.00055559597],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988421,0.000026190017,0.00023547972,0.00048607687,0.00013756411,0.00027258153],"domain_scores_gemma":[0.9992823,0.0003167946,0.000023720575,0.00016389691,0.00011129093,0.000102009406],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039899995,0.00014094921,0.00014636117,0.00017362882,0.00010043012,0.0006425207,0.00018067352,0.00009964483,0.000058581958],"category_scores_gemma":[0.000092542556,0.00012276197,0.00007795196,0.0001779969,0.000045623612,0.00089040434,0.000108059954,0.00014343245,0.00011513572],"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":[0.000005347589,0.00004009143,0.000017327447,0.000097376,0.00001470625,0.000014183335,0.00014855393,2.8589902e-8,0.006259234,0.014994672,0.00072406355,0.97768444],"study_design_scores_gemma":[0.0013942443,0.000883762,0.0014102135,0.0010112147,0.00006593023,0.0006070049,0.00010550419,0.4792126,0.3595277,0.13525805,0.019263754,0.0012599978],"about_ca_topic_score_codex":0.0000059840295,"about_ca_topic_score_gemma":0.0000035128403,"teacher_disagreement_score":0.9764244,"about_ca_system_score_codex":0.000025873078,"about_ca_system_score_gemma":0.00003393725,"threshold_uncertainty_score":0.6195842},"labels":[],"label_agreement":null},{"id":"W4402672028","doi":"10.18653/v1/2024.acl-long.553","title":"BinaryAlign: Word Alignment as Binary Sequence Labeling","year":2024,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ubisoft (Canada)","funders":"","keywords":"Computer science; Word (group theory); Sequence (biology); Binary number; Natural language processing; Sequence labeling; Artificial intelligence; Pseudorandom binary sequence; Arithmetic; Linguistics; Mathematics; Biology; Genetics; Engineering","score_opus":0.03158959059957141,"score_gpt":0.30236305204174474,"score_spread":0.27077346144217335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402672028","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":[0.01890235,0.0017162727,0.88051313,0.01103359,0.0011602885,0.0005089623,0.0000062675704,0.008669853,0.07748927],"genre_scores_gemma":[0.77336997,0.0002812077,0.21493664,0.0021606549,0.00010878169,0.00010822711,0.0000067489136,0.000026466707,0.009001313],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984755,0.000058039153,0.0002477066,0.0005527169,0.0003513059,0.00031476177],"domain_scores_gemma":[0.9992154,0.00010252912,0.000025366438,0.00047443877,0.0000618063,0.00012045491],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003978574,0.00016900428,0.0001304441,0.00023827876,0.00009808349,0.0004860513,0.00072419253,0.00007470736,0.00040449624],"category_scores_gemma":[0.00002105979,0.00014540897,0.00008130259,0.0007180582,0.00004348034,0.00079569157,0.00035448725,0.00015375923,0.002208858],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000032186867,0.00008863959,0.000028813494,0.000091597394,0.00004570369,0.0011164186,0.00066976907,0.0000080027285,0.06111693,0.34217843,0.035350468,0.559302],"study_design_scores_gemma":[0.00024067803,0.0006358066,0.000042185104,0.00086016057,0.000024110037,0.0005010232,0.00014303638,0.07961886,0.51169866,0.224713,0.18040988,0.0011126081],"about_ca_topic_score_codex":0.00006183804,"about_ca_topic_score_gemma":0.0000018408044,"teacher_disagreement_score":0.7544676,"about_ca_system_score_codex":0.00009945234,"about_ca_system_score_gemma":0.00012208741,"threshold_uncertainty_score":0.99856806},"labels":[],"label_agreement":null},{"id":"W4402688456","doi":"10.3233/faia240390","title":"Recognition of Handwritten Tamazight Characters Using ResNet, MobileNet and VGG Transfer Learning","year":2024,"lang":"en","type":"book-chapter","venue":"Frontiers in artificial intelligence and applications","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton; Université Laval","funders":"","keywords":"Residual neural network; Transfer of learning; Computer science; Artificial intelligence; Pattern recognition (psychology); Deep learning","score_opus":0.042119298307355404,"score_gpt":0.26964195768985677,"score_spread":0.22752265938250138,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402688456","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":[0.0007075195,0.0021922127,0.9855013,0.0001670729,0.00017313387,0.0008784532,0.00006022127,0.00016215572,0.010157927],"genre_scores_gemma":[0.4713595,0.07186974,0.37995952,0.00083933026,0.0020977617,0.0029078703,0.001004168,0.0006168872,0.069345236],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982751,0.000026927048,0.0006432332,0.0006569092,0.00018737202,0.00021044897],"domain_scores_gemma":[0.999334,0.00006544051,0.00012447267,0.00027383756,0.000115295355,0.00008696963],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002936648,0.00026918587,0.000391226,0.00059438334,0.0001244882,0.00015394771,0.00028859422,0.00029798824,0.000024047438],"category_scores_gemma":[0.0000089584755,0.00029174378,0.00008347514,0.00020355331,0.0002849869,0.0002579524,0.00010526612,0.0005154447,0.000022392353],"study_design_candidate":"theoretical_or_conceptual","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":[0.000009932977,0.000028622839,0.000017838445,0.00013929787,0.00003690228,0.0000054095476,0.00050109375,0.000014683201,0.0007771599,0.12870558,0.000086708074,0.86967677],"study_design_scores_gemma":[0.000038746875,0.00012570224,0.000014395653,0.00095112494,0.00010265232,0.000025061834,0.00024540143,0.016605502,0.02424203,0.9310347,0.025986752,0.00062794506],"about_ca_topic_score_codex":0.000026151598,"about_ca_topic_score_gemma":0.000017583101,"teacher_disagreement_score":0.86904883,"about_ca_system_score_codex":0.000052336614,"about_ca_system_score_gemma":0.000050599287,"threshold_uncertainty_score":0.99995345},"labels":[],"label_agreement":null},{"id":"W4402712667","doi":"","title":"Initiation to Handwritten Text Recognition with eScriptorium","year":2024,"lang":"en","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Text recognition; Speech recognition; Artificial intelligence; Character recognition; Natural language processing","score_opus":0.014028853629871801,"score_gpt":0.2243038828140989,"score_spread":0.2102750291842271,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402712667","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":[0.013719189,0.0002618061,0.91884303,0.016179895,0.00020046403,0.00041599275,0.00002112981,0.0015758399,0.048782673],"genre_scores_gemma":[0.6757251,0.00011051887,0.31927243,0.00063417526,0.000047182926,0.00020409751,0.00013999933,0.0000451573,0.0038213418],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99651057,0.0015277724,0.00036655075,0.00076308794,0.0004761622,0.00035584837],"domain_scores_gemma":[0.9961916,0.0007163873,0.000106403255,0.0010724535,0.001680216,0.00023292267],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0029788618,0.00024064495,0.00019980619,0.00043393858,0.00027300755,0.0012565036,0.00094700395,0.00012162522,0.00015042491],"category_scores_gemma":[0.0005014666,0.00022906602,0.00009196856,0.0013932084,0.000084328676,0.0010426624,0.00031791074,0.00028936693,0.0005865679],"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":[0.000011912421,0.00027280065,0.0001737618,0.00010678315,0.000052387997,0.000034539225,0.008642336,0.0000024487717,0.013838628,0.1156016,0.008823399,0.8524394],"study_design_scores_gemma":[0.0007799622,0.00000940885,0.0017582183,0.004521772,0.000055724864,0.00017098809,0.00017236052,0.025286065,0.81552786,0.030253667,0.120263636,0.0012003501],"about_ca_topic_score_codex":0.00020443554,"about_ca_topic_score_gemma":0.0003586111,"teacher_disagreement_score":0.851239,"about_ca_system_score_codex":0.00012554419,"about_ca_system_score_gemma":0.00019421482,"threshold_uncertainty_score":0.9997803},"labels":[],"label_agreement":null},{"id":"W4402933071","doi":"10.1002/gdj3.261","title":"Automation of historical weather data rescue","year":2024,"lang":"en","type":"article","venue":"Geoscience Data Journal","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":3,"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":"Environment and Climate Change Canada","keywords":"Automation; Computer science; Aeronautics; Systems engineering; Data science; Engineering","score_opus":0.0765346719700735,"score_gpt":0.3237836979278009,"score_spread":0.24724902595772735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402933071","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":[0.0007184593,0.0007532933,0.99451077,0.0020636627,0.0010524826,0.000063462845,0.00017689368,0.00021274094,0.00044826072],"genre_scores_gemma":[0.10639212,0.00078255247,0.8899748,0.0003790829,0.00063477637,0.0000051715956,0.0002473943,0.000020710217,0.0015634111],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980728,0.00009174051,0.0003905811,0.00055000244,0.00065468665,0.00024017676],"domain_scores_gemma":[0.9974452,0.000089137706,0.000098049386,0.0021504448,0.00009944624,0.000117716576],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.002768541,0.00009396108,0.00013149837,0.00028820758,0.00015173049,0.00060930446,0.007041274,0.000048558548,0.00011131905],"category_scores_gemma":[0.00034866974,0.00007497044,0.000028415232,0.0007864323,0.00007869306,0.005623571,0.0021035078,0.00028738225,0.000102091886],"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":[0.0000017707199,0.00006141792,0.000076298435,0.000028115386,0.000010770484,0.00008205611,0.0002457883,0.0000016821856,0.0030641088,0.0038813038,0.19981368,0.792733],"study_design_scores_gemma":[0.0001286377,0.00012870142,0.0009883562,0.00029460236,0.000020682257,0.0016792964,0.000027444683,0.5786676,0.0014377241,0.009561802,0.40679005,0.00027512558],"about_ca_topic_score_codex":0.000057209818,"about_ca_topic_score_gemma":0.000007650876,"teacher_disagreement_score":0.7924579,"about_ca_system_score_codex":0.00014710175,"about_ca_system_score_gemma":0.0003288448,"threshold_uncertainty_score":0.9983311},"labels":[],"label_agreement":null},{"id":"W4403534596","doi":"10.1109/codit62066.2024.10708517","title":"Handwritten Signature Recognition using Parallel CNNs and Transfer Learning for Forensics","year":2024,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton; Université Laval","funders":"","keywords":"Computer science; Signature (topology); Transfer of learning; Pattern recognition (psychology); Artificial intelligence; Computer forensics; Signature recognition; Feature extraction; Digital forensics; Computer security","score_opus":0.03364014362791952,"score_gpt":0.27376146573660703,"score_spread":0.24012132210868753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403534596","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":[0.007498121,0.0005121372,0.98882973,0.0006776898,0.00016051295,0.000402181,0.00000743736,0.00089988427,0.0010122943],"genre_scores_gemma":[0.4326268,0.00015403202,0.56590366,0.00047092873,0.00014708728,0.000083848536,0.00003303135,0.000032524706,0.00054808223],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989158,0.0000444938,0.0001994955,0.0004389596,0.00014448143,0.00025676255],"domain_scores_gemma":[0.99946547,0.00019434403,0.0000143422585,0.00012641575,0.000120681856,0.00007875663],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031044194,0.00015909236,0.00015657258,0.00023512122,0.0001662277,0.0004602063,0.00016259296,0.00015346646,0.00003103768],"category_scores_gemma":[0.000033033157,0.0001405791,0.0000939072,0.00033910453,0.00004158013,0.000735295,0.000050279446,0.00025347498,0.000011982515],"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":[0.000012946006,0.00001808233,0.000020128471,0.00019319286,0.00004915119,0.00001927907,0.0007135862,0.000034052482,0.011281315,0.019689878,0.0014671116,0.9665013],"study_design_scores_gemma":[0.0006671049,0.00039160246,0.00003760119,0.00045663916,0.00007574386,0.00019065863,0.00013043046,0.7270721,0.06785429,0.18270582,0.019718139,0.0006998479],"about_ca_topic_score_codex":0.0000103815355,"about_ca_topic_score_gemma":0.000009065699,"teacher_disagreement_score":0.9658014,"about_ca_system_score_codex":0.00002777999,"about_ca_system_score_gemma":0.000044699464,"threshold_uncertainty_score":0.57326496},"labels":[],"label_agreement":null},{"id":"W4403539812","doi":"10.1016/j.eswa.2024.125557","title":"VGTS: Visually Guided Text Spotting for novel categories in historical manuscripts","year":2024,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Spotting; Computer science; Natural language processing; Artificial intelligence; Information retrieval","score_opus":0.03840895304255738,"score_gpt":0.301956647548362,"score_spread":0.2635476945058046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403539812","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":[0.00012884407,0.0022013518,0.99097526,0.0016396178,0.0002899439,0.0017573959,0.000009883372,0.0011001368,0.0018975819],"genre_scores_gemma":[0.6391744,0.00007527958,0.32531896,0.00041152516,0.0007133602,0.030839631,0.000047613532,0.00008516143,0.003334047],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99829066,0.000029359633,0.00049160863,0.0006244396,0.00025238888,0.00031154565],"domain_scores_gemma":[0.99889785,0.0001885605,0.00008829749,0.0005411538,0.00018588723,0.00009823227],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036906014,0.00019522564,0.00024821376,0.00030870587,0.00016155475,0.0003870025,0.0005991523,0.000099281984,0.0000029568748],"category_scores_gemma":[0.000027597425,0.00016657598,0.000059278424,0.00079664047,0.000033098986,0.0004593487,0.00007644675,0.00012954936,0.0000482695],"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":[0.0000118733515,0.00036504262,0.00014230832,0.0005192234,0.000062112886,0.00002055205,0.0038636145,0.000033577988,0.017862683,0.8463309,0.087326825,0.043461278],"study_design_scores_gemma":[0.00041024317,0.00012243199,0.00007600847,0.0003849327,0.000008763463,0.00018841143,0.0002969802,0.03487466,0.003967326,0.0032195605,0.95593387,0.0005168191],"about_ca_topic_score_codex":0.0005047831,"about_ca_topic_score_gemma":0.000047782323,"teacher_disagreement_score":0.86860704,"about_ca_system_score_codex":0.00059903355,"about_ca_system_score_gemma":0.00016419266,"threshold_uncertainty_score":0.6792771},"labels":[],"label_agreement":null},{"id":"W4403577522","doi":"10.1145/3627673.3679959","title":"Mamba Retriever: Utilizing Mamba for Effective and Efficient Dense Retrieval","year":2024,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Labrador Retriever; Medicine","score_opus":0.014067627848150164,"score_gpt":0.2747566818798541,"score_spread":0.2606890540317039,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403577522","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":[0.053618785,0.00079093885,0.9391334,0.0006747438,0.00039099366,0.0010495188,0.000017678765,0.001574351,0.0027495648],"genre_scores_gemma":[0.9221589,0.000042468608,0.07646604,0.00039361411,0.0000850292,0.00008096202,0.000005225897,0.000022774639,0.00074501644],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985477,0.000064849955,0.00021830182,0.00062096503,0.00023765417,0.00031054803],"domain_scores_gemma":[0.9987225,0.0006893502,0.000031362484,0.00030532858,0.00012761453,0.00012384303],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007740472,0.00017439354,0.00018081871,0.00022774843,0.00013308844,0.000463887,0.000267413,0.00010484138,0.000026116108],"category_scores_gemma":[0.00020797265,0.00014950865,0.00010005905,0.00057324197,0.000063370724,0.00027042153,0.00021771289,0.00015768665,0.000051830462],"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":[0.00013982489,0.00012755727,0.00006938293,0.00055539835,0.00011227929,0.00020971904,0.001120928,0.000003438971,0.019986078,0.20216864,0.018400153,0.7571066],"study_design_scores_gemma":[0.0008368916,0.00089550915,0.0005870795,0.00042588002,0.000055724002,0.0003070782,0.00010485785,0.28261712,0.65831035,0.026534488,0.028593017,0.0007320246],"about_ca_topic_score_codex":0.000009493272,"about_ca_topic_score_gemma":0.0000019544927,"teacher_disagreement_score":0.8685401,"about_ca_system_score_codex":0.000083035455,"about_ca_system_score_gemma":0.000056779096,"threshold_uncertainty_score":0.60967857},"labels":[],"label_agreement":null},{"id":"W4403664791","doi":"10.1016/j.engappai.2024.109458","title":"Dynamically Adaptive Deformable Feature Fusion for multi-scale character detection in ancient documents","year":2024,"lang":"en","type":"article","venue":"Engineering Applications of Artificial Intelligence","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":"Queen's University","funders":"Kyungpook National University","keywords":"Computer science; Character (mathematics); Artificial intelligence; Feature (linguistics); Scale (ratio); Pattern recognition (psychology); Fusion; Natural language processing; Computer vision; Linguistics","score_opus":0.01956557004669445,"score_gpt":0.2820630817309452,"score_spread":0.26249751168425073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403664791","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":[0.0078056916,0.0001008639,0.99073076,0.00010176202,0.00014985546,0.0007422644,0.000015388845,0.00032948027,0.00002394678],"genre_scores_gemma":[0.6661634,0.000020739439,0.33294544,0.000012954872,0.000033450917,0.0007679812,0.0000078401445,0.000011027507,0.000037199527],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990155,0.000009160949,0.0003106332,0.000328444,0.00013438443,0.00020189052],"domain_scores_gemma":[0.9994422,0.000075112606,0.000048121197,0.00026442527,0.000121688594,0.00004840651],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027102974,0.00011829785,0.00012126323,0.00032675985,0.00005035074,0.00008967071,0.00035706957,0.00008623418,0.0000041332105],"category_scores_gemma":[0.000024431427,0.000121096775,0.00006735101,0.000765284,0.000022657252,0.00038044716,0.000074120166,0.00016730123,0.00003129354],"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":[0.000009372879,0.000114685856,0.000004315488,0.00009811759,0.0000090202875,7.8820227e-7,0.00038194525,0.0030199424,0.18006063,0.01641003,0.0000141577275,0.799877],"study_design_scores_gemma":[0.000009160978,0.000038099704,0.00007031626,0.00007066258,0.0000027923663,0.0000024376384,0.00001968466,0.6786009,0.3185807,0.0016951968,0.0008201647,0.00008991243],"about_ca_topic_score_codex":0.00002316872,"about_ca_topic_score_gemma":0.000040269384,"teacher_disagreement_score":0.7997871,"about_ca_system_score_codex":0.000112778325,"about_ca_system_score_gemma":0.000028916931,"threshold_uncertainty_score":0.4938183},"labels":[],"label_agreement":null},{"id":"W4403914082","doi":"10.1016/j.asoc.2024.112394","title":"Learnable feature alignment with attention-based data augmentation for handling data issue in ancient documents","year":2024,"lang":"en","type":"article","venue":"Applied Soft Computing","topic":"Handwritten Text Recognition Techniques","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":"Queen's University","funders":"","keywords":"Computer science; Feature (linguistics); Artificial intelligence; Pattern recognition (psychology); Data mining; Linguistics","score_opus":0.03320446859801778,"score_gpt":0.3125644634317031,"score_spread":0.2793599948336853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403914082","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":[0.0039436636,0.00021617439,0.992855,0.0008683434,0.00023535197,0.00094657444,0.000043899377,0.0005749191,0.0003160723],"genre_scores_gemma":[0.51888746,0.0000053149497,0.47895095,0.0006085718,0.000120818506,0.000067255416,0.0012142493,0.000028234863,0.0001171606],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99769956,0.000037821912,0.0003145949,0.0011403423,0.00040605516,0.0004016219],"domain_scores_gemma":[0.9982006,0.0002921268,0.000110124856,0.0012738442,0.00005446406,0.00006887432],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012952681,0.00020178851,0.00020106364,0.00020908398,0.0002113649,0.00072923914,0.0016807591,0.00007022765,0.000008673167],"category_scores_gemma":[0.00002738215,0.00018740582,0.000023462138,0.00057268067,0.000030077199,0.0007146034,0.0009164988,0.00020294449,0.000033084933],"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":[0.0000729773,0.000351419,0.0009831866,0.00094296044,0.00015517196,0.00006412724,0.0011066868,0.00662605,0.0097418865,0.00655572,0.045690868,0.9277089],"study_design_scores_gemma":[0.0008883242,0.00006577156,0.0001519273,0.00052083906,0.000025275287,0.000006436056,0.00011752489,0.9715466,0.0043609873,0.00078284444,0.021225434,0.00030804987],"about_ca_topic_score_codex":0.000043284752,"about_ca_topic_score_gemma":0.000025876137,"teacher_disagreement_score":0.9649205,"about_ca_system_score_codex":0.00013476792,"about_ca_system_score_gemma":0.00015674047,"threshold_uncertainty_score":0.76421875},"labels":[],"label_agreement":null},{"id":"W4404047929","doi":"10.2174/0115748936312589240910071837","title":"Robust Somatic Copy Number Estimation using Coarse-to-fine Segmentation","year":2024,"lang":"en","type":"article","venue":"Current Bioinformatics","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"AbCellera (Canada); Canada's Michael Smith Genome Sciences Centre; University of British Columbia; BC Cancer Agency","funders":"Canadian Institutes of Health Research; Genome British Columbia; Canada Foundation for Innovation","keywords":"Somatic cell; Estimation; Segmentation; Computer science; Artificial intelligence; Pattern recognition (psychology); Biology; Genetics; Gene; Engineering","score_opus":0.0595775188455197,"score_gpt":0.329495560016003,"score_spread":0.2699180411704833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404047929","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":[0.008928402,0.000080177386,0.9875509,0.00019613655,0.0010860808,0.0004947044,0.000015668093,0.0010022479,0.0006456724],"genre_scores_gemma":[0.046863835,0.000021493333,0.952768,0.00011334457,0.000067053545,0.000046467772,0.000071054616,0.000016128632,0.00003258629],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99849486,0.000038186135,0.00062362594,0.00019074434,0.00039200537,0.00026055326],"domain_scores_gemma":[0.9992138,0.00009386757,0.00012698186,0.00032414804,0.000114660455,0.00012655044],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004123223,0.00018925655,0.00018461395,0.00028654505,0.00011999263,0.0007556214,0.00037454398,0.000057718,0.00007285279],"category_scores_gemma":[0.00007076431,0.0001764578,0.00007760786,0.0007774553,0.000027519933,0.0018845336,0.00016728713,0.00016002728,0.0014809128],"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":[0.0000016212242,0.00005813286,0.00007972259,0.00092865626,0.000020546317,0.0000042495885,0.002803791,0.0019307653,0.00024477945,0.006058736,0.008277485,0.9795915],"study_design_scores_gemma":[0.00010870175,0.000030123647,0.000014296367,0.00063584786,0.000020761529,0.000056834826,0.00004765322,0.9862492,0.008604153,0.0028974074,0.0011059025,0.00022910394],"about_ca_topic_score_codex":0.0000031335508,"about_ca_topic_score_gemma":9.5207554e-7,"teacher_disagreement_score":0.98431844,"about_ca_system_score_codex":0.00017563556,"about_ca_system_score_gemma":0.00010944625,"threshold_uncertainty_score":0.99929655},"labels":[],"label_agreement":null},{"id":"W4404526681","doi":"10.1145/3687955","title":"Skeleton-Driven Inbetweening of Bitmap Character Drawings","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Graphics","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Character (mathematics); Bitmap; Computer graphics (images); Computer science; Skeleton (computer programming); Character animation; Engineering drawing; Animation; Mathematics; Geometry; Programming language; Computer animation; Engineering","score_opus":0.021074225975353293,"score_gpt":0.2702456496950789,"score_spread":0.24917142371972562,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404526681","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":[0.015496218,0.000083734565,0.98032063,0.002200951,0.00039308716,0.00016587383,0.00002291162,0.00095382665,0.00036273745],"genre_scores_gemma":[0.94305336,0.0002141936,0.05606499,0.00042764403,0.000042993463,0.000049715305,0.000005244278,0.000023572931,0.00011831029],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986679,0.000054719192,0.00032557047,0.00039783865,0.0003214692,0.00023247833],"domain_scores_gemma":[0.998746,0.00027119397,0.000056322333,0.00073172577,0.000113328984,0.00008142318],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023636998,0.00017158907,0.00019457075,0.0008103712,0.00013242463,0.00015302864,0.00083363603,0.00014245466,0.00005957254],"category_scores_gemma":[0.000018573604,0.00016664831,0.00019737924,0.0013552312,0.00009623221,0.00069896004,0.0000201078,0.0004648871,0.00006384679],"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":[0.000008917431,0.00027015095,0.00021816569,0.00026897038,0.000267978,0.00005225447,0.0020792994,0.00003286392,0.017079575,0.046634305,0.00083512464,0.9322524],"study_design_scores_gemma":[0.0008581531,0.0015569995,0.0034639835,0.0022343264,0.0002525306,0.00017531168,0.00007961511,0.033281643,0.6787451,0.18722662,0.09034021,0.0017855064],"about_ca_topic_score_codex":0.000021179772,"about_ca_topic_score_gemma":0.0000071858367,"teacher_disagreement_score":0.9304669,"about_ca_system_score_codex":0.000025909749,"about_ca_system_score_gemma":0.00006899533,"threshold_uncertainty_score":0.6795721},"labels":[],"label_agreement":null},{"id":"W4404625217","doi":"10.1007/978-3-031-73411-3_5","title":"PIXART-$$\\Sigma $$: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":75,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Huawei Technologies (Canada)","funders":"","keywords":"Computer science; Transformer; Sigma; Artificial intelligence; Computer vision; Electrical engineering; Physics; Quantum mechanics; Voltage","score_opus":0.03174797090960109,"score_gpt":0.2780515632484664,"score_spread":0.24630359233886534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404625217","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":[0.00018193205,0.00011283716,0.9905765,0.0018560747,0.0012406986,0.0015368578,0.000044584332,0.00032818492,0.004122354],"genre_scores_gemma":[0.09138771,0.000024046647,0.9053147,0.0013195929,0.0007212549,0.00013394441,0.000022282065,0.00007619971,0.0010003059],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9957989,0.000025630983,0.0008143894,0.0017159878,0.00093580433,0.00070932147],"domain_scores_gemma":[0.9978722,0.00032196438,0.00019344596,0.0009088497,0.00043005557,0.0002734903],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010615377,0.0005739561,0.00067589467,0.0017106599,0.00022311129,0.00057783804,0.002152232,0.00033634764,0.0000314288],"category_scores_gemma":[0.00010105491,0.00052996184,0.00025610655,0.0008925386,0.00027385645,0.0006454657,0.0004611944,0.00053389714,0.00005179866],"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":[0.000008660242,0.000026477795,0.0000014839565,0.000108437474,0.000012676517,0.000010647121,0.0026961735,0.0014269047,0.040230457,0.018625604,0.00016194656,0.9366905],"study_design_scores_gemma":[0.0005085519,0.0013789028,0.000020944477,0.0021095115,0.000043105563,0.00007086025,0.0000025644244,0.6120724,0.22857198,0.13987443,0.013791113,0.0015556124],"about_ca_topic_score_codex":0.000011858864,"about_ca_topic_score_gemma":0.00009425129,"teacher_disagreement_score":0.93513495,"about_ca_system_score_codex":0.00024516287,"about_ca_system_score_gemma":0.00041569181,"threshold_uncertainty_score":0.9997152},"labels":[],"label_agreement":null},{"id":"W4404825578","doi":"10.18280/mmep.111125","title":"CNN-DEdge: Multilingual Scene Text Detection and Extraction","year":2024,"lang":"en","type":"article","venue":"Mathematical Modelling and Engineering Problems","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Artificial intelligence; Extraction (chemistry); Natural language processing; Computer vision; Pattern recognition (psychology); Chromatography","score_opus":0.022003884614037548,"score_gpt":0.24529554639477788,"score_spread":0.22329166178074034,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404825578","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":[0.029468639,0.0007533038,0.96813846,0.00008197756,0.00011150471,0.00014278619,4.825716e-7,0.0011353493,0.00016748122],"genre_scores_gemma":[0.795108,0.00014352702,0.20457956,0.000006470101,0.000043908978,0.000034170705,4.879025e-7,0.000017166954,0.00006665987],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999161,0.000010519637,0.00021022618,0.00030758913,0.00012387468,0.00018679623],"domain_scores_gemma":[0.99959964,0.00013472934,0.000017173801,0.00013212959,0.000028424043,0.00008787912],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031842044,0.00013995076,0.00013438101,0.00014086133,0.00006484587,0.00034265826,0.00008178258,0.000092579205,0.00000396648],"category_scores_gemma":[0.000024615087,0.00012641908,0.000030159474,0.00015494249,0.000019943904,0.00035279503,0.000053081534,0.00017285826,0.00002031644],"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":[0.0000041600197,0.000092358016,0.0000019424076,0.0034161024,0.000054868597,0.00002686127,0.0029413868,0.05663679,0.046405148,0.04405063,0.000017168224,0.8463526],"study_design_scores_gemma":[0.00005328544,0.000035570338,0.0000021083415,0.00039884914,0.000008948072,0.000111341105,0.00000584031,0.9534883,0.013023889,0.032396622,0.00032802773,0.0001472111],"about_ca_topic_score_codex":0.0000051975044,"about_ca_topic_score_gemma":2.503275e-7,"teacher_disagreement_score":0.89685154,"about_ca_system_score_codex":0.000021051239,"about_ca_system_score_gemma":0.000007764904,"threshold_uncertainty_score":0.515522},"labels":[],"label_agreement":null},{"id":"W4404956745","doi":"10.1007/978-3-031-78119-3_19","title":"Offline Handwritten Signature Verification Using a Stream-Based Approach","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":3,"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; Signature (topology); Artificial intelligence","score_opus":0.02415434632497349,"score_gpt":0.26115626794966335,"score_spread":0.23700192162468986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404956745","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":[0.000032480017,0.0009258834,0.99121433,0.00053301913,0.0008752878,0.0006876204,0.000023362729,0.00081814284,0.0048898985],"genre_scores_gemma":[0.093305394,0.000028539469,0.90425617,0.0012114616,0.00056106277,0.000031942072,0.000051448053,0.00007889001,0.00047511692],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9952181,0.000045283483,0.0006562325,0.0022087104,0.0012003749,0.0006713056],"domain_scores_gemma":[0.997178,0.00024726323,0.00030435878,0.0016490745,0.00042168924,0.00019958017],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00096682913,0.0007074644,0.0006143109,0.0016482009,0.0002455507,0.0010792097,0.0030924412,0.0006825228,0.000026256703],"category_scores_gemma":[0.000061941675,0.00064995105,0.00022660065,0.0012507384,0.0006048389,0.00066116685,0.00081675145,0.001441901,0.000057361955],"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":[0.000013826782,0.0001413045,0.000011157558,0.000356613,0.000039065304,0.0001868251,0.00053419755,0.031397577,0.003678616,0.03559063,0.00010627279,0.9279439],"study_design_scores_gemma":[0.00018935924,0.00011822672,0.000005640408,0.0007353897,0.000022900385,0.000073106705,1.6266078e-7,0.858889,0.012459217,0.12551786,0.0012695311,0.00071964384],"about_ca_topic_score_codex":0.00002370295,"about_ca_topic_score_gemma":0.000014034254,"teacher_disagreement_score":0.9272243,"about_ca_system_score_codex":0.0005226381,"about_ca_system_score_gemma":0.00085990794,"threshold_uncertainty_score":0.99995774},"labels":[],"label_agreement":null},{"id":"W4405272702","doi":"10.1109/ubmk63289.2024.10773601","title":"Word Image Representation at Local and Global Levels Based on Vision Transformers","year":2024,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"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; Transformer; Computer vision; Artificial intelligence; Word (group theory); Image (mathematics); Representation (politics); Natural language processing; Linguistics; Engineering; Electrical engineering; Political science; Voltage","score_opus":0.017983993190474116,"score_gpt":0.3111256265403669,"score_spread":0.2931416333498928,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405272702","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":[0.0062231,0.00002917889,0.9690147,0.0025637683,0.00010357701,0.00017164611,0.000009351045,0.000759275,0.021125397],"genre_scores_gemma":[0.94346696,0.000010825229,0.055535484,0.00062117697,0.000013562556,0.000015414678,0.0000058426217,0.000005958941,0.00032478225],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99900323,0.000044445358,0.00014713114,0.00040291142,0.00025018732,0.00015206455],"domain_scores_gemma":[0.999615,0.00008645219,0.000013061509,0.00017307872,0.000033651875,0.000078730365],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017839974,0.00010438409,0.00008592438,0.00006952024,0.000066500106,0.00026587333,0.0001476038,0.000054916574,0.00017440836],"category_scores_gemma":[0.000009522795,0.0000861831,0.00005206641,0.00037378253,0.00006479859,0.00058720435,0.000050860348,0.0000686822,0.0001351824],"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":[0.000012642922,0.000022243828,0.00003969614,0.000025771542,0.000004608074,0.00003555993,0.00007290006,0.000004864113,0.0020472675,0.0044424864,0.0042202245,0.9890717],"study_design_scores_gemma":[0.0005188448,0.0003957654,0.004561358,0.00021098339,0.000011892432,0.0000571659,0.000047473914,0.7832772,0.19101785,0.01559601,0.0039412198,0.00036420225],"about_ca_topic_score_codex":0.000032320964,"about_ca_topic_score_gemma":0.000027608814,"teacher_disagreement_score":0.98870754,"about_ca_system_score_codex":0.00012428375,"about_ca_system_score_gemma":0.00003692571,"threshold_uncertainty_score":0.35144448},"labels":[],"label_agreement":null},{"id":"W4405750315","doi":"10.18280/isi.290614","title":"A Comparative Study of Four Handwritten Text Recognition Models in Arabic Script","year":2024,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Arabic; Natural language processing; Computer science; Arabic script; Artificial intelligence; Text recognition; Linguistics; Speech recognition; Image (mathematics)","score_opus":0.04822347176558293,"score_gpt":0.2736448251904332,"score_spread":0.22542135342485028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405750315","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":[0.48699045,0.00015531233,0.50132054,0.000042092313,0.0002316484,0.0010088675,0.00001869571,0.0005787279,0.009653664],"genre_scores_gemma":[0.9897386,0.000027066404,0.009801103,0.000062755236,0.000022630253,0.00028249502,0.000033467935,0.000008732008,0.000023166993],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99802244,0.00016879919,0.0009107502,0.00024334808,0.00039132408,0.00026331874],"domain_scores_gemma":[0.9989233,0.00011146568,0.00021219242,0.00031186722,0.00038057787,0.000060598977],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00073270866,0.0002069196,0.00035783977,0.0010574452,0.00009657627,0.00049728085,0.0004223029,0.000104076586,0.00001853827],"category_scores_gemma":[0.000060944985,0.0001983185,0.00007121841,0.001332676,0.00007161389,0.009290325,0.00013168233,0.00022449909,0.00013037582],"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":[0.0000585413,0.00042375762,0.0003591012,0.0008346146,0.000121151956,0.000034202807,0.14923535,0.00076864776,0.00055154634,0.007883539,0.0011574448,0.8385721],"study_design_scores_gemma":[0.0015898348,0.0014191169,0.0044306237,0.0022818253,0.000043057375,0.00014868076,0.012892505,0.735596,0.011881912,0.22842865,0.00046967762,0.0008181291],"about_ca_topic_score_codex":0.00022395657,"about_ca_topic_score_gemma":0.00009114115,"teacher_disagreement_score":0.83775395,"about_ca_system_score_codex":0.00023511854,"about_ca_system_score_gemma":0.00010958935,"threshold_uncertainty_score":0.8087194},"labels":[],"label_agreement":null},{"id":"W4405892337","doi":"10.22541/au.173557326.69172598/v1","title":"HTR-JAND: Handwritten Text Recognition with Joint Attention Network and Knowledge Distillation","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":1,"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":"Natural Sciences and Engineering Research Council of Canada","keywords":"Joint (building); Computer science; Speech recognition; Distillation; Artificial intelligence; Natural language processing; Engineering; Chemistry; Structural engineering","score_opus":0.026874695486641044,"score_gpt":0.2563873665745233,"score_spread":0.2295126710878823,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405892337","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":[0.023342451,0.0020311251,0.92782253,0.0017803247,0.001137031,0.001536602,0.000044124074,0.0029600007,0.03934579],"genre_scores_gemma":[0.82080376,0.0007985234,0.17313035,0.00021875209,0.0009845848,0.00053619983,0.00043041544,0.00009943701,0.00299798],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9969865,0.00019708546,0.00061576336,0.0013700597,0.00038175585,0.00044881026],"domain_scores_gemma":[0.99831605,0.000080144535,0.0002787332,0.0007240837,0.00041057638,0.00019042494],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.000776935,0.0005335844,0.000526716,0.0004110879,0.00020663164,0.0012233901,0.00041512848,0.00046182366,0.00008314598],"category_scores_gemma":[0.00003099633,0.0004374905,0.0001629388,0.00051190885,0.00012208386,0.00037563706,0.0020653412,0.00090439053,0.0003907276],"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":[0.000030574858,0.00012894852,0.0003422848,0.0010160815,0.00021219799,0.000044585973,0.00053693476,0.000026025484,0.00024163014,0.009163692,0.01944016,0.9688169],"study_design_scores_gemma":[0.0011990034,0.0007348909,0.0108163245,0.008518782,0.0004702995,0.00042506572,0.00010015233,0.11795994,0.0033458995,0.84552294,0.007976033,0.0029306517],"about_ca_topic_score_codex":0.000082659004,"about_ca_topic_score_gemma":0.00018429747,"teacher_disagreement_score":0.96588624,"about_ca_system_score_codex":0.00014791213,"about_ca_system_score_gemma":0.0002005547,"threshold_uncertainty_score":0.99981344},"labels":[],"label_agreement":null},{"id":"W4405965525","doi":"10.3390/s25010203","title":"Table Extraction with Table Data Using VGG-19 Deep Learning Model","year":2025,"lang":"en","type":"article","venue":"Sensors","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"","keywords":"Table (database); Computer science; Row; Column (typography); Identification (biology); Data mining; Artificial intelligence; Machine learning; Task (project management); Database; Engineering; Frame (networking)","score_opus":0.04168891096115095,"score_gpt":0.3087875127823747,"score_spread":0.26709860182122375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405965525","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":[0.03421584,0.00007660124,0.9570337,0.00017356384,0.00008060383,0.00016653289,0.0000044259273,0.00063343457,0.0076152985],"genre_scores_gemma":[0.39848715,0.00005364215,0.5957772,0.00031662092,0.0000375968,0.000010555294,0.000031631098,0.00002075815,0.005264798],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986858,0.00007580999,0.00018638946,0.0005335565,0.00022030681,0.0002981315],"domain_scores_gemma":[0.99881697,0.00007277559,0.00009964268,0.00081359845,0.00013010696,0.00006690246],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036118206,0.00014003365,0.00016222878,0.00019844476,0.00028323027,0.00024211167,0.0006842139,0.0000796107,0.00001933114],"category_scores_gemma":[0.00010069601,0.00013275945,0.000018302888,0.0007585194,0.00003769826,0.0010606037,0.00034581474,0.00027729565,0.000020831145],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000078477184,0.0003002862,0.0024666847,0.00020272569,0.00016601618,0.00013029594,0.001033076,0.6664046,0.04102958,0.014999859,0.005441111,0.26774725],"study_design_scores_gemma":[0.00017399486,0.000022130289,0.0000279729,0.000063979445,0.00001612751,0.000034132616,0.000081000115,0.98059076,0.01204854,0.001712811,0.005062908,0.00016562342],"about_ca_topic_score_codex":0.00024222014,"about_ca_topic_score_gemma":0.00005396644,"teacher_disagreement_score":0.3642713,"about_ca_system_score_codex":0.000068352674,"about_ca_system_score_gemma":0.00016760611,"threshold_uncertainty_score":0.54137737},"labels":[],"label_agreement":null},{"id":"W4406075203","doi":"10.36227/techrxiv.173610007.79078639/v1","title":"HAND: Hierarchical Attention Network for Multi-Scale Handwritten Document Recognition and Layout Analysis","year":2025,"lang":"en","type":"preprint","venue":"","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":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Scale (ratio); Pattern recognition (psychology); Artificial intelligence; Natural language processing; Cartography; Geography","score_opus":0.040280399896970416,"score_gpt":0.30700751763572787,"score_spread":0.26672711773875746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406075203","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":[0.004237412,0.00026322366,0.9905731,0.0011227097,0.00043736584,0.001652036,0.00024824988,0.0007385837,0.0007272982],"genre_scores_gemma":[0.017924046,0.00029591858,0.9744456,0.0008254509,0.0002615601,0.001502586,0.001439101,0.000021683074,0.003284044],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99656194,0.00026491916,0.000787932,0.0014815186,0.00036027355,0.0005434098],"domain_scores_gemma":[0.9978891,0.00025921583,0.00031615768,0.0008718218,0.0004585555,0.000205156],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0011164849,0.00047118895,0.00082710886,0.00077676406,0.00036354383,0.0011010037,0.0008190711,0.00057381735,0.00005956225],"category_scores_gemma":[0.00006317561,0.00045564448,0.00062604074,0.00078130397,0.00012721424,0.00033744576,0.0016584328,0.000577848,0.00001945842],"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":[0.00011204378,0.00050378224,0.0042068013,0.0009061934,0.0029821496,0.000011576365,0.00084308506,0.0003377514,0.0002507544,0.0031701575,0.009783876,0.9768918],"study_design_scores_gemma":[0.0025806266,0.00032573083,0.009222973,0.0010006761,0.002851005,0.000013739675,0.000055561995,0.69179285,0.0043333187,0.2821286,0.003685799,0.002009155],"about_ca_topic_score_codex":0.00025740868,"about_ca_topic_score_gemma":0.00062247866,"teacher_disagreement_score":0.97488266,"about_ca_system_score_codex":0.00011756554,"about_ca_system_score_gemma":0.00011425383,"threshold_uncertainty_score":0.9999359},"labels":[],"label_agreement":null},{"id":"W4406088539","doi":"10.3390/math13010176","title":"Efficient Image Inpainting for Handwritten Text Removal Using CycleGAN Framework","year":2025,"lang":"en","type":"article","venue":"Mathematics","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Indian Institute of Technology Jodhpur","keywords":"Inpainting; Image (mathematics); Computer science; Artificial intelligence; Pattern recognition (psychology); Computer vision; Natural language processing","score_opus":0.019724432371690727,"score_gpt":0.3027950645457514,"score_spread":0.28307063217406064,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406088539","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":[0.02678835,0.00004563973,0.9671856,0.00058323325,0.00019330066,0.0005495195,0.0000041471467,0.00057418435,0.004076016],"genre_scores_gemma":[0.06014393,0.0000018877463,0.93898624,0.00042369717,0.00005854482,0.000047567144,0.0000013293491,0.00002007186,0.00031672823],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985544,0.000041551106,0.00045498202,0.00034997982,0.00023267958,0.00036638716],"domain_scores_gemma":[0.99837476,0.0005547353,0.00016537207,0.0006368045,0.00020921798,0.00005912796],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008416279,0.00018811607,0.00028744113,0.00024407054,0.00025922936,0.00036828505,0.00072238676,0.00013447861,0.000013555353],"category_scores_gemma":[0.0007571863,0.000180332,0.00013875806,0.0005758914,0.000064612614,0.00011989127,0.00032516097,0.00018444503,0.000025292527],"study_design_candidate":"theoretical_or_conceptual","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":[0.000009830672,0.0006919315,0.000049308393,0.0014823951,0.00011678659,0.000039607112,0.004693777,0.00022618134,0.030913724,0.83382654,0.00292031,0.12502964],"study_design_scores_gemma":[0.00020789562,0.000025043411,0.000010550424,0.00071739714,0.000025761276,0.000033649336,0.00015280073,0.7056536,0.03467381,0.2572548,0.001010387,0.00023428982],"about_ca_topic_score_codex":0.0000049451855,"about_ca_topic_score_gemma":8.29319e-7,"teacher_disagreement_score":0.7054274,"about_ca_system_score_codex":0.00008448379,"about_ca_system_score_gemma":0.00006578311,"threshold_uncertainty_score":0.73537254},"labels":[],"label_agreement":null},{"id":"W4406199199","doi":"10.1016/j.eswa.2025.126461","title":"Rethinking detection based table structure recognition for visually rich document images","year":2025,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Mitacs","keywords":"Computer science; Table (database); Artificial intelligence; Pattern recognition (psychology); Computer vision; Information retrieval; Data mining","score_opus":0.01266045042178457,"score_gpt":0.27734803628360416,"score_spread":0.2646875858618196,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406199199","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":[0.0003728039,0.00029213377,0.99400616,0.0005559951,0.00015983761,0.0027718206,0.0000350056,0.0008526218,0.0009536365],"genre_scores_gemma":[0.71519345,0.0000152340635,0.27032074,0.0005687464,0.00014361809,0.013240549,0.00009910519,0.000023051532,0.00039551235],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99854535,0.000079068224,0.00034444442,0.00055115996,0.0002312106,0.00024878522],"domain_scores_gemma":[0.9984366,0.00019226775,0.00019021073,0.0005924915,0.0005264682,0.000061951585],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002985457,0.00018812867,0.00020069238,0.00027174514,0.000475273,0.00038135366,0.00045083158,0.00012825169,0.000008709876],"category_scores_gemma":[0.000030532137,0.0001658931,0.00004449059,0.0008431374,0.000034960623,0.00044879803,0.000049617895,0.00012826252,0.000009375037],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013982411,0.00046903122,0.000247147,0.0009598425,0.00029558156,0.000004018199,0.0020278452,0.00043358124,0.21597701,0.046549827,0.022912182,0.7099841],"study_design_scores_gemma":[0.0012782882,0.00026769718,0.00009515568,0.00055927725,0.000043145745,0.000029179195,0.00020598932,0.029110095,0.83750784,0.04976142,0.08046364,0.00067826203],"about_ca_topic_score_codex":0.000087394386,"about_ca_topic_score_gemma":0.00002786191,"teacher_disagreement_score":0.7236854,"about_ca_system_score_codex":0.0001429507,"about_ca_system_score_gemma":0.00014869662,"threshold_uncertainty_score":0.67649245},"labels":[],"label_agreement":null},{"id":"W4406659783","doi":"10.1016/j.patcog.2025.111357","title":"A survey of handwriting synthesis from 2019 to 2024: A comprehensive review","year":2025,"lang":"en","type":"review","venue":"Pattern Recognition","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"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":"Ministerio de Universidades; Agencia Estatal de Investigación; European Commission; Ministerio de Ciencia, Innovación y Universidades; Fundación CajaCanarias","keywords":"Handwriting; Computer science; Artificial intelligence; Speech recognition","score_opus":0.08934742922778967,"score_gpt":0.3462928910744655,"score_spread":0.2569454618466758,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406659783","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000014843721,0.873903,0.1189349,0.00007626462,0.00039910266,0.0020778074,0.0038787453,0.00024754496,0.00048118242],"genre_scores_gemma":[0.0000043452483,0.9876921,0.008189797,0.0010100988,0.00008403269,0.0011863392,0.0017020155,0.000047678972,0.00008359771],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.99452984,0.0017337429,0.0016542613,0.0011630469,0.00049838884,0.00042073283],"domain_scores_gemma":[0.99252135,0.004223278,0.000999114,0.001087046,0.0009958018,0.00017339281],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009830769,0.0006619755,0.003050166,0.00076748803,0.000084373045,0.00014819972,0.0014392121,0.00036164533,0.00046675815],"category_scores_gemma":[0.0013815227,0.00063836086,0.0006554214,0.0017175594,0.00003903836,0.0002818377,0.0006842572,0.00047669493,0.0011018522],"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":[0.0000011147044,0.00005033009,0.000005401744,0.04520829,0.00012054089,0.000009964923,0.000011942274,5.847415e-9,7.290398e-7,4.7542517e-7,0.01076832,0.94382286],"study_design_scores_gemma":[0.00013141971,0.000084283776,0.000120211225,0.7150055,0.0010137244,0.000023574492,0.000003707091,0.000024616695,0.00021514895,0.00022438246,0.28205347,0.0010999554],"about_ca_topic_score_codex":0.0014601198,"about_ca_topic_score_gemma":0.00011206667,"teacher_disagreement_score":0.9427229,"about_ca_system_score_codex":0.00012482784,"about_ca_system_score_gemma":0.00033810062,"threshold_uncertainty_score":0.9996759},"labels":[],"label_agreement":null},{"id":"W4406674422","doi":"10.1016/b978-0-08-016349-9.50018-5","title":"10.1016/b978-0-08-016349-9.50018-5","year":2000,"lang":"en","type":"book-chapter","venue":"Time to knit","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Newsprint; Inkwell; Sorption; Materials science; Pulp and paper industry; Environmental science; Composite material; Chemistry; Organic chemistry; Engineering; Adsorption","score_opus":0.010793572510155237,"score_gpt":0.1912791892802392,"score_spread":0.18048561677008398,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406674422","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.6825267e-8,0.00017138435,0.0012276422,0.00032173374,0.000008027266,0.00060887233,0.00007243994,0.0017964562,0.9957934],"genre_scores_gemma":[3.625465e-7,0.00000272322,0.008166143,0.00021797545,0.00032350485,0.0000477657,0.00006724621,0.00011130834,0.991063],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99717915,0.000042501426,0.0005691105,0.0010260142,0.00064508984,0.00053811015],"domain_scores_gemma":[0.9976523,0.00010657159,0.00020381495,0.001466497,0.00021095983,0.00035984788],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00028191693,0.0006319618,0.00063557806,0.00057186495,0.00013703623,0.0003064406,0.002018647,0.0005278254,0.99346375],"category_scores_gemma":[0.000025268328,0.00067017804,0.00030908833,0.0001463152,0.00008922641,0.00035644489,0.00055219955,0.00056562,0.99812114],"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":[0.000009172645,0.000016935643,5.201294e-10,0.000010277492,0.000031421197,0.000039547795,0.000009131575,4.2578478e-7,0.000006274494,0.00060794444,0.27564156,0.7236273],"study_design_scores_gemma":[0.00014875096,0.00026629493,1.5983424e-7,0.00023974602,0.000030888066,0.000067848785,6.020384e-8,0.000083919855,0.00038207776,0.0072325994,0.99073464,0.0008130279],"about_ca_topic_score_codex":0.000009409237,"about_ca_topic_score_gemma":2.709032e-7,"teacher_disagreement_score":0.72281426,"about_ca_system_score_codex":0.00014303366,"about_ca_system_score_gemma":0.00014746764,"threshold_uncertainty_score":0.99957496},"labels":[],"label_agreement":null},{"id":"W4406745964","doi":"10.18280/isi.300117","title":"Identifying the Personality Traits Using Handwriting Recognition in a Real-Time Environment","year":2025,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Handwriting; Big Five personality traits; Personality; Psychology; Computer science; Artificial intelligence; Cognitive psychology; Social psychology","score_opus":0.031184870449715685,"score_gpt":0.2652468139513594,"score_spread":0.23406194350164372,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406745964","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":[0.3261773,0.00005625761,0.66199756,0.0001273802,0.00008108042,0.0005232712,0.000009994598,0.00030291118,0.010724237],"genre_scores_gemma":[0.9435183,0.000083353756,0.055841517,0.00030873992,0.00002965009,0.0001314304,0.000035110883,0.00000690621,0.000044993016],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983749,0.00019508913,0.0006624142,0.00019382812,0.0002782873,0.00029549515],"domain_scores_gemma":[0.999225,0.00013418458,0.0002538816,0.00024015707,0.000109455366,0.000037317437],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001284242,0.00016145915,0.00018281011,0.00039709415,0.00038956196,0.00059684087,0.00042060897,0.00010382525,0.000039010916],"category_scores_gemma":[0.00015407766,0.00014621156,0.000076638105,0.0006488797,0.00010146211,0.0039072763,0.00017579782,0.00018073391,0.00009011857],"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":[0.000016150096,0.0000486703,0.00062633766,0.0003216693,0.00003192516,0.0000045817774,0.011260002,0.00009842297,0.0068436936,0.003538885,0.000164374,0.9770453],"study_design_scores_gemma":[0.0027197597,0.0001899283,0.08840204,0.0056830286,0.00010388901,0.00025463136,0.006953225,0.540187,0.08161207,0.2697288,0.0023869209,0.0017786778],"about_ca_topic_score_codex":0.000293157,"about_ca_topic_score_gemma":0.0000127543535,"teacher_disagreement_score":0.97526664,"about_ca_system_score_codex":0.0005068142,"about_ca_system_score_gemma":0.00008778001,"threshold_uncertainty_score":0.5962334},"labels":[],"label_agreement":null},{"id":"W4406894537","doi":"10.1109/icaase64542.2024.10851029","title":"Advancing Accurate Recognition of Handwritten Arabic Character: An Innovative Hybrid Approach*","year":2024,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Computer science; Character recognition; Arabic; Character (mathematics); Natural language processing; Artificial intelligence; Intelligent character recognition; Speech recognition; Pattern recognition (psychology); Linguistics; Mathematics; Image (mathematics)","score_opus":0.024542112201032994,"score_gpt":0.2768726285357071,"score_spread":0.2523305163346741,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406894537","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":[0.07324698,0.000087399014,0.9133768,0.00032900958,0.00023272584,0.00036543398,0.00003050596,0.0014938224,0.010837308],"genre_scores_gemma":[0.80169153,0.000058344685,0.19729261,0.0003972313,0.00011057937,0.00009966935,0.00011687482,0.000024017309,0.00020912924],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9981517,0.000120685174,0.00049723045,0.00062093546,0.0002892379,0.00032020238],"domain_scores_gemma":[0.99873745,0.00010515888,0.00012857537,0.00044998172,0.00047981678,0.000099005694],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007190555,0.00021318241,0.00027117963,0.0005045268,0.0000698183,0.000303559,0.00057335506,0.00007008107,0.000097238],"category_scores_gemma":[0.00007132789,0.00018590722,0.00007611227,0.001287494,0.00006591725,0.003155849,0.00016402031,0.0002608408,0.00011425135],"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":[0.000009050048,0.00016146092,0.000028885392,0.00015992894,0.000043031836,0.00003018817,0.0008076187,0.0000011899417,0.026310222,0.007324283,0.00095503556,0.9641691],"study_design_scores_gemma":[0.00036454745,0.00054841605,0.0006052943,0.00046877348,0.00002180223,0.0002583996,0.00017950682,0.099439144,0.8572036,0.03554412,0.004610604,0.0007558181],"about_ca_topic_score_codex":0.000024876295,"about_ca_topic_score_gemma":0.0000028893123,"teacher_disagreement_score":0.9634133,"about_ca_system_score_codex":0.00005536241,"about_ca_system_score_gemma":0.00011893136,"threshold_uncertainty_score":0.7581076},"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":"W4407141354","doi":"10.22541/au.173866897.72952916/v1","title":"Base64 Decoding with Ignorable Characters using SIMD instructions","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université TÉLUQ","funders":"","keywords":"SIMD; Decoding methods; Computer science; Parallel computing; Arithmetic; Mathematics; Algorithm","score_opus":0.031876411659650924,"score_gpt":0.2814897438929081,"score_spread":0.24961333223325716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407141354","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":[0.011960599,0.000023052593,0.9598637,0.00033775513,0.00063075323,0.0004808445,0.000021591151,0.001410028,0.025271663],"genre_scores_gemma":[0.100857474,0.0000521224,0.89645135,0.000749632,0.00009435025,0.00011682981,0.00002892954,0.000019912088,0.0016294207],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99810016,0.00008382316,0.00036188492,0.0008192058,0.00029038865,0.00034455035],"domain_scores_gemma":[0.9983122,0.00008184048,0.00022095878,0.000995229,0.00027707996,0.00011270001],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00026260855,0.00032827107,0.00036292383,0.0005889057,0.0002439393,0.00058928126,0.0011144168,0.00024829505,0.00007064343],"category_scores_gemma":[0.000029265524,0.00029864782,0.00011896199,0.0005556288,0.00005982789,0.0005935153,0.0013867605,0.0006294647,0.00001677729],"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":[0.000053052398,0.0006195638,0.0042610266,0.0018226637,0.00095414586,0.00017482838,0.0017692323,0.0038978546,0.0046113334,0.14210385,0.009639567,0.8300929],"study_design_scores_gemma":[0.0013812534,0.0002749723,0.0008090598,0.006097071,0.0002971562,0.00039335436,0.000275506,0.7027103,0.18231192,0.0938451,0.007522306,0.0040820073],"about_ca_topic_score_codex":0.0004182726,"about_ca_topic_score_gemma":0.00007564942,"teacher_disagreement_score":0.8260109,"about_ca_system_score_codex":0.00021345647,"about_ca_system_score_gemma":0.0005916327,"threshold_uncertainty_score":0.9999466},"labels":[],"label_agreement":null},{"id":"W4407253946","doi":"10.1007/978-981-97-8705-0_26","title":"Unlocking Raw Data: The Power of Micro-Inspection in Handwriting Analysis","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","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":"Concordia University","funders":"","keywords":"Handwriting; Computer science; Raw data; Power (physics); Artificial intelligence; Programming language","score_opus":0.019817745536066193,"score_gpt":0.27285573840470195,"score_spread":0.25303799286863576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407253946","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":[0.00019845393,0.00049530016,0.9944554,0.00066601194,0.00049816375,0.0003738922,0.000013663737,0.0001987111,0.0031004162],"genre_scores_gemma":[0.66402626,0.000117579046,0.33451462,0.00097632373,0.00014807278,0.000012095336,0.00002527257,0.000020585368,0.00015921053],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963042,0.00008904489,0.0008164425,0.0015378606,0.0007819531,0.00047050504],"domain_scores_gemma":[0.9958098,0.00083318,0.00044651888,0.0025329574,0.00032108076,0.000056456327],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0021998982,0.00038725926,0.00067292905,0.0025530974,0.00024350747,0.00046083573,0.005466436,0.0002699285,0.000014666784],"category_scores_gemma":[0.00022548396,0.00031683242,0.00017598644,0.0033742886,0.0006217671,0.0007496835,0.0028898362,0.0008825022,0.0000045463607],"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":[0.000009160804,0.00007940622,0.0012562616,0.00009374466,0.00015641062,0.00007607944,0.0016668325,0.007814046,0.0011049197,0.012757468,0.000117908,0.97486776],"study_design_scores_gemma":[0.00040721527,0.00013081249,0.0012929122,0.0017114892,0.00013008702,0.00004532575,0.000002984099,0.88297015,0.030420784,0.08109036,0.00083206984,0.00096583413],"about_ca_topic_score_codex":0.00014682498,"about_ca_topic_score_gemma":0.0006497608,"teacher_disagreement_score":0.9739019,"about_ca_system_score_codex":0.00025043127,"about_ca_system_score_gemma":0.0004394958,"threshold_uncertainty_score":0.99992836},"labels":[],"label_agreement":null},{"id":"W4407417030","doi":"10.69525/jasqde.214","title":"The Effects of Constraint on a Signature’s Static and Dynamic Features","year":2015,"lang":"en","type":"article","venue":"Journal of the American Society of Questioned Document Examiners","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Signature (topology); Constraint (computer-aided design); Computer science; Mathematics","score_opus":0.007786443512853961,"score_gpt":0.26916589387213785,"score_spread":0.2613794503592839,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407417030","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":[0.87416697,0.002011527,0.09609068,0.025927128,0.0006781925,0.0007801414,0.0000061248443,0.00007348623,0.00026574027],"genre_scores_gemma":[0.95991725,0.00068697036,0.038201846,0.0010502464,0.000021001104,0.0000044414783,2.8628517e-7,0.0000072849953,0.00011068682],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984601,0.00030097557,0.0003873409,0.00011670892,0.000589744,0.00014513893],"domain_scores_gemma":[0.9971704,0.0008470182,0.0012733607,0.0002688321,0.00032162745,0.000118757365],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009958543,0.00012676933,0.00029591436,0.000050893435,0.000070887254,0.000054906795,0.0005974438,0.000032748172,4.4328272e-7],"category_scores_gemma":[0.00054795196,0.000069807604,0.00019459518,0.00030133314,0.0007890305,0.00018608982,0.000113169874,0.0002746579,2.793301e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034745067,0.00058267836,0.00096347777,0.00041321127,0.0013282048,0.000020250345,0.012301757,0.0003281313,0.14603288,0.016985891,0.14618088,0.6745152],"study_design_scores_gemma":[0.015180524,0.038623,0.11076346,0.0088679725,0.0011425135,0.0016772059,0.02716907,0.010978081,0.5312819,0.2425376,0.009235017,0.0025436773],"about_ca_topic_score_codex":0.0000361442,"about_ca_topic_score_gemma":0.0000018827667,"teacher_disagreement_score":0.6719715,"about_ca_system_score_codex":0.00012188936,"about_ca_system_score_gemma":0.0001898186,"threshold_uncertainty_score":0.2907216},"labels":[],"label_agreement":null},{"id":"W4407417434","doi":"10.69525/jasqde.269","title":"Forensic Handwriting Identification: Fundamental Concepts and Principles (2nd Edition)","year":2020,"lang":"en","type":"article","venue":"Journal of the American Society of Questioned Document Examiners","topic":"Handwritten Text Recognition Techniques","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":"Government of Canada","funders":"","keywords":"Handwriting; Identification (biology); Computer science; Engineering ethics; Psychology; Engineering; Artificial intelligence; Biology","score_opus":0.02696684877435519,"score_gpt":0.2881317744554926,"score_spread":0.2611649256811374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407417434","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":[0.59019876,0.00033738796,0.37536982,0.033230413,0.00028102993,0.00032437494,0.000009640952,0.00009873338,0.00014985823],"genre_scores_gemma":[0.9113713,0.000246888,0.08587847,0.0022239827,0.00020419336,0.0000046507,0.0000017726143,0.0000085466445,0.00006019673],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983414,0.0001472717,0.00063717243,0.00019236976,0.0005302553,0.00015157333],"domain_scores_gemma":[0.99765915,0.00014718487,0.001558155,0.00019675972,0.00030689308,0.00013183814],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058464945,0.00013251553,0.00030022988,0.00004049,0.00013714393,0.0001355588,0.00055887137,0.00002850329,0.0000115525745],"category_scores_gemma":[0.00013581465,0.00010334857,0.00023333276,0.00042336778,0.00057401275,0.00074172084,0.00021621968,0.00019998144,0.0000017344779],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017127795,0.00043146842,0.022148987,0.00046843334,0.0011302577,0.000020453936,0.018244036,0.00045215402,0.39107326,0.021628179,0.08366089,0.4605706],"study_design_scores_gemma":[0.007006246,0.0052796244,0.21947557,0.0022618466,0.0005975739,0.0014381928,0.026961967,0.02307317,0.6578929,0.01999957,0.033892944,0.0021204054],"about_ca_topic_score_codex":0.000019028837,"about_ca_topic_score_gemma":7.7532366e-7,"teacher_disagreement_score":0.4584502,"about_ca_system_score_codex":0.00009115402,"about_ca_system_score_gemma":0.00008450891,"threshold_uncertainty_score":0.42144322},"labels":[],"label_agreement":null},{"id":"W4408062992","doi":"10.5220/0013340100003905","title":"TokenOCR: An Attention Based Foundational Model for Intelligent Optical Character Recognition","year":2025,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","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":"Government of Canada; Department of National Defence","funders":"","keywords":"Computer science; Character (mathematics); Character recognition; Optical character recognition; Artificial intelligence; Cognitive science; Natural language processing; Psychology; Mathematics","score_opus":0.053160653540065744,"score_gpt":0.31771071711230003,"score_spread":0.2645500635722343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408062992","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":[0.00451496,0.0000029138162,0.98879284,0.0022301667,0.00017946617,0.0005282403,0.000014019908,0.0005101658,0.0032272108],"genre_scores_gemma":[0.24308777,0.000004721287,0.7513253,0.0033840775,0.00005593716,0.0004113311,0.00035906426,0.000009179425,0.0013626382],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988639,0.000038249927,0.00030246144,0.00041042164,0.00017972496,0.00020523948],"domain_scores_gemma":[0.9990501,0.00011028316,0.000054942535,0.00029309557,0.00041767544,0.000073947864],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039214015,0.00012461214,0.000120721445,0.00024988924,0.0001300034,0.0002481822,0.0003531141,0.00009272039,0.000107363965],"category_scores_gemma":[0.000061863895,0.000121636804,0.000101101934,0.00020631663,0.000030872136,0.00090537407,0.00006627096,0.000086271764,0.00007257473],"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":[0.0000383076,0.00037675948,0.000066831264,0.00004284313,0.000020172056,7.4692827e-7,0.00004403167,0.000056859557,0.0048968466,0.14007127,0.0019052817,0.85248005],"study_design_scores_gemma":[0.00027416414,0.00008249592,0.00027075058,0.000035827838,0.000010791976,0.00000150472,0.00000610175,0.8747591,0.037406415,0.08620318,0.00079687487,0.00015284799],"about_ca_topic_score_codex":0.000003254437,"about_ca_topic_score_gemma":0.000009586176,"teacher_disagreement_score":0.8747022,"about_ca_system_score_codex":0.0000820009,"about_ca_system_score_gemma":0.00013800355,"threshold_uncertainty_score":0.4960205},"labels":[],"label_agreement":null},{"id":"W4408062994","doi":"10.5220/0013318800003905","title":"Automated Handwriting Pattern Recognition for Multi-Level Personality Classification Using Transformer OCR (TrOCR)","year":2025,"lang":"en","type":"article","venue":"","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":"Concordia University","funders":"","keywords":"Computer science; Handwriting; Artificial intelligence; Pattern recognition (psychology); Transformer; Speech recognition; Optical character recognition; Engineering","score_opus":0.17281086456275271,"score_gpt":0.36530128643383486,"score_spread":0.19249042187108215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408062994","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":[0.017602948,0.000022443355,0.9769806,0.0008636423,0.00014731522,0.0007878643,0.00006335311,0.002186747,0.001345053],"genre_scores_gemma":[0.5174393,0.000007509829,0.4812687,0.0008018867,0.000031223215,0.00017887066,0.000069682115,0.000012208695,0.00019061084],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99837554,0.00009500089,0.00047026118,0.0005382076,0.00018899763,0.00033199936],"domain_scores_gemma":[0.9989407,0.0001419661,0.00012297864,0.00027638098,0.0004506796,0.000067307046],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005735397,0.00019808627,0.000217425,0.0002683441,0.00032947503,0.00025752714,0.00038145154,0.00015390987,0.000038415368],"category_scores_gemma":[0.000092969276,0.00019896227,0.00015108867,0.00046687698,0.000044878914,0.0007684511,0.00003618082,0.00013140886,0.000020615662],"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":[0.000011247827,0.00018185386,0.00060473126,0.00017008574,0.000044058976,0.0000011768186,0.00024191046,0.0000010036467,0.03430331,0.0012857977,0.0008831274,0.9622717],"study_design_scores_gemma":[0.0009491172,0.00003737147,0.0060144565,0.00021186128,0.0000295787,0.000009497881,0.00014515848,0.8810869,0.10881945,0.0021456121,0.0002573003,0.00029368023],"about_ca_topic_score_codex":0.00012851568,"about_ca_topic_score_gemma":0.00007329379,"teacher_disagreement_score":0.961978,"about_ca_system_score_codex":0.00011738283,"about_ca_system_score_gemma":0.000120915385,"threshold_uncertainty_score":0.8113446},"labels":[],"label_agreement":null},{"id":"W4408596706","doi":"10.1016/j.nucengdes.2025.114002","title":"Automating equipment identification in nuclear engineering drawings","year":2025,"lang":"en","type":"article","venue":"Nuclear Engineering and Design","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Power Generation; Dalhousie University","funders":"Ontario Power Generation","keywords":"Identification (biology); Engineering; Forensic engineering; Engineering drawing; Nuclear engineering; Construction engineering; Systems engineering","score_opus":0.008921568396107048,"score_gpt":0.21470888749522565,"score_spread":0.2057873190991186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408596706","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":[0.038351767,0.00009281429,0.9593065,0.00023550165,0.00015073235,0.0002002717,3.394284e-7,0.0013639785,0.00029812587],"genre_scores_gemma":[0.7987217,0.000022311517,0.20107558,0.000092867755,0.000013685258,0.000016574122,4.984276e-7,0.000019583033,0.00003724575],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990946,0.000022291717,0.00025780455,0.00028292727,0.00011844585,0.00022392927],"domain_scores_gemma":[0.99957305,0.00008236124,0.000036105062,0.00023030717,0.000027165637,0.000050984698],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044412687,0.00013248614,0.00014246357,0.00037176156,0.00006230993,0.00027375107,0.0002795629,0.00007752282,0.000006913571],"category_scores_gemma":[0.00010141424,0.00015348206,0.00002885252,0.0004076308,0.000009194305,0.00035914333,0.00012611542,0.00016302419,0.000023385017],"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":[0.000014530127,0.00015408704,0.00014431855,0.0006211911,0.00007806377,0.00006191497,0.003924759,0.02903688,0.4735848,0.20662174,0.0023027076,0.283455],"study_design_scores_gemma":[0.0001822699,0.000026543432,0.0027447727,0.00026526413,0.0000041443304,0.000008555553,0.000016826603,0.98812973,0.006517125,0.00045205,0.0014645514,0.00018814321],"about_ca_topic_score_codex":0.0000090154335,"about_ca_topic_score_gemma":1.1965977e-7,"teacher_disagreement_score":0.95909286,"about_ca_system_score_codex":0.00007797981,"about_ca_system_score_gemma":0.000013622621,"threshold_uncertainty_score":0.62588173},"labels":[],"label_agreement":null},{"id":"W4408861120","doi":"10.1109/icce63647.2025.10930185","title":"TextureMeDefect: LLM-based Synthetic Railway Defect Texture on Mobile Devices","year":2025,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; University of Ottawa","funders":"","keywords":"Computer science; Texture (cosmology); Artificial intelligence; Image (mathematics)","score_opus":0.008646146351104854,"score_gpt":0.2591624161984798,"score_spread":0.25051626984737496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408861120","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":[0.0042210734,0.0003336021,0.8515778,0.0014002691,0.000300439,0.00080945384,0.0000040379205,0.0021927026,0.13916062],"genre_scores_gemma":[0.9661602,0.0000089300465,0.024084382,0.0072188233,0.000032018128,0.0003006536,0.000005532879,0.000016129105,0.002173348],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99805474,0.0001727445,0.00030220434,0.0007154356,0.0003563663,0.00039851156],"domain_scores_gemma":[0.99814874,0.0005260166,0.00008526611,0.0009845321,0.00014983905,0.00010558177],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044996195,0.00029371018,0.00028706327,0.00045889543,0.00020132917,0.00029528572,0.0011558351,0.00018972626,0.00032580612],"category_scores_gemma":[0.00012337322,0.00023284646,0.00026582243,0.0009261608,0.00007187973,0.00024100598,0.00016433153,0.00029517367,0.0004963695],"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":[0.000027681457,0.0007379161,0.0006840811,0.00016639652,0.00008739986,0.000037445043,0.00010702154,0.00008221936,0.0033356189,0.07635403,0.03356007,0.8848201],"study_design_scores_gemma":[0.0016157641,0.0015521948,0.0022287113,0.0011221131,0.0000948089,0.000027333455,0.000060674036,0.030125925,0.7100535,0.027125115,0.22448428,0.0015095938],"about_ca_topic_score_codex":0.000023422639,"about_ca_topic_score_gemma":0.00004321968,"teacher_disagreement_score":0.9619391,"about_ca_system_score_codex":0.000086922024,"about_ca_system_score_gemma":0.00015874555,"threshold_uncertainty_score":0.94952035},"labels":[],"label_agreement":null},{"id":"W4408980177","doi":"10.1007/978-981-96-0143-1_7","title":"Automatic Table Detection and Tabular Data Extraction from Scanned Documents","year":2025,"lang":"en","type":"book-chapter","venue":"Smart innovation, systems and technologies","topic":"Handwritten Text Recognition Techniques","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":"Lakehead University","funders":"","keywords":"Table (database); Computer science; Extraction (chemistry); Information retrieval; Artificial intelligence; Pattern recognition (psychology); Database; Chromatography; Chemistry","score_opus":0.025238451956285667,"score_gpt":0.2619397415263762,"score_spread":0.23670128957009057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408980177","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":[0.003611927,0.010394562,0.92270523,0.0015975647,0.0025623897,0.0030308932,0.00058388396,0.0125409365,0.042972613],"genre_scores_gemma":[0.70253676,0.010026805,0.11572682,0.0003745799,0.00050100056,0.001124907,0.0026924636,0.0002248425,0.16679181],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99780977,0.000024700903,0.0007453045,0.0009056794,0.00030452467,0.00021005077],"domain_scores_gemma":[0.99742705,0.00010555112,0.00059776736,0.0014334247,0.00041678533,0.000019447818],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00053358736,0.00035596223,0.00046346974,0.0010830278,0.000289863,0.0006276518,0.00081553106,0.0006926874,0.000010956973],"category_scores_gemma":[0.0001972994,0.0003467352,0.000019125593,0.000530418,0.00013839746,0.0012249965,0.0010446319,0.00040013817,0.000011064613],"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":[0.0000030028011,0.000014515392,0.00013431694,0.00030846274,0.00015547233,0.000009231514,0.000021094038,1.5855773e-7,0.0009337701,0.23542447,0.007334053,0.7556614],"study_design_scores_gemma":[0.0006949919,0.00021936723,0.0003354249,0.0032783006,0.00014803128,0.00010251509,0.00029575973,0.02590168,0.0101565365,0.4149238,0.5425775,0.0013661311],"about_ca_topic_score_codex":0.00040793887,"about_ca_topic_score_gemma":0.000074140306,"teacher_disagreement_score":0.8069784,"about_ca_system_score_codex":0.00009246494,"about_ca_system_score_gemma":0.00008860383,"threshold_uncertainty_score":0.9998985},"labels":[],"label_agreement":null},{"id":"W4409094360","doi":"10.1145/3727623","title":"<i>DeepHadad</i> : Enhancing Readability of Damaged Inscriptions with Synthetic Data","year":2025,"lang":"en","type":"article","venue":"Journal on Computing and Cultural Heritage","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Arab-German Young Academy of Sciences and Humanities","keywords":"Readability; Computer science; Archaeology; Geography; Programming language","score_opus":0.023691131902178565,"score_gpt":0.2898824407683843,"score_spread":0.26619130886620573,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409094360","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":[0.7082719,0.00023688226,0.28687504,0.0008879045,0.00019669926,0.00014216162,0.0000057839056,0.00018821056,0.0031953778],"genre_scores_gemma":[0.94968444,0.000044279524,0.049819916,0.0002759382,0.000038165876,0.000001069857,0.000003198419,0.0000044996905,0.00012850731],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986857,0.00017274024,0.00038495712,0.00034010274,0.00022394283,0.00019252978],"domain_scores_gemma":[0.99875927,0.0001744262,0.00019795037,0.00054699276,0.00023975532,0.00008161],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008165169,0.00014172585,0.00024214406,0.000091366506,0.00037248468,0.0003729974,0.00074966945,0.000049197333,0.0000061572146],"category_scores_gemma":[0.0001507843,0.00009647782,0.000041470576,0.00034882044,0.00009340025,0.000770162,0.00033517936,0.00039806194,0.0000016227167],"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":[0.00009456849,0.0007874575,0.0038559965,0.00042189588,0.00023664806,0.00013331555,0.0038851476,0.00006101848,0.05592294,0.012070486,0.005979126,0.9165514],"study_design_scores_gemma":[0.006660793,0.0067455233,0.12112767,0.027891627,0.0006836023,0.0062472895,0.01957539,0.24370162,0.47701997,0.038520556,0.046577152,0.005248811],"about_ca_topic_score_codex":0.000014656601,"about_ca_topic_score_gemma":0.000015299369,"teacher_disagreement_score":0.91130257,"about_ca_system_score_codex":0.000039666793,"about_ca_system_score_gemma":0.00006821257,"threshold_uncertainty_score":0.39342514},"labels":[],"label_agreement":null},{"id":"W4409197052","doi":"10.1134/s1054661824700846","title":"Mining Handwriting Images to Predict Alzheimer’s","year":2024,"lang":"en","type":"article","venue":"Pattern Recognition and Image Analysis","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Handwriting; Computer science; Artificial intelligence; Pattern recognition (psychology)","score_opus":0.033927855952323505,"score_gpt":0.28711871418851304,"score_spread":0.25319085823618953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409197052","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":[0.023307277,0.00071699644,0.97063506,0.0014975508,0.00009106909,0.00018260887,0.00008779795,0.0009715163,0.0025101546],"genre_scores_gemma":[0.9156399,0.00022732757,0.08189789,0.0016637761,0.00015721936,0.00012020199,0.00013949382,0.000025391942,0.00012881366],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99820894,0.000110132605,0.0003739006,0.0007155384,0.0002741336,0.00031734063],"domain_scores_gemma":[0.9990867,0.00016727585,0.000057842695,0.0002939422,0.00018393998,0.00021031103],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004850931,0.00021556085,0.0002958352,0.0011454326,0.00015338608,0.0013659102,0.00028652238,0.00006589142,0.00042382986],"category_scores_gemma":[0.00006855788,0.00020959109,0.00022468505,0.0017130217,0.000043162894,0.0010822517,0.00020755152,0.00015186085,0.00051061105],"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":[0.0000013783016,0.000020443222,0.0007695286,0.00003260924,0.00055553956,0.00007417857,0.00044959344,4.0262003e-7,0.0022119568,0.0000044977037,0.0020338867,0.993846],"study_design_scores_gemma":[0.0014326939,0.0009305784,0.024410715,0.0023336292,0.0109242555,0.0005507628,0.001904976,0.4084661,0.52283776,0.0092717,0.012306132,0.0046307193],"about_ca_topic_score_codex":0.000086098575,"about_ca_topic_score_gemma":0.000028406826,"teacher_disagreement_score":0.98921525,"about_ca_system_score_codex":0.00002086091,"about_ca_system_score_gemma":0.000021427151,"threshold_uncertainty_score":0.99967074},"labels":[],"label_agreement":null},{"id":"W4409205024","doi":"10.1134/s1054661824701141","title":"Determining Optimal Granularity for Effective Handwriting Analysis","year":2024,"lang":"en","type":"article","venue":"Pattern Recognition and Image Analysis","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Granularity; Handwriting; Computer science; Pattern recognition (psychology); Artificial intelligence; Natural language processing","score_opus":0.019515784101361882,"score_gpt":0.28600168791350833,"score_spread":0.26648590381214643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409205024","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":[0.094093524,0.00016814243,0.9042183,0.00020449521,0.00005112426,0.00033690472,0.00017011272,0.0005425461,0.00021483633],"genre_scores_gemma":[0.9209908,0.000084559484,0.07769602,0.0003494709,0.00008476618,0.00035633755,0.00038049964,0.000017717079,0.00003978635],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980093,0.00015972584,0.00042091892,0.0008458559,0.00022657115,0.00033761145],"domain_scores_gemma":[0.9986806,0.0004964422,0.00010616088,0.00029890364,0.00027955492,0.00013835951],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007018608,0.00024823673,0.00051377004,0.0017963724,0.00024479278,0.0012804902,0.00025047868,0.0001019977,0.00014179546],"category_scores_gemma":[0.00009890875,0.00024306901,0.00078250555,0.0029476718,0.00006357993,0.0010459586,0.00012570574,0.00018610149,0.0000537181],"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":[0.000003832238,0.000034832126,0.003949178,0.00010230668,0.003065925,0.000037813446,0.00048240542,0.0000040295345,0.00093819754,0.000010598931,0.00005353853,0.99131733],"study_design_scores_gemma":[0.00044349927,0.00015318349,0.012072429,0.00012656485,0.010769249,0.000028697881,0.00013186262,0.94475657,0.027719742,0.0027973712,0.00030675938,0.00069407333],"about_ca_topic_score_codex":0.000089739515,"about_ca_topic_score_gemma":0.000083533414,"teacher_disagreement_score":0.9906233,"about_ca_system_score_codex":0.00004055717,"about_ca_system_score_gemma":0.000015554226,"threshold_uncertainty_score":0.9997563},"labels":[],"label_agreement":null},{"id":"W4409369895","doi":"10.1609/aaai.v39i3.32283","title":"Latent Diffusion-Enhanced Virtual Try-On via Optimized Pseudo-Label Generation","year":2025,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Key Research and Development Program of China; Wuhan University of Technology; Wuhan University; National Natural Science Foundation of China","keywords":"Diffusion; Computer science; Physics; Thermodynamics","score_opus":0.05674266309541768,"score_gpt":0.29898978350991107,"score_spread":0.2422471204144934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409369895","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":[0.19134416,0.000009146103,0.79102874,0.0042611314,0.0007988115,0.00080532365,0.0000048086695,0.00034537932,0.011402523],"genre_scores_gemma":[0.98166937,0.000079979545,0.016242294,0.0008815659,0.00007347175,0.00012109062,0.0000016697463,0.000013041205,0.00091753964],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99762064,0.000039655733,0.0007207042,0.00069552416,0.0005626773,0.00036077117],"domain_scores_gemma":[0.99809897,0.000114897695,0.00038277695,0.00041708222,0.000899749,0.00008652187],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050754024,0.00030713537,0.00035199293,0.00029876668,0.0003143468,0.0003402436,0.0018907131,0.00016912146,0.0000931885],"category_scores_gemma":[0.0003868434,0.00023556601,0.00014229184,0.00091853447,0.00021095248,0.00043238897,0.00044151576,0.00038789277,0.00012075458],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007206087,0.00026279874,0.000005706979,0.0000133286085,0.000014245512,2.5555545e-7,0.0002957465,0.000039326955,0.3838894,0.3748926,0.00035515116,0.24015938],"study_design_scores_gemma":[0.00007341237,0.00027018815,0.00002858021,0.00023230638,0.000010633864,0.0000011957308,0.000055448654,0.21316025,0.71343386,0.07253204,0.00002058523,0.00018149654],"about_ca_topic_score_codex":0.000022107277,"about_ca_topic_score_gemma":0.000005613906,"teacher_disagreement_score":0.79032516,"about_ca_system_score_codex":0.00009349562,"about_ca_system_score_gemma":0.000116210875,"threshold_uncertainty_score":0.96061033},"labels":[],"label_agreement":null},{"id":"W4410216492","doi":"10.1007/978-3-031-87663-9_6","title":"A Comprehensive Approach to Handwriting Analysis for Alzheimer’s Detection","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Handwritten Text Recognition Techniques","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":"Concordia University","funders":"","keywords":"Computer science; Handwriting; Artificial intelligence","score_opus":0.037011335309276985,"score_gpt":0.2821976279744096,"score_spread":0.24518629266513264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410216492","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":[0.000013475835,0.00036694598,0.99209696,0.00029767086,0.00052950083,0.0013999806,0.000020844696,0.00046999846,0.0048046047],"genre_scores_gemma":[0.0751621,0.000017449813,0.9218325,0.00228249,0.0002519219,0.00018228141,0.000019928075,0.000027863645,0.00022347782],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.995744,0.000047713816,0.00066536566,0.0021071916,0.0007383486,0.0006974131],"domain_scores_gemma":[0.99661976,0.0007503538,0.00027994477,0.0012912756,0.0008538385,0.00020483001],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007638606,0.0005763513,0.000865738,0.0035054055,0.00041981455,0.00076836423,0.002705932,0.0003832979,0.0000048838897],"category_scores_gemma":[0.0001273778,0.0005861167,0.00041210055,0.0027363019,0.00027242,0.00045049822,0.0011786297,0.00057341234,0.000012174665],"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":[0.0000083312525,0.000032508,0.000007824115,0.00006030659,0.00018235776,0.000005584455,0.00030162995,0.008200988,0.00031505153,0.0048907264,0.00003541765,0.9859593],"study_design_scores_gemma":[0.00032658322,0.00027542963,0.000072069546,0.00033372568,0.0002623359,0.000028129614,6.890719e-7,0.89370793,0.02674917,0.07318343,0.003978322,0.0010822017],"about_ca_topic_score_codex":0.000036439214,"about_ca_topic_score_gemma":0.00007108112,"teacher_disagreement_score":0.98487705,"about_ca_system_score_codex":0.00027816553,"about_ca_system_score_gemma":0.00033103253,"threshold_uncertainty_score":0.999659},"labels":[],"label_agreement":null},{"id":"W4410216540","doi":"10.1007/978-3-031-87663-9_34","title":"Optimizing Granularity for Enhanced Handwriting Analysis","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Handwritten Text Recognition Techniques","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":"Concordia University","funders":"","keywords":"Computer science; Granularity; Handwriting; Artificial intelligence; Programming language","score_opus":0.01610035009770196,"score_gpt":0.270233114205087,"score_spread":0.25413276410738506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410216540","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":[0.000021913494,0.00027464525,0.9921664,0.0004232817,0.00059728546,0.000790131,0.000022316683,0.0005107168,0.0051933215],"genre_scores_gemma":[0.06359568,0.000050339087,0.9342525,0.001209299,0.00020739024,0.00007365339,0.000025096617,0.000023572926,0.000562456],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956401,0.0000415709,0.00076801464,0.0020156791,0.00076000777,0.00077465695],"domain_scores_gemma":[0.9963359,0.001008747,0.0003770708,0.0014566579,0.0006661972,0.00015541243],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013054127,0.00058035756,0.00094443525,0.0026401242,0.00046959202,0.00093392923,0.0033562838,0.00044569597,0.000019713205],"category_scores_gemma":[0.00025646412,0.00059393025,0.00051799207,0.0020024467,0.00041934854,0.0006647377,0.0012149354,0.00072599476,0.0000070637548],"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":[0.000006331259,0.000027976826,0.000017907492,0.00009608455,0.00010591476,0.000017365035,0.00045915227,0.004395098,0.0006669694,0.015465075,0.00001969377,0.97872245],"study_design_scores_gemma":[0.0004066365,0.00013199114,0.000025545838,0.00072349416,0.00016439092,0.000009077536,2.3748397e-7,0.64396954,0.0781544,0.27459106,0.00079094747,0.0010326817],"about_ca_topic_score_codex":0.000027000151,"about_ca_topic_score_gemma":0.00014251687,"teacher_disagreement_score":0.97768974,"about_ca_system_score_codex":0.00032723628,"about_ca_system_score_gemma":0.00045759653,"threshold_uncertainty_score":0.9996512},"labels":[],"label_agreement":null},{"id":"W4410241908","doi":"10.18280/mmep.120430","title":"DoubleYolo: Efficient Scene Text Detection Using Double Edge Method and YOLOv8n","year":2025,"lang":"en","type":"article","venue":"Mathematical Modelling and Engineering Problems","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Enhanced Data Rates for GSM Evolution; Computer vision; Computer science; Artificial intelligence; Computer graphics (images)","score_opus":0.029487057284387528,"score_gpt":0.26405629785320206,"score_spread":0.23456924056881454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410241908","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":[0.033255097,0.00028297602,0.9651343,0.00009118645,0.00008042369,0.00025916952,4.1230376e-7,0.0004934582,0.00040298054],"genre_scores_gemma":[0.5032597,0.000023451978,0.49660304,0.000015527907,0.0000114683735,0.000030791252,2.5686427e-7,0.000010195867,0.000045529774],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989245,0.000019660712,0.0002910635,0.00036439017,0.00012800285,0.00027237087],"domain_scores_gemma":[0.999452,0.0001314599,0.000039269864,0.00023116486,0.00005600485,0.00009009003],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005788592,0.00017970633,0.00024488237,0.00022513233,0.00012688291,0.00022383887,0.00016112329,0.00011325762,0.000002175555],"category_scores_gemma":[0.000015983525,0.0001645327,0.00003847969,0.00031610546,0.000027101934,0.0001351263,0.00015947118,0.00019235707,0.000003724793],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008065179,0.00008319694,0.0000030203137,0.0010886962,0.000038828777,0.0000024664241,0.0006225033,0.8689714,0.01116671,0.08211166,0.0000038567046,0.035899576],"study_design_scores_gemma":[0.00026956352,0.000023523893,0.0000018803169,0.0003726106,0.000017899009,0.000034983233,0.0000049858722,0.9479633,0.018333144,0.03272661,0.00008441433,0.00016711322],"about_ca_topic_score_codex":0.000017288634,"about_ca_topic_score_gemma":2.4326147e-7,"teacher_disagreement_score":0.47000465,"about_ca_system_score_codex":0.00003648554,"about_ca_system_score_gemma":0.00001490311,"threshold_uncertainty_score":0.67094487},"labels":[],"label_agreement":null},{"id":"W4410248697","doi":"10.1007/978-3-031-87663-9_25","title":"A Multi-model Approach for Personality Detection from Handwriting: Deep Features, Machine Learning, and Ensemble Techniques","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Handwritten Text Recognition Techniques","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":"Concordia University","funders":"","keywords":"Computer science; Handwriting; Artificial intelligence; Machine learning; Deep learning; Ensemble learning","score_opus":0.01895257687005201,"score_gpt":0.26394954817551,"score_spread":0.24499697130545797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410248697","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":[0.000017977753,0.0013935465,0.9948531,0.00017852843,0.00016773547,0.0010879835,0.00003777909,0.000800501,0.001462853],"genre_scores_gemma":[0.032562878,0.00016051256,0.9654573,0.00064258615,0.00017686775,0.00012661962,0.00004916856,0.000036543963,0.0007874833],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962222,0.000071384944,0.0004956935,0.002051569,0.000586551,0.0005726314],"domain_scores_gemma":[0.99795955,0.0005457796,0.00031648573,0.0006261125,0.00039526768,0.00015679946],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011124496,0.0006219388,0.00065233634,0.00082611566,0.00054373225,0.00073100795,0.0014228817,0.0006227496,0.0000041112617],"category_scores_gemma":[0.00025393706,0.0006040074,0.00018469094,0.00037661268,0.00047246378,0.0004870485,0.001055065,0.0012386912,0.0000012629647],"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":[0.000016604254,0.00004834943,0.000021340906,0.00010914005,0.000018469676,0.00000671543,0.00041907444,0.0003294538,0.003571886,0.00094588264,0.000013875413,0.9944992],"study_design_scores_gemma":[0.00032551403,0.00015573404,0.000015638405,0.00028478028,0.000020417774,0.00003712983,4.0760386e-7,0.8982937,0.05379149,0.045807462,0.0006642637,0.0006034668],"about_ca_topic_score_codex":0.00017183066,"about_ca_topic_score_gemma":0.00038541382,"teacher_disagreement_score":0.99389577,"about_ca_system_score_codex":0.0002707041,"about_ca_system_score_gemma":0.0002683049,"threshold_uncertainty_score":0.9996411},"labels":[],"label_agreement":null},{"id":"W4410604347","doi":"10.1007/s00371-025-03982-x","title":"Enhancing scene text script identification through multi-task self-supervised learning","year":2025,"lang":"en","type":"article","venue":"The Visual Computer","topic":"Handwritten Text Recognition Techniques","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":"Concordia University","funders":"Natural Science Foundation of Jiangxi Province; National Natural Science Foundation of China","keywords":"Computer science; Task (project management); Identification (biology); Computer graphics; Artificial intelligence; Human–computer interaction; Natural language processing; Pattern recognition (psychology); Engineering","score_opus":0.019325376714727074,"score_gpt":0.30204001102849476,"score_spread":0.2827146343137677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410604347","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":[0.020635312,0.00017809034,0.9749001,0.0009175371,0.00060052855,0.00041076643,6.982331e-7,0.0015890625,0.0007678827],"genre_scores_gemma":[0.70065594,0.000052833882,0.29592207,0.0021820967,0.00019257721,0.00006613071,0.000009046714,0.000017688288,0.00090158556],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979029,0.00038905605,0.00047029858,0.00056728156,0.00030077275,0.00036963375],"domain_scores_gemma":[0.9987581,0.00020352787,0.00014500284,0.00060417637,0.00023971783,0.000049494905],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007930959,0.00023040606,0.00023074566,0.00018200673,0.0005470832,0.0006011345,0.001237827,0.00010231512,0.000019348994],"category_scores_gemma":[0.00003809381,0.00018463747,0.00011781381,0.0008513387,0.000064942076,0.0007465293,0.00066683453,0.00038829865,0.00033826934],"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":[0.000017727754,0.00066324155,0.0005523868,0.0001834382,0.0002014325,0.000015738167,0.0075750896,0.000110112014,0.09560839,0.019959427,0.007113365,0.8679997],"study_design_scores_gemma":[0.0006460844,0.00014279797,0.0029826765,0.00018637074,0.00003444949,0.0000150023925,0.0000784492,0.79844993,0.18456079,0.003219315,0.00928128,0.00040284116],"about_ca_topic_score_codex":0.000048118898,"about_ca_topic_score_gemma":0.00000764905,"teacher_disagreement_score":0.8675968,"about_ca_system_score_codex":0.000088279754,"about_ca_system_score_gemma":0.000083475396,"threshold_uncertainty_score":0.75292975},"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":"W4410761886","doi":"10.1080/01615440.2025.2500309","title":"Unlocking the archives: Using large language models to transcribe handwritten historical documents","year":2025,"lang":"en","type":"article","venue":"Historical Methods A Journal of Quantitative and Interdisciplinary History","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University","funders":"","keywords":"Computer science; Natural language processing","score_opus":0.08453474367525225,"score_gpt":0.40172167011081916,"score_spread":0.3171869264355669,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410761886","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":[0.0015329177,0.025785156,0.96471894,0.0029229615,0.0016784485,0.00020982129,0.0000021193912,0.000053053685,0.0030965933],"genre_scores_gemma":[0.03309767,0.00020194652,0.9629442,0.0011530865,0.00011392479,0.000022766728,5.028678e-7,0.000024427834,0.0024414747],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968067,0.0011467901,0.0009235339,0.00041587857,0.00035011448,0.00035701448],"domain_scores_gemma":[0.99774444,0.0009988808,0.000419245,0.00038462368,0.0002276989,0.0002250936],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002033723,0.00027337816,0.0006515877,0.00087045354,0.00038780816,0.000055818353,0.0010146201,0.00009758338,0.000015640113],"category_scores_gemma":[0.0002062196,0.00020220566,0.00033544883,0.00049246376,0.00011216454,0.00079565536,0.0006702095,0.0006455787,0.0000016388337],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010588547,0.0012721082,0.000058434027,0.00030124057,0.0006290931,0.0004318091,0.22156654,0.00016994894,0.0898625,0.1480619,0.12602788,0.41055968],"study_design_scores_gemma":[0.0027804088,0.004437109,0.00018455605,0.002230236,0.00052275043,0.00045165612,0.00810581,0.0769201,0.0045712115,0.22436447,0.67396456,0.0014671333],"about_ca_topic_score_codex":0.00004061153,"about_ca_topic_score_gemma":0.000008613775,"teacher_disagreement_score":0.5479367,"about_ca_system_score_codex":0.0040965625,"about_ca_system_score_gemma":0.00022576949,"threshold_uncertainty_score":0.99972653},"labels":[],"label_agreement":null},{"id":"W4411020509","doi":"10.1093/jcde/qwaf053","title":"Optimizing image format piping and instrumentation diagram recognition: Integrating symbol and text recognition with a single backbone architecture","year":2025,"lang":"en","type":"article","venue":"Journal of Computational Design and Engineering","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"ASTER","funders":"Ministry of Science and ICT, South Korea; Ministry of Education, India; National Research Foundation; National Research Foundation of Korea; Ministry of Education","keywords":"Symbol (formal); Instrumentation (computer programming); Architecture; Piping; Diagram; Computer science; Engineering drawing; Artificial intelligence; Pattern recognition (psychology); Computer vision; Speech recognition; Natural language processing; Engineering; Mechanical engineering; Programming language; Database","score_opus":0.011713344175164665,"score_gpt":0.2171274700654885,"score_spread":0.20541412589032382,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411020509","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":[0.08463982,0.00027687257,0.91442615,0.0003161984,0.000054023967,0.00015424303,0.0000014601045,0.000063693486,0.0000675656],"genre_scores_gemma":[0.3937157,0.00007019542,0.60609657,0.00007639756,0.000022974347,0.0000066223743,0.0000039868905,0.0000060205384,0.0000015031741],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991594,0.00005177348,0.00034360008,0.00015078258,0.00016415199,0.0001302873],"domain_scores_gemma":[0.9991323,0.00034266865,0.00017039017,0.000042627664,0.00023605986,0.00007600249],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035575955,0.00014427942,0.00019168148,0.00041690524,0.000111208254,0.00035732446,0.00007544331,0.000047792684,0.0000018199657],"category_scores_gemma":[0.000058094713,0.00012620525,0.000025930018,0.00025503227,0.00003544231,0.0010000651,0.0000447761,0.00022169862,3.9182817e-7],"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":[0.0000499816,0.000037451446,0.0000273132,0.00018735732,0.00008490986,0.000020186455,0.001389123,0.0109551605,0.007951493,0.00034044616,0.00003473376,0.97892183],"study_design_scores_gemma":[0.0018839142,0.0007737777,0.0010730182,0.0029374808,0.000081930426,0.002043938,0.00041678545,0.9394852,0.015727393,0.035094697,0.000048986793,0.00043288703],"about_ca_topic_score_codex":0.0000017564566,"about_ca_topic_score_gemma":3.84868e-7,"teacher_disagreement_score":0.978489,"about_ca_system_score_codex":0.000040914605,"about_ca_system_score_gemma":0.000040699782,"threshold_uncertainty_score":0.5146501},"labels":[],"label_agreement":null},{"id":"W4411612371","doi":"10.1007/978-981-96-1918-4_44","title":"Handwritten Recognition System Using Image Acquisition Technique","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"Handwritten Text Recognition Techniques","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":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Artificial intelligence; Computer vision; Pattern recognition (psychology); Speech recognition","score_opus":0.01611004771531209,"score_gpt":0.23930916643880065,"score_spread":0.22319911872348858,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411612371","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":[0.000011736345,0.004881701,0.95601237,0.000057959212,0.0008030796,0.001713408,0.000038930582,0.0006865632,0.035794284],"genre_scores_gemma":[0.7203642,0.0046751928,0.2495406,0.0015861031,0.0061494657,0.0021416557,0.0011477392,0.0005888521,0.013806189],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99714345,0.00019400491,0.00088819256,0.0009812317,0.00034163764,0.0004515138],"domain_scores_gemma":[0.9980546,0.00035702443,0.0004783814,0.0006961948,0.00030594252,0.00010780555],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00088537077,0.00061292783,0.0009114386,0.0007200955,0.000202792,0.0006127796,0.00051278505,0.0013633693,0.0000121268085],"category_scores_gemma":[0.00003207566,0.0005947293,0.00016979464,0.00025216554,0.00009043216,0.00034491427,0.0002831897,0.0009092276,0.000008602463],"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":[0.00011658549,0.00010431502,0.000087780616,0.0076188254,0.00045890847,0.001167093,0.0003878809,0.004024546,0.0028711108,0.08019229,0.0030041342,0.89996654],"study_design_scores_gemma":[0.0010487176,0.0003260207,0.00001244748,0.044780273,0.00024769123,0.0017578645,0.000016949627,0.87431026,0.003337082,0.06442259,0.006857124,0.0028829738],"about_ca_topic_score_codex":0.00014813553,"about_ca_topic_score_gemma":0.000030029498,"teacher_disagreement_score":0.8970836,"about_ca_system_score_codex":0.00038916682,"about_ca_system_score_gemma":0.00009212713,"threshold_uncertainty_score":0.99993306},"labels":[],"label_agreement":null},{"id":"W4411856823","doi":"10.1177/17470218251357441","title":"Stroke features in the Chinese character recognition","year":2025,"lang":"en","type":"article","venue":"Quarterly Journal of Experimental Psychology","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal; Université du Québec en Outaouais","funders":"","keywords":"Character (mathematics); Hierarchy; Stroke (engine); Chinese characters; Perception; Feature (linguistics); Computer science; Line (geometry); Artificial intelligence; Psychology; Pattern recognition (psychology); Natural language processing; Speech recognition; Linguistics; Neuroscience; Mathematics; Engineering; Geometry","score_opus":0.013938355929449054,"score_gpt":0.34140462473865807,"score_spread":0.32746626880920904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411856823","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":[0.9299999,0.0014366761,0.04228839,0.0063760877,0.0016569388,0.00029532675,0.000004290066,0.000056121055,0.017886305],"genre_scores_gemma":[0.9892942,0.000022895743,0.005963643,0.0045170174,0.000116299976,0.000022036515,0.00000201022,0.0000046934674,0.000057244073],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.998656,0.00030188967,0.00047114422,0.00019178451,0.00018896275,0.00019024411],"domain_scores_gemma":[0.9992641,0.00010318901,0.00022166893,0.00029298154,0.00008245441,0.00003560218],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00057018944,0.00013510005,0.00021557452,0.00044240034,0.000052252817,0.00011035701,0.0009174773,0.00009697877,0.00004923744],"category_scores_gemma":[0.000012866957,0.00008979062,0.0001276474,0.00038104903,0.00006059164,0.00054372713,0.000021196813,0.00039132175,0.00002414949],"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":[0.00027255935,0.0017794026,0.001922748,0.000008960878,0.00008760554,0.00031738888,0.011689603,8.869596e-8,0.26188856,0.0033312028,0.017935092,0.7007668],"study_design_scores_gemma":[0.015689733,0.020446982,0.49120414,0.0007498512,0.00005946605,0.010352179,0.009922195,0.00013415952,0.25294086,0.18106471,0.015880873,0.0015548434],"about_ca_topic_score_codex":0.0000052156456,"about_ca_topic_score_gemma":0.0000040351674,"teacher_disagreement_score":0.69921196,"about_ca_system_score_codex":0.000036354024,"about_ca_system_score_gemma":0.000025875543,"threshold_uncertainty_score":0.36615553},"labels":[],"label_agreement":null},{"id":"W4412014383","doi":"10.18280/isi.300508","title":"Hyperparameter Optimization for CNN, K-NN, and Decision Tree in Handwritten Digit Classification","year":2025,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Hyperparameter; Decision tree; Numerical digit; Artificial intelligence; Computer science; Pattern recognition (psychology); Speech recognition; Machine learning; Mathematics; Arithmetic","score_opus":0.017002351210511517,"score_gpt":0.2575950149243483,"score_spread":0.24059266371383675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412014383","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":[0.04152342,0.00006336887,0.952814,0.00019898379,0.00014177679,0.0007487495,0.000007661238,0.0002655131,0.0042365217],"genre_scores_gemma":[0.68346345,0.00008031606,0.3156388,0.00036985715,0.000012816274,0.0003239442,0.00007156967,0.000006072791,0.000033158318],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986934,0.000038438156,0.00065001094,0.00022494337,0.00016863276,0.0002245396],"domain_scores_gemma":[0.9988711,0.00026527664,0.00019473891,0.00030339384,0.00031786083,0.000047659767],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046518995,0.00015812086,0.0002122672,0.0007426464,0.00017317003,0.0006536774,0.00031250718,0.00015650429,0.0000053640847],"category_scores_gemma":[0.0004617784,0.0001571129,0.000051158804,0.0007037296,0.0000706826,0.0046747965,0.00010700788,0.0000903956,0.000010592981],"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":[0.000030750776,0.000021560574,0.0008007859,0.00011042028,0.00000792292,2.5067337e-7,0.0007294408,0.00040680077,0.00008844482,0.010099457,0.00052778935,0.98717636],"study_design_scores_gemma":[0.0013574573,0.00014129461,0.012690641,0.0005438485,0.000014352713,0.000013082271,0.00023606131,0.84640175,0.004714336,0.13088562,0.0026650962,0.00033649462],"about_ca_topic_score_codex":0.000017398426,"about_ca_topic_score_gemma":0.000018690562,"teacher_disagreement_score":0.9868399,"about_ca_system_score_codex":0.0002188672,"about_ca_system_score_gemma":0.000076028766,"threshold_uncertainty_score":0.64068776},"labels":[],"label_agreement":null},{"id":"W4413052408","doi":"10.3233/shti251231","title":"An Iterative Composite Method for the De-Identification of Medical Notes","year":2025,"lang":"en","type":"article","venue":"Studies in health technology and informatics","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network","funders":"","keywords":"Identification (biology); Computer science; Identifier; Matching (statistics); Security token; Medical record; Iterative method; Artificial intelligence; Residual; Machine learning; Data mining; Algorithm; Medicine; Statistics; Computer security; Mathematics","score_opus":0.040613310880029896,"score_gpt":0.4391572423483992,"score_spread":0.3985439314683693,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413052408","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":[0.0022934834,0.0017943649,0.9762929,0.019009028,0.00009175839,0.0003820689,0.0000029240946,0.00010294189,0.000030503712],"genre_scores_gemma":[0.44335955,0.0034928885,0.55062014,0.002264754,0.000006081296,0.00024735162,0.0000018602392,0.0000020140046,0.0000053859762],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989902,0.00006584369,0.00062538986,0.000076618584,0.00009877375,0.00014319521],"domain_scores_gemma":[0.9984831,0.00090278697,0.00020776414,0.00023791267,0.00015107129,0.000017341084],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002411264,0.000062329076,0.0001949563,0.000361003,0.00020955666,0.000017800196,0.00047934224,0.000116331496,3.7594043e-7],"category_scores_gemma":[0.00069235294,0.000044413133,0.000014330648,0.00056055834,0.00029304367,0.00019135897,0.00019233089,0.00017317984,2.1543138e-7],"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":[0.0000036786043,0.000025787818,0.00074487925,0.0004761104,0.000028451048,1.3675296e-7,0.007601978,0.000008210124,0.00001690947,0.38968027,0.00014316851,0.60127044],"study_design_scores_gemma":[0.00046120456,0.00031285643,0.0014186848,0.0004407342,0.000009105732,0.000016368633,0.0078016673,0.69117767,0.015382119,0.28107184,0.0018044702,0.00010326527],"about_ca_topic_score_codex":0.000010354844,"about_ca_topic_score_gemma":0.000022718361,"teacher_disagreement_score":0.69116944,"about_ca_system_score_codex":0.00003806293,"about_ca_system_score_gemma":0.00009478649,"threshold_uncertainty_score":0.1811115},"labels":[],"label_agreement":null},{"id":"W4413330321","doi":"10.18280/mmep.120735","title":"Image-Based Text Translation a Fine-Tuning Using DeepSeek-Coder and Transformer Models for Multilingual Optical Character Recognition Processing","year":2025,"lang":"en","type":"article","venue":"Mathematical Modelling and Engineering Problems","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Transformer; Computer science; Translation (biology); Character recognition; Speech recognition; Character (mathematics); Artificial intelligence; Optical character recognition; Natural language processing; Computer vision; Image (mathematics); Engineering; Electrical engineering; Voltage; Mathematics","score_opus":0.050997598677653445,"score_gpt":0.26465872217260356,"score_spread":0.21366112349495012,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413330321","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":[0.019655595,0.00021369268,0.9788169,0.0002207582,0.00002723408,0.00056829216,0.0000053023114,0.00037905978,0.000113122514],"genre_scores_gemma":[0.35576802,0.000011582794,0.644044,0.000030704723,0.0000151978375,0.00009879912,0.0000071720756,0.00001928138,0.0000052614732],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99870676,0.000014398738,0.00041738647,0.0003986899,0.00014043761,0.0003223311],"domain_scores_gemma":[0.9993664,0.00023983943,0.0000470434,0.00012831559,0.0001282905,0.000090090405],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044411808,0.00022945263,0.0002838563,0.00023205792,0.00015285896,0.00029486735,0.000115892195,0.00014821906,0.000001606792],"category_scores_gemma":[0.000032238877,0.00022046507,0.00006479822,0.00018653955,0.000042379947,0.0006283279,0.000017039973,0.0001948206,7.661485e-7],"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":[0.00004384332,0.0002105867,0.0000021446904,0.0064682746,0.00005614906,0.0000029806968,0.0031399454,0.41469428,0.040863637,0.008343492,0.000002202511,0.52617246],"study_design_scores_gemma":[0.00050037645,0.000034213266,5.197704e-7,0.001214141,0.000042928776,0.00001100006,0.000010233067,0.9306551,0.00994955,0.05732582,0.000013769231,0.00024231791],"about_ca_topic_score_codex":0.0000026683126,"about_ca_topic_score_gemma":4.0260662e-7,"teacher_disagreement_score":0.52593017,"about_ca_system_score_codex":0.000025155328,"about_ca_system_score_gemma":0.000039274702,"threshold_uncertainty_score":0.89903045},"labels":[],"label_agreement":null},{"id":"W4413682358","doi":"10.1145/3743679","title":"MuralAgent: Enhancing Ancient Mural Outpainting with RAG-Based Texts and Multimodal Integration","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Multimedia Computing Communications and Applications","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China","keywords":"Mural; Computer science; Human–computer interaction; Computer graphics (images); Visual arts; Art","score_opus":0.013359700270174754,"score_gpt":0.2781374867151397,"score_spread":0.26477778644496497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413682358","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":[0.006578662,0.0002792387,0.9879271,0.0032553277,0.00004014331,0.0009724889,0.000012551545,0.00060204713,0.0003324404],"genre_scores_gemma":[0.5833575,0.00008582663,0.4157557,0.0004042907,0.000010152994,0.00032479418,0.000021549957,0.000010089495,0.000030087007],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99835134,0.00016080434,0.00045521357,0.0005623096,0.00018367817,0.00028662934],"domain_scores_gemma":[0.9962057,0.0012601775,0.00016933937,0.0019620268,0.00027558272,0.00012717128],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00045019612,0.00025642366,0.00023461199,0.00045342403,0.0014547532,0.0002945996,0.0011594454,0.0001034846,0.0000049992445],"category_scores_gemma":[0.000057416895,0.00024170296,0.00006182574,0.00092235673,0.00030949412,0.0002988464,0.0001402648,0.0004567421,0.000008653932],"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":[0.0000058781047,0.00026104497,0.00019037511,0.000027665707,0.000028730374,3.0194184e-7,0.00051260716,0.00022637674,0.0024198561,0.0028949499,0.0000134159,0.9934188],"study_design_scores_gemma":[0.0011216183,0.0001305511,0.004219051,0.00042908711,0.00007101893,0.000013861021,0.00049934833,0.9705398,0.01790948,0.001629105,0.002977543,0.00045954206],"about_ca_topic_score_codex":0.00008489126,"about_ca_topic_score_gemma":0.00014627798,"teacher_disagreement_score":0.99295926,"about_ca_system_score_codex":0.000081964994,"about_ca_system_score_gemma":0.00011064189,"threshold_uncertainty_score":0.9998452},"labels":[],"label_agreement":null},{"id":"W4413968157","doi":"10.22541/au.175692137.72576748/v1","title":"Base64 Decoding with Ignorable Characters using SIMD instructions","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université TÉLUQ","funders":"","keywords":"SIMD; Decoding methods; Computer science; Arithmetic; Parallel computing; Algorithm; Mathematics","score_opus":0.031876411659650924,"score_gpt":0.2814897438929081,"score_spread":0.24961333223325716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413968157","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":[0.011960599,0.000023052593,0.9598637,0.00033775513,0.00063075323,0.0004808445,0.000021591151,0.001410028,0.025271663],"genre_scores_gemma":[0.100857474,0.0000521224,0.89645135,0.000749632,0.00009435025,0.00011682981,0.00002892954,0.000019912088,0.0016294207],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99810016,0.00008382316,0.00036188492,0.0008192058,0.00029038865,0.00034455035],"domain_scores_gemma":[0.9983122,0.00008184048,0.00022095878,0.000995229,0.00027707996,0.00011270001],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00026260855,0.00032827107,0.00036292383,0.0005889057,0.0002439393,0.00058928126,0.0011144168,0.00024829505,0.00007064343],"category_scores_gemma":[0.000029265524,0.00029864782,0.00011896199,0.0005556288,0.00005982789,0.0005935153,0.0013867605,0.0006294647,0.00001677729],"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":[0.000053052398,0.0006195638,0.0042610266,0.0018226637,0.00095414586,0.00017482838,0.0017692323,0.0038978546,0.0046113334,0.14210385,0.009639567,0.8300929],"study_design_scores_gemma":[0.0013812534,0.0002749723,0.0008090598,0.006097071,0.0002971562,0.00039335436,0.000275506,0.7027103,0.18231192,0.0938451,0.007522306,0.0040820073],"about_ca_topic_score_codex":0.0004182726,"about_ca_topic_score_gemma":0.00007564942,"teacher_disagreement_score":0.8260109,"about_ca_system_score_codex":0.00021345647,"about_ca_system_score_gemma":0.0005916327,"threshold_uncertainty_score":0.9999466},"labels":[],"label_agreement":null},{"id":"W4414141043","doi":"10.1109/icmew68306.2025.11152127","title":"MarkMatch: Same-Hand Stuffing Detection","year":2025,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Similarity (geometry); Generalization; Handwriting; Pattern recognition (psychology); Sample (material); Feature extraction; Dual (grammatical number); Diagonal","score_opus":0.011521094634124712,"score_gpt":0.25631763410571173,"score_spread":0.24479653947158703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414141043","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":[0.008061076,0.000037207214,0.9407066,0.0006197875,0.00021322547,0.00012310897,2.5726538e-7,0.0007742117,0.049464487],"genre_scores_gemma":[0.9204655,0.000019803763,0.072669104,0.0013360764,0.000022535567,0.000038251685,5.0497454e-7,0.0000040654477,0.005444145],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993212,0.00003974066,0.00014659323,0.00023621134,0.00010791671,0.00014832061],"domain_scores_gemma":[0.9995014,0.00006655221,0.0000287858,0.0002939168,0.00007817191,0.000031149764],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021411991,0.00007781786,0.00008839301,0.0001985005,0.00014196297,0.0002670854,0.00035913492,0.000052118856,0.000059962353],"category_scores_gemma":[0.000043733195,0.00007181233,0.000040963907,0.00048516304,0.000023674113,0.00034924728,0.00017420997,0.00008844031,0.00008255063],"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":[0.0000022554282,0.000028093851,0.00015498916,0.000017667426,0.000010794622,0.0000030268297,0.00008957313,5.165124e-7,0.013967965,0.017737688,0.002342154,0.96564525],"study_design_scores_gemma":[0.00022609356,0.000050127375,0.0016028482,0.000059359743,0.0000053644367,0.00001001517,0.000045064844,0.0076360744,0.9226095,0.053658698,0.013916457,0.00018037835],"about_ca_topic_score_codex":0.00005609648,"about_ca_topic_score_gemma":0.00006615297,"teacher_disagreement_score":0.9654649,"about_ca_system_score_codex":0.000037849848,"about_ca_system_score_gemma":0.000032000087,"threshold_uncertainty_score":0.29284218},"labels":[],"label_agreement":null},{"id":"W4414253768","doi":"10.1007/978-3-032-04624-6_19","title":"Verification of Dynamic Holographic Behavior in Identity Documents","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Handwritten Text Recognition Techniques","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":"Minnow Environmental (Canada)","funders":"","keywords":"Identity (music); Benchmark (surveying); Cover (algebra); Code (set theory); Verifiable secret sharing; Protocol (science); Static analysis; Identity theft","score_opus":0.011947451828774401,"score_gpt":0.2837292190124842,"score_spread":0.27178176718370983,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414253768","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":[0.0016122779,0.0002493087,0.99499464,0.00014832355,0.0006895239,0.00061218854,0.000008393351,0.00015185056,0.0015335032],"genre_scores_gemma":[0.66960603,0.00022624768,0.3295217,0.00032110343,0.000029124782,0.00006101807,0.000013243044,0.000016425127,0.0002051429],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.996973,0.00005212763,0.0006794402,0.0011677938,0.0007463692,0.00038129135],"domain_scores_gemma":[0.9979084,0.00018675101,0.0003511863,0.0012232373,0.00026390926,0.000066516506],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009314404,0.000336554,0.00047006234,0.0024958001,0.00008088685,0.00023148804,0.0031302536,0.00033987212,0.000016623722],"category_scores_gemma":[0.000077863,0.00035314527,0.00013035258,0.0014511574,0.0005612122,0.0010590934,0.00095271936,0.00061787904,0.0000107134565],"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":[0.000003864444,0.00008921706,0.0007984643,0.00006896493,0.0000059927634,0.000046367768,0.0001639529,0.000081731094,0.0010567402,0.014704327,0.0000073489155,0.98297304],"study_design_scores_gemma":[0.0008520283,0.0004929537,0.031660937,0.0023296406,0.000041954838,0.0000657322,4.1213724e-7,0.106936716,0.017727198,0.8381014,0.00026224027,0.0015287981],"about_ca_topic_score_codex":0.00006942087,"about_ca_topic_score_gemma":0.00029783996,"teacher_disagreement_score":0.98144424,"about_ca_system_score_codex":0.0002878446,"about_ca_system_score_gemma":0.00034735215,"threshold_uncertainty_score":0.99989206},"labels":[],"label_agreement":null},{"id":"W4414416027","doi":"10.1145/3748336.3748344","title":"From Pixels to Paleography: A Dual-Pathway Neural Network for Neume Script Classification","year":2025,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","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":"Centre for Interdisciplinary Research in Music Media and Technology","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Artificial neural network; Pixel; Pattern recognition (psychology); Feature (linguistics); Noise (video)","score_opus":0.02662381851323619,"score_gpt":0.2779707447407486,"score_spread":0.2513469262275124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414416027","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":[0.008409865,0.000089930676,0.97756654,0.0062641227,0.0007092425,0.00082252,0.000021068174,0.0010778155,0.00503888],"genre_scores_gemma":[0.47530976,0.000009508758,0.5149078,0.0073961965,0.0002762635,0.00067145616,0.000040910392,0.000013264511,0.0013748688],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985141,0.000070050366,0.00032336375,0.0005773565,0.00016289657,0.00035220291],"domain_scores_gemma":[0.99879915,0.00020206366,0.000066757835,0.000638205,0.000179084,0.00011475687],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002645003,0.0001661773,0.00019679806,0.00023410775,0.00016477918,0.00030401474,0.00063589396,0.00009533313,0.00003318068],"category_scores_gemma":[0.000052905252,0.00015668142,0.00013513569,0.00088361034,0.000028101793,0.00037479316,0.00017194958,0.0001018725,0.000042864034],"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":[0.000024355493,0.00009788564,0.001545794,0.000018190565,0.00004680788,0.0000031836105,0.00024583781,0.000027905688,0.010678538,0.16340302,0.13739185,0.68651664],"study_design_scores_gemma":[0.0011458056,0.00051201344,0.048690546,0.00024197638,0.00004445783,0.000004915873,0.00015705862,0.17306677,0.05758203,0.41398573,0.30350405,0.0010646597],"about_ca_topic_score_codex":0.000087936016,"about_ca_topic_score_gemma":0.00006958943,"teacher_disagreement_score":0.685452,"about_ca_system_score_codex":0.000027302205,"about_ca_system_score_gemma":0.00005769374,"threshold_uncertainty_score":0.6389283},"labels":[],"label_agreement":null},{"id":"W4414432576","doi":"10.1109/tpami.2025.3612940","title":"Translating Images to Road Network: A Sequence-to-Sequence Perspective","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Huawei Technologies (Canada)","funders":"National Natural Science Foundation of China","keywords":"Landmark; Merge (version control); Encoder; Network topology; Representation (politics); Perspective (graphical); Euclidean distance; Intersection (aeronautics); Feature extraction","score_opus":0.030178584743459396,"score_gpt":0.32041145360797274,"score_spread":0.2902328688645133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414432576","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":[0.0010606949,0.000083984814,0.99263674,0.004455809,0.00014975022,0.0003926068,0.00006137966,0.00032641654,0.00083260867],"genre_scores_gemma":[0.9642942,0.00012761497,0.03208575,0.0029197163,0.000021623062,0.00013761019,0.0000022348886,0.000011957915,0.00039929277],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99765605,0.00014903683,0.0004948196,0.0009513312,0.00030426562,0.00044449122],"domain_scores_gemma":[0.99864525,0.00014670493,0.000079113335,0.00062499556,0.00026850833,0.00023544334],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00044245945,0.00031797503,0.00044416465,0.0011080612,0.0003658888,0.00030508626,0.0007674654,0.00008467157,0.000108899556],"category_scores_gemma":[0.000017841554,0.00030301994,0.0002880599,0.0038975792,0.00007340027,0.0003294052,0.00001557645,0.0003654059,0.000059849946],"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":[0.000011182238,0.00007805362,0.00012173104,0.000011205211,0.00030310074,0.000013577384,0.00095274753,0.013825837,0.0019747235,0.0004865081,0.000030206342,0.98219115],"study_design_scores_gemma":[0.00028459466,0.00073702337,0.002069724,0.0005643182,0.0011030913,0.00004072597,0.0007585455,0.29886526,0.68098354,0.012598512,0.0003782036,0.0016164284],"about_ca_topic_score_codex":0.0035297717,"about_ca_topic_score_gemma":0.0025535568,"teacher_disagreement_score":0.9805747,"about_ca_system_score_codex":0.00014276622,"about_ca_system_score_gemma":0.00006510656,"threshold_uncertainty_score":0.9999422},"labels":[],"label_agreement":null},{"id":"W4414629702","doi":"10.22541/au.175924882.28819604/v1","title":"HAND: Hierarchical Attention Network for Multi-Scale Handwritten Document Recognition and Layout Analysis","year":2025,"lang":"en","type":"article","venue":"","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":"Natural Sciences and Engineering Research Council of Canada","keywords":"Field (mathematics); Convolutional neural network; Intelligent character recognition; Feature (linguistics); Document processing; Sketch recognition; Pattern recognition (psychology); Handwriting recognition; Encoder; Key (lock)","score_opus":0.02701011423814828,"score_gpt":0.29434568947318723,"score_spread":0.2673355752350389,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414629702","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":[0.0144056035,0.000110649176,0.9821464,0.0013570277,0.0001344573,0.0006085493,0.000017029415,0.00038971042,0.0008305908],"genre_scores_gemma":[0.15334313,0.00006862433,0.84184057,0.0013056902,0.000082558996,0.00043874022,0.00016584681,0.000010497032,0.002744337],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983879,0.000113150236,0.00038636406,0.00059948245,0.00016948573,0.0003436604],"domain_scores_gemma":[0.9990927,0.00016655306,0.000086339496,0.0003432898,0.00020615035,0.000104948536],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006479094,0.00017833729,0.00031424855,0.00042458085,0.0003257854,0.00047940976,0.0003089712,0.00013166766,0.000040805826],"category_scores_gemma":[0.00004090317,0.00016310679,0.00021423901,0.0010351636,0.00008548228,0.00042861555,0.00020823436,0.00012789416,0.00001948883],"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":[0.00006796626,0.0002744477,0.010163551,0.00010404074,0.0008308197,0.000004090896,0.0003056608,0.000025207482,0.0016896186,0.009511054,0.007652304,0.96937126],"study_design_scores_gemma":[0.0051484862,0.00054702867,0.060952798,0.00032669437,0.0015454543,0.000016993092,0.00013187836,0.6035209,0.023341168,0.29304126,0.010070742,0.0013566428],"about_ca_topic_score_codex":0.00007753675,"about_ca_topic_score_gemma":0.00032899325,"teacher_disagreement_score":0.9680146,"about_ca_system_score_codex":0.000046171772,"about_ca_system_score_gemma":0.00003042831,"threshold_uncertainty_score":0.66513014},"labels":[],"label_agreement":null},{"id":"W4415318477","doi":"10.1109/synasc69064.2025.00010","title":"Well-Conditioned Polynomial Representations for Mathematical Handwriting Recognition","year":2025,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Western University","funders":"","keywords":"Legendre polynomials; Representation (politics); Polynomial; Parameterized complexity; Degree (music); Chebyshev polynomials; Degree of a polynomial; Matrix polynomial","score_opus":0.023230329129858052,"score_gpt":0.30764483143375293,"score_spread":0.28441450230389487,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415318477","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":[0.0014781766,0.000009086011,0.8847666,0.0029055348,0.00013356807,0.00058474595,0.000013645996,0.0007616454,0.10934699],"genre_scores_gemma":[0.20912611,0.000009835279,0.7797336,0.0019895595,0.00012935603,0.0009596038,0.00010290396,0.000014033836,0.007934971],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988495,0.000050966504,0.00037142352,0.00036857702,0.00012953691,0.00023001405],"domain_scores_gemma":[0.9988179,0.0004973909,0.00007251825,0.00033135287,0.00022377422,0.00005704656],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033766642,0.00011586845,0.00016035479,0.0002704608,0.00027054903,0.00025915116,0.00034512984,0.00008696083,0.00029754618],"category_scores_gemma":[0.00027448218,0.0001166916,0.000118286065,0.00037554026,0.00004538545,0.0005591207,0.00010613795,0.000086593725,0.00021678417],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030533505,0.00036077018,0.00007627081,0.00018376934,0.00009410776,0.000005884984,0.00027873093,0.0000022281229,0.0076661794,0.43433177,0.20068532,0.35628444],"study_design_scores_gemma":[0.001140112,0.000080654274,0.00016809913,0.00016825166,0.00003423696,0.00002239408,0.00018255248,0.02430918,0.27801973,0.6898343,0.0057319803,0.00030854263],"about_ca_topic_score_codex":0.000009487323,"about_ca_topic_score_gemma":0.00000559595,"teacher_disagreement_score":0.3559759,"about_ca_system_score_codex":0.00004189107,"about_ca_system_score_gemma":0.00006820862,"threshold_uncertainty_score":0.47585452},"labels":[],"label_agreement":null},{"id":"W4416154085","doi":"10.1016/j.patcog.2026.114258","title":"ProtoSig: Enhancing training data for offline handwritten signature verification using prototypical signatures","year":2025,"lang":"en","type":"article","venue":"Pattern Recognition","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":"Natural Sciences and Engineering Research Council of Canada","keywords":"Training (meteorology); Signature (topology); Training set; Pattern recognition (psychology); Feature (linguistics); Identification (biology)","score_opus":0.08839965685597474,"score_gpt":0.33670995703139506,"score_spread":0.24831030017542033,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416154085","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":[0.007547858,0.00012176137,0.9856996,0.0007923817,0.00030957573,0.004439773,0.00019897324,0.00061989756,0.00027020482],"genre_scores_gemma":[0.684875,0.000019467641,0.30909112,0.0015144368,0.00035552648,0.0025316584,0.0015191779,0.000039519007,0.000054077886],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9975798,0.00016999335,0.0005623072,0.0009812736,0.00028445167,0.0004221436],"domain_scores_gemma":[0.9980875,0.00025587864,0.00023204887,0.0009330533,0.0004096733,0.00008179323],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009349115,0.00027587666,0.00031370315,0.00036087426,0.00029900693,0.000331959,0.001165756,0.00030528245,0.000031288655],"category_scores_gemma":[0.00038746902,0.00027952262,0.000096799355,0.0005216106,0.00005067296,0.0011453603,0.00030188498,0.0003881946,0.000016668611],"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":[0.000043231084,0.00011669186,0.00005127086,0.00026097783,0.00004520221,0.0000031524296,0.00023239,0.0000030359924,0.07672452,0.00013798563,0.00078882877,0.9215927],"study_design_scores_gemma":[0.0021670656,0.00032185338,0.00060166034,0.002207248,0.00014991399,0.000031264128,0.00019590433,0.3548542,0.5946151,0.03605257,0.0077481857,0.0010550591],"about_ca_topic_score_codex":0.00001964234,"about_ca_topic_score_gemma":0.000023933528,"teacher_disagreement_score":0.92053765,"about_ca_system_score_codex":0.00009018241,"about_ca_system_score_gemma":0.00019678273,"threshold_uncertainty_score":0.99996567},"labels":[],"label_agreement":null},{"id":"W4416249422","doi":"10.1109/icccnp63914.2025.11233508","title":"Bengali Handwriting Detection Using Ensemble Learning","year":2025,"lang":"","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Horizon College and Seminary","funders":"","keywords":"Bengali; Pattern recognition (psychology); Handwriting; Ensemble learning; Support vector machine; Feature (linguistics); Handwriting recognition","score_opus":0.0236416808873468,"score_gpt":0.28760841035633355,"score_spread":0.26396672946898675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416249422","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":[0.04749111,0.00045474703,0.8987738,0.00025406698,0.00089187105,0.00042641544,7.9471056e-7,0.0011773005,0.050529916],"genre_scores_gemma":[0.9196247,0.000117350326,0.07389929,0.0004798518,0.00016126249,0.000024668027,0.0000014722187,0.000026297486,0.0056651374],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99633384,0.00053773756,0.00086190813,0.0010304071,0.00042745285,0.00080866704],"domain_scores_gemma":[0.99814194,0.00030013613,0.00028251312,0.0005703418,0.00055172155,0.00015335766],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0013953515,0.00042083237,0.00045320202,0.0008484302,0.0015075841,0.0012881081,0.0007056294,0.00037045946,0.0002525578],"category_scores_gemma":[0.0004576128,0.00048814344,0.0002500542,0.0020534648,0.00012524858,0.0012470412,0.0007141394,0.0009856584,0.00011622371],"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":[0.000010083709,0.00007618456,0.00042309737,0.00012705341,0.000057160683,0.000015549116,0.00033620826,0.00016128138,0.091308564,0.0051622307,0.00006148241,0.9022611],"study_design_scores_gemma":[0.0003348472,0.00011662382,0.00010052503,0.00059177907,0.000049057955,0.00004082124,0.00037190938,0.47841355,0.5134589,0.0040808693,0.0020526217,0.00038850718],"about_ca_topic_score_codex":0.00032986686,"about_ca_topic_score_gemma":0.00007758991,"teacher_disagreement_score":0.9018726,"about_ca_system_score_codex":0.00032507387,"about_ca_system_score_gemma":0.00031367902,"threshold_uncertainty_score":0.99979234},"labels":[],"label_agreement":null},{"id":"W4416345839","doi":"10.18280/isi.300923","title":"Accurate Detection of Handwriting Features Using Bounding Box Optimization","year":2025,"lang":"","type":"article","venue":"Ingénierie des systèmes d information","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Minimum bounding box; Pattern recognition (psychology); Bounding overwatch; Noise (video); Feature (linguistics); Handwriting","score_opus":0.017134959781274182,"score_gpt":0.26635960738289655,"score_spread":0.24922464760162236,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416345839","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":[0.025838038,0.00062448456,0.9645199,0.000051547206,0.0013050167,0.00092098035,0.000027967923,0.0004400132,0.0062720575],"genre_scores_gemma":[0.9096259,0.00023528708,0.08970428,0.00016732927,0.000084773295,0.000053914173,0.000044769105,0.000018620418,0.00006512514],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961045,0.00030784318,0.0020246438,0.00038541653,0.0005626075,0.00061499],"domain_scores_gemma":[0.9957674,0.00019214084,0.001701416,0.00057612953,0.0016537744,0.00010913887],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0014676857,0.00046154374,0.00058976153,0.0018363928,0.001147102,0.0018620774,0.0006906999,0.0004760334,0.000033631597],"category_scores_gemma":[0.0010666666,0.0005353545,0.00022898821,0.0028765665,0.00033326357,0.012223916,0.00039456208,0.00041997788,0.00001302411],"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":[0.00012093633,0.00008777112,0.00028112464,0.0033054224,0.00020239486,0.0000034383652,0.009017451,0.0633696,0.013322189,0.0064266357,0.00010233171,0.9037607],"study_design_scores_gemma":[0.00061269343,0.00014093677,0.0005725219,0.0033776548,0.00010080809,0.00006832425,0.00110595,0.75443244,0.23525235,0.0036664507,0.0002073491,0.00046250343],"about_ca_topic_score_codex":0.00026674411,"about_ca_topic_score_gemma":0.00001650396,"teacher_disagreement_score":0.9032982,"about_ca_system_score_codex":0.00095023564,"about_ca_system_score_gemma":0.00049806276,"threshold_uncertainty_score":0.9997098},"labels":[],"label_agreement":null},{"id":"W565356442","doi":"10.1016/j.patrec.2015.06.008","title":"Document image binarization using a discriminative structural classifier","year":2015,"lang":"en","type":"article","venue":"Pattern Recognition Letters","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":"University of Waterloo","funders":"","keywords":"CRFS; Discriminative model; Artificial intelligence; Computer science; Pattern recognition (psychology); Conditional random field; Pixel; Classifier (UML); Graphical model; Image (mathematics)","score_opus":0.05941645178811838,"score_gpt":0.29693986722573656,"score_spread":0.23752341543761818,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W565356442","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":[0.26054388,0.000009505393,0.7354772,0.0026034508,0.00038583286,0.00030609994,0.000015599891,0.00036186678,0.00029658922],"genre_scores_gemma":[0.8926767,0.0000042289976,0.10217098,0.004744345,0.00017499518,0.00007864837,0.00010523111,0.000028917028,0.000015933303],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9980325,0.00024835957,0.0003659823,0.00051795674,0.00047144556,0.00036375687],"domain_scores_gemma":[0.9989,0.00004097346,0.00022420706,0.0003308702,0.00030694786,0.00019702296],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031437023,0.00024914453,0.00019990072,0.00031199292,0.00013622333,0.00042179608,0.00042833682,0.0000773907,0.00008269447],"category_scores_gemma":[0.0000667813,0.00024145118,0.000091193586,0.00037287426,0.000093988594,0.0020007791,0.00019046846,0.00019901604,0.00024995548],"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":[0.00002902263,0.0001057686,0.0022803084,0.000086801294,0.000094036914,0.00017343512,0.0067574424,0.00002411414,0.06496138,0.00021005694,0.0044653798,0.92081225],"study_design_scores_gemma":[0.009738257,0.0011920311,0.012997879,0.0015311927,0.0003520193,0.0012466013,0.0024034595,0.2847451,0.54209816,0.13479614,0.0026844873,0.0062146494],"about_ca_topic_score_codex":0.00010006432,"about_ca_topic_score_gemma":0.000006699776,"teacher_disagreement_score":0.91459763,"about_ca_system_score_codex":0.00026563043,"about_ca_system_score_gemma":0.00005126786,"threshold_uncertainty_score":0.98460937},"labels":[],"label_agreement":null},{"id":"W58960893","doi":"","title":"Automatic segmentation and recognition of unconstrained handwritten numeral strings","year":2007,"lang":"en","type":"dissertation","venue":"Spectrum Research Repository (Concordia University)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Segmentation; Numeral system; Pattern recognition (psychology); Computer science; Artificial intelligence; Feature (linguistics); Speech recognition","score_opus":0.026013658697113907,"score_gpt":0.2949577432537067,"score_spread":0.2689440845565928,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W58960893","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":[0.9434151,0.00011621808,0.007983616,0.000103428254,0.00040632542,0.00095998304,0.000021016316,0.00041291022,0.046581406],"genre_scores_gemma":[0.9858326,0.00020863643,0.005282064,0.000010265123,0.00012773903,0.000010963433,0.00024584893,0.000040222363,0.008241665],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99663335,0.0004916845,0.00051536225,0.0007949009,0.00096481136,0.0005998963],"domain_scores_gemma":[0.99770504,0.00038252646,0.00044587415,0.00051516155,0.0006767568,0.00027462744],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001063673,0.00032030485,0.0004769879,0.0025092473,0.0004296381,0.00025145066,0.0008586386,0.00043488177,0.00005721648],"category_scores_gemma":[0.00009540447,0.00038277535,0.00016501415,0.0015659578,0.0002929038,0.00094733265,0.00019533251,0.0008715935,0.000017602211],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006114449,0.0005658942,0.007827611,0.0024752798,0.0007219284,0.0018298624,0.004859407,9.70541e-7,0.1230077,0.008040624,0.0015368166,0.8485225],"study_design_scores_gemma":[0.0018084686,0.0012440734,0.025567522,0.0012139811,0.00013417272,0.00014501433,0.004171338,0.0013031239,0.95144045,0.011160908,0.00081734697,0.0009936043],"about_ca_topic_score_codex":0.004075911,"about_ca_topic_score_gemma":0.0022257974,"teacher_disagreement_score":0.8475289,"about_ca_system_score_codex":0.0004513325,"about_ca_system_score_gemma":0.00072646217,"threshold_uncertainty_score":0.99986243},"labels":[],"label_agreement":null},{"id":"W590209030","doi":"","title":"Pattern detection and recognition using over-complete and sparse representations","year":2009,"lang":"en","type":"dissertation","venue":"Spectrum Research Repository (Concordia University)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Pattern recognition (psychology); Artificial intelligence; Sparse approximation; K-SVD; Computer science; Gabor wavelet; Feature extraction; Wavelet; Invariant (physics); Wavelet transform; Mathematics; Discrete wavelet transform","score_opus":0.049563626015947874,"score_gpt":0.3009830481752399,"score_spread":0.251419422159292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W590209030","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":[0.9565709,0.00016363303,0.0252185,0.00011931748,0.00039768277,0.00081936136,0.000020770865,0.00039136602,0.016298436],"genre_scores_gemma":[0.9957438,0.00046080627,0.001074224,0.000018741826,0.00021245677,0.000007745987,0.000085144864,0.000035407702,0.0023616874],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99671054,0.0006732343,0.0003191382,0.0011053089,0.0006391101,0.00055268826],"domain_scores_gemma":[0.9982201,0.00023248179,0.00026348425,0.0005996627,0.0003825983,0.00030171158],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004950857,0.000315626,0.0003557818,0.0019269377,0.0010196441,0.0006113887,0.00054937985,0.00036767073,0.000014130556],"category_scores_gemma":[0.00007417751,0.00039774546,0.000112290945,0.001127974,0.00018274678,0.0011670317,0.00022986735,0.00096634735,0.0000112878],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032424444,0.00024044311,0.0067980285,0.0004578945,0.00027005517,0.0018926756,0.001758488,0.0000026185417,0.12980346,0.0007486177,0.00030206674,0.85740143],"study_design_scores_gemma":[0.0033685518,0.0024748887,0.51384306,0.0015990759,0.00040983935,0.0011451066,0.003747566,0.029543487,0.3899804,0.043711647,0.0068357913,0.0033405686],"about_ca_topic_score_codex":0.014260838,"about_ca_topic_score_gemma":0.013035136,"teacher_disagreement_score":0.8540608,"about_ca_system_score_codex":0.0004147335,"about_ca_system_score_gemma":0.00026083802,"threshold_uncertainty_score":0.9998475},"labels":[],"label_agreement":null},{"id":"W64109705","doi":"10.1007/978-3-642-31374-5_27","title":"Writing on Clouds","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","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":"Western University","funders":"","keywords":"Handwriting; Computer science; Handwriting recognition; Intelligent character recognition; Sample (material); Character (mathematics); Cloud computing; Function (biology); Software; Word (group theory); Symbol (formal); Artificial intelligence; Speech recognition; Natural language processing; Character recognition; Feature extraction; Operating system; Programming language","score_opus":0.022684363430050994,"score_gpt":0.26215221121005716,"score_spread":0.23946784778000618,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W64109705","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":[0.00005049878,0.00041017393,0.97343224,0.00063407724,0.0012386562,0.00036748493,0.0000046319706,0.0006253877,0.023236841],"genre_scores_gemma":[0.24588059,0.0001253266,0.7464745,0.0052665663,0.0015995229,0.000028946451,0.000007751034,0.000077497156,0.0005392889],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9959048,0.000045402023,0.0005759584,0.0014270508,0.0011509827,0.00089579035],"domain_scores_gemma":[0.99708,0.0005750028,0.00029564204,0.0015458018,0.00024802462,0.00025551306],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013545677,0.00057875423,0.0005157509,0.0010192498,0.0002765272,0.00059353607,0.0034611565,0.0004258533,0.00008118722],"category_scores_gemma":[0.00009407078,0.0005453011,0.00016503152,0.0005525656,0.000515307,0.0007568781,0.0012934979,0.0011704968,0.00036276592],"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":[0.0000018407004,0.000025719764,0.000019335308,0.000018699408,0.000004567482,0.000040774932,0.00019974883,0.00015819713,0.00011729661,0.042988636,0.000045329052,0.95637983],"study_design_scores_gemma":[0.000563676,0.00077407795,0.00024228643,0.002381053,0.000020484349,0.00037120472,2.4506363e-7,0.10497457,0.048881132,0.82339525,0.015534814,0.0028611792],"about_ca_topic_score_codex":0.000008318245,"about_ca_topic_score_gemma":0.000009869236,"teacher_disagreement_score":0.9535187,"about_ca_system_score_codex":0.00035420468,"about_ca_system_score_gemma":0.00028652177,"threshold_uncertainty_score":0.99969983},"labels":[],"label_agreement":null},{"id":"W6888871807","doi":"10.22111/ieco.2023.45650.1480","title":"Investigation of Deep Learning Optimization Algorithms in Scene Text Detection","year":2023,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Benchmark (surveying); Pipeline (software); Deep learning; Text detection; Object detection; Focus (optics); Feature (linguistics); Stochastic gradient descent","score_opus":0.1744468246417349,"score_gpt":0.47835125156538566,"score_spread":0.3039044269236508,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6888871807","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":[0.28569475,0.0010129274,0.7111617,0.000140841,0.00034118246,0.00053915096,0.0000035220955,0.0003363716,0.00076959823],"genre_scores_gemma":[0.96904445,0.0037880137,0.02684424,0.000076890334,0.000061562234,0.000071838374,0.000016851107,0.000033482705,0.000062690495],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99726063,0.0004653614,0.0009055009,0.00043425048,0.0006362873,0.00029794796],"domain_scores_gemma":[0.9978819,0.00027946066,0.0008921619,0.00034752558,0.00046044175,0.00013853601],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00212865,0.00020719873,0.00045652245,0.002209496,0.00017134902,0.00073851604,0.0019903083,0.00013706609,0.0005493394],"category_scores_gemma":[0.0004506361,0.00021902064,0.00010046299,0.0043252204,0.00009042526,0.0041433685,0.00079766224,0.00039582423,0.000018003653],"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":[0.00003171953,0.000069916474,0.10540904,0.000104319384,0.000046709807,0.000022351544,0.00068128266,0.024048988,0.16822065,0.0000678231,0.00053714594,0.70076007],"study_design_scores_gemma":[0.0004058894,0.000027790478,0.22788729,0.00042680427,0.000014696158,0.0000120182995,0.00006546307,0.31225184,0.44870076,0.009747436,0.00012944978,0.0003305804],"about_ca_topic_score_codex":0.00040905006,"about_ca_topic_score_gemma":0.000048685095,"teacher_disagreement_score":0.70042944,"about_ca_system_score_codex":0.00011734051,"about_ca_system_score_gemma":0.000083419756,"threshold_uncertainty_score":0.89314026},"labels":[],"label_agreement":null},{"id":"W6888934964","doi":"10.25316/ir-14092","title":"The Nanaimo Free Press [Saturday, April 9, 1881]","year":2020,"lang":"en","type":"other","venue":"VIURRSpace (Vancouver Island University)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Free press; Gloom; Ridiculous","score_opus":0.010520109999739834,"score_gpt":0.20076283007978485,"score_spread":0.190242720080045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6888934964","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.4633065e-8,0.00054429634,0.13611683,0.0011357997,0.0011634126,0.00043788351,0.00011135402,0.0013893067,0.85910106],"genre_scores_gemma":[0.00005435306,0.0020850494,0.0074916724,0.00026303096,0.0003387772,0.000004349443,9.568739e-7,0.00018389533,0.9895779],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977857,0.00018934587,0.00015965712,0.0008249825,0.00052752957,0.0005127862],"domain_scores_gemma":[0.99761456,0.00015205395,0.00033622276,0.0015829334,0.00009041922,0.00022383446],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000118164724,0.00046941466,0.00042302685,0.00036907935,0.00033420487,0.0002693698,0.0037940256,0.000422972,0.00016029793],"category_scores_gemma":[0.00006519817,0.0003902734,0.00023035609,0.00076901854,0.00018875596,0.00031351112,0.0014025668,0.0005969821,0.00014823534],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011871303,0.0000230686,3.0781084e-7,0.000034405675,0.00009827799,0.00018056456,0.00014837213,7.69008e-7,0.0000057107727,0.007975668,0.9841971,0.007323889],"study_design_scores_gemma":[0.00058878126,0.00007605218,7.9836667e-7,0.00013039248,0.000049654012,0.0000045928446,0.000095819145,0.00024330917,0.00021393747,0.00071991776,0.9973612,0.0005155531],"about_ca_topic_score_codex":0.00059722713,"about_ca_topic_score_gemma":0.0032902423,"teacher_disagreement_score":0.13047685,"about_ca_system_score_codex":0.0001270574,"about_ca_system_score_gemma":0.00019034787,"threshold_uncertainty_score":0.9998549},"labels":[],"label_agreement":null},{"id":"W6893735387","doi":"10.5281/zenodo.4065270","title":"Combining Visual and Textual Features for Semantic Segmentation of Historical Newspapers","year":2021,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Fredericton","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Categorization; Segmentation; Robustness (evolution); Newspaper; Embedding; Variety (cybernetics); Identification (biology); Process (computing)","score_opus":0.026225554421811886,"score_gpt":0.2630946295209617,"score_spread":0.2368690750991498,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6893735387","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":[0.029267343,0.0003311299,0.94677573,0.0024108146,0.00017071751,0.00078907533,0.00007632246,0.001293907,0.018884933],"genre_scores_gemma":[0.96132284,0.00012727756,0.036123924,0.0002756366,0.000078838726,2.3347438e-7,0.00056090433,0.00042449645,0.0010858441],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988863,0.00017506212,0.00020167301,0.00031971824,0.000235077,0.00018217172],"domain_scores_gemma":[0.9990348,0.000058758727,0.000093270726,0.00020190666,0.0005211056,0.000090159854],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035261665,0.000087751294,0.00013362269,0.00014462993,0.00065197825,0.00037975956,0.00040944148,0.000048354697,0.00029950257],"category_scores_gemma":[0.0003916049,0.00009644205,0.000040615432,0.00036053534,0.00005907181,0.0002833556,0.0005972502,0.00011084323,0.00006184452],"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":[0.00003681297,0.00023255727,0.000011600101,0.00016885673,0.000049307106,0.000014962686,0.0023885642,0.0000054871184,0.11311383,0.02181413,0.09111768,0.7710462],"study_design_scores_gemma":[0.0025638328,0.0017173294,0.0017850905,0.0001772372,0.000054972377,0.0006342597,0.0017124059,0.00549247,0.19324006,0.0037121011,0.78826046,0.0006497565],"about_ca_topic_score_codex":0.000011957043,"about_ca_topic_score_gemma":5.5336255e-7,"teacher_disagreement_score":0.9320555,"about_ca_system_score_codex":0.000121473015,"about_ca_system_score_gemma":0.000006736485,"threshold_uncertainty_score":0.50145555},"labels":[],"label_agreement":null},{"id":"W6901861880","doi":"10.60692/y5r26-qff82","title":"Exploring the Limits of Simple Learners in Knowledge Distillation for Document Classification with DocBERT","year":2020,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; University of Waterloo","funders":"","keywords":"Distillation; Baseline (sea); Simple (philosophy); Document classification; Knowledge extraction; Knowledge acquisition; Natural language; Question answering","score_opus":0.15061390910739683,"score_gpt":0.2681573197427652,"score_spread":0.11754341063536836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6901861880","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":[0.20304498,0.0000014008309,0.7944009,0.0004137422,0.000055711113,0.0007442474,0.000009506629,0.00020448478,0.001125056],"genre_scores_gemma":[0.9949717,3.1146175e-7,0.004510425,0.00006198035,0.000027195847,0.00040400086,0.000012744243,0.000005453974,0.000006202593],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989848,0.00006202401,0.00048794542,0.00014033541,0.00018745485,0.00013739898],"domain_scores_gemma":[0.9991997,0.000029583975,0.00028221335,0.0002481547,0.00019181578,0.000048559155],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034129867,0.00010614041,0.00014784126,0.0001456098,0.00007276577,0.00013927488,0.00029314333,0.00003107031,0.000001149954],"category_scores_gemma":[0.00003146343,0.000071135815,0.00003923458,0.00045218633,0.000020485644,0.0016200552,0.000042187163,0.000060284798,0.00003741657],"study_design_candidate":"qualitative","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":[0.00028988224,0.000013131754,0.061839446,0.0020343543,0.00007866526,0.0000011692624,0.72285414,0.0011224711,0.00008589805,0.058278877,0.00026571643,0.15313624],"study_design_scores_gemma":[0.0055442895,0.001235309,0.24153219,0.0011812447,0.000070645445,0.00003301552,0.079969324,0.60273284,0.05888396,0.000212402,0.007351738,0.001253039],"about_ca_topic_score_codex":0.000004570389,"about_ca_topic_score_gemma":9.132928e-7,"teacher_disagreement_score":0.7919267,"about_ca_system_score_codex":0.00007968928,"about_ca_system_score_gemma":0.000036299127,"threshold_uncertainty_score":0.29008344},"labels":[],"label_agreement":null},{"id":"W6920575173","doi":"10.60692/r8a9d-3vs67","title":"Exploring the Limits of Simple Learners in Knowledge Distillation for Document Classification with DocBERT","year":2020,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; University of Waterloo","funders":"","keywords":"Distillation; Baseline (sea); Simple (philosophy); Document classification; Knowledge extraction; Knowledge acquisition; Natural language; Question answering","score_opus":0.15061390910739683,"score_gpt":0.2681573197427652,"score_spread":0.11754341063536836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6920575173","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":[0.20304498,0.0000014008309,0.7944009,0.0004137422,0.000055711113,0.0007442474,0.000009506629,0.00020448478,0.001125056],"genre_scores_gemma":[0.9949717,3.1146175e-7,0.004510425,0.00006198035,0.000027195847,0.00040400086,0.000012744243,0.000005453974,0.000006202593],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989848,0.00006202401,0.00048794542,0.00014033541,0.00018745485,0.00013739898],"domain_scores_gemma":[0.9991997,0.000029583975,0.00028221335,0.0002481547,0.00019181578,0.000048559155],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034129867,0.00010614041,0.00014784126,0.0001456098,0.00007276577,0.00013927488,0.00029314333,0.00003107031,0.000001149954],"category_scores_gemma":[0.00003146343,0.000071135815,0.00003923458,0.00045218633,0.000020485644,0.0016200552,0.000042187163,0.000060284798,0.00003741657],"study_design_candidate":"qualitative","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":[0.00028988224,0.000013131754,0.061839446,0.0020343543,0.00007866526,0.0000011692624,0.72285414,0.0011224711,0.00008589805,0.058278877,0.00026571643,0.15313624],"study_design_scores_gemma":[0.0055442895,0.001235309,0.24153219,0.0011812447,0.000070645445,0.00003301552,0.079969324,0.60273284,0.05888396,0.000212402,0.007351738,0.001253039],"about_ca_topic_score_codex":0.000004570389,"about_ca_topic_score_gemma":9.132928e-7,"teacher_disagreement_score":0.7919267,"about_ca_system_score_codex":0.00007968928,"about_ca_system_score_gemma":0.000036299127,"threshold_uncertainty_score":0.29008344},"labels":[],"label_agreement":null},{"id":"W6931670430","doi":"10.5683/sp3/esc5og","title":"Fichier des codes postaux par circonscriptions électorales fédérales [Canada], septembre 2006, Recensement de la population 2001","year":2025,"lang":"fr","type":"dataset","venue":"Borealis","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Population; Civilian population; Code (set theory)","score_opus":0.023700435203855435,"score_gpt":0.28429159315807184,"score_spread":0.2605911579542164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931670430","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00052931433,0.0022724306,0.016575148,0.0022066156,0.0004953754,0.00083378697,0.9739078,0.00038910646,0.0027903703],"genre_scores_gemma":[0.0012211476,0.0045492165,0.02915821,0.0019200532,0.00029498976,0.0002739636,0.9605383,0.000039220333,0.0020048532],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99451905,0.0015265344,0.0010277712,0.0010754183,0.0007383828,0.001112837],"domain_scores_gemma":[0.99618924,0.00072367885,0.0005108654,0.0014788845,0.00065471133,0.0004426474],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010918033,0.00076501316,0.0007784837,0.00048904645,0.0009300544,0.0008520086,0.001432213,0.00072541676,0.00034397372],"category_scores_gemma":[0.00075437163,0.00086139794,0.00026870437,0.0008510611,0.0005750226,0.000641168,0.00045655563,0.0007734751,0.000011316546],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015114061,0.0002393155,0.0023854985,0.00042430116,0.00015799988,0.00013182999,0.000092456976,0.000020109761,0.00008736267,0.0021399257,0.9746733,0.019632803],"study_design_scores_gemma":[0.00028346395,0.00010177009,0.023489343,0.0014226717,0.0002500165,0.00011423146,0.00005373141,0.00049596647,0.0011023317,0.0058952756,0.9659354,0.000855761],"about_ca_topic_score_codex":0.911377,"about_ca_topic_score_gemma":0.9654447,"teacher_disagreement_score":0.054067664,"about_ca_system_score_codex":0.001502231,"about_ca_system_score_gemma":0.0028677667,"threshold_uncertainty_score":0.9993837},"labels":[],"label_agreement":null},{"id":"W6939130192","doi":"10.60692/rj43s-hn605","title":"A New Computational Method for Arabic Calligraphy Style Representation and Classification","year":2021,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Calligraphy; Style (visual arts); Arabic; Representation (politics); Set (abstract data type); Feature (linguistics)","score_opus":0.05487492215301315,"score_gpt":0.2854315584098109,"score_spread":0.23055663625679773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6939130192","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":[0.0032769907,0.0000057540165,0.9943065,0.00040958662,0.00015551214,0.00044899006,0.00003511249,0.00043625262,0.0009253241],"genre_scores_gemma":[0.4778349,2.4383866e-7,0.52164584,0.00021451918,0.00003476509,0.00011479293,0.00006346426,0.000004623156,0.000086843844],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99869037,0.00011048664,0.00050868094,0.00026540202,0.00027040488,0.00015468769],"domain_scores_gemma":[0.9986956,0.000051789906,0.00027766163,0.00031864562,0.00055056054,0.00010571587],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037729982,0.00012721035,0.00017560748,0.00027277952,0.00014599145,0.0005114844,0.00017837073,0.000089737514,0.000006716823],"category_scores_gemma":[0.000045768753,0.00012468503,0.00007899088,0.00046165116,0.000011979167,0.0014792256,0.00006427706,0.00005995236,0.000068353176],"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":[0.000126995,0.00002402845,0.03128378,0.0016025403,0.00033329887,0.0000149203015,0.15639657,0.0008961859,0.0003115083,0.26637,0.0117372945,0.53090286],"study_design_scores_gemma":[0.0026596372,0.00011309822,0.07975193,0.00022381257,0.000053521362,0.00044472658,0.00605524,0.89194566,0.0129277995,0.0027976003,0.0024102202,0.00061673427],"about_ca_topic_score_codex":0.0000061965243,"about_ca_topic_score_gemma":3.0263192e-7,"teacher_disagreement_score":0.8910495,"about_ca_system_score_codex":0.000054192828,"about_ca_system_score_gemma":0.00010456411,"threshold_uncertainty_score":0.5084508},"labels":[],"label_agreement":null},{"id":"W6949488576","doi":"10.5281/zenodo.13788176","title":"McCATMuS - Transcription model for handwritten, printed and typewritten documents from the 16th century to the 21st century","year":2024,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Transcription (linguistics); Interoperability; Unicode; Normalization (sociology); Line (geometry)","score_opus":0.02879822394015591,"score_gpt":0.25276384359141213,"score_spread":0.22396561965125622,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6949488576","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":[0.0033817848,0.0013285466,0.95609695,0.022449452,0.00040196825,0.0022545431,0.0006601605,0.0024616076,0.010965003],"genre_scores_gemma":[0.98165196,0.0023949947,0.0098379245,0.0025960994,0.00039968765,0.0000033414938,0.0010691716,0.0009723215,0.0010745176],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983326,0.00021720189,0.0002366834,0.0005504041,0.00033584313,0.0003272443],"domain_scores_gemma":[0.9988648,0.000072706294,0.000043790147,0.0005544753,0.00032587862,0.00013831111],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00071271026,0.00015987003,0.00011735565,0.00012950081,0.0014422073,0.0023918592,0.0015385867,0.000062152,0.00044001828],"category_scores_gemma":[0.0001808727,0.00011154877,0.00006748565,0.00051479094,0.000089638605,0.0004956741,0.0008481071,0.0002591399,0.0010333535],"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":[0.000045703884,0.00006989711,8.767849e-7,0.000052844654,0.00007494991,0.0000043058476,0.006699957,0.000027788079,0.006643898,0.031929076,0.15929589,0.7951548],"study_design_scores_gemma":[0.00024161208,0.00011626155,0.00009682014,0.00008562403,0.000021251453,0.000027971919,0.00033246228,0.03941861,0.0008823612,0.0024120545,0.956203,0.00016199499],"about_ca_topic_score_codex":0.000028281029,"about_ca_topic_score_gemma":0.000002256669,"teacher_disagreement_score":0.9782702,"about_ca_system_score_codex":0.00009752621,"about_ca_system_score_gemma":0.000008148598,"threshold_uncertainty_score":0.9998578},"labels":[],"label_agreement":null},{"id":"W6957558492","doi":"10.60692/6tkhq-ack17","title":"The Interplay Between Strictness of Policies and Individuals' Self-Regulatory Efforts: Associations with Handwashing During the COVID-19 Pandemic","year":2021,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Public health; Pandemic; Psychological intervention; Government (linguistics); Psychosocial; Containment (computer programming); Hygiene; Behavior change; Health policy","score_opus":0.025208496621051037,"score_gpt":0.25313285849228656,"score_spread":0.22792436187123552,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6957558492","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":[0.8402787,0.000014847758,0.15839757,0.0002478291,0.000060626444,0.00030611918,0.00008804793,0.0004030037,0.00020327995],"genre_scores_gemma":[0.9987514,0.000001718259,0.00093184033,0.00016626227,0.000033150973,0.00006691096,0.000010519121,0.000006018612,0.0000321946],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9984309,0.00020019434,0.0005784004,0.00014235885,0.00042904692,0.00021907306],"domain_scores_gemma":[0.99845624,0.00016824403,0.0005550028,0.00045189192,0.000276606,0.00009199013],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010316017,0.00014436507,0.0002131025,0.00016827563,0.00069850433,0.0006744845,0.00045450887,0.00008749651,0.0000012864758],"category_scores_gemma":[0.00009008426,0.000083405546,0.000048769645,0.00047631402,0.00007369536,0.0010249319,0.0002753436,0.00014456722,0.0000066395005],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002483708,0.0000014061359,0.8969187,0.00017749066,0.000114618575,9.518269e-7,0.10089985,0.000016511478,0.0000024226122,0.0010888822,0.00003124098,0.0007454513],"study_design_scores_gemma":[0.0010861211,0.000049500206,0.976263,0.0002460734,0.0000798827,0.0002890207,0.015936216,0.0007026182,0.00413701,0.000050255498,0.00084075774,0.0003195721],"about_ca_topic_score_codex":0.000022121276,"about_ca_topic_score_gemma":0.0000042137895,"teacher_disagreement_score":0.15847272,"about_ca_system_score_codex":0.0001983829,"about_ca_system_score_gemma":0.00016958971,"threshold_uncertainty_score":0.65040696},"labels":[],"label_agreement":null},{"id":"W6957698156","doi":"10.6068/dp1530adb547e40","title":"Most Recent Data (2002). Statistics Canada. CANSIM: Health - Mental Health and Well-Being | Country: Canada | Table: Mental Health and Well-being profile, Canadian Community Health Survey (CCHS), by age group and sex | Variable: 25 to 64 years, Barriers accessing mental health services encountered due to availability issues, Females | Units: , 2002. Data-Planet™ Statistical Ready Reference by Conquest Systems, Inc. Dataset-ID: 075-001-115.","year":2016,"lang":"en","type":"other","venue":"Data Planet","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mental health; Census; Official statistics; Summary statistics; Health statistics; Socioeconomic status; Economic statistics; General Social Survey; Mental illness","score_opus":0.021900736470364824,"score_gpt":0.2836127206547498,"score_spread":0.26171198418438496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6957698156","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000042328998,0.0077567645,0.00032492008,0.0005773118,0.00067056704,0.0035345159,0.9866691,0.00018075162,0.0002818075],"genre_scores_gemma":[0.000029009636,0.016810779,0.0046681953,0.023460347,0.00008983285,0.000029826568,0.95421576,0.00020581295,0.0004904153],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.987417,0.0042902906,0.001959458,0.002623192,0.0014033456,0.0023067277],"domain_scores_gemma":[0.98781997,0.00058939203,0.0014290884,0.004326703,0.00010391391,0.005730905],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0061950264,0.0011237237,0.0020106959,0.0003107799,0.0018716535,0.0013168112,0.0044334377,0.00029472634,0.0009799125],"category_scores_gemma":[0.00010165227,0.0011752547,4.4702932e-7,0.00078167487,0.00030667247,0.0010692767,0.003596622,0.0012572065,0.000014351272],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051095263,0.00008145781,0.00027202154,0.002147692,0.00011948185,0.0000506707,0.00024302413,1.2603626e-7,6.1425186e-7,0.0001066064,0.99171466,0.005212526],"study_design_scores_gemma":[0.0007971139,0.00047401214,0.000052634812,0.000798435,0.0000132872565,0.00020894135,0.0014281789,0.0009416509,7.959842e-8,6.687011e-7,0.99431133,0.0009736556],"about_ca_topic_score_codex":0.999972,"about_ca_topic_score_gemma":0.9999631,"teacher_disagreement_score":0.048489965,"about_ca_system_score_codex":0.0031013836,"about_ca_system_score_gemma":0.05159135,"threshold_uncertainty_score":0.9999333},"labels":[],"label_agreement":null},{"id":"W6957862094","doi":"10.6084/m9.figshare.11480379.v1","title":"MOESM1 of Projected local rain events due to climate change and the impacts on waterborne diseases in Vancouver, British Columbia, Canada","year":2019,"lang":"en","type":"article","venue":"Figshare","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Precipitation; Climate change; Turbidity; Waterborne diseases; Water supply; Air temperature; Hydrology (agriculture)","score_opus":0.014426490493266775,"score_gpt":0.21939065608067537,"score_spread":0.2049641655874086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6957862094","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":[0.6997442,0.00049406703,0.0001311083,0.001017785,0.0005379556,0.009179863,0.28696048,0.0005319432,0.0014025504],"genre_scores_gemma":[0.9969258,0.0000074787436,0.0001136932,0.0009975486,0.000020555455,0.00046969336,0.0013695497,0.000011457447,0.00008426888],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99888664,0.000098814315,0.00019092219,0.00028204682,0.0002597661,0.00028179376],"domain_scores_gemma":[0.99930865,0.0001303354,0.00007896185,0.00027988068,0.00009611744,0.000106039326],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00008651878,0.00009174173,0.00022104922,0.000048409103,0.000043169384,0.00010837434,0.00040034813,0.000044155884,0.0023113843],"category_scores_gemma":[0.00021798996,0.000095040334,0.000029615905,0.00029587446,0.000009062353,0.00021430587,0.0002920501,0.00009557956,0.000033917084],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000112557726,0.00026758193,0.010700463,0.0010599624,0.000033513385,0.00037771903,0.0010378333,0.0000068513896,0.000029775758,0.000022841152,0.71457905,0.27177188],"study_design_scores_gemma":[0.0053364276,0.00071991526,0.95323706,0.01719433,0.00001338135,0.00007256647,0.00017805396,0.006357495,0.0026774122,0.000953268,0.012258409,0.0010016684],"about_ca_topic_score_codex":0.3923275,"about_ca_topic_score_gemma":0.92344505,"teacher_disagreement_score":0.9425366,"about_ca_system_score_codex":0.00008898796,"about_ca_system_score_gemma":0.00015207358,"threshold_uncertainty_score":0.99860066},"labels":[],"label_agreement":null},{"id":"W6963737880","doi":"10.18739/a2c824f6g","title":"Precipitation Occurrence Sensor System measurements taken at Summit Station, Greenland, 2013","year":2013,"lang":"en","type":"dataset","venue":"California Digital Library","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Snow; Precipitation; NetCDF; Summit; Radar; Arctic; Doppler radar; Reflectivity","score_opus":0.02678733159809471,"score_gpt":0.22677976916471818,"score_spread":0.19999243756662347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6963737880","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000049204613,0.0002828792,0.016227135,0.00013247253,0.00039544518,0.0013658544,0.97965026,0.0011514147,0.0007453168],"genre_scores_gemma":[0.0001268956,0.00010614537,0.0038748267,0.00029210286,0.00022939318,0.00054014707,0.99420756,0.000041723044,0.0005811906],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9963134,0.00018436101,0.00090054114,0.0010257893,0.0010040257,0.00057187816],"domain_scores_gemma":[0.99730176,0.00019134929,0.0006624392,0.0011738806,0.00027758346,0.00039300683],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00017407491,0.00062587205,0.0005498163,0.00042481942,0.00020688804,0.002177242,0.0018033487,0.00041720248,0.00048329105],"category_scores_gemma":[0.000058975507,0.0005771755,0.0001977853,0.0005029579,0.00009986386,0.0046956795,0.0009154658,0.00036348525,0.027683588],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010693576,0.00006374459,0.00042257083,0.00050280255,0.00004746034,0.000023981174,0.0000067590654,0.0000010753328,0.0000014838055,0.000010265757,0.98731333,0.0115958555],"study_design_scores_gemma":[0.000269603,0.00008384945,0.000030493316,0.0003971178,0.000027388076,0.000029976658,0.000012296051,0.00017193735,0.000304379,0.00031153165,0.9976684,0.00069303147],"about_ca_topic_score_codex":0.000019536003,"about_ca_topic_score_gemma":0.000005853567,"teacher_disagreement_score":0.027200297,"about_ca_system_score_codex":0.00020900476,"about_ca_system_score_gemma":0.00022643546,"threshold_uncertainty_score":0.99966794},"labels":[],"label_agreement":null},{"id":"W6964528860","doi":"10.25549/wpacards-m107658","title":"WPA household census for 2449 GATES ST, Los Angeles","year":2012,"lang":"en","type":"dataset","venue":"University of Southern California Digital Library","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Census; Population; Quarter (Canadian coin); Government (linguistics)","score_opus":0.016043808270480898,"score_gpt":0.1845391333604501,"score_spread":0.1684953250899692,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6964528860","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00005849014,0.0001760536,0.0058391076,0.00010857606,0.000051531835,0.0003617399,0.9924702,0.0005297899,0.00040452855],"genre_scores_gemma":[0.000083624014,0.000067340654,0.0057394123,0.00012682902,0.00013938332,0.0000015989502,0.99357015,0.000038994545,0.00023266212],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985255,0.00004099612,0.00025988917,0.0004689544,0.00029670572,0.0004079253],"domain_scores_gemma":[0.9985298,0.00017019094,0.00034774886,0.0006530069,0.00006438362,0.00023484872],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0000800611,0.00034939763,0.00042572053,0.0003033645,0.00013940944,0.00024897518,0.0017057837,0.00034754362,0.00023745],"category_scores_gemma":[0.000022426377,0.00036463546,0.00031591742,0.00023616472,0.00020251879,0.000938393,0.0008478148,0.00024385483,0.00034840815],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003307196,0.00014433076,0.00009496516,0.00019659815,0.00004605418,0.000022473534,0.0000052542614,2.5387126e-7,0.0000022044742,0.000025670786,0.9948337,0.004595431],"study_design_scores_gemma":[0.0002683987,0.000046309542,0.0000020257944,0.00015295373,0.000047888094,0.000009902543,0.000109968125,0.000026119362,0.00023047066,0.0011105326,0.9975789,0.00041652832],"about_ca_topic_score_codex":0.00002108697,"about_ca_topic_score_gemma":0.0000023556474,"teacher_disagreement_score":0.0041789026,"about_ca_system_score_codex":0.000033962155,"about_ca_system_score_gemma":0.00011661268,"threshold_uncertainty_score":0.99988055},"labels":[],"label_agreement":null},{"id":"W6969185994","doi":"10.5281/zenodo.8107448","title":"Workshop HTR-United: metadata, quality control and sharing process for HTR training data","year":2023,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Suite; Process (computing); Quality (philosophy); Control (management); Training (meteorology); Training set","score_opus":0.2218400509208137,"score_gpt":0.361761120748736,"score_spread":0.13992106982792232,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6969185994","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":[0.007665016,0.00005909646,0.97829944,0.0026812833,0.00009190281,0.001034733,0.00091745274,0.004456393,0.0047946936],"genre_scores_gemma":[0.9784853,0.00013345145,0.010152813,0.0007680787,0.00022464636,0.0000012151968,0.00787253,0.001153197,0.0012087832],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977589,0.00025448753,0.0003408346,0.000817552,0.00037815567,0.00045002982],"domain_scores_gemma":[0.99788034,0.00018477983,0.00013896446,0.001085728,0.0005241382,0.00018607483],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0030256796,0.00015423587,0.00021275217,0.0004465401,0.0015666172,0.0022054946,0.0032708198,0.000069252244,0.00029150437],"category_scores_gemma":[0.002330127,0.00016320402,0.000034377903,0.0013111519,0.00011271124,0.001806142,0.0028498995,0.00023721496,0.00050620607],"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":[0.00009049081,0.00013507473,0.000014633494,0.00038624412,0.00016495038,0.00002412464,0.005363134,0.000054474796,0.002746173,0.045759644,0.106834225,0.8384268],"study_design_scores_gemma":[0.0014899418,0.00018320925,0.00046141498,0.0001238467,0.000032995453,0.00008483223,0.0013143801,0.10376666,0.0006855163,0.007556622,0.88379294,0.00050766283],"about_ca_topic_score_codex":0.000010211901,"about_ca_topic_score_gemma":7.60298e-7,"teacher_disagreement_score":0.97082025,"about_ca_system_score_codex":0.00004054604,"about_ca_system_score_gemma":0.000007704684,"threshold_uncertainty_score":0.9997332},"labels":[],"label_agreement":null},{"id":"W6977350230","doi":"10.6084/m9.figshare.14266999","title":"Additional file 1 of Caesarean section in pregnancies conceived by assisted reproductive technology: a systematic review and meta-analysis","year":2021,"lang":"en","type":"article","venue":"Figshare","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Queen's University","funders":"","keywords":"Caesarean section; Section (typography); MEDLINE; Pregnancy","score_opus":0.0424765447448523,"score_gpt":0.26491594389944007,"score_spread":0.22243939915458777,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6977350230","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[5.216245e-7,0.0144161,0.00008203524,0.00030991528,0.0000025561092,0.000489456,0.9842499,0.0001315449,0.00031800938],"genre_scores_gemma":[0.0008999158,0.000074151634,0.011346946,0.00045466228,0.0000085986785,0.012098713,0.9725934,0.000012104244,0.002511503],"study_design_codex":"not_applicable","study_design_gemma":"systematic_review","domain_scores_codex":[0.99866027,0.00018544104,0.0003892821,0.00046807725,0.00018477958,0.000112170805],"domain_scores_gemma":[0.9979662,0.00052670954,0.00034645814,0.0005439362,0.0005885251,0.000028217264],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00008235246,0.00012349655,0.0009060187,0.00022711132,0.00003794557,0.000036241374,0.00024291717,0.0000858234,0.8014128],"category_scores_gemma":[0.0065556704,0.00010755236,0.00022386124,0.0020230014,0.000017646293,0.000250885,0.000155571,0.0001232323,0.000050935287],"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":[1.5552752e-7,0.000027619108,1.5366514e-7,0.012957683,0.002672461,0.000009187353,0.000021952797,1.1315697e-7,0.000016715032,0.000006055752,0.98423207,0.000055807388],"study_design_scores_gemma":[0.0009416534,0.0005869359,0.0013725295,0.43781924,0.20835969,0.0014147563,0.00077488925,0.0018764389,0.07752931,0.0036450701,0.26196128,0.0037182034],"about_ca_topic_score_codex":0.0000033310848,"about_ca_topic_score_gemma":0.000025958821,"teacher_disagreement_score":0.8013619,"about_ca_system_score_codex":0.00003557514,"about_ca_system_score_gemma":0.00007711082,"threshold_uncertainty_score":0.78482234},"labels":[],"label_agreement":null},{"id":"W6977843585","doi":"10.6084/m9.figshare.c.5800963.v1","title":"Correction to: Human microbiota research in Africa: a systematic review reveals gaps and priorities for future research","year":2022,"lang":"en","type":"other","venue":"Figshare","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Hamilton Health Sciences; St. Joseph’s Healthcare Hamilton","funders":"","keywords":"MEDLINE; Systematic review; Human microbiome; Microbiome","score_opus":0.14843391796134348,"score_gpt":0.3999603071262112,"score_spread":0.25152638916486775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6977843585","genre_codex":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000011588343,0.44688058,0.000096847536,0.002560119,0.0010873193,0.04879965,0.15120582,0.0019886813,0.3473798],"genre_scores_gemma":[0.00005515532,0.0055531,0.0048621893,0.00064688077,0.0009943342,0.053793076,0.019053077,0.0005998333,0.91444236],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99599963,0.001342782,0.00046184793,0.0008208086,0.00075997337,0.0006149615],"domain_scores_gemma":[0.99737144,0.00089832477,0.00017789453,0.0009674015,0.00046514787,0.000119792974],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0027644923,0.0002433137,0.0007076133,0.001574079,0.00031616807,0.00032378698,0.0014082686,0.00022949977,0.027270336],"category_scores_gemma":[0.0024439585,0.00023613666,0.000092076385,0.0017755021,0.000019223853,0.00011659923,0.0011730669,0.0010643416,0.00041532645],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.3738786e-7,0.000012472875,2.8400652e-7,0.19453166,0.000007965053,0.000011501331,0.0001674311,2.381661e-9,0.000018430097,0.0000749447,0.80474126,0.00043320493],"study_design_scores_gemma":[0.00007095111,0.00014958704,0.000004755772,0.4224427,0.0000054464535,0.000024944498,0.00009075351,0.000003931384,0.000029266273,0.000295387,0.5766709,0.00021141722],"about_ca_topic_score_codex":0.000042701722,"about_ca_topic_score_gemma":0.00017026148,"teacher_disagreement_score":0.56706256,"about_ca_system_score_codex":0.0003533541,"about_ca_system_score_gemma":0.00017240485,"threshold_uncertainty_score":0.97361887},"labels":[],"label_agreement":null},{"id":"W6980070335","doi":"","title":"Automatic Recognition of Handwritten Dates on Brazilian Bank Cheques","year":2003,"lang":"en","type":"article","venue":"Library and Archives Canada (Government of Canada)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Period (music); Segmentation; Identity (music)","score_opus":0.005828525092875262,"score_gpt":0.16511041429899212,"score_spread":0.15928188920611686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6980070335","genre_codex":"other","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":[0.33230275,0.00033871992,0.011278075,0.0045269323,0.0003649603,0.00068095163,0.00031056168,0.0002000622,0.649997],"genre_scores_gemma":[0.9736826,0.00009449461,0.024329511,0.001107507,0.000013752871,0.00001340847,0.0000073510305,0.000012596142,0.0007387735],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99801975,0.000119888304,0.0003375913,0.00026380902,0.0010293965,0.00022955201],"domain_scores_gemma":[0.99907297,0.00028192363,0.00019265269,0.0002886338,0.000001661743,0.00016216401],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000028523491,0.00016399536,0.00024284153,0.00005006404,0.000098542994,0.000034921908,0.00034725224,0.000028833727,0.00007611629],"category_scores_gemma":[0.0000146301945,0.00015679323,0.00003107965,0.00013634014,0.00006798477,0.0005992911,0.00008516019,0.00010302653,1.3074901e-8],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010203208,0.00019534591,0.0060452437,0.00057413033,0.00014544974,0.00009496076,0.00033200954,0.0000055371574,0.052484732,0.34035534,0.0028714132,0.59679383],"study_design_scores_gemma":[0.00027533298,0.00017319422,0.0054598213,0.00026820693,0.000009842899,0.000011365676,0.0002998364,0.0023468367,0.96759206,0.019402042,0.0039218715,0.00023959781],"about_ca_topic_score_codex":0.000551717,"about_ca_topic_score_gemma":0.0022054662,"teacher_disagreement_score":0.9151073,"about_ca_system_score_codex":0.0000061224705,"about_ca_system_score_gemma":0.0006965976,"threshold_uncertainty_score":0.6393842},"labels":[],"label_agreement":null},{"id":"W6987686194","doi":"","title":"Towards Private Biometric Authentication and Identification","year":2023,"lang":"en","type":"dissertation","venue":"UWSpace (University of Waterloo)","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":"Natural Sciences and Engineering Research Council of Canada; Strong","keywords":"Handwriting; Biometrics; Robustness (evolution); Task (project management); Handwriting recognition; Identification (biology); Set (abstract data type); Authentication (law)","score_opus":0.015410398169232542,"score_gpt":0.2324065540435118,"score_spread":0.21699615587427926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6987686194","genre_codex":"empirical","genre_gemma":"other","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":[0.9849105,0.00009202728,0.012534694,0.0007867017,0.0003924777,0.00041177514,0.000022388433,0.0006508806,0.00019855937],"genre_scores_gemma":[0.38071713,0.0018084655,0.051018175,0.000022205251,0.000053302443,0.0000068256372,0.0014062459,0.000069753085,0.5648979],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99876136,0.000058797545,0.00017155748,0.00048304148,0.0003415627,0.00018369271],"domain_scores_gemma":[0.99880964,0.00003434219,0.000357273,0.0004603749,0.0002597046,0.0000786583],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030541592,0.00017079778,0.00025148652,0.0014655341,0.00016163188,0.00010109596,0.0007429463,0.00024269316,0.000026306985],"category_scores_gemma":[0.000042518892,0.00021034853,0.00008967143,0.0013495963,0.00006091395,0.0005226032,0.00015680122,0.00014241264,0.0001666502],"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":[0.0000515651,0.00019255557,0.00030407065,0.001319223,0.00024226835,0.000043950797,0.16712141,8.3944167e-7,0.077112675,0.013866544,0.0034810156,0.7362639],"study_design_scores_gemma":[0.0022586433,0.00070931547,0.47772723,0.0016225734,0.0007371424,0.000026577212,0.08332789,0.011471913,0.3525395,0.06351184,0.0030104036,0.0030569567],"about_ca_topic_score_codex":0.003716721,"about_ca_topic_score_gemma":0.0013059078,"teacher_disagreement_score":0.7332069,"about_ca_system_score_codex":0.000059895956,"about_ca_system_score_gemma":0.000057452566,"threshold_uncertainty_score":0.8577764},"labels":[],"label_agreement":null},{"id":"W7008725215","doi":"","title":"Computer analysis of composite documents with non-uniform background.","year":2004,"lang":"en","type":"dissertation","venue":"Scholarship at UWindsor (University of Windsor)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Feature (linguistics); Pattern recognition (psychology); Process (computing); Frame (networking); Nucleofection; Noise (video)","score_opus":0.012198972783099464,"score_gpt":0.2403772574912556,"score_spread":0.22817828470815613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7008725215","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":[0.91228527,0.000060785093,0.08118914,0.00007997221,0.0001971791,0.0005393676,0.00011127801,0.00020970443,0.0053272797],"genre_scores_gemma":[0.86072594,0.00007974025,0.13301969,0.00008252519,0.000037552487,0.0000023709692,0.0017837521,0.000053258467,0.004215173],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9965842,0.00014879428,0.00053430063,0.0010079702,0.0012256923,0.0004990768],"domain_scores_gemma":[0.9962476,0.00010016597,0.0012587137,0.0012332998,0.0008970054,0.0002632376],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005276012,0.00055896025,0.0013178128,0.0023527946,0.00039716854,0.00013702815,0.0025947932,0.0006249449,0.00033308452],"category_scores_gemma":[0.0000068287136,0.00064060546,0.00071017514,0.0030935786,0.00020318136,0.0018857758,0.00042901325,0.00073295616,0.000082464794],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.012332342,0.012185399,0.38597637,0.012914315,0.105741896,0.0034902007,0.114116184,0.008259753,0.10013432,0.024780178,0.0041381856,0.21593086],"study_design_scores_gemma":[0.0064014588,0.0019290843,0.9169476,0.003059542,0.0074750152,0.000047350713,0.002284442,0.004151116,0.051397562,0.002329036,0.00094142876,0.0030363444],"about_ca_topic_score_codex":0.00048290115,"about_ca_topic_score_gemma":0.0019605244,"teacher_disagreement_score":0.5309712,"about_ca_system_score_codex":0.00041945494,"about_ca_system_score_gemma":0.00037324877,"threshold_uncertainty_score":0.9996045},"labels":[],"label_agreement":null},{"id":"W7009082550","doi":"","title":"Diagrams Based on Structured Object Perception","year":2000,"lang":"en","type":"article","venue":"University of New Hampshire Scholars Repository (University of New Hampshire at Manchester)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Class diagram; Unified Modeling Language; Perception; Set (abstract data type); Story-driven modeling; Object (grammar); Line drawings; Applications of UML","score_opus":0.012642394326165794,"score_gpt":0.1975389972805796,"score_spread":0.18489660295441382,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7009082550","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":[0.93438715,0.000078799814,0.049762722,0.0011125894,0.00023324271,0.0006407913,0.000029016768,0.0007060687,0.013049593],"genre_scores_gemma":[0.9149581,0.0001281916,0.058873005,0.00026593448,0.00008701709,1.2245164e-7,0.000056551646,0.000034153778,0.025596905],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9968074,0.00032442942,0.0003426266,0.0010848886,0.00092490844,0.0005157741],"domain_scores_gemma":[0.99703425,0.00015575204,0.0005028012,0.0014646727,0.00024752726,0.0005950121],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00028398656,0.00046614124,0.00066576735,0.00046110858,0.00082778867,0.000112995964,0.0022081854,0.00047111898,0.0012825271],"category_scores_gemma":[0.000029586397,0.0006330558,0.0005586509,0.00081624824,0.00035605486,0.0020759373,0.00040836667,0.00056011125,0.00021825808],"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":[0.003546692,0.0012938362,0.023570178,0.00048291878,0.0005838086,0.001778915,0.037348755,0.0011355145,0.08440559,0.0007089294,0.07487646,0.7702684],"study_design_scores_gemma":[0.018005548,0.0042294194,0.620891,0.0022938207,0.0006675538,0.0005353586,0.008942837,0.02016873,0.029100144,0.0026320117,0.28789526,0.004638357],"about_ca_topic_score_codex":0.0011064629,"about_ca_topic_score_gemma":0.00037416423,"teacher_disagreement_score":0.76563007,"about_ca_system_score_codex":0.00056051154,"about_ca_system_score_gemma":0.0005123358,"threshold_uncertainty_score":0.99963045},"labels":[],"label_agreement":null},{"id":"W7020610085","doi":"","title":"Mine Rehabilitation and the Community: A Case Study from Canada","year":2003,"lang":"en","type":"article","venue":"UNSWorks (UNSW Sydney)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Rehabilitation; Work (physics); MEDLINE; Government (linguistics)","score_opus":0.012730382806993769,"score_gpt":0.23665394336200013,"score_spread":0.22392356055500637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7020610085","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":[0.92975295,0.00021153032,0.06550242,0.0020425483,0.00020162415,0.0008079395,0.000007416439,0.00019630924,0.0012772799],"genre_scores_gemma":[0.97287774,0.000007630086,0.025919337,0.0009678487,0.000022313963,0.00009900636,0.0000039627053,0.000012278489,0.0000898895],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99730366,0.001592745,0.0003055358,0.00028871783,0.00028754637,0.00022179428],"domain_scores_gemma":[0.99613017,0.0025443353,0.00010803108,0.0009669916,0.00013568738,0.00011476374],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013599921,0.00017301354,0.00024218003,0.00008612587,0.0005415984,0.0002035168,0.0004906624,0.00006611097,0.000030181336],"category_scores_gemma":[0.00076908467,0.00013039152,0.000040988514,0.00049387175,0.00014997847,0.00027099525,0.0001672063,0.00047166663,0.0000037206812],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023139127,0.0039596134,0.11302235,0.0001522691,0.00087544625,0.007422428,0.19226992,0.000073257375,0.00019294952,0.11875238,0.063192554,0.49985546],"study_design_scores_gemma":[0.04097695,0.0048518325,0.047967903,0.0009414438,0.0007848391,0.010621923,0.3053683,0.042703573,0.004523914,0.47274625,0.06267387,0.005839206],"about_ca_topic_score_codex":0.7366453,"about_ca_topic_score_gemma":0.731888,"teacher_disagreement_score":0.49401623,"about_ca_system_score_codex":0.00009036573,"about_ca_system_score_gemma":0.00020713842,"threshold_uncertainty_score":0.5317212},"labels":[],"label_agreement":null},{"id":"W7023822651","doi":"","title":"A proclamation to the Government Officials of te United States of America and to the Government Officials of Canada","year":2010,"lang":"en","type":"book","venue":"Virtual Defense Library (Ministerio de Defensa)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Proclamation; State government; Public policy","score_opus":0.00785247193736137,"score_gpt":0.20055070926095,"score_spread":0.19269823732358862,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7023822651","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":[0.5318714,0.001292174,0.20754936,0.044156168,0.0029645867,0.022833165,0.03373214,0.0011274987,0.15447351],"genre_scores_gemma":[0.74206614,0.0008813312,0.0654346,0.049865607,0.0008598005,0.0010985604,0.00079837244,0.00056981656,0.13842575],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9953491,0.00037009225,0.0013617645,0.00062065665,0.0018327968,0.0004656078],"domain_scores_gemma":[0.9960206,0.0008582721,0.0013899456,0.0012903659,0.00017513814,0.00026568183],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005411127,0.00052101194,0.0009385574,0.0001660641,0.00015612245,0.00016085412,0.0016538148,0.0002673285,0.000060856324],"category_scores_gemma":[0.00029955158,0.00037917175,0.00017095752,0.00060802524,0.00026636515,0.00026624816,0.0012184298,0.00041220797,0.000007664904],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014806137,0.0006539212,0.00021087161,0.0013823475,0.0008886899,0.000078478486,0.030916221,0.0005243458,0.014010215,0.048137505,0.6183345,0.28338233],"study_design_scores_gemma":[0.000335681,0.0020270753,0.0005040126,0.0008549996,0.00013154792,0.000045094548,0.0013490673,0.001522373,0.06517671,0.0012493097,0.9260524,0.0007517649],"about_ca_topic_score_codex":0.003441481,"about_ca_topic_score_gemma":0.0073516304,"teacher_disagreement_score":0.3077179,"about_ca_system_score_codex":0.00023971128,"about_ca_system_score_gemma":0.0017503346,"threshold_uncertainty_score":0.999866},"labels":[],"label_agreement":null},{"id":"W7024154702","doi":"","title":"Revue de littérature sur les interactions conducteurs – usagers vulnérables","year":2025,"lang":"fr","type":"other","venue":"EspaceINRS (National Institute for Scientific Research (Canada))","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Sugar industry; Urban environment; Limiting","score_opus":0.07297526248881354,"score_gpt":0.33398782484368666,"score_spread":0.26101256235487313,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7024154702","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00031046246,0.003645596,0.20406473,0.28075108,0.023530409,0.0048895166,0.0072793616,0.00042611882,0.47510275],"genre_scores_gemma":[0.007008181,0.00027008785,0.028773358,0.00053382514,0.0011274699,0.00078249763,0.0011657595,0.000114391536,0.96022445],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9912001,0.000772545,0.00086851016,0.0020836615,0.0033581094,0.0017170929],"domain_scores_gemma":[0.98625565,0.002044016,0.0004315269,0.0011826233,0.009390665,0.00069551205],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005126819,0.0006604348,0.000657946,0.0020296525,0.0030015758,0.0029260057,0.0031428582,0.00052177947,0.002618602],"category_scores_gemma":[0.008790433,0.00072973926,0.00029526363,0.0041589183,0.0018561053,0.0014327834,0.0007112644,0.002029962,0.00006345838],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000018599032,0.00012395739,0.000026775395,0.00043387277,0.00014086885,0.00006648871,0.00008860509,0.00054754573,0.0007986389,0.3959269,0.57972735,0.022100383],"study_design_scores_gemma":[0.00038967235,0.000057346988,0.00013747132,0.0017939564,0.000028771314,0.00004889562,0.00014359817,0.009948866,0.00474016,0.009823347,0.9722353,0.00065259263],"about_ca_topic_score_codex":0.60752976,"about_ca_topic_score_gemma":0.99789387,"teacher_disagreement_score":0.4851217,"about_ca_system_score_codex":0.0054287803,"about_ca_system_score_gemma":0.064002246,"threshold_uncertainty_score":0.9995589},"labels":[],"label_agreement":null},{"id":"W7024632191","doi":"","title":"38: Since Conservatives Don't Listen","year":2019,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Politics; Racism; Indigenous; Government (linguistics); State (computer science)","score_opus":0.007959276489167055,"score_gpt":0.19791189979749613,"score_spread":0.18995262330832907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7024632191","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000034987956,0.00026145185,0.0001467283,0.00051045493,0.00031668963,0.00064320926,0.00009430346,0.00087769626,0.99714595],"genre_scores_gemma":[0.00012565503,0.00025334265,0.022218736,0.0007050884,0.00008847359,0.000028447355,0.0000683113,0.0000963669,0.9764156],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980155,0.00012046867,0.0006659377,0.0003445564,0.00051929423,0.00033423686],"domain_scores_gemma":[0.99780244,0.00018849024,0.0008042634,0.0008216967,0.00026647816,0.00011663241],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0002695894,0.0003959996,0.000525997,0.00015454816,0.000055444438,0.00016396384,0.0011773627,0.00045510443,0.12078798],"category_scores_gemma":[0.00012471998,0.0003910702,0.00018657545,0.000018604578,0.00016194185,8.4037805e-7,0.0003141503,0.00031320678,0.024766002],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010600423,0.0000328563,0.0000017438632,0.00035296395,0.000042330408,0.000012581778,0.00012433878,0.000004234422,7.463326e-7,0.0006073957,0.9941147,0.0046955207],"study_design_scores_gemma":[0.0003326648,0.00014566313,0.000004878352,0.00047038827,0.000015495143,0.000065059845,0.00003921419,0.00006089195,0.000104737,0.0000639839,0.99825954,0.00043747225],"about_ca_topic_score_codex":0.0020684542,"about_ca_topic_score_gemma":0.00027986814,"teacher_disagreement_score":0.09602197,"about_ca_system_score_codex":0.00005035041,"about_ca_system_score_gemma":0.00007515093,"threshold_uncertainty_score":0.99985415},"labels":[],"label_agreement":null},{"id":"W7034177394","doi":"","title":"A Study of the Lived Experiences of Intersectional Women and Non-Binary People in Canadian Publishing","year":2021,"lang":"en","type":"other","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Lived experience; Intersectionality; Publishing; Qualitative research; Identity (music); Narrative","score_opus":0.01595926198846362,"score_gpt":0.24743223188424823,"score_spread":0.2314729698957846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7034177394","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":[0.80793196,0.00009636322,0.0005802604,0.00011978968,0.00029977498,0.0005483008,0.0000038277394,0.00005096378,0.19036876],"genre_scores_gemma":[0.98390096,0.000008864285,0.0011289108,0.00006297708,0.000016728629,0.00015545405,0.0000013503322,0.000019881603,0.014704848],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9990741,0.00008934736,0.00020303445,0.00026222056,0.0002044894,0.00016680818],"domain_scores_gemma":[0.9994081,0.000040072002,0.00013183082,0.00028976245,0.000057386493,0.000072843],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024890804,0.000101878635,0.000227135,0.0004729694,0.000025160418,0.00011443525,0.00065657997,0.000096054784,0.0009118746],"category_scores_gemma":[0.000058770544,0.00007716722,0.000025667287,0.000532635,0.000046379817,0.00018479436,0.00033492479,0.000141578,2.9140602e-7],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000043550026,0.0006313711,0.04000988,0.00016985022,0.0001055314,0.000037032234,0.8958237,6.3145797e-7,0.00011447714,0.00027001803,0.055434845,0.007398313],"study_design_scores_gemma":[0.0013287344,0.0010822081,0.0793321,0.0016010199,0.000010202405,0.00005248693,0.9069327,0.0012464451,0.0013690144,0.0007067434,0.0054937233,0.0008445839],"about_ca_topic_score_codex":0.39663556,"about_ca_topic_score_gemma":0.75125915,"teacher_disagreement_score":0.35462356,"about_ca_system_score_codex":0.00008429194,"about_ca_system_score_gemma":0.00037329548,"threshold_uncertainty_score":0.9984387},"labels":[],"label_agreement":null},{"id":"W7036048844","doi":"","title":"Analisis Rasio Pendapatan Terhadap Partisipasi Anggota Koperasi Karyawan Horasi Wisata Akademi Pariwisata Medan (Kopkarsita Akpar Medan)","year":2006,"lang":"id","type":"dissertation","venue":"Repository Universitas Medan area (yes, our institution host repository self.)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Work (physics); Revenue; Government (linguistics); Quarter (Canadian coin); State (computer science)","score_opus":0.014856174985440113,"score_gpt":0.24186420272550252,"score_spread":0.2270080277400624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7036048844","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":[0.69457465,0.011410292,0.015508566,0.0016498565,0.033400375,0.010292102,0.0009756746,0.010452502,0.22173597],"genre_scores_gemma":[0.9746436,0.00097135844,0.005366422,0.0003266017,0.0020736768,0.00021789082,0.0053271665,0.00041129105,0.01066201],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9769871,0.0035434156,0.0046063745,0.006407715,0.0052736034,0.003181766],"domain_scores_gemma":[0.98303527,0.00039710908,0.0047596525,0.0059745414,0.0033346426,0.0024987655],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","research_integrity"],"consensus_categories":["metaepi_narrow","research_integrity"],"category_scores_codex":[0.0022405207,0.0039427723,0.0036303098,0.0030874014,0.006629069,0.00315296,0.007212478,0.0035486058,0.000138404],"category_scores_gemma":[0.0003639414,0.004520669,0.0021948821,0.0035390952,0.0010750411,0.007425601,0.0017965299,0.003919745,0.00025297003],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0038487085,0.014105192,0.12745638,0.0073373932,0.013048534,0.07508874,0.0537113,0.0010606656,0.23870097,0.024730656,0.4295896,0.011321874],"study_design_scores_gemma":[0.010057909,0.0044191848,0.07605775,0.012529681,0.013033688,0.013510604,0.09321251,0.0061612288,0.56688917,0.00024936936,0.1855078,0.0183711],"about_ca_topic_score_codex":0.0032719586,"about_ca_topic_score_gemma":0.0010891216,"teacher_disagreement_score":0.3281882,"about_ca_system_score_codex":0.0059910836,"about_ca_system_score_gemma":0.005450866,"threshold_uncertainty_score":0.9983783},"labels":[],"label_agreement":null},{"id":"W7065759846","doi":"","title":"FEDERAL GOVERNMENT HOUSING POLICY \"MY HOME, MY LIFE\" AND ITS INFLUENCE ON CIVIL CONSTRUCTION INDUSTRIES.","year":2018,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Real estate; Quarter (Canadian coin); Subdivision; Real estate development; Square (algebra)","score_opus":0.01680539721511493,"score_gpt":0.25197979674421656,"score_spread":0.23517439952910163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7065759846","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":[0.85888684,0.000031900043,0.11382612,0.002743222,0.00021133992,0.0003331233,0.000009312515,0.00081734225,0.023140807],"genre_scores_gemma":[0.98308885,0.000044781413,0.01324694,0.003122158,0.0002358928,0.000015885851,6.7125995e-7,0.000010164175,0.00023467916],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985862,0.00005190542,0.00023470247,0.0004050612,0.0004323758,0.00028978058],"domain_scores_gemma":[0.9992319,0.000056331573,0.000110682275,0.00026941256,0.00015239751,0.00017929636],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018144558,0.00016854754,0.00015235116,0.00012081344,0.00028229653,0.00039363722,0.00030242075,0.00012581528,0.000064997104],"category_scores_gemma":[0.00018948782,0.00015620574,0.000023460852,0.0004552623,0.00017819031,0.00078816153,0.00027590868,0.00017781804,0.00005918981],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041094263,0.00013869829,0.01066501,0.000035936006,0.000052905685,0.000015419582,0.0007698147,0.0000041460685,0.0067273295,0.13733871,0.007485085,0.83672583],"study_design_scores_gemma":[0.0026919958,0.002409886,0.04976435,0.0004928394,0.000020296893,0.00034050885,0.00043462767,0.010011089,0.8853882,0.021295303,0.02509464,0.0020562923],"about_ca_topic_score_codex":0.000088528584,"about_ca_topic_score_gemma":0.000030283174,"teacher_disagreement_score":0.87866086,"about_ca_system_score_codex":0.00015859194,"about_ca_system_score_gemma":0.00018148578,"threshold_uncertainty_score":0.6369885},"labels":[],"label_agreement":null},{"id":"W7069838725","doi":"","title":"Outil de détermination des temps de parcours dans un contexte de proctection des prises d'eau potable. Implantation sur le bassin versant de la rivière Saint-Charles, Ville de Québec.","year":2014,"lang":"fr","type":"other","venue":"EspaceINRS (National Institute for Scientific Research (Canada))","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Work (physics); Field (mathematics); Public policy","score_opus":0.03549440826397179,"score_gpt":0.30454379030288453,"score_spread":0.26904938203891277,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7069838725","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":[0.09855921,0.00063223584,0.88303506,0.005454602,0.00083070586,0.002010095,0.00074845064,0.00025976167,0.008469888],"genre_scores_gemma":[0.83782333,0.00031110834,0.10952758,0.00024079085,0.0005242861,0.0013164437,0.00056884787,0.00020276633,0.04948487],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.991298,0.0022423503,0.0007219388,0.0013073981,0.0023969368,0.0020333524],"domain_scores_gemma":[0.99312884,0.0017961051,0.0005123051,0.00057934946,0.0031693294,0.00081404846],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":["sts"],"category_scores_codex":[0.014124137,0.00057512487,0.0004975429,0.0010710504,0.0035642318,0.0020722707,0.0015512396,0.0005335061,0.00019555383],"category_scores_gemma":[0.006355874,0.00063900615,0.00019554782,0.00137876,0.00292107,0.0012949196,0.00027807956,0.00089872774,0.000015732441],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.0005652328,0.0019188091,0.024972763,0.0037403214,0.0007998507,0.0004957485,0.017080165,0.018287592,0.07776161,0.20062923,0.22829528,0.4254534],"study_design_scores_gemma":[0.0019313258,0.00029028856,0.02745968,0.0018691819,0.00008744144,0.00067967724,0.0012171591,0.14658266,0.097749874,0.027316507,0.6935966,0.001219609],"about_ca_topic_score_codex":0.9139089,"about_ca_topic_score_gemma":0.9972497,"teacher_disagreement_score":0.7735075,"about_ca_system_score_codex":0.019030156,"about_ca_system_score_gemma":0.06902818,"threshold_uncertainty_score":0.9997924},"labels":[],"label_agreement":null},{"id":"W7083422163","doi":"10.4103/jcneo_20120101_13","title":"Antenatal Magnesium Sulfate Decreases Risk of Cerebral Palsy","year":2012,"lang":"en","type":"article","venue":"Journal of Clinical Neonatology","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Cerebral palsy; Context (archaeology); Randomized controlled trial; Pregnancy; Gestation; Preterm delivery; Placebo; Asphyxia; Inclusion and exclusion criteria","score_opus":0.03859726649919957,"score_gpt":0.35161636065390856,"score_spread":0.31301909415470897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7083422163","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":[0.84278834,0.001033925,0.15294378,0.0009865678,0.0015177779,0.000088772846,0.000008185364,0.00005480956,0.0005778586],"genre_scores_gemma":[0.9191897,0.0002760151,0.079815015,0.00032104005,0.00035781006,0.0000015785488,7.717097e-7,0.000009386612,0.000028687822],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9962179,0.00087306614,0.0019928066,0.00018328201,0.0003547332,0.00037819217],"domain_scores_gemma":[0.9948435,0.0020178633,0.0018398919,0.00035954185,0.0005487427,0.00039045632],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032573957,0.00015175478,0.00084849604,0.00023144907,0.000051073843,0.00002034097,0.00095828634,0.00025145363,0.00014695374],"category_scores_gemma":[0.0027728959,0.00011407906,0.0005082623,0.00024072902,0.0002690026,0.00073190866,0.0002301154,0.00064769946,0.00003933122],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029076287,0.0011054414,0.660085,0.000047018286,0.00017416426,0.00033280152,0.00012374892,8.842874e-7,0.000119383614,0.014125485,0.0033113821,0.3202839],"study_design_scores_gemma":[0.0060532037,0.0037569336,0.84651273,0.0001887121,0.00037827116,0.013617278,0.00009180988,0.0010951833,0.032139406,0.066393875,0.029007819,0.000764788],"about_ca_topic_score_codex":0.000021940525,"about_ca_topic_score_gemma":0.0000042908155,"teacher_disagreement_score":0.3195191,"about_ca_system_score_codex":0.000012057264,"about_ca_system_score_gemma":0.00014298673,"threshold_uncertainty_score":0.4652009},"labels":[],"label_agreement":null},{"id":"W7083708886","doi":"10.15468/dl.sugs5y","title":"Occurrence Download","year":2025,"lang":"en","type":"dataset","venue":"Global Biodiversity Information Facility","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Download; Matching (statistics); Range (aeronautics); Data set","score_opus":0.012577553947730911,"score_gpt":0.2296120079376032,"score_spread":0.21703445398987228,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7083708886","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000056263784,0.00001767651,0.004328473,0.00033095214,0.0005913056,0.0003829393,0.9933704,0.00052387646,0.0004487192],"genre_scores_gemma":[0.0000018307054,0.00009540699,0.00009185598,0.0013650234,9.234958e-7,0.0000107417945,0.9984339,4.4101114e-9,3.024858e-7],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99821305,0.00009596326,0.0004677888,0.00035705217,0.00054146943,0.00032469453],"domain_scores_gemma":[0.9979626,0.00003568145,0.00031068482,0.0010644911,0.00047811063,0.00014846669],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00033178,0.000317108,0.00031347605,0.00022411245,0.00028596583,0.00046678644,0.0020502068,0.00042707223,0.00041203905],"category_scores_gemma":[0.00019190645,0.00033845843,0.0001837925,0.0007503739,0.000118214186,0.0022996701,0.0012295853,0.00035771375,0.040172473],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000062297504,0.00003058557,0.000052280124,0.00013904466,0.00001915526,0.0000024379165,0.00001715075,4.4255893e-7,1.9608322e-8,0.0000017197361,0.9828613,0.016869653],"study_design_scores_gemma":[0.00019555511,0.000031466436,0.000010200947,0.000008166545,0.000021240667,0.0000052636287,0.000013502297,8.3299966e-7,0.000028876471,0.000014339184,0.9993557,0.00031490388],"about_ca_topic_score_codex":0.00025533844,"about_ca_topic_score_gemma":0.000006701184,"teacher_disagreement_score":0.039760433,"about_ca_system_score_codex":0.00035163076,"about_ca_system_score_gemma":0.00034471837,"threshold_uncertainty_score":0.9999067},"labels":[],"label_agreement":null},{"id":"W7090714166","doi":"10.5281/zenodo.17351326","title":"eic/EICrecon: v1.30.0","year":2025,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Digitization; Tracking (education); Timestamp; Workflow; Debugging; Detector; Identification (biology)","score_opus":0.02480174436751295,"score_gpt":0.24937461173716985,"score_spread":0.2245728673696569,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7090714166","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[9.4089745e-7,0.00019860611,0.20698497,0.00053669605,0.0001903629,0.0004630388,0.00020991269,0.0058542914,0.7855612],"genre_scores_gemma":[0.0007853728,0.00094886747,0.018244527,0.0010679582,0.0006071213,3.0508642e-7,0.002050478,0.009657741,0.9666376],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976364,0.00037068792,0.0003036594,0.0008110726,0.00043506207,0.00044312308],"domain_scores_gemma":[0.9979823,0.000026569129,0.00020583918,0.0011630908,0.0004384466,0.00018372016],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00051215105,0.00028583608,0.00029293398,0.00085333193,0.00088365184,0.0014624909,0.0035080193,0.00025407088,0.09924837],"category_scores_gemma":[0.0003389394,0.0003153095,0.000103413586,0.000782077,0.00013465346,0.00022337666,0.0027715508,0.00045998016,0.046683937],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000019093568,0.00004316594,7.203885e-8,0.00006104572,0.000033094726,0.000013439596,0.00006256377,1.4081019e-7,0.000056214634,0.012327371,0.7159443,0.27145672],"study_design_scores_gemma":[0.0002326377,0.000101170364,0.0000062128534,0.00020677688,0.000011716712,0.000050814204,0.000015203426,0.000117984644,0.00050088775,0.0012654577,0.9971725,0.00031863802],"about_ca_topic_score_codex":0.000037971906,"about_ca_topic_score_gemma":5.16404e-7,"teacher_disagreement_score":0.2812282,"about_ca_system_score_codex":0.00014148442,"about_ca_system_score_gemma":0.000014792203,"threshold_uncertainty_score":0.9999299},"labels":[],"label_agreement":null},{"id":"W7096021006","doi":"","title":"Visual Word Recognition","year":2011,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Windsor; Permission; Documentation; Word (group theory); Legislation; Intellectual property","score_opus":0.05146013378516957,"score_gpt":0.26856521799036454,"score_spread":0.21710508420519498,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7096021006","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":[0.010327602,0.000006687213,0.8168829,0.000091273985,0.00010593998,0.00009543596,4.6162288e-7,0.0011854176,0.17130427],"genre_scores_gemma":[0.5496327,0.0000123913605,0.4487562,0.000763935,0.000034246805,0.000035545443,0.0000029377527,0.000006721393,0.00075530127],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993641,0.00003418469,0.000113326576,0.00021577066,0.000115617884,0.00015699724],"domain_scores_gemma":[0.9995978,0.000019726038,0.000035342542,0.00019628355,0.00008481819,0.00006606181],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00015676653,0.00007488703,0.00006946948,0.00011029438,0.000044987097,0.000050904888,0.00032693072,0.00004819524,0.0010960599],"category_scores_gemma":[0.000018767265,0.000067312685,0.00003996663,0.00023152468,0.000021107904,0.00057845004,0.000102310456,0.000067970424,0.0015428236],"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":[0.0000020771977,0.000065278524,0.0000872907,0.0000021851574,0.0000040481336,0.000007838969,0.0001970276,1.3127412e-9,0.00046005906,0.0057842354,0.0023299602,0.99106],"study_design_scores_gemma":[0.00032901848,0.00031677686,0.0040091206,0.000036059097,0.000006803021,0.00007067055,0.000055636156,0.0015228869,0.77914137,0.20864584,0.005354925,0.00051087054],"about_ca_topic_score_codex":0.000026729593,"about_ca_topic_score_gemma":0.0000064076844,"teacher_disagreement_score":0.99054915,"about_ca_system_score_codex":0.000012486228,"about_ca_system_score_gemma":0.000016915375,"threshold_uncertainty_score":0.9998171},"labels":[],"label_agreement":null},{"id":"W7096403569","doi":"","title":"Proc. ICDAR’95, Third International Conference on Document Analysis and Recognition, Montreal, Canada,","year":2008,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Segmentation; Headline; Set (abstract data type); Benchmark (surveying); Data set; Image segmentation; Scale-space segmentation","score_opus":0.02398816545746102,"score_gpt":0.2477707573966606,"score_spread":0.22378259193919958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7096403569","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":[0.07744344,0.000060106406,0.7669153,0.008171885,0.0002915943,0.0005336448,0.00005762316,0.0007724683,0.1457539],"genre_scores_gemma":[0.9673155,0.00041350044,0.028075727,0.0018400738,0.00003963066,0.00006679862,0.000044325603,0.0000059380723,0.00219852],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9986503,0.000047025962,0.00025047033,0.00042161593,0.0004453175,0.00018526496],"domain_scores_gemma":[0.9991308,0.000052437896,0.00008702932,0.00027186426,0.00032774507,0.00013016645],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013080456,0.00014319997,0.00018007726,0.0002042837,0.00013321778,0.00012965429,0.0004311642,0.00004699875,0.00039134308],"category_scores_gemma":[0.000032606942,0.00012603887,0.00005041464,0.00043003075,0.00004986158,0.00037654414,0.00011983127,0.000107136715,0.000030311634],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005514163,0.0004217055,0.010295996,0.000025132764,0.0013033886,0.00038350024,0.0013943862,0.000014847474,0.0004920166,0.023252154,0.1984103,0.7639514],"study_design_scores_gemma":[0.005203011,0.0017436334,0.302948,0.0003763034,0.0007080576,0.0010784946,0.0007822163,0.1889498,0.1854117,0.27122176,0.03612142,0.0054555917],"about_ca_topic_score_codex":0.24127233,"about_ca_topic_score_gemma":0.39129958,"teacher_disagreement_score":0.889872,"about_ca_system_score_codex":0.000104795305,"about_ca_system_score_gemma":0.00024530638,"threshold_uncertainty_score":0.7637801},"labels":[],"label_agreement":null},{"id":"W7097373972","doi":"","title":"Author manuscript, published in &amp;quot;ICFHR, Montreal: Canada (2008)&amp;quot; Recognition-based Vs Syntax-directed Models for Numerical Field Extraction in Handwritten Documents","year":2009,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Handwriting; Handwriting recognition; Field (mathematics); Feature extraction; Information extraction; Pattern recognition (psychology)","score_opus":0.030079536067806004,"score_gpt":0.28033197832606904,"score_spread":0.25025244225826304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7097373972","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":[0.015074689,0.00008152213,0.95779634,0.0178491,0.00058965234,0.001831568,0.000063028514,0.001275681,0.005438423],"genre_scores_gemma":[0.69354504,0.00003242788,0.29144895,0.008206772,0.00013231397,0.00096851226,0.0004987693,0.00005735903,0.005109862],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956298,0.0002825648,0.001153879,0.0011950729,0.0007371463,0.0010015554],"domain_scores_gemma":[0.9973629,0.0006964619,0.0002969551,0.00083883805,0.0004521276,0.00035270868],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00086182455,0.0004980393,0.0006649048,0.00088117924,0.00017295634,0.00057480996,0.00095667323,0.00037782613,0.00042334653],"category_scores_gemma":[0.00068882015,0.00050766545,0.00016484792,0.0014377305,0.00002754261,0.0024623268,0.00008080376,0.0005841036,0.00002671417],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00067642273,0.001680246,0.0011925404,0.00010803112,0.000058594465,0.00013771314,0.000499731,0.00062588503,0.0014217013,0.00063631305,0.4850823,0.5078805],"study_design_scores_gemma":[0.011275796,0.0015039829,0.0165332,0.0011956631,0.00010215329,0.00015883787,0.00020250537,0.6506485,0.05320871,0.20478651,0.055746835,0.004637329],"about_ca_topic_score_codex":0.38648313,"about_ca_topic_score_gemma":0.67647773,"teacher_disagreement_score":0.6784703,"about_ca_system_score_codex":0.0007310143,"about_ca_system_score_gemma":0.00071100413,"threshold_uncertainty_score":0.9997375},"labels":[],"label_agreement":null},{"id":"W7098145901","doi":"","title":"Automatic Segmentation and Recognition System for Handwritten Dates on Canadian Bank Cheques","year":2002,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Segmentation; Cheque; Cursive; Set (abstract data type); Pattern recognition (psychology); Test set; Handwriting recognition","score_opus":0.03149555831714395,"score_gpt":0.24110989483288162,"score_spread":0.20961433651573766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7098145901","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":[0.17709713,0.0003271716,0.74828875,0.0069022565,0.0006995194,0.0045169755,0.00020269197,0.0055802544,0.056385227],"genre_scores_gemma":[0.8610887,0.000037084676,0.1370702,0.0009567106,0.00005846387,0.00035026934,0.000054674485,0.000016256907,0.0003676714],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99900275,0.000051943363,0.00022542698,0.00032803367,0.00013766123,0.0002541643],"domain_scores_gemma":[0.99931294,0.000121105346,0.00006723454,0.00021764141,0.00011134217,0.00016976208],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024775555,0.00013714348,0.00014286787,0.00028379084,0.00019233316,0.0003017602,0.00020583853,0.00007769171,0.00014907084],"category_scores_gemma":[0.000039221177,0.00012625109,0.00003548902,0.00016845048,0.000022959928,0.0005689663,0.000025350579,0.000056602526,0.00015051455],"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":[0.0000013505104,0.000026259462,0.000046084006,0.00012215792,0.000016853755,0.000004966296,0.00037888807,1.7398713e-7,0.0007085242,0.0027758328,0.0073016984,0.9886172],"study_design_scores_gemma":[0.0019154224,0.0011157522,0.00088321336,0.0008612835,0.00006291688,0.00018390141,0.0006518369,0.50357825,0.47007796,0.016006984,0.0034827937,0.0011796899],"about_ca_topic_score_codex":0.003088019,"about_ca_topic_score_gemma":0.0030790672,"teacher_disagreement_score":0.98743755,"about_ca_system_score_codex":0.00014989062,"about_ca_system_score_gemma":0.000022421382,"threshold_uncertainty_score":0.514837},"labels":[],"label_agreement":null},{"id":"W7099848519","doi":"","title":"Generalized Quality Control for Optical Data Capture at Statistics Canada","year":2015,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Process (computing); Control (management); Quality (philosophy); Statistical process control; Data quality; Process control; Automatic identification and data capture","score_opus":0.08684502614710958,"score_gpt":0.3319107995220021,"score_spread":0.2450657733748925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7099848519","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":[0.00048181586,0.000033339147,0.99362993,0.0021875806,0.00024308852,0.00033577447,0.0016596685,0.00019761155,0.0012311742],"genre_scores_gemma":[0.06589112,0.0000024398462,0.92737246,0.004220059,0.000073658615,0.00004823055,0.00052521366,0.000009878197,0.0018569317],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99865234,0.00007414809,0.00027591252,0.00038046643,0.00036166265,0.0002554652],"domain_scores_gemma":[0.9980134,0.0003540082,0.00006802538,0.0009450626,0.00035451632,0.00026499215],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006792562,0.0001126572,0.0002050545,0.000021050117,0.00006349746,0.00008983417,0.0011069624,0.00005840172,0.000037533613],"category_scores_gemma":[0.0005953101,0.00009411331,0.00001564093,0.00008117323,0.00003219928,0.00022171294,0.00037847488,0.00006594415,0.000010116194],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001760488,0.000020142767,0.00008101058,0.000009118343,0.00001604068,0.000008840905,0.000025335656,0.000002614363,0.00012638987,0.14952531,0.84170353,0.00846406],"study_design_scores_gemma":[0.007824054,0.00024782165,0.0006876211,0.000018663923,0.00006550084,0.00007578341,0.000094421266,0.35560536,0.016149966,0.05997588,0.5579495,0.0013054318],"about_ca_topic_score_codex":0.16648258,"about_ca_topic_score_gemma":0.5458927,"teacher_disagreement_score":0.37941012,"about_ca_system_score_codex":0.00017816343,"about_ca_system_score_gemma":0.0008149674,"threshold_uncertainty_score":0.8390679},"labels":[],"label_agreement":null},{"id":"W7100866710","doi":"","title":"Research Article Role Clarification Processes for Better Integration of Nurse Practitioners into Primary Healthcare Teams: A Multiple-Case Study","year":2016,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"CLARITY; Variety (cybernetics); Health care; Qualitative research; Primary care; Primary health care; Empirical research; Process (computing)","score_opus":0.05561197410931885,"score_gpt":0.37684954894441697,"score_spread":0.3212375748350981,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7100866710","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":[0.3384418,0.000024485737,0.65317595,0.0064191623,0.000027025391,0.0015136002,0.0000059725558,0.00022942376,0.00016261938],"genre_scores_gemma":[0.87554234,0.000008806085,0.123064436,0.00020145363,0.00003520058,0.0010301742,0.000006929619,0.00001147597,0.00009916414],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9981705,0.0003411569,0.00041759163,0.00045003492,0.00037080797,0.0002499231],"domain_scores_gemma":[0.996476,0.0008745506,0.00015970945,0.00051015307,0.0018902218,0.000089394416],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016174983,0.00011115755,0.0001536428,0.00031634752,0.00021176982,0.000099100645,0.000351169,0.000091800095,0.000010506799],"category_scores_gemma":[0.0007703006,0.00007681209,0.000038375252,0.000664947,0.00009260414,0.0014763812,0.00007041728,0.00014534808,0.000018736955],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007405891,0.0012555277,0.006846608,0.00016599931,0.000022131642,0.000013111917,0.008403716,2.2443052e-7,0.12604308,0.0033092871,0.0009332351,0.85293305],"study_design_scores_gemma":[0.0024419841,0.00267635,0.0034428579,0.00033111704,0.000021236541,0.00016758803,0.03511511,0.0023940352,0.902225,0.05017301,0.00057457126,0.00043709227],"about_ca_topic_score_codex":0.0006012607,"about_ca_topic_score_gemma":0.00073314237,"teacher_disagreement_score":0.8524959,"about_ca_system_score_codex":0.00017959333,"about_ca_system_score_gemma":0.0002909869,"threshold_uncertainty_score":0.3132306},"labels":[],"label_agreement":null},{"id":"W7125409899","doi":"10.18280/mmep.121207","title":"A Novel Swarm-Based Hybridization of Puma Optimizer and Crested Porcupine Algorithm for Complex Handwriting Recognition in Writer Identification","year":2025,"lang":"","type":"article","venue":"Mathematical Modelling and Engineering Problems","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Porcupine; Identification (biology); Puma; Handwriting; Pattern recognition (psychology)","score_opus":0.04675143932627295,"score_gpt":0.25862750660513795,"score_spread":0.211876067278865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7125409899","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":[0.0070455913,0.00031893863,0.9906966,0.0003273753,0.00006730341,0.0012836669,0.00005460827,0.00017194753,0.000033943084],"genre_scores_gemma":[0.3255333,0.000111505586,0.6739585,0.00003007571,0.000018842638,0.00023742687,0.00005770972,0.000026339996,0.000026342954],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997521,0.000039623268,0.0012412516,0.00060885365,0.00021525765,0.00037403734],"domain_scores_gemma":[0.99861383,0.00047011397,0.00024096227,0.00027422394,0.0003054919,0.000095358155],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011963692,0.00032259885,0.00056881335,0.0006489731,0.00011326656,0.00033513122,0.00019408576,0.00020331936,0.00000521961],"category_scores_gemma":[0.00016155667,0.00035925573,0.00008272924,0.0005746043,0.00008447474,0.0003711545,0.000089860376,0.0002219498,0.0000010062829],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035770165,0.00078001467,0.000010612819,0.011830428,0.00009589884,0.0000021581789,0.0010904535,0.6801058,0.020790124,0.008710316,0.000015086216,0.2765333],"study_design_scores_gemma":[0.0013873208,0.00009207811,0.000022361106,0.004954059,0.000063539606,0.000011200765,0.000019451614,0.9575702,0.013616166,0.021928115,0.000013134786,0.0003224054],"about_ca_topic_score_codex":0.000019447592,"about_ca_topic_score_gemma":7.396339e-7,"teacher_disagreement_score":0.3184877,"about_ca_system_score_codex":0.000051819614,"about_ca_system_score_gemma":0.000046609155,"threshold_uncertainty_score":0.9998859},"labels":[],"label_agreement":null},{"id":"W7126175075","doi":"10.18280/isi.301220","title":"A Hybrid U-Net–GAN Framework for Restoring Broken Kannada Handwritten Characters","year":2025,"lang":"","type":"article","venue":"Ingénierie des systèmes d information","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Feature (linguistics); Pattern recognition (psychology); Intersection (aeronautics); Character recognition; Field (mathematics)","score_opus":0.016879031672600815,"score_gpt":0.26242725813810946,"score_spread":0.24554822646550864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7126175075","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":[0.018357191,0.0005077282,0.9648788,0.00097570935,0.0034027842,0.0025059439,0.00015111784,0.0010182656,0.008202488],"genre_scores_gemma":[0.8955495,0.00032887512,0.09938624,0.0024066148,0.00038180928,0.001039534,0.00020777123,0.00004434805,0.00065532036],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9949264,0.00021055994,0.0021942058,0.00068792206,0.0007392543,0.0012416911],"domain_scores_gemma":[0.99515194,0.0006411987,0.0011726888,0.00129818,0.0014409873,0.0002950038],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0017635114,0.00073454547,0.00084279897,0.0014016058,0.0013694754,0.003001199,0.0017009355,0.0005300957,0.000046815097],"category_scores_gemma":[0.0020865048,0.00084153144,0.00043045045,0.0014397188,0.00035611884,0.01019663,0.00045811897,0.00072968454,0.00017538904],"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":[0.00017056546,0.00009146541,0.0003898343,0.002430443,0.0002482082,0.0000086874,0.007186517,0.000041374715,0.00020912853,0.0892612,0.0066622747,0.8933003],"study_design_scores_gemma":[0.003415246,0.0012208631,0.007489746,0.016214732,0.00037524707,0.00018351927,0.0016042806,0.102147706,0.107755035,0.6062534,0.15006222,0.0032780066],"about_ca_topic_score_codex":0.00022445264,"about_ca_topic_score_gemma":0.000012909869,"teacher_disagreement_score":0.8900223,"about_ca_system_score_codex":0.0012764119,"about_ca_system_score_gemma":0.00081153103,"threshold_uncertainty_score":0.9999306},"labels":[],"label_agreement":null},{"id":"W7128562304","doi":"","title":"Reconnaissance de Graphiques en utilisant les Relations Spatiales et Analyse de la Forme","year":2011,"lang":"en","type":"article","venue":"theses.fr (ABES)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Institut national de recherche en informatique et en automatique (INRIA)","keywords":"Statistical analysis; Nova scotia; Emic and etic","score_opus":0.05270325927231056,"score_gpt":0.3057542872049931,"score_spread":0.2530510279326825,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7128562304","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":[0.16616376,0.0002601285,0.68262017,0.00039183992,0.00006239951,0.00026179582,0.000015580701,0.0011440341,0.14908028],"genre_scores_gemma":[0.8451539,0.0004005563,0.1539573,0.00029132143,0.00003849671,0.000079570076,0.0000046495466,0.000021099171,0.000053090273],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99799126,0.00072438933,0.00032993185,0.00036795848,0.00019217723,0.00039426918],"domain_scores_gemma":[0.99841344,0.0005647916,0.00015745073,0.00060182746,0.00011564211,0.00014686542],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016417232,0.00020981136,0.00023698343,0.00029864255,0.00017838505,0.00013651673,0.0008908138,0.00019149367,0.00026193084],"category_scores_gemma":[0.0003842624,0.00019318926,0.00014971319,0.00039668113,0.00024085386,0.0007959005,0.00018319645,0.00033575625,0.000074662545],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022654513,0.00035753727,0.0708046,0.0000420404,0.00012240733,0.00007307249,0.033307448,0.0000049392597,0.003903364,0.7528345,0.0013905169,0.13713689],"study_design_scores_gemma":[0.00048047866,0.00027195533,0.12083627,0.0003809152,0.00008915978,0.00022588024,0.0014078909,0.0060878824,0.23747988,0.6144352,0.0173771,0.00092740514],"about_ca_topic_score_codex":0.0030787264,"about_ca_topic_score_gemma":0.0007506077,"teacher_disagreement_score":0.6789901,"about_ca_system_score_codex":0.00009473207,"about_ca_system_score_gemma":0.00012833335,"threshold_uncertainty_score":0.78780293},"labels":[],"label_agreement":null},{"id":"W7131543556","doi":"","title":"Djupinlärning för klassifikation av inskannade dokument : Vad är viktigt?","year":2025,"lang":"en","type":"article","venue":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Pipeline (software); Deep learning; Training set; Image quality; Modality (human–computer interaction); Set (abstract data type); Robustness (evolution); Quality (philosophy)","score_opus":0.018995281880474543,"score_gpt":0.27866394729386573,"score_spread":0.2596686654133912,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7131543556","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":[0.0077841175,0.0003124458,0.9384544,0.02698775,0.000813678,0.000987393,0.00015576318,0.0030149051,0.021489589],"genre_scores_gemma":[0.61573756,0.0002109648,0.37734047,0.0017277132,0.00008243825,0.0009427086,0.0013683925,0.000033696135,0.0025560625],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99686146,0.00007320063,0.0009969987,0.0010189833,0.0005221767,0.00052717136],"domain_scores_gemma":[0.99598366,0.000053464213,0.0006056112,0.0022289879,0.0009937099,0.00013458333],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007925518,0.0003631281,0.000427813,0.0024869493,0.00036933745,0.00027023815,0.0026496612,0.00040392243,0.00008895758],"category_scores_gemma":[0.00097613176,0.000379818,0.00012086498,0.003456803,0.0004247394,0.0023312408,0.0015381225,0.0005788297,0.00010994654],"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":[0.000013719254,0.00046104818,0.0019755277,0.000158489,0.00012291656,0.000009457007,0.00006495366,0.00003360244,0.0061422656,0.6217181,0.04743888,0.32186103],"study_design_scores_gemma":[0.0012634991,0.00016171268,0.0030942953,0.0006037503,0.000078879,0.000017099394,0.00007873477,0.021915993,0.20982893,0.011481807,0.7507052,0.00077009614],"about_ca_topic_score_codex":0.00012366158,"about_ca_topic_score_gemma":0.00004103166,"teacher_disagreement_score":0.7032663,"about_ca_system_score_codex":0.00024269804,"about_ca_system_score_gemma":0.00047500196,"threshold_uncertainty_score":0.99986535},"labels":[],"label_agreement":null},{"id":"W7160034663","doi":"10.1109/iccv51701.2025.02155","title":"A Token-Level Text Image Foundation Model for Document Understanding","year":2025,"lang":"","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","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":"Artificial Intelligence in Medicine (Canada)","funders":"National Natural Science Foundation of China","keywords":"Foundation (evidence); Image (mathematics); Context (archaeology); Image processing; Feature (linguistics)","score_opus":0.09104862361110418,"score_gpt":0.3344530283190299,"score_spread":0.24340440470792574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7160034663","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":[0.0000487921,0.00007123517,0.94367033,0.007080187,0.0005913447,0.0019057641,0.000023607763,0.000532264,0.04607647],"genre_scores_gemma":[0.39966646,0.000149432,0.5700198,0.002009861,0.0000539954,0.0003536002,0.000019982575,0.000022732604,0.027704187],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968786,0.00009350346,0.0008666337,0.0010196371,0.00042882873,0.0007127573],"domain_scores_gemma":[0.9980389,0.00032687132,0.00023062628,0.00077155116,0.0004793289,0.00015274575],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0010958081,0.0004122523,0.00040448943,0.00063383294,0.00068381004,0.0017809483,0.0009901007,0.00022265804,0.00037310543],"category_scores_gemma":[0.00015104674,0.00043528227,0.00027793605,0.00084485224,0.00016195056,0.002204453,0.0005693717,0.00022490874,0.0001265437],"study_design_candidate":"theoretical_or_conceptual","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":[0.000037219364,0.00013878928,0.000004505726,0.00019893599,0.00007720587,0.000001552545,0.0006075819,0.00007158111,0.0013625856,0.7310404,0.016261097,0.25019854],"study_design_scores_gemma":[0.0007181778,0.00008809599,0.000005332144,0.00019051565,0.000041407104,0.0000022448169,0.0001542818,0.58197176,0.013122151,0.40252125,0.000888991,0.00029577332],"about_ca_topic_score_codex":0.00004423764,"about_ca_topic_score_gemma":0.00006869308,"teacher_disagreement_score":0.5819002,"about_ca_system_score_codex":0.0012998794,"about_ca_system_score_gemma":0.00072558946,"threshold_uncertainty_score":0.9998099},"labels":[],"label_agreement":null},{"id":"W7160830763","doi":"10.1109/rcsm67767.2025.11507832","title":"Automated Library Book Identification Using YOLO-Based Detection and Google Vision Text Extraction","year":2025,"lang":"","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","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":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Identification (biology); Information extraction; Feature extraction; Text detection; Key (lock)","score_opus":0.01358203460884771,"score_gpt":0.29551841219336195,"score_spread":0.28193637758451423,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7160830763","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":[0.027996037,0.001095556,0.9595189,0.0013882326,0.0010099863,0.0010114381,0.0000076082792,0.004596611,0.0033756504],"genre_scores_gemma":[0.95256287,0.00034127873,0.0415688,0.0012920329,0.00006943829,0.00005970968,0.000019935887,0.0000361241,0.004049839],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99660516,0.00044028368,0.0009947508,0.0011505627,0.0003853152,0.00042394194],"domain_scores_gemma":[0.9981549,0.00022631667,0.00046473052,0.00075173785,0.0002485549,0.0001538025],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006121851,0.00039697214,0.0003377383,0.001220723,0.00076079904,0.0019340026,0.0004481103,0.00046606676,0.0004324752],"category_scores_gemma":[0.00008624654,0.00043697236,0.00013400959,0.0018070043,0.00018664179,0.00617294,0.000298253,0.00037004394,0.0001054972],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006257341,0.00028734223,0.00014351988,0.00021261211,0.00003450447,0.000007886939,0.00007700505,0.00007476643,0.34479046,0.00068071246,0.003589945,0.65003866],"study_design_scores_gemma":[0.00032451155,0.000108533386,0.0033224379,0.0003003851,0.00004521027,0.000017552977,0.000019990579,0.5695846,0.42204463,0.00097113213,0.003009676,0.00025131128],"about_ca_topic_score_codex":0.00009879465,"about_ca_topic_score_gemma":0.0000117906,"teacher_disagreement_score":0.9245668,"about_ca_system_score_codex":0.0002112837,"about_ca_system_score_gemma":0.0003562309,"threshold_uncertainty_score":0.9998082},"labels":[],"label_agreement":null},{"id":"W76404166","doi":"10.29173/cais269","title":"Le traitement des articles initiaux dans les catalogues de bibliothèque : une étude de cas","year":2013,"lang":"fr","type":"article","venue":"Proceedings of the Annual Conference of CAIS / Actes du congrès annuel de l ACSI","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Humanities; Philosophy; Word (group theory); Linguistics","score_opus":0.042628897178122564,"score_gpt":0.26403125193598165,"score_spread":0.22140235475785908,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W76404166","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":[0.970629,0.0009511988,0.0119541595,0.009350892,0.000109882785,0.00068662,0.00019454076,0.0001908635,0.005932854],"genre_scores_gemma":[0.9803589,0.0009674386,0.017457766,0.0004403791,0.00011423536,0.00018371124,0.0000065958175,0.00004540214,0.00042559684],"study_design_codex":"qualitative","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9967598,0.00011921051,0.0009171533,0.0005701736,0.00058399624,0.0010497152],"domain_scores_gemma":[0.96355593,0.00031714037,0.00088092766,0.0003631551,0.034491103,0.00039176043],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0011523904,0.00048761728,0.00064732233,0.0006033058,0.00038244878,0.0065425285,0.0031384788,0.00034413105,0.00006607744],"category_scores_gemma":[0.0077756643,0.0004436835,0.0002940301,0.0019045557,0.0018866122,0.019867273,0.0010895116,0.00051236234,0.000020365427],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006763268,0.0011777052,0.1708103,0.0017767834,0.00033029076,0.00001653061,0.33064973,0.00001395124,0.2254382,0.11024866,0.007531582,0.1519386],"study_design_scores_gemma":[0.0006121108,0.0006440443,0.25867334,0.0014870745,0.000130741,0.0003109787,0.010663887,0.0028643669,0.63396585,0.08375775,0.0062541724,0.0006356979],"about_ca_topic_score_codex":0.020998713,"about_ca_topic_score_gemma":0.0018803638,"teacher_disagreement_score":0.4085276,"about_ca_system_score_codex":0.00023571968,"about_ca_system_score_gemma":0.0013662338,"threshold_uncertainty_score":0.9998015},"labels":[],"label_agreement":null},{"id":"W899286121","doi":"","title":"Binarization of Degraded Historical Document Images","year":2014,"lang":"en","type":"article","venue":"Rapports de recherche internes","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Thresholding; Historical document; Artificial intelligence; Computer science; Image (mathematics); Pattern recognition (psychology); Computer vision; Task (project management); Document image processing; Image segmentation; Engineering","score_opus":0.09602289950378384,"score_gpt":0.3399753025780331,"score_spread":0.24395240307424926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W899286121","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":[0.018463254,0.000121140336,0.9772949,0.0008418569,0.00015983557,0.00012005247,3.4200173e-7,0.00035464796,0.0026439477],"genre_scores_gemma":[0.77799016,0.00010636195,0.22005026,0.00018263752,0.000047123292,0.000035549114,0.0000024245749,0.000013034776,0.001572477],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983154,0.00065645407,0.00034918232,0.00027753925,0.00020329346,0.00019813304],"domain_scores_gemma":[0.9989359,0.0002588556,0.00018751482,0.00038928684,0.00014196386,0.000086472755],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023345961,0.00012882384,0.00020951199,0.0001765314,0.000023174132,0.000056872857,0.0005575211,0.00020568943,0.000036383426],"category_scores_gemma":[0.00046341197,0.00011899556,0.00009969485,0.0002761936,0.000032689608,0.00029313378,0.00012975783,0.00024471284,0.000014991625],"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":[0.000013066188,0.00022599408,0.0041543175,0.00010824039,0.000039348342,0.000017202949,0.0019085926,0.0000038302765,0.036624327,0.014754141,0.008483951,0.933667],"study_design_scores_gemma":[0.00035728057,0.00041821945,0.0019708506,0.00024327624,0.000024840541,0.000108574626,0.000038930226,0.005201533,0.7710711,0.19267368,0.027453782,0.0004379234],"about_ca_topic_score_codex":0.00011674877,"about_ca_topic_score_gemma":0.0000035570813,"teacher_disagreement_score":0.9332291,"about_ca_system_score_codex":0.0005065471,"about_ca_system_score_gemma":0.00009198092,"threshold_uncertainty_score":0.48524982},"labels":[],"label_agreement":null}]}