{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":605,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":605,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"03ce2755ddb7","filters":{"topic":"Handwritten Text Recognition Techniques"}},"results":[{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04721076647622582,"gpt":0.2951678601617646,"spread":0.2479570936855387,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003140557,0.0002778237,0.0004265995,0.0005085857,0.0002750633,0.0002219974,0.0002993291,0.00009281442,0.0007576719],"category_scores_gemma":[0.000007338643,0.0002611333,0.0001672618,0.001160101,0.0001163314,0.0003311942,0.000007275473,0.0003395969,0.00005343977],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002022244,"about_ca_system_score_gemma":0.00001589428,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001827967,"about_ca_topic_score_gemma":0.003828054,"domain_scores_codex":[0.99806,0.0002395574,0.0005010411,0.0006811271,0.0002528717,0.0002653842],"domain_scores_gemma":[0.9987658,0.0003552639,0.00009810795,0.0003972481,0.0002043207,0.0001793037],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001391798,0.0002082734,0.0002970808,0.00001271407,0.0002168748,0.00001170066,0.0001214178,0.0002763094,0.00008642333,0.000002231141,0.000007258606,0.9987458],"study_design_scores_gemma":[0.001065478,0.00146045,0.04350984,0.000425664,0.001447915,0.0003852046,0.0002331308,0.6646537,0.2808706,0.002544079,0.001010128,0.002393862],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08270099,0.0002530979,0.9159328,0.0003325498,0.00004581918,0.0001536853,0.0003127028,0.0001988461,0.00006949147],"genre_scores_gemma":[0.9887236,0.004284753,0.005547666,0.001100854,0.00002398663,0.0000249479,0.00006906695,0.00001440275,0.0002106602],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.996352,"threshold_uncertainty_score":0.9999841,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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)","retraction":null,"screen_n_in":null,"score":{"opus":0.02285943870308256,"gpt":0.2794097470582382,"spread":0.2565503083551556,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003030669,0.000266246,0.0003568934,0.0003032778,0.000829989,0.0007106006,0.0005164848,0.00005887709,0.00003336067],"category_scores_gemma":[0.000007708395,0.0002029243,0.0001386491,0.0003916018,0.0001248944,0.0006864777,0.00001652048,0.0003370655,0.000007126956],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001857907,"about_ca_system_score_gemma":0.00001124059,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004978615,"about_ca_topic_score_gemma":0.001284593,"domain_scores_codex":[0.9985103,0.00007487521,0.000302649,0.0006074312,0.0002189946,0.0002857274],"domain_scores_gemma":[0.9987621,0.0001080164,0.0002193056,0.0006696469,0.00007913353,0.0001617487],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001215547,0.00004639375,0.008033604,0.00001239343,0.0002244521,0.00001547256,0.0002150083,0.0004498991,0.00007594974,0.00001212595,0.000002140965,0.9909004],"study_design_scores_gemma":[0.0006087202,0.001005873,0.1879607,0.0005008361,0.001340158,0.0002159749,0.00007781589,0.757223,0.04743348,0.001693614,0.0001038886,0.001835901],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08779517,0.00006543513,0.9109733,0.0006558556,0.0001628069,0.0001386391,0.00001082439,0.0001306549,0.00006733948],"genre_scores_gemma":[0.9947261,0.0005675383,0.004222524,0.0003451156,0.00004079559,0.00003208306,0.000003236942,0.00001323174,0.00004934517],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9890645,"threshold_uncertainty_score":0.8275012,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Search engine indexing; Information retrieval; Relevance (law); Human–computer information retrieval; Image retrieval; Normalization (sociology); Document retrieval; Key (lock); Optical character recognition; Graphics; Relevance feedback; Notation; Artificial intelligence; Pattern recognition (psychology); Search engine; Image (mathematics); Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.04133708286574984,"gpt":0.2874709149178449,"spread":0.246133832052095,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007521482,0.000175839,0.0003150802,0.001075836,0.0001201377,0.0002685564,0.0003812852,0.0001009534,0.001457274],"category_scores_gemma":[0.0001485314,0.0001417623,0.0002288896,0.0004244372,0.00009670984,0.0007992024,0.0001513341,0.0002545156,0.00005661203],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004250039,"about_ca_system_score_gemma":0.00002840716,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000140593,"about_ca_topic_score_gemma":0.000002553724,"domain_scores_codex":[0.9980052,0.0001539113,0.000685522,0.0003206846,0.0006672787,0.0001673642],"domain_scores_gemma":[0.9983554,0.0001544795,0.0004835896,0.0001675765,0.0006474913,0.0001914094],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0005052387,0.001291863,0.002543117,0.00004777978,0.00434081,0.000207075,0.003531263,0.000001652355,0.006637692,0.007426254,0.0006401884,0.9728271],"study_design_scores_gemma":[0.001945627,0.0008834123,0.01032626,0.0007325073,0.0009675898,0.0006619008,0.0003554267,0.001427643,0.1692885,0.8122157,0.0004858614,0.0007095958],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.634381,0.0001234062,0.3581386,0.0007649934,0.0003582237,0.0002156329,0.0000561357,0.0001140133,0.00584805],"genre_scores_gemma":[0.9480997,0.001330654,0.04992367,0.000321139,0.00011802,0.00001102489,0.00004414204,0.00001075758,0.0001409165],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9721175,"threshold_uncertainty_score":0.9994555,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Perspective (graphical); Signature (topology); Artificial intelligence; Natural language processing","retraction":null,"screen_n_in":null,"score":{"opus":0.05095119436942392,"gpt":0.3541816603901525,"spread":0.3032304660207286,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003201868,0.0006515728,0.003950426,0.004359682,0.0001130894,0.0001423161,0.005359216,0.001005625,0.00002862885],"category_scores_gemma":[0.00126466,0.0005771667,0.001414242,0.01098775,0.0001575005,0.0001813385,0.002528931,0.001121465,0.0000942404],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002836912,"about_ca_system_score_gemma":0.0004239129,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001125447,"about_ca_topic_score_gemma":0.00002252784,"domain_scores_codex":[0.9946559,0.001790381,0.001123816,0.001372063,0.0005000122,0.0005578079],"domain_scores_gemma":[0.9925381,0.002003713,0.001298735,0.003159568,0.0009123153,0.00008757768],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[3.028506e-7,0.00006415743,0.00004441062,0.00133919,0.00231576,0.00001540321,0.0001328121,0.00000610233,8.516481e-7,0.002881957,0.0002708251,0.9929282],"study_design_scores_gemma":[0.001294914,0.001299681,0.00101752,0.04244998,0.03090418,0.0003391862,0.000334313,0.01881065,0.000279341,0.02613374,0.869158,0.0079785],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000003796577,0.6868256,0.311128,0.00006686193,0.0002147619,0.0005504836,0.00005015983,0.0006752762,0.0004850956],"genre_scores_gemma":[0.000678742,0.9466631,0.05207967,0.0000455665,0.0000796822,0.00003208546,0.0001335616,0.00006635697,0.000221186],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9849497,"threshold_uncertainty_score":0.999668,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.028366212247756,"gpt":0.2974230507446503,"spread":0.2690568384968943,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001102541,0.0001004775,0.0001775529,0.000260088,0.00004594452,0.0002931209,0.001343465,0.0000574006,0.0001091609],"category_scores_gemma":[0.000801734,0.00007541805,0.00008435958,0.0002146374,0.00009345719,0.006805247,0.0005151798,0.0002188557,0.00007922298],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006435479,"about_ca_system_score_gemma":0.0001075748,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004473377,"about_ca_topic_score_gemma":7.985251e-7,"domain_scores_codex":[0.9981337,0.00006550825,0.0007792226,0.00005953077,0.0008172241,0.0001448528],"domain_scores_gemma":[0.9974514,0.0001865498,0.0007498234,0.0001433907,0.001337098,0.0001317224],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001743909,0.0001582435,0.001857248,0.00001918818,0.0001306688,0.000004077449,0.003866477,0.000005061873,0.001004745,0.001142708,0.009822547,0.9818146],"study_design_scores_gemma":[0.006149016,0.0006989501,0.05439053,0.000811897,0.00007699087,0.002291268,0.0004410657,0.01135248,0.7034184,0.01460956,0.2049616,0.0007981792],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3875933,0.0004321618,0.578747,0.01261865,0.009718899,0.001191418,0.0001068287,0.0001319032,0.009459846],"genre_scores_gemma":[0.7537103,0.0002257624,0.244258,0.001240575,0.0004066604,0.000006140411,0.00001960866,0.000008614651,0.0001243683],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9810165,"threshold_uncertainty_score":0.493364,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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)","retraction":null,"screen_n_in":null,"score":{"opus":0.04277814179642096,"gpt":0.2567714621377233,"spread":0.2139933203413024,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007654604,0.0004503826,0.0005987066,0.0004094111,0.0003872565,0.0007072665,0.0008110809,0.0002936775,0.0002511585],"category_scores_gemma":[0.0001025111,0.0004266785,0.0001500705,0.0009545526,0.0001004833,0.001467753,0.0002374412,0.0003588577,0.0002570142],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001430696,"about_ca_system_score_gemma":0.0001444089,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001345307,"about_ca_topic_score_gemma":0.0007158059,"domain_scores_codex":[0.9961668,0.0001191849,0.0008455776,0.001148569,0.0007886131,0.0009312984],"domain_scores_gemma":[0.997259,0.0003210751,0.000349405,0.0007880401,0.001072106,0.0002103438],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001694271,0.0014706,0.000200466,0.0002938683,0.0002448407,0.00002147654,0.0003387152,0.000004267082,0.04630397,0.001247627,0.0104402,0.9392645],"study_design_scores_gemma":[0.005406099,0.001571876,0.001346761,0.001978869,0.0001881747,0.00003801335,0.0001360303,0.01095774,0.9414559,0.02377777,0.01067123,0.002471521],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06059623,0.00004629495,0.9009652,0.00773178,0.00007814387,0.00154252,0.0000814837,0.001761386,0.027197],"genre_scores_gemma":[0.2920867,0.000105257,0.6910732,0.01356869,0.0005833414,0.0006115611,0.0003805702,0.00009031793,0.001500372],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.936793,"threshold_uncertainty_score":0.9998185,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"École de Technologie Supérieure","funders":"Conselho Nacional de Desenvolvimento Científico e Tecnológico","keywords":"Computer science; 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","retraction":null,"screen_n_in":null,"score":{"opus":0.03730559397107888,"gpt":0.2786587819514879,"spread":0.241353187980409,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003931316,0.0001907005,0.0002599932,0.000272905,0.00006141246,0.00008727539,0.0003764071,0.0001981481,0.00004929061],"category_scores_gemma":[0.00006838417,0.0002015045,0.00009161887,0.0004760388,0.00003593278,0.00107953,0.00004685964,0.0002897783,0.00003912266],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009126162,"about_ca_system_score_gemma":0.00004339493,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005593634,"about_ca_topic_score_gemma":0.00003188074,"domain_scores_codex":[0.9982193,0.0001318865,0.0005533696,0.0004767472,0.0003324746,0.0002862379],"domain_scores_gemma":[0.9989715,0.00007254947,0.0002851387,0.0004056111,0.0002134631,0.00005175616],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001653219,0.0001606572,0.0001985099,0.00003407561,0.000006622774,0.00001079023,0.000915773,0.000004309752,0.04112053,0.0001426668,0.0001965291,0.957193],"study_design_scores_gemma":[0.0008884023,0.0005258903,0.01064189,0.0006611007,0.00001752431,0.00004532801,0.0002176918,0.007301676,0.9262336,0.05257632,0.0003843052,0.0005062115],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.277327,0.0001675246,0.7178763,0.001105753,0.0002111594,0.0004378049,0.00002313496,0.0002775735,0.002573831],"genre_scores_gemma":[0.9723051,0.0002280932,0.0265955,0.0005994434,0.0000693812,0.00004678812,0.0001135597,0.00001236338,0.00002974885],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9566868,"threshold_uncertainty_score":0.8217114,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2098345386","doi":"10.1007/s10032-006-0020-2","title":"A survey of document image classification: problem statement, classifier architecture and performance evaluation","year":2006,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":174,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"Xerox Foundation","keywords":"Computer science; Classifier (UML); Document classification; Contextual image classification; Artificial intelligence; Pattern recognition (psychology); Problem statement; Ambiguity; Information retrieval; Machine learning; Data mining; Image (mathematics)","retraction":null,"screen_n_in":null,"score":{"opus":0.02727027337698614,"gpt":0.3066844968063903,"spread":0.2794142234294041,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002610092,0.0002138797,0.0002987199,0.001076402,0.0001648205,0.0007244788,0.0003797886,0.00007766073,0.0003577771],"category_scores_gemma":[0.00005773034,0.0001759364,0.000141063,0.0006210809,0.00009395547,0.0009583492,0.000106911,0.0002526276,0.00001362313],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001690418,"about_ca_system_score_gemma":0.00008876112,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001638734,"about_ca_topic_score_gemma":0.0001310962,"domain_scores_codex":[0.9967981,0.00041323,0.0009287193,0.0004224125,0.001241011,0.0001965485],"domain_scores_gemma":[0.9970593,0.0001447507,0.0008287504,0.0001952438,0.00166441,0.000107586],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001452085,0.0003145308,0.03312308,0.00002414911,0.001262804,0.00001128509,0.00022661,0.000110431,0.001262075,0.001153215,0.0009167804,0.9614499],"study_design_scores_gemma":[0.00273554,0.0007365838,0.8932781,0.0003155858,0.0006942907,0.0001237344,0.00007572821,0.02849116,0.01416995,0.05713075,0.001566541,0.000682054],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7562963,0.0002298146,0.2370886,0.0025974,0.0002655585,0.0005007182,0.00006072151,0.00007015313,0.002890733],"genre_scores_gemma":[0.9795442,0.0009252122,0.01871325,0.000162928,0.0001051626,0.00005317228,0.0002841387,0.000009714541,0.0002022721],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9607678,"threshold_uncertainty_score":0.7174479,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02365538275580699,"gpt":0.2715072332501407,"spread":0.2478518504943337,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004127086,0.0001769034,0.0001446071,0.0002424559,0.0002633313,0.0002918327,0.0003132454,0.000110455,0.0001624135],"category_scores_gemma":[0.00005879768,0.0001809567,0.00009196813,0.0003761027,0.00006559817,0.001009412,0.00008453325,0.000105572,0.0002963991],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009722811,"about_ca_system_score_gemma":0.00005291549,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002310927,"about_ca_topic_score_gemma":0.000005610829,"domain_scores_codex":[0.998485,0.00008997926,0.0002991008,0.0005400387,0.0002768063,0.0003090871],"domain_scores_gemma":[0.998815,0.00005047719,0.0001469884,0.0002498221,0.0006568894,0.00008083099],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001947131,0.0002369034,0.0002130154,0.00008114857,0.00003709258,0.000001450322,0.0005817272,7.246594e-7,0.009563821,0.0002825871,0.003830184,0.9851519],"study_design_scores_gemma":[0.002719809,0.001896715,0.002735766,0.000236588,0.00008690689,0.0002260649,0.00009025611,0.432538,0.4026528,0.1489928,0.006281085,0.001543162],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003505804,0.000008511513,0.9915762,0.0003764554,0.0002683478,0.0007276947,0.00002863119,0.0007223984,0.002785933],"genre_scores_gemma":[0.49164,0.00001121637,0.5054246,0.0009996975,0.0005372101,0.0008530321,0.000380683,0.00002716248,0.0001263492],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9836087,"threshold_uncertainty_score":0.7379201,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02886706353236065,"gpt":0.2801902910180454,"spread":0.2513232274856847,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008861933,0.0001415904,0.0002472228,0.0002996908,0.000283627,0.0002184938,0.0002708131,0.00006285479,0.0001687794],"category_scores_gemma":[0.0000444324,0.000141513,0.0001236026,0.001641997,0.00003197829,0.0002034886,0.00008314208,0.00011924,0.00009977875],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001475409,"about_ca_system_score_gemma":0.00002102945,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008495145,"about_ca_topic_score_gemma":0.0004634061,"domain_scores_codex":[0.9985718,0.0001979766,0.0003290962,0.000488173,0.0001738015,0.0002391613],"domain_scores_gemma":[0.9989027,0.0001504464,0.0001274617,0.0004910392,0.0002053276,0.0001229591],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.000001010746,0.0002995559,0.07998347,0.00002069062,0.0003678484,0.000004095826,0.0001440997,0.000002155652,0.0002421356,0.003197909,0.0003027577,0.9154343],"study_design_scores_gemma":[0.004461076,0.0004003713,0.5022442,0.0002289974,0.003329195,0.0002295593,0.0008154893,0.1253541,0.09851772,0.07393754,0.1851194,0.005362283],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008993214,0.0002964354,0.9886625,0.0001925455,0.000009720437,0.000220959,0.0001007471,0.0001962279,0.001327686],"genre_scores_gemma":[0.9871905,0.0002975621,0.01100031,0.0007206158,0.00004043575,0.0003380431,0.0002766949,0.000009940047,0.0001259019],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9781973,"threshold_uncertainty_score":0.5770732,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Artificial intelligence; Natural language processing; Speech recognition","retraction":null,"screen_n_in":null,"score":{"opus":0.02725931608844788,"gpt":0.2944965036999926,"spread":0.2672371876115447,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006114382,0.0005248829,0.0005287865,0.000396817,0.00026389,0.001167912,0.002015143,0.0004385687,0.0001364433],"category_scores_gemma":[0.00008826592,0.0004592803,0.0002534403,0.0003354933,0.00009796066,0.0006618391,0.00329013,0.0006718009,0.0001456795],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001428438,"about_ca_system_score_gemma":0.0002302629,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002008276,"about_ca_topic_score_gemma":0.00002172987,"domain_scores_codex":[0.9971007,0.0001594367,0.0006132688,0.001148563,0.000466425,0.0005116725],"domain_scores_gemma":[0.997555,0.00005829798,0.000383815,0.001453318,0.000352894,0.0001966501],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004827247,0.001173266,0.01516206,0.001715952,0.001291841,0.0006625461,0.009686142,0.0008906046,0.2716711,0.01032283,0.02155691,0.6658185],"study_design_scores_gemma":[0.0004376868,0.0001107401,0.002222188,0.0006508102,0.00004445937,0.0001742554,0.00001942304,0.9100186,0.05414525,0.02942953,0.0006606797,0.002086427],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2996622,0.00005126773,0.6943488,0.0003687267,0.001005446,0.0003957755,0.000008979735,0.001527629,0.002631132],"genre_scores_gemma":[0.379843,0.00002862326,0.6169866,0.001403752,0.001187527,0.00006657869,0.00004249102,0.00005183716,0.0003895779],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.909128,"threshold_uncertainty_score":0.999869,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01943581435024508,"gpt":0.2674221363277768,"spread":0.2479863219775318,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001120771,0.0001373835,0.0001351375,0.0001171401,0.0001100938,0.0002279097,0.0004371907,0.000072544,0.000814819],"category_scores_gemma":[0.00001402428,0.0001273125,0.00007539511,0.000210245,0.00005142602,0.0005550194,0.00007060699,0.0001061723,0.0005759902],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004278621,"about_ca_system_score_gemma":0.00002791974,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001620331,"about_ca_topic_score_gemma":0.0001301553,"domain_scores_codex":[0.9988875,0.00006140611,0.0002372442,0.0003771173,0.0002248787,0.0002118678],"domain_scores_gemma":[0.9991814,0.0001582927,0.00007885679,0.0004190677,0.0001049527,0.00005741],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000009218061,0.0005200347,0.002256372,0.00001053961,0.00001116125,0.00003558765,0.00003265955,0.00003163465,0.327575,0.005203643,0.1801788,0.4841354],"study_design_scores_gemma":[0.0005738075,0.00005222134,0.06453684,0.00002016797,0.000006303052,0.000007702738,0.000008397991,0.0527694,0.841163,0.01547656,0.02503093,0.0003547011],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006065535,0.00003028325,0.9615855,0.00102593,0.0001167973,0.0001634591,0.00001550115,0.001385968,0.02961099],"genre_scores_gemma":[0.5834856,0.000001678024,0.4149876,0.0004186771,0.00009642352,0.0000249325,0.00004229137,0.00000815365,0.0009346901],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5774201,"threshold_uncertainty_score":0.8921697,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03557646882454432,"gpt":0.3029209010096701,"spread":0.2673444321851258,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004351936,0.0002216233,0.0002518725,0.00008791441,0.0002761155,0.0001667939,0.0004635698,0.00009146422,0.0002574139],"category_scores_gemma":[0.00008512812,0.0001962105,0.0001729704,0.0003354869,0.00004654059,0.0001802466,0.00038406,0.0001728837,0.00006059881],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001327964,"about_ca_system_score_gemma":0.000623857,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000127446,"about_ca_topic_score_gemma":0.00003949834,"domain_scores_codex":[0.9978185,0.0001796366,0.000447704,0.0006128317,0.0005244853,0.0004168304],"domain_scores_gemma":[0.9986893,0.0002035527,0.0001280221,0.0003341954,0.0005113857,0.0001335251],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001134149,0.0009858585,0.0001233935,0.000101406,0.0003185401,0.00009589243,0.002580433,0.04133663,0.0008991679,0.2187529,0.2171128,0.5175795],"study_design_scores_gemma":[0.002778762,0.0008913065,0.001160769,0.0003217543,0.00005627151,0.0001130377,0.0002953961,0.4925771,0.1613182,0.2029729,0.1361269,0.001387495],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001448347,0.00009318927,0.9901174,0.003804797,0.001292159,0.0006592413,0.00002152117,0.000664227,0.001899059],"genre_scores_gemma":[0.09502529,0.00001987232,0.8970801,0.004593993,0.000672362,0.000371321,0.0001060836,0.00003055336,0.00210048],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.516192,"threshold_uncertainty_score":0.8001232,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04405373487622228,"gpt":0.3069373633876797,"spread":0.2628836285114575,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001835874,0.0001980222,0.0004801635,0.0006698807,0.0001974317,0.0000392075,0.0004253429,0.00004602251,0.00009313829],"category_scores_gemma":[0.000002017763,0.0001729039,0.0001848423,0.001362653,0.00009782911,0.0002261932,0.000007379513,0.0002208969,0.00001475933],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002074851,"about_ca_system_score_gemma":0.00002013489,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001542432,"about_ca_topic_score_gemma":0.001136942,"domain_scores_codex":[0.9983812,0.0001484183,0.0004643787,0.0004765952,0.0003587677,0.000170638],"domain_scores_gemma":[0.9989913,0.0001195634,0.0001472112,0.0004839856,0.0001593959,0.00009851473],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002068558,0.002704754,0.0004917104,0.00001270644,0.00115176,0.00009695245,0.00856136,0.002885278,0.0004828078,0.00002499931,0.00001570004,0.9835513],"study_design_scores_gemma":[0.0004758945,0.00283074,0.003056215,0.00004586303,0.00075284,0.0002038074,0.001630898,0.2943914,0.6954941,0.0003780027,0.00005823879,0.000682103],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1212401,0.00003376888,0.878172,0.00003870753,0.00005318818,0.0002116078,0.00002187296,0.0001088151,0.0001198987],"genre_scores_gemma":[0.9922225,0.0002046185,0.007368196,0.00005390497,0.000007254803,0.00003302004,0.000001838531,0.000006356524,0.0001022973],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9828692,"threshold_uncertainty_score":0.7050815,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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)","retraction":null,"screen_n_in":null,"score":{"opus":0.03535804179603201,"gpt":0.2296545057060582,"spread":0.1942964639100263,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003693378,0.0002478054,0.0002626,0.0002501562,0.0002232578,0.00009173596,0.0003911328,0.0001294136,0.0003148465],"category_scores_gemma":[0.00009349459,0.0002011953,0.0001201547,0.0003382883,0.0001003502,0.0006138514,0.0001132585,0.0002758543,0.0002537754],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003710892,"about_ca_system_score_gemma":0.00005360521,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001623431,"about_ca_topic_score_gemma":0.00001416339,"domain_scores_codex":[0.9981962,0.0002057178,0.0004198004,0.0004812251,0.0003910232,0.0003059865],"domain_scores_gemma":[0.9987096,0.0002993871,0.000269388,0.0003828203,0.0001998092,0.0001390572],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002170423,0.00008092374,0.001102007,0.00002490052,0.00003038744,0.00001828218,0.0007532188,4.361863e-8,0.001984405,0.00004660468,0.002712076,0.9932255],"study_design_scores_gemma":[0.005068633,0.002793237,0.179981,0.00243846,0.0001746976,0.001648985,0.0003465006,0.002708778,0.7088968,0.08992755,0.003292015,0.002723345],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8163055,0.00006751497,0.1764924,0.00300533,0.0002818899,0.0007067275,0.00007448042,0.0003347515,0.002731372],"genre_scores_gemma":[0.988768,0.0003540909,0.008031983,0.002296509,0.0001819641,0.000101429,0.000140145,0.00002448739,0.0001013314],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9905021,"threshold_uncertainty_score":0.8204508,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01471688984861719,"gpt":0.2596056761146642,"spread":0.244888786266047,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001510231,0.0006307516,0.0009142048,0.001940384,0.0003830936,0.00147832,0.002923448,0.0003814556,0.0001368249],"category_scores_gemma":[0.0002615103,0.0006277391,0.0005568049,0.001946705,0.0004104681,0.0007330102,0.001004126,0.0008670398,0.00002595358],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004225165,"about_ca_system_score_gemma":0.0006102682,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002436213,"about_ca_topic_score_gemma":0.0001481594,"domain_scores_codex":[0.9952019,0.00009837569,0.00073349,0.00210199,0.001057972,0.0008062756],"domain_scores_gemma":[0.996054,0.0009777276,0.0004360068,0.001498382,0.0008107848,0.0002230939],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001346952,0.00005917499,0.00006019714,0.0001050224,0.000172829,0.0001714749,0.0004491071,0.03678847,0.000420873,0.0124018,0.0000249033,0.9493327],"study_design_scores_gemma":[0.000475787,0.0002919855,0.00005608227,0.0003075694,0.0001618205,0.00002069615,5.423796e-7,0.9143375,0.01386668,0.06526912,0.004122955,0.001089273],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00003157362,0.0002687473,0.9955791,0.0008361756,0.0004458376,0.0006642013,0.000008845686,0.0004772286,0.00168825],"genre_scores_gemma":[0.03996862,0.00004218427,0.9570712,0.001676924,0.0002333529,0.00008731497,0.00007309002,0.00004684932,0.0008004188],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9482434,"threshold_uncertainty_score":0.9996174,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.07374208121636969,"gpt":0.1862878112567369,"spread":0.1125457300403672,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003112154,0.0005727515,0.0005207307,0.0007715204,0.0001970989,0.0004033351,0.002219503,0.000309465,0.0004062249],"category_scores_gemma":[0.00002499843,0.000613184,0.0002238964,0.0007308719,0.0001473849,0.001402196,0.002020726,0.0008417496,0.00128597],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000327007,"about_ca_system_score_gemma":0.0002822361,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000421321,"about_ca_topic_score_gemma":0.00005965406,"domain_scores_codex":[0.9967486,0.0002066461,0.0003264408,0.001860216,0.0002446301,0.0006134916],"domain_scores_gemma":[0.9968281,0.0001147814,0.000343209,0.001659656,0.0006181659,0.0004360887],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004751681,0.001744982,0.001043499,0.0009778779,0.001376645,0.005102144,0.002449437,0.1062821,0.0008586782,0.3262186,0.02772185,0.525749],"study_design_scores_gemma":[0.0009647273,0.0004321674,0.0002207696,0.0006888243,0.0001814119,0.0001075596,0.00009045973,0.4282388,0.01049314,0.5545027,0.001918982,0.002160481],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1375464,0.00001832882,0.8465027,0.0002637939,0.0002255498,0.0009453113,0.00008266193,0.001144312,0.01327084],"genre_scores_gemma":[0.9551993,0.0001333971,0.04170421,0.0004849685,0.00008398062,0.00002422894,0.00009962838,0.00005117616,0.00221911],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8176529,"threshold_uncertainty_score":0.9996319,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2150428256","doi":"10.1007/s10032-011-0180-6","title":"Multi-feature extraction and selection in writer-independent off-line signature verification","year":2011,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":98,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Computer science; Pattern recognition (psychology); Feature selection; Feature extraction; Artificial intelligence; Signature (topology); Data mining; Feature (linguistics); Boosting (machine learning); Feature vector; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.02541672727111226,"gpt":0.2942723971238677,"spread":0.2688556698527554,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007547585,0.0002121949,0.000243762,0.001608479,0.0001415997,0.0005397794,0.0003196892,0.0001909035,0.0003053468],"category_scores_gemma":[0.0000564632,0.00018734,0.0001549807,0.000633006,0.0000346758,0.001343739,0.00006782774,0.0005917721,0.00002117329],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001764871,"about_ca_system_score_gemma":0.00003185084,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005975685,"about_ca_topic_score_gemma":0.0001516326,"domain_scores_codex":[0.998065,0.0001854421,0.0005074029,0.0004710873,0.0005808507,0.0001901976],"domain_scores_gemma":[0.9987674,0.00005863259,0.0004167268,0.0001030705,0.0005144267,0.0001397875],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0002722325,0.0008329403,0.01102168,0.00001215577,0.001160114,0.000147644,0.001186774,0.00003396205,0.01236586,0.0007558391,0.0003263041,0.9718845],"study_design_scores_gemma":[0.007325678,0.001585023,0.738387,0.0007271666,0.001059544,0.001906107,0.0006138367,0.08070202,0.1203266,0.0398138,0.00562202,0.001931143],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4860411,0.0004636849,0.5096648,0.002006303,0.0005843989,0.000366829,0.00002190044,0.0001710737,0.0006798239],"genre_scores_gemma":[0.9506407,0.00249472,0.04586954,0.0004255404,0.0001722556,0.00002807442,0.00005203605,0.00001121615,0.0003058584],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9699534,"threshold_uncertainty_score":0.7639504,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"École de Technologie Supérieure","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"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","retraction":null,"screen_n_in":null,"score":{"opus":0.05284061859672254,"gpt":0.2807842239529998,"spread":0.2279436053562773,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002862131,0.000171949,0.0001933169,0.000246999,0.00009807727,0.00003444899,0.0002634992,0.0001418879,0.0001067202],"category_scores_gemma":[0.00006616836,0.0001722781,0.0001012159,0.000271815,0.00004272137,0.0005882208,0.00003941077,0.0001273103,0.00002871632],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005971225,"about_ca_system_score_gemma":0.00003639778,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002787391,"about_ca_topic_score_gemma":0.00005557576,"domain_scores_codex":[0.9987472,0.0001229274,0.0003530464,0.0004074002,0.0001743642,0.0001950452],"domain_scores_gemma":[0.9986956,0.00008400356,0.0003058319,0.0002012085,0.0006651686,0.00004816237],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002541511,0.0001691141,0.0000763139,0.00006599418,0.00002692169,7.421353e-7,0.0009649087,5.980323e-7,0.05392648,0.0001716451,0.0001973255,0.9443746],"study_design_scores_gemma":[0.0004410927,0.0007083928,0.002583775,0.0001104849,0.00003724735,0.00001333701,0.00008716823,0.03732976,0.9366,0.02172983,0.00008650011,0.0002724206],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06058731,0.00006635343,0.9375572,0.0001050483,0.00015772,0.0006353591,0.00008355814,0.0002444515,0.0005630087],"genre_scores_gemma":[0.8173258,0.00009376353,0.1818087,0.0001275059,0.00003847295,0.0003019077,0.000239092,0.00001786411,0.00004679362],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9441021,"threshold_uncertainty_score":0.7025298,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","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","retraction":null,"screen_n_in":null,"score":{"opus":0.03118144229899085,"gpt":0.2355363793179783,"spread":0.2043549370189875,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008928858,0.0004566033,0.000387697,0.00059193,0.0003094389,0.0003568937,0.000515948,0.000276997,0.00004582675],"category_scores_gemma":[0.00003661053,0.0004056196,0.0001135329,0.0006532858,0.00007419697,0.001295411,0.000107315,0.0004795279,0.001235692],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003080948,"about_ca_system_score_gemma":0.00006392319,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001502927,"about_ca_topic_score_gemma":0.0001343834,"domain_scores_codex":[0.9967919,0.00009111881,0.0006387745,0.0009387441,0.0007627274,0.0007767424],"domain_scores_gemma":[0.9980639,0.0002373642,0.0003713385,0.0005908761,0.0004729454,0.0002636089],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001182816,0.0002565061,0.0004217691,0.0001738395,0.00004535095,0.0000848579,0.0002055717,0.000002138477,0.004797028,0.0000631222,0.0002201037,0.9936115],"study_design_scores_gemma":[0.005333094,0.003209548,0.02908603,0.005125813,0.000126767,0.002496494,0.0004294879,0.01037858,0.939281,0.001118051,0.0009234186,0.002491682],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3814839,0.000008340953,0.6102285,0.000147333,0.0002532277,0.000541031,0.00005292684,0.0009589997,0.006325759],"genre_scores_gemma":[0.9737805,0.00002750665,0.02422377,0.0009852804,0.0003183187,0.0002384467,0.0002486762,0.0000629112,0.0001145462],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9911197,"threshold_uncertainty_score":0.9998395,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Montréal; École de Technologie Supérieure; Concordia University","funders":"","keywords":"Thresholding; Artificial intelligence; Computer science; Pattern recognition (psychology); Segmentation; Character (mathematics); Font; Image segmentation; Handwriting; Computer vision; Image (mathematics); Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.02495847943340175,"gpt":0.2910954083966361,"spread":0.2661369289632344,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002538692,0.000333935,0.0002555452,0.0004080838,0.000487686,0.0008841755,0.0005576271,0.0001428027,0.0001743613],"category_scores_gemma":[0.000008325796,0.00033577,0.0001705573,0.0004488713,0.00009030336,0.00340053,0.000004140099,0.0004961027,0.0001331534],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001759735,"about_ca_system_score_gemma":0.0001771188,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007566261,"about_ca_topic_score_gemma":0.00002032127,"domain_scores_codex":[0.9978102,0.0000821381,0.0004410874,0.0007196229,0.000512637,0.0004342825],"domain_scores_gemma":[0.9986973,0.00009853447,0.0002018895,0.0005248751,0.0003156852,0.0001616759],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00004547954,0.0003454428,0.00001124374,0.00002103145,0.00001920333,0.00003383772,0.0001854251,0.0005623561,0.1626528,0.000009599571,0.0001326678,0.8359809],"study_design_scores_gemma":[0.0006395389,0.00007973758,0.0002711349,0.0001664557,0.00004011256,0.00003007631,0.0000257189,0.1713753,0.8250263,0.001566743,0.0003312615,0.0004476665],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007395022,0.00005319048,0.9891887,0.0008915081,0.0002900822,0.0002856181,0.00006518448,0.001128052,0.0007027012],"genre_scores_gemma":[0.6723907,0.00004102522,0.3261687,0.0006235241,0.00005911021,0.000143593,0.000007976289,0.00003004533,0.0005353593],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8355333,"threshold_uncertainty_score":0.9999095,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"","keywords":"Computer science; Signature (topology); Natural language processing; Artificial intelligence; Information retrieval","retraction":null,"screen_n_in":null,"score":{"opus":0.01462210256935671,"gpt":0.2342790208130376,"spread":0.2196569182436808,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007417982,0.000318269,0.0003338118,0.002343778,0.0001667971,0.0009516969,0.001825722,0.0002582829,0.0001377103],"category_scores_gemma":[0.0001754388,0.0003009886,0.0001490866,0.00389924,0.00005097039,0.001297208,0.0003653869,0.000394909,0.001655484],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002894121,"about_ca_system_score_gemma":0.00006472089,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000962034,"about_ca_topic_score_gemma":0.000001312672,"domain_scores_codex":[0.9968607,0.0001473282,0.0006293778,0.0008066067,0.001031721,0.0005242017],"domain_scores_gemma":[0.9973006,0.0001545595,0.0003095749,0.001264162,0.0007026969,0.0002684358],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001062717,0.0005819153,0.0006502666,0.0003511186,0.0001018539,0.0001528002,0.0002506693,0.000005902084,0.05389382,0.01088832,0.04605293,0.8870598],"study_design_scores_gemma":[0.003204283,0.001213323,0.0145348,0.0005191192,0.0001070128,0.001164231,0.0003155301,0.1146694,0.8029057,0.008534152,0.04950387,0.003328613],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02546499,0.0006945108,0.9659858,0.0007161353,0.001017826,0.0009774527,0.0000747908,0.001825368,0.003243081],"genre_scores_gemma":[0.9437423,0.00008833512,0.05453672,0.0003987935,0.0001924183,0.0001607782,0.00007990371,0.0000323909,0.000768402],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9182773,"threshold_uncertainty_score":0.9999442,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; National Institute of Standards and Technology; Ministerio de Economía y Competitividad","keywords":"Algorithm; Signature (topology); Computer science; Line (geometry); Artificial intelligence; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.2096118314133996,"gpt":0.3119696942014851,"spread":0.1023578627880855,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006599014,0.0001884242,0.0002050921,0.0001985505,0.0001137022,0.00007437892,0.0002534842,0.0001712988,0.0003727637],"category_scores_gemma":[0.0001186205,0.0001752615,0.00005663413,0.0001599584,0.00005723493,0.0003359036,0.00009269614,0.000234949,0.0002791951],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002131292,"about_ca_system_score_gemma":0.00001596403,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003575241,"about_ca_topic_score_gemma":0.00001610142,"domain_scores_codex":[0.9983397,0.0004077191,0.0002781718,0.0005532067,0.0001777516,0.0002434895],"domain_scores_gemma":[0.9990953,0.0001934761,0.0001254324,0.0003294771,0.0001531102,0.0001032581],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000004071546,0.00007872325,0.00005175219,0.00001141833,0.0000153466,0.00001892929,0.0003313685,2.190817e-7,0.001117564,0.0001679272,0.0006073723,0.9975953],"study_design_scores_gemma":[0.001086381,0.001661659,0.001246511,0.0002910178,0.00007876677,0.0004402368,0.00007270533,0.0377879,0.8666676,0.0873699,0.002102081,0.001195285],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01679318,0.00009132293,0.9797522,0.0004275572,0.0004630429,0.0002770068,0.00002968731,0.0004070429,0.001758902],"genre_scores_gemma":[0.5905284,0.000312604,0.4040608,0.004044759,0.0005089009,0.0002700914,0.0001238008,0.00003579256,0.0001148167],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9964,"threshold_uncertainty_score":0.7146958,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Hidden Markov model; Markov chain; Artificial intelligence; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.03608557462599119,"gpt":0.2853434635284394,"spread":0.2492578889024482,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000435357,0.0003980906,0.0004175931,0.0004573673,0.0001481164,0.0003346023,0.0007616644,0.0003615262,0.0007105509],"category_scores_gemma":[0.00003464284,0.0004080335,0.0001054417,0.0002564983,0.0002748934,0.0009829006,0.0004155824,0.0006411669,0.0002125427],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001602949,"about_ca_system_score_gemma":0.0001191498,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007441139,"about_ca_topic_score_gemma":0.000343181,"domain_scores_codex":[0.9977626,0.0001083319,0.0006785755,0.0007654975,0.0003370392,0.000347985],"domain_scores_gemma":[0.9989944,0.0000634578,0.0001636887,0.0005379066,0.0001189072,0.0001216768],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001927539,0.00004146024,0.000006038747,0.00003836121,0.000006458475,0.0000352349,0.001025039,0.000008937173,0.0001369358,0.1147495,0.001469379,0.8824634],"study_design_scores_gemma":[0.00002308579,0.0001498796,0.00004751852,0.0002277672,0.000008927856,0.0001050634,0.0001962675,0.04139499,0.000292351,0.9452041,0.01172757,0.0006224032],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.0001380896,0.0002477422,0.7627964,0.001168897,0.0003459714,0.0004454215,0.00002864776,0.0004867311,0.2343421],"genre_scores_gemma":[0.05419768,0.01753063,0.2137929,0.002195107,0.001097753,0.0002829897,0.0003642919,0.000190486,0.7103482],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.881841,"threshold_uncertainty_score":0.9998372,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04366332411408295,"gpt":0.3050093866377097,"spread":0.2613460625236267,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003698116,0.0002326706,0.0002236219,0.0004614234,0.0001030596,0.0002154383,0.0003732106,0.0001323735,0.00007344654],"category_scores_gemma":[0.00002734528,0.0002521663,0.00007996488,0.0004581769,0.00002511228,0.001593875,0.00007887456,0.0002163026,0.0001526308],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001809487,"about_ca_system_score_gemma":0.00004212684,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000814361,"about_ca_topic_score_gemma":0.00005281386,"domain_scores_codex":[0.9981236,0.0001066302,0.0005020637,0.0005241887,0.0003564118,0.0003871333],"domain_scores_gemma":[0.9992349,0.0000356456,0.0001851723,0.0003027929,0.0001429044,0.00009859069],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000009345852,0.0001855975,0.0004154877,0.0000163026,0.000006555231,0.00001701856,0.0004087379,0.0001524795,0.0157463,0.00001672345,0.0001287322,0.9828967],"study_design_scores_gemma":[0.001523584,0.0002568122,0.002035141,0.0003724273,0.0000203404,0.00005264036,0.0000647593,0.8237476,0.1154984,0.05580203,0.00002499983,0.0006012741],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2640366,0.00002452639,0.7340443,0.0003052469,0.00009016591,0.000383129,0.0000153349,0.0002808039,0.0008198839],"genre_scores_gemma":[0.8904195,0.00006694702,0.1073007,0.001879633,0.00008173494,0.00005653138,0.000131141,0.00001649502,0.0000473121],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9822955,"threshold_uncertainty_score":0.9999931,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01654186517863969,"gpt":0.2724687514698033,"spread":0.2559268862911636,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002670249,0.0002365433,0.0003907329,0.0002151721,0.0001619854,0.0001541155,0.000716513,0.0001647556,0.0003393245],"category_scores_gemma":[0.0004751172,0.000206779,0.0001350638,0.0004211634,0.0001559773,0.0004476265,0.0003433925,0.0003030541,0.0001043733],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000388706,"about_ca_system_score_gemma":0.00004349073,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001809989,"about_ca_topic_score_gemma":0.0001276027,"domain_scores_codex":[0.9979422,0.0002895279,0.0003860757,0.0005835103,0.0004922223,0.0003064529],"domain_scores_gemma":[0.9981374,0.0004723534,0.0003145601,0.0006351675,0.0003262487,0.0001142401],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003753071,0.0006011886,0.01384515,0.00007485453,0.0002882471,0.00004597094,0.01004858,0.000059515,0.7019461,0.007266467,0.0217442,0.2437044],"study_design_scores_gemma":[0.001205386,0.0004524068,0.02190758,0.0001895943,0.00003332879,0.000004321897,0.0002002119,0.01485889,0.9483064,0.008949344,0.003470899,0.0004216305],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.531148,0.000274036,0.4616606,0.002262151,0.0004595074,0.000457889,0.00001248561,0.0009153906,0.002809978],"genre_scores_gemma":[0.9682613,0.0000636372,0.02977237,0.0002031418,0.0002880465,0.00003324162,0.00003356415,0.00002288804,0.001321836],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4371133,"threshold_uncertainty_score":0.8432202,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Huawei Technologies (Canada)","funders":"","keywords":"Computer science; Transformer; Sigma; Artificial intelligence; Computer vision; Electrical engineering; Physics; Quantum mechanics; Voltage","retraction":null,"screen_n_in":null,"score":{"opus":0.03174797090960109,"gpt":0.2780515632484664,"spread":0.2463035923388653,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001061538,0.0005739561,0.0006758947,0.00171066,0.0002231113,0.000577838,0.002152232,0.0003363476,0.0000314288],"category_scores_gemma":[0.0001010549,0.0005299618,0.0002561065,0.0008925386,0.0002738565,0.0006454657,0.0004611944,0.0005338971,0.00005179866],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002451629,"about_ca_system_score_gemma":0.0004156918,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001185886,"about_ca_topic_score_gemma":0.00009425129,"domain_scores_codex":[0.9957989,0.00002563098,0.0008143894,0.001715988,0.0009358043,0.0007093215],"domain_scores_gemma":[0.9978722,0.0003219644,0.000193446,0.0009088497,0.0004300556,0.0002734903],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008660242,0.0000264778,0.000001483956,0.0001084375,0.00001267652,0.00001064712,0.002696173,0.001426905,0.04023046,0.0186256,0.0001619466,0.9366905],"study_design_scores_gemma":[0.0005085519,0.001378903,0.00002094448,0.002109512,0.00004310556,0.00007086025,0.000002564424,0.6120724,0.228572,0.1398744,0.01379111,0.001555612],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000181932,0.0001128372,0.9905765,0.001856075,0.001240699,0.001536858,0.00004458433,0.0003281849,0.004122354],"genre_scores_gemma":[0.09138771,0.00002404665,0.9053147,0.001319593,0.0007212549,0.0001339444,0.00002228207,0.00007619971,0.001000306],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9351349,"threshold_uncertainty_score":0.9997152,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.06877897661628128,"gpt":0.2812801912057318,"spread":0.2125012145894505,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000414971,0.0001378515,0.0001880109,0.00009585849,0.0001544185,0.00008797544,0.0006418849,0.00004912036,0.001170194],"category_scores_gemma":[0.00004335561,0.00009813398,0.000137293,0.0002553109,0.00009460526,0.0003844474,0.0001105188,0.00007787628,0.00004956664],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002090425,"about_ca_system_score_gemma":0.00001588366,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006966131,"about_ca_topic_score_gemma":0.00002174178,"domain_scores_codex":[0.9987912,0.00005342768,0.000399018,0.0002765558,0.0002332399,0.0002465809],"domain_scores_gemma":[0.9987363,0.0004425136,0.0001348248,0.0003781389,0.0002520424,0.00005621384],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000004157196,0.0001028641,0.00001467295,0.00001763304,0.00005433172,0.000001444487,0.0002256012,7.522374e-7,0.001472959,0.005982401,0.02272287,0.9694003],"study_design_scores_gemma":[0.005410919,0.001890238,0.0004998087,0.0002302479,0.0001508795,0.0002052022,0.0007554496,0.3194,0.4331286,0.194055,0.04292189,0.001351764],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004167359,0.0001065872,0.9806569,0.005106409,0.0001451794,0.0008230935,0.00007500458,0.0003082248,0.01236188],"genre_scores_gemma":[0.3115018,0.0001067223,0.684451,0.00241417,0.0001330952,0.0003159727,0.00004813128,0.00001880682,0.001010352],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9680486,"threshold_uncertainty_score":0.9997429,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University; École de Technologie Supérieure","funders":"Conselho Nacional de Desenvolvimento Científico e Tecnológico","keywords":"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02659709395423231,"gpt":0.2655471610991083,"spread":0.2389500671448759,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002870958,0.0001638652,0.0002667466,0.0005915915,0.0001058969,0.00008216084,0.000209449,0.00007392138,0.0001446743],"category_scores_gemma":[0.000005900652,0.000153813,0.0001286672,0.000782545,0.0001081122,0.0003470162,0.000004348066,0.0001645069,0.00001901264],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000021104,"about_ca_system_score_gemma":0.0000149421,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003254383,"about_ca_topic_score_gemma":0.0005593065,"domain_scores_codex":[0.9987639,0.00007771153,0.0004093035,0.0004084863,0.0001936671,0.0001468891],"domain_scores_gemma":[0.9992283,0.0001073143,0.0001381587,0.0003147167,0.0001164623,0.00009507818],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000006781047,0.0001007729,0.0001175042,0.00001287847,0.0001412413,9.134832e-7,0.0003025802,0.000129804,0.001664996,0.00003181082,0.000003058803,0.9974877],"study_design_scores_gemma":[0.0001794044,0.0002118716,0.001121961,0.00006283502,0.0003889382,0.00002559167,0.00008024584,0.07912143,0.9168657,0.001528408,0.00008528867,0.0003283341],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01800045,0.00007658618,0.9809482,0.0005154138,0.00003696151,0.0001298143,0.00005663321,0.0001099115,0.0001260194],"genre_scores_gemma":[0.9848491,0.0006255989,0.01416903,0.0002385798,0.00001435664,0.00002946881,0.00001164373,0.000007096459,0.00005514898],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9971593,"threshold_uncertainty_score":0.6272312,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02718084531866138,"gpt":0.3010477378835328,"spread":0.2738668925648714,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002079076,0.0001198641,0.0003337029,0.00187604,0.0001231584,0.00001699605,0.001782073,0.0001016608,0.0000377369],"category_scores_gemma":[0.0004789884,0.0000727129,0.0002051574,0.00528636,0.0008136742,0.0009250519,0.000277271,0.0001168258,0.000001701388],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004160644,"about_ca_system_score_gemma":0.00004706117,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008436227,"about_ca_topic_score_gemma":1.167038e-7,"domain_scores_codex":[0.9970292,0.0000276631,0.0006646584,0.0003732008,0.001732013,0.0001732704],"domain_scores_gemma":[0.9979264,0.0004998215,0.0006811713,0.0000311753,0.0008146387,0.00004685248],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002291696,0.0001291513,0.002943914,0.00004653023,0.00006940514,1.452807e-8,0.0001677183,0.00001882938,0.9417456,0.04362667,0.0004328951,0.01079639],"study_design_scores_gemma":[0.0001513964,0.0001520769,0.0483984,0.0003530272,0.00004326752,0.000004145943,0.00002537023,0.007942377,0.9155348,0.0272803,0.00002217159,0.00009265],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9851758,0.0001344042,0.003910111,0.006320517,0.00003338708,0.000318766,0.0000721714,0.00006368433,0.003971165],"genre_scores_gemma":[0.984736,0.00005142817,0.01497763,0.0001580144,0.00002551367,0.00001097213,1.847868e-7,0.000002883472,0.00003740535],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04545449,"threshold_uncertainty_score":0.3311564,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2795776870","doi":"10.1007/s10032-018-0301-6","title":"Fixed-sized representation learning from offline handwritten signatures of different sizes","year":2018,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":66,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"École de Technologie Supérieure","funders":"Fonds de recherche du Québec – Nature et technologies; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Signature (topology); Feature (linguistics); Convolutional neural network; Feature learning; Pyramid (geometry); Representation (politics); Pattern recognition (psychology); Constraint (computer-aided design)","retraction":null,"screen_n_in":null,"score":{"opus":0.01616332556073162,"gpt":0.2904750571368058,"spread":0.2743117315760741,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004729771,0.0002188221,0.0004175995,0.001037432,0.0001990957,0.000588419,0.0005660299,0.0001107094,0.001292129],"category_scores_gemma":[0.0002287839,0.000172444,0.0003588441,0.0005049712,0.0001071486,0.0006823466,0.000167048,0.0003580536,0.00003658086],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000765126,"about_ca_system_score_gemma":0.00003063058,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009861599,"about_ca_topic_score_gemma":0.00005075985,"domain_scores_codex":[0.9973561,0.0002980607,0.0007622541,0.0004320775,0.0009642543,0.000187317],"domain_scores_gemma":[0.9974634,0.0003527215,0.0007348121,0.0001974411,0.001111015,0.0001405963],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006538403,0.0007249606,0.01949545,0.00001172848,0.007414434,0.00009149003,0.001611087,0.0001077725,0.02941622,0.001672077,0.001896436,0.9369045],"study_design_scores_gemma":[0.006221712,0.002125654,0.08920935,0.0008012642,0.001765755,0.00009035716,0.0005110591,0.03219854,0.6790616,0.1836071,0.003120504,0.001287112],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6953447,0.0001427626,0.3003482,0.002108641,0.0006479166,0.0001600339,0.00002683529,0.0001219769,0.001098909],"genre_scores_gemma":[0.9886348,0.0009012459,0.008956488,0.0004068644,0.0005823358,0.0000132145,0.0001757049,0.00001120136,0.0003181658],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9356174,"threshold_uncertainty_score":0.9996209,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"École de Technologie Supérieure","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Preprocessor; Robustness (evolution); Ground truth; Computer science; Pattern recognition (psychology); Historical document; Phase congruency; Computer vision; Feature (linguistics); Image (mathematics)","retraction":null,"screen_n_in":null,"score":{"opus":0.01304638156847595,"gpt":0.2772989232520176,"spread":0.2642525416835417,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000223541,0.0001344813,0.0001439314,0.000272109,0.0002397616,0.0001891645,0.0002390313,0.00005023239,0.000005272691],"category_scores_gemma":[0.000005746254,0.0001355789,0.00004604555,0.0004452081,0.0001094254,0.0008026189,0.00000273362,0.0001161091,0.000005680364],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003926114,"about_ca_system_score_gemma":0.00009357752,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004478875,"about_ca_topic_score_gemma":0.00000123983,"domain_scores_codex":[0.9989389,0.00004168414,0.0002767973,0.0003475177,0.0002299496,0.0001651212],"domain_scores_gemma":[0.9991886,0.00003982624,0.0001384984,0.0002916594,0.0002649466,0.00007647181],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000009384462,0.0005064359,9.221333e-7,0.0001506841,0.000004387795,2.593507e-7,0.0001755479,0.003868121,0.1495082,0.0002515137,0.00001873166,0.8455058],"study_design_scores_gemma":[0.0005454277,0.0001236747,0.000002134059,0.00007660185,0.00001356269,0.000002679709,0.00001105379,0.5569233,0.440026,0.002075944,0.0000867245,0.0001128333],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001357804,0.00004978868,0.9974015,0.0002264246,0.00002362444,0.000314797,0.000008877961,0.0003186465,0.0002985182],"genre_scores_gemma":[0.7271665,0.00001003939,0.272359,0.0002350733,0.000008041479,0.0001898132,0.000001769769,0.00001042902,0.00001929885],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.845393,"threshold_uncertainty_score":0.5528746,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01647702975498928,"gpt":0.2375908017093598,"spread":0.2211137719543705,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0002007779,0.0001514856,0.0001311969,0.0002329718,0.0005510625,0.001050428,0.0004357501,0.0001157932,0.00001877781],"category_scores_gemma":[0.0002194335,0.0001436968,0.00004561778,0.0001121741,0.00008164819,0.004715045,0.0001170685,0.0002065434,0.00007185007],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004820269,"about_ca_system_score_gemma":0.00003214911,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004704509,"about_ca_topic_score_gemma":0.000006355403,"domain_scores_codex":[0.9989483,0.00004332519,0.00032789,0.0001756942,0.000289616,0.0002151369],"domain_scores_gemma":[0.998791,0.00008654551,0.0003281145,0.0004797296,0.0002178724,0.00009670464],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000544476,0.00004053336,0.001393714,0.00002223992,0.000008813084,0.000004320031,0.00008797403,0.0003603106,0.00001949552,0.001117328,0.002940361,0.9939505],"study_design_scores_gemma":[0.0007855108,0.0001607608,0.04989723,0.00006090457,0.000005790623,0.00001965752,0.000003600876,0.943756,0.0005941497,0.001639336,0.002869107,0.0002079344],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03004895,0.00002212583,0.9581493,0.002760572,0.0003427498,0.0004816833,0.00005175636,0.0007088393,0.007434078],"genre_scores_gemma":[0.9925286,0.00002245024,0.00560842,0.001369613,0.00007115672,0.00005643587,0.0003016532,0.000005756951,0.0000359058],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9937425,"threshold_uncertainty_score":0.9999866,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2120888827","doi":"10.1007/s10032-011-0166-4","title":"Writer verification using texture-based features","year":2011,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":64,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"École de Technologie Supérieure","funders":"Conselho Nacional de Desenvolvimento Científico e Tecnológico","keywords":"Computer science; Classifier (UML); Word error rate; Artificial intelligence; Pattern recognition (psychology); Texture (cosmology); Segmentation; Representation (politics); Writing style; Set (abstract data type); Image (mathematics)","retraction":null,"screen_n_in":null,"score":{"opus":0.03427482938487292,"gpt":0.2878837232854027,"spread":0.2536088939005298,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005762335,0.0002059458,0.0002345456,0.001377039,0.0001990901,0.000799962,0.0006193857,0.0001077889,0.0009355406],"category_scores_gemma":[0.0000472561,0.0001712707,0.0003122467,0.0005489969,0.00005400622,0.000901935,0.00007060834,0.000303831,0.00005598965],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001321927,"about_ca_system_score_gemma":0.0000527575,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005626146,"about_ca_topic_score_gemma":0.00001393633,"domain_scores_codex":[0.9980339,0.000160043,0.0005021849,0.0003884329,0.0007148439,0.0002006137],"domain_scores_gemma":[0.9984385,0.00006190425,0.000425028,0.0002350991,0.0006765689,0.0001628872],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002688821,0.0007797376,0.005864519,0.00001294456,0.003237613,0.0002404552,0.001049545,0.00007527752,0.00296804,0.005307234,0.001334501,0.9788613],"study_design_scores_gemma":[0.008683669,0.002167348,0.1784246,0.001299327,0.004085522,0.001903395,0.0005373861,0.07787878,0.4130346,0.2882066,0.01944849,0.004330218],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1071933,0.0001329038,0.887013,0.001249031,0.0007176076,0.0001808018,0.00002223539,0.0001671647,0.003324055],"genre_scores_gemma":[0.9371278,0.000223783,0.0605906,0.001563726,0.0002364651,0.00001443286,0.00006175961,0.00001225429,0.0001691782],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9745311,"threshold_uncertainty_score":0.9999778,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02850450827785052,"gpt":0.2731796874880275,"spread":0.244675179210177,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003042131,0.0001710962,0.0001992818,0.0002795967,0.00008379754,0.0002432705,0.0008118143,0.000110221,0.00004579064],"category_scores_gemma":[0.0002224878,0.0001542665,0.0000655742,0.0006633481,0.00004716932,0.0004276318,0.0002129024,0.0003191727,0.0001439788],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007868921,"about_ca_system_score_gemma":0.00005608148,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001475007,"about_ca_topic_score_gemma":0.0007106033,"domain_scores_codex":[0.9985539,0.00004553352,0.0003251288,0.0004792719,0.0002992413,0.0002968712],"domain_scores_gemma":[0.9990801,0.0001678861,0.00007034284,0.0005046809,0.00007737339,0.0000996029],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002585279,0.0009319707,0.005788884,0.00002413273,0.00003895315,0.000424727,0.002423275,0.0002574931,0.001958905,0.6401086,0.002050285,0.3459669],"study_design_scores_gemma":[0.002460928,0.0004724219,0.0121998,0.0005868053,0.000007748428,0.00002132529,0.00008389649,0.01191712,0.09071453,0.8769065,0.0036595,0.0009694186],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07899171,0.00004974693,0.8996494,0.003871791,0.0001843592,0.0002250378,0.00000784049,0.001031913,0.01598815],"genre_scores_gemma":[0.8589556,0.00002443838,0.1382691,0.002543153,0.00007392743,0.00002520949,0.00001165947,0.00001252851,0.00008440056],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7799639,"threshold_uncertainty_score":0.6290804,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.07700851734809266,"gpt":0.3149699149892884,"spread":0.2379613976411958,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001459599,0.000214146,0.0001852339,0.000128733,0.000291956,0.0002522579,0.0004880266,0.0001493413,0.000001947293],"category_scores_gemma":[0.00004290412,0.0001840136,0.0001016287,0.0005420978,0.00002559109,0.0002697672,0.000006030029,0.0002857715,0.00005565742],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002119321,"about_ca_system_score_gemma":0.0001191023,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001782755,"about_ca_topic_score_gemma":0.0000882387,"domain_scores_codex":[0.998058,0.000206346,0.0003307205,0.0004780886,0.0005960216,0.0003308513],"domain_scores_gemma":[0.9979511,0.0001840346,0.0001567048,0.0005509855,0.0009807013,0.0001764796],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003090278,0.00006293994,6.979482e-7,0.00001581826,0.00001484759,1.861276e-7,0.0004007134,0.5551502,0.00008955062,0.0002117822,0.01309153,0.4309309],"study_design_scores_gemma":[0.0004873953,0.0002652674,0.000003535166,0.00008835188,0.00006995549,0.00001539738,0.00007084884,0.9887458,0.003104131,0.003002888,0.003914881,0.0002315187],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001492277,0.0001150434,0.9908955,0.003188123,0.001022897,0.002619549,0.0001177669,0.0003679523,0.0001808925],"genre_scores_gemma":[0.8851062,0.00003575401,0.1100807,0.000794511,0.0004306725,0.003129245,0.00009557224,0.00003856664,0.0002887779],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8836139,"threshold_uncertainty_score":0.7503859,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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)","retraction":null,"screen_n_in":null,"score":{"opus":0.03388004897220471,"gpt":0.2716556090274912,"spread":0.2377755600552865,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001582411,0.0001709029,0.0003662217,0.0005927225,0.0001196973,0.00002320217,0.0002987129,0.00007456919,0.00006202124],"category_scores_gemma":[0.000005541607,0.0001609563,0.0002259111,0.0006534674,0.0001578661,0.0003186668,0.000004413519,0.0001850959,0.000003757118],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002514333,"about_ca_system_score_gemma":0.00003866375,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004092696,"about_ca_topic_score_gemma":0.0001909155,"domain_scores_codex":[0.998507,0.00008211892,0.0005825819,0.0003634957,0.0003235528,0.0001411997],"domain_scores_gemma":[0.9989721,0.0001244616,0.000228352,0.0003259776,0.0002773017,0.00007182352],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006319589,0.001846982,0.002169942,0.0001448732,0.001670966,0.00001248404,0.001448825,0.0456416,0.04873076,0.0007921702,0.00007915879,0.897399],"study_design_scores_gemma":[0.00006606284,0.0001018514,0.001592366,0.00003122414,0.0001468227,0.00001563281,0.00005485207,0.7182584,0.2791207,0.0004457427,0.000008461549,0.0001579562],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1460316,0.00004875562,0.853117,0.000346468,0.00003605965,0.00008410624,0.0002592577,0.00006016013,0.00001665425],"genre_scores_gemma":[0.9964806,0.00074515,0.002399051,0.0002083595,0.0000079418,0.00001692219,0.00007834213,0.000008185655,0.00005540125],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8972411,"threshold_uncertainty_score":0.6563606,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02849303801420109,"gpt":0.293090132543413,"spread":0.2645970945292119,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002789494,0.0001872638,0.0002162153,0.0001725728,0.0002912542,0.00002651845,0.0005680612,0.000112164,0.00004939803],"category_scores_gemma":[0.0002567057,0.0001549623,0.0001117591,0.0004622951,0.0005744145,0.0002970858,0.0001516303,0.0003145785,0.0002369186],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000223887,"about_ca_system_score_gemma":0.00004681883,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009483961,"about_ca_topic_score_gemma":0.00001862093,"domain_scores_codex":[0.9980618,0.0004471288,0.000428359,0.0004793393,0.0002494129,0.0003339599],"domain_scores_gemma":[0.9982076,0.0005854939,0.0002672036,0.0003274199,0.0005392571,0.00007308533],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0002549335,0.0006426675,0.01319573,0.00001900473,0.00007919176,0.0003991153,0.0006137827,2.153373e-7,0.001070255,0.002158322,0.0171028,0.9644639],"study_design_scores_gemma":[0.01267194,0.0135912,0.5478334,0.0005454167,0.0002172317,0.009187602,0.0005260815,0.01953064,0.1711798,0.1710952,0.04913425,0.00448723],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4582973,0.00005039041,0.5292461,0.003033472,0.0007137439,0.0004741005,0.00002604143,0.0003742551,0.007784574],"genre_scores_gemma":[0.9919547,0.0001473791,0.003052194,0.004303114,0.0001214891,0.00007308137,0.00008315758,0.00002348859,0.0002413922],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9599767,"threshold_uncertainty_score":0.6319177,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03112518242818602,"gpt":0.2809702338494022,"spread":0.2498450514212162,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00168687,0.0006702981,0.0006835268,0.001210275,0.000391191,0.0008279121,0.00281757,0.0004401947,0.00007300139],"category_scores_gemma":[0.0003402563,0.0006778185,0.0002415394,0.000680783,0.0001962185,0.00132988,0.0009215656,0.0008517061,0.00007695024],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000267134,"about_ca_system_score_gemma":0.0008128241,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000178759,"about_ca_topic_score_gemma":0.0001183351,"domain_scores_codex":[0.9952215,0.00004198589,0.0008139349,0.001993183,0.0009283641,0.001001022],"domain_scores_gemma":[0.9966279,0.0006508995,0.0004500084,0.001362767,0.0005739967,0.0003344033],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000009618264,0.00003586227,0.000001535382,0.00004308342,0.000007175167,0.00004061727,0.0001374883,0.00005292814,0.0002723919,0.003618388,0.0003444209,0.9954365],"study_design_scores_gemma":[0.001461034,0.0008282752,0.00001199757,0.00243559,0.00003500089,0.0002166671,2.99088e-7,0.2626499,0.03331843,0.6727286,0.02459963,0.00171461],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00001057402,0.0007941828,0.9929903,0.001101973,0.0007551509,0.001121736,0.0001076576,0.0006647357,0.002453741],"genre_scores_gemma":[0.00222835,0.0002137926,0.9914547,0.003705586,0.001269229,0.00003832232,0.0001678379,0.00005437575,0.0008677855],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9937219,"threshold_uncertainty_score":0.9995673,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2107835247","doi":"10.1007/s10032-011-0157-5","title":"A local linear level set method for the binarization of degraded historical document images","year":2011,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":59,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"École de Technologie Supérieure","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Active contour model; Historical document; Set (abstract data type); Segmentation; Curvature; Computer vision; Probabilistic logic; Image (mathematics); Pattern recognition (psychology); Pixel; Image segmentation; Level set (data structures); Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.0645111069674379,"gpt":0.3269907466057523,"spread":0.2624796396383144,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001295014,0.0001845009,0.0002940833,0.0008156978,0.000186396,0.0002175266,0.000653044,0.00008417325,0.0002086796],"category_scores_gemma":[0.0001157797,0.00012698,0.0004114312,0.0004832958,0.00005772819,0.0004600523,0.000116342,0.00020655,0.000008653644],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000240059,"about_ca_system_score_gemma":0.00005665453,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001580659,"about_ca_topic_score_gemma":0.00001891089,"domain_scores_codex":[0.9979055,0.000198746,0.0006978569,0.0003235927,0.0006972343,0.0001770528],"domain_scores_gemma":[0.9978723,0.0002598038,0.0005844597,0.0001968241,0.0009738021,0.0001128079],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003271741,0.0004267794,0.0007689941,0.00001762955,0.003748052,0.00002710056,0.001401946,0.000117145,0.0007634278,0.005301673,0.002342326,0.9847578],"study_design_scores_gemma":[0.008404355,0.00447353,0.01957409,0.0006918701,0.005467342,0.0008042253,0.001066531,0.1112003,0.4069467,0.4079522,0.03124209,0.002176812],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00246502,0.0001374541,0.9943182,0.002220592,0.0004156373,0.0002185435,0.0000302119,0.00003905779,0.0001552459],"genre_scores_gemma":[0.6910412,0.001036284,0.3063052,0.0007029576,0.0002362222,0.00008666755,0.00006568118,0.00001648228,0.0005092889],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.982581,"threshold_uncertainty_score":0.5178093,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01713105310537766,"gpt":0.2556298412927902,"spread":0.2384987881874125,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004271237,0.0001415354,0.000161826,0.0001686895,0.0002423618,0.0002560989,0.0001244967,0.0001336363,0.000012746],"category_scores_gemma":[0.00001545449,0.0001390322,0.00005388364,0.0001442041,0.00003759998,0.002017726,0.000004776942,0.0001859365,0.00001094725],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002851365,"about_ca_system_score_gemma":0.00003606858,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001465144,"about_ca_topic_score_gemma":0.00000537239,"domain_scores_codex":[0.9990783,0.00003206923,0.0003219066,0.0002007577,0.0002051878,0.0001617817],"domain_scores_gemma":[0.9991902,0.0001339969,0.0001557129,0.0002119065,0.0002395031,0.00006873481],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001359446,0.00004723437,0.00001854912,0.0002210758,0.00004454549,1.891858e-7,0.006388879,0.00009342268,0.006056496,0.02005117,0.0001477908,0.9667947],"study_design_scores_gemma":[0.004405836,0.001427381,0.0008144086,0.0002389464,0.00007899983,0.00004514612,0.0007544255,0.8112869,0.1254943,0.03429079,0.02023183,0.0009309973],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08000024,0.00001671314,0.9180997,0.0003801087,0.0003713632,0.0006770825,0.0000873146,0.0001680882,0.0001993803],"genre_scores_gemma":[0.9661937,0.00008465933,0.03302003,0.0005092751,0.0000345241,0.00007683166,0.00005786778,0.000006652469,0.00001642958],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9658637,"threshold_uncertainty_score":0.5669569,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01940022983190206,"gpt":0.2546375944098515,"spread":0.2352373645779494,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001801314,0.00008455422,0.0000768809,0.00006577992,0.0001074346,0.0001096131,0.0001236189,0.00007954735,0.0001389918],"category_scores_gemma":[0.00003174817,0.00007738404,0.00002455376,0.0002513466,0.00002825689,0.0003751991,0.00003321768,0.0001294264,0.000007900784],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002076395,"about_ca_system_score_gemma":0.00001741984,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006934014,"about_ca_topic_score_gemma":0.00000264576,"domain_scores_codex":[0.9993177,0.00006778858,0.0001260596,0.0002406442,0.0001146244,0.0001331686],"domain_scores_gemma":[0.9996063,0.00004583893,0.00004379882,0.0001633329,0.00008473186,0.00005600234],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001668088,0.0002587947,0.002390412,0.00002554629,0.00004985136,0.00002067163,0.0002167766,0.00383317,0.03693919,0.1208558,0.00593695,0.8294562],"study_design_scores_gemma":[0.0001464773,0.0000399395,0.0008078417,0.000008813468,0.0000045235,0.00009229581,0.000006794693,0.9701792,0.02182369,0.003315814,0.003407134,0.0001674578],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01100917,0.000273464,0.9844236,0.0001652985,0.0001762062,0.0001029241,3.871427e-7,0.0002699328,0.003579007],"genre_scores_gemma":[0.8363928,0.00004379397,0.1623966,0.0005077068,0.00005926231,0.00000802487,0.000003624086,0.000005851437,0.0005823117],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.966346,"threshold_uncertainty_score":0.315563,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02841701672352499,"gpt":0.2719150356142068,"spread":0.2434980188906818,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002045546,0.0001146098,0.0001386602,0.00009190945,0.00009856979,0.00006478655,0.0001083844,0.0001356276,0.00002006019],"category_scores_gemma":[0.0001366052,0.0001120851,0.00003878777,0.00009370158,0.00009763195,0.0002441855,0.00002324447,0.0001838858,0.000003396761],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006336249,"about_ca_system_score_gemma":0.00002600923,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001567412,"about_ca_topic_score_gemma":0.00004209439,"domain_scores_codex":[0.9991899,0.00004288073,0.0001969857,0.0002985766,0.0001371967,0.0001345309],"domain_scores_gemma":[0.9992638,0.0002311407,0.00006357184,0.0001749923,0.0001941965,0.00007232292],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00007792886,0.0003140745,0.001199633,0.0002042908,0.0000308945,0.000001340194,0.0002541806,0.000001023132,0.08110172,0.001163813,0.0002351174,0.915416],"study_design_scores_gemma":[0.00108019,0.0009539176,0.01494232,0.0001127705,0.00006225927,0.00001168434,0.00001766603,0.02851215,0.9355507,0.01796969,0.0004834931,0.0003031436],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4600275,0.0000223107,0.5386519,0.0004746284,0.0001426784,0.0003696997,0.0001340636,0.0001216321,0.00005552443],"genre_scores_gemma":[0.9816826,0.00001201636,0.01774649,0.0001723732,0.00007703993,0.0001836219,0.0001141974,0.000009282139,0.000002348109],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9151129,"threshold_uncertainty_score":0.4570697,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04250751311295106,"gpt":0.2913897140188765,"spread":0.2488822009059254,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004594531,0.0002223054,0.0002253007,0.000257713,0.0001804987,0.0003322539,0.0007003566,0.0001597625,0.001757019],"category_scores_gemma":[0.0001455669,0.0002057809,0.0001027925,0.0004585311,0.00007808019,0.0008536553,0.0002268598,0.0004275616,0.0006231567],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003605351,"about_ca_system_score_gemma":0.00009882356,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001755438,"about_ca_topic_score_gemma":0.0001272686,"domain_scores_codex":[0.9983521,0.00005936148,0.0003550325,0.0005109634,0.0003189221,0.0004036141],"domain_scores_gemma":[0.9987435,0.00009687495,0.0001178508,0.0006084275,0.0002300804,0.0002032729],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001363937,0.0002284253,0.0006397357,0.00003477848,0.00003091916,0.00008616976,0.0002183773,4.937268e-7,0.09262586,0.00464849,0.004180206,0.8972929],"study_design_scores_gemma":[0.003000814,0.0007489095,0.01020336,0.0002044054,0.0001507281,0.00230356,0.00008280776,0.1383159,0.6778207,0.1248492,0.0387912,0.003528464],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1001461,0.0000133547,0.8832817,0.0006938012,0.0009764378,0.000368825,0.00002698591,0.001648636,0.01284419],"genre_scores_gemma":[0.6620639,0.000008006145,0.336318,0.0007934013,0.0002014545,0.00003144297,0.00003778842,0.00002334135,0.0005226538],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8937644,"threshold_uncertainty_score":0.9991555,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01706083671525831,"gpt":0.26583255067561,"spread":0.2487717139603517,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002146059,0.0001584875,0.0001275776,0.00007731374,0.0001554478,0.0001986774,0.0003366864,0.0000690064,0.00003453549],"category_scores_gemma":[0.00001584549,0.0001146357,0.00002933799,0.0002850511,0.00007899024,0.0005725449,0.000202723,0.00007807976,0.00002902307],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007127107,"about_ca_system_score_gemma":0.00001975206,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002096318,"about_ca_topic_score_gemma":0.000006398328,"domain_scores_codex":[0.9988292,0.00003834682,0.0002456925,0.0003880502,0.0002195848,0.0002790946],"domain_scores_gemma":[0.9993801,0.0001085232,0.0001168241,0.0002485508,0.00006674953,0.00007926233],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000009885422,0.000009188891,0.0003130912,0.000008077294,0.00001000652,0.000001807642,0.0001920577,0.0001484488,0.0281288,0.0593431,0.0003444661,0.9114911],"study_design_scores_gemma":[0.0003455228,0.000193068,0.004087577,0.0001817268,0.00003223872,0.0001010526,0.0001332961,0.01820483,0.7445861,0.230289,0.0009262185,0.0009193956],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02184442,0.00008682484,0.9762522,0.000332075,0.0001508406,0.0003338999,0.000001285594,0.0002689199,0.0007295118],"genre_scores_gemma":[0.8757168,0.0001217003,0.123539,0.000386686,0.00009366168,0.00003880156,0.000003793732,0.00001003202,0.00008956333],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9105717,"threshold_uncertainty_score":0.4674707,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03382729573277333,"gpt":0.2929195803504617,"spread":0.2590922846176884,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000308325,0.00007556269,0.0001397568,0.0001446203,0.0000305356,0.00003634156,0.0001893454,0.00004217545,0.000001719084],"category_scores_gemma":[0.00004286504,0.00007164245,0.00002685282,0.0001565285,0.00001269199,0.0002656725,0.00005323617,0.00004888449,8.610995e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001657206,"about_ca_system_score_gemma":0.00001381776,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003808147,"about_ca_topic_score_gemma":0.00001445468,"domain_scores_codex":[0.9992569,0.00002011065,0.0002809956,0.000214579,0.00009335174,0.0001340604],"domain_scores_gemma":[0.9995846,0.00007972166,0.00009298599,0.0001614379,0.0000433765,0.00003794136],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001734719,0.00003832162,0.0001658491,0.00002955393,0.000001366255,4.25387e-7,0.0001544251,0.000003148269,0.005113179,0.0009876435,0.0001040285,0.9934003],"study_design_scores_gemma":[0.0009468924,0.0001664475,0.03694952,0.0001062968,0.000005870648,0.00001030146,0.00005804127,0.9109047,0.03830559,0.01184434,0.0004379094,0.00026408],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006082139,0.00003841918,0.9923583,0.0007599176,0.00002246218,0.0003799936,5.264899e-7,0.0001773836,0.0001808991],"genre_scores_gemma":[0.4774685,0.000005824304,0.5223173,0.00007599878,0.000005339045,0.00004401242,5.33757e-7,0.000002219944,0.0000802627],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9931362,"threshold_uncertainty_score":0.2921495,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; National Institute of Standards and Technology","keywords":"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03687812625994893,"gpt":0.2475267493980877,"spread":0.2106486231381388,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002368811,0.0001034358,0.0001247631,0.0001215056,0.0001004297,0.000115772,0.0005891585,0.0000468571,0.0002591526],"category_scores_gemma":[0.00004280073,0.00007262236,0.00004019151,0.0005238354,0.00004145743,0.0003447958,0.0001240397,0.0000922849,0.0003271595],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002298178,"about_ca_system_score_gemma":0.00001390458,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001347396,"about_ca_topic_score_gemma":0.000007199889,"domain_scores_codex":[0.9990605,0.0000340283,0.0002240653,0.0002605758,0.0002353145,0.0001855272],"domain_scores_gemma":[0.9992862,0.00003912954,0.00009087956,0.0003082157,0.0002167896,0.0000588301],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000001632252,0.00004796049,0.000005115042,0.0000146705,0.000005392465,7.726869e-7,0.001245786,5.675388e-7,0.003943922,0.002638914,0.01219279,0.9799025],"study_design_scores_gemma":[0.000269803,0.0001939461,0.000185971,0.000154578,0.0000174562,0.00002255002,0.0003075098,0.008258112,0.9435963,0.03235695,0.0142393,0.0003975101],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002471902,0.0001033035,0.8909297,0.003097592,0.00007071033,0.0004704646,0.00000317128,0.000511108,0.1023421],"genre_scores_gemma":[0.8416615,0.0000293584,0.1553161,0.00231189,0.00006465287,0.0001216974,0.000002526377,0.000009588157,0.0004827156],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9795049,"threshold_uncertainty_score":0.4205083,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02624383913859495,"gpt":0.2742199011466865,"spread":0.2479760620080915,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003227509,0.0001723622,0.000157187,0.0001272367,0.0002459537,0.0002005661,0.0006186961,0.000209789,0.00003888086],"category_scores_gemma":[0.00003368313,0.0001532547,0.0000988097,0.0003026775,0.00009388259,0.0004892998,0.0001301227,0.0002014466,0.000004137341],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006935732,"about_ca_system_score_gemma":0.00003916415,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001897566,"about_ca_topic_score_gemma":0.000009330326,"domain_scores_codex":[0.9986063,0.00006393506,0.0002448604,0.0005016517,0.0002644245,0.0003188807],"domain_scores_gemma":[0.9988835,0.00006440289,0.0001132419,0.0003996564,0.0004476821,0.00009149038],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004318453,0.001464942,0.001130954,0.0001904463,0.0002996556,0.00001500119,0.001375318,0.00856095,0.04669866,0.2881764,0.04125223,0.6104035],"study_design_scores_gemma":[0.0003283013,0.0001270444,0.0008091975,0.000007730652,0.00001008638,0.00005807166,0.00001636076,0.9891478,0.007095621,0.001807885,0.0003830715,0.0002087839],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001496378,0.000153433,0.9959149,0.0002155416,0.0002491997,0.000560955,0.000006633696,0.0004627117,0.0009402988],"genre_scores_gemma":[0.5466874,0.000002317781,0.4520617,0.000582238,0.000402436,0.00005525922,0.00005258691,0.00001010006,0.0001459599],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9805869,"threshold_uncertainty_score":0.6249546,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.05016178984653617,"gpt":0.2380046570476502,"spread":0.187842867201114,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000387848,0.0001546107,0.0001528755,0.0002113508,0.000151463,0.0001085584,0.00048767,0.00009441921,0.002456648],"category_scores_gemma":[0.00003036059,0.0001498112,0.00008213522,0.0002103493,0.00005377906,0.001170072,0.0001352939,0.0001514724,0.002907568],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003331572,"about_ca_system_score_gemma":0.00002994919,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001229313,"about_ca_topic_score_gemma":0.00002050661,"domain_scores_codex":[0.9986935,0.0000905061,0.0003061261,0.0004008776,0.0002154175,0.0002936257],"domain_scores_gemma":[0.9991378,0.00004656701,0.0001060718,0.0003825974,0.0002164555,0.0001105357],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001377733,0.0003399039,0.0006123958,0.00004175607,0.00002848073,0.00004919874,0.00101861,6.351725e-8,0.005830394,0.1252483,0.004593803,0.8622233],"study_design_scores_gemma":[0.0007892781,0.0004553662,0.005329548,0.0001906079,0.00002144062,0.000234991,0.0001847604,0.002665272,0.6387889,0.3473145,0.00307193,0.0009533186],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008742184,0.00002979868,0.8124244,0.0001684134,0.000163206,0.0002042355,0.000003950345,0.001520142,0.1767437],"genre_scores_gemma":[0.6217699,0.00004760061,0.3768007,0.0007635123,0.00007639863,0.00006925057,0.00002131149,0.00001498328,0.0004363942],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.86127,"threshold_uncertainty_score":0.9984552,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02858199877554003,"gpt":0.2767923243620172,"spread":0.2482103255864772,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002570684,0.00007849947,0.00007595739,0.0001271935,0.00009987073,0.000269843,0.0004457379,0.00003966433,0.00020848],"category_scores_gemma":[0.00001924152,0.00007601183,0.00003702857,0.0002742462,0.00001904622,0.001235353,0.00008017945,0.00006247112,0.0003182687],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006504178,"about_ca_system_score_gemma":0.00003207759,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003321678,"about_ca_topic_score_gemma":0.000008919195,"domain_scores_codex":[0.9991449,0.00003469881,0.0002082599,0.0002535878,0.0001804871,0.0001780597],"domain_scores_gemma":[0.999374,0.00001800067,0.00006018233,0.0003831002,0.0001073783,0.00005732938],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00000283174,0.000155385,0.0002073559,0.00001885095,0.0000194254,0.000005421035,0.0005410024,0.00008450491,0.2738813,0.04459686,0.03847452,0.6420125],"study_design_scores_gemma":[0.0001985451,0.00002653405,0.000586064,0.00002511736,0.000005989154,0.00003093671,0.000034772,0.1840355,0.7807757,0.004629622,0.0293675,0.0002837598],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01431707,0.00004055278,0.9767858,0.0009887078,0.000133723,0.0001333937,0.000001215897,0.000668055,0.006931516],"genre_scores_gemma":[0.5339221,0.000008847978,0.4617697,0.001005378,0.00007142802,0.00001389753,0.000002495889,0.000007092173,0.003199107],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6417288,"threshold_uncertainty_score":0.4090806,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}