{"meta":{"query_hash":"fef9bd4f6705","filters":{"topic":"Speech Recognition and Synthesis"},"cohort_total":749,"direct_labels_cover":1,"predictions_cover":749,"exported":749,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/fef9bd4f6705","api":"https://metacan.xera.ac/api/v1/cohort?topic=Speech+Recognition+and+Synthesis"},"results":[{"id":"W100623710","doi":"10.1007/3-540-33486-6_6","title":"Neural Probabilistic Language Models","year":2006,"lang":"en","type":"book-chapter","venue":"Studies in fuzziness and soft computing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":491,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Generalization; Sentence; Curse of dimensionality; Artificial intelligence; Word (group theory); Language model; Natural language processing; Probabilistic logic; Representation (politics); Sequence (biology); Set (abstract data type); Linguistics; Mathematics","score_opus":0.06406113222153774,"score_gpt":0.28941119288099004,"score_spread":0.2253500606594523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W100623710","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005854535,0.027271051,0.097223446,0.0007637673,0.0026555953,0.0010399147,0.000028114844,0.00082750065,0.8643361],"genre_scores_gemma":[0.8668099,0.001058679,0.04017885,0.0009828177,0.0014563786,0.00004531004,0.000033461198,0.00016140424,0.08927318],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983869,0.000030243364,0.00043495526,0.0005997604,0.00024351779,0.0003045942],"domain_scores_gemma":[0.9988773,0.00045507628,0.0001702497,0.00031418967,0.00013520742,0.000048001697],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00028059035,0.00034575403,0.00059416064,0.00019642693,0.00018273458,0.000104969724,0.00036822126,0.00013081929,0.0000049009996],"category_scores_gemma":[0.00007909731,0.00030641598,0.00009243999,0.000077313605,0.00018241315,0.00013934904,0.0006721122,0.00028323187,0.000007980156],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000077092345,0.000047525366,0.00007798458,0.00067804335,0.00013707347,0.0005585744,0.0039008593,0.002741684,0.0000033691392,0.2241621,0.0021599727,0.7655251],"study_design_scores_gemma":[0.00073510635,0.00006934301,0.00022975242,0.0016047539,0.000059200567,0.00012657774,0.0004791156,0.7836746,0.0000067083897,0.20910777,0.002542676,0.0013643674],"about_ca_topic_score_codex":0.000023348583,"about_ca_topic_score_gemma":0.00004249541,"teacher_disagreement_score":0.8609554,"about_ca_system_score_codex":0.00006141826,"about_ca_system_score_gemma":0.000026069572,"threshold_uncertainty_score":0.9999388},"labels":[],"label_agreement":null},{"id":"W1269046860","doi":"10.1201/9781482276237","title":"Speech Processing","year":2018,"lang":"en","type":"book","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":239,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Université du Québec à Montréal","funders":"","keywords":"Speech recognition; Computer science; Natural language processing","score_opus":0.027255205319896805,"score_gpt":0.24671951605143588,"score_spread":0.21946431073153908,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1269046860","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.2660147e-7,0.00006386782,0.14680646,0.00027783724,0.00026430647,0.000075078744,0.0000011155255,0.00036661033,0.8521443],"genre_scores_gemma":[0.000002610029,0.000009543915,0.20917279,0.0011312625,0.00034321763,0.000003486709,0.0000032223757,0.000013419801,0.78932047],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989225,0.000016124328,0.00017322635,0.00040163173,0.00030398,0.00018248521],"domain_scores_gemma":[0.9991875,0.000046625486,0.00009498173,0.00043639683,0.00015565875,0.00007881502],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00016653696,0.00017266397,0.00018818173,0.00014489314,0.0000770879,0.00027167253,0.00084135705,0.00019781054,0.0019576575],"category_scores_gemma":[0.000026771526,0.00014453288,0.0000874714,0.00008395059,0.000047888174,0.0002100111,0.00016935966,0.00013296842,0.005687085],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[2.844536e-7,0.000006076278,1.3780614e-7,0.000015230783,0.000005236035,0.000017915434,0.000017151686,1.6692746e-9,0.0000029071728,0.008011482,0.32252523,0.6693983],"study_design_scores_gemma":[0.00004999029,0.000020796493,0.000002985709,0.000109567016,0.0000068181484,0.00006363713,0.0000015851249,0.0012932234,0.0009318386,0.050267216,0.9469854,0.0002668896],"about_ca_topic_score_codex":0.0000011968066,"about_ca_topic_score_gemma":0.000005191399,"teacher_disagreement_score":0.66913146,"about_ca_system_score_codex":0.00006450869,"about_ca_system_score_gemma":0.00039087763,"threshold_uncertainty_score":0.9989547},"labels":[],"label_agreement":null},{"id":"W129600432","doi":"10.1522/18186435","title":"Exploration de reseaux de neurones a decharges dans un contexte de reconnaissance de parole /","year":2004,"lang":"fr","type":"book","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; Université du Québec à Chicoutimi","funders":"","keywords":"Humanities; Geography; Philosophy","score_opus":0.08794847652498944,"score_gpt":0.28725285037479914,"score_spread":0.1993043738498097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W129600432","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007944476,0.0010348295,0.86660343,0.007221663,0.0005497108,0.00052921195,0.00003813565,0.00043275888,0.11564581],"genre_scores_gemma":[0.1029818,0.005259488,0.4213602,0.01254573,0.0013938098,0.0006732293,0.000068834604,0.00024372556,0.45547318],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.995272,0.0010903922,0.0007147228,0.0010446478,0.0004867676,0.001391465],"domain_scores_gemma":[0.9967391,0.0009771712,0.00037029342,0.0008716037,0.000347412,0.00069445284],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0019443415,0.0006126269,0.0006042196,0.0002461453,0.00060475006,0.0006236139,0.0013783259,0.0006450069,0.0010148346],"category_scores_gemma":[0.0010919268,0.0006653979,0.00034296472,0.00034439698,0.0004400445,0.0011129081,0.0002053693,0.0007048747,0.0005761836],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001755339,0.00067456637,0.0022695195,0.0003912264,0.00026199996,0.0013462611,0.014872515,0.00050955394,0.010617643,0.26311758,0.018346684,0.6874169],"study_design_scores_gemma":[0.0020230287,0.00066632545,0.0051479028,0.0022624445,0.00023925508,0.0021311473,0.0011549757,0.10693934,0.2854634,0.38817778,0.20337549,0.0024189306],"about_ca_topic_score_codex":0.0011831342,"about_ca_topic_score_gemma":0.001586736,"teacher_disagreement_score":0.684998,"about_ca_system_score_codex":0.00205546,"about_ca_system_score_gemma":0.005579599,"threshold_uncertainty_score":0.9998984},"labels":[],"label_agreement":null},{"id":"W141927798","doi":"10.21437/interspeech.2009-111","title":"Cepstral and long-term features for emotion recognition","year":2009,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Computer science; Mel-frequency cepstrum; Term (time); Speech recognition; Emotion recognition; Cepstrum; Recall; Artificial intelligence; Class (philosophy); Pattern recognition (psychology); Logistic regression; Machine learning; Feature extraction; Cognitive psychology; Psychology","score_opus":0.033999945749153625,"score_gpt":0.27037137966234537,"score_spread":0.23637143391319174,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W141927798","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27512577,0.00004971524,0.7108231,0.0039200527,0.00022138437,0.0003153882,0.0000052714245,0.00029297586,0.009246339],"genre_scores_gemma":[0.8473728,0.00003214566,0.1500879,0.0014535771,0.00009908026,0.000009519707,0.00001555935,0.0000034732154,0.00092599314],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9995136,0.000015514628,0.00008367978,0.00018949383,0.00007432698,0.00012334573],"domain_scores_gemma":[0.999722,0.00004658831,0.000025496363,0.00010079657,0.00004997237,0.0000551458],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000093398994,0.000065695676,0.0000672745,0.00006301414,0.00007159679,0.0001393167,0.00010030004,0.000046245084,0.00005329942],"category_scores_gemma":[0.000029821013,0.000056202276,0.000039525457,0.00007070115,0.000010281708,0.0003136206,0.000010405522,0.000033155757,0.000022726266],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000048283355,0.000025861471,0.00014435184,0.0000039785814,0.0000026398352,0.0000015874656,0.00003956281,3.3172736e-8,0.0006923684,0.0017964902,0.0009046172,0.99638367],"study_design_scores_gemma":[0.0011074793,0.0004916587,0.848985,0.00006151931,0.000021071384,0.00020799186,0.000038407135,0.0024648462,0.080096036,0.06572946,0.00034909337,0.00044742803],"about_ca_topic_score_codex":0.000001356411,"about_ca_topic_score_gemma":0.000005929318,"teacher_disagreement_score":0.9959363,"about_ca_system_score_codex":0.000008398992,"about_ca_system_score_gemma":0.000007257846,"threshold_uncertainty_score":0.22918624},"labels":[],"label_agreement":null},{"id":"W1501761272","doi":"10.1109/icassp.1988.196632","title":"Three probabilistic language models for a large-vocabulary speech recognizer","year":2003,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bell (Canada); Institut National de la Recherche Scientifique","funders":"","keywords":"Trigram; Computer science; Language model; Vocabulary; Decoding methods; Speech recognition; Word (group theory); Natural language processing; Artificial intelligence; Bigram; Probabilistic logic; Conversation; Linguistics; Algorithm","score_opus":0.0377717494101761,"score_gpt":0.2618095162160192,"score_spread":0.2240377668058431,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1501761272","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031498715,0.000087990025,0.9391506,0.00034842506,0.00020668011,0.0005263803,0.000010164847,0.00028779902,0.056232147],"genre_scores_gemma":[0.10046295,0.000006571079,0.8953333,0.0014276251,0.00005269738,0.00016606788,0.0000068242675,0.000022637267,0.0025213298],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99873495,0.00004582141,0.00021278861,0.00042744743,0.00020352191,0.00037547972],"domain_scores_gemma":[0.9989889,0.0002347205,0.000046344954,0.0004927174,0.00012454434,0.0001127593],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000577081,0.00014774084,0.00017766173,0.00009239966,0.00010707141,0.00012573811,0.000404166,0.00007977758,0.00047836042],"category_scores_gemma":[0.0003302417,0.00012331452,0.00012352811,0.0002469561,0.0000145791355,0.00035797487,0.000053449607,0.00007392254,0.00021996575],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013473346,0.00034321295,0.000058736103,0.000052629424,0.000046907484,0.000046018376,0.0004662252,0.000018043056,0.000405198,0.7230863,0.010503209,0.26496008],"study_design_scores_gemma":[0.0012949834,0.00011061228,0.000054081447,0.000030985073,0.000025726735,0.00011985208,0.00018943285,0.44742766,0.018502166,0.5195756,0.012098668,0.00057025347],"about_ca_topic_score_codex":0.0000123982845,"about_ca_topic_score_gemma":0.0001257248,"teacher_disagreement_score":0.4474096,"about_ca_system_score_codex":0.000028579878,"about_ca_system_score_gemma":0.000073067036,"threshold_uncertainty_score":0.5237711},"labels":[],"label_agreement":null},{"id":"W1509434377","doi":"10.1109/nnsp.1991.239500","title":"Neural-network architecture for linear and nonlinear predictive hidden Markov models: application to speech recognition","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Speech recognition; Artificial neural network; Hidden Markov model; Linear prediction; Nonlinear system; Artificial intelligence; Term (time); Frame (networking); Markov model; Pattern recognition (psychology); Linear model; Markov chain; Machine learning","score_opus":0.033613259919094314,"score_gpt":0.241170703534018,"score_spread":0.2075574436149237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1509434377","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006425261,0.000055687906,0.9825097,0.0035777804,0.00010880467,0.00095710286,0.00003739777,0.0002895885,0.0060387217],"genre_scores_gemma":[0.019070901,0.000047370573,0.9775318,0.002073063,0.00043246595,0.0002499365,0.000024761532,0.000018547706,0.00055115926],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987663,0.000047699657,0.00021553309,0.00050803984,0.00018707826,0.00027534558],"domain_scores_gemma":[0.999093,0.00022236987,0.000059618516,0.00030533585,0.00015223127,0.00016745522],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020425364,0.00015726945,0.00016242852,0.00011101597,0.00013901439,0.00009652417,0.00028069955,0.0000925624,0.00006690104],"category_scores_gemma":[0.000059990958,0.0001404116,0.00006307054,0.00033066922,0.000022428945,0.00031432445,0.00009692567,0.000103597864,0.00008952837],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021691389,0.00004077725,0.0000104758265,0.000010406701,0.000011805072,0.0000012099937,0.0001471037,0.00028195188,0.00007542814,0.00013665942,0.0036075127,0.995655],"study_design_scores_gemma":[0.00027223074,0.00014182153,0.00005474984,0.00001828727,0.000012756374,0.000031758074,0.000019643447,0.97876245,0.0015511829,0.0146667985,0.0042707105,0.00019761459],"about_ca_topic_score_codex":0.000011009423,"about_ca_topic_score_gemma":0.000024613842,"teacher_disagreement_score":0.99545735,"about_ca_system_score_codex":0.000021579512,"about_ca_system_score_gemma":0.0000071735853,"threshold_uncertainty_score":0.5725819},"labels":[],"label_agreement":null},{"id":"W1512994456","doi":"10.1023/a:1015568521453","title":"Learning Prosodic Patterns for Mandarin Speech Synthesis","year":2002,"lang":"en","type":"article","venue":"Journal of Intelligent Information Systems","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; University of Alberta","funders":"Chinese Academy of Sciences","keywords":"Naturalness; Computer science; Prosody; Intelligibility (philosophy); Speech synthesis; Speech recognition; Cluster analysis; Artificial intelligence; Decision tree; Artificial neural network; Natural language processing","score_opus":0.03588713324134827,"score_gpt":0.24375575159079285,"score_spread":0.2078686183494446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1512994456","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011715751,0.00010364915,0.9824516,0.00032626488,0.0011816779,0.0003268982,0.000007757964,0.00005612886,0.003830227],"genre_scores_gemma":[0.9889064,0.00023266893,0.00994737,0.00015675499,0.00021071822,0.000038042945,0.0000016948102,0.000008058997,0.000498301],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99798065,0.00008041328,0.0011665699,0.00007431691,0.0005088383,0.00018923129],"domain_scores_gemma":[0.9977242,0.00031236236,0.0010306757,0.0001631631,0.0006604173,0.00010921938],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011253138,0.0001215665,0.00025939767,0.00043025392,0.00012761136,0.00056210527,0.0004964646,0.00007216956,0.0001031342],"category_scores_gemma":[0.000549197,0.00009614671,0.00019130134,0.00018842929,0.000011692782,0.0019428286,0.000035222823,0.00016485857,0.00028033115],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002109403,0.00007028501,0.0008275312,0.0002465552,0.0000918345,0.000010113845,0.0030185957,0.00080309436,0.00007560173,0.0022295038,0.0039696996,0.9886361],"study_design_scores_gemma":[0.0007144085,0.0006865724,0.00022193369,0.0009047758,0.000053352902,0.002141763,0.004767182,0.53292423,0.05160228,0.0001783224,0.40526912,0.0005360467],"about_ca_topic_score_codex":0.000005227754,"about_ca_topic_score_gemma":3.7297264e-7,"teacher_disagreement_score":0.98810005,"about_ca_system_score_codex":0.00010081767,"about_ca_system_score_gemma":0.00002734153,"threshold_uncertainty_score":0.5420394},"labels":[],"label_agreement":null},{"id":"W1519446688","doi":"10.1109/isspit.2004.1433721","title":"Acoustic training system for speaker independent continuous Arabic speech recognition system","year":2005,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Bigram; Computer science; Speech recognition; Word error rate; Acoustic model; Vocabulary; Context (archaeology); Grammar; Natural language processing; Artificial intelligence; Language model; Test set; Word (group theory); Speaker recognition; Context-free grammar; Set (abstract data type); Hidden Markov model; Rule-based machine translation; Speech processing; Linguistics; Programming language","score_opus":0.04519592834410268,"score_gpt":0.24455521439190864,"score_spread":0.19935928604780595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1519446688","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06274569,0.000044350676,0.87932456,0.00043132584,0.0010914913,0.0009371871,0.000025862564,0.0014326328,0.0539669],"genre_scores_gemma":[0.82977396,0.0000021073176,0.16828243,0.00024124715,0.00040937224,0.00012526325,0.000009941414,0.000021904907,0.001133755],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99794865,0.00009577855,0.00052031083,0.0005612018,0.00040215004,0.00047193802],"domain_scores_gemma":[0.99869037,0.00028821136,0.00017743804,0.00040144386,0.0002632457,0.00017927124],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008389846,0.00022957702,0.000365905,0.00021463026,0.00018411037,0.0003087305,0.0004899083,0.00014423254,0.000117940865],"category_scores_gemma":[0.00009262291,0.00020416077,0.00018074496,0.00024152355,0.000021351512,0.0005678966,0.000060985414,0.00012238459,0.0011297445],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016392392,0.000055633565,0.000016427864,0.00016253896,0.000044465167,0.000038593294,0.00038653833,0.000016411002,0.0020126433,0.002146679,0.00090386556,0.9941998],"study_design_scores_gemma":[0.006495964,0.0005438181,0.0008058198,0.0018914472,0.00031354403,0.0052484083,0.023930615,0.66081315,0.28051296,0.0008312276,0.01600783,0.0026052415],"about_ca_topic_score_codex":0.000015424552,"about_ca_topic_score_gemma":0.00005241541,"teacher_disagreement_score":0.99159455,"about_ca_system_score_codex":0.00027770482,"about_ca_system_score_gemma":0.00007411586,"threshold_uncertainty_score":0.999648},"labels":[],"label_agreement":null},{"id":"W1525833316","doi":"10.1109/isspit.2003.1341231","title":"On the use of dynamic spectral parameters in speech recognition","year":2004,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Speech recognition; Computer science; Mel-frequency cepstrum; Cepstrum; Feature extraction; Set (abstract data type); Feature (linguistics); Dynamics (music); Speech processing; Pattern recognition (psychology); Artificial intelligence; Task (project management); Linear predictive coding; Feature vector; Acoustics; Engineering","score_opus":0.07952758791153693,"score_gpt":0.2500826680213651,"score_spread":0.17055508010982817,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1525833316","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9548802,0.0000016995593,0.0395537,0.0024324874,0.00009152591,0.00014670972,0.0000024235833,0.000051834126,0.0028394577],"genre_scores_gemma":[0.78477645,0.000011311942,0.21411249,0.0010111508,0.0000030711622,0.0000068350123,0.000001354611,0.000003864071,0.000073443676],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999304,0.00005500533,0.00016467812,0.0001747315,0.00016380298,0.0001377616],"domain_scores_gemma":[0.9992937,0.0003477965,0.000044489632,0.00026008466,0.000026477952,0.000027447548],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016707495,0.000072114584,0.0000880958,0.00012992222,0.000023597058,0.000058647136,0.00024290188,0.00003374512,0.000104947336],"category_scores_gemma":[0.00016245703,0.000048205697,0.000056824334,0.00031829084,0.000033904667,0.00025578262,0.000025690071,0.0000878211,0.0001865688],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028090484,0.00037137824,0.000087052445,0.0000065955837,0.000019469016,0.00005181528,0.0003094067,0.00023559551,0.0018249794,0.036392655,0.0003283501,0.9603446],"study_design_scores_gemma":[0.0014094075,0.0004120186,0.014184589,0.00024154372,0.000011352762,0.0000854425,0.00017558255,0.04046035,0.5076726,0.43463078,0.00018220286,0.000534091],"about_ca_topic_score_codex":0.00016425159,"about_ca_topic_score_gemma":0.0002512698,"teacher_disagreement_score":0.9598105,"about_ca_system_score_codex":0.00005492582,"about_ca_system_score_gemma":0.000023741328,"threshold_uncertainty_score":0.23980267},"labels":[],"label_agreement":null},{"id":"W1527831725","doi":"10.1109/sipnn.1994.344894","title":"A theory on optimal construction of dynamic features of speech for HMM-based speech recognition","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Hidden Markov model; Speech recognition; Computer science; Weighting; Generalization; Domain (mathematical analysis); Dynamic programming; Artificial intelligence; Pattern recognition (psychology); Speech processing; Algorithm; Mathematics","score_opus":0.026997126286302024,"score_gpt":0.2480160064840671,"score_spread":0.22101888019776508,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1527831725","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20090677,0.0000549794,0.7494415,0.0012197859,0.0005671378,0.0008561755,0.000107699954,0.00026207024,0.04658385],"genre_scores_gemma":[0.29637483,0.000014210751,0.7028529,0.00020136894,0.00002756325,0.000019837727,0.000012706704,0.000010104132,0.00048651104],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99891585,0.00008979651,0.00029360678,0.0002845532,0.00024943944,0.0001667336],"domain_scores_gemma":[0.9987178,0.0005164443,0.00018300423,0.00030555468,0.00022827239,0.00004894032],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003484432,0.00013048704,0.00021855252,0.00026704368,0.00005015118,0.000028158971,0.0002687461,0.00009877636,0.00081306143],"category_scores_gemma":[0.00019011453,0.000114075476,0.00016392449,0.00026650337,0.00010013878,0.0001704389,0.000020968884,0.00007729695,0.0000397223],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006866815,0.00013039562,0.0000063264556,0.000035507615,0.000020300848,0.000002681465,0.000039895865,0.00000421019,0.0024759166,0.006482565,0.00042638488,0.99030715],"study_design_scores_gemma":[0.0012921618,0.0006130879,0.00037757942,0.00012910785,0.000035254674,0.00008937157,0.00016391983,0.071653955,0.90325,0.021833248,0.00028324328,0.00027906706],"about_ca_topic_score_codex":0.000008582158,"about_ca_topic_score_gemma":0.000008956503,"teacher_disagreement_score":0.9900281,"about_ca_system_score_codex":0.000029163934,"about_ca_system_score_gemma":0.00002270367,"threshold_uncertainty_score":0.89024526},"labels":[],"label_agreement":null},{"id":"W1529062431","doi":"10.1002/9781118561911.ch7","title":"Voice Biometrics: Speaker Verification and Identification","year":2012,"lang":"en","type":"other","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Université du Québec; Université de Moncton; Université du Québec à Montréal","funders":"","keywords":"Speaker recognition; Biometrics; Speech recognition; Speaker identification; Computer science; Speaker verification; Identification (biology); Artificial intelligence","score_opus":0.025402642770240055,"score_gpt":0.24913427525055878,"score_spread":0.22373163248031874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1529062431","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000064730757,0.00072030316,0.3247443,0.00022701609,0.0005168417,0.00013727689,0.0000062048166,0.00035922707,0.6732824],"genre_scores_gemma":[0.00097372726,0.0005288307,0.08514604,0.00018606895,0.00018897714,0.000019581485,0.000025088848,0.00009031524,0.9128414],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991907,0.000035939458,0.0001462338,0.0003090373,0.00018679968,0.00013127395],"domain_scores_gemma":[0.999227,0.000044424225,0.00014577054,0.00046921227,0.0000343251,0.00007929371],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00021031593,0.00012036957,0.000116038354,0.0007577628,0.000029777677,0.00016907079,0.00030371643,0.00015302913,0.0017965274],"category_scores_gemma":[0.000052228912,0.00010830814,0.00002976908,0.00059111643,0.0000267344,0.00017901116,0.000058018555,0.000052558138,0.0036503281],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.381842e-7,0.000038551905,0.000087121225,0.000025888901,0.000018043489,4.7127585e-7,0.000032124248,2.2111664e-9,0.00030735385,0.009094944,0.33636567,0.6540295],"study_design_scores_gemma":[0.00005886202,0.0000036929064,0.0016163185,0.000015775244,0.000011982011,0.000008403271,0.0000075860466,0.00024279852,0.0010243176,0.00019400987,0.9966402,0.00017602749],"about_ca_topic_score_codex":0.00005331487,"about_ca_topic_score_gemma":0.000011879091,"teacher_disagreement_score":0.66027457,"about_ca_system_score_codex":0.000016916994,"about_ca_system_score_gemma":0.000011947057,"threshold_uncertainty_score":0.99911594},"labels":[],"label_agreement":null},{"id":"W1532958172","doi":"10.1109/icassp.2005.1415194","title":"Factor Analysis Simplified","year":2006,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":94,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Factor (programming language); Programming language","score_opus":0.015439453837839722,"score_gpt":0.22813516016071944,"score_spread":0.2126957063228797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1532958172","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023895832,0.000005604566,0.8551174,0.00043660085,0.000043359854,0.000024624735,0.0000016294821,0.00021425827,0.12026073],"genre_scores_gemma":[0.9236625,7.249312e-7,0.071983404,0.00033681878,0.000024906834,0.0000024225415,0.0000021087346,0.0000017058655,0.0039854264],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9994946,0.000016505355,0.00009790838,0.00016089405,0.000121219404,0.00010887531],"domain_scores_gemma":[0.9996198,0.000056130422,0.000020979636,0.00023879955,0.0000309141,0.000033413304],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00004140367,0.00004961095,0.00008616874,0.00015646595,0.000038239992,0.000100789795,0.00024668404,0.00002272474,0.0011380385],"category_scores_gemma":[0.000008737485,0.000039140363,0.00010376427,0.0006756323,0.0000073544147,0.00013127932,0.000032849126,0.000021191785,0.0003798703],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002969866,0.0002432919,0.027020808,0.0000041154644,0.0003877799,0.00003370693,0.000085135114,0.00006715765,0.004446638,0.28503707,0.016648551,0.6660228],"study_design_scores_gemma":[0.00047725116,0.00003650016,0.6140212,0.0000025684358,0.00015725136,0.000010155138,0.00003639003,0.18672463,0.11509134,0.028911497,0.053777594,0.0007536263],"about_ca_topic_score_codex":0.00011697724,"about_ca_topic_score_gemma":0.00008878026,"teacher_disagreement_score":0.8997666,"about_ca_system_score_codex":0.000008929016,"about_ca_system_score_gemma":0.000007734142,"threshold_uncertainty_score":0.99977505},"labels":[],"label_agreement":null},{"id":"W1543961788","doi":"10.1109/ccece.1995.526599","title":"A syllabic-filler-based continuous speech recognizer for unlimited vocabulary","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Computer science; Speech recognition; Vocabulary; Syllabic verse; Hidden Markov model; Natural language processing; Artificial intelligence; Viterbi algorithm; Word (group theory); Context (archaeology); Audio mining; Speech processing; Acoustic model; Linguistics","score_opus":0.044705110074156264,"score_gpt":0.2341426591592357,"score_spread":0.18943754908507945,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1543961788","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012121791,0.00016028194,0.8751057,0.011224689,0.00078166864,0.0009670579,0.000020144478,0.0012199006,0.09839876],"genre_scores_gemma":[0.100080736,0.000029447874,0.8700136,0.012420241,0.00017118496,0.00017279544,0.000015111111,0.000042701136,0.01705418],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984461,0.000069374204,0.00030774964,0.00050681655,0.00026203136,0.00040789763],"domain_scores_gemma":[0.9984865,0.00047493484,0.00008391597,0.000548754,0.00024335987,0.00016254581],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00028478113,0.00019834371,0.0002633519,0.00020810723,0.00013388468,0.00019119508,0.0005924814,0.00011895507,0.0025585205],"category_scores_gemma":[0.0002657882,0.00017262495,0.00019488331,0.00046624686,0.00003645324,0.00024189577,0.00005706794,0.00009069431,0.0010337955],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015054225,0.00026896282,0.00014533848,0.000017908806,0.00003662004,0.000042117008,0.00006644444,0.000001982315,0.00095128303,0.0009356374,0.12534776,0.87217087],"study_design_scores_gemma":[0.0035953908,0.00044829235,0.00036373304,0.00007419493,0.000045400793,0.00011703802,0.00009099946,0.5633357,0.09067156,0.0026959302,0.3375102,0.0010515542],"about_ca_topic_score_codex":0.000009876185,"about_ca_topic_score_gemma":0.000014562035,"teacher_disagreement_score":0.8711193,"about_ca_system_score_codex":0.000033965818,"about_ca_system_score_gemma":0.000026202377,"threshold_uncertainty_score":0.999744},"labels":[],"label_agreement":null},{"id":"W1556470778","doi":"","title":"Prosodylab-aligner: A tool for forced alignment of laboratory speech","year":2011,"lang":"en","type":"article","venue":"Canadian acoustics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":228,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Computer science; Hidden Markov model; Unix; Scripting language; Speech recognition; Operating system; Process (computing); Computer graphics (images); Software","score_opus":0.02785983580016489,"score_gpt":0.21887743944143986,"score_spread":0.19101760364127499,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1556470778","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12546298,0.00009387691,0.8519852,0.00048056175,0.0013605694,0.0015538373,0.00083000073,0.00019343487,0.018039508],"genre_scores_gemma":[0.6825685,0.000008838217,0.31539896,0.0012311359,0.00006937145,0.00006355424,0.0000070885226,0.000019413344,0.00063313113],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99903715,0.000021848497,0.00023099604,0.00022413467,0.00015035828,0.00033553437],"domain_scores_gemma":[0.9989009,0.00006296746,0.0000812575,0.00040333127,0.00026748577,0.00028403994],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002223141,0.000114842325,0.00015797885,0.00016821829,0.00007453654,0.00004097386,0.00046403462,0.00008784898,0.0001469591],"category_scores_gemma":[0.00016687933,0.000117642216,0.0000607432,0.00023627306,0.000043777298,0.00011889282,0.000028181712,0.000044622735,0.000035353354],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005842448,0.00036489932,0.0019484352,0.0005048794,0.0003145191,0.0003710918,0.0053427448,0.00002689796,0.2149309,0.1914515,0.15494286,0.42974284],"study_design_scores_gemma":[0.003397741,0.0011942707,0.013136529,0.00028035112,0.00030360336,0.00009586182,0.0011230739,0.06995209,0.79813546,0.03039292,0.07931206,0.0026760388],"about_ca_topic_score_codex":0.0015965024,"about_ca_topic_score_gemma":0.0009996244,"teacher_disagreement_score":0.58320457,"about_ca_system_score_codex":0.00012242554,"about_ca_system_score_gemma":0.00063553674,"threshold_uncertainty_score":0.47973102},"labels":[],"label_agreement":null},{"id":"W1560330215","doi":"","title":"Speaker identification by computer and human evaluated on the SPIDRE corpus","year":2000,"lang":"en","type":"article","venue":"Canadian acoustics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Handset; Confusion; Speech recognition; Identification (biology); Set (abstract data type); Speaker identification; Computer science; Speaker recognition; Block (permutation group theory); Speaker diarisation; Telecommunications; Mathematics; Psychology","score_opus":0.019226333859752205,"score_gpt":0.22697263187271016,"score_spread":0.20774629801295796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1560330215","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.911377,0.0000857674,0.058444448,0.011598274,0.0006219488,0.0005434849,0.00012555583,0.00017537968,0.017028145],"genre_scores_gemma":[0.9899771,0.0000227482,0.00141511,0.005675687,0.00009354391,0.0000075258467,0.000019589206,0.000010740196,0.0027779187],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992008,0.000060640854,0.00013899706,0.00022863034,0.00016255083,0.00020835566],"domain_scores_gemma":[0.9992538,0.000078587065,0.000033049157,0.00034973203,0.00006221861,0.00022262661],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020712055,0.00009526373,0.00007724254,0.00007205583,0.00028084358,0.00031782742,0.000333958,0.00007462535,0.00074520323],"category_scores_gemma":[0.00002559566,0.00007728307,0.00002146487,0.00016734694,0.00006098995,0.00007901312,0.000012643468,0.00012828475,0.00043559133],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020902532,0.000037956845,0.0001520161,0.0000069281564,0.000027126738,0.000041959003,0.000268778,0.00010236863,0.0071359877,0.011936622,0.3185427,0.6617455],"study_design_scores_gemma":[0.0007751098,0.00018855887,0.16946135,0.000093731745,0.000078202895,0.00012715778,0.00008231003,0.60828227,0.0023549353,0.0050389795,0.21251799,0.0009993948],"about_ca_topic_score_codex":0.0022016612,"about_ca_topic_score_gemma":0.0011588354,"teacher_disagreement_score":0.6607461,"about_ca_system_score_codex":0.000077186065,"about_ca_system_score_gemma":0.00007192991,"threshold_uncertainty_score":0.81594527},"labels":[],"label_agreement":null},{"id":"W1563583513","doi":"10.1109/cccrv.2004.1301488","title":"Categorization and learning of pen motion using hidden Markov models","year":2004,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Hidden Markov model; Artificial intelligence; Categorization; Categorical variable; Pattern recognition (psychology); Motion (physics); Segmentation; Feature extraction; Representation (politics); Computer vision; Gesture; Speech recognition; Machine learning","score_opus":0.035867179137375055,"score_gpt":0.2423057353273397,"score_spread":0.20643855618996465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1563583513","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13760512,0.000010631587,0.85697794,0.00012027823,0.000028814788,0.000041261614,9.4122214e-8,0.000045568064,0.005170294],"genre_scores_gemma":[0.75755286,0.000008974563,0.24228893,0.000031754567,0.00000749504,6.59305e-7,7.739177e-7,0.0000024317633,0.00010614654],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99957883,0.00003254314,0.00009823917,0.00012182595,0.00010154865,0.000066994995],"domain_scores_gemma":[0.9997783,0.000021031703,0.000044714543,0.0000760888,0.000052448522,0.00002743996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013914467,0.000042579737,0.000062610794,0.00006991137,0.00005964151,0.000043616543,0.00008168221,0.000027390455,0.000019496165],"category_scores_gemma":[0.000024448103,0.000039302275,0.000015554626,0.00012906805,0.00001225975,0.00045943557,0.00004264627,0.000032776967,0.0000025616057],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000040483774,0.000053963373,0.0006289987,0.0000243904,0.000013132276,0.0000033902395,0.0012934988,0.0079393145,0.013580922,0.13111593,0.000007222126,0.8453352],"study_design_scores_gemma":[0.00023449164,0.00002198074,0.00081624795,0.000015937341,0.00000513644,0.000017859076,0.00010804841,0.94462746,0.02555262,0.02850174,0.000011616022,0.00008685421],"about_ca_topic_score_codex":0.00013396032,"about_ca_topic_score_gemma":0.0000040277696,"teacher_disagreement_score":0.9366882,"about_ca_system_score_codex":0.000019106192,"about_ca_system_score_gemma":0.000019232646,"threshold_uncertainty_score":0.16027002},"labels":[],"label_agreement":null},{"id":"W1565000507","doi":"10.1109/icassp.2015.7178921","title":"Multi-lingual speech recognition with low-rank multi-task deep neural networks","year":2015,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Speech recognition; Task (project management); Artificial neural network; Deep neural networks; Rank (graph theory); Artificial intelligence; Time delay neural network; Deep learning; Natural language processing; Pattern recognition (psychology); Mathematics; Engineering","score_opus":0.055310939327397494,"score_gpt":0.266749287209576,"score_spread":0.21143834788217852,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1565000507","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07207038,0.000070485235,0.92373824,0.00033469673,0.0006072402,0.00029813944,0.0000030841134,0.0005901242,0.0022875874],"genre_scores_gemma":[0.39312252,0.000008558476,0.6050326,0.001169192,0.00017071939,0.000024143445,0.000018991559,0.000023097951,0.00043013977],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981462,0.0001378891,0.00029950606,0.00056442275,0.00039049052,0.00046151562],"domain_scores_gemma":[0.99856716,0.00012360957,0.00010883207,0.0004528155,0.00038154473,0.0003660122],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041572397,0.00025320522,0.00023903819,0.00014765518,0.00011882148,0.00027996566,0.0005520573,0.00013159042,0.00013078145],"category_scores_gemma":[0.00014646737,0.00019722334,0.00008530889,0.00046832036,0.00006685548,0.0007123118,0.00012413476,0.0002352204,0.0004939858],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042395586,0.00027666692,0.0004814585,0.000005787963,0.000028517345,0.00015293599,0.00036580296,0.00037465154,0.0001205579,0.000017990715,0.00036946317,0.99776375],"study_design_scores_gemma":[0.0019493422,0.00013851428,0.0007097808,0.00002417589,0.000015945054,0.00020675195,0.0002295239,0.9907641,0.00522188,0.000077915785,0.0002570754,0.0004049894],"about_ca_topic_score_codex":0.000107628526,"about_ca_topic_score_gemma":0.0004665857,"teacher_disagreement_score":0.9973588,"about_ca_system_score_codex":0.000053844884,"about_ca_system_score_gemma":0.0000548209,"threshold_uncertainty_score":0.80425346},"labels":[],"label_agreement":null},{"id":"W156741778","doi":"10.1007/978-3-319-06483-3_38","title":"Effects of Frequency-Based Inter-frame Dependencies on Automatic Speech Recognition","year":2014,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Hidden Markov model; Computer science; Speech recognition; Concatenation (mathematics); Independence (probability theory); Frame (networking); Artificial intelligence; Pattern recognition (psychology); State (computer science); Conditional independence; Natural language processing; Algorithm; Mathematics","score_opus":0.01700488331830339,"score_gpt":0.23309256416691512,"score_spread":0.21608768084861174,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W156741778","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010022722,0.00008000727,0.99267423,0.00037528077,0.001525965,0.000540331,0.000007945408,0.00025703205,0.0035369329],"genre_scores_gemma":[0.13838513,0.000015884129,0.8586818,0.0025041664,0.00022828524,0.000025298812,0.00000898829,0.000043989166,0.00010646335],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961074,0.00012000483,0.0006927039,0.0013010739,0.0012334544,0.0005453791],"domain_scores_gemma":[0.9951483,0.0026142783,0.00052207784,0.001179258,0.00036182403,0.00017427723],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009874711,0.0005805823,0.00074489345,0.0014420693,0.00014334341,0.0003082539,0.0025886286,0.00042633674,0.00009640054],"category_scores_gemma":[0.0006742154,0.0005194502,0.00025231714,0.0005639105,0.00057602883,0.00032218735,0.00036760897,0.0007094472,0.00025467534],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003443433,0.00005047599,0.000008597638,0.00021251569,0.000011762025,0.00007398841,0.00010821653,0.000108330445,0.0006030961,0.0015621268,0.000017058326,0.99724036],"study_design_scores_gemma":[0.0006791469,0.0009042707,0.00014655071,0.0044934284,0.00003793932,0.00008840016,2.123711e-7,0.46230882,0.24726276,0.2827017,0.00022179098,0.0011549849],"about_ca_topic_score_codex":0.000022807286,"about_ca_topic_score_gemma":0.00004524643,"teacher_disagreement_score":0.9960854,"about_ca_system_score_codex":0.0002668831,"about_ca_system_score_gemma":0.00044664642,"threshold_uncertainty_score":0.9997257},"labels":[],"label_agreement":null},{"id":"W1573256281","doi":"10.1109/icassp.1987.1169587","title":"Specifying intonation in a text-to-speech system using only a small dictionary","year":2005,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Computer science; Intonation (linguistics); Sentence; Parsing; Natural language processing; Artificial intelligence; Speech synthesis; Set (abstract data type); Speech recognition; Linguistics; Programming language","score_opus":0.046446059321591515,"score_gpt":0.2596009731072042,"score_spread":0.2131549137856127,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1573256281","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26814145,0.000025557943,0.6726023,0.0015370724,0.00024231052,0.0002521607,0.000001059795,0.00037382098,0.056824293],"genre_scores_gemma":[0.5822755,0.000002124932,0.41667917,0.00050618657,0.0001176884,0.000007975921,7.081088e-7,0.000006589561,0.00040401024],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989338,0.000061919025,0.00026557563,0.00031257432,0.00022480561,0.00020133388],"domain_scores_gemma":[0.999491,0.00008229397,0.000045718447,0.00022239772,0.00007050782,0.00008813383],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003453519,0.00010136062,0.00012271879,0.00042751926,0.00007738689,0.00012535013,0.00031187528,0.000054581396,0.00010855783],"category_scores_gemma":[0.000038797058,0.000097842756,0.00004391991,0.0006331411,0.000008271727,0.0003907318,0.00010744054,0.00008405578,0.00042531113],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006046777,0.00009901856,0.0012760077,0.000014477522,0.000006537479,0.000032003947,0.0004000863,0.00024598383,0.0017177943,0.020468721,0.00013839192,0.97559494],"study_design_scores_gemma":[0.00063015346,0.00004000458,0.014755446,0.0002464913,0.0000057911984,0.0005503319,0.00055654376,0.95729554,0.012490599,0.0003215085,0.012674356,0.00043323572],"about_ca_topic_score_codex":0.00009873188,"about_ca_topic_score_gemma":0.00042506403,"teacher_disagreement_score":0.9751617,"about_ca_system_score_codex":0.0003592836,"about_ca_system_score_gemma":0.00007085021,"threshold_uncertainty_score":0.5466656},"labels":[],"label_agreement":null},{"id":"W1577476315","doi":"","title":"Better analysis for automatic speech recognition","year":2002,"lang":"en","type":"article","venue":"Canadian acoustics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"","keywords":"Speech recognition; Computer science; Linear predictive coding; Speech coding; Linear prediction; Speech processing; Coding (social sciences); Filter (signal processing); Voice activity detection; Ideal (ethics); Artificial intelligence; Mathematics; Computer vision","score_opus":0.046145550814051445,"score_gpt":0.22786070183211787,"score_spread":0.18171515101806643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1577476315","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05018018,0.00004373008,0.9365475,0.0034693056,0.00046371523,0.00032910303,0.00019818601,0.00022189999,0.00854638],"genre_scores_gemma":[0.35264787,0.000013804294,0.6407476,0.0053472295,0.000158614,0.000045444158,0.000043459833,0.000016904274,0.0009790699],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990096,0.000027013339,0.00019515825,0.00026202292,0.00014325685,0.00036296307],"domain_scores_gemma":[0.998926,0.0001575033,0.000054253418,0.00035012234,0.00014447923,0.00036762888],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00014311342,0.000114829214,0.00017172602,0.00060568564,0.00015358037,0.00022121785,0.00035464927,0.00009017743,0.001441942],"category_scores_gemma":[0.00019169302,0.00012289772,0.00014392969,0.00082663156,0.000023498971,0.00018324053,0.000014113007,0.00006968816,0.00063152617],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.9562785e-7,0.0000149677,0.00018168053,0.000011364688,0.00011640889,0.000032866817,0.00007002311,0.000007786414,0.00016795598,0.00008661138,0.02393258,0.97537756],"study_design_scores_gemma":[0.00017694764,0.000026339116,0.004341494,0.000010655803,0.0002798452,0.000020639893,0.00002650571,0.9863287,0.0003572226,0.002427692,0.005722532,0.00028140115],"about_ca_topic_score_codex":0.0010545173,"about_ca_topic_score_gemma":0.003405755,"teacher_disagreement_score":0.9863209,"about_ca_system_score_codex":0.00014615859,"about_ca_system_score_gemma":0.000059738064,"threshold_uncertainty_score":0.9994709},"labels":[],"label_agreement":null},{"id":"W1577971346","doi":"10.1016/j.patrec.2008.12.013","title":"-Gaussian mixture modelling for speaker recognition","year":2009,"lang":"en","type":"article","venue":"Pattern Recognition Letters","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Mixture model; Computer science; Speech recognition; Speaker recognition; Set (abstract data type); Pattern recognition (psychology); Gaussian process; Artificial intelligence; Gaussian; Process (computing)","score_opus":0.04911657388391709,"score_gpt":0.24529012247867654,"score_spread":0.19617354859475944,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1577971346","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039849747,0.000023863802,0.93775487,0.019164369,0.0005602782,0.00056289945,0.000084708176,0.00042890327,0.0015703668],"genre_scores_gemma":[0.50163686,0.00007537861,0.40506223,0.091018446,0.0011214449,0.00025252078,0.0006626871,0.00006298618,0.0001074414],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99788404,0.000109263754,0.00044487166,0.00069968996,0.00033316985,0.0005289786],"domain_scores_gemma":[0.9988781,0.0001791026,0.00019561144,0.00038577808,0.00017650315,0.00018488713],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003506856,0.0003066986,0.00027156112,0.0003146871,0.00022716705,0.00032709425,0.00043959165,0.00020222245,0.00025475887],"category_scores_gemma":[0.000048552305,0.00031147565,0.00026818295,0.00030166935,0.000030144876,0.0008522031,0.000028209839,0.0002948461,0.0008409031],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017832459,0.000091412396,0.000031047977,0.000019812025,0.000024069786,0.00001923974,0.00019318373,0.000025711848,0.0026935153,0.000018454586,0.004810108,0.9920556],"study_design_scores_gemma":[0.011352897,0.0013842188,0.004782643,0.0018068411,0.0004810709,0.0009157746,0.0004612551,0.586553,0.18630186,0.15030017,0.048034806,0.0076255],"about_ca_topic_score_codex":0.000011542767,"about_ca_topic_score_gemma":0.000004310839,"teacher_disagreement_score":0.98443013,"about_ca_system_score_codex":0.000068116904,"about_ca_system_score_gemma":0.000020942496,"threshold_uncertainty_score":0.99993706},"labels":[],"label_agreement":null},{"id":"W1582122176","doi":"10.5772/6376","title":"Practical Issues of Building Robust HMM Models Using HTK and SPHINX Systems","year":2008,"lang":"en","type":"book-chapter","venue":"InTech eBooks","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Sphinx; Hidden Markov model; Computer science; Artificial intelligence; Pattern recognition (psychology); Geography","score_opus":0.15384614204963004,"score_gpt":0.31019928073344255,"score_spread":0.1563531386838125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1582122176","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00018889557,0.0007364137,0.74381775,0.000086571,0.0003516937,0.00029456298,0.000011326674,0.00016262046,0.25435016],"genre_scores_gemma":[0.09995782,0.00052174885,0.7205279,0.00019147036,0.00048732193,0.000024112871,0.0000029103855,0.00014845753,0.17813829],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982289,0.00003761705,0.00051463355,0.0005255243,0.00046194345,0.00023135003],"domain_scores_gemma":[0.9985383,0.0002192804,0.00035759507,0.00051598105,0.00024945964,0.00011936674],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00026923465,0.00031858354,0.0005630816,0.00031562347,0.00010115773,0.00015282034,0.00041993504,0.0003778768,0.000028320406],"category_scores_gemma":[0.000058881393,0.00030432062,0.00013761656,0.000020931897,0.00019851812,0.00023024836,0.00031812326,0.00039110478,0.000013079069],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006259136,0.00008936818,0.0000043898117,0.00065852393,0.00066742074,0.0013327764,0.0017658693,0.0001464536,0.023939501,0.82794803,0.0031090223,0.14027604],"study_design_scores_gemma":[0.00082756986,0.00035313572,0.0000010521505,0.0069813384,0.0002943657,0.0072396277,0.00019107138,0.58988726,0.17275752,0.10528469,0.113536514,0.0026458648],"about_ca_topic_score_codex":0.00011128033,"about_ca_topic_score_gemma":0.0000038104527,"teacher_disagreement_score":0.72266334,"about_ca_system_score_codex":0.00007473767,"about_ca_system_score_gemma":0.00014128002,"threshold_uncertainty_score":0.9999409},"labels":[],"label_agreement":null},{"id":"W1588166307","doi":"10.1007/978-3-540-24840-8_61","title":"An Investigation of Grammar Design in Natural-Language Speech Recognition","year":2004,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Robustness (evolution); Speech recognition; Natural language; Natural language processing; Grammar; Artificial intelligence; Linguistics","score_opus":0.02942735014565632,"score_gpt":0.2518051128363049,"score_spread":0.2223777626906486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1588166307","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0049351,0.00023377212,0.99272174,0.00025573434,0.0007726784,0.0005044797,0.0000054509705,0.00012371833,0.0004473323],"genre_scores_gemma":[0.2963299,0.000030945244,0.7028617,0.0005838159,0.00012367641,0.000008155793,0.000016504802,0.000021396823,0.000023897528],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99677384,0.00012518205,0.00063518976,0.0011661181,0.0008534391,0.00044621428],"domain_scores_gemma":[0.99785775,0.00047448033,0.00035900387,0.0008933446,0.00026421025,0.00015118928],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014046172,0.00040716355,0.00047950255,0.0015296583,0.00008899847,0.0002544682,0.0018830373,0.00032706978,0.00005002758],"category_scores_gemma":[0.00015147975,0.00039427623,0.00009964561,0.0009408334,0.00049474475,0.0010866825,0.0002331492,0.000650539,0.000037930306],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007718771,0.00002738825,0.000036266378,0.00003105355,0.000004094622,0.000108139415,0.0012410813,0.0014210939,0.002603876,0.0007397945,0.0000019608422,0.9937775],"study_design_scores_gemma":[0.0006233855,0.00033393237,0.0007701339,0.0012658981,0.000011261849,0.00012628191,0.0000019823547,0.2881589,0.18476316,0.5229996,0.000009053011,0.0009364625],"about_ca_topic_score_codex":0.00011462807,"about_ca_topic_score_gemma":0.00019849824,"teacher_disagreement_score":0.99284106,"about_ca_system_score_codex":0.00035927416,"about_ca_system_score_gemma":0.0006101287,"threshold_uncertainty_score":0.9998509},"labels":[],"label_agreement":null},{"id":"W1589469711","doi":"10.5772/6388","title":"Normalization and Transformation Techniques for Robust Speaker Recognition","year":2008,"lang":"en","type":"book-chapter","venue":"InTech eBooks","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Speaker recognition; Normalization (sociology); Speech recognition; Computer science; Speaker diarisation; Identity (music); Task (project management); Artificial intelligence; Pattern recognition (psychology); Frame (networking); Feature (linguistics); Transformation (genetics); Linguistics; Engineering","score_opus":0.05414298100150217,"score_gpt":0.23917453223290874,"score_spread":0.18503155123140658,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1589469711","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000006994447,0.000038824943,0.600107,0.000096379146,0.00010272287,0.0005741452,0.000034345056,0.00033992113,0.39869964],"genre_scores_gemma":[0.0068973512,0.0018972913,0.7448815,0.002142523,0.000711577,0.0007301043,0.00056008855,0.00022811379,0.24195147],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988253,0.000014856042,0.0004001766,0.000369678,0.00021735724,0.00017264736],"domain_scores_gemma":[0.9991191,0.000068166904,0.00019566779,0.0002522849,0.00029514657,0.00006963786],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00019043153,0.00027027784,0.00025756922,0.00035457633,0.00014921676,0.00012185574,0.00024066099,0.00037694772,0.00005345308],"category_scores_gemma":[0.000026312531,0.0002733122,0.00013722514,0.000019239384,0.00007810408,0.0002904213,0.00004260146,0.00018311702,0.000049070415],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012628905,0.0000061693286,1.3508603e-7,0.00005871662,0.000022546714,0.0000049990526,0.00031345463,2.8494242e-8,0.0005326976,0.0062129926,0.00069143914,0.99214417],"study_design_scores_gemma":[0.0004450094,0.00026422727,0.0000028447153,0.00077232096,0.00007062665,0.00041909644,0.000019032736,0.00219486,0.28871804,0.0724334,0.6337292,0.0009313384],"about_ca_topic_score_codex":0.0000049867217,"about_ca_topic_score_gemma":0.000017217084,"teacher_disagreement_score":0.99121284,"about_ca_system_score_codex":0.00006106867,"about_ca_system_score_gemma":0.000050950395,"threshold_uncertainty_score":0.9999719},"labels":[],"label_agreement":null},{"id":"W1597208282","doi":"10.1109/icassp.2015.7178806","title":"Speaker change point detection using deep neural nets","year":2015,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Speaker diarisation; Change detection; Computer science; Speech recognition; Frame (networking); Artificial neural network; Point (geometry); Set (abstract data type); Speaker recognition; Test set; Speech processing; Word error rate; Voice activity detection; Artificial intelligence; Mathematics; Telecommunications","score_opus":0.1755712714818029,"score_gpt":0.28642138628171554,"score_spread":0.11085011479991264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1597208282","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17163953,0.000038671114,0.81670994,0.0009791023,0.00087936403,0.0001219169,2.1625648e-7,0.00027589814,0.00935535],"genre_scores_gemma":[0.9410715,0.0000010940277,0.0570792,0.0015995343,0.00014025235,0.0000056243157,2.8885248e-7,0.000005527673,0.00009699375],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993509,0.0000448496,0.00009755156,0.00018020821,0.00016666258,0.00015983391],"domain_scores_gemma":[0.99958175,0.000018756173,0.000031222375,0.00019469627,0.00007241958,0.00010116423],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016379882,0.00007193141,0.00007096596,0.000081821316,0.000047013757,0.00010725593,0.0001767973,0.00003427313,0.000091796486],"category_scores_gemma":[0.000037309197,0.000060809856,0.000037890346,0.00019682584,0.000011298931,0.0005770597,0.00007795575,0.00004648437,0.000242102],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003439883,0.000022474958,0.000161135,0.0000013234311,0.0000040663226,0.000016747108,0.00040599328,0.000006717212,0.0008604237,0.0004283595,0.00009211731,0.9979972],"study_design_scores_gemma":[0.00021551929,0.0000458017,0.0021289543,0.0000035824644,0.0000037713476,0.00015271392,0.0001026932,0.9753251,0.018454617,0.0015050316,0.0019078773,0.00015435558],"about_ca_topic_score_codex":0.00015270195,"about_ca_topic_score_gemma":0.00012636956,"teacher_disagreement_score":0.99784285,"about_ca_system_score_codex":0.000041906616,"about_ca_system_score_gemma":0.000009307564,"threshold_uncertainty_score":0.31118122},"labels":[],"label_agreement":null},{"id":"W1599370399","doi":"10.22215/etd/2005-07974","title":"Speaker recognition in reverberant environments","year":2005,"lang":"en","type":"dissertation","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Reverberation; Speech recognition; Autoregressive model; Covariance; Computer science; Measure (data warehouse); Divergence (linguistics); Mixture model; Perceptron; Hidden Markov model; Pattern recognition (psychology); Speaker recognition; Artificial intelligence; Acoustics; Artificial neural network; Mathematics; Statistics","score_opus":0.020984961485154177,"score_gpt":0.24283301073382352,"score_spread":0.22184804924866935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1599370399","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043398924,0.00021966838,0.012158259,0.00053174037,0.0016365909,0.0007113337,0.000016520082,0.00023243477,0.9410945],"genre_scores_gemma":[0.05584168,0.0035236035,0.45150512,0.0043258416,0.00089496846,0.00044652485,0.0035662325,0.00017364438,0.47972238],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985713,0.00006295525,0.00035058352,0.0004748989,0.0003154407,0.00022482107],"domain_scores_gemma":[0.9994318,0.000049212853,0.000118232354,0.00031797995,0.00001716976,0.00006563049],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00018640359,0.00020735266,0.00022211332,0.00028880747,0.000035655536,0.000086477674,0.00038619566,0.00022702519,0.0010595344],"category_scores_gemma":[0.000031552776,0.00020338409,0.000091393296,0.00019626683,0.000006949295,0.000356035,0.0000239061,0.00021129986,0.0081977155],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009889969,0.00011296955,0.000020876698,0.000013499333,0.000011055092,0.000027120917,0.00020641265,3.7245204e-7,0.0004285803,0.00019631146,0.001449787,0.9975231],"study_design_scores_gemma":[0.006227511,0.0003298311,0.23217763,0.0028380768,0.0001820483,0.00018614317,0.0026728641,0.01102822,0.37431923,0.03485111,0.32773396,0.0074533643],"about_ca_topic_score_codex":0.00005657619,"about_ca_topic_score_gemma":0.0009980906,"teacher_disagreement_score":0.99006975,"about_ca_system_score_codex":0.00011400697,"about_ca_system_score_gemma":0.000040058363,"threshold_uncertainty_score":0.9998536},"labels":[],"label_agreement":null},{"id":"W1600818689","doi":"10.1109/icassp.1983.1172259","title":"Further experiments in text-independent speaker recognition over communications channels","year":2005,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Speech recognition; Computer science; Set (abstract data type); Noise (video); Cepstrum; Variation (astronomy); Speaker recognition; Mel-frequency cepstrum; Telephony; Data set; Pattern recognition (psychology); Feature extraction; Artificial intelligence; Telecommunications","score_opus":0.06782045268047239,"score_gpt":0.30437250612255395,"score_spread":0.23655205344208158,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1600818689","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24039869,0.00049945683,0.12636797,0.024560021,0.0008668648,0.0010925828,0.000011776034,0.00082498335,0.6053777],"genre_scores_gemma":[0.91343117,0.00007341941,0.08262402,0.0020723613,0.00006805794,0.000068376066,0.000007395634,0.0000103621915,0.0016448699],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99897826,0.000098363154,0.00024114792,0.00025634695,0.00021561245,0.0002102759],"domain_scores_gemma":[0.9990434,0.00007429081,0.000051676652,0.00071010797,0.00004572375,0.00007476797],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00024171663,0.0001086469,0.00010985372,0.00017681342,0.00006129813,0.00012291533,0.0006973567,0.00006326135,0.0026043556],"category_scores_gemma":[0.000021790467,0.000101486905,0.000053834356,0.0002483933,0.00002730794,0.0006022615,0.00022287862,0.00010802681,0.002164787],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005804247,0.00056972273,0.00045064703,0.0000021237377,0.000017066397,0.0000053072217,0.0018835553,0.0000042963184,0.0016935106,0.0034027942,0.0016062342,0.99035895],"study_design_scores_gemma":[0.007253539,0.00022018253,0.045522276,0.00031304214,0.00003089765,0.00015519708,0.0028581782,0.34769702,0.3186221,0.022461167,0.25205246,0.002813929],"about_ca_topic_score_codex":0.00006606192,"about_ca_topic_score_gemma":0.00024236956,"teacher_disagreement_score":0.987545,"about_ca_system_score_codex":0.000080359016,"about_ca_system_score_gemma":0.000020631545,"threshold_uncertainty_score":0.99861217},"labels":[],"label_agreement":null},{"id":"W1603105762","doi":"10.1109/icassp.2015.7178988","title":"Document-specific context plsa language model for speech recognition","year":2015,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Bigram; Perplexity; Computer science; Natural language processing; Artificial intelligence; Language model; Word error rate; Word (group theory); Context (archaeology); Speech recognition; Probabilistic latent semantic analysis; Context model; Probabilistic logic; Linguistics","score_opus":0.10465832487019365,"score_gpt":0.29118332861545226,"score_spread":0.1865250037452586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1603105762","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0119363945,0.00012178708,0.9544692,0.0012396266,0.00030529528,0.00034039712,0.00001552597,0.00032457782,0.031247165],"genre_scores_gemma":[0.26009348,0.000026496356,0.72868323,0.0021591666,0.000145953,0.000102556056,0.00003270095,0.000017953747,0.008738475],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989771,0.00003536247,0.0001980702,0.00031948445,0.00023672804,0.00023320799],"domain_scores_gemma":[0.9991371,0.000107020634,0.000054499782,0.00032072674,0.00021013623,0.00017050236],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00041819087,0.000117989315,0.00013905147,0.00010173483,0.00005816101,0.00019578314,0.00036654406,0.00006515172,0.00019269154],"category_scores_gemma":[0.000084311716,0.000103610335,0.000083949126,0.00014273654,0.000020317666,0.0005851086,0.00006336083,0.000058311387,0.0008927623],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016068656,0.00004078209,0.0000029941557,0.0000037779246,0.000008215231,0.000005954292,0.00075912813,0.0000035171406,0.00036915427,0.0062981136,0.03656261,0.9559297],"study_design_scores_gemma":[0.0029535359,0.00018091638,0.000014425745,0.000038511815,0.000015715552,0.00007606411,0.0023824663,0.695403,0.13402355,0.12051704,0.043673072,0.00072170974],"about_ca_topic_score_codex":0.000023898738,"about_ca_topic_score_gemma":0.000040200764,"teacher_disagreement_score":0.95520794,"about_ca_system_score_codex":0.000054834698,"about_ca_system_score_gemma":0.000055482335,"threshold_uncertainty_score":0.99988514},"labels":[],"label_agreement":null},{"id":"W1607690733","doi":"10.1109/ccece.2015.7129496","title":"A study on dimensions of feature space for text-independent speaker verification systems","year":2015,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Normalization (sociology); Computer science; TIMIT; Mel-frequency cepstrum; Speech recognition; Pattern recognition (psychology); Feature vector; Artificial intelligence; Feature extraction; Feature (linguistics); Speaker verification; Speaker recognition; Hidden Markov model","score_opus":0.07998948450069451,"score_gpt":0.2978836968724527,"score_spread":0.21789421237175818,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1607690733","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29905537,0.000106445084,0.6516774,0.004866249,0.0022100818,0.0037504004,0.00002037994,0.0004267178,0.037886955],"genre_scores_gemma":[0.98185515,0.0000011651969,0.014697801,0.0000689766,0.000026714562,0.000056850102,0.0000016248068,0.000005727905,0.00328599],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99915457,0.000064658045,0.00013195496,0.00023763892,0.00030350912,0.000107668726],"domain_scores_gemma":[0.99910784,0.00010827201,0.0000746652,0.00041602514,0.00020324565,0.00008995678],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003772208,0.00007928347,0.00013261031,0.000085692045,0.0000383458,0.00005832356,0.00024226833,0.000042942393,0.000004795541],"category_scores_gemma":[0.00010250467,0.000052609,0.00004288255,0.00016079633,0.000008573112,0.00010817004,0.00003994871,0.00004467375,0.00008331578],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046850485,0.010777057,0.01381884,0.00013941432,0.0006049061,0.000067494344,0.020533511,0.0006553102,0.014492164,0.44451594,0.3732936,0.12063326],"study_design_scores_gemma":[0.022940634,0.013408987,0.13357764,0.0006333736,0.0004231476,0.00032708736,0.10398801,0.28016353,0.18783197,0.00782333,0.24515024,0.003732051],"about_ca_topic_score_codex":0.000033599736,"about_ca_topic_score_gemma":0.000017098742,"teacher_disagreement_score":0.6827998,"about_ca_system_score_codex":0.00003465728,"about_ca_system_score_gemma":0.000043407803,"threshold_uncertainty_score":0.21453327},"labels":[],"label_agreement":null},{"id":"W1618069598","doi":"10.1109/icassp.1995.479661","title":"On the use of stochastic inference networks for representing multiple word pronunciations","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Science Council","keywords":"Computer science; Inference; Vocabulary; Speech recognition; Syllabic verse; Word (group theory); Artificial intelligence; Natural language processing; Linguistics","score_opus":0.1777085634039263,"score_gpt":0.2724514577590311,"score_spread":0.09474289435510483,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1618069598","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005766732,0.000005235121,0.9916926,0.0012338749,0.00008145915,0.0003106401,0.0000018028082,0.00006303121,0.00084461574],"genre_scores_gemma":[0.94006324,0.0000017271149,0.058485802,0.0004826014,0.000023834267,0.00007376545,6.0594795e-7,0.0000038798253,0.00086453126],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993823,0.000037547095,0.00015619828,0.00016119968,0.00012722505,0.00013549482],"domain_scores_gemma":[0.995294,0.004148086,0.000079756355,0.0003383773,0.00011225684,0.000027545642],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014559974,0.000058057853,0.000074212214,0.000043491753,0.00011829624,0.0000934407,0.0002699324,0.000026987334,0.00014727408],"category_scores_gemma":[0.0026560193,0.00003786965,0.00005500077,0.00020329273,0.000021296202,0.00017965058,0.000056352896,0.00005391868,0.000020787886],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013217896,0.00037561185,0.0008813193,0.000011726401,0.00005538859,0.0000010832642,0.0007480549,0.062058013,0.00012591676,0.22238682,0.02235267,0.6909902],"study_design_scores_gemma":[0.000087979475,0.00001659586,0.0003823607,0.000017534845,0.0000028707263,4.904343e-7,0.000012431094,0.9974859,0.00023181003,0.0014116376,0.00029827835,0.000052120035],"about_ca_topic_score_codex":0.00001378598,"about_ca_topic_score_gemma":0.00002229973,"teacher_disagreement_score":0.9354279,"about_ca_system_score_codex":0.000008857581,"about_ca_system_score_gemma":0.0000065425747,"threshold_uncertainty_score":0.3179695},"labels":[],"label_agreement":null},{"id":"W1629536855","doi":"10.1109/icassp.1995.479602","title":"Improved speech modeling and recognition using multi-dimensional articulatory states as primitive speech units","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; TIMIT; Speech recognition; Asynchronous communication; Feature (linguistics); Context (archaeology); Task (project management); Artificial intelligence; Hidden Markov model; Natural language processing","score_opus":0.09840003892361633,"score_gpt":0.2645703920844242,"score_spread":0.16617035316080786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1629536855","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8282274,0.000090284746,0.16977839,0.00017390438,0.00013616274,0.00022786252,0.0000067017995,0.00021660588,0.0011426616],"genre_scores_gemma":[0.5021572,0.000044611184,0.4964846,0.00092345505,0.00004054264,0.000007222325,0.000007826326,0.000017672814,0.00031687494],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998509,0.000094367155,0.00029701102,0.0004980853,0.00027356346,0.0003280045],"domain_scores_gemma":[0.99894834,0.0001410117,0.00007765564,0.00023327475,0.00041045417,0.00018924753],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026296233,0.00020109637,0.00018924018,0.00018644548,0.00020235871,0.00018287024,0.00016231346,0.00009867394,0.00040724932],"category_scores_gemma":[0.00015925831,0.00018535629,0.000047486345,0.00036158794,0.000050634368,0.0006865455,0.00013987574,0.00014988244,0.0001913324],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025034968,0.00043303866,0.00014703126,0.000032237458,0.0001124122,0.00017906415,0.00132944,0.0005935315,0.05506352,0.00032827808,0.00013893734,0.9416175],"study_design_scores_gemma":[0.0005019426,0.000041144798,0.000046832076,0.000042639855,0.000016371367,0.0002279675,0.00017271361,0.94262975,0.054726582,0.001297662,0.000020993652,0.00027538062],"about_ca_topic_score_codex":0.0001710157,"about_ca_topic_score_gemma":0.000026472475,"teacher_disagreement_score":0.9420362,"about_ca_system_score_codex":0.000044681205,"about_ca_system_score_gemma":0.000039784663,"threshold_uncertainty_score":0.75586104},"labels":[],"label_agreement":null},{"id":"W1633122917","doi":"10.5281/zenodo.42857","title":"Lda-Based Lm Adaptation Using Latent Semantic Marginals And Minimum Discriminant Information","year":2012,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Latent Dirichlet allocation; Perplexity; Computer science; Artificial intelligence; Probabilistic latent semantic analysis; Topic model; Linear discriminant analysis; Cluster analysis; Language model; Latent variable; Hidden Markov model; Word (group theory); Pattern recognition (psychology); Decoding methods; Word error rate; Speech recognition; Natural language processing; Mathematics; Algorithm","score_opus":0.0771586839017472,"score_gpt":0.25201567795297825,"score_spread":0.17485699405123106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1633122917","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10919992,0.00007982138,0.8772443,0.0011582221,0.00021569367,0.0004475152,0.00004038531,0.00064939994,0.010964731],"genre_scores_gemma":[0.9851835,0.000023908013,0.014096486,0.00025242876,0.000051435254,5.0024244e-8,0.00017730394,0.0001635066,0.000051396015],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.998795,0.00020849564,0.00021968118,0.00017279152,0.0003042056,0.0002998326],"domain_scores_gemma":[0.9991519,0.00003014884,0.000112883405,0.00025734634,0.00027926647,0.00016846663],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006485815,0.000106207735,0.00010083985,0.00026292528,0.00096527726,0.00082340476,0.0004202537,0.000041671137,0.0008515257],"category_scores_gemma":[0.00026594277,0.00010267702,0.000032183314,0.0003494119,0.00005878842,0.0015537112,0.00037398358,0.00009352426,0.0015890726],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000429644,0.0001976255,0.000047476522,0.00014540966,0.000030651543,0.0000057678035,0.0050055003,0.00015506835,0.004252113,0.00922806,0.007878941,0.9730104],"study_design_scores_gemma":[0.0011114978,0.00023140696,0.009163033,0.00013582976,0.00004743315,0.00028682363,0.0011805946,0.44772854,0.0055708736,0.0004145574,0.5335715,0.0005579495],"about_ca_topic_score_codex":0.000014557527,"about_ca_topic_score_gemma":1.3341781e-7,"teacher_disagreement_score":0.97245246,"about_ca_system_score_codex":0.00007631421,"about_ca_system_score_gemma":0.000004510755,"threshold_uncertainty_score":0.9991883},"labels":[],"label_agreement":null},{"id":"W164170074","doi":"10.21437/interspeech.2005-141","title":"Augmented state space acoustic decoding for modeling local variability in speech","year":2005,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Normalization (sociology); Speech recognition; Decoding methods; Image warping; Word error rate; Viterbi algorithm; Hidden Markov model; Dynamic time warping; Viterbi decoder; Artificial intelligence; Vocal tract; Language model; Context (archaeology); Computation; Pattern recognition (psychology); Algorithm","score_opus":0.03088791563739247,"score_gpt":0.2718763472945246,"score_spread":0.24098843165713213,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W164170074","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03965038,0.00000537052,0.956047,0.001094586,0.000092798175,0.0002359252,0.0000023611185,0.0001483416,0.0027232692],"genre_scores_gemma":[0.57400775,0.0000036996144,0.42551044,0.00023288565,0.000019630026,0.000015509144,7.5012883e-7,0.000004549924,0.00020481258],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988529,0.00006724944,0.00026262188,0.0003563536,0.00015820244,0.0003026426],"domain_scores_gemma":[0.99916357,0.00037387785,0.00003206508,0.0002658468,0.000080527265,0.00008410585],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010988917,0.000107300824,0.00014555377,0.00011527999,0.000058822337,0.000086843465,0.0003016625,0.000044644137,0.00010648039],"category_scores_gemma":[0.00022587858,0.000099461664,0.000055537836,0.00022877892,0.000015814689,0.00035646767,0.000080104386,0.000079862635,0.000053820695],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015429745,0.00011932896,0.00009543328,0.000015628542,0.000007687684,0.0000042931338,0.00016521133,0.047391657,0.0009237945,0.0022933204,0.00015311627,0.9488151],"study_design_scores_gemma":[0.0003496679,0.000013942088,0.000024173154,0.000014106377,0.000002901577,0.000005600933,0.000047050824,0.9832746,0.010273746,0.00569645,0.00016694982,0.00013081056],"about_ca_topic_score_codex":0.00005186364,"about_ca_topic_score_gemma":0.00036242712,"teacher_disagreement_score":0.9486843,"about_ca_system_score_codex":0.00015229636,"about_ca_system_score_gemma":0.000056479326,"threshold_uncertainty_score":0.4055929},"labels":[],"label_agreement":null},{"id":"W165087859","doi":"10.21437/interspeech.2010-529","title":"Novel weighting scheme for unsupervised language model adaptation using latent dirichlet allocation","year":2010,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Latent Dirichlet allocation; Computer science; Weighting; Scheme (mathematics); Hierarchical Dirichlet process; Adaptation (eye); Artificial intelligence; Language model; Latent variable; Topic model; Machine learning; Natural language processing; Mathematics","score_opus":0.07224011613154238,"score_gpt":0.2863947272958288,"score_spread":0.21415461116428644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W165087859","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18814567,0.0000044251638,0.81001776,0.00039002852,0.00011760719,0.00015762106,0.0000029434418,0.00013552124,0.0010284006],"genre_scores_gemma":[0.37639326,6.170989e-7,0.6230928,0.00025604523,0.000040056417,0.000014436344,0.000006593462,0.0000063886355,0.00018982055],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992669,0.000008730485,0.00016690094,0.00023867154,0.0001542303,0.00016455463],"domain_scores_gemma":[0.99944746,0.00006419055,0.00005543542,0.00023031136,0.00014391444,0.000058676524],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002435344,0.00008899301,0.00008424805,0.000087351684,0.00011565152,0.000114525086,0.000241838,0.00006201463,0.00003473044],"category_scores_gemma":[0.00009125778,0.00007952763,0.00005514065,0.00015042505,0.000010820041,0.00041869763,0.000042105512,0.000071384864,0.00001652844],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000032141481,0.00005736737,0.000028301953,0.000008469308,0.000007865139,3.4357254e-7,0.00066355243,0.00068916887,0.91043556,0.020343509,0.00004440355,0.06771824],"study_design_scores_gemma":[0.00027409568,0.0000066887364,0.00006879125,0.000006330805,0.000004862597,0.0000048550396,0.00008470207,0.9316506,0.06718415,0.0005452282,0.00005552585,0.00011420152],"about_ca_topic_score_codex":0.000053989672,"about_ca_topic_score_gemma":0.00006301288,"teacher_disagreement_score":0.9309614,"about_ca_system_score_codex":0.000018519011,"about_ca_system_score_gemma":0.000053245138,"threshold_uncertainty_score":0.32430425},"labels":[],"label_agreement":null},{"id":"W1663228875","doi":"10.1109/icslp.1996.606915","title":"New developments in the INRS continuous speech recognition system","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Speech recognition; Computer science; Phone; Vocabulary; Artificial intelligence; Pruning; Task (project management); Tree (set theory); Hidden Markov model; Graph; Natural language processing; Pattern recognition (psychology); Mathematics; Linguistics; Theoretical computer science","score_opus":0.04481888551069555,"score_gpt":0.21890995217122564,"score_spread":0.1740910666605301,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1663228875","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.055828575,0.000083074585,0.09282968,0.0027535288,0.00065376,0.0005590087,0.000001693596,0.00049300084,0.8467977],"genre_scores_gemma":[0.69568765,0.0000248316,0.2974153,0.0019895625,0.00007973271,0.000031375013,0.0000025493928,0.0000086275495,0.004760363],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99898124,0.0001105229,0.00022196608,0.0002208317,0.0002693427,0.00019611101],"domain_scores_gemma":[0.9994952,0.00012259709,0.000047017616,0.00023746262,0.00004196159,0.00005575],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00035440832,0.00009363606,0.00011090969,0.000121646604,0.0000625009,0.00017762974,0.000544067,0.00004906915,0.00031704028],"category_scores_gemma":[0.000048065962,0.00006416866,0.000036045614,0.00045486202,0.000007990714,0.0002976904,0.000043964985,0.000084469786,0.0024639454],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.5509087e-7,0.00002582708,0.00023133821,0.000004108556,0.000003930631,0.000042696633,0.00034224926,3.5833953e-8,0.000021842752,0.0012709814,0.010392357,0.98766387],"study_design_scores_gemma":[0.01629666,0.00087820715,0.12878522,0.00248618,0.0001313827,0.009138265,0.02438815,0.08951129,0.2347467,0.015591781,0.47076544,0.0072807358],"about_ca_topic_score_codex":0.00008496591,"about_ca_topic_score_gemma":0.000042959164,"teacher_disagreement_score":0.98038316,"about_ca_system_score_codex":0.000048760652,"about_ca_system_score_gemma":0.000019064071,"threshold_uncertainty_score":0.9983128},"labels":[],"label_agreement":null},{"id":"W1688440848","doi":"10.1109/icslp.1996.607209","title":"Detection of ambiguous portions of signal corresponding to OOV words or misrecognized portions of input","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Word (group theory); Artificial intelligence; Speech recognition; Noise (video); Frame (networking); Vocabulary; Key (lock); Base (topology); SIGNAL (programming language); Pattern recognition (psychology); Natural language processing; Algorithm; Image (mathematics); Mathematics","score_opus":0.04833407454510028,"score_gpt":0.26299407245431927,"score_spread":0.214659997909219,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1688440848","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31256115,0.000018913399,0.67981166,0.00024093656,0.00023513437,0.00022247747,0.000017340031,0.00009401746,0.006798374],"genre_scores_gemma":[0.95224416,0.000012249107,0.045303427,0.000096835916,0.000018369436,0.000015636708,0.0000013634823,0.000007697546,0.002300288],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984973,0.00007438843,0.00066908676,0.00023978253,0.00033793572,0.00018148792],"domain_scores_gemma":[0.99878097,0.00016230793,0.00031069774,0.00032401987,0.00030677466,0.000115263116],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00030618053,0.00011282285,0.00029275037,0.00056436897,0.0000647165,0.000020207404,0.00034348088,0.00007044894,0.002653553],"category_scores_gemma":[0.00032886167,0.00009771192,0.00014559583,0.0012963141,0.000035384426,0.00022094673,0.00007819165,0.00007016643,0.000054975335],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000093917144,0.0005181966,0.00026585648,0.000030783034,0.00006143966,0.000008228761,0.0009636231,0.000042084957,0.2682199,0.0006989238,0.0005228623,0.7285742],"study_design_scores_gemma":[0.0005931702,0.00044097868,0.0061791027,0.000094543284,0.000040332703,0.000056128712,0.00036292672,0.028086342,0.9632029,0.00031731627,0.0004028723,0.00022336579],"about_ca_topic_score_codex":0.00016190193,"about_ca_topic_score_gemma":0.00012423258,"teacher_disagreement_score":0.7283508,"about_ca_system_score_codex":0.000026221951,"about_ca_system_score_gemma":0.000042975422,"threshold_uncertainty_score":0.9982582},"labels":[],"label_agreement":null},{"id":"W1736190149","doi":"10.1109/icassp.1990.115896","title":"Acoustic recognition component of an 86000-word speech recognizer","year":2002,"lang":"en","type":"article","venue":"International Conference on Acoustics, Speech, and Signal Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Hidden Markov model; Speech recognition; Computer science; Context (archaeology); Word (group theory); Vocabulary; Artificial intelligence; Natural language processing; Word recognition; Mixture model; Pattern recognition (psychology); Mathematics; Linguistics","score_opus":0.0784269689885228,"score_gpt":0.2843761123875949,"score_spread":0.2059491433990721,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1736190149","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33023196,0.00017880484,0.61692995,0.0024289798,0.0011675137,0.0005121495,0.00014117238,0.00044632005,0.047963135],"genre_scores_gemma":[0.92000675,0.00020404253,0.078480005,0.0006195313,0.00022113029,0.000011145958,0.000030841373,0.000021141688,0.00040542567],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99759156,0.00010146808,0.00057843496,0.0006315697,0.0007785804,0.0003184169],"domain_scores_gemma":[0.99812245,0.00017751944,0.0003428771,0.00024212025,0.0009061573,0.00020887433],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00038205174,0.00029330113,0.00033246845,0.00037961872,0.00018527874,0.00045575204,0.00070431805,0.000153316,0.001649159],"category_scores_gemma":[0.00016022536,0.00028427973,0.00007969111,0.00021928526,0.0001682939,0.00083067245,0.00011132345,0.0003130743,0.00012951314],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004604263,0.00035189686,0.00002769262,0.000048749014,0.000031465555,0.00007076226,0.00028207182,0.000029535326,0.033327147,0.00047820722,0.00016920023,0.96513724],"study_design_scores_gemma":[0.0008497761,0.00030931507,0.00054420804,0.00053325656,0.000048890553,0.00024591427,0.00041026692,0.9541998,0.023581807,0.01850766,0.0002131063,0.00055603305],"about_ca_topic_score_codex":0.00002835785,"about_ca_topic_score_gemma":0.000010125914,"teacher_disagreement_score":0.9645812,"about_ca_system_score_codex":0.00006540854,"about_ca_system_score_gemma":0.0000665432,"threshold_uncertainty_score":0.99996096},"labels":[],"label_agreement":null},{"id":"W1749856071","doi":"","title":"A new algorithm for the alignment of phonetic sequences","year":2000,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":167,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Similarity (geometry); Algorithm; Basis (linear algebra); Scheme (mathematics); Sequence (biology); Phonology; Multiple sequence alignment; Artificial intelligence; Speech recognition; Sequence alignment; Mathematics; Image (mathematics); Linguistics","score_opus":0.022999810208332715,"score_gpt":0.24775321148392893,"score_spread":0.2247534012755962,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1749856071","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00028691403,0.00009271494,0.98636883,0.001958852,0.00008174398,0.00014278623,0.0000016226089,0.000035100595,0.011031455],"genre_scores_gemma":[0.010596703,0.00008765461,0.9763611,0.00077321107,0.000047654263,0.00002232937,2.8294494e-7,0.0000026324362,0.012108433],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99956816,0.000012369966,0.00009917906,0.00010596832,0.00012410275,0.000090200105],"domain_scores_gemma":[0.999576,0.00017541934,0.000019352106,0.00017661462,0.00001837001,0.000034263485],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000108232096,0.000042503485,0.000059310572,0.000015777177,0.000039740087,0.00003379015,0.0003503413,0.000014107435,0.002170802],"category_scores_gemma":[0.0000053089193,0.000024428562,0.000050342747,0.00009843112,0.00001740734,0.00006378964,0.00001424092,0.000013140396,0.00007654703],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.6520906e-7,0.000008115039,0.0000011331258,6.982835e-7,0.0000070478013,2.6853945e-7,0.00009025643,0.0000023398773,0.00008762752,0.0011096472,0.003124005,0.9955683],"study_design_scores_gemma":[0.0008792391,0.00026505362,0.00080887903,0.000031235042,0.000032284774,0.000041674444,0.00026062658,0.55174166,0.22384061,0.03409684,0.18768965,0.00031225185],"about_ca_topic_score_codex":0.00012466163,"about_ca_topic_score_gemma":0.0000069994903,"teacher_disagreement_score":0.99525607,"about_ca_system_score_codex":0.0000057560856,"about_ca_system_score_gemma":0.000034919514,"threshold_uncertainty_score":0.9987413},"labels":[],"label_agreement":null},{"id":"W1823609680","doi":"10.5430/air.v4n2p72","title":"Cross-language phoneme mapping for phonetic search keyword spotting in continuous speech of under-resourced languages","year":2015,"lang":"en","type":"article","venue":"Artificial Intelligence Research","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Keyword spotting; Computer science; Spotting; Speech recognition; Natural language processing; Keyword search; Artificial intelligence; Information retrieval","score_opus":0.2760964527524231,"score_gpt":0.44965197702364745,"score_spread":0.17355552427122434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1823609680","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8000891,0.00026726007,0.19493166,0.0007322911,0.00014787899,0.0006733433,0.000008599118,0.00008409196,0.0030657654],"genre_scores_gemma":[0.9534855,0.000016074868,0.04558071,0.00005317191,0.00011660625,0.00005802016,0.000004976576,0.000022240074,0.0006627011],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9962489,0.00045550527,0.0006913597,0.00059425173,0.0010792718,0.00093071925],"domain_scores_gemma":[0.9965125,0.0016934535,0.00009306209,0.00060015975,0.0008570498,0.00024380446],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0066928086,0.00016922328,0.00034219195,0.0008741119,0.00016426739,0.00034883778,0.0012470757,0.00013601675,0.00014967087],"category_scores_gemma":[0.002370806,0.00016791515,0.000111399284,0.001855029,0.00033972177,0.0002620077,0.00038788133,0.00043575713,0.00028704683],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013179997,0.00029725826,0.0010945344,0.000080387166,0.00002109974,0.00011731509,0.01476263,0.00041534237,0.06472067,0.009707202,0.000120703386,0.90853107],"study_design_scores_gemma":[0.00020097672,0.00025032798,0.0006907778,0.00016689589,0.000002435678,0.000023121442,0.04449277,0.10605109,0.8321275,0.01540062,0.0002947138,0.0002987669],"about_ca_topic_score_codex":0.0016794223,"about_ca_topic_score_gemma":0.00030764725,"teacher_disagreement_score":0.9082323,"about_ca_system_score_codex":0.00014931225,"about_ca_system_score_gemma":0.00027771818,"threshold_uncertainty_score":0.68473804},"labels":[],"label_agreement":null},{"id":"W182365161","doi":"10.21437/interspeech.2013-691","title":"Text-dependent speaker recognition using PLDA with uncertainty propagation","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":72,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Computer science; Utterance; Speech recognition; Phrase; Speaker recognition; Artificial intelligence; Channel (broadcasting); Speaker verification; Bridge (graph theory); Natural language processing; Pattern recognition (psychology)","score_opus":0.03518198583893034,"score_gpt":0.23009311793928353,"score_spread":0.19491113210035318,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W182365161","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31147912,0.0000052834866,0.66525716,0.0007285409,0.00012747523,0.00046707643,0.0000014395259,0.00028002937,0.021653911],"genre_scores_gemma":[0.7594241,0.0000036821964,0.23904537,0.0006956951,0.00006338553,0.00004556858,0.0000066744133,0.000011152183,0.00070436153],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989607,0.000061074905,0.00017230556,0.00030466195,0.00029369228,0.00020759039],"domain_scores_gemma":[0.99930185,0.0000488539,0.00007764059,0.00024791647,0.00023221533,0.00009153714],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00015369171,0.000118573436,0.000103430786,0.00010174523,0.000104923514,0.0002896428,0.00020790643,0.000047243935,0.0015972398],"category_scores_gemma":[0.000029076422,0.00008336956,0.000032583015,0.000245388,0.000026858246,0.0009310574,0.000047842652,0.000073032184,0.0013778068],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008131214,0.00009283111,0.00029878606,0.0000106603775,0.000022794235,0.000009696881,0.00015855323,0.00006655361,0.005932873,0.0007133738,0.00053265895,0.9921531],"study_design_scores_gemma":[0.0013490514,0.00027219558,0.008165763,0.00015150242,0.000037059966,0.00036938695,0.00044825423,0.8547016,0.12106851,0.01152229,0.0009222679,0.000992126],"about_ca_topic_score_codex":0.00041037667,"about_ca_topic_score_gemma":0.00007152581,"teacher_disagreement_score":0.991161,"about_ca_system_score_codex":0.0000670487,"about_ca_system_score_gemma":0.00005372782,"threshold_uncertainty_score":0.9993997},"labels":[],"label_agreement":null},{"id":"W1826414049","doi":"10.1109/icassp.1989.266372","title":"A locus model of coarticulation in an HMM speech recognizer","year":2003,"lang":"en","type":"article","venue":"International Conference on Acoustics, Speech, and Signal Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bell (Canada); Institut National de la Recherche Scientifique","funders":"","keywords":"Coarticulation; Hidden Markov model; Speech recognition; Vowel; Computer science; Consonant; Artificial intelligence; Gaussian; Physics","score_opus":0.07357010464901313,"score_gpt":0.30215801015917104,"score_spread":0.2285879055101579,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1826414049","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28519145,0.000027790886,0.6997789,0.00037849217,0.00015150385,0.00014641635,0.000011959208,0.00005891237,0.014254556],"genre_scores_gemma":[0.90717727,0.00002785482,0.09233129,0.00027023107,0.000031562104,0.0000062532517,0.000005477521,0.00000963127,0.00014041134],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984461,0.000074519674,0.00040679966,0.0004034629,0.0004644452,0.00020467996],"domain_scores_gemma":[0.99893343,0.00007618352,0.00018135727,0.00014874354,0.0005585222,0.000101758655],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041491847,0.00016673628,0.00020686614,0.0002874507,0.000069268,0.00025146673,0.0003356753,0.00010010375,0.0001598742],"category_scores_gemma":[0.00016452157,0.00016232645,0.000036957368,0.00017222886,0.00008272921,0.0006528964,0.000039476705,0.00017880664,0.000011496078],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007833296,0.000439597,0.0010482486,0.000053273896,0.000019274361,0.000049438677,0.00081142725,0.002669678,0.10418241,0.042059623,0.000035261062,0.8485534],"study_design_scores_gemma":[0.00043540852,0.00007681305,0.00028422603,0.00015508094,0.000007994105,0.000025134334,0.00019849397,0.9245805,0.022844117,0.051178657,0.000013409555,0.00020017244],"about_ca_topic_score_codex":0.00001554506,"about_ca_topic_score_gemma":0.000021972375,"teacher_disagreement_score":0.9219108,"about_ca_system_score_codex":0.000051346888,"about_ca_system_score_gemma":0.0001857695,"threshold_uncertainty_score":0.661948},"labels":[],"label_agreement":null},{"id":"W1829432249","doi":"10.1109/icassp.1994.389344","title":"Application of vector quantized hidden Markov modeling to telephone network based connected digit recognition","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Codebook; Hidden Markov model; Speech recognition; Telephone network; Computer science; Telephony; Pattern recognition (psychology); Artificial intelligence; Markov model; Markov chain; Machine learning; Telecommunications","score_opus":0.04209136715797211,"score_gpt":0.23181024252240348,"score_spread":0.18971887536443138,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1829432249","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041607544,0.000016370204,0.9499053,0.00095135183,0.00012800375,0.00027259547,0.000006043428,0.00031077903,0.00680206],"genre_scores_gemma":[0.68290746,0.000007055953,0.31614578,0.00065221754,0.00006200444,0.00006048995,0.000012614029,0.000010211357,0.00014220485],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99870837,0.00007529047,0.00035728866,0.0003630482,0.00025644017,0.0002395887],"domain_scores_gemma":[0.99890983,0.00023990296,0.00009698101,0.00040138,0.00023029519,0.000121620804],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002014338,0.00012942591,0.0002156555,0.0001421691,0.00007223568,0.00007498595,0.0003508548,0.000071881004,0.0007341017],"category_scores_gemma":[0.00013860072,0.00012443903,0.00008155693,0.0007903579,0.000012604353,0.00022092821,0.000050301096,0.000061155544,0.0005785671],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028884651,0.00012785266,0.00007468167,0.000013984472,0.000017047823,0.0000015412407,0.000058612193,0.00051659887,0.0055105314,0.00036866826,0.0017776274,0.99150395],"study_design_scores_gemma":[0.00041537042,0.00004705092,0.0001287238,0.000034447854,0.0000082884135,0.0000027836306,0.000011213023,0.9794082,0.018618576,0.0007305909,0.00040645542,0.0001882913],"about_ca_topic_score_codex":0.000055004864,"about_ca_topic_score_gemma":0.000022268669,"teacher_disagreement_score":0.99131566,"about_ca_system_score_codex":0.000029215124,"about_ca_system_score_gemma":0.000015080142,"threshold_uncertainty_score":0.80378985},"labels":[],"label_agreement":null},{"id":"W1835856534","doi":"","title":"Effects of acoustic interaction between the subglottic and supraglottic cavities of the human phonatory system","year":2009,"lang":"en","type":"article","venue":"Canadian acoustics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Glottis; Vocal tract; Acoustics; Phase (matter); Physics; SIGNAL (programming language); Coupling (piping); Larynx; Vocal folds; Resonance (particle physics); Optics; Computer science; Materials science; Anatomy; Medicine","score_opus":0.010766971592418888,"score_gpt":0.2158009963327643,"score_spread":0.20503402474034543,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1835856534","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9870378,0.00018593839,0.010640497,0.00036301464,0.00047021892,0.00031403144,0.000024584759,0.000038020626,0.0009259234],"genre_scores_gemma":[0.99935734,0.00000606315,0.0002922687,0.0002236781,0.00005183929,0.000003897544,9.029329e-7,0.0000065124036,0.000057489266],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9991157,0.000113987975,0.00023212042,0.00014529403,0.00019046504,0.00020245553],"domain_scores_gemma":[0.9988063,0.00048373677,0.00013508406,0.0003395405,0.000100927544,0.00013443253],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019353417,0.000110246154,0.00018511729,0.00013104008,0.00019273201,0.000056686968,0.00049216906,0.000066463916,0.0000037377881],"category_scores_gemma":[0.00016282484,0.000075081436,0.000056372653,0.0002280127,0.00012753268,0.00009425042,0.000034248234,0.00013703555,0.0000030194756],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022412507,0.00030241202,0.025920255,0.005779789,0.00074597396,0.00029426898,0.0141766565,0.0014445136,0.4884412,0.10134642,0.013196711,0.34832937],"study_design_scores_gemma":[0.0006406882,0.00024166256,0.9324198,0.00094363606,0.0005083925,0.00011847582,0.0018579612,0.024260107,0.03586398,0.0023947584,0.00026490266,0.00048568408],"about_ca_topic_score_codex":0.00261361,"about_ca_topic_score_gemma":0.000792059,"teacher_disagreement_score":0.9064995,"about_ca_system_score_codex":0.00015075441,"about_ca_system_score_gemma":0.00018916835,"threshold_uncertainty_score":0.39510137},"labels":[],"label_agreement":null},{"id":"W1846073453","doi":"10.1109/icassp.2000.859138","title":"Towards language independent acoustic modeling","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":111,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Universidade Federal de Alagoas; Rice University","keywords":"Computer science; Czech; Discriminative model; Hidden Markov model; Acoustic model; Language model; Speech recognition; Natural language processing; Mandarin Chinese; Artificial intelligence; Adaptation (eye); Speech processing; Linguistics","score_opus":0.04217330464563866,"score_gpt":0.24696833763924592,"score_spread":0.20479503299360724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1846073453","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028609544,0.000059417027,0.8819358,0.0005028206,0.00012265882,0.00004200916,5.2175056e-7,0.00026109524,0.08846613],"genre_scores_gemma":[0.93901455,0.000014952339,0.058765274,0.0006929221,0.000035786543,0.0000046534265,2.4875422e-7,0.000004030548,0.0014676009],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993403,0.000018418243,0.00010095666,0.00017887198,0.00020858075,0.00015288095],"domain_scores_gemma":[0.9996249,0.000019941797,0.000014016383,0.00024206583,0.000029128767,0.000069961614],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000094879935,0.0000650243,0.00006955599,0.000067621135,0.000045741115,0.000101480655,0.00034232019,0.000029673613,0.0015129598],"category_scores_gemma":[0.000036177455,0.00005371076,0.000040882762,0.00014694018,0.0000054805055,0.00019697925,0.00008057144,0.000061701176,0.000996774],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.6730246e-7,0.000084583575,0.000022176962,0.000005737728,0.00001269329,0.00007236211,0.0010380634,0.0007040499,0.0013446832,0.005420912,0.0011694657,0.9901246],"study_design_scores_gemma":[0.00008666043,0.000008244181,0.000032706605,0.00000310706,0.0000022162976,0.000022731605,0.00009878854,0.9968617,0.0023671493,0.00029913607,0.00012869493,0.00008885139],"about_ca_topic_score_codex":0.00004413397,"about_ca_topic_score_gemma":0.000022546199,"teacher_disagreement_score":0.99615765,"about_ca_system_score_codex":0.000027719057,"about_ca_system_score_gemma":0.0000065965155,"threshold_uncertainty_score":0.9997811},"labels":[],"label_agreement":null},{"id":"W1849264953","doi":"10.1109/icassp.1994.389695","title":"Fast match acoustic models in large vocabulary continuous speech recognition","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Vocabulary; Speech recognition; Computer science; Context (archaeology); Word (group theory); Task (project management); Computation; Hidden Markov model; State (computer science); Artificial intelligence; Natural language processing; Mathematics; Algorithm; Engineering; Linguistics","score_opus":0.037260184739906416,"score_gpt":0.2281018144157373,"score_spread":0.19084162967583088,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1849264953","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.061327353,0.000094897296,0.7992082,0.0010544725,0.00030029565,0.0003005775,0.000014338263,0.00046221886,0.1372376],"genre_scores_gemma":[0.8685123,0.00011285187,0.12573312,0.001654952,0.00006210056,0.000034457433,0.0000083859895,0.000017778262,0.0038640557],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985147,0.00008378586,0.00030498678,0.00040809903,0.00028203666,0.00040640405],"domain_scores_gemma":[0.9992886,0.00010668087,0.000056784284,0.00035625615,0.0000868929,0.0001047469],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0003095751,0.00015750411,0.0002153726,0.0002348654,0.00006762452,0.00014981587,0.00041534565,0.00010724823,0.002175779],"category_scores_gemma":[0.000049422426,0.00015025651,0.00007379373,0.00045673206,0.00001859317,0.0008177384,0.00010536366,0.00015816638,0.0021845878],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000040296773,0.0003844357,0.00017859034,0.0000134922675,0.000010836031,0.00022336445,0.0003907116,0.00003253864,0.0005280082,0.00072179234,0.0046924385,0.9928198],"study_design_scores_gemma":[0.0008207835,0.000050563885,0.00038880063,0.000056294164,0.000008052477,0.0001586273,0.0002285413,0.9778337,0.005593988,0.01397606,0.00050029915,0.00038430234],"about_ca_topic_score_codex":0.000040135285,"about_ca_topic_score_gemma":0.000120411714,"teacher_disagreement_score":0.99243546,"about_ca_system_score_codex":0.000044422744,"about_ca_system_score_gemma":0.000011649127,"threshold_uncertainty_score":0.9987364},"labels":[],"label_agreement":null},{"id":"W1882201698","doi":"10.1109/ccece.2001.933735","title":"Efficient recognition of continuously-spoken numbers","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Computer science; Speech recognition; Vocabulary; Hidden Markov model; Mel-frequency cepstrum; Telephone line; Task (project management); Telephony; Noise (video); Computation; Artificial intelligence; Pattern recognition (psychology); Feature extraction; Telecommunications; Algorithm; Engineering","score_opus":0.03455514357779255,"score_gpt":0.21929813520673452,"score_spread":0.18474299162894198,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1882201698","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28047767,0.00005820481,0.19010837,0.0010198698,0.00037600021,0.00020263823,0.000005577366,0.0003388326,0.52741283],"genre_scores_gemma":[0.91250306,0.000014248614,0.08507851,0.00038257238,0.000022779777,0.0000075061866,0.000001057839,0.0000052161477,0.0019850503],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992559,0.000038472466,0.00018911883,0.000183607,0.00019301733,0.00013987793],"domain_scores_gemma":[0.9994573,0.00009503145,0.000066027584,0.00022791298,0.00009448723,0.00005923553],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00014583589,0.0000698633,0.00011670995,0.00008861676,0.000034602628,0.000032009848,0.0002472162,0.000038272985,0.002717472],"category_scores_gemma":[0.000061035855,0.00006120129,0.000072366856,0.00024609297,0.00002991817,0.000067634304,0.00004104174,0.00004119604,0.001182007],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027001777,0.00023396155,0.00014623399,0.000009206143,0.000016475007,0.000009138086,0.0004654372,0.00000818694,0.0013393188,0.00272776,0.0072252075,0.9878164],"study_design_scores_gemma":[0.0021920528,0.00028072324,0.003015892,0.00014493027,0.0000389875,0.00016459194,0.00055515807,0.69738066,0.27344513,0.0050709345,0.01669684,0.0010140929],"about_ca_topic_score_codex":0.000024368353,"about_ca_topic_score_gemma":0.0000049807572,"teacher_disagreement_score":0.9868023,"about_ca_system_score_codex":0.000012497377,"about_ca_system_score_gemma":0.0000047921185,"threshold_uncertainty_score":0.9995957},"labels":[],"label_agreement":null},{"id":"W1885745269","doi":"10.1109/icassp.2005.1415064","title":"Discriminative Training Based on the Criterion of Least Phone Competing Tokens for Large Vocabulary Speech Recognition","year":2006,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"York University","keywords":"Security token; Computer science; Discriminative model; Hidden Markov model; Speech recognition; Word error rate; Phone; Normalization (sociology); Vocabulary; Sigmoid function; Artificial intelligence; Set (abstract data type); Generalization; Overfitting; Pattern recognition (psychology); Artificial neural network; Mathematics","score_opus":0.06140262388372575,"score_gpt":0.26316123209178,"score_spread":0.20175860820805425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1885745269","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08594742,0.000009176604,0.8634977,0.0044743167,0.00021883752,0.00047022634,0.00007421121,0.0001437656,0.045164384],"genre_scores_gemma":[0.8736309,0.000001056068,0.12492741,0.00114804,0.000078016536,0.00004037739,0.00003890263,0.000010321624,0.00012497873],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998839,0.00013331155,0.00027241796,0.00026266466,0.00024679804,0.00024578883],"domain_scores_gemma":[0.99857116,0.00087255955,0.0001264794,0.0002245558,0.00017275817,0.00003248393],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00074364454,0.0001290057,0.00017030438,0.00012237056,0.0001935218,0.000077769146,0.00027482168,0.000060840168,0.00025214575],"category_scores_gemma":[0.0001770283,0.000091862836,0.00012628306,0.0002260157,0.000035414087,0.00020367373,0.000036917903,0.000111362395,0.000031375846],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011585451,0.0008873405,0.00014669176,0.000098357326,0.000032666332,0.000017396977,0.002467846,0.00003068776,0.019579569,0.032992963,0.004287212,0.9393434],"study_design_scores_gemma":[0.0014732594,0.0002840844,0.0024350237,0.00031820155,0.00003054325,0.000017592378,0.003659684,0.5408755,0.4400564,0.008566158,0.0018535272,0.0004300387],"about_ca_topic_score_codex":0.00003295639,"about_ca_topic_score_gemma":0.000040892133,"teacher_disagreement_score":0.9389134,"about_ca_system_score_codex":0.000024570803,"about_ca_system_score_gemma":0.00003848595,"threshold_uncertainty_score":0.37460577},"labels":[],"label_agreement":null},{"id":"W1898340511","doi":"10.1109/icassp.1976.1169963","title":"Computer synthesis of Mandarin","year":2005,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Mandarin Chinese; Speech recognition; Intelligibility (philosophy); Computer science; Syllable; String (physics); Speech synthesis; Mathematics; Linguistics","score_opus":0.015528201415972557,"score_gpt":0.22890639170066504,"score_spread":0.2133781902846925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1898340511","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008766503,0.000012802808,0.88182104,0.0019116557,0.00009556305,0.00004707231,0.0000011438564,0.0001465001,0.10719772],"genre_scores_gemma":[0.4134089,0.0000049722253,0.58553135,0.00049424224,0.00005276004,0.0000036351319,1.0555014e-7,0.0000024976302,0.0005014939],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994504,0.000024495243,0.00014418802,0.00014060824,0.00013815155,0.00010216035],"domain_scores_gemma":[0.9994904,0.00014110007,0.000034450088,0.00024837884,0.000042207725,0.000043505217],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013090434,0.00005536979,0.00010422695,0.00007521447,0.000025132573,0.000034563112,0.0003549838,0.000026156351,0.0006127139],"category_scores_gemma":[0.00001803702,0.000044980257,0.000056964444,0.00011747729,0.000020841704,0.00018627712,0.00008139327,0.000026625556,0.00035215745],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.879975e-7,0.00003967807,0.000090580375,0.0000027283234,0.000007004598,0.0000012416184,0.00003028225,0.000004164112,0.00015883957,0.017730761,0.0026187636,0.97931504],"study_design_scores_gemma":[0.00030929563,0.00005450397,0.0074981824,0.0000400223,0.000011157063,0.000049038787,0.000017631002,0.214278,0.6893702,0.0016195319,0.086415075,0.0003373296],"about_ca_topic_score_codex":0.000008417845,"about_ca_topic_score_gemma":0.000007781924,"teacher_disagreement_score":0.97897774,"about_ca_system_score_codex":0.000009520126,"about_ca_system_score_gemma":0.000014323309,"threshold_uncertainty_score":0.67087877},"labels":[],"label_agreement":null},{"id":"W1902248030","doi":"10.1109/icassp.1995.479599","title":"Use of generalized dynamic feature parameters for speech recognition: maximum likelihood and minimum classification error approaches","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Weighting; Speech recognition; Preprocessor; TIMIT; Hidden Markov model; Pattern recognition (psychology); Speech processing; Mel-frequency cepstrum; Word error rate; Feature (linguistics); Artificial intelligence; Feature extraction","score_opus":0.19788699775342944,"score_gpt":0.26767754017287687,"score_spread":0.06979054241944743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1902248030","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37050557,0.000300938,0.6089223,0.014675121,0.0004528915,0.0015893322,0.00011261489,0.00039080234,0.0030504286],"genre_scores_gemma":[0.09660368,0.00010818418,0.90161157,0.00043209663,0.000019820312,0.00009503383,0.00003515515,0.000015347407,0.0010791046],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998772,0.00007802117,0.00026906983,0.00045572245,0.00018806652,0.00023706583],"domain_scores_gemma":[0.99897146,0.00027256852,0.00014911004,0.0003758708,0.00012441164,0.00010659143],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018271884,0.00016927214,0.00023478149,0.00016910474,0.000084923486,0.00016339871,0.0002445826,0.00014368286,0.00008356423],"category_scores_gemma":[0.000118099764,0.000148325,0.0001174922,0.00026352142,0.00006861149,0.00055065047,0.000047226036,0.00007845648,0.000026292755],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018621446,0.00013808602,0.000053447187,0.000038453287,0.000038316994,0.0000017260008,0.00015996261,5.26354e-7,0.0022103072,0.00037887742,0.0038952022,0.9930665],"study_design_scores_gemma":[0.0013188614,0.00020435137,0.0014464452,0.000050819224,0.000072165334,0.00009361342,0.00025746488,0.9459731,0.031251516,0.0150576485,0.0037390518,0.0005349456],"about_ca_topic_score_codex":0.000008001537,"about_ca_topic_score_gemma":0.000020371353,"teacher_disagreement_score":0.99253154,"about_ca_system_score_codex":0.000024366758,"about_ca_system_score_gemma":0.000012285497,"threshold_uncertainty_score":0.6048518},"labels":[],"label_agreement":null},{"id":"W1906553149","doi":"10.1109/icpr.1998.711998","title":"HMM-KNN word recognition engine for bank cheque processing","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Hidden Markov model; Cheque; Classifier (UML); Phone; Word (group theory); Alphabet; Speech recognition; Artificial intelligence; Natural language processing; Segmentation; Modular design; Document processing; Scheme (mathematics); Set (abstract data type); Pattern recognition (psychology); Linguistics","score_opus":0.0708022711339814,"score_gpt":0.24500677916979036,"score_spread":0.17420450803580895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1906553149","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023032716,0.00008098458,0.952935,0.0033316077,0.0001925169,0.00025572223,0.0000037219008,0.0004592631,0.040437937],"genre_scores_gemma":[0.22006528,0.000048344904,0.7707546,0.002539109,0.0002481047,0.00015651456,0.000009829904,0.000020337513,0.0061578806],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99915844,0.000019901525,0.00017405923,0.00028237395,0.000136323,0.00022890899],"domain_scores_gemma":[0.99945337,0.00011039125,0.000050379425,0.00017865843,0.0001290541,0.000078163204],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00017720262,0.0001058068,0.00011364808,0.00010969224,0.00011481873,0.00017628046,0.00025830636,0.000060534367,0.0010943385],"category_scores_gemma":[0.000111900765,0.00009391883,0.00006970318,0.00027569826,0.0000146876555,0.0005023019,0.00003025854,0.000059585454,0.00045558478],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000016266839,0.000045941313,0.0000032128532,0.000015698151,0.0000042272827,0.0000018381204,0.00009489239,4.4435734e-7,0.00032588397,0.0003337591,0.0031963547,0.99597615],"study_design_scores_gemma":[0.0011383097,0.0001214453,0.00022915378,0.00013131872,0.00002300146,0.00007868381,0.000086088716,0.8098478,0.11729744,0.01765482,0.05268069,0.00071126706],"about_ca_topic_score_codex":0.0000028543325,"about_ca_topic_score_gemma":0.0000050453623,"teacher_disagreement_score":0.9952648,"about_ca_system_score_codex":0.000025137211,"about_ca_system_score_gemma":0.000012433051,"threshold_uncertainty_score":0.9998188},"labels":[],"label_agreement":null},{"id":"W1920148782","doi":"10.1109/icassp.1979.1170591","title":"Speech synthesis from vocal tract area function acoustical measurements","year":2005,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Vocal tract; Formant; Glottis; Vowel; Speech synthesis; Interpolation (computer graphics); Acoustics; Speech recognition; Computer science; Speech production; Larynx; Artificial intelligence; Physics; Anatomy; Medicine; Motion (physics)","score_opus":0.06744084468741475,"score_gpt":0.2526280988849138,"score_spread":0.18518725419749904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1920148782","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024294816,0.000026178112,0.9200447,0.00175563,0.00036662916,0.000106387844,0.0000058276623,0.00041883308,0.052980978],"genre_scores_gemma":[0.76852435,0.0000055831188,0.22958595,0.0012114282,0.00022918748,0.000017299262,0.0000020993712,0.000009553741,0.0004145746],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983632,0.00008212745,0.00025554874,0.00043691674,0.0005817188,0.00028050892],"domain_scores_gemma":[0.9989159,0.00035874327,0.000047639405,0.00040838541,0.00009328581,0.00017602887],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0003162646,0.00016238958,0.00018054606,0.00010053783,0.00010330447,0.00018236895,0.00043875512,0.000110256944,0.0046096365],"category_scores_gemma":[0.00026938677,0.00013629402,0.000113305425,0.0001877635,0.000027272734,0.00052913284,0.000045847573,0.00011863727,0.0024299105],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013220156,0.00025693895,0.0005007791,0.000001354635,0.00003300016,0.00000912349,0.0000225548,0.000009072768,0.0067227054,0.0002156418,0.003734809,0.9884808],"study_design_scores_gemma":[0.0012057554,0.00017474224,0.06180365,0.00009450039,0.00022799581,0.000109069035,0.00015752121,0.3639587,0.53264964,0.005237485,0.033061523,0.0013194253],"about_ca_topic_score_codex":0.000049135244,"about_ca_topic_score_gemma":0.000045902147,"teacher_disagreement_score":0.9871614,"about_ca_system_score_codex":0.00008219405,"about_ca_system_score_gemma":0.000041391406,"threshold_uncertainty_score":0.9983468},"labels":[],"label_agreement":null},{"id":"W1929451993","doi":"","title":"A CROSS-LANGUAGE VOWEL NORMALISATION PROCEDURE","year":2006,"lang":"en","type":"article","venue":"Canadian acoustics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Normalization (sociology); Vowel; Vocal tract; Mathematics; Speech recognition; Correlation; Computer science; Statistics","score_opus":0.008281416018026528,"score_gpt":0.22551136531735344,"score_spread":0.2172299492993269,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1929451993","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.58696073,0.00015528906,0.34553832,0.0015534435,0.0008708306,0.0003233681,0.00012304762,0.0003764348,0.06409854],"genre_scores_gemma":[0.9760183,0.000001662258,0.019582594,0.0012942,0.00019652334,0.000008655025,0.00002095723,0.000009769823,0.0028673299],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99920905,0.000013890257,0.00013724343,0.00019366403,0.00014477712,0.00030136228],"domain_scores_gemma":[0.99935603,0.00003088347,0.000038655275,0.0002519299,0.000100050645,0.00022242089],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000098078286,0.00009242934,0.000073324394,0.00016622622,0.00014744342,0.0003325075,0.00033532336,0.000079286496,0.00020869472],"category_scores_gemma":[0.00009603694,0.000097110234,0.000034202,0.0002597189,0.000034239656,0.00022506293,0.000017925391,0.00007838986,0.000245257],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015535365,0.00028426008,0.033723924,0.0002893934,0.00008289651,0.0027043312,0.006665788,0.00389179,0.073813066,0.0875007,0.28499088,0.5060375],"study_design_scores_gemma":[0.0008462231,0.000062834595,0.65639716,0.000058061625,0.000037072954,0.00032842217,0.00034418434,0.30794466,0.006531535,0.0049158474,0.0213627,0.0011712939],"about_ca_topic_score_codex":0.024208473,"about_ca_topic_score_gemma":0.022494854,"teacher_disagreement_score":0.6226733,"about_ca_system_score_codex":0.00014987163,"about_ca_system_score_gemma":0.00038969534,"threshold_uncertainty_score":0.9953421},"labels":[],"label_agreement":null},{"id":"W1930794383","doi":"10.1109/icassp.1987.1169578","title":"Integration of acoustic information in a large vocabulary word recognizer","year":2005,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":89,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Codebook; Computer science; Vector quantization; Speech recognition; Hidden Markov model; Vocabulary; Word (group theory); Linde–Buzo–Gray algorithm; Feature vector; Artificial intelligence; Learning vector quantization; Pattern recognition (psychology); Gaussian; Feature (linguistics); Curse of dimensionality; Set (abstract data type); Mathematics","score_opus":0.016004160455804595,"score_gpt":0.24165227794504474,"score_spread":0.22564811748924013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1930794383","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07766975,0.000010653656,0.90388525,0.00075369317,0.00008129038,0.000112523616,0.0000019221109,0.000073700685,0.017411225],"genre_scores_gemma":[0.86944056,0.000012177557,0.12960972,0.0007257268,0.000014916956,0.000009113172,0.000005424191,0.0000016659188,0.00018071213],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99937093,0.000030425326,0.00026681274,0.00008073755,0.00013836425,0.00011270578],"domain_scores_gemma":[0.9996239,0.000058671274,0.00006329029,0.0001501381,0.000076205375,0.000027795406],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029037186,0.000056651676,0.00008709273,0.00023043675,0.000016918793,0.00003987896,0.00017535627,0.00004470767,0.0002996099],"category_scores_gemma":[0.00012370577,0.000048107915,0.00003080159,0.00032352543,0.000007385084,0.0013920693,0.000037637008,0.000060726583,0.00027239608],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004978558,0.00005806693,0.00012946277,0.0000053705394,0.0000025176255,5.7093985e-7,0.00060986244,0.00002563662,0.0011613198,0.0018601019,0.00065462425,0.9954875],"study_design_scores_gemma":[0.0010871547,0.00005521997,0.020657875,0.00009594983,0.0000065747163,0.000016421865,0.0004982316,0.90754145,0.058078866,0.0018676505,0.009817699,0.00027691698],"about_ca_topic_score_codex":0.000014981182,"about_ca_topic_score_gemma":0.00019534194,"teacher_disagreement_score":0.9952106,"about_ca_system_score_codex":0.000028748596,"about_ca_system_score_gemma":0.000027093462,"threshold_uncertainty_score":0.35011914},"labels":[],"label_agreement":null},{"id":"W1940972223","doi":"10.1109/icassp.1978.1170469","title":"A phoneme recognition system based on human audition","year":2005,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Speech recognition; Artificial intelligence","score_opus":0.05221428637379322,"score_gpt":0.2634940145083017,"score_spread":0.21127972813450846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1940972223","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020910239,0.000003702294,0.58866066,0.0026201324,0.00027824068,0.00024387545,0.000008192739,0.001308603,0.38596633],"genre_scores_gemma":[0.9196521,5.9360866e-7,0.07766353,0.0019472083,0.00016066992,0.00003878361,0.000016803815,0.0000072276275,0.00051306596],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990569,0.00007345629,0.00018007237,0.00027644951,0.00025164316,0.00016152943],"domain_scores_gemma":[0.99942046,0.000073474024,0.000061715255,0.00029623555,0.00007157254,0.00007655311],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00022927235,0.00010057655,0.000097830445,0.00017610188,0.00015404365,0.000114633636,0.00022530643,0.000053839674,0.000877056],"category_scores_gemma":[0.000021137155,0.000090038986,0.000070980845,0.00020480886,0.000012163321,0.00029194783,0.000018545403,0.000064354375,0.0037890759],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008873074,0.00024255658,0.000015580503,0.000025741474,0.000008854978,0.000013923918,0.00005548525,0.000030918673,0.0029905254,0.01326213,0.010911605,0.9724338],"study_design_scores_gemma":[0.0018709378,0.00034932903,0.0020505115,0.00035110413,0.000020538917,0.000056026187,0.00013900752,0.67331016,0.30264196,0.0019647626,0.016454104,0.0007915723],"about_ca_topic_score_codex":0.0000115539115,"about_ca_topic_score_gemma":0.000017797876,"teacher_disagreement_score":0.97164226,"about_ca_system_score_codex":0.00010757846,"about_ca_system_score_gemma":0.000018809182,"threshold_uncertainty_score":0.99698657},"labels":[],"label_agreement":null},{"id":"W1942035323","doi":"10.21437/interspeech.2015-654","title":"A study of the recurrent neural network encoder-decoder for large vocabulary speech recognition","year":2015,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":95,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Speech recognition; Vocabulary; Encoder; Artificial neural network; Recurrent neural network; Artificial intelligence; Natural language processing; Linguistics","score_opus":0.10396958659478608,"score_gpt":0.2999294749775426,"score_spread":0.1959598883827565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1942035323","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77555466,0.00012301195,0.20535739,0.0019613933,0.003619611,0.0027095852,0.000025043682,0.00030041425,0.010348905],"genre_scores_gemma":[0.9254738,0.0000051610173,0.072700374,0.0009374295,0.00025056794,0.00014163328,0.000006514573,0.000016180298,0.00046832583],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985192,0.00020271128,0.00031810315,0.000313695,0.00035911598,0.00028717227],"domain_scores_gemma":[0.9988191,0.00017492067,0.00013349399,0.00048361515,0.0002891069,0.0000997559],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008227921,0.00012971832,0.00018793519,0.0000538464,0.00011857564,0.000068387875,0.00061056693,0.00005207405,0.000048255213],"category_scores_gemma":[0.00018013106,0.00008648943,0.00011628514,0.0003841609,0.000014535452,0.00026682782,0.00021882559,0.00009700871,0.00003568338],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007232705,0.0020197486,0.0051247417,0.000019357727,0.00008471228,0.000010487684,0.0024978812,0.000055703527,0.000026281377,0.0011153818,0.0544728,0.9345006],"study_design_scores_gemma":[0.019668924,0.0059898975,0.025265485,0.00031689627,0.00038853192,0.00034074223,0.013419785,0.77715313,0.023128124,0.09285585,0.038948126,0.0025244798],"about_ca_topic_score_codex":0.00001831558,"about_ca_topic_score_gemma":0.00021841878,"teacher_disagreement_score":0.9319761,"about_ca_system_score_codex":0.000026535841,"about_ca_system_score_gemma":0.00006151021,"threshold_uncertainty_score":0.35269368},"labels":[],"label_agreement":null},{"id":"W1954526745","doi":"10.1109/ccece.2000.849540","title":"Automatic identification of filled pauses in spontaneous speech","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Speech recognition; Computer science; Utterance; Spectral envelope; Confusion; Mel-frequency cepstrum; Identification (biology); Voice activity detection; Speech processing; Natural language processing; Artificial intelligence; Feature extraction; Psychology","score_opus":0.026060496288684152,"score_gpt":0.23438707841155257,"score_spread":0.20832658212286842,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1954526745","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94015235,0.00005041802,0.028221818,0.0007836285,0.00016873106,0.0002031884,0.0000022066004,0.00023953017,0.030178105],"genre_scores_gemma":[0.9655095,0.000016941018,0.03304347,0.00008884132,0.0000058507144,0.000005917205,4.4736845e-7,0.0000027639346,0.0013263038],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992741,0.00004285026,0.0002838973,0.00014358688,0.00016052734,0.00009503779],"domain_scores_gemma":[0.99947524,0.00012769681,0.00006903897,0.00026566646,0.000036534337,0.000025821695],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00016982647,0.00005278998,0.00010491721,0.00015106863,0.000016147069,0.000037272286,0.00028320303,0.000029044159,0.0026876095],"category_scores_gemma":[0.000118667675,0.000046293073,0.000031040225,0.0003037713,0.000014117105,0.00014543807,0.000028761558,0.00003005245,0.0005968591],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000010379866,0.0002017266,0.00023404657,0.000020258094,0.00000689068,0.00020117541,0.00036825065,0.0000029248122,0.0065415613,0.0026766122,0.0011942094,0.9885513],"study_design_scores_gemma":[0.00041963265,0.00004338354,0.010221679,0.000045749082,0.0000059390704,0.0006144399,0.00011432121,0.83833313,0.14570211,0.003742207,0.0005268757,0.00023053655],"about_ca_topic_score_codex":0.00002124388,"about_ca_topic_score_gemma":0.000042636464,"teacher_disagreement_score":0.98832077,"about_ca_system_score_codex":0.000017675027,"about_ca_system_score_gemma":0.000005389132,"threshold_uncertainty_score":0.9982241},"labels":[],"label_agreement":null},{"id":"W1960168474","doi":"10.1109/icassp.1983.1172102","title":"A comparison of distance measures for text-independent speaker identification","year":2005,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Mahalanobis distance; Distance measures; Measure (data warehouse); Pattern recognition (psychology); k-nearest neighbors algorithm; Artificial intelligence; A priori and a posteriori; Earth mover's distance; Speech recognition; Maximum a posteriori estimation; Distance measurement; Correlation; Mathematics; Statistics; Computer science; Maximum likelihood; Data mining","score_opus":0.057792731379237454,"score_gpt":0.3270319084667389,"score_spread":0.26923917708750145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1960168474","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0050870157,0.0000766217,0.9870688,0.0010711582,0.000106165455,0.00017524583,0.0000035093774,0.00007078533,0.006340742],"genre_scores_gemma":[0.8934108,0.000003572891,0.10510886,0.0000926893,0.00003537639,0.000022025453,0.0000017202062,0.0000035263724,0.001321431],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991278,0.000022598057,0.0002879924,0.00019948433,0.0002491023,0.00011300475],"domain_scores_gemma":[0.9993434,0.000087646484,0.00011293544,0.00027467476,0.00014079257,0.000040526404],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027889607,0.00006304005,0.00012744707,0.000058432965,0.00004880465,0.00006602779,0.00034238375,0.000030299425,0.00008349793],"category_scores_gemma":[0.00006628457,0.00005455656,0.000068457724,0.00011491347,0.000018881025,0.00024517,0.000026160327,0.000029051844,0.000086348795],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009426805,0.0001987176,0.0011443457,0.000011667633,0.00001379268,1.3741224e-7,0.00034611308,0.000017840992,0.0071407026,0.04611273,0.0043328144,0.9406717],"study_design_scores_gemma":[0.00050284417,0.00004506891,0.014752446,0.00002163352,0.000014818558,0.0000037366137,0.00019754058,0.16393405,0.70794463,0.0032298223,0.10911801,0.00023541489],"about_ca_topic_score_codex":0.000005170929,"about_ca_topic_score_gemma":0.00012129797,"teacher_disagreement_score":0.9404363,"about_ca_system_score_codex":0.00002617545,"about_ca_system_score_gemma":0.000018341105,"threshold_uncertainty_score":0.22247519},"labels":[],"label_agreement":null},{"id":"W1963733617","doi":"10.1007/s10772-012-9146-4","title":"Speaker-independent ASR for Modern Standard Arabic: effect of regional accents","year":2012,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Computer science; Speech recognition; Hidden Markov model; Arabic; Stress (linguistics); Modern Standard Arabic; Natural language processing; Artificial intelligence; Linguistics","score_opus":0.020494706954978407,"score_gpt":0.304830386805333,"score_spread":0.2843356798503546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1963733617","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.53696674,0.00052485464,0.45082673,0.0078301355,0.0026766777,0.00027339565,0.000027526417,0.00008328895,0.00079063844],"genre_scores_gemma":[0.91343945,0.000086444394,0.085902035,0.0001277947,0.0003498298,0.000008320448,0.000001938896,0.000011903165,0.000072286406],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99812716,0.00004945345,0.0005737797,0.00016235876,0.00082021987,0.00026702858],"domain_scores_gemma":[0.9978858,0.00026101636,0.00062729226,0.00022758558,0.00090399676,0.00009431333],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009445513,0.00014828905,0.0003471565,0.0008181737,0.000035369667,0.0000440769,0.0016007422,0.00017343489,0.000066132765],"category_scores_gemma":[0.0004425246,0.00011964414,0.00024321431,0.00019765741,0.000086275635,0.00059244153,0.00018568269,0.0002442145,0.000016215961],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000356793,0.00014688514,0.009803661,0.000013551541,0.00032046193,0.00005033211,0.00008281356,0.000005714831,0.009412422,0.011878276,0.0012668783,0.9666622],"study_design_scores_gemma":[0.004428855,0.0013965489,0.003405634,0.00024394477,0.000073117684,0.0042107143,0.000069697955,0.0016589591,0.8930755,0.05262996,0.038452093,0.00035496688],"about_ca_topic_score_codex":0.0000027964084,"about_ca_topic_score_gemma":0.000002171513,"teacher_disagreement_score":0.9663072,"about_ca_system_score_codex":0.00016117356,"about_ca_system_score_gemma":0.0000802042,"threshold_uncertainty_score":0.48789462},"labels":[],"label_agreement":null},{"id":"W1963794214","doi":"10.1159/000265737","title":"Speaker Race Identification of Selected Adult North American Indians","year":2009,"lang":"en","type":"article","venue":"Folia Phoniatrica et Logopaedica","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Race (biology); Identification (biology); Speech recognition; Linguistics; Psychology; Computer science; Biology; Sociology; Gender studies","score_opus":0.0067712174134919294,"score_gpt":0.23543182760619846,"score_spread":0.22866061019270653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1963794214","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8021968,0.00013974089,0.17588028,0.014142455,0.0005056263,0.0005992849,0.00007148253,0.0006253185,0.0058389744],"genre_scores_gemma":[0.97412443,0.0002074913,0.024020266,0.0013091591,0.0001022818,0.000011290244,0.000021685446,0.0000122999945,0.00019110258],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9977701,0.00019117702,0.00058835634,0.00049873727,0.0005719108,0.00037972],"domain_scores_gemma":[0.99803966,0.00015565447,0.0005178387,0.0006247407,0.00046243944,0.00019964964],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002952629,0.00020237986,0.00033915482,0.00039070018,0.00010268979,0.00009181605,0.0008770747,0.000064342676,0.000059013622],"category_scores_gemma":[0.00051835435,0.00019312116,0.00013777272,0.0030001474,0.000093708215,0.00032736151,0.000064181724,0.00023273566,0.00031811037],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007281128,0.0010995936,0.019973278,0.000027653083,0.000103081155,0.000078339704,0.00209086,0.000024642895,0.005739834,0.003441966,0.030203355,0.9371446],"study_design_scores_gemma":[0.000687005,0.00040288267,0.97339374,0.000016598147,0.00005730611,0.000056669054,0.000053760294,0.0046593356,0.014013295,0.0006707673,0.00549979,0.0004888753],"about_ca_topic_score_codex":0.000065830536,"about_ca_topic_score_gemma":0.00009300753,"teacher_disagreement_score":0.95342046,"about_ca_system_score_codex":0.000056437773,"about_ca_system_score_gemma":0.00020601999,"threshold_uncertainty_score":0.78752524},"labels":[],"label_agreement":null},{"id":"W1966290010","doi":"10.1063/1.3615726","title":"Nonlinear vocal fold dynamics resulting from asymmetric fluid loading on a two-mass model of speech","year":2011,"lang":"en","type":"article","venue":"Chaos An Interdisciplinary Journal of Nonlinear Science","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Science Foundation","keywords":"Glottis; Bernoulli's principle; Inviscid flow; Nonlinear system; Vocal folds; Bifurcation; Fold (higher-order function); Flow (mathematics); Physics; Mechanics; Mathematics; Computer science; Larynx; Anatomy; Thermodynamics","score_opus":0.05962507340745751,"score_gpt":0.31863793774453036,"score_spread":0.2590128643370728,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1966290010","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6306203,0.000034562865,0.36366093,0.0002960757,0.00081917015,0.00011691831,0.0000542664,0.000044423294,0.0043533607],"genre_scores_gemma":[0.5471434,0.000011974393,0.45247856,0.00007276124,0.00024674088,0.0000010254461,0.0000021153583,0.00001568476,0.000027756707],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99623865,0.00011368959,0.0011907252,0.0006524348,0.001264604,0.0005398685],"domain_scores_gemma":[0.99656546,0.00027070392,0.00095252146,0.0008099566,0.00093230995,0.0004690436],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0023825301,0.0003050827,0.00054894615,0.0014117311,0.00042883845,0.00020231295,0.003351765,0.000105212726,0.00004152292],"category_scores_gemma":[0.00041696735,0.0002520404,0.00029989798,0.001781458,0.00046585998,0.0020334236,0.0009952273,0.00053767505,0.000035762907],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010428205,0.0029037287,0.001325984,0.000059647733,0.00017328806,0.0009209819,0.016545985,0.003183025,0.15408355,0.0046299137,0.000116217845,0.81501484],"study_design_scores_gemma":[0.0005803967,0.00092953787,0.00026334578,0.00027759222,0.000020639252,0.00015420397,0.0008499081,0.88136774,0.111223266,0.004069836,0.000004896842,0.00025863317],"about_ca_topic_score_codex":0.000026008847,"about_ca_topic_score_gemma":0.000019471656,"teacher_disagreement_score":0.87818474,"about_ca_system_score_codex":0.000254934,"about_ca_system_score_gemma":0.00043407734,"threshold_uncertainty_score":0.9999932},"labels":[],"label_agreement":null},{"id":"W1968419113","doi":"10.1109/asru.2013.6707745","title":"Deep maxout neural networks for speech recognition","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":76,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Université de Montréal","keywords":"Sigmoid function; Computer science; Benchmark (surveying); Artificial neural network; Dropout (neural networks); Artificial intelligence; Task (project management); Deep neural networks; Speech recognition; Nonlinear system; Generalization; Machine learning; Engineering; Mathematics","score_opus":0.03354279461887392,"score_gpt":0.23932929487816432,"score_spread":0.2057865002592904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1968419113","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006428762,0.00002049425,0.9760064,0.0016359931,0.00045086333,0.00043489263,7.9234144e-7,0.00029262473,0.014729161],"genre_scores_gemma":[0.21012829,0.000014263606,0.78273904,0.0045240084,0.00029847937,0.00029096304,0.000018606082,0.000017547762,0.0019688043],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99913514,0.000032269363,0.00017451895,0.00026956157,0.00011658128,0.0002719252],"domain_scores_gemma":[0.9992546,0.00018983972,0.000045481705,0.00024233399,0.00016457097,0.00010319948],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00013362839,0.00010424526,0.00010915762,0.00007051241,0.00009169871,0.00026266737,0.00033555046,0.00006862831,0.0013702341],"category_scores_gemma":[0.000060763363,0.00008774074,0.00009393349,0.00016303321,0.000016397158,0.00065346935,0.000055816472,0.00006279142,0.00083062897],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000015864941,0.000020358648,0.00003656623,0.000002504779,0.000005413162,0.0000012577987,0.000013267533,0.000009676658,0.00004767716,0.00039132588,0.0054583536,0.994012],"study_design_scores_gemma":[0.00022618595,0.000044524684,0.0005414043,0.000004366284,0.0000044148665,0.000028492052,0.0000261402,0.983883,0.0030731272,0.010857266,0.0011435703,0.00016746124],"about_ca_topic_score_codex":0.000035599307,"about_ca_topic_score_gemma":0.000019931993,"teacher_disagreement_score":0.99384457,"about_ca_system_score_codex":0.000015200508,"about_ca_system_score_gemma":0.0000069880343,"threshold_uncertainty_score":0.99994737},"labels":[],"label_agreement":null},{"id":"W1970000881","doi":"10.1016/s0167-6393(02)00013-4","title":"Analytic assessment of telephone transmission impact on ASR performance using a simulation model","year":2002,"lang":"en","type":"article","venue":"Speech Communication","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute of Nutrition, Metabolism and Diabetes","keywords":"Computer science; Telephone network; Transmission channel; Transmission (telecommunications); Speech recognition; Degradation (telecommunications); Voice activity detection; Relation (database); Speech processing; Telecommunications; Data mining","score_opus":0.08195727356324413,"score_gpt":0.34907161388960445,"score_spread":0.26711434032636033,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1970000881","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5301093,0.000058490663,0.46441096,0.00017658119,0.000014769565,0.00015887438,0.0000019985835,0.00006593287,0.005003089],"genre_scores_gemma":[0.758909,0.00018421125,0.24079083,0.00004285834,0.000005498059,0.000003427355,0.0000045982415,0.000007323465,0.000052292657],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988186,0.00014010545,0.00032017607,0.00019211505,0.0003769251,0.00015207537],"domain_scores_gemma":[0.9983856,0.00017737494,0.00019483796,0.0010251981,0.00015346831,0.0000635162],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041377606,0.00012952437,0.0001844538,0.00022550332,0.00015464218,0.000052007716,0.00063382904,0.00006888285,0.00011160283],"category_scores_gemma":[0.000024393725,0.00011212942,0.00010512652,0.00047089552,0.000031770156,0.0004915123,0.00006648175,0.00015662024,0.000019061108],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009911569,0.00029600994,0.00045303899,0.000018730922,0.000022479067,5.158151e-7,0.00031583046,0.486833,0.0065046414,0.00024104596,0.000037689482,0.5052671],"study_design_scores_gemma":[0.00024190084,0.00008146688,0.004127994,0.000095984404,0.000012735216,0.0000040571026,0.000008158696,0.9839834,0.010917963,0.00037437314,0.000031558364,0.00012041271],"about_ca_topic_score_codex":0.000024592187,"about_ca_topic_score_gemma":0.0000012562098,"teacher_disagreement_score":0.5051467,"about_ca_system_score_codex":0.00016284987,"about_ca_system_score_gemma":0.000041189647,"threshold_uncertainty_score":0.45725048},"labels":[],"label_agreement":null},{"id":"W1970749564","doi":"10.2316/journal.201.2007.1.201-1545","title":"SPEECH RECOGNITION USING MULTILAYER RECURRENT NEURAL PREDICTION MODELS AND HMM","year":2007,"lang":"en","type":"article","venue":"Control and Intelligent Systems","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Hidden Markov model; Speech recognition; Computer science; Artificial neural network; Artificial intelligence; Pattern recognition (psychology)","score_opus":0.0753432608597366,"score_gpt":0.2743650464735851,"score_spread":0.19902178561384853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1970749564","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24703562,0.0017340704,0.7487602,0.00006790416,0.0012328534,0.000439534,0.000015617661,0.00011454315,0.0005996581],"genre_scores_gemma":[0.99541897,0.00020328542,0.003941249,0.00015237999,0.00021730775,0.000013198763,0.0000036364945,0.000009589771,0.000040381416],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99863863,0.000095568874,0.00041446288,0.00036859882,0.00021997809,0.00026277176],"domain_scores_gemma":[0.9992343,0.00014966805,0.00012216288,0.00017124992,0.00015392888,0.00016866179],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000748187,0.00016024447,0.00022296379,0.00017308615,0.00014188972,0.00022162253,0.00011876772,0.00009646601,0.000010583896],"category_scores_gemma":[0.000044075427,0.00013836948,0.000052447824,0.000121150646,0.000037111568,0.00055970764,0.00003970629,0.00011149579,0.000018360448],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039669878,0.000047597285,0.0004423564,0.00003925191,0.000031465963,0.000013630051,0.00025724436,0.00007449848,0.0018166847,0.00032604355,0.00008092403,0.99683064],"study_design_scores_gemma":[0.00042496735,0.000080332815,0.0005238393,0.00010718844,0.00002371584,0.00021429658,0.00017507968,0.9952103,0.0018592472,0.00043200102,0.00078418234,0.00016487404],"about_ca_topic_score_codex":0.00008837942,"about_ca_topic_score_gemma":0.0000082230235,"teacher_disagreement_score":0.9966658,"about_ca_system_score_codex":0.000046326117,"about_ca_system_score_gemma":0.000011846125,"threshold_uncertainty_score":0.56425434},"labels":[],"label_agreement":null},{"id":"W1970996882","doi":"10.1121/1.1420380","title":"An overlapping-feature-based phonological model incorporating linguistic constraints: Applications to speech recognition","year":2002,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":71,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Hidden Markov model; Feature (linguistics); Syllable; Speech recognition; Phrase; Artificial intelligence; Morpheme; Word (group theory); Natural language processing; Dependency (UML); Acoustic model; Linguistics; Speech processing","score_opus":0.04045392051542798,"score_gpt":0.2698564663430641,"score_spread":0.2294025458276361,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1970996882","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015394057,0.00004178582,0.9904214,0.0071140323,0.00010318813,0.00019231351,0.000013542207,0.000034752833,0.000539583],"genre_scores_gemma":[0.36544654,0.000024729994,0.63028455,0.0040756296,0.0001445785,0.000004470513,4.646409e-7,0.0000062789504,0.000012740016],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985454,0.00018910949,0.0004207758,0.00015733358,0.0004769884,0.00021037082],"domain_scores_gemma":[0.9977703,0.0006924653,0.0005030176,0.00043531426,0.00044007643,0.00015881885],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006287445,0.00013703422,0.00026544378,0.000036192636,0.00025865046,0.000058320828,0.0011961709,0.00008771928,0.00007348401],"category_scores_gemma":[0.00061849185,0.000079618665,0.00028200084,0.0005287021,0.0005081889,0.00011916172,0.00010859187,0.0004416531,0.000022702421],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035529534,0.00056768267,0.000019790044,0.000023285656,0.0000817388,0.0000027798858,0.00068270735,0.010215294,0.022913758,0.00010489811,0.010484346,0.9548682],"study_design_scores_gemma":[0.00021470299,0.00020312064,0.00005144358,0.000057983114,0.00007410106,0.00006925576,0.00026132437,0.9887065,0.0028655312,0.0070248386,0.00034851115,0.0001226782],"about_ca_topic_score_codex":0.0000049651794,"about_ca_topic_score_gemma":2.3820479e-7,"teacher_disagreement_score":0.9784912,"about_ca_system_score_codex":0.000067465444,"about_ca_system_score_gemma":0.00008146173,"threshold_uncertainty_score":0.32467547},"labels":[],"label_agreement":null},{"id":"W1972278020","doi":"10.1006/csla.2000.0143","title":"Tree-structured vector quantization for speech recognition","year":2000,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Smoothing; Hidden Markov model; Computer science; Vector quantization; Pattern recognition (psychology); Speech recognition; Gaussian; Tree (set theory); Entropy (arrow of time); Artificial intelligence; Feature vector; Mixture model; Curse of dimensionality; Mathematics","score_opus":0.019873500248218698,"score_gpt":0.2541196303712127,"score_spread":0.234246130122994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1972278020","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17091633,0.00017250048,0.81591743,0.0010292876,0.0013936078,0.00095999707,0.000075867654,0.001103636,0.008431315],"genre_scores_gemma":[0.067016415,0.000031678876,0.9283493,0.0017114884,0.0011413301,0.000058729827,0.00022405405,0.000048335525,0.0014186708],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99805653,0.00010908916,0.00038541682,0.0006699926,0.00033477883,0.0004441815],"domain_scores_gemma":[0.9987912,0.00015207996,0.000115178445,0.00063078204,0.00015084437,0.00015991488],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002761165,0.00028485525,0.00030880308,0.00020814211,0.00017613517,0.00035305115,0.00076805946,0.00015759074,0.0021720508],"category_scores_gemma":[0.000046348425,0.00027461615,0.00021013465,0.0004839798,0.000037537447,0.0005950735,0.00007359048,0.00014204612,0.00057252275],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022081382,0.00006701264,0.000015450622,0.000020087426,0.00002534538,0.00006213755,0.00049477577,0.000002900614,0.0014763856,0.00026095592,0.0044780932,0.9930748],"study_design_scores_gemma":[0.0053365747,0.0008509218,0.008223173,0.00023993813,0.00013002973,0.0011924595,0.0002238924,0.43182114,0.47288477,0.011482135,0.06495636,0.0026585986],"about_ca_topic_score_codex":0.00002914425,"about_ca_topic_score_gemma":0.0000598027,"teacher_disagreement_score":0.99041617,"about_ca_system_score_codex":0.000049708127,"about_ca_system_score_gemma":0.00004532928,"threshold_uncertainty_score":0.9999706},"labels":[],"label_agreement":null},{"id":"W1972404024","doi":"10.1109/dsp-spe.2013.6642556","title":"Diacritization, automatic segmentation and labeling for Levantine Arabic speech","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Computer science; Arabic; Pronunciation; Transcription (linguistics); Segmentation; Speech recognition; Phonetic transcription; Artificial intelligence; Natural language processing; Speech processing; Speech corpus; Reliability (semiconductor); Speech synthesis; Linguistics","score_opus":0.015979757172952688,"score_gpt":0.24563861917994184,"score_spread":0.22965886200698915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1972404024","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10203608,0.00003480692,0.8937559,0.0020272653,0.00010865827,0.00039737337,0.0000010609125,0.00021497268,0.0014238738],"genre_scores_gemma":[0.13713059,0.000021404885,0.86114156,0.0008407005,0.000031471616,0.00008904306,0.0000057933466,0.0000062733952,0.000733168],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99945885,0.000018903973,0.00014771443,0.00016479316,0.00009428386,0.000115478295],"domain_scores_gemma":[0.99952114,0.00015734592,0.00003411693,0.00011102425,0.00012982638,0.000046576784],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013583731,0.00006206537,0.00007600694,0.00006700176,0.00008432451,0.00022382996,0.000103612816,0.000023628976,0.0002444092],"category_scores_gemma":[0.00010960345,0.00005284072,0.000019572071,0.00012371023,0.000011664488,0.00052734884,0.000027869484,0.000018207724,0.00012609929],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[2.955364e-7,0.0000247376,0.00046499528,0.00003461508,0.000008066247,3.89758e-7,0.00011782412,7.2546845e-7,0.013121862,0.0063861273,0.0015446066,0.97829574],"study_design_scores_gemma":[0.0005638594,0.000044698496,0.0056554885,0.000033075754,0.0000108174345,0.000022818203,0.00014748839,0.90955806,0.060203847,0.023094626,0.00044435475,0.00022089748],"about_ca_topic_score_codex":0.000015232644,"about_ca_topic_score_gemma":0.000004201012,"teacher_disagreement_score":0.97807485,"about_ca_system_score_codex":0.000008173157,"about_ca_system_score_gemma":0.000010593299,"threshold_uncertainty_score":0.26761094},"labels":[],"label_agreement":null},{"id":"W1976677479","doi":"10.1007/s10772-015-9276-6","title":"Feature selection for robust automatic speech recognition: a temporal offset approach","year":2015,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Computer science; Speech recognition; Offset (computer science); Pattern recognition (psychology); Mel-frequency cepstrum; Feature selection; Artificial intelligence; Noise (video); Selection (genetic algorithm); Feature (linguistics); Feature extraction","score_opus":0.05480987488323085,"score_gpt":0.28389007859278653,"score_spread":0.22908020370955567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1976677479","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.056820333,0.0002124956,0.89286715,0.04373778,0.0029167372,0.00045922786,0.000031790012,0.00049221545,0.0024622635],"genre_scores_gemma":[0.042646643,0.000021091291,0.9559304,0.00034048114,0.00062549737,0.000025075802,0.000020069507,0.000017739787,0.00037299254],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982233,0.000056184566,0.00049542024,0.00028191908,0.0006975232,0.00024565388],"domain_scores_gemma":[0.9966002,0.000095778785,0.0006075789,0.00020164443,0.0023630038,0.00013178962],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00085382623,0.00018503459,0.00031855665,0.0012463201,0.000064457054,0.00017840775,0.0014334789,0.0003029805,0.000039022667],"category_scores_gemma":[0.0007487368,0.00016531721,0.00018458844,0.0006621903,0.00007793523,0.00074030063,0.00013139936,0.00041933582,0.00005174612],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056380897,0.00019143506,0.0006021734,0.000009706159,0.00017320957,0.00008819615,0.0000622904,0.000012682157,0.00037903123,0.0012924374,0.027126975,0.9700055],"study_design_scores_gemma":[0.0099973045,0.0024184922,0.00042202842,0.00049493386,0.00018466798,0.07194811,0.0017984937,0.3562468,0.14505336,0.21887952,0.19113976,0.0014165429],"about_ca_topic_score_codex":0.00000767473,"about_ca_topic_score_gemma":0.000010989466,"teacher_disagreement_score":0.96858895,"about_ca_system_score_codex":0.00026863534,"about_ca_system_score_gemma":0.00028312564,"threshold_uncertainty_score":0.67414397},"labels":[],"label_agreement":null},{"id":"W1976874961","doi":"10.1121/1.2935778","title":"Adaptive threshold estimation for speaker verification systems","year":2008,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Speaker verification; Speech recognition; Authentication (law); Speaker recognition; Outlier; Artificial intelligence","score_opus":0.03994724399412187,"score_gpt":0.2565891544558379,"score_spread":0.21664191046171605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1976874961","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002599364,0.00011006442,0.9937493,0.0029374026,0.00025539857,0.00016688342,0.000003611553,0.000011496391,0.0001664715],"genre_scores_gemma":[0.57221115,0.00015647823,0.42694673,0.0005220615,0.000086060216,0.000003001604,1.9219699e-7,0.000005616628,0.00006868637],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99899197,0.00008572553,0.00033276132,0.00007295392,0.0003907553,0.00012584722],"domain_scores_gemma":[0.998309,0.0005938479,0.00047697828,0.00027596572,0.00029694504,0.00004726586],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005124877,0.00007743461,0.00018706941,0.000014409108,0.00021723543,0.000019243518,0.0007127768,0.000040662548,0.000007049836],"category_scores_gemma":[0.00018099204,0.00004038392,0.00027855134,0.00021395004,0.00027138492,0.000166471,0.000060747407,0.00014585537,0.000005260915],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00069593947,0.0011492715,0.00036197866,0.00020882487,0.0012092977,0.000004451697,0.0108568845,0.1191289,0.02799038,0.003446711,0.35045496,0.48449242],"study_design_scores_gemma":[0.00019384218,0.00013692946,0.00081109896,0.000038717593,0.00006231413,0.0001316035,0.00045069953,0.99493337,0.001115136,0.0013433491,0.00072465965,0.000058255126],"about_ca_topic_score_codex":0.000012486179,"about_ca_topic_score_gemma":5.697504e-8,"teacher_disagreement_score":0.8758045,"about_ca_system_score_codex":0.000047549533,"about_ca_system_score_gemma":0.000079052865,"threshold_uncertainty_score":0.16708212},"labels":[],"label_agreement":null},{"id":"W1977321041","doi":"10.1121/1.4778589","title":"Speaker adaptation of HMMs using evolutionary strategy-based linear regression","year":2002,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Computer science; TIMIT; Hidden Markov model; Robustness (evolution); Transformation (genetics); Speech recognition; Regression; Artificial intelligence; Pattern recognition (psychology); Linear map; Mathematics; Statistics","score_opus":0.05762203781710408,"score_gpt":0.27280874767060403,"score_spread":0.21518670985349997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1977321041","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0181567,0.00033544266,0.97908014,0.0021053036,0.00012990837,0.00006255578,0.0000034007844,0.0000084982385,0.00011805135],"genre_scores_gemma":[0.5427436,0.00011434578,0.45662987,0.0004028482,0.00007164836,1.75723e-7,1.06352815e-7,0.00000498923,0.00003241142],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986076,0.00020443395,0.00041208375,0.0000730774,0.0005705948,0.00013226118],"domain_scores_gemma":[0.99827284,0.0004682618,0.0006540624,0.00026252473,0.00028689438,0.000055411423],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040188723,0.00008948875,0.00021346034,0.0000245414,0.00013206158,0.0000104091305,0.0006302566,0.00005105444,0.00011740056],"category_scores_gemma":[0.00016278116,0.00004576791,0.0003342154,0.0003569932,0.00033167607,0.0001464567,0.0000787593,0.00022362775,0.000003908941],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020923319,0.001240213,0.0002983362,0.00012891344,0.00034139198,0.000006722879,0.0027520352,0.3621679,0.10415241,0.000060928098,0.03290052,0.4957414],"study_design_scores_gemma":[0.0002160998,0.00013325021,0.0005227094,0.000119936936,0.00006825261,0.000036581336,0.0006049908,0.99447715,0.0031586995,0.00038245227,0.00022438573,0.000055468176],"about_ca_topic_score_codex":0.000023841436,"about_ca_topic_score_gemma":1.10127054e-7,"teacher_disagreement_score":0.63230926,"about_ca_system_score_codex":0.000044784636,"about_ca_system_score_gemma":0.00008117973,"threshold_uncertainty_score":0.18663612},"labels":[],"label_agreement":null},{"id":"W1977413534","doi":"10.1121/1.4788442","title":"The tube resonance model speech synthesizer","year":2005,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Acoustics; RADIUS; Resonance (particle physics); Vocal tract; Physics; Tube (container); Acoustic resonance; Scattering; Range (aeronautics); Optics; Materials science; Computer science; Atomic physics","score_opus":0.017115047730919007,"score_gpt":0.24677283586155804,"score_spread":0.22965778813063903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1977413534","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035018413,0.00093497586,0.9199721,0.07395638,0.0002056461,0.00011859058,0.000003727043,0.0000234931,0.0012832563],"genre_scores_gemma":[0.2692184,0.0025277105,0.71824765,0.00860563,0.0003735431,0.0000022544004,3.6960916e-8,0.000018464845,0.0010063307],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99812096,0.00022241815,0.000479265,0.00010960859,0.0007731686,0.00029454735],"domain_scores_gemma":[0.996743,0.0018468886,0.00043830593,0.00063376373,0.00024927885,0.00008872566],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00137161,0.00013320851,0.00024820646,0.000012054883,0.00044200002,0.00006516135,0.0024800152,0.000057603596,0.00003103796],"category_scores_gemma":[0.0005237098,0.000055652014,0.0005046542,0.0003185257,0.0006486054,0.00018937631,0.0003137993,0.00044953602,0.000022115004],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004995716,0.0001121607,0.000006975851,0.000005722204,0.00008907802,9.32424e-7,0.0006011769,0.0045994427,0.0036950964,0.00018380552,0.078930646,0.911725],"study_design_scores_gemma":[0.00016085015,0.00005427406,0.00019055126,0.000046111072,0.00006989754,0.00012071047,0.00034375722,0.9665113,0.005973226,0.004081469,0.022351142,0.00009668109],"about_ca_topic_score_codex":0.0000076122387,"about_ca_topic_score_gemma":6.5485506e-7,"teacher_disagreement_score":0.9619119,"about_ca_system_score_codex":0.00006599014,"about_ca_system_score_gemma":0.00013301676,"threshold_uncertainty_score":0.46085262},"labels":[],"label_agreement":null},{"id":"W1978513628","doi":"10.2316/journal.201.2011.4.201-2300","title":"cROVER: THE CONTEXT-AUGMENTED ROVER","year":2011,"lang":"en","type":"article","venue":"Control and Intelligent Systems","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Vocabulary; Word error rate; Speech recognition; Context (archaeology); Word (group theory); Artificial intelligence; Natural language processing; Linguistics; History","score_opus":0.034877992398342265,"score_gpt":0.2140671539285279,"score_spread":0.17918916153018563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1978513628","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009171959,0.005580534,0.934823,0.0010954073,0.0027321414,0.0010672958,0.000014174591,0.00026929838,0.04524621],"genre_scores_gemma":[0.9968134,0.00010977759,0.00014992995,0.0012321112,0.00008166468,0.000056188375,4.8853906e-7,0.0000065843683,0.0015498301],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989656,0.00013070874,0.00027345697,0.0002478399,0.0001742536,0.00020814319],"domain_scores_gemma":[0.9991905,0.00016529752,0.00009703075,0.00036006633,0.00008996885,0.000097153075],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003634502,0.00013126334,0.00019456852,0.000050179235,0.0001391003,0.00018557822,0.00044351266,0.000050860785,0.00010533671],"category_scores_gemma":[0.000052093274,0.000078445955,0.00007829796,0.00009170766,0.000063683445,0.00019856208,0.000056932597,0.00008148233,0.00029165504],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011111295,0.00023090349,0.0030694357,0.00005252434,0.00039169684,0.000042189833,0.004818631,0.0000022176184,0.0009984901,0.30564818,0.016250128,0.6683845],"study_design_scores_gemma":[0.003020455,0.0005858464,0.010822544,0.0002920631,0.00013515099,0.00036043097,0.005046997,0.2492636,0.014692397,0.0039593894,0.7106581,0.0011630496],"about_ca_topic_score_codex":0.00026897714,"about_ca_topic_score_gemma":0.0000142490335,"teacher_disagreement_score":0.98764145,"about_ca_system_score_codex":0.000018793507,"about_ca_system_score_gemma":0.000016678805,"threshold_uncertainty_score":0.37487328},"labels":[],"label_agreement":null},{"id":"W1979346920","doi":"10.1121/1.4779372","title":"Evaluation of a strategy for automatic formant tracking","year":2002,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Formant; Speech recognition; Computer science; Spectrogram; Utterance; Autocorrelation; Vowel; Set (abstract data type); Sampling (signal processing); Intelligibility (philosophy); Mathematics; Statistics; Detector; Telecommunications","score_opus":0.0884424278516014,"score_gpt":0.31017590874627304,"score_spread":0.22173348089467165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1979346920","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016633017,0.00021560313,0.9796623,0.0028466175,0.00011507904,0.00019187303,0.0000027312399,0.000008281759,0.00032452564],"genre_scores_gemma":[0.8437509,0.00008785933,0.1557751,0.00032207344,0.00004412248,0.0000018333011,3.9531987e-8,0.000004090229,0.0000140131615],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983763,0.00019892927,0.0004157178,0.00005137332,0.0008283485,0.00012929547],"domain_scores_gemma":[0.99781054,0.000738711,0.00059629465,0.0002180593,0.0005994005,0.00003700321],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002198509,0.00006763364,0.00020298423,0.000016811677,0.00009822668,0.000018588544,0.0006981721,0.000032443917,0.00011314173],"category_scores_gemma":[0.00048501432,0.000034445937,0.00035453483,0.00020825272,0.0001667691,0.00015908015,0.00005520846,0.00012219905,0.0000019417653],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006021314,0.00012275396,0.000003690859,0.00002945817,0.00011560485,7.129102e-8,0.0010146959,0.0028651007,0.0040481994,0.00002158792,0.0050753946,0.98669744],"study_design_scores_gemma":[0.00031926238,0.00018087086,0.00034575246,0.000058471614,0.00028732576,0.000031682823,0.00065974356,0.9899252,0.0038371698,0.0042337966,0.000078251775,0.000042461128],"about_ca_topic_score_codex":0.0000037070272,"about_ca_topic_score_gemma":1.349577e-7,"teacher_disagreement_score":0.9870601,"about_ca_system_score_codex":0.00004376719,"about_ca_system_score_gemma":0.00006722244,"threshold_uncertainty_score":0.14046645},"labels":[],"label_agreement":null},{"id":"W1980921678","doi":"10.1075/pc.14.2.16kan","title":"Speech transformation solutions","year":2006,"lang":"en","type":"article","venue":"Pragmatics & Cognition","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cape Breton University","funders":"","keywords":"Dictation; Computer science; Spotting; Speech recognition; Keyword spotting; Perception; Interface (matter); Distributive property; Transformation (genetics); Human–computer interaction; Multimedia; Artificial intelligence; Natural language processing","score_opus":0.022333147322471096,"score_gpt":0.23427528483208632,"score_spread":0.2119421375096152,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1980921678","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008961932,0.000027063668,0.8731203,0.0013888628,0.00018447946,0.00023419573,0.000011295246,0.00036727727,0.11570456],"genre_scores_gemma":[0.8406129,0.000023513088,0.15861818,0.00033789268,0.0001053319,0.000050772454,0.00007831668,0.000009860954,0.00016322648],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988587,0.00007294512,0.0003252376,0.00017925962,0.00031508072,0.00024877736],"domain_scores_gemma":[0.9993432,0.000115944844,0.00009968265,0.00021167926,0.00017857728,0.000050885552],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00033820124,0.00011646031,0.00011152186,0.00017234411,0.00023263629,0.0002000322,0.00021847188,0.00007133424,0.00014082406],"category_scores_gemma":[0.000057787493,0.00011941062,0.000076445125,0.00035716878,0.00002940557,0.00085560186,0.000028866827,0.000094408904,0.00079692935],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000061880123,0.00045099485,0.000023075692,0.00007147132,0.00002693831,0.000015373009,0.00048552823,0.000029141569,0.0076110777,0.3224047,0.0039170254,0.6649585],"study_design_scores_gemma":[0.0014144005,0.00010214608,0.0056734676,0.0001489551,0.00011533433,0.00029887768,0.00021334298,0.27848428,0.05085349,0.6483649,0.01351523,0.00081557105],"about_ca_topic_score_codex":0.000027727783,"about_ca_topic_score_gemma":0.00005136499,"teacher_disagreement_score":0.831651,"about_ca_system_score_codex":0.000037152666,"about_ca_system_score_gemma":0.00003449855,"threshold_uncertainty_score":0.99998105},"labels":[],"label_agreement":null},{"id":"W1981185131","doi":"10.1109/iscslp.2014.6936584","title":"Speaker adaptive bottleneck features extraction for LVCSR based on discriminative learning of speaker codes","year":2014,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Speech recognition; Discriminative model; Speaker recognition; Hidden Markov model; Bottleneck; Speaker diarisation; Adaptation (eye); Word error rate; Pattern recognition (psychology); Feature extraction; Artificial intelligence; Task (project management); Engineering","score_opus":0.027343633529193816,"score_gpt":0.27562299606117074,"score_spread":0.24827936253197694,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1981185131","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005177617,0.0000059976746,0.9304417,0.0006518315,0.00017136108,0.00020134827,0.000004373122,0.00010364438,0.06324213],"genre_scores_gemma":[0.8273231,0.000002364194,0.17013766,0.0003404254,0.00005792871,0.000022268525,0.000005155784,0.000010190003,0.0021009077],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99891585,0.00014655122,0.00017644581,0.0003218623,0.00025530008,0.00018398222],"domain_scores_gemma":[0.99856156,0.0008372928,0.00013807778,0.00022354905,0.00017788465,0.000061608655],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039641885,0.00013906907,0.00019363195,0.00014090836,0.0001053672,0.000059610167,0.00022209925,0.0000639219,0.00014551646],"category_scores_gemma":[0.00040353107,0.000109345914,0.00012374713,0.0001410415,0.000046951518,0.00025087333,0.000028116254,0.00011944019,0.000038269325],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029988014,0.000476725,0.0003312847,0.000051672912,0.00006335417,0.0000036106667,0.0010858937,0.0012226128,0.011453896,0.19733152,0.0056331395,0.78204644],"study_design_scores_gemma":[0.000960278,0.0009844549,0.027765747,0.00011609066,0.000031463565,0.000005776627,0.0007295284,0.71358824,0.24350871,0.004328373,0.0076024407,0.0003788895],"about_ca_topic_score_codex":0.000029033194,"about_ca_topic_score_gemma":0.000029697081,"teacher_disagreement_score":0.82214546,"about_ca_system_score_codex":0.00003037401,"about_ca_system_score_gemma":0.000024948045,"threshold_uncertainty_score":0.4458997},"labels":[],"label_agreement":null},{"id":"W1981517541","doi":"10.1121/1.4877151","title":"Using criterio voice familiarity to augment the accuracy of speaker identification in voice lineups","year":2014,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Psychology; Speaker identification; Identification (biology); Syllable; Speech recognition; Semitone; Duration (music); Audiology; Speaker recognition; Computer science; Acoustics","score_opus":0.03805159423408117,"score_gpt":0.3033150911949351,"score_spread":0.26526349696085394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1981517541","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12095831,0.00004630588,0.8657606,0.012760336,0.00025477933,0.00014301937,0.0000028404133,0.0000058562764,0.00006792109],"genre_scores_gemma":[0.85719883,0.00010516251,0.13951074,0.0030327637,0.00011825756,0.0000010860413,8.547693e-8,0.00000673555,0.000026367998],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980131,0.0004565366,0.0006404103,0.00011403398,0.0005912676,0.00018467235],"domain_scores_gemma":[0.99670166,0.0017059379,0.0006673348,0.00054347236,0.00031456468,0.00006704926],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021134827,0.000106971245,0.00026362864,0.000030116164,0.00014366618,0.000046504403,0.0015388805,0.00004412268,0.000013859725],"category_scores_gemma":[0.001439609,0.00005324498,0.00027552055,0.0005775753,0.00027899072,0.00017855299,0.00032163892,0.00031837932,0.00000892407],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022040501,0.00096654764,0.0010000659,0.00015432946,0.00028940846,0.0000016608321,0.0141777685,0.021220056,0.49040344,0.00014641453,0.017044516,0.4543754],"study_design_scores_gemma":[0.0003079773,0.0001300901,0.025498303,0.00017289155,0.00013672741,0.00004462829,0.0018919336,0.9501826,0.01739025,0.0017027184,0.0024048344,0.00013703569],"about_ca_topic_score_codex":0.00016295057,"about_ca_topic_score_gemma":0.0000034167697,"teacher_disagreement_score":0.9289625,"about_ca_system_score_codex":0.00007123066,"about_ca_system_score_gemma":0.00007591199,"threshold_uncertainty_score":0.28596485},"labels":[],"label_agreement":null},{"id":"W1981932308","doi":"10.1109/icassp.2010.5495109","title":"I-smooth for improved minimum classification error training","year":2010,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Hidden Markov model; TIMIT; Discriminative model; Computer science; Boundary (topology); Interpolation (computer graphics); Generalization; Speech recognition; Word error rate; Pattern recognition (psychology); Confusion; Artificial intelligence; Training (meteorology); Training set; Task (project management); Mathematics; Engineering","score_opus":0.0834741312720563,"score_gpt":0.29785911738937093,"score_spread":0.21438498611731463,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1981932308","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018105669,0.0000017634619,0.9465584,0.0057545607,0.0007472102,0.00025469754,0.0000036163772,0.00027738677,0.028296709],"genre_scores_gemma":[0.44171768,5.9658885e-7,0.5555419,0.0008010613,0.00009625272,0.000065143024,0.0000034272155,0.000006640736,0.001767315],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99938434,0.000010671553,0.00013607783,0.00023628712,0.00006644262,0.00016615108],"domain_scores_gemma":[0.99936604,0.00015378938,0.00004882969,0.00028275358,0.00007651989,0.00007206872],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002414986,0.00006896067,0.00008117935,0.000062804684,0.00008515879,0.000108413864,0.0003467755,0.000062543935,0.00014749097],"category_scores_gemma":[0.00014874665,0.00005818025,0.000062204104,0.00010573211,0.000021098844,0.00022576343,0.00002243259,0.00007148682,0.00005911663],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000026007783,0.000022130216,0.000007535948,0.0000020969694,0.0000030525516,1.4472214e-7,0.00019481494,1.939495e-8,0.17102304,0.032041818,0.0011438603,0.79555887],"study_design_scores_gemma":[0.00071923784,0.000083768406,0.003276946,0.0000052803466,0.000008442775,0.000012242595,0.00040984622,0.7728646,0.057873297,0.013138288,0.15127243,0.00033561766],"about_ca_topic_score_codex":0.0000033192628,"about_ca_topic_score_gemma":0.00004234031,"teacher_disagreement_score":0.79522324,"about_ca_system_score_codex":0.0000060933207,"about_ca_system_score_gemma":0.000048362406,"threshold_uncertainty_score":0.23725218},"labels":[],"label_agreement":null},{"id":"W1988809937","doi":"10.5539/mas.v4n10p97","title":"Concatenative Synthesis of Persian Language Based on Word, Diphone and Triphone Databases","year":2010,"lang":"en","type":"article","venue":"Modern Applied Science","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Speech synthesis; Speech recognition; Word (group theory); Persian; Set (abstract data type); Vocabulary; Natural language processing; Artificial intelligence; Speech corpus; Part of speech; Database; Linguistics","score_opus":0.015493047792780346,"score_gpt":0.2480546913990974,"score_spread":0.23256164360631704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1988809937","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43410364,0.00002494834,0.528542,0.0008341144,0.0002817501,0.0004000741,0.000060296516,0.00019897116,0.035554234],"genre_scores_gemma":[0.92933273,0.0000027116582,0.07024704,0.00032269253,0.00001654128,0.00003000984,0.0000012015408,0.000006744363,0.000040336636],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983436,0.000025216406,0.0001770509,0.00059018075,0.0005753585,0.00028861372],"domain_scores_gemma":[0.9985206,0.0004768524,0.00010879715,0.0006444635,0.000076837096,0.00017243312],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007594472,0.00014663638,0.0002081053,0.00030971572,0.00021874062,0.00010759879,0.0008542092,0.000036403584,0.000077483855],"category_scores_gemma":[0.00032907352,0.00012264283,0.00003525974,0.0006995951,0.0007376541,0.00028523084,0.00017369674,0.00016211161,0.00003198787],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019251804,0.00010066191,0.000053790445,0.0000086579885,0.000003357629,0.0000057317284,0.0009312936,0.000006017909,0.7234304,0.004568428,0.000028166432,0.27084425],"study_design_scores_gemma":[0.0002893219,0.000020611202,0.002289708,0.000019575753,0.000006333851,0.000005169245,0.000279638,0.27840453,0.7179868,0.0004434851,0.00006577127,0.00018901231],"about_ca_topic_score_codex":0.000036830366,"about_ca_topic_score_gemma":0.000027749727,"teacher_disagreement_score":0.4952291,"about_ca_system_score_codex":0.000021485637,"about_ca_system_score_gemma":0.00014663384,"threshold_uncertainty_score":0.50012296},"labels":[],"label_agreement":null},{"id":"W1990505856","doi":"10.1109/icassp.2014.6854321","title":"Deep mixture density networks for acoustic modeling in statistical parametric speech synthesis","year":2014,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":193,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Naturalness; Parametric statistics; Computer science; Speech synthesis; Artificial neural network; Speech recognition; Probability density function; Layer (electronics); Deep neural networks; Mixture model; Statistical model; Artificial intelligence; Mathematics; Statistics","score_opus":0.027659185034576744,"score_gpt":0.24981290520688473,"score_spread":0.222153720172308,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1990505856","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007316679,0.000020071087,0.9907631,0.00022879597,0.00018885359,0.00021561264,0.0000016677023,0.00013542952,0.0011297466],"genre_scores_gemma":[0.5902571,0.000007613695,0.40929046,0.00033017682,0.000049637954,0.000028699453,0.0000015919462,0.0000076014994,0.000027076605],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99852645,0.00012438933,0.0002872464,0.00044509151,0.00021730982,0.00039952417],"domain_scores_gemma":[0.9964512,0.0029077097,0.000043484542,0.00035331756,0.00010812007,0.00013614366],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007314714,0.00015494128,0.00027443352,0.00024205413,0.000090333764,0.00014738612,0.00043273857,0.0001400365,0.00007527889],"category_scores_gemma":[0.0021331352,0.00013559336,0.000073365096,0.0005271453,0.000022391609,0.00016148071,0.00008196736,0.00014590155,0.000045027948],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020516087,0.00011256815,0.00033345626,0.000024810204,0.000015311954,0.00001522267,0.000028344062,0.039195947,0.00003565282,0.012935101,0.00044186466,0.9468412],"study_design_scores_gemma":[0.0001651063,0.000025959433,0.00032235135,0.000015645086,0.000014666308,0.000015306154,0.000015003489,0.9892396,0.00043486618,0.009512761,0.000046185432,0.00019257466],"about_ca_topic_score_codex":0.00005618233,"about_ca_topic_score_gemma":0.00022679614,"teacher_disagreement_score":0.9500436,"about_ca_system_score_codex":0.000048498026,"about_ca_system_score_gemma":0.000023880208,"threshold_uncertainty_score":0.5529337},"labels":[],"label_agreement":null},{"id":"W1993282646","doi":"10.1121/1.4784179","title":"The nonaccommodation of speech errors.","year":2009,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Voice; Vowel; Accommodation; Coda; Perception; Plural; Consonant; Speech recognition; Computer science; Speech error; Acoustics; Psychology; Audiology; Linguistics; Speech production","score_opus":0.015970871322222482,"score_gpt":0.25634350632712977,"score_spread":0.2403726350049073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993282646","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012027601,0.00022753763,0.9216655,0.06449205,0.00029335628,0.00012275395,0.0000026299715,0.000013455828,0.0011551107],"genre_scores_gemma":[0.7610902,0.00059982063,0.23541695,0.0026376056,0.00015149583,3.4709257e-7,9.288042e-8,0.0000052365203,0.000098256445],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99855304,0.00019596805,0.00043860104,0.00006267717,0.0005904914,0.00015923251],"domain_scores_gemma":[0.99761885,0.0009973017,0.00063867087,0.00042384857,0.0002718639,0.000049452425],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010609685,0.00008503369,0.00021004045,0.000013519884,0.00021863895,0.000027621933,0.0016370282,0.00004061009,0.000022729204],"category_scores_gemma":[0.00033327893,0.00003608121,0.00038474187,0.00035724527,0.00037589166,0.00012816016,0.0001299149,0.00027463352,0.000004593858],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046442074,0.00012298745,0.00002422152,0.0000062069753,0.00008417294,5.5892644e-7,0.00058763404,0.00032323744,0.014295644,0.00019763615,0.023042874,0.96126837],"study_design_scores_gemma":[0.0012214466,0.0013906333,0.020499364,0.00026776642,0.00048290874,0.0004644687,0.004441518,0.7991831,0.086799264,0.064586535,0.020238936,0.00042408754],"about_ca_topic_score_codex":0.000011476945,"about_ca_topic_score_gemma":2.8790242e-7,"teacher_disagreement_score":0.9608443,"about_ca_system_score_codex":0.000029472496,"about_ca_system_score_gemma":0.000074380325,"threshold_uncertainty_score":0.3042033},"labels":[],"label_agreement":null},{"id":"W1993409002","doi":"10.1109/icassp.2013.6639211","title":"Fast speaker adaptation of hybrid NN/HMM model for speech recognition based on discriminative learning of speaker code","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":224,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Speech recognition; Computer science; TIMIT; Hidden Markov model; Speaker diarisation; Adaptation (eye); Speaker recognition; Discriminative model; Artificial intelligence; Artificial neural network; Pattern recognition (psychology)","score_opus":0.06434906411656907,"score_gpt":0.2616561921307978,"score_spread":0.19730712801422876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993409002","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07350665,0.000002521044,0.91391224,0.00043373226,0.00007254207,0.0004928307,0.00003506648,0.00007169387,0.011472744],"genre_scores_gemma":[0.65986013,0.00000294191,0.33898994,0.00017324954,0.000016237424,0.00004799789,0.00003597292,0.00001232922,0.0008611751],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99859107,0.000097674354,0.00039980476,0.00034819846,0.0003564114,0.00020684529],"domain_scores_gemma":[0.9984005,0.00040957108,0.0002729438,0.00024869505,0.000596322,0.000071941125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033936277,0.00016052638,0.00024960373,0.00023090851,0.000066015564,0.00005035784,0.0002506618,0.000043412125,0.00039729665],"category_scores_gemma":[0.0002858671,0.00013963027,0.00014586875,0.00018407808,0.000054386262,0.00055751286,0.000037420188,0.00009945053,0.00010507038],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055570265,0.0003251071,0.000057711433,0.00006759682,0.000026086533,0.000001688263,0.00081938854,0.011970615,0.0038274517,0.0015064547,0.00083015225,0.9805122],"study_design_scores_gemma":[0.0004899175,0.00019246683,0.0002875574,0.00007076332,0.000014991011,0.000002375628,0.00047738274,0.83851683,0.15635064,0.0034082644,0.00003837376,0.00015043556],"about_ca_topic_score_codex":0.000084247265,"about_ca_topic_score_gemma":0.000028214512,"teacher_disagreement_score":0.98036176,"about_ca_system_score_codex":0.000035648758,"about_ca_system_score_gemma":0.00005945603,"threshold_uncertainty_score":0.56939566},"labels":[],"label_agreement":null},{"id":"W1993882792","doi":"10.1109/tasl.2011.2109382","title":"Acoustic Modeling Using Deep Belief Networks","year":2011,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1746,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"University of Pennsylvania","keywords":"TIMIT; Hidden Markov model; Discriminative model; Computer science; Artificial intelligence; Pattern recognition (psychology); Deep belief network; Mixture model; Artificial neural network; Speech recognition; Feature (linguistics); Backpropagation; Feature extraction; Markov model; Generative model; Gaussian; Generative grammar; Machine learning; Markov chain","score_opus":0.03523967748347272,"score_gpt":0.24992323005654898,"score_spread":0.21468355257307625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993882792","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025285978,0.00078248035,0.9721779,0.000030858486,0.0002177811,0.00011173776,0.0000016864525,0.00028829538,0.0011032877],"genre_scores_gemma":[0.8078824,0.00005481129,0.19155148,0.0003602099,0.0000495892,0.000008845283,4.0137263e-7,0.000019340452,0.000072885705],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987368,0.00005355815,0.00023783829,0.0004134761,0.0002024656,0.00035584124],"domain_scores_gemma":[0.9993995,0.00004326913,0.000071916795,0.00025180005,0.000074455646,0.00015907105],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023646158,0.00020474862,0.00019353446,0.00021311281,0.00042252193,0.00018469621,0.00026245054,0.00011353647,0.00012862515],"category_scores_gemma":[0.000008945613,0.00019230538,0.00007514592,0.00037854613,0.00004404059,0.0005473257,0.000004306778,0.00026845024,0.00001620425],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001619908,0.00009645099,0.0000030882093,0.000030512958,0.000019481657,0.00006707281,0.0023358427,0.012048066,0.0021953934,0.000007682115,0.0000017372414,0.9831785],"study_design_scores_gemma":[0.00022155953,0.000034926008,0.0000057278203,0.0001033057,0.00004056339,0.00018574293,0.0005484823,0.9775599,0.020932913,0.00011657101,0.0000033442575,0.00024692793],"about_ca_topic_score_codex":0.000075720265,"about_ca_topic_score_gemma":0.000072589355,"teacher_disagreement_score":0.98293155,"about_ca_system_score_codex":0.000039010516,"about_ca_system_score_gemma":0.000048208192,"threshold_uncertainty_score":0.7841986},"labels":[],"label_agreement":null},{"id":"W1995014979","doi":"10.1121/1.4783360","title":"Measuring articulatory similarity with algorithmically reweighted principal component analysis.","year":2009,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University","funders":"","keywords":"Principal component analysis; Similarity (geometry); Context (archaeology); Pattern recognition (psychology); Mathematics; Variance (accounting); Cross-validation; Interpolation (computer graphics); Variation (astronomy); Vocal tract; Computer science; Speech recognition; Artificial intelligence; Statistics; Image (mathematics)","score_opus":0.02139409261340762,"score_gpt":0.23111114208511416,"score_spread":0.20971704947170655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1995014979","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041081622,0.00007718116,0.94925547,0.009265968,0.00005881959,0.000081560844,0.0000018688258,0.000021043674,0.00015647075],"genre_scores_gemma":[0.64636374,0.000048561655,0.3513981,0.0021206513,0.00005424822,3.0214414e-7,1.256525e-7,0.0000037232992,0.000010515287],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980047,0.00026053638,0.00046334628,0.00012556148,0.00090964127,0.00023626516],"domain_scores_gemma":[0.99813247,0.00040113568,0.00051013153,0.00047598025,0.00034383676,0.00013644528],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009110595,0.00013412474,0.00039997755,0.000039084494,0.000195434,0.000039912415,0.0011545834,0.000050581195,0.000023355307],"category_scores_gemma":[0.000121968624,0.00006306186,0.0005749135,0.00083903485,0.00032670432,0.00013400542,0.00013018817,0.0004107515,0.000003023195],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011118178,0.0048079262,0.0034621318,0.00009988905,0.012585902,0.00007961456,0.007487474,0.090405084,0.11872357,0.00067383,0.017365493,0.74319726],"study_design_scores_gemma":[0.00046338007,0.00034306364,0.05196183,0.00005550554,0.0011791885,0.00011436092,0.00025374754,0.93871325,0.0050513824,0.001074893,0.00060889975,0.00018049257],"about_ca_topic_score_codex":0.000009062871,"about_ca_topic_score_gemma":4.428719e-7,"teacher_disagreement_score":0.84830815,"about_ca_system_score_codex":0.00006887318,"about_ca_system_score_gemma":0.00009302192,"threshold_uncertainty_score":0.25715882},"labels":[],"label_agreement":null},{"id":"W1996861904","doi":"10.1121/1.2942936","title":"Effects of frequency shifts on the identification of vowels and words in sentences","year":2007,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Vowel; Envelope (radar); Context (archaeology); Mathematics; Sentence; Acoustics; Set (abstract data type); Identification (biology); Speech recognition; Physics; Computer science; Telecommunications; Natural language processing; Geology","score_opus":0.011600546567526362,"score_gpt":0.24777718816970928,"score_spread":0.23617664160218294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1996861904","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.52361655,0.0002290101,0.4699602,0.0057626907,0.00015459162,0.00014038775,0.0000014698426,0.0000036992656,0.00013136731],"genre_scores_gemma":[0.9808387,0.0002908066,0.018360006,0.00047178587,0.000026145794,4.7394627e-7,1.9338028e-8,0.0000028001614,0.0000092653045],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986494,0.00020234822,0.00050813804,0.00006777294,0.00045253482,0.00011978342],"domain_scores_gemma":[0.99615675,0.002795636,0.0006775163,0.00022044741,0.0001160419,0.000033579563],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019486956,0.00007003627,0.00020127643,0.000029901368,0.0000615317,0.000011708468,0.0007507369,0.000036163314,0.0000072334788],"category_scores_gemma":[0.0006569392,0.000031524116,0.00016650905,0.00039114113,0.0005136406,0.000083612584,0.00008788093,0.00020355725,7.7994855e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017036698,0.00077899103,0.0017907611,0.00021949234,0.00027534904,0.000004385336,0.01147895,0.0003911981,0.56250894,0.0009047821,0.002017918,0.41945884],"study_design_scores_gemma":[0.00095531787,0.00085897435,0.26949397,0.00093985576,0.00029000815,0.000060825274,0.008254592,0.115355656,0.56514865,0.03831612,0.000067026114,0.00025904225],"about_ca_topic_score_codex":0.000039101345,"about_ca_topic_score_gemma":0.0000010048342,"teacher_disagreement_score":0.45722213,"about_ca_system_score_codex":0.000019846604,"about_ca_system_score_gemma":0.000034223613,"threshold_uncertainty_score":0.18925302},"labels":[],"label_agreement":null},{"id":"W1996941879","doi":"10.1121/1.4781999","title":"Efficient spectral measures for automatic speech recognition","year":2007,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Spectrogram; Computer science; Speech recognition; Spectral envelope; Mel-frequency cepstrum; Linear prediction; Cepstrum; Wideband; Wavelet; Acoustics; Bandwidth (computing); Pattern recognition (psychology); Artificial intelligence; Feature extraction; Telecommunications","score_opus":0.02682802096998669,"score_gpt":0.2669700108464535,"score_spread":0.24014198987646682,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1996941879","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031580966,0.00006980095,0.96336144,0.004197464,0.00032743724,0.00017473806,0.0000038360345,0.000021795377,0.0002625341],"genre_scores_gemma":[0.24638443,0.00004236388,0.7520276,0.0013219991,0.00018659602,9.66363e-7,1.2933336e-7,0.000008204046,0.000027762158],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984236,0.00011390984,0.00048748273,0.000089980684,0.0006192575,0.00026581393],"domain_scores_gemma":[0.99734247,0.001471022,0.0004942812,0.0002698487,0.00033345324,0.00008892759],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022858607,0.00010761948,0.00024182547,0.00003032202,0.00018863622,0.00003039568,0.0009128144,0.000052268635,0.000035866757],"category_scores_gemma":[0.0005863752,0.000055874723,0.0005357077,0.0003467248,0.00027575728,0.000060324423,0.00008999465,0.00023429016,0.000008632635],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050538827,0.00017989574,0.000009019331,0.00002519701,0.000108277876,0.0000011785385,0.0005268442,0.00033572907,0.010980586,0.000013418251,0.00815228,0.97961706],"study_design_scores_gemma":[0.0006663406,0.00041219316,0.0016034936,0.00014377234,0.00027086126,0.0003305575,0.0014225639,0.9270935,0.058921274,0.007835225,0.0011098823,0.00019032092],"about_ca_topic_score_codex":0.000007832949,"about_ca_topic_score_gemma":4.4199493e-7,"teacher_disagreement_score":0.97942674,"about_ca_system_score_codex":0.00007156893,"about_ca_system_score_gemma":0.00007816647,"threshold_uncertainty_score":0.22785051},"labels":[],"label_agreement":null},{"id":"W1997539970","doi":"10.1109/icassp.2010.5494926","title":"Large margin estimation of n-gram language models for speech recognition via linear programming","year":2010,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Discriminative model; Computer science; Margin (machine learning); Speech recognition; Language model; Viterbi algorithm; Vocabulary; Word error rate; Viterbi decoder; n-gram; Artificial intelligence; Pattern recognition (psychology); Decoding methods; Hidden Markov model; Algorithm; Machine learning","score_opus":0.02641845991397187,"score_gpt":0.28234568494186885,"score_spread":0.255927225027897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1997539970","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.055546034,0.0000052854803,0.9413152,0.00020405499,0.00019071372,0.00043697894,0.000015354213,0.00021364569,0.0020727625],"genre_scores_gemma":[0.25812018,0.0000012402778,0.7414831,0.00008848274,0.00004498357,0.000054396216,0.000037129696,0.000008326787,0.00016220896],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991019,0.000023153083,0.00023831046,0.00023833448,0.00018193471,0.00021641773],"domain_scores_gemma":[0.99926454,0.00012961095,0.00010043325,0.0002733609,0.0001669063,0.00006515903],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004882466,0.00010068672,0.00013854874,0.00013039727,0.00006569629,0.000059686907,0.00025764707,0.00009426794,0.00013001627],"category_scores_gemma":[0.00013497035,0.00009098181,0.00009244463,0.00021093288,0.000018825302,0.00054688234,0.000047236204,0.00009970615,0.000059005088],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000058846563,0.000117670534,0.0000047387443,0.000027093694,0.000007177674,0.000001551569,0.00022557714,0.000008767981,0.0043368023,0.0027589155,0.000080961785,0.99242485],"study_design_scores_gemma":[0.00032730744,0.00004776821,0.00001607201,0.000014034607,0.000008272587,0.000014919207,0.00007087769,0.8225347,0.163912,0.0124397,0.000492342,0.000122032645],"about_ca_topic_score_codex":0.000031648713,"about_ca_topic_score_gemma":0.00008644178,"teacher_disagreement_score":0.99230283,"about_ca_system_score_codex":0.000008346093,"about_ca_system_score_gemma":0.000024653345,"threshold_uncertainty_score":0.37101308},"labels":[],"label_agreement":null},{"id":"W1997805633","doi":"10.1145/1640377.1640388","title":"Avoiding speaker variability in pronunciation verification of children's disordered speech","year":2009,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Shanghai Ocean University; Universität Wien; McGill University","keywords":"Normalization (sociology); Pronunciation; Speech recognition; Computer science; Word error rate; Speaker recognition; Adaptation (eye); Artificial intelligence; Speaker verification; Test set; Pattern recognition (psychology); Natural language processing; Linguistics; Psychology","score_opus":0.011219972688645814,"score_gpt":0.22778042803402457,"score_spread":0.21656045534537877,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1997805633","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5797348,0.000006946932,0.4033925,0.0009345212,0.000053166146,0.00027623374,0.0000011341384,0.00009340515,0.015507309],"genre_scores_gemma":[0.94015765,0.000006888281,0.059685625,0.00008521475,0.00001229509,0.0000035424166,0.0000040118903,0.0000018489219,0.00004289226],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.999025,0.00019707247,0.0002484337,0.00023811939,0.00017667956,0.0001147274],"domain_scores_gemma":[0.999434,0.00011128447,0.00008122221,0.00028266595,0.00006415107,0.000026690777],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011932718,0.00006750961,0.000109132314,0.000102486345,0.000039096594,0.000031356936,0.0002308794,0.000046491434,0.00007321354],"category_scores_gemma":[0.00050193997,0.000062246036,0.00003541675,0.00039600435,0.000010541166,0.0003224714,0.000018231149,0.000085894746,0.000024769179],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000063898683,0.0002917523,0.012396112,0.000003899296,0.0000034223956,6.1451124e-7,0.0003197438,0.000007501877,0.0047470066,0.022248657,0.0000444595,0.9599304],"study_design_scores_gemma":[0.00032690231,0.000040683914,0.8605185,0.00001767993,0.0000028886516,0.000005994099,0.000038239472,0.022633635,0.09590846,0.02032015,0.000038250473,0.00014857772],"about_ca_topic_score_codex":0.000035107078,"about_ca_topic_score_gemma":0.000014309167,"teacher_disagreement_score":0.9597819,"about_ca_system_score_codex":0.000044167093,"about_ca_system_score_gemma":0.000029443381,"threshold_uncertainty_score":0.25383195},"labels":[],"label_agreement":null},{"id":"W1998280908","doi":"10.1109/asru.2007.4430198","title":"Multiple feature combination to improve speaker diarization of telephone conversations","year":2007,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Speaker diarisation; Viterbi algorithm; Computer science; Mixture model; Cluster analysis; Speech recognition; Pattern recognition (psychology); Segmentation; Feature (linguistics); Bayesian information criterion; Artificial intelligence; Hierarchical clustering; Test set; Speaker recognition; Word error rate; Hidden Markov model","score_opus":0.010190349140749892,"score_gpt":0.2296411357601296,"score_spread":0.2194507866193797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1998280908","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.042355463,0.0000031382494,0.94662607,0.0014850092,0.00027068116,0.00021401687,0.0000034609232,0.00009600241,0.0089461785],"genre_scores_gemma":[0.8653333,0.0000014540576,0.13311611,0.00048804056,0.000021775564,0.000004294882,0.000008008581,0.0000040266104,0.001022982],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99934363,0.000015416237,0.00015451162,0.00017187932,0.00019126055,0.00012327716],"domain_scores_gemma":[0.99928325,0.00016020171,0.00006138532,0.0002120189,0.00020752141,0.0000755931],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027985027,0.000064224,0.00008418051,0.00016936923,0.000046873527,0.000034658544,0.00018359114,0.000055143184,0.00008414285],"category_scores_gemma":[0.00021923664,0.0000592463,0.000035948833,0.00047825568,0.000014957602,0.00024510812,0.000046297453,0.00004371727,0.00010453155],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028268081,0.00043112817,0.009628013,0.000020382424,0.00003569154,0.000004302059,0.00172066,0.000012858482,0.30840105,0.05287322,0.0067774225,0.620067],"study_design_scores_gemma":[0.0006277868,0.00007774377,0.0681055,0.0000098343935,0.0000057520965,0.0000031742568,0.00016234016,0.01815293,0.90827817,0.0010655872,0.0033501463,0.00016105892],"about_ca_topic_score_codex":0.000038828013,"about_ca_topic_score_gemma":0.000086551525,"teacher_disagreement_score":0.82297784,"about_ca_system_score_codex":0.000030329058,"about_ca_system_score_gemma":0.000020658606,"threshold_uncertainty_score":0.2415994},"labels":[],"label_agreement":null},{"id":"W1998948935","doi":"10.1109/iciet.2007.4381302","title":"Speaker Accent Classification System Using a Fuzzy Gaussian Classifier","year":2007,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Mixture model; Stress (linguistics); Hidden Markov model; Computer science; Pattern recognition (psychology); Artificial intelligence; Speech recognition; Vector quantization; Fuzzy logic; Gaussian; Classifier (UML); Cluster analysis; Phonetic transcription; Speaker recognition; Fuzzy clustering; Feature vector; Speaker diarisation","score_opus":0.08100266918697686,"score_gpt":0.29624603515127984,"score_spread":0.215243365964303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1998948935","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013824797,0.000010463522,0.6880316,0.00035965294,0.0004330973,0.00012385628,5.529457e-7,0.00030731058,0.29690868],"genre_scores_gemma":[0.85126495,0.0000020308164,0.14746194,0.0003367049,0.00012130292,0.000003350009,0.0000012009829,0.000009101823,0.0007993883],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986453,0.000051355888,0.0003159727,0.00035231333,0.00031703635,0.00031802998],"domain_scores_gemma":[0.9991011,0.00007265801,0.000101619444,0.00047045326,0.000092317765,0.00016184102],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061806146,0.00012415017,0.00013143691,0.00018911484,0.00013373306,0.00020431867,0.00040963673,0.00008879971,0.000112993854],"category_scores_gemma":[0.000024077633,0.000102608225,0.00007803265,0.00042651303,0.00002579394,0.00039002806,0.000073121046,0.00008610145,0.00048236264],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012911635,0.000124084,0.0014836994,0.00003527033,0.000031313837,0.000055348763,0.00023511794,0.0000021950461,0.015831716,0.57837594,0.0011812832,0.40263116],"study_design_scores_gemma":[0.0017184295,0.000109170716,0.17857519,0.0003489989,0.00007692227,0.00091063685,0.006764939,0.6200341,0.12884071,0.002553508,0.058199637,0.0018677574],"about_ca_topic_score_codex":0.000029509742,"about_ca_topic_score_gemma":0.00002700153,"teacher_disagreement_score":0.8374402,"about_ca_system_score_codex":0.00020186647,"about_ca_system_score_gemma":0.000049220544,"threshold_uncertainty_score":0.61999565},"labels":[],"label_agreement":null},{"id":"W1999102959","doi":"10.1121/1.3248416","title":"Listener voice identification in foreign and accented English.","year":2009,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Mandarin Chinese; Formant; Salient; Speech recognition; Voice; Perception; Identification (biology); Variation (astronomy); Computer science; Acoustics; Vowel; Linguistics; Psychology; Artificial intelligence","score_opus":0.014998237736868186,"score_gpt":0.24662990598075027,"score_spread":0.2316316682438821,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1999102959","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047709074,0.0002504994,0.9374954,0.013222177,0.00021275201,0.00013707043,0.0000021287904,0.000017979066,0.0009529031],"genre_scores_gemma":[0.929031,0.00034937132,0.06833278,0.002168285,0.000073215575,3.630758e-7,8.5656275e-8,0.0000029479575,0.000041919935],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990367,0.00013324682,0.0003316567,0.00007316308,0.0003022657,0.00012293478],"domain_scores_gemma":[0.9988458,0.00037221497,0.0003119687,0.00022797582,0.00019429154,0.000047730362],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00066164765,0.00006704156,0.00015753509,0.000021809756,0.00007863348,0.00004040889,0.00071064034,0.00003674121,0.000008709455],"category_scores_gemma":[0.00039708143,0.00003549426,0.00014490355,0.0003285962,0.00016307479,0.00019707246,0.00008405779,0.00020717617,0.0000015404465],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010516617,0.00048032362,0.0005288044,0.0000269168,0.000106737156,0.000002849661,0.005148718,0.0007083952,0.03907244,0.0004817322,0.021649659,0.93168825],"study_design_scores_gemma":[0.0013424729,0.00044514833,0.11002671,0.00021789172,0.00021357661,0.00017557482,0.005619993,0.83334005,0.016320074,0.028608851,0.0033697102,0.00031996306],"about_ca_topic_score_codex":0.000008764951,"about_ca_topic_score_gemma":2.683611e-7,"teacher_disagreement_score":0.9313683,"about_ca_system_score_codex":0.000031193085,"about_ca_system_score_gemma":0.000030587835,"threshold_uncertainty_score":0.1447414},"labels":[],"label_agreement":null},{"id":"W2001936727","doi":"10.1109/lsp.2007.905088","title":"Combining Gaussianized/Non-Gaussianized Features to Improve Speaker Diarization of Telephone Conversations","year":2007,"lang":"en","type":"article","venue":"IEEE Signal Processing Letters","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Speaker diarisation; Viterbi algorithm; Computer science; Cluster analysis; Speech recognition; Mixture model; Pattern recognition (psychology); Segmentation; Bayesian information criterion; Mel-frequency cepstrum; Feature (linguistics); Artificial intelligence; Speaker recognition; Word error rate; Test set; Hierarchical clustering; Feature extraction; Hidden Markov model","score_opus":0.010488642288494734,"score_gpt":0.23965041366761372,"score_spread":0.22916177137911897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2001936727","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07256859,0.000021293286,0.9216519,0.0032738557,0.00038555107,0.00027334955,0.0000040080195,0.00016166846,0.0016597651],"genre_scores_gemma":[0.91225696,0.0000012501418,0.083100595,0.0043457127,0.00014769482,0.000011379708,0.00000515405,0.000023084547,0.00010819014],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99812037,0.000054620083,0.00046471818,0.00045995973,0.00048368998,0.00041661656],"domain_scores_gemma":[0.9988885,0.00019308146,0.00027641997,0.00027214887,0.00018009852,0.00018976595],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006241198,0.00021856424,0.00028779224,0.00038700807,0.00021693266,0.00022728983,0.0005059643,0.00009817316,0.000045787507],"category_scores_gemma":[0.000070157585,0.000208924,0.000092272676,0.0009615098,0.000089284156,0.00055742863,0.00005454964,0.00019611846,0.00005793147],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044736116,0.00007033194,0.00016027904,0.00004851119,0.000027197475,0.000025529594,0.0018675878,0.00007026279,0.83629894,0.00014988371,0.001683875,0.15955287],"study_design_scores_gemma":[0.001241973,0.0000972802,0.0076345378,0.00023106243,0.00003649126,0.00002974124,0.00024265361,0.0089566875,0.98028386,0.00033838415,0.00040223054,0.0005051284],"about_ca_topic_score_codex":0.000038235263,"about_ca_topic_score_gemma":0.000008248983,"teacher_disagreement_score":0.83968836,"about_ca_system_score_codex":0.00007137498,"about_ca_system_score_gemma":0.00010277847,"threshold_uncertainty_score":0.85196733},"labels":[],"label_agreement":null},{"id":"W2002840771","doi":"10.1115/fmd2013-16131","title":"Implementation of Agent Based Model of Tissue Inflammation on a Graphics Processing Unit Platform","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Graphics processing unit; Inflammation; Computer science; Process (computing); Wound healing; Medicine; Surgery; Immunology; Operating system","score_opus":0.06734610164530011,"score_gpt":0.3046940250340357,"score_spread":0.2373479233887356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2002840771","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37881348,0.0000013315189,0.61862326,0.00026600316,0.000013012099,0.00018802812,0.0000014206779,0.00003307082,0.0020604287],"genre_scores_gemma":[0.92509353,0.0000016328459,0.074716724,0.00012022934,0.000004495658,0.000019718665,0.000003938204,0.0000029455714,0.0000367953],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99934596,0.000012469201,0.00023848633,0.00010032878,0.00022396083,0.00007876916],"domain_scores_gemma":[0.9994616,0.00003671629,0.00014416309,0.0001381372,0.00018968467,0.000029708666],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012974719,0.000057201865,0.00008044537,0.00017430703,0.000030011552,0.000032098418,0.00015056023,0.00002758526,0.00018733848],"category_scores_gemma":[0.000010544003,0.000048108563,0.000025270669,0.00021969802,0.000014295451,0.0004258313,0.000018342329,0.000026463264,0.000015105951],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003160286,0.00004392204,0.00024999227,0.000065904664,0.000005916425,1.5350342e-7,0.00044397474,0.00088208955,0.026303202,0.022091057,0.00007648736,0.94983417],"study_design_scores_gemma":[0.00014896724,0.000040619143,0.0010615882,0.000015958933,0.0000023728044,1.6777673e-7,0.00009629466,0.5727114,0.4227943,0.0030726066,0.000014311524,0.000041388226],"about_ca_topic_score_codex":0.000120875426,"about_ca_topic_score_gemma":0.00006762428,"teacher_disagreement_score":0.94979274,"about_ca_system_score_codex":0.0000101322175,"about_ca_system_score_gemma":0.000059753173,"threshold_uncertainty_score":0.20512249},"labels":[],"label_agreement":null},{"id":"W2005604008","doi":"10.1109/isie.2006.295643","title":"Incorporation of State-Level Variable Stime-Varying Property into the HMM","year":2006,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Hidden Markov model; Property (philosophy); TIMIT; Computer science; Process (computing); Speech recognition; Variable (mathematics); State (computer science); Task (project management); Pattern recognition (psychology); Artificial intelligence; State variable; Mathematics; Algorithm; Engineering","score_opus":0.029661954659008713,"score_gpt":0.22242534827765117,"score_spread":0.19276339361864248,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2005604008","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0053532803,0.000012941382,0.9133563,0.00087936706,0.00009214859,0.00014218007,0.0000014785118,0.00008800463,0.08007431],"genre_scores_gemma":[0.50663376,0.0000028425134,0.4846825,0.00033644823,0.000031701566,0.00001488594,0.0000031012316,0.0000052987175,0.00828944],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99925834,0.000059871752,0.00020810968,0.00016051737,0.00020559365,0.00010755943],"domain_scores_gemma":[0.9993948,0.00009431149,0.00008467416,0.00027130143,0.00013311797,0.000021814127],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034614935,0.00006858012,0.00008644652,0.000051952604,0.0001030275,0.00008953704,0.00035349626,0.000025590818,0.00014152858],"category_scores_gemma":[0.000040151015,0.000034177414,0.000026590971,0.00032160233,0.000032986336,0.0003497724,0.00008837178,0.00004756028,0.00006577772],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018911549,0.00030959776,0.0011508829,0.000038181926,0.000033132765,0.0000061430324,0.0009861026,0.00080364157,0.05642924,0.11359677,0.015293543,0.81133384],"study_design_scores_gemma":[0.0005601295,0.000103172795,0.004050807,0.000049218765,0.000014006063,0.00001607231,0.0000907297,0.37316293,0.43167922,0.17619061,0.01369604,0.00038706022],"about_ca_topic_score_codex":0.0018512156,"about_ca_topic_score_gemma":0.00011811907,"teacher_disagreement_score":0.8109468,"about_ca_system_score_codex":0.000019801337,"about_ca_system_score_gemma":0.00007717286,"threshold_uncertainty_score":0.27984965},"labels":[],"label_agreement":null},{"id":"W2005708641","doi":"10.1109/asru.2013.6707742","title":"Hybrid speech recognition with Deep Bidirectional LSTM","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1794,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"TIMIT; Computer science; Word error rate; Speech recognition; Leverage (statistics); Hidden Markov model; Artificial neural network; Recurrent neural network; Artificial intelligence; Deep neural networks; Word (group theory); Vocabulary; Acoustic model; Deep learning; Speech processing","score_opus":0.01839249538427433,"score_gpt":0.20616813503791803,"score_spread":0.1877756396536437,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2005708641","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16852638,0.00001945359,0.58246183,0.0024483385,0.00036046535,0.0003365498,0.0000026150344,0.00078488304,0.2450595],"genre_scores_gemma":[0.22632816,0.000017732817,0.76711714,0.0020945966,0.00014641788,0.00011000729,0.00001314186,0.000015619604,0.00415717],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990868,0.000038555787,0.0001319693,0.00028916795,0.0002577376,0.00019576655],"domain_scores_gemma":[0.9993347,0.00008890335,0.000041840147,0.00022506155,0.0002023831,0.00010710175],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00010401315,0.000106357256,0.00009516346,0.00012333205,0.00009508435,0.00021475043,0.00023990695,0.000028279805,0.0056700087],"category_scores_gemma":[0.000029739549,0.000079357174,0.000043152966,0.00021014122,0.000027970054,0.0008056699,0.000041152533,0.00007340583,0.006445366],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000022429376,0.000050025523,0.0001406248,0.0000021568242,0.000013181076,0.000010488413,0.000013745669,3.1439131e-7,0.0003525222,0.00047712962,0.00529702,0.99364054],"study_design_scores_gemma":[0.0018293869,0.00052345806,0.02373952,0.00009681722,0.000036981895,0.0030688944,0.00020000033,0.09762096,0.7309854,0.10792448,0.032218862,0.001755214],"about_ca_topic_score_codex":0.00011934876,"about_ca_topic_score_gemma":0.00002757868,"teacher_disagreement_score":0.99188536,"about_ca_system_score_codex":0.000025823987,"about_ca_system_score_gemma":0.000029254232,"threshold_uncertainty_score":0.99523896},"labels":[],"label_agreement":null},{"id":"W2006577961","doi":"10.1109/icassp.2014.6854925","title":"Improvements to filterbank and delta learning within a deep neural network framework","year":2014,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Filter bank; Speech recognition; Filter (signal processing); Word error rate; Artificial neural network; Artificial intelligence; Deep learning; Computer vision","score_opus":0.013459571748814604,"score_gpt":0.2353835797920289,"score_spread":0.2219240080432143,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2006577961","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.080915764,0.000015213158,0.9141111,0.00090855896,0.00031505676,0.000104703606,1.4652483e-7,0.00018950523,0.003439955],"genre_scores_gemma":[0.5845667,0.0000015316402,0.40978494,0.0051433216,0.00011749871,0.00001227079,5.7128125e-7,0.000007082604,0.00036604272],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99901843,0.00008434909,0.00015897724,0.00031651888,0.0001596626,0.00026203893],"domain_scores_gemma":[0.9992981,0.00021207603,0.000045683857,0.00024129025,0.00003693848,0.00016592705],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033567927,0.000108156215,0.00012142885,0.000047462294,0.00015325731,0.00024715863,0.00031163683,0.000053887634,0.00011106049],"category_scores_gemma":[0.0002418125,0.000091563605,0.00002925643,0.00022884068,0.000014201054,0.00018268685,0.00023131922,0.00015068911,0.00010122062],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000069666376,0.000016938517,0.0034099536,0.000005698088,0.00001280377,0.0000034189477,0.00054247107,0.0007479223,0.00016454596,0.017871657,0.0007868402,0.9764308],"study_design_scores_gemma":[0.00019717263,0.00022361029,0.005005924,0.000034168646,0.000005684199,0.000012758057,0.000051503845,0.9751421,0.0012360987,0.013157032,0.004649736,0.00028417987],"about_ca_topic_score_codex":0.000023704262,"about_ca_topic_score_gemma":0.00002993679,"teacher_disagreement_score":0.9761466,"about_ca_system_score_codex":0.000008692948,"about_ca_system_score_gemma":0.0000053203817,"threshold_uncertainty_score":0.37338555},"labels":[],"label_agreement":null},{"id":"W2007243334","doi":"10.1109/taslp.2014.2332043","title":"Linear Regression Based Acoustic Adaptation for the Subspace Gaussian Mixture Model","year":2014,"lang":"en","type":"article","venue":"IEEE/ACM Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Hidden Markov model; Computer science; Mixture model; Subspace topology; Feature vector; Pattern recognition (psychology); Adaptation (eye); Speech recognition; Context (archaeology); Linear subspace; Artificial intelligence; Gaussian; Projection (relational algebra); Gaussian process; Algorithm; Mathematics","score_opus":0.02573889994601482,"score_gpt":0.2738997070314438,"score_spread":0.24816080708542895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2007243334","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022903592,0.0003322139,0.99244386,0.004050927,0.00017127836,0.00029446837,0.000012952851,0.00022294672,0.00018099688],"genre_scores_gemma":[0.6393767,0.000025464016,0.35889316,0.0010501303,0.00008368208,0.00005943726,0.0000036217964,0.000019903988,0.00048794644],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99877256,0.00006606184,0.000195459,0.0004117165,0.00027561357,0.00027856417],"domain_scores_gemma":[0.99876815,0.00042624932,0.00011427657,0.00046265038,0.00011224951,0.00011643529],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037649015,0.00021058565,0.00017850279,0.00015259783,0.0006805118,0.00023164628,0.00040388163,0.00012208715,0.00002405621],"category_scores_gemma":[0.00012230461,0.0001421844,0.00009980795,0.0003032745,0.000055226606,0.0003183186,0.0000049709424,0.00023522998,0.000009319864],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004534154,0.0000610462,0.0000010732648,0.00008067312,0.000011041611,0.0000032916532,0.0012883458,0.013885575,0.0066579776,0.000016469603,0.00008708324,0.97786206],"study_design_scores_gemma":[0.000506296,0.000063210595,0.000014291472,0.00015860674,0.00004971908,0.000019215884,0.00043581755,0.9419299,0.055975653,0.00038448503,0.0002689561,0.00019389318],"about_ca_topic_score_codex":0.000014034151,"about_ca_topic_score_gemma":0.000100749545,"teacher_disagreement_score":0.97766817,"about_ca_system_score_codex":0.000030548632,"about_ca_system_score_gemma":0.0000939499,"threshold_uncertainty_score":0.57981116},"labels":[],"label_agreement":null},{"id":"W2008066109","doi":"10.1016/j.specom.2009.04.006","title":"Tools and Technologies for Computer-Aided Speech and Language Therapy","year":2009,"lang":"en","type":"article","venue":"Speech Communication","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":133,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Pronunciation; Speech recognition; Population; Dysarthria; Set (abstract data type); Speech technology; Articulation (sociology); Domain (mathematical analysis); Speech processing; Speech corpus; Natural language processing; Speech synthesis; Linguistics; Audiology; Medicine","score_opus":0.03613621209312245,"score_gpt":0.28753021798531103,"score_spread":0.2513940058921886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2008066109","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.68918735,0.008743736,0.25780216,0.034424957,0.00014351725,0.0017494223,0.000026016398,0.0021862865,0.0057365564],"genre_scores_gemma":[0.366828,0.0021804068,0.6302824,0.00059468334,0.000017344051,0.000022487657,0.000013820037,0.000005870767,0.000054975106],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992449,0.000066416185,0.0001720906,0.00024553383,0.00011234063,0.00015870533],"domain_scores_gemma":[0.99862564,0.00032426981,0.00008244895,0.0008530842,0.00008060039,0.000033978926],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037787313,0.000119748576,0.00015826973,0.00011846161,0.00018340437,0.00029637245,0.00067027466,0.0000924326,0.0000035030796],"category_scores_gemma":[0.000100447505,0.00010867786,0.000034071287,0.00017834507,0.000072558076,0.00042449066,0.00016681755,0.000109081084,0.000006260069],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000063742737,0.00003612979,0.000042660587,0.0000034527775,0.0000063217876,0.0000013254182,0.00026648358,1.225135e-7,0.0033679458,0.0061801886,0.0002531927,0.9898358],"study_design_scores_gemma":[0.0048415423,0.0015872122,0.042608727,0.00028344014,0.000034266035,0.0005027884,0.002107626,0.05544677,0.63919437,0.20090328,0.050910894,0.0015790566],"about_ca_topic_score_codex":0.000010359139,"about_ca_topic_score_gemma":0.000008903427,"teacher_disagreement_score":0.98825675,"about_ca_system_score_codex":0.000017428982,"about_ca_system_score_gemma":0.000013263554,"threshold_uncertainty_score":0.44317544},"labels":[],"label_agreement":null},{"id":"W2009049512","doi":"10.1016/s0167-6393(00)00089-3","title":"Speaker clustering for speech recognition using vocal tract parameters","year":2002,"lang":"en","type":"article","venue":"Speech Communication","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Vocal tract; Speech recognition; Formant; Speaker recognition; Cluster analysis; Computer science; Speaker diarisation; Hidden Markov model; Pattern recognition (psychology); Artificial intelligence; Vowel","score_opus":0.14078547902367666,"score_gpt":0.2975063171245893,"score_spread":0.15672083810091264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2009049512","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21005622,0.00040910963,0.77135956,0.0028344083,0.0004987789,0.0011053481,0.000024572857,0.00057755696,0.013134477],"genre_scores_gemma":[0.21176846,0.00020051465,0.787325,0.00042398865,0.00005190046,0.000044551598,0.000032008742,0.000023947969,0.00012958354],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983822,0.00020990137,0.00041547563,0.00037409112,0.000282855,0.00033547822],"domain_scores_gemma":[0.9978473,0.00043704972,0.00020759889,0.0011887028,0.00021352548,0.00010582027],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006671723,0.00019431906,0.00021866968,0.00020788285,0.00032919092,0.0002892508,0.0009800403,0.0001351289,0.00016478138],"category_scores_gemma":[0.00025483718,0.00021002805,0.00016302112,0.00037723876,0.00006282613,0.00095773005,0.0001883868,0.00020838284,0.00028041558],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007682936,0.00015173377,0.000036034777,0.000014763438,0.000016787299,0.0000039657198,0.00023433102,0.000020968175,0.0011503792,0.00008622273,0.0005260454,0.99775106],"study_design_scores_gemma":[0.0009415189,0.000107882275,0.00034661804,0.0001857237,0.000046679113,0.00032600405,0.00016266544,0.933767,0.04964767,0.0072818026,0.0066076512,0.00057876174],"about_ca_topic_score_codex":0.000077866054,"about_ca_topic_score_gemma":0.00005249754,"teacher_disagreement_score":0.9971723,"about_ca_system_score_codex":0.00014526922,"about_ca_system_score_gemma":0.0000177979,"threshold_uncertainty_score":0.8564695},"labels":[],"label_agreement":null},{"id":"W2014517133","doi":"10.1109/icassp.2014.6854820","title":"Regularized constrained maximum likelihood linear regression for speech recognition","year":2014,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Hidden Markov model; Embedding; Regularization (linguistics); Pattern recognition (psychology); Computer science; Feature vector; Feature (linguistics); Artificial intelligence; Graph; Speech recognition; Maximization; Mathematics; Mathematical optimization; Theoretical computer science","score_opus":0.02884976113153596,"score_gpt":0.2597818766113098,"score_spread":0.23093211547977385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014517133","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007122225,0.0000071792583,0.9579344,0.0029042538,0.00045949678,0.00041954542,0.000009486299,0.00051923294,0.030624203],"genre_scores_gemma":[0.018325042,0.000010220848,0.978788,0.0014366447,0.00021962044,0.00006045539,0.00003830679,0.000017321188,0.001104392],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985408,0.00011412578,0.00030401704,0.00045969812,0.00024681925,0.00033453203],"domain_scores_gemma":[0.99863654,0.00038060462,0.00011689949,0.00045241296,0.00025505593,0.00015851224],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00075985776,0.0001743603,0.0002342943,0.00014746799,0.0001606181,0.00012527517,0.000411179,0.00013976982,0.00034897064],"category_scores_gemma":[0.0004238535,0.00013862019,0.00015747658,0.00022650743,0.000045408113,0.00035103527,0.00007438201,0.00009126399,0.00039350064],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023903573,0.000057701312,0.0000068471945,0.0000136913095,0.000010603784,0.0000023383282,0.000028806346,4.6365717e-8,0.006265487,0.001971971,0.0022694657,0.9893491],"study_design_scores_gemma":[0.0037466772,0.00039418478,0.00011150643,0.00017249801,0.000035248646,0.00012896335,0.000070384056,0.18108469,0.48899722,0.275141,0.049396873,0.00072076806],"about_ca_topic_score_codex":0.000007517506,"about_ca_topic_score_gemma":0.000007746629,"teacher_disagreement_score":0.9886284,"about_ca_system_score_codex":0.000021761167,"about_ca_system_score_gemma":0.000048164326,"threshold_uncertainty_score":0.56527674},"labels":[],"label_agreement":null},{"id":"W2015633636","doi":"10.1109/icassp.2014.6854823","title":"I-vector-based speaker adaptation of deep neural networks for French broadcast audio transcription","year":2014,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":119,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Speech recognition; Computer science; Speaker diarisation; Word error rate; Transcription (linguistics); Feature vector; Hidden Markov model; Artificial neural network; Artificial intelligence; Speaker recognition; Acoustic model; Vector quantization; Pattern recognition (psychology); Speech processing","score_opus":0.027729139316015762,"score_gpt":0.22933402300871766,"score_spread":0.2016048836927019,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2015633636","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007863239,0.000026135842,0.9896209,0.0004235755,0.00035455017,0.00019077421,0.0000016007679,0.00010626293,0.0014129359],"genre_scores_gemma":[0.82714456,0.0000010986062,0.17232339,0.00034084564,0.00007584228,0.000021075992,0.000009558611,0.0000063466555,0.00007729334],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991374,0.000071799426,0.00022877831,0.00022682753,0.0001614603,0.00017375847],"domain_scores_gemma":[0.9993014,0.0001977018,0.000082144965,0.0002210581,0.00013706238,0.00006064656],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002520087,0.000099682264,0.00014291472,0.00008353911,0.000058784022,0.000052784082,0.0002339065,0.000060897135,0.00012842088],"category_scores_gemma":[0.0000481758,0.000088197696,0.00012303436,0.00018446408,0.000024218298,0.00022483383,0.000008619801,0.000046303863,0.000009342182],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012814743,0.000060855295,0.00012091682,0.00001545841,0.000008712835,2.8959698e-7,0.00014037268,0.010184682,0.0016671927,0.004777859,0.00022965588,0.9827812],"study_design_scores_gemma":[0.0004883284,0.00012468513,0.0030141324,0.000006871755,0.000009959331,0.0000017617141,0.00001784527,0.9906013,0.004143672,0.00035656823,0.0011238747,0.00011100677],"about_ca_topic_score_codex":0.00005850014,"about_ca_topic_score_gemma":0.00015693356,"teacher_disagreement_score":0.9826702,"about_ca_system_score_codex":0.0000146537195,"about_ca_system_score_gemma":0.000011303766,"threshold_uncertainty_score":0.35965976},"labels":[],"label_agreement":null},{"id":"W2016084804","doi":"10.1109/icassp.2013.6639015","title":"Incoherent training of deep neural networks to de-correlate bottleneck features for speech recognition","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Hidden Markov model; Computer science; Speech recognition; Artificial neural network; Artificial intelligence; Bottleneck; Pattern recognition (psychology); Feature extraction; Context (archaeology); Feature (linguistics)","score_opus":0.032801787651130274,"score_gpt":0.2504833423333723,"score_spread":0.21768155468224204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016084804","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1033913,0.000030133291,0.8890082,0.0011667602,0.00038205506,0.0005792096,0.000002393824,0.00014142887,0.005298468],"genre_scores_gemma":[0.5989331,0.0000042786737,0.39929152,0.0012834086,0.000086445725,0.00012993946,0.000005461041,0.000010966979,0.00025489458],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99896646,0.000051706123,0.0002496476,0.00026753268,0.0001420739,0.00032261072],"domain_scores_gemma":[0.99910975,0.00027030925,0.00007902209,0.00021485376,0.00017006994,0.00015601993],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024551435,0.00012606954,0.00018115599,0.00011680621,0.00006803926,0.0001177335,0.00035079723,0.00009404073,0.0003846154],"category_scores_gemma":[0.00012655475,0.000108762695,0.0001113706,0.00023198254,0.000016631322,0.00032424755,0.00006928174,0.000095227464,0.00006957931],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007678837,0.000027010436,0.00006592985,0.0000063834987,0.000012233218,0.0000011391594,0.00032245647,0.0001574194,0.0004708701,0.0001867467,0.0017811981,0.99696094],"study_design_scores_gemma":[0.0005445429,0.0002632562,0.0093047265,0.000046352045,0.000018672132,0.00006243333,0.00035780083,0.9602211,0.018457294,0.010073303,0.00029321888,0.00035728273],"about_ca_topic_score_codex":0.000075261705,"about_ca_topic_score_gemma":0.00006911137,"teacher_disagreement_score":0.99660367,"about_ca_system_score_codex":0.000027364033,"about_ca_system_score_gemma":0.000015678272,"threshold_uncertainty_score":0.44352138},"labels":[],"label_agreement":null},{"id":"W2016489207","doi":"10.1080/07434610310001605801","title":"Research Issues of Speech Recognition Accuracy Measurements: Response to Bruce Wisenburn","year":2004,"lang":"en","type":"article","venue":"Augmentative and Alternative Communication","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Speech recognition; Psychology; Computer science; Natural language processing; Audiology; Linguistics; Medicine","score_opus":0.24923239326747362,"score_gpt":0.4405365790829401,"score_spread":0.19130418581546646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016489207","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9392027,0.00053615717,0.04198988,0.013920844,0.000078534846,0.0007380459,0.000022866807,0.00006334782,0.0034475927],"genre_scores_gemma":[0.8545277,0.0008267706,0.14407569,0.00032866758,0.000024573512,0.00008191139,0.000014272979,0.000009929045,0.000110480556],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9972461,0.0013356076,0.00032035325,0.0003184194,0.00057655043,0.00020296448],"domain_scores_gemma":[0.9971293,0.0010528835,0.00017371097,0.0005933346,0.0009463214,0.000104448605],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002550494,0.00012773104,0.00017467841,0.00037874316,0.00025793444,0.00011882698,0.00079593307,0.000036223555,0.00004607756],"category_scores_gemma":[0.0009997932,0.00012458219,0.000039275314,0.0006319602,0.00017482281,0.0008816155,0.0004197491,0.00018285694,0.00011830414],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042895827,0.00029717654,0.00021974632,0.000017490007,0.0001056851,0.0000062483387,0.014942116,0.000010182123,0.12030036,0.0030694087,0.00035350476,0.8602491],"study_design_scores_gemma":[0.0011633292,0.0004094016,0.0054939054,0.00034072192,0.0000091379525,0.0000095284995,0.00309892,0.00010214631,0.9357826,0.05210318,0.0012887642,0.00019836906],"about_ca_topic_score_codex":0.0005750704,"about_ca_topic_score_gemma":0.0000690765,"teacher_disagreement_score":0.86005074,"about_ca_system_score_codex":0.00016629549,"about_ca_system_score_gemma":0.00006550583,"threshold_uncertainty_score":0.5080314},"labels":[],"label_agreement":null},{"id":"W2017183468","doi":"10.1121/1.4805645","title":"Pitch affects voice onset time: A cross-linguistic study","year":2013,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Voice-onset time; Audiology; Duration (music); Psychology; Variation (astronomy); Acoustics; Speech recognition; Linguistics; Mathematics; Voice; Computer science; Physics; Medicine","score_opus":0.013919449524999374,"score_gpt":0.27194627925465964,"score_spread":0.2580268297296603,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017183468","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40635094,0.0001510079,0.5813878,0.009684056,0.0007164879,0.0006697638,0.000006088214,0.000058879916,0.0009749479],"genre_scores_gemma":[0.92025334,0.000032837626,0.07735112,0.0019218596,0.0001473977,0.0000029963774,6.320172e-8,0.0000101581,0.00028019928],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99819833,0.00035650926,0.00039008804,0.00012064071,0.0006803343,0.00025407286],"domain_scores_gemma":[0.99663323,0.001840714,0.00047954405,0.00051462784,0.00041197208,0.000119896344],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00096170406,0.00013857902,0.00031832565,0.000020595075,0.00024774057,0.00011294979,0.0017462722,0.000046505935,0.00020123592],"category_scores_gemma":[0.0011076289,0.00006931883,0.00037204128,0.00040115413,0.0004236459,0.00015177352,0.00035339256,0.0003895397,0.00015882635],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027022389,0.0057195225,0.007358414,0.00016524768,0.0022557895,0.000037255486,0.021484384,0.0025936244,0.035908613,0.000035791545,0.4681025,0.45606863],"study_design_scores_gemma":[0.0017633386,0.0019492883,0.084048286,0.000191388,0.0006052833,0.0004951848,0.0032987166,0.89451015,0.0032998947,0.0068450714,0.0024685434,0.00052487775],"about_ca_topic_score_codex":0.00005829336,"about_ca_topic_score_gemma":2.412943e-7,"teacher_disagreement_score":0.8919165,"about_ca_system_score_codex":0.000045638757,"about_ca_system_score_gemma":0.00009876985,"threshold_uncertainty_score":0.32450372},"labels":[],"label_agreement":null},{"id":"W2019393631","doi":"10.1109/icassp.2007.366866","title":"Bias Estimation and Correction in a Classifier using Product of Likelihood-Gaussians","year":2007,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"","keywords":"Classifier (UML); Computer science; Artificial intelligence; Pattern recognition (psychology); Feature vector; Gaussian; Linear discriminant analysis; Mixture model; Machine learning","score_opus":0.05380874776208271,"score_gpt":0.2863807500740105,"score_spread":0.23257200231192776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2019393631","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4222046,0.000013109472,0.5730675,0.0001376263,0.00021076143,0.00007573515,1.16128035e-7,0.000034596505,0.004255922],"genre_scores_gemma":[0.8558921,0.0000036352822,0.1439169,0.00005231598,0.000013682478,9.31404e-7,2.786833e-7,0.0000023903249,0.00011776025],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99942756,0.00001939105,0.00017842118,0.00015944242,0.000105851715,0.000109342494],"domain_scores_gemma":[0.9996782,0.000077787714,0.000056535675,0.00011649657,0.00003864184,0.000032363987],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050910935,0.000050138333,0.000079263526,0.00021015503,0.000025107554,0.000029048277,0.000065510794,0.000029182123,0.000016536418],"category_scores_gemma":[0.00011588502,0.00004360958,0.000015133489,0.00035804778,0.000019676438,0.00026410248,0.000023504123,0.00004401232,0.0000046942023],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000053550484,0.000049540762,0.005665468,0.000008290682,0.0000025790478,0.0000031768816,0.00033319782,0.000029550198,0.0060561444,0.000583979,0.00007000557,0.9871927],"study_design_scores_gemma":[0.00017640846,0.000028856892,0.057402432,0.00004627358,0.0000033627416,0.00005000339,0.00012960497,0.81495184,0.12622176,0.00081195385,0.00008102177,0.00009647975],"about_ca_topic_score_codex":0.00012601943,"about_ca_topic_score_gemma":0.00019310474,"teacher_disagreement_score":0.98709625,"about_ca_system_score_codex":0.000025552617,"about_ca_system_score_gemma":0.000026213816,"threshold_uncertainty_score":0.17783472},"labels":[],"label_agreement":null},{"id":"W2020639336","doi":"10.1109/ccece.2008.4564576","title":"A preliminary study of factors affecting the performance of a Playback Attack Detector","year":2008,"lang":"en","type":"article","venue":"Conference proceedings - Canadian Conference on Electrical and Computer Engineering","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Utterance; Phrase; Process (computing); Channel (broadcasting); Detector; Speaker verification; Speech recognition; Speaker recognition; Artificial intelligence; Computer network; Telecommunications","score_opus":0.03531933933036837,"score_gpt":0.21073675545623322,"score_spread":0.17541741612586484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2020639336","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9928598,0.000026864484,0.006294606,0.00007713116,0.00008527227,0.00034987665,0.0000021253936,0.000068338966,0.00023602217],"genre_scores_gemma":[0.9984274,0.000030292184,0.0014210715,0.000039354185,0.000034983506,0.000019022249,5.3212415e-7,0.000011925927,0.000015457079],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984641,0.000019274023,0.00035590964,0.0004142902,0.00030531938,0.0004411062],"domain_scores_gemma":[0.99888813,0.00019273687,0.00014089794,0.00019187576,0.0003051739,0.0002811647],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016125065,0.00026317264,0.0003738506,0.0003594806,0.00019069084,0.000097378586,0.000711985,0.000088596185,0.000014334866],"category_scores_gemma":[0.000058738,0.00020248622,0.000057046476,0.0006332829,0.00006568422,0.00026423347,0.00009985419,0.000325209,0.0000028869108],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003521307,0.001912565,0.37905997,0.0011011333,0.00087486947,0.000176476,0.092720576,0.0015812534,0.010125442,0.031764362,0.0008526935,0.4794785],"study_design_scores_gemma":[0.00035331142,0.0021183884,0.15569296,0.00013380821,0.000015530273,0.000072896204,0.00023624663,0.835632,0.0054046875,0.0000150358765,0.00002529796,0.000299775],"about_ca_topic_score_codex":0.0008633679,"about_ca_topic_score_gemma":0.00017603124,"teacher_disagreement_score":0.8340508,"about_ca_system_score_codex":0.0000533719,"about_ca_system_score_gemma":0.0002475229,"threshold_uncertainty_score":0.8257148},"labels":[],"label_agreement":null},{"id":"W2020683423","doi":"10.1109/asru.2013.6707749","title":"Improvements to Deep Convolutional Neural Networks for LVCSR","year":2013,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Dropout (neural networks); Pooling; Convolutional neural network; Word error rate; Speech recognition; Task (project management); Artificial intelligence; Deep neural networks; Baseline (sea); Deep learning; Adaptation (eye); Machine learning; Pattern recognition (psychology)","score_opus":0.033450896165499386,"score_gpt":0.26621165720297973,"score_spread":0.23276076103748033,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2020683423","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022566398,0.000041817355,0.98872066,0.0021005247,0.002338667,0.0011243811,0.0000135800565,0.00023608273,0.0031676297],"genre_scores_gemma":[0.17131759,0.000013345371,0.8078754,0.012125957,0.0008284998,0.0018755498,0.00009267051,0.00003670589,0.005834311],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983669,0.00003463136,0.000308762,0.00065773947,0.00024891368,0.00038306115],"domain_scores_gemma":[0.99868,0.00015319177,0.00010436142,0.0005631971,0.00028008534,0.00021919115],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001956175,0.00023186675,0.00024526237,0.00012324098,0.0000983808,0.000377629,0.0011108032,0.000199983,0.00051499973],"category_scores_gemma":[0.000063899475,0.00020900705,0.00019506128,0.00009844097,0.000019109902,0.00015479265,0.001184283,0.00019866799,0.00022670766],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012342483,0.00010682279,0.00012735197,0.00004282722,0.00010105115,0.0000024635528,0.00007021848,0.0032492673,0.000059219154,0.024399921,0.047361918,0.9244666],"study_design_scores_gemma":[0.00019581764,0.00004449988,0.0006137104,0.000015151351,0.000008386768,0.000002556437,0.0000068143704,0.98540515,0.0002714021,0.0093775345,0.003763435,0.00029554233],"about_ca_topic_score_codex":0.00007403371,"about_ca_topic_score_gemma":0.000024029638,"teacher_disagreement_score":0.98215586,"about_ca_system_score_codex":0.00007141095,"about_ca_system_score_gemma":0.000056103847,"threshold_uncertainty_score":0.852306},"labels":[],"label_agreement":null},{"id":"W2021552769","doi":"10.1121/1.4743145","title":"Acoustic and perceptual speaker normalization","year":2000,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Normalization (sociology); Formant; Vowel; Perception; Speech recognition; Weighting; Acoustics; Computer science; Rounding; Mathematics; Psychology; Physics","score_opus":0.01212370106382214,"score_gpt":0.22852819087477924,"score_spread":0.2164044898109571,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2021552769","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039606646,0.00014049608,0.9532676,0.0059261634,0.00012185183,0.000070797985,0.0000022200713,0.000013955634,0.000850269],"genre_scores_gemma":[0.8271663,0.001247678,0.16697149,0.004094543,0.00015184366,4.6432058e-7,1.2648198e-7,0.000008677502,0.0003588701],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99899215,0.00013769329,0.000278311,0.00007019358,0.00037879392,0.00014284585],"domain_scores_gemma":[0.99903446,0.00037519753,0.00018579255,0.00021977413,0.00011596077,0.000068802896],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000400151,0.00008316946,0.00016995355,0.0000120153645,0.00015653584,0.00003286443,0.00062361226,0.0000392524,0.00040669861],"category_scores_gemma":[0.000106452724,0.000042055613,0.00017985601,0.00023806612,0.00039622045,0.00016465623,0.00009621825,0.00019298034,0.0000132697705],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006510492,0.00017507363,0.00013314183,0.00002602163,0.00014011943,0.0000021148762,0.0039085085,0.004358612,0.01124756,0.000031216736,0.03208763,0.9478249],"study_design_scores_gemma":[0.0005004167,0.0002775764,0.008145893,0.00008046579,0.00024126316,0.0005009985,0.0019263602,0.97874075,0.0012653592,0.0015364084,0.006600516,0.00018400326],"about_ca_topic_score_codex":0.000011258559,"about_ca_topic_score_gemma":2.4742252e-7,"teacher_disagreement_score":0.9743821,"about_ca_system_score_codex":0.000020521835,"about_ca_system_score_gemma":0.000042587708,"threshold_uncertainty_score":0.44530648},"labels":[],"label_agreement":null},{"id":"W2022164734","doi":"10.1121/1.4778214","title":"Glottal-wave and vocal-tract-area-function estimations from vowel sounds based on realistic assumptions and models","year":2005,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Vocal tract; Vowel; Acoustics; Glottis; Mathematics; Inverse filter; Speech recognition; Inverse; Computer science; Physics; Medicine; Larynx; Anatomy; Geometry","score_opus":0.033551128964869295,"score_gpt":0.2502150606801642,"score_spread":0.2166639317152949,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2022164734","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0074999146,0.00007658781,0.9783213,0.013551709,0.00008328523,0.00007076984,0.000021161177,0.000017657076,0.0003575978],"genre_scores_gemma":[0.69692916,0.00013737593,0.3001539,0.002666245,0.000077485376,0.0000011891651,7.8024703e-7,0.0000059906306,0.000027875523],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99889064,0.00013508655,0.00031395323,0.000115890456,0.00040542366,0.00013901602],"domain_scores_gemma":[0.9976968,0.0014800534,0.00029728937,0.00027862014,0.00014061348,0.00010662781],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039684933,0.00011353417,0.00020176116,0.000028221317,0.00027824074,0.00006773732,0.00029806705,0.00005939786,0.00004318555],"category_scores_gemma":[0.00022620572,0.00006532903,0.0001657066,0.0001769665,0.00035509342,0.00024064435,0.000083956365,0.0002769512,0.0000033187007],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028803403,0.0011705165,0.0001346778,0.000039857096,0.00040555093,0.0000034098098,0.0031351813,0.23373386,0.0060341447,0.00066000567,0.041168254,0.7132265],"study_design_scores_gemma":[0.0002688138,0.0001311695,0.0049601174,0.00005249644,0.00017917102,0.000035468518,0.00018971451,0.98259735,0.00009128671,0.011150795,0.00026802023,0.00007560735],"about_ca_topic_score_codex":0.00005510761,"about_ca_topic_score_gemma":0.0000016977367,"teacher_disagreement_score":0.74886346,"about_ca_system_score_codex":0.0000476742,"about_ca_system_score_gemma":0.000059148875,"threshold_uncertainty_score":0.26640406},"labels":[],"label_agreement":null},{"id":"W2022663094","doi":"10.1145/1979742.1979700","title":"Ubiquitous voice synthesis","year":2011,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Speech synthesis; Interactivity; Ubiquitous computing; Human–computer interaction; Embodied cognition; Phone; Production (economics); Multimedia; Speech recognition; Artificial intelligence; Linguistics","score_opus":0.0597872934221393,"score_gpt":0.22510852878167537,"score_spread":0.16532123535953608,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2022663094","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0045538964,0.000013490348,0.31763205,0.00030550145,0.0002391769,0.00005249673,5.7948915e-7,0.0004568427,0.67674595],"genre_scores_gemma":[0.59954256,0.0000111743475,0.39688188,0.0010870324,0.00004080688,0.000025157336,1.0241918e-7,0.000007030359,0.0024042896],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99935365,0.000036466638,0.00010872632,0.0002066715,0.000128332,0.00016613741],"domain_scores_gemma":[0.9993634,0.00012600767,0.00002608715,0.0003600959,0.000041866493,0.00008249585],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00014363388,0.00007282881,0.00008358514,0.000073049654,0.000054571225,0.000047007266,0.0005642106,0.000036831112,0.0018307023],"category_scores_gemma":[0.000094281626,0.000058981153,0.000054649296,0.00016856093,0.000018935236,0.00026528968,0.000086554894,0.00003816237,0.0032358763],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000032148243,0.00010857345,0.00025745764,0.0000041778103,0.000018450392,0.000039707833,0.00044397757,2.6072957e-8,0.00052145944,0.05681933,0.0046828017,0.9371008],"study_design_scores_gemma":[0.00021908976,0.000085718246,0.015003716,0.000029465853,0.00002355598,0.0001634198,0.00022786063,0.0062517608,0.91496545,0.024023287,0.038298454,0.0007082309],"about_ca_topic_score_codex":0.000058420126,"about_ca_topic_score_gemma":0.000013567323,"teacher_disagreement_score":0.9363926,"about_ca_system_score_codex":0.000009624198,"about_ca_system_score_gemma":0.000017610864,"threshold_uncertainty_score":0.99908173},"labels":[],"label_agreement":null},{"id":"W2023289124","doi":"10.1109/isspa.2012.6310464","title":"Developing a hybrid language model for open vocabulary automatic speech recognition in a lecture speech task","year":2012,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Vocabulary; Task (project management); Lexicon; Speech recognition; Natural language processing; Artificial intelligence; Language model; Word (group theory); Domain (mathematical analysis); Linguistics","score_opus":0.06461673165344403,"score_gpt":0.3074663054317703,"score_spread":0.24284957377832625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2023289124","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09774013,0.00009000599,0.8955966,0.001078575,0.0001693264,0.00092317193,0.000014404243,0.00023795583,0.004149819],"genre_scores_gemma":[0.21341226,0.000007742657,0.78383374,0.0020974798,0.000060216527,0.00015600867,0.000030421717,0.000018094923,0.00038404996],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984828,0.000083511084,0.00033807414,0.0003686807,0.00021758172,0.0005093569],"domain_scores_gemma":[0.9991529,0.00019140284,0.00008958773,0.00036255748,0.00007928536,0.00012425738],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00089248223,0.00019368425,0.00026855987,0.0002456351,0.00009771503,0.0002792591,0.00086348463,0.00008254289,0.00015338785],"category_scores_gemma":[0.00022398285,0.00017396404,0.00007849151,0.00037879337,0.0000149549,0.0013609154,0.0003029064,0.0001243672,0.00023018815],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007405428,0.00009959449,0.00008235532,0.000041975865,0.000014730733,0.000018866547,0.0008957534,0.0000044997746,0.0006234887,0.000642343,0.0011602622,0.9964087],"study_design_scores_gemma":[0.00080789777,0.000027143602,0.0003153046,0.0001356882,0.000013178146,0.0002329572,0.00015170663,0.88968617,0.088271655,0.019517241,0.0003620375,0.0004790439],"about_ca_topic_score_codex":0.00008543381,"about_ca_topic_score_gemma":0.0001483269,"teacher_disagreement_score":0.99592966,"about_ca_system_score_codex":0.00013554364,"about_ca_system_score_gemma":0.00015637475,"threshold_uncertainty_score":0.7094048},"labels":[],"label_agreement":null},{"id":"W2024218073","doi":"10.1145/1066078.1066081","title":"A speech synthesizer for Persian text using a neural network with a smooth ergodic HMM","year":2005,"lang":"en","type":"article","venue":"ACM Transactions on Asian Language Information Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Preprocessor; Speech recognition; Speech synthesis; Hidden Markov model; Artificial neural network; Intelligibility (philosophy); Natural language processing; Artificial intelligence; Active listening; Language model; Time delay neural network","score_opus":0.015612561096692375,"score_gpt":0.2520033667490014,"score_spread":0.23639080565230905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2024218073","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010136163,0.00005112241,0.9830914,0.0029098424,0.000088298715,0.00042527355,0.000012621152,0.00036967374,0.0029156057],"genre_scores_gemma":[0.55332494,0.0000018677658,0.444677,0.0017598956,0.00008511516,0.000054461772,0.0000056400354,0.000015688764,0.00007540989],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99857026,0.000040055067,0.00038479827,0.00024286866,0.00034176317,0.00042023446],"domain_scores_gemma":[0.99895155,0.00010200816,0.00021258809,0.00045485512,0.00014498318,0.00013399124],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025100625,0.00023293258,0.00020209241,0.0003323086,0.00060354493,0.0005964686,0.00053905847,0.00010280376,0.00014064614],"category_scores_gemma":[0.000058322712,0.00020109753,0.00011550345,0.0006760423,0.000049852224,0.0037244526,0.00000919282,0.00020512867,0.00006414239],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051379797,0.000043337517,0.0000026578607,0.00004908973,0.000018371753,0.000003685921,0.004878422,0.0040760487,0.00004718399,0.000060961447,0.000030739884,0.9907381],"study_design_scores_gemma":[0.0016871786,0.0002139163,0.0001941792,0.00046916128,0.000104672734,0.0005417122,0.0078114974,0.97428256,0.005775776,0.0002508177,0.007864279,0.000804249],"about_ca_topic_score_codex":0.000013020274,"about_ca_topic_score_gemma":0.000044451008,"teacher_disagreement_score":0.98993385,"about_ca_system_score_codex":0.00012666718,"about_ca_system_score_gemma":0.00015273593,"threshold_uncertainty_score":0.82005197},"labels":[],"label_agreement":null},{"id":"W2026159472","doi":"10.1016/j.engappai.2009.09.006","title":"An efficient speech recognition system in adverse conditions using the nonparametric regression","year":2009,"lang":"en","type":"article","venue":"Engineering Applications of Artificial Intelligence","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Speech recognition; Robustness (evolution); Hidden Markov model; Artificial neural network; Artificial intelligence; Noise (video); Pattern recognition (psychology)","score_opus":0.03786793650265436,"score_gpt":0.2989782076400465,"score_spread":0.26111027113739216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2026159472","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17374596,0.0000352284,0.825417,0.00007316531,0.000082460414,0.00037077215,0.000007307515,0.00013968558,0.00012844581],"genre_scores_gemma":[0.863084,0.0000051857337,0.13678664,0.00001672068,0.00003972832,0.000054635544,0.00000592713,0.000005656026,0.0000015102739],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988271,0.00004415111,0.00043980769,0.00028149315,0.00022266748,0.00018478524],"domain_scores_gemma":[0.99892896,0.00018278872,0.00012638488,0.0005542236,0.0001417196,0.00006592548],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042487332,0.00012015977,0.00014049538,0.0004658639,0.00012312642,0.0000501573,0.0005599047,0.00006373441,0.000012023858],"category_scores_gemma":[0.000081310915,0.00010298703,0.000059308408,0.001856868,0.000035830988,0.00018898006,0.000024841253,0.00014034209,0.000049511866],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000059402146,0.00034107323,0.000011473071,0.000022260836,0.000005788327,0.0000046936916,0.00028174755,0.17534228,0.025477657,0.034682963,0.0000051137617,0.76381904],"study_design_scores_gemma":[0.000014820908,0.000026542719,0.00023332544,0.000083790765,0.0000063989237,0.00001818976,0.00031252325,0.8321556,0.16570108,0.0013083778,0.000025693173,0.00011368156],"about_ca_topic_score_codex":0.000034624845,"about_ca_topic_score_gemma":0.0000032384573,"teacher_disagreement_score":0.7637053,"about_ca_system_score_codex":0.00009260951,"about_ca_system_score_gemma":0.000033103977,"threshold_uncertainty_score":0.41996893},"labels":[],"label_agreement":null},{"id":"W2029459011","doi":"10.1155/2008/258184","title":"On the Use of Complementary Spectral Features for Speaker Recognition","year":2007,"lang":"en","type":"article","venue":"EURASIP Journal on Advances in Signal Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Additive white Gaussian noise; Mel-frequency cepstrum; Speech recognition; Computer science; Cepstrum; Vocal tract; Pattern recognition (psychology); Crest factor; Linear prediction; Speaker recognition; Noise (video); White noise; Artificial intelligence; Mathematics; Bandwidth (computing); Feature extraction; Telecommunications","score_opus":0.08896500203753117,"score_gpt":0.3259021926772365,"score_spread":0.23693719063970536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2029459011","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09635004,0.0007473969,0.8962305,0.0025773768,0.00048030386,0.00040782863,0.000013879898,0.000047530466,0.00314512],"genre_scores_gemma":[0.8338726,0.00012680484,0.16196142,0.0036690312,0.00029556692,0.000006399962,0.0000036328438,0.00001785705,0.000046674442],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99850804,0.00010103752,0.0004539017,0.00021610939,0.0004158573,0.00030504892],"domain_scores_gemma":[0.9978492,0.0014543876,0.00035776375,0.00011228848,0.00015519756,0.00007111346],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001073251,0.0001481555,0.00017606151,0.00025344826,0.00023892394,0.00020551503,0.00037627705,0.00003394684,0.00009415034],"category_scores_gemma":[0.0002069213,0.000099194905,0.000101667574,0.00033527514,0.00006331354,0.0011220537,0.000023066941,0.00035266363,0.000006939243],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002840396,0.00013768405,0.00014419002,0.000021073238,0.0000080940845,0.0000376427,0.00020778232,0.00023758474,0.0008652513,0.0020133415,0.00047606722,0.99556726],"study_design_scores_gemma":[0.0063029476,0.0040474054,0.020292165,0.0057968576,0.00007462863,0.0015885463,0.002100648,0.031169666,0.39388135,0.46396425,0.0689115,0.0018700216],"about_ca_topic_score_codex":0.000001084205,"about_ca_topic_score_gemma":0.000017163671,"teacher_disagreement_score":0.9936972,"about_ca_system_score_codex":0.000073498726,"about_ca_system_score_gemma":0.00004039838,"threshold_uncertainty_score":0.40450507},"labels":[],"label_agreement":null},{"id":"W2032491068","doi":"10.1121/1.4788447","title":"ArtiSynth designing a modular 3D articulatory speech synthesizer","year":2005,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Modular design; Component (thermodynamics); Vocal tract; Interface (matter); Rendering (computer graphics); Scripting language; Speech synthesis; Parametric statistics; Parametric model; Speech recognition; Computer vision","score_opus":0.015587821268608273,"score_gpt":0.23411663528967858,"score_spread":0.2185288140210703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2032491068","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020672113,0.0002604255,0.9677894,0.010612883,0.00019980337,0.00010358644,0.0000013269321,0.000027664588,0.000332757],"genre_scores_gemma":[0.43068314,0.000126883,0.5662501,0.0026658368,0.00017945227,9.6165e-7,2.3469157e-8,0.000010303671,0.00008330684],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979979,0.00031004485,0.00052542554,0.00012663307,0.00074088015,0.0002991526],"domain_scores_gemma":[0.9975627,0.0010692143,0.0005087005,0.00051648065,0.00021610122,0.00012677742],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011881308,0.00014979657,0.0003269241,0.000027616941,0.00021754813,0.00004777213,0.0013455715,0.00006717796,0.000116757175],"category_scores_gemma":[0.00048115238,0.00007913324,0.0005082437,0.000360251,0.00042520429,0.00025558923,0.00023101739,0.00038890974,0.000036293004],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054234344,0.00036177677,0.000052340416,0.000024358345,0.00035707478,0.0000073318724,0.0013958268,0.010183139,0.08848092,0.0000521702,0.022085024,0.8769458],"study_design_scores_gemma":[0.00030247655,0.00012837687,0.0010110129,0.00013742162,0.00023409698,0.0003639315,0.0005546703,0.9206722,0.0697394,0.001321302,0.005335598,0.00019952399],"about_ca_topic_score_codex":0.000008150695,"about_ca_topic_score_gemma":2.2964957e-7,"teacher_disagreement_score":0.910489,"about_ca_system_score_codex":0.00007678367,"about_ca_system_score_gemma":0.00010556826,"threshold_uncertainty_score":0.322696},"labels":[],"label_agreement":null},{"id":"W2034785571","doi":"10.1109/wosspa.2013.6602390","title":"Crim's French speech transcription system for ETAPE 2011","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Discriminative model; Speech recognition; Language model; Decoding methods; Artificial intelligence; Confusion; Transcription (linguistics); Algorithm","score_opus":0.029538230472533733,"score_gpt":0.22587332114791253,"score_spread":0.1963350906753788,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2034785571","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010102507,0.000042162053,0.9310869,0.0016567919,0.00074197096,0.0005458166,0.000003328453,0.00049763295,0.055322867],"genre_scores_gemma":[0.62804765,0.0000054253383,0.36381483,0.0005475085,0.0001051403,0.00020170654,0.0000040979394,0.000010614774,0.007263063],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99910885,0.000034027376,0.00019552534,0.00027487162,0.00016749566,0.00021925198],"domain_scores_gemma":[0.99932444,0.00007818178,0.000037932346,0.00030479045,0.00016082259,0.00009385616],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000181027,0.00010334076,0.0001317367,0.00008964026,0.00008550625,0.00020335021,0.00040003736,0.00006672978,0.0015742762],"category_scores_gemma":[0.00001348996,0.0000833058,0.000107863525,0.00009109214,0.000013120163,0.0005433644,0.00001991468,0.000043274842,0.0033790611],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001965427,0.00008163899,0.00006779773,0.00009467862,0.000027928685,0.0000034185214,0.00021739621,5.1020913e-7,0.02011081,0.0357428,0.08702629,0.8566248],"study_design_scores_gemma":[0.002459129,0.00043004073,0.012685589,0.00014633247,0.00007559039,0.00026013496,0.0009893207,0.26954037,0.61343575,0.022821782,0.07564146,0.0015145248],"about_ca_topic_score_codex":0.00029162582,"about_ca_topic_score_gemma":0.000022702137,"teacher_disagreement_score":0.8551102,"about_ca_system_score_codex":0.000031227864,"about_ca_system_score_gemma":0.000020684423,"threshold_uncertainty_score":0.99933845},"labels":[],"label_agreement":null},{"id":"W2035327776","doi":"10.1016/j.engappai.2012.06.006","title":"Adaptation to non-native speech using evolutionary-based discriminative linear transforms","year":2012,"lang":"en","type":"article","venue":"Engineering Applications of Artificial Intelligence","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Computer science; Hidden Markov model; Speech recognition; Discriminative model; Adaptation (eye); Maximum a posteriori estimation; Artificial intelligence; Word error rate; Pattern recognition (psychology); Vocabulary; Genetic algorithm; Machine learning; Maximum likelihood; Statistics; Mathematics","score_opus":0.05886253252009006,"score_gpt":0.30295699338179793,"score_spread":0.24409446086170788,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2035327776","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009487421,0.000031036863,0.98943806,0.00020346537,0.000118572556,0.00045773972,0.000014814152,0.00009986282,0.00014902426],"genre_scores_gemma":[0.5365557,0.0000016289738,0.4632528,0.000020156034,0.000057378347,0.00009500109,0.0000038099301,0.0000075301405,0.0000059782374],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99891293,0.000016233447,0.00034730826,0.00022439875,0.0002488131,0.0002502869],"domain_scores_gemma":[0.99907655,0.0001752154,0.000075993485,0.00030022234,0.00023219416,0.00013980005],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025676936,0.00013642969,0.00014313139,0.00031040848,0.0000952895,0.00002432621,0.00039666047,0.000052821106,0.00002586224],"category_scores_gemma":[0.0000957768,0.00014082209,0.0000728914,0.00096945924,0.000037500828,0.00037729923,0.000033992885,0.00009757128,0.00008871088],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012585085,0.00038960826,0.000024664856,0.000043795175,0.000026272322,5.906398e-7,0.0040621473,0.21691734,0.023596354,0.08099215,0.00001256621,0.67392194],"study_design_scores_gemma":[0.0000102162785,0.00002251723,0.00010768317,0.00002251305,0.0000072182916,0.0000018033915,0.0002784605,0.69052595,0.3077846,0.00083625637,0.00027405305,0.0001287657],"about_ca_topic_score_codex":0.000055735643,"about_ca_topic_score_gemma":0.0000039200913,"teacher_disagreement_score":0.67379314,"about_ca_system_score_codex":0.000088097506,"about_ca_system_score_gemma":0.000055220673,"threshold_uncertainty_score":0.57425576},"labels":[],"label_agreement":null},{"id":"W2035647012","doi":"10.1121/1.3508941","title":"An acoustic study of [liquid + stop] sequences by native and second-language speakers of English.","year":2010,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Percept; Context (archaeology); Variation (astronomy); Perception; Speech production; First language; Variety (cybernetics); Linguistics; Formant; Computer science; Sample (material); Acoustics; Psychology; Speech recognition; Geography; Artificial intelligence; Physics; Vowel","score_opus":0.009730380559663037,"score_gpt":0.25841855956011117,"score_spread":0.24868817900044812,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2035647012","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93423444,0.00008588488,0.06480381,0.0003291819,0.0002412901,0.00013795821,0.00001737184,0.000008349069,0.00014170643],"genre_scores_gemma":[0.9683573,0.000053673597,0.031229261,0.00026392486,0.00007152621,6.7849703e-7,1.1776948e-7,0.0000063263415,0.00001717173],"study_design_codex":"bench_or_experimental","study_design_gemma":"qualitative","domain_scores_codex":[0.99842185,0.0002774329,0.00046879877,0.00011791027,0.0005566855,0.00015729935],"domain_scores_gemma":[0.9973304,0.0009659544,0.00073968805,0.0003586562,0.0005074875,0.00009778888],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00096427987,0.000121174504,0.00036917444,0.000028198054,0.000097833836,0.000019285608,0.0011578257,0.000055795845,0.000089398294],"category_scores_gemma":[0.00063873717,0.00006564351,0.00017039529,0.00028616367,0.000831678,0.00021365118,0.00016013361,0.0004241216,3.2174398e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019199804,0.0012448357,0.00024548348,0.0000624132,0.00042882253,0.0000026341827,0.07773527,0.0003763917,0.884137,0.00001826627,0.003660801,0.0318961],"study_design_scores_gemma":[0.0034158605,0.012353095,0.007949498,0.00023916732,0.0011805963,0.00017530438,0.41668937,0.21208234,0.34350625,0.0011345437,0.00053524645,0.0007387556],"about_ca_topic_score_codex":0.0000712598,"about_ca_topic_score_gemma":0.0000065528693,"teacher_disagreement_score":0.54063076,"about_ca_system_score_codex":0.000015411728,"about_ca_system_score_gemma":0.000085250336,"threshold_uncertainty_score":0.30643523},"labels":[],"label_agreement":null},{"id":"W2036242736","doi":"10.1109/icassp.2013.6638952","title":"A deep convolutional neural network using heterogeneous pooling for trading acoustic invariance with phonetic confusion","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":188,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Word error rate; Speech recognition; Pooling; Convolutional neural network; TIMIT; Artificial intelligence; Dropout (neural networks); Deep learning; Artificial neural network; Hidden Markov model; Pattern recognition (psychology); Machine learning","score_opus":0.032079038474955385,"score_gpt":0.23135305306931908,"score_spread":0.1992740145943637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2036242736","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13299626,0.00007070028,0.8657231,0.00017891871,0.00023690276,0.00038118992,7.256913e-7,0.00011821048,0.0002940477],"genre_scores_gemma":[0.69008684,0.0000016338148,0.30895498,0.0007574912,0.00010971242,0.000039138242,0.0000016054636,0.000009776363,0.000038809074],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99884766,0.0000428021,0.00020477915,0.00033170579,0.00018605785,0.00038701756],"domain_scores_gemma":[0.99919915,0.00027138038,0.00008101507,0.00019099678,0.00013693649,0.00012050246],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012071937,0.00014606197,0.00016632843,0.0000565278,0.00026792337,0.00023017591,0.00028154562,0.000052610078,0.000292583],"category_scores_gemma":[0.00003160375,0.00011900039,0.000060530998,0.00020590144,0.0000432714,0.00033453805,0.000052736414,0.000068599096,0.000030005745],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015610526,0.0002979954,0.001164795,0.0001456654,0.00024916424,0.000094715884,0.000878106,0.68696994,0.07857637,0.012279733,0.0015512076,0.21763623],"study_design_scores_gemma":[0.0003852696,0.000069241236,0.0003254412,0.000036699563,0.00001432629,0.00025919898,0.000019967963,0.995303,0.0013367928,0.0020264832,0.00003265871,0.00019096766],"about_ca_topic_score_codex":0.000054192624,"about_ca_topic_score_gemma":0.000030035106,"teacher_disagreement_score":0.5570906,"about_ca_system_score_codex":0.000044185956,"about_ca_system_score_gemma":0.00005173636,"threshold_uncertainty_score":0.48526952},"labels":[],"label_agreement":null},{"id":"W2038598237","doi":"10.1109/asru.2013.6707717","title":"Cross-lingual context sharing and parameter-tying for multi-lingual speech recognition","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Speech recognition; Context (archaeology); Tying; Natural language processing; Artificial intelligence; Subspace topology; Covariance; Language model; Task (project management); Dialog box","score_opus":0.12312297462305719,"score_gpt":0.3351410842406935,"score_spread":0.2120181096176363,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2038598237","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8207644,0.000045661924,0.1768491,0.0001586009,0.00029492247,0.0005004421,0.000005589589,0.0002556737,0.0011256097],"genre_scores_gemma":[0.5211993,0.000010408636,0.47678715,0.00075072737,0.00009233097,0.000093677365,0.0000073378123,0.000015131427,0.0010439686],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985946,0.000026080124,0.00032200507,0.0005543923,0.00015385317,0.00034908188],"domain_scores_gemma":[0.99883354,0.00037999405,0.00009186152,0.00026427105,0.0002836116,0.00014670745],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036546402,0.00017116628,0.00019797006,0.00012524186,0.00022543513,0.0009646366,0.00034517352,0.00010345416,0.00039950418],"category_scores_gemma":[0.00061858195,0.00015582333,0.00008881694,0.00012363694,0.00005811612,0.00094024517,0.00016328343,0.000108164895,0.00029564655],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000048107713,0.000042677133,0.0013615094,0.000016949685,0.0000149314665,0.0000035661635,0.00025225728,2.2834753e-7,0.0008700078,0.00017716373,0.00007546796,0.9971804],"study_design_scores_gemma":[0.0034656292,0.00025273414,0.0059545822,0.00015292496,0.000028651502,0.00020259275,0.0010216592,0.58398485,0.38299602,0.019418456,0.0014096386,0.0011122403],"about_ca_topic_score_codex":0.00020789803,"about_ca_topic_score_gemma":0.000052700823,"teacher_disagreement_score":0.9960682,"about_ca_system_score_codex":0.000024091445,"about_ca_system_score_gemma":0.000025715231,"threshold_uncertainty_score":0.93020135},"labels":[],"label_agreement":null},{"id":"W2041644614","doi":"10.1121/1.4783150","title":"Experimental and numerical determination of the surface deformation of a synthetic model of the human vocal folds.","year":2008,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"von Mises yield criterion; Materials science; Synthetic data; Mechanics; Deformation (meteorology); Vocal folds; Stress (linguistics); Displacement (psychology); Acoustics; Oscillation (cell signaling); Experimental data; Amplitude; Surface (topology); Finite element method; Computer science; Optics; Mathematics; Geometry; Physics; Algorithm; Composite material; Thermodynamics","score_opus":0.02363772537464647,"score_gpt":0.2537168821655702,"score_spread":0.23007915679092372,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2041644614","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55088896,0.000060599836,0.447602,0.0012064677,0.000060436836,0.000102649916,0.0000037158038,0.0000031671705,0.00007200307],"genre_scores_gemma":[0.94947255,0.000037080725,0.0502557,0.00019650959,0.000013157451,6.1646205e-7,5.0795837e-8,0.0000053378194,0.000019022958],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983907,0.00020375213,0.00054176105,0.00007434537,0.0006644147,0.00012503375],"domain_scores_gemma":[0.9981885,0.00032366707,0.0008895532,0.00036636286,0.0001919191,0.00004003134],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047325852,0.00010194425,0.00028459888,0.000013911464,0.00020936747,0.000007274127,0.0009833183,0.000053256896,0.000010257869],"category_scores_gemma":[0.00012271738,0.000044861437,0.00040374167,0.00025399914,0.0010006332,0.00013971984,0.00031218305,0.00019959788,3.5202106e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010224102,0.0008872679,0.001000747,0.00010640664,0.00017466703,3.1816734e-7,0.016297009,0.012459899,0.94148844,0.00019765629,0.0014594499,0.025825866],"study_design_scores_gemma":[0.00026062157,0.00012305568,0.003077015,0.00008850621,0.00008825798,0.000096706965,0.00092919485,0.7640857,0.23022956,0.0009480329,0.000009494634,0.00006383304],"about_ca_topic_score_codex":0.000027933895,"about_ca_topic_score_gemma":1.7653487e-7,"teacher_disagreement_score":0.75162584,"about_ca_system_score_codex":0.00004135572,"about_ca_system_score_gemma":0.00007947979,"threshold_uncertainty_score":0.36868748},"labels":[],"label_agreement":null},{"id":"W2044054970","doi":"10.1109/asru.2011.6163886","title":"Multi-taper MFCC features for speaker verification using I-vectors","year":2011,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique; Computer Research Institute of Montréal","funders":"National Institute of Standards and Technology","keywords":"NIST; Mel-frequency cepstrum; Computer science; Speech recognition; Speaker recognition; Pattern recognition (psychology); Classifier (UML); Speaker verification; Hamming distance; Hamming code; Microphone; Variance (accounting); Artificial intelligence; Feature extraction; Algorithm; Decoding methods; Telecommunications","score_opus":0.16905148776932388,"score_gpt":0.2935253001225161,"score_spread":0.12447381235319221,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2044054970","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02220382,0.000019175171,0.9689353,0.000093763454,0.00034130376,0.00018657272,0.0000017044866,0.00016245713,0.008055919],"genre_scores_gemma":[0.22603068,0.0000025344625,0.7725333,0.0003393213,0.000027918311,0.00001288607,0.0000012991474,0.0000065861623,0.0010454465],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99942243,0.000020556821,0.000105381776,0.00022395351,0.00008553632,0.00014214667],"domain_scores_gemma":[0.99954253,0.000040163894,0.000038450748,0.00025142435,0.000075269374,0.0000521387],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000116892144,0.000076760094,0.00007390636,0.00006640298,0.00008104271,0.00005803488,0.00025581845,0.00004785639,0.0002705008],"category_scores_gemma":[0.000049337883,0.000062407664,0.000064181746,0.0001140471,0.000017035385,0.00026812212,0.000028623808,0.000032448024,0.00008424711],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006168219,0.0007959479,0.0053819637,0.000049586473,0.0001301602,0.000009688039,0.005942648,0.000008886801,0.12891644,0.052384894,0.00883203,0.79748607],"study_design_scores_gemma":[0.001236119,0.00010694879,0.13560632,0.0000342117,0.000041437703,0.00006667305,0.00039420096,0.2345571,0.6066414,0.0021922372,0.018283747,0.00083955924],"about_ca_topic_score_codex":0.00007963918,"about_ca_topic_score_gemma":0.000029166009,"teacher_disagreement_score":0.79664654,"about_ca_system_score_codex":0.0000185081,"about_ca_system_score_gemma":0.00001975319,"threshold_uncertainty_score":0.2961794},"labels":[],"label_agreement":null},{"id":"W2048311555","doi":"10.1121/1.2918787","title":"Suppressing aliasing noise in the speech feature domain for automatic speech recognition","year":2008,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"","keywords":"Computer science; Speech recognition; Noise (video); Aliasing; Feature (linguistics); Baseband; Voice activity detection; Speech processing; Linear predictive coding; Artificial intelligence; Pattern recognition (psychology); Telecommunications","score_opus":0.030908986815525338,"score_gpt":0.2663822704639665,"score_spread":0.23547328364844117,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2048311555","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16619758,0.00019117953,0.7977467,0.03466908,0.0003663272,0.00044943858,0.000011858059,0.000028300576,0.0003395297],"genre_scores_gemma":[0.14790885,0.00017531295,0.8479983,0.0036630936,0.00020029055,0.0000035629596,5.819945e-7,0.000012089976,0.00003786442],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998021,0.00045366937,0.00045601337,0.000121180834,0.00066686794,0.00028127572],"domain_scores_gemma":[0.9968154,0.001998459,0.0005298851,0.00039217313,0.00020758627,0.00005650909],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016696536,0.00014636165,0.00031313812,0.000036986763,0.0003878667,0.000060760773,0.0014072962,0.000085509666,0.00002303253],"category_scores_gemma":[0.00052219344,0.000069308946,0.00048087473,0.00053496583,0.00041885694,0.00025115005,0.00012217072,0.00048042703,0.000004693427],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009301703,0.00038314075,0.00009073179,0.00008099145,0.00013553788,0.000022199425,0.007350264,0.00014724357,0.019999785,0.0000077637,0.073815204,0.8978741],"study_design_scores_gemma":[0.0029493815,0.00074346334,0.008857326,0.0011131833,0.00054587796,0.007776036,0.014084671,0.8704315,0.04819737,0.039243475,0.0053536855,0.0007040309],"about_ca_topic_score_codex":0.000014376927,"about_ca_topic_score_gemma":7.1911086e-7,"teacher_disagreement_score":0.89717007,"about_ca_system_score_codex":0.00006753184,"about_ca_system_score_gemma":0.00010871127,"threshold_uncertainty_score":0.2983196},"labels":[],"label_agreement":null},{"id":"W2052003572","doi":"10.1007/s10772-005-2166-6","title":"Aligning Text and Phonemes for Speech Technology Applications Using an EM-Like Algorithm","year":2005,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada; National Research Council Institute for Biodiagnostics","funders":"","keywords":"Computer science; Speech recognition; Speech synthesis; Speech technology; Algorithm; Artificial intelligence; Natural language processing","score_opus":0.021730622613951044,"score_gpt":0.3048551054452593,"score_spread":0.28312448283130826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2052003572","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06907795,0.0005206947,0.9171021,0.0121286,0.00050381286,0.00026323253,0.000016485063,0.00022632685,0.0001607926],"genre_scores_gemma":[0.097160645,0.00014639333,0.90167135,0.00040460986,0.00048567046,0.000026975216,0.0000027379463,0.00001941761,0.000082187114],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99835104,0.000022547341,0.0006107537,0.00035062674,0.00038099047,0.00028403982],"domain_scores_gemma":[0.99793994,0.0001014191,0.00049854605,0.00031983858,0.0010469484,0.000093324554],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042927786,0.00018559066,0.0002998471,0.0019616375,0.00013992445,0.0001616804,0.0016355143,0.0002893265,0.000036864978],"category_scores_gemma":[0.00012627599,0.00018119239,0.00009894162,0.0005850838,0.00017182711,0.00071521674,0.00025821244,0.00031727008,0.00001713392],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000070042083,0.00012312476,0.0001360287,0.0000025318109,0.00009459504,0.000046891455,0.00005417845,0.0000082164715,0.012405897,0.006416903,0.00012691777,0.9805777],"study_design_scores_gemma":[0.002828685,0.0005963357,0.00013556027,0.00017089548,0.000094786534,0.020132344,0.0017416895,0.0802945,0.5306677,0.14323749,0.21931808,0.00078194955],"about_ca_topic_score_codex":0.0000051693846,"about_ca_topic_score_gemma":0.000017734832,"teacher_disagreement_score":0.97979575,"about_ca_system_score_codex":0.00014624647,"about_ca_system_score_gemma":0.000112316986,"threshold_uncertainty_score":0.7388811},"labels":[],"label_agreement":null},{"id":"W2052793700","doi":"10.1186/1743-0003-6-26","title":"Development of an automated speech recognition interface for personal emergency response systems","year":2009,"lang":"en","type":"article","venue":"Journal of NeuroEngineering and Rehabilitation","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":74,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Microphone; Phone; Computer science; Dialog box; Interface (matter); Speech recognition; Telecommunications; World Wide Web; Operating system","score_opus":0.02038812681467578,"score_gpt":0.28212500849185024,"score_spread":0.26173688167717446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2052793700","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87960535,0.00005639146,0.119457476,0.00036510057,0.00035488518,0.000101274556,0.0000016165046,0.0000535087,0.0000043839996],"genre_scores_gemma":[0.7328382,0.000007915393,0.2671105,0.000005089628,0.000024527719,0.000002169526,5.4928915e-7,0.0000039226925,0.0000071003146],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990888,0.00008313373,0.00047089715,0.00010605318,0.0001637341,0.000087333785],"domain_scores_gemma":[0.9991314,0.00024611526,0.00020224281,0.000057936737,0.0002960125,0.00006631749],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000713399,0.000075653545,0.0001463826,0.00025023514,0.0000412694,0.000028889344,0.00009312422,0.000029736751,0.0000016002231],"category_scores_gemma":[0.00045633133,0.00006676028,0.00005491323,0.00013822796,0.000008186031,0.0003930964,0.0000063727566,0.000060480044,5.48901e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000607856,0.0002473018,0.000029116756,0.0002211082,0.00003299019,0.000009068181,0.0077085034,0.00062551897,0.31620374,0.000031335843,0.00024359676,0.67403984],"study_design_scores_gemma":[0.0009328211,0.0038172277,0.042075153,0.00040327883,0.000022947956,0.00038867717,0.0009408446,0.92427975,0.025724916,0.00024948857,0.0009244853,0.00024042233],"about_ca_topic_score_codex":3.329101e-7,"about_ca_topic_score_gemma":1.5045438e-7,"teacher_disagreement_score":0.9236542,"about_ca_system_score_codex":0.000028311062,"about_ca_system_score_gemma":0.00003696004,"threshold_uncertainty_score":0.27224052},"labels":[],"label_agreement":null},{"id":"W2053878040","doi":"10.1109/ccece.2010.5575245","title":"An approach to recognize and pronounce words with alternative pronunciations in Farsi","year":2010,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Pronunciation; Computer science; Vowel; Orthography; Word (group theory); Layer (electronics); Artificial intelligence; Speech recognition; Set (abstract data type); Artificial neural network; Perceptron; Natural language processing; Speech synthesis; Index (typography); Mathematics; Linguistics; Reading (process)","score_opus":0.016614110171937292,"score_gpt":0.2418820508242266,"score_spread":0.2252679406522893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2053878040","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.488237,0.0000023502766,0.44160274,0.00085905014,0.00008591658,0.00052281225,0.000002555998,0.00012497962,0.068562604],"genre_scores_gemma":[0.5243037,8.5733035e-7,0.475039,0.00026022317,0.000020935311,0.000085835694,0.0000011338627,0.000004062048,0.0002842822],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99918383,0.000034382047,0.000105126346,0.00035704483,0.00015918899,0.00016042376],"domain_scores_gemma":[0.99946314,0.000043400836,0.000029661665,0.00025864306,0.000084073676,0.000121064615],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025528972,0.00008788109,0.000094044604,0.00013259289,0.000053486314,0.00016005804,0.00030991566,0.00003521829,0.000024219471],"category_scores_gemma":[0.000056459696,0.000065422704,0.00000925992,0.00035345816,0.000026708305,0.00050031906,0.000046477886,0.0001270916,0.00002427445],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000297479,0.0007613125,0.0186745,0.000011440903,0.000019000281,0.000007805563,0.007259211,0.000021637336,0.0031994435,0.049028885,0.0001573702,0.92082965],"study_design_scores_gemma":[0.004260779,0.001442939,0.4614674,0.00013821684,0.000030443396,0.00033136323,0.004046035,0.4318572,0.0564816,0.025988465,0.011150765,0.0028048023],"about_ca_topic_score_codex":0.00007575341,"about_ca_topic_score_gemma":0.00045408632,"teacher_disagreement_score":0.91802484,"about_ca_system_score_codex":0.000017366818,"about_ca_system_score_gemma":0.000055535624,"threshold_uncertainty_score":0.26678607},"labels":[],"label_agreement":null},{"id":"W2054060258","doi":"10.1109/icassp.2014.6853889","title":"JFA-based front ends for speaker recognition","year":2014,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"National Institute of Standards and Technology; Johns Hopkins University","keywords":"NIST; Computer science; Speaker recognition; Normalization (sociology); Speech recognition; Adaptation (eye); Diagonal; Feature extraction; Artificial intelligence; Pattern recognition (psychology); Mathematics","score_opus":0.03535858043039168,"score_gpt":0.2393011804715223,"score_spread":0.20394260004113063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054060258","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013100723,0.0000035158944,0.9253552,0.0014477886,0.00027807837,0.0001289304,0.0000041402527,0.00022659036,0.07124566],"genre_scores_gemma":[0.16060185,0.000001398887,0.83191353,0.00491834,0.00017077265,0.000081001075,0.000018296007,0.000011067503,0.0022837056],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992598,0.000044885353,0.00013879965,0.00025041943,0.00013006428,0.00017597899],"domain_scores_gemma":[0.9992717,0.0002619661,0.00003694445,0.0002562139,0.00009733022,0.00007588218],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00032523737,0.00008462698,0.00010126192,0.00008374863,0.00007061796,0.00009841077,0.00024262244,0.00004724914,0.00080994767],"category_scores_gemma":[0.00014481672,0.000071688846,0.00009067593,0.000073027455,0.000013777665,0.00017907438,0.000021257403,0.00003406427,0.0009285015],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000058797223,0.00004228925,0.000026521657,0.000006230495,0.0000045879146,4.430665e-7,0.000020247542,9.189485e-7,0.00034217752,0.0026009742,0.008610768,0.98833895],"study_design_scores_gemma":[0.00145577,0.00023139591,0.0009068423,0.00003225022,0.000016284317,0.000007647854,0.000021573505,0.556694,0.16801365,0.034740042,0.23741663,0.00046397178],"about_ca_topic_score_codex":0.000009579846,"about_ca_topic_score_gemma":0.000022785496,"teacher_disagreement_score":0.987875,"about_ca_system_score_codex":0.00001696767,"about_ca_system_score_gemma":0.000021744736,"threshold_uncertainty_score":0.9998494},"labels":[],"label_agreement":null},{"id":"W2055696218","doi":"10.1109/odyssey.2006.248137","title":"The Geometry of the Channel Space in GMM-Based Speaker Recognition","year":2006,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Channel (broadcasting); Mixture model; Joint (building); Range (aeronautics); Rank (graph theory); Pattern recognition (psychology); Computer science; Gaussian; Factor (programming language); Artificial intelligence; Feature (linguistics); Factor analysis; Feature vector; Space (punctuation); Limiting; Mathematics; Machine learning; Combinatorics; Telecommunications; Physics; Engineering","score_opus":0.015656382955508016,"score_gpt":0.20454701128938582,"score_spread":0.18889062833387782,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2055696218","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.54402816,0.00020307342,0.22824767,0.033848982,0.0012929575,0.0007778878,0.000012335333,0.00023953174,0.19134937],"genre_scores_gemma":[0.9906201,0.000007128381,0.007486757,0.0005350698,0.000042485957,0.000012915775,0.0000012389185,0.0000051143593,0.0012891849],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99918914,0.00009208185,0.00018290982,0.00015335213,0.00022034302,0.00016220441],"domain_scores_gemma":[0.99919766,0.00029650057,0.00007606753,0.00034513287,0.000066185916,0.000018462792],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040208915,0.00007116733,0.00007851132,0.000088856854,0.000088298184,0.00005960093,0.0004457878,0.00003922111,0.000075516444],"category_scores_gemma":[0.0000929976,0.000038167465,0.000074039264,0.00065690937,0.00005443039,0.00010333969,0.000059276637,0.00007587527,0.00007560474],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006392171,0.0010338839,0.011425042,0.00005747925,0.000038178983,0.000022825143,0.0003300108,0.00036718883,0.006487054,0.051513657,0.030458445,0.8982023],"study_design_scores_gemma":[0.0014750039,0.00007482988,0.22636831,0.00015157089,0.000014128968,0.000018804842,0.00028345725,0.09852088,0.5872496,0.07353759,0.011790949,0.00051489205],"about_ca_topic_score_codex":0.00024032102,"about_ca_topic_score_gemma":0.0005333639,"teacher_disagreement_score":0.89768744,"about_ca_system_score_codex":0.000021693208,"about_ca_system_score_gemma":0.000034995697,"threshold_uncertainty_score":0.1556424},"labels":[],"label_agreement":null},{"id":"W2055842011","doi":"10.1109/icassp.2014.6854822","title":"Deep neural network trained with speaker representation for speaker normalization","year":2014,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Hidden Markov model; Normalization (sociology); Speech recognition; Computer science; Discriminative model; Speaker recognition; Pattern recognition (psychology); Feature extraction; Word error rate; Artificial neural network; Artificial intelligence; Speaker diarisation","score_opus":0.02168773414574742,"score_gpt":0.2424845208748048,"score_spread":0.22079678672905736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2055842011","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036130634,0.0000042280944,0.97645664,0.0010563378,0.00019458875,0.00025223545,3.1949986e-7,0.00018456411,0.018238036],"genre_scores_gemma":[0.5293452,0.0000019787285,0.46699277,0.0020743106,0.0003744613,0.000047365833,0.000023967414,0.000015457455,0.0011245013],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991005,0.00006445253,0.00016675207,0.00027834627,0.00017310277,0.00021681683],"domain_scores_gemma":[0.99930465,0.00016453644,0.000070021684,0.00027184444,0.000120474106,0.00006847919],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022862182,0.00009871102,0.00011259921,0.00004833139,0.00010799837,0.00014647952,0.00020478996,0.000035627843,0.00014303853],"category_scores_gemma":[0.00006567135,0.0000747673,0.000050651266,0.0002910595,0.000019309065,0.00044536573,0.000024924942,0.000031516654,0.00004078296],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010066668,0.000086258246,0.004810705,0.000020154495,0.000044663313,0.00000457735,0.0005818676,0.011780891,0.0002350703,0.103121415,0.007647502,0.87156624],"study_design_scores_gemma":[0.00057580584,0.000097269076,0.006970744,0.0000057879915,0.000010050423,0.00001771258,0.000027005486,0.9834781,0.0013176117,0.0028029087,0.0045421165,0.00015485624],"about_ca_topic_score_codex":0.0000107970245,"about_ca_topic_score_gemma":0.000112080736,"teacher_disagreement_score":0.9716972,"about_ca_system_score_codex":0.000011106916,"about_ca_system_score_gemma":0.000009108044,"threshold_uncertainty_score":0.30489218},"labels":[],"label_agreement":null},{"id":"W2056986748","doi":"10.1139/p07-102","title":"SIMCV un simulateur analogue de la propagation du son dans le conduit vocal","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Physics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formant; Physics; Vocal tract; Transfer function; Acoustics; Speech recognition; Computer science","score_opus":0.012028217570712731,"score_gpt":0.22079727505460972,"score_spread":0.20876905748389699,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2056986748","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.289348,0.000021188409,0.706903,0.00035384815,0.00015411389,0.000035248544,0.0000026059724,0.000009911845,0.003172113],"genre_scores_gemma":[0.9922286,0.000002556397,0.0071044615,0.00037065058,0.0002507968,2.7358678e-7,0.0000012459067,0.000007828555,0.00003354244],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99921346,0.00010205107,0.00020834885,0.000092912385,0.0001436953,0.00023954143],"domain_scores_gemma":[0.9989655,0.0001582534,0.00014190983,0.0001180606,0.0001711866,0.0004450699],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00076140166,0.00007879876,0.000117988704,0.00010990671,0.00015507732,0.00012601897,0.00034149253,0.000058065674,0.000016730162],"category_scores_gemma":[0.00009115782,0.0000767704,0.00008319502,0.00025104618,0.00008266952,0.00032586968,0.000008981076,0.00017794422,0.000014412915],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010327081,0.00009744818,0.008241013,0.000012977811,0.00007975778,0.001567917,0.00394741,0.0015544973,0.0065630795,0.092971936,0.0014015603,0.8835521],"study_design_scores_gemma":[0.0034337097,0.0005806872,0.12886667,0.00026208334,0.00012604712,0.002341048,0.0019366626,0.15130815,0.51327616,0.15608133,0.040470432,0.0013170013],"about_ca_topic_score_codex":0.0017863236,"about_ca_topic_score_gemma":0.0033132723,"teacher_disagreement_score":0.88223505,"about_ca_system_score_codex":0.00015690234,"about_ca_system_score_gemma":0.0010311877,"threshold_uncertainty_score":0.31306058},"labels":[],"label_agreement":null},{"id":"W2058080055","doi":"10.1016/j.csl.2014.06.002","title":"Unsupervised language model adaptation using LDA-based mixture models and latent semantic marginals","year":2014,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Computer science; Latent Dirichlet allocation; Artificial intelligence; Language model; Topic model; Probabilistic latent semantic analysis; Pattern recognition (psychology); Scaling; Mixture model; Cluster analysis; Machine learning; Mathematics","score_opus":0.03687698171248772,"score_gpt":0.25634630427735217,"score_spread":0.21946932256486446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2058080055","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23515289,0.00023099157,0.7632119,0.00035332429,0.00015088163,0.00020058619,0.0000070397873,0.00027402784,0.0004183405],"genre_scores_gemma":[0.525066,0.000005278073,0.47341326,0.0012789253,0.000115882365,0.000005736436,0.000013008314,0.000021658647,0.00008023864],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980686,0.0001830902,0.00031247383,0.00062486297,0.0004031143,0.00040790593],"domain_scores_gemma":[0.9987664,0.00012512156,0.000120854405,0.0006835813,0.00010632557,0.00019767879],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004272985,0.00030569278,0.00034912088,0.00026043295,0.00014655034,0.00034080652,0.00058370386,0.00013426994,0.000039682523],"category_scores_gemma":[0.00002350365,0.00028042195,0.00012225087,0.00029653552,0.000045036693,0.00051996624,0.00020497805,0.00018373586,0.000032255684],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021183741,0.00016725919,0.00006820081,0.00013595853,0.00005131261,0.00022491321,0.0072792564,0.06652021,0.008417365,0.003206565,0.00032186555,0.9135859],"study_design_scores_gemma":[0.00066557544,0.000046193254,0.00013615748,0.000081712635,0.000025788298,0.000060108196,0.00009136996,0.9906916,0.006590789,0.001212368,0.000041048344,0.00035730953],"about_ca_topic_score_codex":0.000090845795,"about_ca_topic_score_gemma":0.000029589075,"teacher_disagreement_score":0.9241714,"about_ca_system_score_codex":0.000046729318,"about_ca_system_score_gemma":0.00005900077,"threshold_uncertainty_score":0.9999648},"labels":[],"label_agreement":null},{"id":"W2058506073","doi":"10.1016/s1319-1578(09)80002-5","title":"Investigating Emphatic Consonants in Foreign Accented Arabic","year":2009,"lang":"en","type":"article","venue":"Journal of King Saud University - Computer and Information Sciences","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick; Université de Moncton","funders":"","keywords":"Pronunciation; Arabic; Speech recognition; Computer science; Hidden Markov model; Linguistics; Word error rate; Point (geometry); Natural language processing; First language; Artificial intelligence; Mathematics","score_opus":0.023722153588125638,"score_gpt":0.23345435003278556,"score_spread":0.20973219644465993,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2058506073","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.51282376,0.00003323898,0.47769937,0.0022310119,0.00021934604,0.000078025914,7.103902e-7,0.000030027679,0.00688453],"genre_scores_gemma":[0.90174633,0.0000665089,0.09696396,0.0011977329,0.000020063668,1.7833058e-8,2.2081088e-7,4.5163122e-7,0.000004730463],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99914986,0.000060144303,0.00028889603,0.00007298415,0.00029945705,0.0001286418],"domain_scores_gemma":[0.9993009,0.000111595815,0.0003096025,0.000056094676,0.00013820428,0.00008361211],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007106361,0.00006512909,0.00013719525,0.00062016404,0.00018745352,0.00028710742,0.0004667851,0.000028085182,0.00000407121],"category_scores_gemma":[0.00006315413,0.000055912544,0.00003901597,0.0006496165,0.00008534538,0.007225438,0.000059996262,0.000089816574,0.0000029112448],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000062394115,0.000033794426,0.015840258,0.000011512496,0.000008010791,0.000018715245,0.0027905144,0.00042572714,0.0000463826,0.026142256,0.00041068927,0.9542659],"study_design_scores_gemma":[0.0015049098,0.00049805426,0.3529271,0.00043293592,0.000009542939,0.00041237377,0.0017344295,0.62795717,0.00036585497,0.007948038,0.0059285094,0.00028107464],"about_ca_topic_score_codex":0.000006803896,"about_ca_topic_score_gemma":0.0000022351508,"teacher_disagreement_score":0.9539848,"about_ca_system_score_codex":0.000037797756,"about_ca_system_score_gemma":0.00010849136,"threshold_uncertainty_score":0.52382684},"labels":[],"label_agreement":null},{"id":"W2058877998","doi":"10.1121/1.4786938","title":"Better model and decoding methods for automatic speech recognition","year":2006,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Hidden Markov model; Speech recognition; Syllable; Decoding methods; Computer science; TIMIT; Task (project management); Artificial intelligence; Pattern recognition (psychology); Algorithm","score_opus":0.034629954055449885,"score_gpt":0.30929439296888855,"score_spread":0.27466443891343867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2058877998","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0118801305,0.00008318875,0.9804784,0.007205942,0.00009430165,0.000110926085,0.0000033196684,0.000014358941,0.00012942149],"genre_scores_gemma":[0.019016165,0.000075712036,0.9787699,0.0020075506,0.00009040663,0.0000019281126,1.6845323e-7,0.000007193358,0.000030979656],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989622,0.00018116362,0.0003755294,0.00008601343,0.00022890429,0.0001661515],"domain_scores_gemma":[0.9976605,0.0015424376,0.0003847012,0.00019030804,0.00017636473,0.0000456576],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012468606,0.0000937404,0.00023246159,0.00002160033,0.00017293026,0.00004304017,0.00051568326,0.00004855412,0.000014155175],"category_scores_gemma":[0.0002574371,0.000050554347,0.00029289248,0.00017147075,0.00020963137,0.00016762731,0.00011684753,0.00017263836,0.000001413978],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008927724,0.000043440145,0.0000067920923,0.000022827135,0.000042636202,1.5740888e-7,0.00013903822,0.00025989205,0.012312179,0.000010929892,0.0072023966,0.9799508],"study_design_scores_gemma":[0.0002060728,0.0000579862,0.000141006,0.000045998757,0.00012334395,0.00007710477,0.0001201871,0.9415078,0.008982618,0.04848155,0.00018676033,0.00006955899],"about_ca_topic_score_codex":0.000008867604,"about_ca_topic_score_gemma":1.758896e-7,"teacher_disagreement_score":0.9798812,"about_ca_system_score_codex":0.000030544314,"about_ca_system_score_gemma":0.000041063606,"threshold_uncertainty_score":0.20615464},"labels":[],"label_agreement":null},{"id":"W2062003163","doi":"10.1007/s12559-012-9197-5","title":"Low-variance Multitaper Mel-frequency Cepstral Coefficient Features for Speech and Speaker Recognition Systems","year":2012,"lang":"en","type":"article","venue":"Cognitive Computation","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec; Computer Research Institute of Montréal; Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"","keywords":"Multitaper; Speech recognition; Window function; Computer science; Cepstrum; Mel-frequency cepstrum; Hamming code; NIST; Estimator; Pattern recognition (psychology); Spectral density; Artificial intelligence; Algorithm; Feature extraction; Mathematics; Statistics; Telecommunications","score_opus":0.03785654066309455,"score_gpt":0.2835100555252821,"score_spread":0.24565351486218753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2062003163","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09975318,0.0005393796,0.8949568,0.00015094524,0.0012476572,0.0009801936,0.00008329059,0.00019202378,0.0020964828],"genre_scores_gemma":[0.9407571,0.000028062,0.05810339,0.00035757796,0.00033327984,0.00013889081,0.00015047065,0.000022243326,0.000108983004],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982728,0.00017686353,0.0003284556,0.0004741611,0.00029557833,0.00045216456],"domain_scores_gemma":[0.9981167,0.00072509766,0.00018707759,0.000089617824,0.0006815705,0.00019997256],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051957,0.0002424597,0.0002478288,0.0001867861,0.00024622423,0.00029593863,0.00012854171,0.00012723611,0.000021648679],"category_scores_gemma":[0.00040814665,0.00023745558,0.000088001725,0.0002907851,0.00008254016,0.000903769,0.000061321625,0.0001319892,0.00014852235],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004491,0.00033206813,0.0005555531,0.00013902392,0.00006592645,0.000008889569,0.00092371996,0.000016400943,0.0015293304,0.0014438977,0.0007650798,0.9941752],"study_design_scores_gemma":[0.012510605,0.0012659172,0.22580379,0.002757084,0.0005613586,0.001489899,0.005716867,0.6294314,0.101445965,0.013027805,0.0015781579,0.0044111414],"about_ca_topic_score_codex":0.000017833077,"about_ca_topic_score_gemma":0.000004590345,"teacher_disagreement_score":0.98976403,"about_ca_system_score_codex":0.0000667248,"about_ca_system_score_gemma":0.00004222004,"threshold_uncertainty_score":0.9683157},"labels":[],"label_agreement":null},{"id":"W2062227835","doi":"10.1109/icassp.2013.6639346","title":"Improving deep neural networks for LVCSR using rectified linear units and dropout","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1281,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Dropout (neural networks); Artificial neural network; Speech recognition; Artificial intelligence; Sigmoid function; Discriminative model; Deep neural networks; Task (project management); Vocabulary; Deep learning; Mixture model; Hidden Markov model; Time delay neural network; Bayesian probability; Pattern recognition (psychology); Machine learning","score_opus":0.0442634602867148,"score_gpt":0.2510945759761163,"score_spread":0.2068311156894015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2062227835","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08331096,0.000037196914,0.9151063,0.0002465244,0.00028223012,0.0002487318,3.1699813e-7,0.00013622706,0.0006314968],"genre_scores_gemma":[0.65076804,0.0000038518606,0.34800416,0.00073773,0.00013975234,0.00002171571,0.0000011887576,0.000011321449,0.00031222988],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99926656,0.00003367453,0.00014527152,0.00024815963,0.000074822055,0.00023150096],"domain_scores_gemma":[0.9992913,0.0002047009,0.000049840444,0.00018434525,0.0001715048,0.000098328535],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014198537,0.00009537755,0.00010941829,0.00006280994,0.00016020847,0.0002473006,0.00019158392,0.000059836588,0.000063493084],"category_scores_gemma":[0.0001227201,0.00007995032,0.0000295428,0.00021657093,0.000023220813,0.00044640695,0.000096404336,0.00006802346,0.000010513766],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027506944,0.000009877947,0.00015868459,0.0000074682357,0.0000077484965,0.0000012215909,0.00007644167,0.00012342693,0.0015955898,0.00069817604,0.00014604747,0.9971726],"study_design_scores_gemma":[0.0001697164,0.000027539932,0.00012283248,0.0000042797346,0.000005009479,0.000018927827,0.0000630959,0.9966101,0.0024271852,0.0003180912,0.00011226566,0.000120950484],"about_ca_topic_score_codex":0.000216962,"about_ca_topic_score_gemma":0.000028513905,"teacher_disagreement_score":0.9970516,"about_ca_system_score_codex":0.000013330109,"about_ca_system_score_gemma":0.000014611859,"threshold_uncertainty_score":0.32602793},"labels":[],"label_agreement":null},{"id":"W2063689849","doi":"10.1109/iscslp.2012.6423452","title":"Investigation of deep neural networks (DNN) for large vocabulary continuous speech recognition: Why DNN surpasses GMMS in acoustic modeling","year":2012,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":98,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Speech recognition; Artificial neural network; Vocabulary; Context (archaeology); Mel-frequency cepstrum; Word error rate; Artificial intelligence; Task (project management); Reduction (mathematics); Deep neural networks; Hidden Markov model; Logarithm; Pattern recognition (psychology); Feature extraction; Mathematics","score_opus":0.05066265927163722,"score_gpt":0.2545038198180309,"score_spread":0.20384116054639367,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2063689849","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23861572,0.00013604412,0.7597689,0.0002953662,0.0003965321,0.00032369117,0.0000055996275,0.00010782482,0.0003503208],"genre_scores_gemma":[0.90122217,0.000018325385,0.09740314,0.0009894428,0.0002339919,0.00005736174,0.00003492455,0.000016209688,0.000024458315],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99832624,0.00013330003,0.00049436855,0.00030233746,0.00023437057,0.0005093906],"domain_scores_gemma":[0.99866724,0.0005131535,0.00013895877,0.00027993415,0.000245413,0.00015530383],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009144932,0.00017875312,0.00029624667,0.00020856192,0.00008397001,0.00008084323,0.0003263968,0.00012788016,0.000065749606],"category_scores_gemma":[0.00028004358,0.00017115785,0.00010673297,0.00046170567,0.00002670749,0.0011046263,0.000087885084,0.00014183075,0.0000144890055],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010641176,0.00039925086,0.036434066,0.00021566114,0.00009500178,0.000018383264,0.0014731805,0.012619069,0.0025500162,0.0014987264,0.0024064,0.94218385],"study_design_scores_gemma":[0.0005286934,0.000049324,0.000767538,0.00003471342,0.00002026299,0.000022048038,0.00017941442,0.99120903,0.005422439,0.0014933806,0.00004348996,0.00022966602],"about_ca_topic_score_codex":0.00004691264,"about_ca_topic_score_gemma":0.00022328226,"teacher_disagreement_score":0.97858995,"about_ca_system_score_codex":0.000042074196,"about_ca_system_score_gemma":0.000026955742,"threshold_uncertainty_score":0.69796145},"labels":[],"label_agreement":null},{"id":"W2064364374","doi":"10.1109/icassp.2013.6639151","title":"PLDA for speaker verification with utterances of arbitrary duration","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":205,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"NIST; Computer science; Speaker verification; Covariance; Speech recognition; Classifier (UML); Speaker recognition; Duration (music); Speech processing; Artificial intelligence; Pattern recognition (psychology); Mathematics; Statistics","score_opus":0.013820470872802554,"score_gpt":0.20593647213030436,"score_spread":0.1921160012575018,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2064364374","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13560914,0.0000074498275,0.84849304,0.001584458,0.000057827383,0.00027451583,9.935045e-7,0.00005769836,0.013914918],"genre_scores_gemma":[0.6707506,0.0000030040642,0.32850945,0.00030980117,0.000014733577,0.000058336424,0.0000026814964,0.0000022986735,0.0003490532],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9996128,0.000010504537,0.00011448962,0.00011583795,0.00008489821,0.000061489045],"domain_scores_gemma":[0.9996291,0.000051526633,0.000054837164,0.00014440907,0.00009965233,0.000020520041],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00005576915,0.000040877636,0.000056905632,0.000035498026,0.00002539087,0.000048645506,0.00012655262,0.000016425334,0.00016879318],"category_scores_gemma":[0.000010697387,0.00002835837,0.000020407308,0.00008822271,0.000014996899,0.00049801084,0.0000060268467,0.000013771849,0.000057468435],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029269362,0.00017000047,0.0027344082,0.00006258037,0.000041178966,5.304689e-7,0.0006046642,0.0000050288263,0.036576323,0.0888043,0.0066971816,0.86427456],"study_design_scores_gemma":[0.0009052384,0.00030019123,0.07849468,0.000051517138,0.000012213119,0.000017067428,0.00021942235,0.113295384,0.7808867,0.018541053,0.0069319285,0.00034462343],"about_ca_topic_score_codex":0.000028303917,"about_ca_topic_score_gemma":0.00000924572,"teacher_disagreement_score":0.8639299,"about_ca_system_score_codex":0.000004079574,"about_ca_system_score_gemma":0.000014913198,"threshold_uncertainty_score":0.1848167},"labels":[],"label_agreement":null},{"id":"W2064505662","doi":"10.5539/mas.v3n8p106","title":"Design and Implementation of Speech Recognition System Based on Field Programmable Gate Array","year":2009,"lang":"en","type":"article","venue":"Modern Applied Science","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Field-programmable gate array; Computer science; Hidden Markov model; Viterbi algorithm; Gate array; Speech recognition; Chip; Field (mathematics); Pattern recognition (psychology); Computer hardware; Artificial intelligence; Telecommunications; Mathematics","score_opus":0.028217468432939964,"score_gpt":0.26512092911509694,"score_spread":0.23690346068215698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2064505662","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022335071,0.000003893553,0.9719252,0.00035100483,0.000048892896,0.00049109454,0.0000012035877,0.0001253133,0.0047183377],"genre_scores_gemma":[0.72811264,0.0000013780848,0.2715404,0.0003014295,0.000009894959,0.000026085994,9.1916786e-7,0.000002591198,0.000004694719],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99856585,0.00003563662,0.00021269132,0.0004405641,0.0004817136,0.00026356263],"domain_scores_gemma":[0.9992908,0.0001041832,0.000120410914,0.0002942902,0.00009670611,0.000093575436],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009860845,0.00011035172,0.00013225003,0.00021458164,0.00018555399,0.00017890641,0.00038964234,0.000036346184,0.000012410583],"category_scores_gemma":[0.000017327475,0.00010034133,0.000023100069,0.0005377449,0.00006423223,0.00029947585,0.000022230115,0.00006267917,0.000018334711],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014547036,0.000024557254,0.0000059571043,0.000010522384,9.848573e-7,0.000001569762,0.0001648234,0.00004870044,0.15398553,0.00064786413,0.000010571571,0.84508437],"study_design_scores_gemma":[0.00025800255,0.00017960616,0.00019737211,0.000027880224,0.0000037233813,0.0000052300957,0.00008259455,0.30552548,0.6895946,0.0040085334,0.000010122928,0.00010683415],"about_ca_topic_score_codex":0.000009221752,"about_ca_topic_score_gemma":0.0000017817589,"teacher_disagreement_score":0.84497756,"about_ca_system_score_codex":0.00004997482,"about_ca_system_score_gemma":0.00010057425,"threshold_uncertainty_score":0.40918005},"labels":[],"label_agreement":null},{"id":"W2067459736","doi":"10.1002/ecjb.10119","title":"Model‐based speaker normalization methods for speech recognition","year":2003,"lang":"en","type":"article","venue":"Electronics and Communications in Japan (Part II Electronics)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Vocal tract; Formant; Normalization (sociology); Speech recognition; Computer science; Speaker recognition; Smoothing; Speaker diarisation; Image warping; Pattern recognition (psychology); Artificial intelligence; Computer vision","score_opus":0.06666757292295987,"score_gpt":0.3387917852170029,"score_spread":0.27212421229404304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2067459736","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0127433585,0.007985932,0.9682823,0.002446082,0.00009522876,0.0009257195,0.000011916202,0.00020596507,0.007303522],"genre_scores_gemma":[0.14905998,0.0056522945,0.84330547,0.0009207484,0.000020591893,0.0005284969,0.0001486612,0.000043770375,0.00031997182],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99742484,0.00052315614,0.0005630077,0.00054325326,0.0001764125,0.0007693307],"domain_scores_gemma":[0.9973914,0.00048112022,0.0002018324,0.0015554785,0.00025779774,0.00011238263],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0020729892,0.0002735027,0.00031696178,0.0003494945,0.0006927728,0.00017309753,0.0010732219,0.00017641415,0.00003194066],"category_scores_gemma":[0.0003052244,0.00030624543,0.0001235294,0.0008517183,0.00008660413,0.0005046778,0.00016838731,0.0004579517,0.000010269906],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018686022,0.00037977914,0.000058120295,0.000016086966,0.00003694982,1.9565009e-7,0.00020972289,0.00014765776,0.0015102155,0.3753526,0.00034067652,0.62192935],"study_design_scores_gemma":[0.00089717476,0.000276544,0.000015167115,0.00003122675,0.000034435998,0.00002726084,0.00003147156,0.69308215,0.025761541,0.13532132,0.14408879,0.00043288953],"about_ca_topic_score_codex":0.000007158946,"about_ca_topic_score_gemma":0.0004058694,"teacher_disagreement_score":0.6929345,"about_ca_system_score_codex":0.00030789964,"about_ca_system_score_gemma":0.0005912937,"threshold_uncertainty_score":0.99993896},"labels":[],"label_agreement":null},{"id":"W2068004116","doi":"10.1109/icassp.2013.6639168","title":"Compensation for inter-frame correlations in speaker diarization and recognition","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"NIST; Speaker diarisation; Computer science; Speech recognition; Speaker recognition; Cluster analysis; Sample (material); Sample size determination; Pattern recognition (psychology); Feature (linguistics); Set (abstract data type); Hierarchical clustering; Scaling; Inference; Artificial intelligence; Statistics; Mathematics","score_opus":0.030146364738411622,"score_gpt":0.23712867836759066,"score_spread":0.20698231362917904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2068004116","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05627863,0.000004579155,0.93719643,0.001529889,0.00013958404,0.00043027513,0.000002072041,0.00007796656,0.0043405853],"genre_scores_gemma":[0.8048969,0.000008964329,0.19388562,0.00058928115,0.000025575464,0.00012963958,0.00003646647,0.0000052690593,0.00042227178],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99946725,0.000034151282,0.00016688701,0.00017407071,0.000060219158,0.000097410244],"domain_scores_gemma":[0.9994907,0.00022301808,0.000043020867,0.000099571276,0.00010597681,0.000037736485],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012609914,0.000059337297,0.00007059212,0.00014264972,0.000046154106,0.00015115745,0.00007654484,0.000048358954,0.00025747714],"category_scores_gemma":[0.00013104947,0.00005588661,0.000019661824,0.0001661392,0.00001551877,0.00072181807,0.00002658097,0.000041231822,0.00020655697],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020421433,0.000054005555,0.002577852,0.00000736214,0.0000044087897,2.4077843e-7,0.00038944854,0.0000037390257,0.0005012799,0.010849671,0.0010714199,0.98453856],"study_design_scores_gemma":[0.0007462635,0.000062127525,0.075192966,0.0000451847,0.0000060887423,0.0000105079625,0.00018861002,0.80629027,0.0022137363,0.11389199,0.00111343,0.00023880067],"about_ca_topic_score_codex":0.00008304745,"about_ca_topic_score_gemma":0.000089575435,"teacher_disagreement_score":0.9842997,"about_ca_system_score_codex":0.000020481779,"about_ca_system_score_gemma":0.000009628389,"threshold_uncertainty_score":0.2819194},"labels":[],"label_agreement":null},{"id":"W2069483556","doi":"10.1109/ais.2010.5547038","title":"Systems combination in large vocabulary continuous speech recognition","year":2010,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Word error rate; Vocabulary; Speech recognition; Confusion; Word (group theory); Field (mathematics); Frame (networking); Reduction (mathematics); Artificial intelligence; Natural language processing; Linguistics; Telecommunications","score_opus":0.015475374975381833,"score_gpt":0.23333525023105964,"score_spread":0.2178598752556778,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2069483556","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79806507,0.000028559158,0.10658119,0.0009782542,0.0024501649,0.00051729893,0.000008277025,0.0005001059,0.090871066],"genre_scores_gemma":[0.9722929,0.000007635642,0.026411032,0.0003264428,0.0000578667,0.000033206645,0.00001682871,0.000007877981,0.0008462271],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99894303,0.00008175147,0.0002487539,0.0002731352,0.00022256825,0.00023077567],"domain_scores_gemma":[0.9993403,0.0001107022,0.00006555776,0.0002867714,0.0001283524,0.00006829914],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069731654,0.0000986647,0.0001479145,0.00022810414,0.000056397184,0.00019094117,0.00031292244,0.000113208735,0.0002707953],"category_scores_gemma":[0.00012877217,0.000093148774,0.00004107806,0.000330589,0.000014833779,0.0005462977,0.000058652287,0.00020714846,0.00077511487],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000771638,0.00064180046,0.006338164,0.000025813099,0.0000123678,0.00012754313,0.00021465926,2.7755976e-7,0.009024365,0.047120586,0.0025943292,0.93389237],"study_design_scores_gemma":[0.010833618,0.00053980644,0.13027222,0.0003652679,0.00003848914,0.0015191385,0.0014932367,0.47886306,0.2504253,0.06325575,0.059409034,0.0029850702],"about_ca_topic_score_codex":0.00010033936,"about_ca_topic_score_gemma":0.00023260221,"teacher_disagreement_score":0.9309073,"about_ca_system_score_codex":0.000020127605,"about_ca_system_score_gemma":0.000026973143,"threshold_uncertainty_score":0.99627924},"labels":[],"label_agreement":null},{"id":"W2069929513","doi":"10.1017/s0025100313000327","title":"A study of laryngeal gestures in Mandarin citation tones using simultaneous laryngoscopy and laryngeal ultrasound (SLLUS)","year":2014,"lang":"en","type":"article","venue":"Journal of the International Phonetic Association","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":76,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Larynx; Laryngoscopy; Tone (literature); Mandarin Chinese; Articulatory phonetics; Audiology; Speech production; Vocal folds; Phonation; Medicine; Acoustics; Speech recognition; Computer science; Anatomy; Surgery; Intubation; Linguistics; Physics","score_opus":0.01320693738831537,"score_gpt":0.2537196381902821,"score_spread":0.2405127008019667,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2069929513","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99418026,0.00003096984,0.0039873645,0.00073477783,0.0006998705,0.00011654853,0.000002462364,0.000006167547,0.00024157531],"genre_scores_gemma":[0.9950122,0.000021004946,0.0046320627,0.00013569016,0.00011834536,0.000001342209,5.5574884e-7,0.000005483845,0.00007327078],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9982715,0.0002536857,0.00048717682,0.00012066255,0.00076227146,0.000104677885],"domain_scores_gemma":[0.9975862,0.001094513,0.0008340065,0.00010866145,0.0003437951,0.00003282031],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011440748,0.000088510074,0.0001993267,0.0002129929,0.00006077018,0.000107400694,0.00045765215,0.00006057653,0.000008935687],"category_scores_gemma":[0.00168701,0.00006902264,0.00006552876,0.00019898394,0.0000160817,0.00028576606,0.00008230315,0.00017755809,0.0000011650685],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003579479,0.0031511043,0.83571833,0.000046942154,0.0008042554,0.00007401712,0.023990689,0.014595733,0.057501074,0.0013435307,0.0009567815,0.061459605],"study_design_scores_gemma":[0.0042568087,0.00060529826,0.87381303,0.0002130859,0.00010439938,0.00025535564,0.0015792878,0.09917524,0.010060061,0.009347717,0.0003252003,0.00026452402],"about_ca_topic_score_codex":0.00012443285,"about_ca_topic_score_gemma":0.00023897567,"teacher_disagreement_score":0.084579505,"about_ca_system_score_codex":0.00022673742,"about_ca_system_score_gemma":0.000048717582,"threshold_uncertainty_score":0.28146616},"labels":[],"label_agreement":null},{"id":"W2070080535","doi":"10.1121/1.2980456","title":"Identification of frequency-shifted vowels","year":2008,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Social Sciences and Humanities Research Council of Canada; National Science Foundation","keywords":"Acoustics; Identification (biology); Mathematics; Computer science; Physics; Biology","score_opus":0.020696442230777004,"score_gpt":0.24597708902980844,"score_spread":0.22528064679903143,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070080535","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052387647,0.00014284418,0.9412313,0.0057119927,0.00021439944,0.00007445354,0.0000040464265,0.00001119211,0.0002221309],"genre_scores_gemma":[0.8357966,0.0004061208,0.16295707,0.00070341356,0.00005853072,5.2447746e-7,7.490399e-8,0.0000050407784,0.000072637835],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985001,0.0001782626,0.00056017877,0.00007166396,0.000560029,0.00012976445],"domain_scores_gemma":[0.9978739,0.0005343875,0.000805581,0.00039691554,0.00033504507,0.000054184966],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00066698494,0.00007811495,0.00022776578,0.000021721129,0.00014501975,0.000010458049,0.0012823298,0.00004427921,0.000044051354],"category_scores_gemma":[0.0003641818,0.00004128717,0.00037735087,0.0004250132,0.0005837977,0.00015482376,0.00011862386,0.00021247994,0.0000076169586],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010749596,0.0010201308,0.0009245854,0.00009877203,0.000736168,0.000008230386,0.0092615085,0.0011100217,0.6982237,0.00047860225,0.06468661,0.22334416],"study_design_scores_gemma":[0.0014271546,0.00075729506,0.05922242,0.0002795051,0.0005975708,0.0011741245,0.0029321415,0.5451022,0.34762383,0.038890164,0.0014541335,0.00053946127],"about_ca_topic_score_codex":0.000019901536,"about_ca_topic_score_gemma":1.028856e-7,"teacher_disagreement_score":0.78340894,"about_ca_system_score_codex":0.000029042038,"about_ca_system_score_gemma":0.000104737876,"threshold_uncertainty_score":0.2382909},"labels":[],"label_agreement":null},{"id":"W2071007762","doi":"10.1121/1.4806678","title":"Nonlinearities in block-type reduced-order vocal fold models with asymmetric tissue properties","year":2013,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Phonation; Vocal folds; Nonlinear system; Fold (higher-order function); Bifurcation; Sensitivity (control systems); Computer science; Mathematics; Speech recognition; Physics; Larynx","score_opus":0.02419412231878018,"score_gpt":0.23448301451663472,"score_spread":0.21028889219785454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2071007762","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10065754,0.00082004396,0.8685361,0.028022297,0.00032101595,0.000425049,0.0000022851361,0.000035713812,0.0011799154],"genre_scores_gemma":[0.70249575,0.00026537248,0.2955844,0.0013719146,0.00007686249,0.0000023474045,5.307429e-8,0.000009829938,0.00019342253],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985274,0.00016124881,0.00038755243,0.00010540302,0.00057423423,0.00024416333],"domain_scores_gemma":[0.9984647,0.00037633596,0.00027588036,0.00031634007,0.0004891402,0.000077573386],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041674398,0.00013032173,0.0002995348,0.000050556675,0.00011010711,0.000057468027,0.001067009,0.000058991813,0.000028720984],"category_scores_gemma":[0.0002173794,0.00005830463,0.00013219482,0.0009635605,0.0005252544,0.00032352022,0.00020087147,0.00038902057,0.000010530909],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037510874,0.0016450086,0.00021027542,0.00018632355,0.00071796036,0.000012173344,0.01013738,0.05635368,0.04986454,0.0002232942,0.05484211,0.8254321],"study_design_scores_gemma":[0.00039954853,0.00050577323,0.0005567747,0.00015915143,0.00007581348,0.00018154163,0.0025809342,0.9818579,0.01082788,0.002259511,0.00042326102,0.00017188964],"about_ca_topic_score_codex":0.00019242766,"about_ca_topic_score_gemma":0.0000012045742,"teacher_disagreement_score":0.92550427,"about_ca_system_score_codex":0.000045206183,"about_ca_system_score_gemma":0.00016502627,"threshold_uncertainty_score":0.23775938},"labels":[],"label_agreement":null},{"id":"W2072245166","doi":"10.1007/s10772-005-2168-4","title":"Post Recognition Speech Localization","year":2005,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Phrase; Speech recognition; SIGNAL (programming language); Speech processing; Multilateration; Word (group theory); Artificial intelligence; Pattern recognition (psychology); Acoustics; Mathematics","score_opus":0.01544005197725855,"score_gpt":0.2639430521250483,"score_spread":0.24850300014778975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2072245166","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18050732,0.00035136484,0.710793,0.096877515,0.0031740277,0.00019448418,0.000021483358,0.00045348902,0.0076272623],"genre_scores_gemma":[0.54223526,0.0002896435,0.4538623,0.0023163427,0.0009797737,0.00000412475,0.000009248794,0.000018092258,0.00028524513],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983664,0.00003853336,0.0005971957,0.00020043935,0.00060964446,0.00018775497],"domain_scores_gemma":[0.99724525,0.00007201037,0.00047123485,0.00021482984,0.0019252505,0.00007143352],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040760703,0.00013231051,0.00019350063,0.0013399019,0.0000530575,0.0001267293,0.0014758832,0.00018774244,0.00039103083],"category_scores_gemma":[0.000483252,0.00012362868,0.00012560947,0.00045345427,0.000074907766,0.00091031694,0.00015325673,0.00029624972,0.00046140404],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020337196,0.00010131265,0.00022418196,0.0000014005395,0.00006524965,0.00022229574,0.000044490465,0.00000896611,0.005128833,0.0031662395,0.000931942,0.99008477],"study_design_scores_gemma":[0.0018435365,0.00042413134,0.00041877586,0.00018950825,0.000034473913,0.016277835,0.00025803348,0.008722926,0.7235506,0.064151704,0.183653,0.00047547542],"about_ca_topic_score_codex":0.000007665699,"about_ca_topic_score_gemma":0.000019925907,"teacher_disagreement_score":0.9896093,"about_ca_system_score_codex":0.000179689,"about_ca_system_score_gemma":0.0000979588,"threshold_uncertainty_score":0.5930569},"labels":[],"label_agreement":null},{"id":"W2072667706","doi":"10.1109/iccspa.2013.6487262","title":"Effect of characteristics of speakers on MSA ASR performance","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Pronunciation; Speech recognition; Stress (linguistics); Hidden Markov model; Arabic; Computer science; Word error rate; Word (group theory); Linguistics; Speech corpus; Natural language processing; Artificial intelligence; Speech synthesis","score_opus":0.008206595823481298,"score_gpt":0.21461453454020782,"score_spread":0.20640793871672652,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2072667706","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97016823,0.0000016833244,0.0032942856,0.000093526265,0.0001204713,0.000109170745,0.00000128055,0.00003161888,0.026179701],"genre_scores_gemma":[0.99452555,0.0000104213195,0.004962369,0.00009538872,0.000012884736,0.0000058971254,7.031878e-7,0.000002778198,0.0003840136],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99944925,0.000040894556,0.00016045531,0.00010478764,0.00015225628,0.00009234429],"domain_scores_gemma":[0.999393,0.00019456158,0.00007879803,0.00023872852,0.000058621234,0.000036297843],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001808059,0.00006437088,0.00014879061,0.000061976985,0.000014533719,0.0000158972,0.00025291005,0.000026190677,0.0004891475],"category_scores_gemma":[0.000057179546,0.000045183795,0.000046083824,0.00010870987,0.000027159573,0.00014568547,0.000035751884,0.000036565158,0.00041398627],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008928251,0.000037108435,0.003791962,0.000058704918,0.00000939287,5.7263685e-7,0.000047340098,4.824226e-7,0.003495072,0.0006213537,0.0006486246,0.99128044],"study_design_scores_gemma":[0.00025542706,0.0008584345,0.11826236,0.00006352591,0.0000055567575,0.000003689387,0.0000055537353,0.027399212,0.85253257,0.00003393123,0.00046849294,0.000111268266],"about_ca_topic_score_codex":0.00001370691,"about_ca_topic_score_gemma":2.3557511e-7,"teacher_disagreement_score":0.9911692,"about_ca_system_score_codex":0.0000064478722,"about_ca_system_score_gemma":0.000008746382,"threshold_uncertainty_score":0.5355822},"labels":[],"label_agreement":null},{"id":"W2074176370","doi":"10.1109/icassp.2013.6639312","title":"Comparison of a bigram PLSA and a novel context-based PLSA language model for speech recognition","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Bigram; Probabilistic latent semantic analysis; Perplexity; Computer science; Context (archaeology); Artificial intelligence; Language model; Natural language processing; Topic model; Context model; Speech recognition; Word (group theory); Latent semantic analysis; Linguistics","score_opus":0.08940868257063371,"score_gpt":0.31921028913982696,"score_spread":0.22980160656919324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2074176370","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21037267,0.00003070164,0.78742695,0.000593756,0.000039200484,0.00043408468,0.00002739403,0.00010275073,0.00097247685],"genre_scores_gemma":[0.64687306,0.0000012421102,0.3523215,0.00055163505,0.0000106955285,0.000072882205,0.000009727786,0.0000061701094,0.00015307505],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990764,0.000022159662,0.0002797452,0.0002709654,0.0001664364,0.00018424349],"domain_scores_gemma":[0.99906266,0.00029423484,0.00011044573,0.00022677993,0.00021458697,0.00009128318],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001870259,0.000116002644,0.0002446735,0.00013409674,0.00005403416,0.00009967464,0.0002175333,0.00008101235,0.000097569304],"category_scores_gemma":[0.00009888979,0.00010346358,0.00007615462,0.00014132954,0.000045977886,0.00028666118,0.000040994426,0.00006375428,0.000041832656],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015143273,0.0002806251,0.00014376933,0.000047964993,0.000015897474,4.00163e-7,0.000559694,0.000013068321,0.0199294,0.0014917022,0.001273161,0.9762292],"study_design_scores_gemma":[0.0007798368,0.000081754086,0.0002011205,0.000031897365,0.000009373465,0.000003314128,0.00033466553,0.8773194,0.11887812,0.002170244,0.00005084214,0.00013943245],"about_ca_topic_score_codex":0.00019123171,"about_ca_topic_score_gemma":0.00014746116,"teacher_disagreement_score":0.9760897,"about_ca_system_score_codex":0.0000128144475,"about_ca_system_score_gemma":0.000043215547,"threshold_uncertainty_score":0.42191222},"labels":[],"label_agreement":null},{"id":"W2074517850","doi":"10.1007/s11042-014-1973-7","title":"Spectro-temporal directional derivative based automatic speech recognition for a serious game scenario","year":2014,"lang":"en","type":"article","venue":"Multimedia Tools and Applications","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Speech recognition; Feature (linguistics); Discrete cosine transform; Arabic numerals; Feature vector; Artificial intelligence; Pattern recognition (psychology); Image (mathematics)","score_opus":0.030683642402534274,"score_gpt":0.2570780568454679,"score_spread":0.22639441444293365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2074517850","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010685252,0.000019497895,0.98445463,0.001689106,0.000086328706,0.0011570128,0.00009625118,0.00033108352,0.0014808105],"genre_scores_gemma":[0.109208,0.00001007231,0.8873676,0.0006784084,0.0002649174,0.0020989547,0.00022753332,0.000017628096,0.00012685893],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99889004,0.000054078242,0.00025083756,0.00041222904,0.0001685085,0.00022428161],"domain_scores_gemma":[0.9985902,0.0007273714,0.00012090365,0.00027208723,0.00015316899,0.00013631445],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002605206,0.00015440196,0.0001872031,0.00011045274,0.00023134258,0.00022247867,0.0002181297,0.00007468422,0.000090774556],"category_scores_gemma":[0.00018301235,0.00014864422,0.00008022202,0.0002627986,0.0000680446,0.00030126146,0.000036107398,0.000086672946,0.000121861536],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000433898,0.00009831009,0.00016751586,0.000020629888,0.00001192252,3.37582e-7,0.00005856096,0.0000014948695,0.0010168055,0.00072039315,0.00031552624,0.99758416],"study_design_scores_gemma":[0.0014169613,0.000118543656,0.01193798,0.00004841623,0.00003472895,0.000029129787,0.0000349206,0.8627175,0.028809417,0.018387549,0.075989775,0.0004750566],"about_ca_topic_score_codex":0.000019385801,"about_ca_topic_score_gemma":0.000027582455,"teacher_disagreement_score":0.9971091,"about_ca_system_score_codex":0.000033186334,"about_ca_system_score_gemma":0.00006136949,"threshold_uncertainty_score":0.60615355},"labels":[],"label_agreement":null},{"id":"W2075449699","doi":"10.1109/icassp.2014.6854638","title":"Phone sequence modeling with recurrent neural networks","year":2014,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; TIMIT; Phone; Speech recognition; Artificial neural network; Word error rate; Decoding methods; Language model; Artificial intelligence; Recurrent neural network; Sequence (biology); Classifier (UML); Acoustic model; Context model; Complementarity (molecular biology); Hidden Markov model; Speech processing; Algorithm","score_opus":0.04426966286379785,"score_gpt":0.24659188787626132,"score_spread":0.20232222501246347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2075449699","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01585224,0.000013391744,0.97400206,0.00056164246,0.00018048585,0.00004744954,1.3126304e-7,0.00020533116,0.009137283],"genre_scores_gemma":[0.8770805,0.0000067861465,0.12197422,0.0007726231,0.00006019981,0.0000066419884,7.458675e-7,0.0000045875136,0.00009370778],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992574,0.00004522344,0.00010708097,0.00024074421,0.00015804834,0.00019150703],"domain_scores_gemma":[0.9995028,0.000053475647,0.00002675883,0.00027311366,0.000059063696,0.00008478283],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016831227,0.00008589935,0.00009091501,0.00003845776,0.00007005245,0.000111198424,0.00033653277,0.000026576885,0.000060580074],"category_scores_gemma":[0.000017640003,0.00006031115,0.000027763152,0.00018428621,0.000016263153,0.00024648444,0.000056420395,0.00008469428,0.000057166988],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000056342856,0.00002655123,0.00006361143,0.000002776186,0.0000059815216,0.0000050686995,0.000059778708,0.026713392,0.00007555094,0.0131522855,0.00023258,0.9596568],"study_design_scores_gemma":[0.00010906172,0.00003503861,0.00001829678,0.000010929431,0.000001918665,0.000023705194,0.000007419173,0.9988128,0.0002454616,0.00046556108,0.00015859846,0.0001111955],"about_ca_topic_score_codex":0.00001934558,"about_ca_topic_score_gemma":0.000017358852,"teacher_disagreement_score":0.9720994,"about_ca_system_score_codex":0.000012291377,"about_ca_system_score_gemma":0.00001028226,"threshold_uncertainty_score":0.24594173},"labels":[],"label_agreement":null},{"id":"W2076029080","doi":"10.1121/1.2942600","title":"Intelligibility of information in temporally desynchronized bands of speech","year":2007,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Intelligibility (philosophy); Mathematics; Maxima and minima; Syllable; Acoustics; Speech recognition; Computer science; Physics; Mathematical analysis","score_opus":0.014513416696958636,"score_gpt":0.2617047805084385,"score_spread":0.24719136381147985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2076029080","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10664161,0.000046486482,0.891305,0.001294309,0.00009084921,0.000089472785,0.0000023211092,0.0000044730773,0.0005254585],"genre_scores_gemma":[0.750074,0.00011630787,0.24949758,0.0002842306,0.000019700354,1.3275718e-7,9.919421e-8,0.0000020307896,0.0000059090517],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982582,0.0001286217,0.0008912533,0.00004930291,0.0005263503,0.00014632326],"domain_scores_gemma":[0.9973857,0.0010026963,0.0008988458,0.00030441457,0.0003594515,0.000048897517],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002731417,0.00007918284,0.00031341662,0.000047824502,0.000034828216,0.000009325649,0.00093290803,0.0000567038,0.000035351954],"category_scores_gemma":[0.00065575086,0.000042965316,0.0003038351,0.0005422346,0.00042507853,0.0002675712,0.00015906295,0.00024724493,0.0000016390755],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034139934,0.0003470928,0.0019205646,0.00013685536,0.00012987493,0.0000011262608,0.0037977914,0.0009075399,0.015163189,0.00006452187,0.002747012,0.974443],"study_design_scores_gemma":[0.0027111722,0.0013376785,0.050308954,0.0006867845,0.0002471338,0.00020824275,0.008548847,0.54774374,0.36960664,0.016278189,0.0019167463,0.00040587442],"about_ca_topic_score_codex":0.00006582169,"about_ca_topic_score_gemma":0.000001512153,"teacher_disagreement_score":0.9740372,"about_ca_system_score_codex":0.00005942589,"about_ca_system_score_gemma":0.00012845156,"threshold_uncertainty_score":0.17520748},"labels":[],"label_agreement":null},{"id":"W2076794394","doi":"10.1109/asru.2011.6163900","title":"Making Deep Belief Networks effective for large vocabulary continuous speech recognition","year":2011,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":192,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Speech recognition; Vocabulary; Artificial intelligence; Natural language processing; Linguistics","score_opus":0.04830958816975836,"score_gpt":0.2643455917612188,"score_spread":0.21603600359146044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2076794394","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003666086,0.00008333469,0.9520586,0.00006620299,0.00053748087,0.0007541736,0.0000056473755,0.0003778688,0.0424506],"genre_scores_gemma":[0.47547647,0.000016293137,0.5218537,0.0018381876,0.0002027143,0.0002566983,0.0000163726,0.00002473016,0.00031484707],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99862736,0.0001032402,0.00023925978,0.00044192906,0.00015097274,0.0004372312],"domain_scores_gemma":[0.9989771,0.00031787323,0.00010320871,0.00031433,0.00020093592,0.0000864978],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005977419,0.00017402416,0.0002234626,0.00012535184,0.00018198045,0.00010247143,0.00039689717,0.00013330574,0.00045757447],"category_scores_gemma":[0.00012870393,0.00015906391,0.00015454165,0.00023756202,0.000019290865,0.0004476813,0.00011525797,0.00011863955,0.000236265],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030715262,0.00014226577,0.00024964305,0.000009844843,0.00003878753,0.000025175235,0.0002703959,3.1099447e-7,0.00003855557,0.0038094295,0.0008080166,0.9945769],"study_design_scores_gemma":[0.0065927194,0.001929206,0.02198635,0.00045122486,0.0002406039,0.00059544056,0.0009449878,0.69692236,0.13837177,0.11022795,0.018791234,0.0029461458],"about_ca_topic_score_codex":0.000013904321,"about_ca_topic_score_gemma":0.000054851615,"teacher_disagreement_score":0.99163073,"about_ca_system_score_codex":0.000033253542,"about_ca_system_score_gemma":0.000014395767,"threshold_uncertainty_score":0.64864385},"labels":[],"label_agreement":null},{"id":"W2078373756","doi":"10.1115/sbc2011-53952","title":"Nonlinear Vocal Fold Dynamics in a Two-Mass Model of Speech Arising From Asymmetric Intraglottal Flow","year":2011,"lang":"en","type":"article","venue":"ASME 2011 Summer Bioengineering Conference, Parts A and B","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Vocal folds; Nonlinear system; Vocal tract; Vocal fold paralysis; Speech recognition; Larynx; Phonation; Computer science; Acoustics; Audiology; Physics; Paralysis; Anatomy; Medicine","score_opus":0.04746612188469605,"score_gpt":0.24105739890266928,"score_spread":0.19359127701797324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2078373756","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22409256,0.0001120372,0.7709492,0.00009215479,0.00029779848,0.00015058652,0.00006124392,0.00010706898,0.004137353],"genre_scores_gemma":[0.7325341,0.000050752868,0.26728827,0.000030397894,0.000032617674,0.0000070391884,0.00001146816,0.000012825881,0.000032495667],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998569,0.00003130599,0.00039750698,0.0004248396,0.00021834679,0.00035897238],"domain_scores_gemma":[0.9992396,0.00008277111,0.00008905143,0.00033768374,0.00009702074,0.00015385654],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002144556,0.00024145443,0.00036429125,0.0004431311,0.00003603982,0.00008104179,0.00039773568,0.00010714705,0.00006812332],"category_scores_gemma":[0.000036388556,0.0002298853,0.00007468976,0.0003261297,0.000066395085,0.0003300412,0.00012226259,0.00020543141,0.000025735797],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000069262765,0.0005963363,0.032081135,0.00010968265,0.00024666364,0.00016709013,0.002319643,0.000807112,0.006315702,0.041506276,0.0001295615,0.91565156],"study_design_scores_gemma":[0.0004325793,0.00004694737,0.0015301727,0.00006520486,0.000017612236,0.0000068798117,0.000061069375,0.9840338,0.011672175,0.0017993193,0.000048088816,0.00028614586],"about_ca_topic_score_codex":0.000708441,"about_ca_topic_score_gemma":0.00030256208,"teacher_disagreement_score":0.9832267,"about_ca_system_score_codex":0.000039211976,"about_ca_system_score_gemma":0.00006979631,"threshold_uncertainty_score":0.93744504},"labels":[],"label_agreement":null},{"id":"W2080551551","doi":"10.1186/s13636-014-0042-5","title":"Homogenous ensemble phonotactic language recognition based on SVM supervector reconstruction","year":2014,"lang":"en","type":"article","venue":"EURASIP Journal on Audio Speech and Music Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"GLS Industries (Canada)","funders":"National Natural Science Foundation of China","keywords":"Computer science; Phonotactics; Support vector machine; Word error rate; NIST; Speech recognition; Language model; Artificial intelligence; Pattern recognition (psychology); Feature vector","score_opus":0.023246705929737776,"score_gpt":0.2328707149487062,"score_spread":0.20962400901896844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2080551551","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8442683,0.0001990745,0.13781098,0.0017397831,0.001177362,0.00019048742,0.000004069517,0.00026728894,0.014342668],"genre_scores_gemma":[0.9386086,0.000046079178,0.05682711,0.0037768993,0.000587592,0.000006907139,0.0000037258792,0.000027339172,0.000115753566],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99816936,0.00023684531,0.00035581758,0.00043102534,0.00042298608,0.00038395092],"domain_scores_gemma":[0.998785,0.00023007908,0.00029159326,0.00024760552,0.00017562015,0.00027010858],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008150538,0.00024919564,0.00027238295,0.0004042423,0.00058166985,0.00071117276,0.00026545796,0.00010283809,0.00018249197],"category_scores_gemma":[0.00044365105,0.0002130284,0.00011066264,0.00037162975,0.000048998536,0.00068025297,0.000026407222,0.000468156,0.00015368046],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004844601,0.00008924657,0.00006836885,0.00003123534,0.000009283609,0.00008096567,0.00028519167,0.00000428523,0.008844721,0.000017992268,0.00021212698,0.99030817],"study_design_scores_gemma":[0.009561072,0.004548177,0.011984654,0.0049829436,0.00024094201,0.025312893,0.0013711745,0.15870285,0.7566338,0.013558191,0.009733079,0.0033702382],"about_ca_topic_score_codex":0.00000575724,"about_ca_topic_score_gemma":0.000010552362,"teacher_disagreement_score":0.9869379,"about_ca_system_score_codex":0.000098581484,"about_ca_system_score_gemma":0.00012852185,"threshold_uncertainty_score":0.8687046},"labels":[],"label_agreement":null},{"id":"W2081811590","doi":"10.1109/tasl.2013.2271591","title":"Large Vocabulary Speech Recognition on Parallel Architectures","year":2013,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Parallel computing; Graphics processing unit; Viterbi algorithm; CUDA; Speedup; Scalability; Massively parallel; Beam search; Heuristic; Multi-core processor; Computation; Search algorithm; Decoding methods; Algorithm; Artificial intelligence","score_opus":0.015379626009789192,"score_gpt":0.24419802523908518,"score_spread":0.22881839922929598,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2081811590","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16782132,0.0003258793,0.8256763,0.0012627887,0.00021655683,0.0003822901,0.000020227464,0.00047969792,0.0038149396],"genre_scores_gemma":[0.8885668,0.00006009435,0.10743015,0.0029232646,0.000098855046,0.00009429812,0.0000061879878,0.00003053065,0.00078981783],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9982214,0.00011629075,0.0002706157,0.00056797994,0.00036740385,0.0004563203],"domain_scores_gemma":[0.9991206,0.00014568474,0.00009874253,0.0003344518,0.000092856826,0.00020766223],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00026660843,0.00028446506,0.00024093161,0.0003561468,0.00042825035,0.0004134472,0.00029464645,0.00013840123,0.00067615067],"category_scores_gemma":[0.000024858122,0.00024626625,0.00011113664,0.00038390097,0.000055530723,0.00044133596,0.0000047405083,0.00041649162,0.0005868481],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022026252,0.00019794088,0.000003982644,0.00004297231,0.000020629503,0.000060858714,0.00104637,0.000021550855,0.0026003912,0.0000062389586,0.00018598263,0.9957911],"study_design_scores_gemma":[0.0037470793,0.0008565388,0.0012016529,0.0010735111,0.00012640239,0.0013948109,0.003086416,0.087819375,0.889805,0.007081155,0.0015422867,0.002265746],"about_ca_topic_score_codex":0.000058065234,"about_ca_topic_score_gemma":0.000059510705,"teacher_disagreement_score":0.9935253,"about_ca_system_score_codex":0.00003827178,"about_ca_system_score_gemma":0.000048403403,"threshold_uncertainty_score":0.999999},"labels":[],"label_agreement":null},{"id":"W2082488947","doi":"10.1155/2009/540409","title":"Alternative Speech Communication System for Persons with Severe Speech Disorders","year":2009,"lang":"en","type":"article","venue":"EURASIP Journal on Advances in Signal Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique; Université de Moncton","funders":"Natural Sciences and Engineering Research Council of Canada; New Brunswick Innovation Foundation; Université de Moncton","keywords":"Intelligibility (philosophy); Computer science; Dysarthria; Speech recognition; PESQ; Speech synthesis; PSQM; Voice activity detection; Perception; Speech processing; Speech communication; Speech technology; Speech enhancement; Artificial intelligence; Audiology; Psychology; Linguistics; Medicine","score_opus":0.019855821837908207,"score_gpt":0.2904018645717373,"score_spread":0.2705460427338291,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2082488947","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01341674,0.0025440003,0.95948803,0.0027907807,0.0001772711,0.00043459248,0.0000048120874,0.00015521765,0.020988578],"genre_scores_gemma":[0.812417,0.00022140621,0.18674178,0.00043710403,0.000097993,0.000010468872,0.0000014601699,0.000013564472,0.000059234524],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99835134,0.00015597543,0.0003683702,0.00032011804,0.00047176203,0.00033245707],"domain_scores_gemma":[0.99880064,0.00026984303,0.00041004797,0.00020908147,0.00019590574,0.00011448871],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060791854,0.00021291545,0.0002554339,0.00027373005,0.00044996446,0.00040898676,0.00082145445,0.000049403967,0.000010600596],"category_scores_gemma":[0.00005309958,0.0001661083,0.00007888213,0.00046707597,0.000054252792,0.0019817422,0.00002558231,0.00041970357,0.00000823127],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012348485,0.0001100618,0.00015830109,0.00003658345,0.0000075050975,0.000045903264,0.0004837708,0.0010716764,0.00010165787,0.0013583243,0.000027595843,0.99647516],"study_design_scores_gemma":[0.016397137,0.0073845442,0.0033069572,0.01895931,0.0001427768,0.0142228175,0.015480272,0.63817006,0.05165616,0.1993746,0.030444192,0.004461165],"about_ca_topic_score_codex":0.0000017561538,"about_ca_topic_score_gemma":0.000015759208,"teacher_disagreement_score":0.992014,"about_ca_system_score_codex":0.0002060685,"about_ca_system_score_gemma":0.00009837225,"threshold_uncertainty_score":0.67736995},"labels":[],"label_agreement":null},{"id":"W2084215616","doi":"10.1109/icassp.2014.6854821","title":"Two-stage speaker adaptation in subspace Gaussian mixture models","year":2014,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Subspace topology; Feature vector; Hidden Markov model; Pattern recognition (psychology); Context (archaeology); Mixture model; Artificial intelligence; Projection (relational algebra); Linear subspace; Feature (linguistics); Covariance; Gaussian; Adaptation (eye); Algorithm; Mathematics; Statistics","score_opus":0.033974109288578774,"score_gpt":0.2480830844242725,"score_spread":0.2141089751356937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2084215616","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0058094403,0.000009222003,0.82332325,0.001608643,0.00009658656,0.00007148355,5.461061e-7,0.0001132964,0.16896752],"genre_scores_gemma":[0.7591478,0.0000048053653,0.23612522,0.0008584099,0.000032383,0.000006736926,0.0000016170145,0.00000576547,0.0038172256],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991384,0.00009004774,0.00013795552,0.00026731924,0.00018334866,0.00018289233],"domain_scores_gemma":[0.99947435,0.00007696502,0.000037587626,0.00030550282,0.00003299084,0.00007263002],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029351917,0.00009188592,0.00010512039,0.00012420579,0.000034563895,0.00010248061,0.00028344482,0.000046274556,0.00020418808],"category_scores_gemma":[0.00003341872,0.00007738729,0.00003861606,0.00026320663,0.000012886366,0.00050746213,0.00004383793,0.00008048392,0.0002155496],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006677055,0.00007800763,0.00020953022,0.000008505958,0.000005943774,0.000015022129,0.0014636626,0.002617475,0.00064619735,0.74350035,0.0009144678,0.25053415],"study_design_scores_gemma":[0.00030830328,0.000013912928,0.0007237676,0.000011048697,0.0000011771946,0.0000041109756,0.00014216635,0.97700894,0.0027632846,0.01620585,0.0026795294,0.00013791556],"about_ca_topic_score_codex":0.00015782162,"about_ca_topic_score_gemma":0.0010026542,"teacher_disagreement_score":0.97439146,"about_ca_system_score_codex":0.000022296148,"about_ca_system_score_gemma":0.000020316596,"threshold_uncertainty_score":0.3155762},"labels":[],"label_agreement":null},{"id":"W2084514013","doi":"10.1109/msp.2009.932166","title":"Developments and directions in speech recognition and understanding, Part 1 [DSP Education]","year":2009,"lang":"en","type":"article","venue":"IEEE Signal Processing Magazine","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":227,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Computer science; Set (abstract data type); Focus (optics); Field (mathematics); Data science; Speech processing; Digital signal processing; Speech recognition","score_opus":0.06475663745855617,"score_gpt":0.2729375041776006,"score_spread":0.20818086671904443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2084514013","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4775688,0.003085946,0.3330736,0.0101634525,0.0013947426,0.0012473192,0.000018626968,0.001095215,0.1723523],"genre_scores_gemma":[0.93420607,0.00019008412,0.06372764,0.0009692683,0.00009521849,0.0000151309,0.000007935136,0.000009362049,0.0007793027],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.999076,0.00004026051,0.00021137041,0.0003289755,0.000158183,0.00018523088],"domain_scores_gemma":[0.99963397,0.000045930286,0.00007454961,0.00007479693,0.00007519831,0.00009557866],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024190267,0.00012329714,0.00012587824,0.00026598107,0.00017290066,0.00027018922,0.00010101924,0.000055902834,0.000026049624],"category_scores_gemma":[0.000030548952,0.0001206337,0.000013754274,0.00045530937,0.00004194084,0.0006580491,0.000017203976,0.00010838435,0.000037432],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000052827386,0.00009240721,0.00031566148,0.00001648735,0.0000026971954,0.000005606366,0.0002067974,1.9688527e-7,0.0012381844,0.00011048766,0.00062990363,0.99737626],"study_design_scores_gemma":[0.005264725,0.00086392,0.17337158,0.0046334914,0.00013147666,0.0022873157,0.0014710588,0.024949059,0.07672463,0.64339477,0.06283494,0.0040730243],"about_ca_topic_score_codex":0.0000051740312,"about_ca_topic_score_gemma":0.000030435513,"teacher_disagreement_score":0.99330324,"about_ca_system_score_codex":0.00008083587,"about_ca_system_score_gemma":0.000205494,"threshold_uncertainty_score":0.49192992},"labels":[],"label_agreement":null},{"id":"W2084716563","doi":"10.1109/isspa.2012.6310452","title":"The A* speech recognition system on parallel architectures","year":2012,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Viterbi algorithm; Parallel computing; Viterbi decoder; Speedup; Graphics processing unit; Scalability; Computation; Thread (computing); Speech recognition; Decoding methods; Hidden Markov model; Algorithm","score_opus":0.03562324010333636,"score_gpt":0.2451685944611037,"score_spread":0.20954535435776733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2084716563","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10244062,0.00022290686,0.2208288,0.0047159884,0.0022944156,0.00054778974,0.00000477188,0.001327693,0.667617],"genre_scores_gemma":[0.9215849,0.000011733059,0.07608546,0.0008722221,0.000266769,0.00003923918,0.0000014419682,0.000008124955,0.0011301035],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990517,0.00012162377,0.0001390339,0.00015162108,0.00024255979,0.00029345625],"domain_scores_gemma":[0.99906605,0.000398289,0.00004526655,0.0003496172,0.000037439957,0.00010333719],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00046986566,0.000095318006,0.00007661984,0.000055968463,0.00024711646,0.00014735803,0.00039184952,0.00003961572,0.000059106063],"category_scores_gemma":[0.00006860488,0.00005364348,0.0000665908,0.00013767944,0.000023777195,0.000119701166,0.000051568288,0.00009264741,0.0021177593],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000065474696,0.000029269548,0.00005173388,0.0000039075217,0.000009274059,0.0000021506462,0.00007079214,9.06882e-7,0.000039438753,0.01717972,0.0022893636,0.9803169],"study_design_scores_gemma":[0.003144608,0.00083696423,0.048869275,0.000576871,0.00009906264,0.0024965869,0.0034396467,0.044173643,0.4720605,0.06045469,0.36047813,0.0033699968],"about_ca_topic_score_codex":0.000011166987,"about_ca_topic_score_gemma":0.000008057408,"teacher_disagreement_score":0.9769469,"about_ca_system_score_codex":0.000030385583,"about_ca_system_score_gemma":0.000010376745,"threshold_uncertainty_score":0.9986592},"labels":[],"label_agreement":null},{"id":"W2085555790","doi":"10.1121/1.4785782","title":"Improving automatic speech recognition via better analysis and adaptation","year":2005,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Computer science; Speech recognition; Mel-frequency cepstrum; Normalization (sociology); Hidden Markov model; Maximum a posteriori estimation; Feature (linguistics); Pattern recognition (psychology); Speech processing; Autoregressive model; Parametric statistics; Artificial intelligence; Feature extraction; Maximum likelihood","score_opus":0.016954566396927488,"score_gpt":0.2345133681408842,"score_spread":0.2175588017439567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2085555790","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036383323,0.000057381665,0.955903,0.0074846577,0.00005486213,0.000058194866,0.0000016813018,0.0000137422185,0.000043151475],"genre_scores_gemma":[0.14129274,0.000083422114,0.8565651,0.0019501715,0.00009098709,5.7569355e-7,2.067405e-7,0.000004128132,0.000012668518],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987973,0.00017008751,0.00041070813,0.00008610414,0.0003991399,0.00013667559],"domain_scores_gemma":[0.9984363,0.0005560439,0.00055351795,0.00021743463,0.00017677671,0.00005993938],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007508299,0.0000878229,0.00022899394,0.000048424223,0.00014023672,0.000043064447,0.0004626021,0.000042356318,0.00006558759],"category_scores_gemma":[0.00017487361,0.00004789953,0.00033147004,0.0005712157,0.00018565984,0.00027075753,0.00010951029,0.00020707063,0.0000072140933],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000051187717,0.00003607797,0.00003972083,0.000008072164,0.00019359481,2.80491e-7,0.00032369694,0.000063209896,0.0041282414,3.8717133e-7,0.0005113,0.9946903],"study_design_scores_gemma":[0.00013945925,0.000059601665,0.0017191052,0.000019923125,0.00061441626,0.00006113196,0.00033784012,0.99227905,0.0037867522,0.0008290325,0.00008731058,0.00006638011],"about_ca_topic_score_codex":0.000032121792,"about_ca_topic_score_gemma":0.0000017092711,"teacher_disagreement_score":0.9946239,"about_ca_system_score_codex":0.000039828825,"about_ca_system_score_gemma":0.000032222393,"threshold_uncertainty_score":0.19532862},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W2087119585","doi":"10.1109/icassp.2010.5495503","title":"Score normalization in playback attack detection","year":2010,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":59,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Phrase; Utterance; Computer science; Speech recognition; Similarity (geometry); Normalization (sociology); Set (abstract data type); Pattern recognition (psychology); Thresholding; Task (project management); Artificial intelligence; Natural language processing; Detector","score_opus":0.025001573441882915,"score_gpt":0.24846226710243866,"score_spread":0.22346069366055574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2087119585","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.51634943,0.0000015466825,0.45484823,0.00023529847,0.0004629661,0.00007518771,1.6393331e-7,0.00013670651,0.027890442],"genre_scores_gemma":[0.97809905,0.0000023403322,0.021222256,0.00026277802,0.00003438777,0.000006751488,8.261907e-7,0.0000030125357,0.000368607],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999522,0.00001797535,0.00010705691,0.00014893326,0.00010079233,0.00010328029],"domain_scores_gemma":[0.9996948,0.000031886153,0.00002365671,0.00017670677,0.000036408383,0.000036538655],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013585007,0.000049019414,0.000049333987,0.00011242508,0.00003493316,0.000072430215,0.00018604966,0.000053051255,0.00033662195],"category_scores_gemma":[0.000050781116,0.000043955235,0.00002050871,0.0002955476,0.000010413479,0.00038971042,0.00003329579,0.00008963615,0.0003724597],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000053713625,0.00008785897,0.011549799,0.000007355846,0.0000036484184,0.000010162565,0.00022227192,0.000026752981,0.04606506,0.011516155,0.0005752443,0.9299303],"study_design_scores_gemma":[0.0005711483,0.000049085073,0.11560449,0.000013820421,0.0000024737933,0.000070007,0.000036216312,0.38623077,0.4853896,0.0020568392,0.009634847,0.00034070632],"about_ca_topic_score_codex":0.000033128043,"about_ca_topic_score_gemma":0.001669584,"teacher_disagreement_score":0.9295896,"about_ca_system_score_codex":0.000009559307,"about_ca_system_score_gemma":0.000013146962,"threshold_uncertainty_score":0.47873402},"labels":[],"label_agreement":null},{"id":"W2088104516","doi":"10.1121/1.4806530","title":"Coarticulation in a whole event model of speech production","year":2013,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan; University of British Columbia","funders":"","keywords":"Coarticulation; Speech production; Computer science; Event (particle physics); Variation (astronomy); Biomechanics; Speech recognition; Physics; Vowel","score_opus":0.01987518365265132,"score_gpt":0.24551915067460545,"score_spread":0.22564396702195413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2088104516","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19920212,0.000031286374,0.7809313,0.019523913,0.0001099566,0.00014067201,7.80279e-7,0.0000050920703,0.000054866934],"genre_scores_gemma":[0.81336176,0.000035010784,0.18620178,0.00029968529,0.000040422503,0.0000011426289,3.957562e-8,0.0000030050082,0.00005713819],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989396,0.00011727716,0.0003787592,0.00006276413,0.00039185796,0.00010975312],"domain_scores_gemma":[0.998933,0.00016497489,0.00039356848,0.00023413156,0.00024026178,0.000034055047],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056347315,0.000058910566,0.00016863512,0.00002072224,0.000044522883,0.000011540812,0.0004705743,0.000030654748,0.00002008273],"category_scores_gemma":[0.00023145684,0.00003134335,0.00018698523,0.00028966248,0.00017705715,0.00019143021,0.00009488688,0.00016527792,0.000005561646],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003854997,0.00036756563,0.00028740862,0.000043718635,0.00008587239,3.2695758e-7,0.002505574,0.1498431,0.39368677,0.00003320422,0.016648704,0.4364592],"study_design_scores_gemma":[0.000119420605,0.000055655,0.0023031684,0.000048879076,0.000026725533,0.00001797796,0.00035549988,0.97421914,0.017677587,0.005100519,0.000036652837,0.00003875381],"about_ca_topic_score_codex":0.000039460603,"about_ca_topic_score_gemma":4.741469e-7,"teacher_disagreement_score":0.82437605,"about_ca_system_score_codex":0.00003879203,"about_ca_system_score_gemma":0.00005582939,"threshold_uncertainty_score":0.12781447},"labels":[],"label_agreement":null},{"id":"W2092684968","doi":"10.1121/1.1315288","title":"Spontaneous speech recognition using a statistical coarticulatory model for the vocal-tract-resonance dynamics","year":2000,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":89,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Science Foundation","keywords":"Vocal tract; Computer science; Context (archaeology); Speech recognition; Benchmark (surveying); Hidden Markov model; Property (philosophy); Set (abstract data type); Artificial intelligence; Statistical model; Computation; Pattern recognition (psychology); Algorithm","score_opus":0.028178239125639517,"score_gpt":0.26690674222336963,"score_spread":0.2387285030977301,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2092684968","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020320548,0.00013759757,0.9753565,0.003717065,0.00013885266,0.00020613434,0.000052079296,0.000013779471,0.000057412093],"genre_scores_gemma":[0.26005885,0.00034955345,0.736653,0.0026941712,0.00012853931,0.0000028272498,6.5331665e-7,0.000016021124,0.00009644354],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983693,0.00016964377,0.00048331902,0.00012761938,0.00056651194,0.00028365734],"domain_scores_gemma":[0.9966207,0.0023298496,0.00033174548,0.00036827463,0.00025928143,0.00009010974],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00086334965,0.00014108719,0.0002714719,0.000012948316,0.00035646875,0.000052479583,0.0009780284,0.00007099634,0.000095924515],"category_scores_gemma":[0.0003140355,0.00007066201,0.00038690298,0.00022834315,0.0005562728,0.00015117814,0.00008482431,0.00036966288,0.000008189535],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014955958,0.00018429896,0.000004175135,0.000015737656,0.00007928361,0.000011195604,0.0003673699,0.018685216,0.0007824401,0.00003379087,0.0039161295,0.97577083],"study_design_scores_gemma":[0.00025278665,0.000098966186,0.00014144181,0.000049764654,0.00022246137,0.0013269932,0.00027868172,0.99154484,0.00024645432,0.0053451415,0.00039039602,0.000102080674],"about_ca_topic_score_codex":0.00002911617,"about_ca_topic_score_gemma":0.0000019359463,"teacher_disagreement_score":0.9756687,"about_ca_system_score_codex":0.00011871447,"about_ca_system_score_gemma":0.00015986909,"threshold_uncertainty_score":0.28815132},"labels":[],"label_agreement":null},{"id":"W2095168634","doi":"10.1121/1.4781344","title":"Auditory priming releases Chinese speech from informational masking","year":2006,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Sentence; Masking (illustration); Speech recognition; Priming (agriculture); Noise (video); Computer science; Speech perception; Psychology; Perception; Natural language processing; Artificial intelligence","score_opus":0.008951168816919612,"score_gpt":0.22461454555542765,"score_spread":0.21566337673850802,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2095168634","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05477078,0.00012124211,0.9389473,0.0047627697,0.00045271686,0.000060369133,0.0000069874063,0.000020384885,0.00085744896],"genre_scores_gemma":[0.5626851,0.000083600826,0.43484196,0.0016132608,0.0007108134,5.133814e-7,5.9791114e-7,0.00000636913,0.00005778943],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985745,0.000105287305,0.00044736947,0.00006430693,0.00065479614,0.000153741],"domain_scores_gemma":[0.9977783,0.0011428542,0.0005862568,0.00026210694,0.00018276754,0.00004770606],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004099054,0.00010175998,0.00020378978,0.000020597461,0.00019721105,0.000044868008,0.0010160335,0.00004441433,0.000075436226],"category_scores_gemma":[0.00027830616,0.00005138996,0.0003471785,0.00026499352,0.00024619777,0.00028930037,0.00020703606,0.00027771606,0.0000115077855],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014080381,0.00061350927,0.0018704875,0.00006635013,0.0005014908,0.00000989148,0.0029780266,0.017171042,0.039184116,0.00016771058,0.24094199,0.69635457],"study_design_scores_gemma":[0.0006790226,0.0001236098,0.05073673,0.00019838689,0.00018809727,0.0002290677,0.0011288585,0.9127311,0.006141655,0.020056127,0.007499304,0.00028803188],"about_ca_topic_score_codex":0.00008799068,"about_ca_topic_score_gemma":5.5844555e-7,"teacher_disagreement_score":0.8955601,"about_ca_system_score_codex":0.000052362895,"about_ca_system_score_gemma":0.000097799166,"threshold_uncertainty_score":0.20956218},"labels":[],"label_agreement":null},{"id":"W2095504751","doi":"10.1558/ijsll.v14i1.145","title":"Forensic automatic speaker recognition using Bayesian interpretation and statistical compensation for mismatched conditions","year":2007,"lang":"en","type":"article","venue":"International Journal of Speech Language and the Law","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Bayesian probability; Interpretation (philosophy); Computer science; Speech recognition; Speaker recognition; Compensation (psychology); Artificial intelligence; Natural language processing; Pattern recognition (psychology); Psychology; Programming language","score_opus":0.018240739386723357,"score_gpt":0.30168284742505624,"score_spread":0.28344210803833286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2095504751","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22837602,0.00007788594,0.76909137,0.0012995545,0.00035811352,0.00013914455,0.0000230081,0.0000137580255,0.0006211498],"genre_scores_gemma":[0.8281643,0.000010764845,0.17110252,0.00050850323,0.00018305231,0.0000016269383,0.000013737877,0.000005215603,0.000010284221],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991407,0.000054249656,0.00035231607,0.000102681115,0.00024988523,0.000100177385],"domain_scores_gemma":[0.9984811,0.00071735476,0.0003353135,0.00008853739,0.00031927318,0.000058426936],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009542216,0.000080786835,0.00015443664,0.00011550853,0.00012941935,0.00028559266,0.00022286778,0.000037558235,0.000033078504],"category_scores_gemma":[0.0002640667,0.00005829047,0.00006093456,0.00003425585,0.00016340433,0.00047079747,0.0000386145,0.000086897795,0.000001932266],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001712874,0.000029869647,0.000028963297,0.000013803147,0.00013849974,0.0001036755,0.002596701,0.0000016422024,0.001803236,0.049767967,0.000036557827,0.9453078],"study_design_scores_gemma":[0.008330033,0.00020420265,0.0035574646,0.0005881291,0.00026321498,0.0067388336,0.0032868362,0.46647787,0.029165495,0.48061123,0.00037207783,0.00040461327],"about_ca_topic_score_codex":0.000046997444,"about_ca_topic_score_gemma":0.000076670156,"teacher_disagreement_score":0.9449032,"about_ca_system_score_codex":0.000034039,"about_ca_system_score_gemma":0.000021437529,"threshold_uncertainty_score":0.27539766},"labels":[],"label_agreement":null},{"id":"W2096698602","doi":"10.1109/sipnn.1994.344815","title":"HMMs with mixtures of trend functions for automatic speech recognition","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Hidden Markov model; Speech recognition; TIMIT; Computer science; Set (abstract data type); Task (project management); State (computer science); Mixture model; Trajectory; Pattern recognition (psychology); SIGNAL (programming language); Artificial intelligence; Maximum likelihood; Mathematics; Algorithm; Statistics; Engineering","score_opus":0.04627982596179582,"score_gpt":0.2315993290325417,"score_spread":0.1853195030707459,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096698602","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048391324,0.00007302885,0.86264807,0.0012358637,0.00027335514,0.00047558872,0.00003659869,0.0005048127,0.08636134],"genre_scores_gemma":[0.17677009,0.0000116549745,0.81592417,0.00034710194,0.00005635562,0.00008577057,0.000013268085,0.000011914701,0.0067796884],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99934363,0.000022838434,0.00016653091,0.00018500965,0.00014910828,0.00013289953],"domain_scores_gemma":[0.99940234,0.0001827773,0.000069471695,0.00021541135,0.00008019969,0.000049795806],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00008821369,0.00008365118,0.00012313719,0.0001349577,0.00006589355,0.00004637209,0.00016510724,0.000038410388,0.0015240368],"category_scores_gemma":[0.000043089,0.0000609624,0.00006585431,0.0002762523,0.000027909433,0.00025212954,0.000014379579,0.000033004646,0.00012978185],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000031251936,0.00010906765,0.00002786773,0.000018410088,0.000022756829,0.0000015504193,0.00008444227,3.9129267e-7,0.00043533268,0.00021669535,0.0118106445,0.9872697],"study_design_scores_gemma":[0.0038181753,0.00177969,0.0025082417,0.00027875006,0.00019956437,0.0004288761,0.0005454175,0.48132277,0.47232488,0.01615739,0.019470977,0.0011652773],"about_ca_topic_score_codex":0.000008211487,"about_ca_topic_score_gemma":0.000045098026,"teacher_disagreement_score":0.9861044,"about_ca_system_score_codex":0.000010316811,"about_ca_system_score_gemma":0.000007689056,"threshold_uncertainty_score":0.9993887},"labels":[],"label_agreement":null},{"id":"W2096875330","doi":"10.1109/tasl.2008.916530","title":"Rapid Speaker Adaptation Using Clustered Maximum-Likelihood Linear Basis With Sparse Training Data","year":2008,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Basis (linear algebra); Adaptation (eye); Computer science; Maximum likelihood; Pattern recognition (psychology); Speech recognition; Artificial intelligence; Statistics; Mathematics; Psychology","score_opus":0.09851490030450993,"score_gpt":0.2764646673115335,"score_spread":0.17794976700702358,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096875330","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07160345,0.0004363657,0.92659557,0.00025545558,0.00012779044,0.00019029409,0.000029935602,0.00026160915,0.00049951905],"genre_scores_gemma":[0.58382297,0.000095972864,0.41548195,0.000404064,0.000072950614,0.0000070212895,0.000008871165,0.00002658308,0.00007958303],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99810684,0.000098539495,0.00029918845,0.0006862794,0.0004049936,0.00040415986],"domain_scores_gemma":[0.99888647,0.000092260445,0.00014570709,0.00058212015,0.000100677695,0.00019277981],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035623033,0.00026877495,0.00028012568,0.00028289127,0.0006112436,0.00018276283,0.0004391051,0.00010030737,0.000117647454],"category_scores_gemma":[0.00001842702,0.00023433556,0.00005347495,0.00058333745,0.00010390263,0.0012444059,0.000008942401,0.00028027003,0.000022570784],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052647913,0.00009563517,0.0000056822823,0.000035641206,0.000035532048,0.00019627323,0.006966261,0.00022380521,0.0014955009,6.83234e-7,0.000013370368,0.99087894],"study_design_scores_gemma":[0.0016576486,0.00018305742,0.00009626,0.0003745579,0.00011914317,0.0024510792,0.0054312637,0.9326308,0.05590977,0.000045864293,0.00040569075,0.00069490017],"about_ca_topic_score_codex":0.00008591004,"about_ca_topic_score_gemma":0.00017112313,"teacher_disagreement_score":0.99018407,"about_ca_system_score_codex":0.00004746579,"about_ca_system_score_gemma":0.0002493566,"threshold_uncertainty_score":0.9555927},"labels":[],"label_agreement":null},{"id":"W2096958852","doi":"10.1109/itng.2009.332","title":"Feature Combination Using Multiple Spectral Cues for Robust Speech Recognition in Mobile Communications","year":2009,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Computer science; Speech recognition; Mel-frequency cepstrum; GSM; Feature (linguistics); Front and back ends; Speech processing; Feature extraction; Task (project management); Cepstrum; Artificial intelligence; Mobile telephony; Voice activity detection; Pattern recognition (psychology); Mobile radio; Engineering; Telecommunications","score_opus":0.08309602341530054,"score_gpt":0.30263847420268214,"score_spread":0.2195424507873816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096958852","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20364282,0.00018139099,0.77802205,0.007409777,0.0002558421,0.0015168563,0.000022845185,0.00044230465,0.00850614],"genre_scores_gemma":[0.30180293,0.000047194004,0.69749856,0.00037533758,0.000025835947,0.00003821228,0.000045569675,0.0000053301414,0.00016101086],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99920344,0.00006115055,0.00017123041,0.00023842315,0.00012596976,0.00019979278],"domain_scores_gemma":[0.9990801,0.00020523337,0.000068910405,0.00045969867,0.0001382339,0.000047816633],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027380043,0.00010554878,0.00013425271,0.00020819099,0.00014705893,0.00013601471,0.0005005374,0.00008626428,0.000026733329],"category_scores_gemma":[0.00010208014,0.000105867664,0.0000714508,0.00039498127,0.000023106595,0.0006142154,0.000045713034,0.00011742517,0.000023236758],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010505401,0.00042424354,0.00045590536,0.000006021771,0.0000054944053,0.0000017587537,0.00017987793,0.000042753338,0.0040886076,0.0017358639,0.0009646422,0.9920843],"study_design_scores_gemma":[0.0015538032,0.00022293905,0.0059583755,0.00007781271,0.000012569698,0.00004368669,0.00027684073,0.8989129,0.06656939,0.023538664,0.0024298152,0.00040318476],"about_ca_topic_score_codex":0.000027269632,"about_ca_topic_score_gemma":0.0002478349,"teacher_disagreement_score":0.99168116,"about_ca_system_score_codex":0.00009090237,"about_ca_system_score_gemma":0.000030128072,"threshold_uncertainty_score":0.4317158},"labels":[],"label_agreement":null},{"id":"W2098509485","doi":"10.1109/ccece.1997.614787","title":"Recent progress in automatic recognition of continuous speech","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Computer science; Merge (version control); Speech recognition; Vocabulary; Artificial intelligence; Language model; Pruning; Word error rate; Phone; Graph; Natural language processing; Pattern recognition (psychology); Information retrieval; Theoretical computer science","score_opus":0.04223942686832255,"score_gpt":0.25127615110540286,"score_spread":0.2090367242370803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2098509485","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7695247,0.0010854921,0.014355741,0.005330004,0.00058272784,0.0008930191,0.0000057073203,0.0007645901,0.20745803],"genre_scores_gemma":[0.6411268,0.00045820305,0.35694566,0.00046012932,0.000028797147,0.00005063864,0.0000029735447,0.000011399642,0.0009154141],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99911314,0.000068218935,0.00028306947,0.00018464451,0.00019326573,0.00015767361],"domain_scores_gemma":[0.9994886,0.00007751154,0.000080607904,0.00021685725,0.00009239621,0.000044035467],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00021945684,0.00007496659,0.00015651489,0.00016806152,0.000016055998,0.00003935993,0.00025060217,0.00004528421,0.0023652625],"category_scores_gemma":[0.00006852732,0.000065876,0.00003688231,0.0004430133,0.000030554893,0.00021101818,0.000040645275,0.00005480189,0.0005197297],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.889906e-7,0.00016292126,0.0008595581,0.000009148218,0.0000034897137,0.00001530379,0.00012204786,2.9866097e-8,0.00003202089,0.00016487604,0.0008037178,0.9978262],"study_design_scores_gemma":[0.004123246,0.0006613121,0.044467878,0.00075126946,0.000032809632,0.00041817094,0.00049078284,0.6933038,0.21435888,0.017837578,0.022117907,0.0014363303],"about_ca_topic_score_codex":0.0000046945397,"about_ca_topic_score_gemma":0.000014357406,"teacher_disagreement_score":0.99638987,"about_ca_system_score_codex":0.00002248968,"about_ca_system_score_gemma":0.000008097337,"threshold_uncertainty_score":0.9985467},"labels":[],"label_agreement":null},{"id":"W2099621636","doi":"","title":"Vocal Tract Length Perturbation (VTLP) improves speech recognition","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":335,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Speech recognition; Vocal tract; Normalization (sociology); Convolutional neural network; Spectrogram; Artificial neural network; Test set; Dynamic time warping; Word error rate; TIMIT; Image warping; Artificial intelligence; Pattern recognition (psychology); Hidden Markov model","score_opus":0.024196056855806596,"score_gpt":0.22428764260694675,"score_spread":0.20009158575114017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2099621636","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38393107,0.00004819433,0.3286797,0.008211552,0.0009938665,0.0008194505,0.000004411078,0.0012313428,0.2760804],"genre_scores_gemma":[0.7033343,0.00003884849,0.28639516,0.0024030055,0.00021998184,0.00009333124,0.000018218672,0.000017494936,0.0074796993],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99886036,0.00006464784,0.00023081941,0.00034549725,0.00025595605,0.0002426992],"domain_scores_gemma":[0.9991799,0.00016613443,0.00006627383,0.00029167152,0.00017727503,0.0001187712],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00019095014,0.00013567605,0.00012553304,0.00012808394,0.000099627265,0.0003426846,0.00032965624,0.000093813425,0.0023431662],"category_scores_gemma":[0.00013627115,0.00011059399,0.00008771928,0.00022125947,0.000025524692,0.0015840582,0.000050395694,0.00011319925,0.005139957],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001083639,0.00008251918,0.00002620575,0.000003534365,0.000005752305,0.000002649804,0.0000695294,4.4173596e-8,0.0043995227,0.0007057286,0.0033685889,0.99133486],"study_design_scores_gemma":[0.0016869392,0.00058540876,0.047527615,0.00007872809,0.000041586703,0.0004484887,0.00073082367,0.2405309,0.52996004,0.15838647,0.018263321,0.0017597178],"about_ca_topic_score_codex":0.00010757934,"about_ca_topic_score_gemma":0.00000766501,"teacher_disagreement_score":0.98957515,"about_ca_system_score_codex":0.000036261175,"about_ca_system_score_gemma":0.0000309995,"threshold_uncertainty_score":0.99856883},"labels":[],"label_agreement":null},{"id":"W2100220834","doi":"10.1109/icassp.2005.1415060","title":"Discriminative Training of CDHMMs for Maximum Relative Separation Margin","year":2006,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Discriminative model; Minimax; Computer science; Margin (machine learning); Hidden Markov model; Probabilistic logic; Pattern recognition (psychology); Artificial intelligence; Separation (statistics); Reduction (mathematics); Optimization problem; Mathematical optimization; Word error rate; Mathematics; Algorithm; Machine learning","score_opus":0.05021710298073339,"score_gpt":0.29499860457972443,"score_spread":0.24478150159899104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2100220834","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0043447614,0.000007628085,0.882652,0.00057482446,0.00007092078,0.00016478142,0.0000058339087,0.000051981748,0.11212727],"genre_scores_gemma":[0.65905994,6.7010797e-7,0.33831885,0.00006120288,0.000026288897,0.000029523417,0.000007032345,0.0000038315807,0.0024926339],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99939,0.000040795247,0.00017319391,0.0001668076,0.00011404753,0.00011516164],"domain_scores_gemma":[0.9993954,0.0002909743,0.00008053431,0.00011244605,0.00010008439,0.000020573074],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022856113,0.000066552486,0.0001110657,0.00007862496,0.000051490453,0.000028922968,0.00014947752,0.000033195785,0.00006659687],"category_scores_gemma":[0.00005989851,0.00005557822,0.00006706799,0.00014462227,0.000028320335,0.00039641222,0.000021005506,0.00002874657,0.000013416633],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000115735675,0.00007190989,0.000059252576,0.000011394877,0.00001662816,0.0000013015201,0.002111581,0.000013650876,0.0023833804,0.67321867,0.0018111438,0.32028952],"study_design_scores_gemma":[0.0009876039,0.0002337602,0.0060911304,0.00004552842,0.000026674192,0.000009904006,0.0017556897,0.1500144,0.20688261,0.629266,0.0043182843,0.00036839867],"about_ca_topic_score_codex":0.00002471921,"about_ca_topic_score_gemma":0.000030841784,"teacher_disagreement_score":0.6547152,"about_ca_system_score_codex":0.00001761084,"about_ca_system_score_gemma":0.000024621808,"threshold_uncertainty_score":0.2266414},"labels":[],"label_agreement":null},{"id":"W2102113734","doi":"","title":"Towards End-To-End Speech Recognition with Recurrent Neural Networks","year":2014,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1855,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Word error rate; Trigram; Speech recognition; Connectionism; Language model; Recurrent neural network; Artificial intelligence; Lexicon; Artificial neural network; Word (group theory); Time delay neural network; Natural language processing","score_opus":0.02874013249881295,"score_gpt":0.24337099036898666,"score_spread":0.21463085787017372,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102113734","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030109417,0.00001057001,0.8987174,0.0028819507,0.0006594907,0.00023486326,0.0000027397575,0.00040970108,0.06697389],"genre_scores_gemma":[0.6809036,0.000012477232,0.3146043,0.003626865,0.00031783,0.00004062855,0.000015007834,0.000018382323,0.00046086079],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984757,0.00012650884,0.0002118675,0.00046947895,0.00036122647,0.00035524217],"domain_scores_gemma":[0.9990068,0.00012422922,0.000061882485,0.00041453948,0.0001501941,0.00024237354],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040688284,0.00018002898,0.00018470464,0.00014626606,0.000104921084,0.00024158291,0.00047195223,0.00006541959,0.00088095246],"category_scores_gemma":[0.00007702717,0.00013525343,0.0000670964,0.0004731862,0.000029727169,0.0003737988,0.000116378396,0.00015278894,0.0004522608],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011861743,0.000039228893,0.00005935427,0.0000027629203,0.000008034753,0.0000071276386,0.00004085911,0.000018324468,0.000025517531,0.00067365455,0.0016873063,0.997426],"study_design_scores_gemma":[0.0011297875,0.001123027,0.0069566346,0.00011981684,0.000039435625,0.0003336217,0.00007642042,0.93269646,0.019717103,0.0037369346,0.032890495,0.0011802629],"about_ca_topic_score_codex":0.000053291362,"about_ca_topic_score_gemma":0.00010388852,"teacher_disagreement_score":0.9962457,"about_ca_system_score_codex":0.000033012555,"about_ca_system_score_gemma":0.000024837998,"threshold_uncertainty_score":0.96458113},"labels":[],"label_agreement":null},{"id":"W2103359087","doi":"","title":"Phone Recognition with the Mean-Covariance Restricted Boltzmann Machine","year":2010,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":275,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"TIMIT; Boltzmann machine; Computer science; Covariance; Hidden Markov model; Restricted Boltzmann machine; Speech recognition; Mixture model; Artificial intelligence; Covariance matrix; Pattern recognition (psychology); Algorithm; Artificial neural network; Mathematics; Statistics","score_opus":0.01803519807988988,"score_gpt":0.2190759133437164,"score_spread":0.20104071526382652,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103359087","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07910521,0.000031025764,0.801684,0.018529676,0.00071778987,0.00040506865,0.0000120890145,0.0007938029,0.09872129],"genre_scores_gemma":[0.6467043,0.00002307235,0.34641904,0.0035244497,0.00017732121,0.000057531684,0.000013292848,0.000017706945,0.0030632957],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99903816,0.000060871775,0.0001319271,0.00029623884,0.00026866145,0.00020416357],"domain_scores_gemma":[0.9989732,0.00019385692,0.000070805916,0.0005422967,0.00014317883,0.000076694516],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023981532,0.000121386896,0.00010280565,0.000073939365,0.00019068006,0.00019067315,0.0005930828,0.00005835178,0.00073450245],"category_scores_gemma":[0.00007205134,0.000067532674,0.000039103266,0.00056024466,0.00006106221,0.0003463222,0.00006483474,0.00027085247,0.0007490541],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004954717,0.00017431738,0.000117061994,0.000006259807,0.00004776669,0.000047207806,0.0003913259,0.0000015859451,0.024226576,0.01178994,0.01510084,0.9480476],"study_design_scores_gemma":[0.0057724644,0.0006533781,0.04235618,0.000114961535,0.00013810162,0.0016382164,0.0004619315,0.12990539,0.53569,0.033658642,0.24688613,0.0027245693],"about_ca_topic_score_codex":0.00011655067,"about_ca_topic_score_gemma":0.0007131912,"teacher_disagreement_score":0.945323,"about_ca_system_score_codex":0.0000078999865,"about_ca_system_score_gemma":0.000042569554,"threshold_uncertainty_score":0.96278244},"labels":[],"label_agreement":null},{"id":"W2103385917","doi":"10.1109/icassp.1994.389568","title":"Vowel classification using a neural predictive HMM: a discriminative training approach","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Hidden Markov model; Discriminative model; Speech recognition; Computer science; Perceptron; Artificial intelligence; Pattern recognition (psychology); Frame (networking); Multilayer perceptron; Vowel; Artificial neural network","score_opus":0.2575933512278999,"score_gpt":0.2855798959375007,"score_spread":0.027986544709600825,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103385917","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02015533,0.00001720061,0.87363005,0.00052234286,0.000108314634,0.0001625245,0.0000025174775,0.00022575134,0.10517596],"genre_scores_gemma":[0.8173096,0.0000026837372,0.1818993,0.0002245033,0.000042695032,0.0000213353,0.0000015366307,0.000006350613,0.0004920053],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99894166,0.000094511575,0.00016628027,0.00035474636,0.00022981013,0.00021298957],"domain_scores_gemma":[0.99945366,0.000083834864,0.00007115347,0.0002333465,0.00007371096,0.000084318795],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013917791,0.00011391835,0.00012188304,0.00012472148,0.00014295141,0.0001374262,0.00032810742,0.00004813424,0.00013517097],"category_scores_gemma":[0.00006981184,0.00009541782,0.00006488946,0.00033325324,0.000054891272,0.00064435904,0.0000575305,0.00010061076,0.000037146598],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000075452276,0.00036045277,0.00014545432,0.0000135812315,0.000047770103,0.00001176093,0.037722144,0.00010521732,0.0022799284,0.0237866,0.0008198733,0.93469965],"study_design_scores_gemma":[0.00015462779,0.000031232456,0.0024380009,0.000007166279,0.00000907286,0.00004004472,0.0024100957,0.9937714,0.0004819106,0.00046721255,0.000061423685,0.00012783767],"about_ca_topic_score_codex":0.00001303374,"about_ca_topic_score_gemma":0.0000016315219,"teacher_disagreement_score":0.9936662,"about_ca_system_score_codex":0.000051553925,"about_ca_system_score_gemma":0.00001300095,"threshold_uncertainty_score":0.38910258},"labels":[],"label_agreement":null},{"id":"W2103962059","doi":"10.1109/tasl.2006.881695","title":"Dialect/Accent Classification Using Unrestricted Audio","year":2007,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Artificial intelligence; Classifier (UML); Natural language processing; Speech recognition; Utterance","score_opus":0.03328024716986407,"score_gpt":0.2886593159864606,"score_spread":0.25537906881659656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103962059","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10905296,0.00032863746,0.8881769,0.0002159637,0.00025255888,0.0001627073,0.000004140919,0.0003118488,0.001494249],"genre_scores_gemma":[0.9048303,0.000053012664,0.09435242,0.0004088848,0.00008182996,0.0000076318765,0.0000016463785,0.000018997715,0.0002453087],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984516,0.0000650379,0.00031312474,0.0004542253,0.00032787872,0.00038816364],"domain_scores_gemma":[0.9991508,0.00014311516,0.0001343772,0.00027760587,0.00010579826,0.00018828826],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046875258,0.00020446746,0.00018693224,0.00040069188,0.00044210203,0.00028197354,0.00025262684,0.000120679346,0.000069078436],"category_scores_gemma":[0.000027735437,0.00019440074,0.000075081414,0.00084813527,0.000060543967,0.00051596086,0.0000032302537,0.00026055076,0.000029006249],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022919705,0.00010956298,0.000024019782,0.000026756523,0.000013920286,0.00005267276,0.0006992275,0.000021028396,0.044355445,0.000024841496,0.0000137984025,0.9546358],"study_design_scores_gemma":[0.0010991279,0.00012164825,0.002990936,0.0002582212,0.00008849279,0.0004678727,0.0012687927,0.14521383,0.8469469,0.00018000195,0.00057154975,0.0007926171],"about_ca_topic_score_codex":0.0000538316,"about_ca_topic_score_gemma":0.00007644988,"teacher_disagreement_score":0.9538432,"about_ca_system_score_codex":0.000115791605,"about_ca_system_score_gemma":0.000100074285,"threshold_uncertainty_score":0.7927432},"labels":[],"label_agreement":null},{"id":"W2104046483","doi":"10.1109/isspa.2001.950249","title":"Hybrid architectures for complex phonetic features classification: a unified approach","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Computer science; Hidden Markov model; Speech recognition; Artificial intelligence; Artificial neural network; Classifier (UML); Pattern recognition (psychology); Boosting (machine learning); Backpropagation; Learning vector quantization; Vector quantization; Time delay neural network; Machine learning","score_opus":0.0997431855592085,"score_gpt":0.2613932056576351,"score_spread":0.16165002009842658,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2104046483","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026721454,0.00007693093,0.8556696,0.003313686,0.00010760255,0.0003804289,0.0000075908993,0.00035403864,0.13741794],"genre_scores_gemma":[0.5778649,0.0000042549264,0.41732103,0.0011509401,0.00006517618,0.000077996636,0.0000071070044,0.0000074593613,0.003501165],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99903286,0.000049228493,0.00015663853,0.00035696596,0.00018282875,0.00022147977],"domain_scores_gemma":[0.9991937,0.00017898742,0.000048925704,0.00042463004,0.00006391437,0.00008979875],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010527369,0.00012362933,0.0001374124,0.000113677284,0.00014491673,0.00015850089,0.00057212886,0.000034942273,0.0004032548],"category_scores_gemma":[0.000052857857,0.000099062665,0.00009653104,0.00016546261,0.00004829213,0.000040530922,0.000045471013,0.00007334701,0.0001032101],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011200744,0.00029493147,0.000021135007,0.000034460143,0.0000380209,0.0000035653059,0.00042659242,0.000032516127,0.0025600241,0.05456191,0.12193586,0.8200798],"study_design_scores_gemma":[0.00075100345,0.00008424558,0.008894391,0.0000076202527,0.000013207958,0.00018837664,0.000085353335,0.931653,0.010240152,0.013127167,0.034543104,0.0004123354],"about_ca_topic_score_codex":0.000005342232,"about_ca_topic_score_gemma":0.0000024676667,"teacher_disagreement_score":0.93162054,"about_ca_system_score_codex":0.000014564106,"about_ca_system_score_gemma":0.000008826879,"threshold_uncertainty_score":0.4415357},"labels":[],"label_agreement":null},{"id":"W2105626703","doi":"10.1142/s0218001410008329","title":"PHONETIC SEGMENTATION OF EMOTIONAL SPEECH WITH HMM-BASED METHODS","year":2010,"lang":"en","type":"article","venue":"International Journal of Pattern Recognition and Artificial Intelligence","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"European Commission; McMaster University","keywords":"Segmentation; Computer science; Hidden Markov model; Speech segmentation; Speech recognition; Artificial intelligence; Process (computing); Pattern recognition (psychology)","score_opus":0.07410581644215461,"score_gpt":0.3492316905540887,"score_spread":0.2751258741119341,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105626703","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26720214,0.000008505041,0.7307821,0.0009076898,0.0008570915,0.00006194528,0.000014552546,0.000012227422,0.0001537416],"genre_scores_gemma":[0.6792536,0.000021467371,0.32021344,0.00032794697,0.00016053648,0.0000029299226,0.000007942184,0.00000623748,0.0000059106455],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984159,0.000121541816,0.00062456884,0.00018275336,0.00054090814,0.000114364826],"domain_scores_gemma":[0.99776727,0.00034104788,0.00054458337,0.00010822724,0.0011384852,0.000100385536],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068113,0.000123157,0.00017548125,0.0003837213,0.000045337103,0.00014666615,0.00043261942,0.000061385785,0.0006939138],"category_scores_gemma":[0.00017712553,0.00010251623,0.00009328687,0.00017522207,0.00012340605,0.00041544795,0.00003733561,0.00024011095,0.000033469594],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051394192,0.00016529797,0.0003847508,0.000007516858,0.00004563217,0.000032305223,0.00019181277,0.000013451248,0.042289156,0.00035379897,0.00000967123,0.95645523],"study_design_scores_gemma":[0.00020999658,0.00026412104,0.0016837337,0.00017387618,0.000024763085,0.0005648436,0.00027899747,0.02067946,0.95355606,0.022287948,0.00009021414,0.00018596838],"about_ca_topic_score_codex":0.000019686338,"about_ca_topic_score_gemma":0.000038899852,"teacher_disagreement_score":0.95626926,"about_ca_system_score_codex":0.00001868497,"about_ca_system_score_gemma":0.0000903596,"threshold_uncertainty_score":0.7597869},"labels":[],"label_agreement":null},{"id":"W2106901945","doi":"10.1109/slt.2012.6424216","title":"Topic n-gram count language model adaptation for speech recognition","year":2012,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"n-gram; Gram; Latent Dirichlet allocation; Topic model; Cluster analysis; Word (group theory); Set (abstract data type); Computer science; Artificial intelligence; Test set; Adaptation (eye); Natural language processing; Language model; Speech recognition; Mathematics; Statistics","score_opus":0.07775270899817129,"score_gpt":0.2867773065104716,"score_spread":0.20902459751230035,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106901945","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030469725,0.000039019516,0.9536755,0.00037573784,0.00025081084,0.00022665122,0.0000082083325,0.00020305705,0.014751304],"genre_scores_gemma":[0.29888168,0.00000811373,0.6983525,0.0008459459,0.00012591135,0.00006143554,0.000020606081,0.000006517453,0.0016972829],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993271,0.000021047319,0.00013182125,0.00015096378,0.0001487326,0.0002203254],"domain_scores_gemma":[0.9995191,0.00009132633,0.000041081723,0.00018138277,0.00008771996,0.00007936633],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027427316,0.0000783835,0.00008170698,0.000068517395,0.000064745036,0.00006945803,0.00016153943,0.000052720086,0.00012945352],"category_scores_gemma":[0.000067876,0.000069549154,0.000059978163,0.00010135845,0.000008148116,0.0006781518,0.000024245184,0.000038035872,0.0002444825],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000033706935,0.00006127328,0.000019678137,0.000007969106,0.000005760064,4.4719698e-7,0.00068666,0.000007353341,0.00080286805,0.0064033037,0.0012980155,0.9907033],"study_design_scores_gemma":[0.00040095887,0.000041122992,0.00023380779,0.000012430568,0.000014070766,0.000018207918,0.0004655921,0.9291231,0.05544453,0.010865836,0.0031318234,0.00024852628],"about_ca_topic_score_codex":0.000022952257,"about_ca_topic_score_gemma":0.000021524434,"teacher_disagreement_score":0.9904548,"about_ca_system_score_codex":0.000032678847,"about_ca_system_score_gemma":0.000022318467,"threshold_uncertainty_score":0.31424096},"labels":[],"label_agreement":null},{"id":"W2107638917","doi":"10.1109/tasl.2006.881693","title":"Joint Factor Analysis Versus Eigenchannels in Speaker Recognition","year":2007,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":709,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Normalization (sociology); NIST; Speaker recognition; Speech recognition; Computer science; Speaker verification; Gaussian; Joint (building); Session (web analytics); Mixture model; Pattern recognition (psychology); Artificial intelligence; Engineering","score_opus":0.0407489263447483,"score_gpt":0.28112707873527615,"score_spread":0.24037815239052784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107638917","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18616126,0.0002132089,0.8111976,0.0001380639,0.00022083361,0.00011938602,0.000011912041,0.00015131231,0.0017864571],"genre_scores_gemma":[0.9591091,0.000052174397,0.040376995,0.00023822229,0.000046028807,0.000010091406,0.0000035912026,0.0000123500995,0.00015141806],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984975,0.000058633923,0.0003345964,0.00045731317,0.00028432845,0.00036764264],"domain_scores_gemma":[0.9993193,0.00013907632,0.00009763881,0.0002161528,0.00007269192,0.00015512506],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005038469,0.00019369864,0.0002577322,0.0009560433,0.00017411399,0.00018097149,0.00015948371,0.00011291264,0.0003050107],"category_scores_gemma":[0.000024685227,0.00018474975,0.00013431432,0.0015307058,0.000039349805,0.0004945417,0.000002714139,0.00025440817,0.00006132271],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052365398,0.00010258928,0.000017978695,0.000018508981,0.000060314655,0.00009585273,0.0019164756,0.000025874042,0.0026644352,0.0000019574743,0.000002572658,0.9950411],"study_design_scores_gemma":[0.0025476345,0.0002492324,0.004024476,0.00022581354,0.00030420945,0.00010149541,0.0038941838,0.042509682,0.9446577,0.00028422684,0.00013314253,0.0010682245],"about_ca_topic_score_codex":0.00010248891,"about_ca_topic_score_gemma":0.0010423285,"teacher_disagreement_score":0.99397284,"about_ca_system_score_codex":0.000083874256,"about_ca_system_score_gemma":0.000039855684,"threshold_uncertainty_score":0.7533876},"labels":[],"label_agreement":null},{"id":"W2107687614","doi":"10.1109/icassp.2013.6639210","title":"Phonetic subspace adaptation for automatic speech recognition","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Subspace topology; Computer science; Projection (relational algebra); Adaptation (eye); Speech recognition; Artificial intelligence; Random subspace method; Pattern recognition (psychology); Vocabulary; Linear subspace; Algorithm; Mathematics","score_opus":0.044783962692685975,"score_gpt":0.24030223560061933,"score_spread":0.19551827290793336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107687614","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05850503,0.000013479215,0.92719877,0.0023098735,0.0002733326,0.0006961883,0.0000019442846,0.00048349338,0.010517907],"genre_scores_gemma":[0.12577471,0.000007091407,0.87170184,0.00067365647,0.000044737953,0.00025983708,0.000009769566,0.000009213139,0.0015191274],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99918413,0.000039372535,0.00018109386,0.00023725806,0.00016213395,0.00019600663],"domain_scores_gemma":[0.9991981,0.00024181303,0.00006328483,0.00022364486,0.00019444436,0.000078749414],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00016530917,0.00009590957,0.00010510448,0.000109540764,0.00007950474,0.00021289397,0.00023096355,0.000050896404,0.0014359092],"category_scores_gemma":[0.00013006583,0.00008472782,0.00006571406,0.00021354447,0.000014202397,0.00067669706,0.000025389862,0.000036703022,0.0031828578],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.374805e-7,0.000029445304,0.000005664149,0.000011324988,0.000005704785,5.172892e-7,0.00012721786,5.0906914e-7,0.0008258766,0.00041612887,0.005381295,0.99319565],"study_design_scores_gemma":[0.0004438235,0.000088243636,0.0014892779,0.000027790737,0.000010184753,0.000027529448,0.0002787904,0.9038294,0.049844667,0.042655293,0.0010515542,0.00025344035],"about_ca_topic_score_codex":0.00007916287,"about_ca_topic_score_gemma":0.000027897211,"teacher_disagreement_score":0.9929422,"about_ca_system_score_codex":0.000025406116,"about_ca_system_score_gemma":0.000027410088,"threshold_uncertainty_score":0.9994769},"labels":[],"label_agreement":null},{"id":"W2109302000","doi":"10.1109/vecims.2005.1567572","title":"Accent adaptation in speech user interface","year":2006,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Defense Advanced Research Projects Agency","keywords":"Speech recognition; Computer science; Stress (linguistics); Utterance; Word error rate; Hidden Markov model; TIMIT; Adaptation (eye); Artificial intelligence; Natural language processing","score_opus":0.02355940262558318,"score_gpt":0.24947106186015072,"score_spread":0.22591165923456755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109302000","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.094909646,0.000015747411,0.81237274,0.0010255462,0.00015930914,0.00008720908,3.9682004e-7,0.00013525422,0.09129413],"genre_scores_gemma":[0.8140114,0.00000333152,0.18172976,0.0002433558,0.000022984352,0.000004558074,9.549519e-7,0.0000031378793,0.003980543],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99944824,0.000026809268,0.00013122821,0.00015910598,0.00012010205,0.000114525654],"domain_scores_gemma":[0.9997408,0.00003980385,0.000021827867,0.00014942324,0.00002789659,0.000020278478],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000110691304,0.000052718813,0.00005723987,0.00009504962,0.000016008626,0.00008488235,0.00022652105,0.000026270043,0.00029231017],"category_scores_gemma":[0.000013867422,0.000046128855,0.000021948434,0.0002151028,0.000006700572,0.00029621818,0.000047819693,0.000040407645,0.00039621672],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000060035954,0.0002145205,0.0025509736,0.000003880137,0.0000038145972,0.00003235208,0.00020303046,0.0002466548,0.0019878973,0.060194965,0.007466712,0.9270892],"study_design_scores_gemma":[0.0011659401,0.00006778988,0.09879469,0.000053628286,0.0000041613216,0.00005147434,0.0002814665,0.41254392,0.4116428,0.021309301,0.053464126,0.00062072655],"about_ca_topic_score_codex":0.0004305158,"about_ca_topic_score_gemma":0.0007584176,"teacher_disagreement_score":0.9264685,"about_ca_system_score_codex":0.00003264872,"about_ca_system_score_gemma":0.000013747992,"threshold_uncertainty_score":0.50926965},"labels":[],"label_agreement":null},{"id":"W2109740207","doi":"10.1109/isccsp.2008.4537397","title":"A playback attack detector for speaker verification systems","year":2008,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Detector; Similarity (geometry); Frame (networking); Set (abstract data type); Speech recognition; Cosine similarity; Feature (linguistics); Speaker verification; Utterance; Fast Fourier transform; Artificial intelligence; Pattern recognition (psychology); Speaker recognition; Algorithm; Telecommunications","score_opus":0.09712723700519299,"score_gpt":0.26977739776514476,"score_spread":0.17265016075995177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109740207","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.066866405,0.00003741252,0.92109233,0.00029712883,0.0004531111,0.00033848878,0.000004100942,0.0002516417,0.010659399],"genre_scores_gemma":[0.8614304,0.00001801573,0.13284342,0.00031120132,0.00010429525,0.00011082316,0.0000037088014,0.000009796356,0.005168353],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99932677,0.000023200046,0.0001547773,0.00022133697,0.00013141148,0.00014249963],"domain_scores_gemma":[0.9993929,0.00011225945,0.000042926393,0.00030003942,0.00009065124,0.00006119519],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011658906,0.000070234106,0.00009420211,0.000051763727,0.00010462242,0.00006641365,0.00026692566,0.000041230633,0.0000716156],"category_scores_gemma":[0.000041354797,0.000059057846,0.00005746123,0.00013102559,0.000017057828,0.00021114567,0.000020088632,0.000025736606,0.0006335099],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001308957,0.00076315715,0.004990511,0.00026844584,0.00024645284,0.000067691406,0.0027492384,0.00017204836,0.028288066,0.110330135,0.41163766,0.44035572],"study_design_scores_gemma":[0.001535725,0.0002267613,0.014826937,0.000041487307,0.000016675647,0.0005017325,0.00014888297,0.5567641,0.06005944,0.00034761778,0.3647257,0.00080492836],"about_ca_topic_score_codex":0.0000125511315,"about_ca_topic_score_gemma":0.000004074271,"teacher_disagreement_score":0.794564,"about_ca_system_score_codex":0.000023677609,"about_ca_system_score_gemma":0.000029353285,"threshold_uncertainty_score":0.81426996},"labels":[],"label_agreement":null},{"id":"W2109848220","doi":"10.1109/icassp.2011.5947460","title":"Adapting acoustic and lexical models to dysarthric speech","year":2011,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":80,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Dysarthria; Pronunciation; Speech recognition; Computer science; Vocabulary; Word error rate; Speech production; Lexicon; Artificial intelligence; Audiology; Linguistics","score_opus":0.1228450209147413,"score_gpt":0.24206564249048945,"score_spread":0.11922062157574816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109848220","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034389604,0.000015170561,0.86062956,0.00020869127,0.0000740595,0.00007320805,3.6311948e-7,0.00016580668,0.10444354],"genre_scores_gemma":[0.60971576,0.000004169088,0.3890194,0.0006925795,0.000016152937,0.0000029799085,6.318114e-8,0.000003515185,0.0005453652],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999303,0.000022208267,0.00011440235,0.0002480086,0.0001308777,0.00018154338],"domain_scores_gemma":[0.999533,0.000056664092,0.000015867297,0.00019899178,0.000037953025,0.0001575074],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015538307,0.00007661833,0.000091585505,0.000083169834,0.00005234051,0.00006306375,0.00023560466,0.000034985816,0.00022108015],"category_scores_gemma":[0.000029386794,0.00006371195,0.000023555382,0.00017085188,0.000015373325,0.00028124938,0.00014627946,0.000049802256,0.00028048267],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000068359577,0.000064828186,0.0000821891,0.0000053994913,0.000009497552,0.000046680343,0.001230783,0.000017668923,0.0012075967,0.054292656,0.00085090694,0.942185],"study_design_scores_gemma":[0.00038755164,0.00023866938,0.0021712186,0.000043667074,0.000013591127,0.0002454918,0.0004144562,0.8977665,0.029906038,0.06747542,0.0007447672,0.0005926314],"about_ca_topic_score_codex":0.00004880402,"about_ca_topic_score_gemma":0.00003197807,"teacher_disagreement_score":0.94159234,"about_ca_system_score_codex":0.0000075209955,"about_ca_system_score_gemma":0.000014444264,"threshold_uncertainty_score":0.36051306},"labels":[],"label_agreement":null},{"id":"W2109886035","doi":"10.1109/icassp.2016.7472618","title":"End-to-end attention-based large vocabulary speech recognition","year":2016,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":124,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Compute Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Canadian Institute for Advanced Research","keywords":"Computer science; Hidden Markov model; Recurrent neural network; Speech recognition; Decoding methods; Vocabulary; Sequence (biology); Pooling; Artificial intelligence; Character (mathematics); Language model; Process (computing); Pattern recognition (psychology); Artificial neural network; Algorithm","score_opus":0.035201277585039846,"score_gpt":0.26630435358302523,"score_spread":0.23110307599798538,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109886035","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008313604,0.00003578897,0.9217717,0.007686906,0.0021128356,0.0007185619,0.00027749248,0.0009256444,0.058157444],"genre_scores_gemma":[0.23830824,0.00006209214,0.73772216,0.011702805,0.0010510099,0.0005285342,0.00058622786,0.00011504056,0.00992391],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9964646,0.000255365,0.000575304,0.0013159383,0.0007738587,0.00061491266],"domain_scores_gemma":[0.99726313,0.00033710292,0.00023629382,0.0013938535,0.0004136615,0.0003559413],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00094004726,0.00045651427,0.0004547439,0.00064569886,0.00017304861,0.00044829719,0.001403332,0.0004356206,0.0067740786],"category_scores_gemma":[0.00021004524,0.0003816348,0.00042873595,0.00033861693,0.00003928691,0.00031622723,0.001011658,0.0004167266,0.008813525],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001619125,0.00027003564,0.00034349886,0.000079659905,0.00007819768,0.000105753636,0.000036145062,0.0000011841499,0.0010064116,0.0012740759,0.0140276775,0.98276114],"study_design_scores_gemma":[0.0072129723,0.0006484445,0.025271809,0.005724936,0.00044985683,0.0002870476,0.00018017269,0.070308045,0.4177328,0.27452856,0.18760903,0.010046305],"about_ca_topic_score_codex":0.00004832787,"about_ca_topic_score_gemma":0.00006294052,"teacher_disagreement_score":0.97271484,"about_ca_system_score_codex":0.00015855127,"about_ca_system_score_gemma":0.00031992298,"threshold_uncertainty_score":0.99986356},"labels":[],"label_agreement":null},{"id":"W2112021726","doi":"10.1109/taslp.2014.2346313","title":"Fast Adaptation of Deep Neural Network Based on Discriminant Codes for Speech Recognition","year":2014,"lang":"en","type":"article","venue":"IEEE/ACM Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":139,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"University of Science and Technology of China","keywords":"Computer science; Speech recognition; TIMIT; Normalization (sociology); Adaptation (eye); Artificial neural network; Artificial intelligence; Speaker recognition; Pattern recognition (psychology); Word error rate; Hidden Markov model","score_opus":0.02681299895984912,"score_gpt":0.26100173092852763,"score_spread":0.2341887319686785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112021726","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035789173,0.00010636262,0.962364,0.000552687,0.0002579727,0.00032265842,0.000027549178,0.00015772691,0.0004218609],"genre_scores_gemma":[0.67809975,0.000010421873,0.32116577,0.0004896244,0.00010217043,0.000049789447,0.00001611384,0.000019628786,0.000046750443],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984644,0.00011226765,0.00033677093,0.00045809156,0.00029733384,0.00033115296],"domain_scores_gemma":[0.9987566,0.0004220583,0.000194131,0.00035005345,0.00015984764,0.000117338524],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042636905,0.00023072421,0.00028528064,0.00023250868,0.00035680342,0.0001627947,0.00028632962,0.00010700052,0.000043547818],"category_scores_gemma":[0.00010765681,0.00020625904,0.00012634865,0.0003675963,0.00006549773,0.00037404525,0.000004541018,0.0001745881,0.00000980958],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000104207866,0.00013665353,0.000008567584,0.00012521473,0.000010693636,0.000005004461,0.00060265535,0.0030371828,0.0015313909,0.000009951091,0.000012535388,0.99441594],"study_design_scores_gemma":[0.00092480105,0.00044415842,0.00016059056,0.00028706115,0.000066267254,0.000033465978,0.0006661433,0.88078713,0.1152522,0.0009689324,0.00009304905,0.00031618364],"about_ca_topic_score_codex":0.00003752575,"about_ca_topic_score_gemma":0.00019390958,"teacher_disagreement_score":0.99409974,"about_ca_system_score_codex":0.00003252941,"about_ca_system_score_gemma":0.000037839447,"threshold_uncertainty_score":0.8411},"labels":[],"label_agreement":null},{"id":"W2112582577","doi":"10.1109/tasl.2007.894527","title":"Speaker and Session Variability in GMM-Based Speaker Verification","year":2007,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":227,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"NIST; Computer science; Speaker recognition; Speech recognition; Session (web analytics); Set (abstract data type); Statistic; Pattern recognition (psychology); Artificial intelligence; Speaker diarisation; Factor (programming language); Feature (linguistics); Statistics; Mathematics; Linguistics","score_opus":0.012953082206222183,"score_gpt":0.2605477096187157,"score_spread":0.24759462741249352,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112582577","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18192267,0.00012491253,0.8160593,0.0003891807,0.00010050781,0.00014406041,0.0000027842093,0.0001221778,0.0011344046],"genre_scores_gemma":[0.9241261,0.000019468402,0.075253546,0.00045593551,0.000022617221,0.000008462847,0.0000014522951,0.000010850841,0.000101584825],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99869066,0.00010733639,0.00026558127,0.00045595202,0.00021735764,0.0002631053],"domain_scores_gemma":[0.9992757,0.00022033851,0.00007445329,0.00024823874,0.000053111406,0.00012815058],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013153028,0.00016185497,0.0001653428,0.00026854884,0.00018325324,0.00015891023,0.00013222608,0.00010820421,0.00007621456],"category_scores_gemma":[0.000040186133,0.0001476082,0.000036707825,0.0004684351,0.00006659441,0.00041183527,0.0000024887331,0.00023030431,0.000012807935],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036473262,0.00013872149,0.0002293225,0.000052044983,0.0000034475013,0.0000303324,0.0008241988,0.000014352992,0.009569786,0.000014056833,0.000004907499,0.98908234],"study_design_scores_gemma":[0.002332906,0.00014413876,0.025291488,0.0005402766,0.000046764868,0.00021599619,0.0013829583,0.14089848,0.82697713,0.0006315889,0.00062103523,0.0009172293],"about_ca_topic_score_codex":0.000054199492,"about_ca_topic_score_gemma":0.00018137875,"teacher_disagreement_score":0.98816514,"about_ca_system_score_codex":0.00006003976,"about_ca_system_score_gemma":0.000059922986,"threshold_uncertainty_score":0.6019288},"labels":[],"label_agreement":null},{"id":"W2113395503","doi":"10.1109/tasl.2008.2001105","title":"Transforming Perceived Vocal Effort and Breathiness Using Adaptive Pre-Emphasis Linear Prediction","year":2008,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"University of Victoria","keywords":"Emphasis (telecommunications); Formant; Vocal tract; Spectral envelope; Speech recognition; Filter (signal processing); Active listening; Computer science; Breathy voice; Envelope (radar); Linear prediction; Acoustics; Phonation; Vowel; Psychology; Audiology; Telecommunications; Radar; Communication","score_opus":0.024238213379658247,"score_gpt":0.2607480318921048,"score_spread":0.23650981851244657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2113395503","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41213995,0.00027373384,0.58691615,0.000061465806,0.00008478349,0.00015440397,0.000012345016,0.0001812147,0.00017597542],"genre_scores_gemma":[0.9157196,0.00019589096,0.08362484,0.00017700916,0.00007069955,0.000019158404,0.0000016344911,0.000021964464,0.00016918959],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99858236,0.000052518484,0.00027196106,0.0004944951,0.00029648875,0.00030216452],"domain_scores_gemma":[0.9994189,0.00006692945,0.000072510826,0.00017534028,0.000088576286,0.00017771896],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020333599,0.0002478332,0.0002597341,0.0002528838,0.0007749027,0.00011419095,0.00014776718,0.00013835597,0.000032239746],"category_scores_gemma":[0.000008010382,0.00022704357,0.00008131248,0.0003644347,0.00013613729,0.0009213349,0.0000031966342,0.00026435044,0.0000042552997],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007631772,0.000118801945,0.00006656629,0.00006486325,0.000036648144,0.00011914658,0.009190902,0.0001702845,0.013624797,0.00000324606,0.0000032015726,0.97652525],"study_design_scores_gemma":[0.0018488573,0.00032723826,0.0027729198,0.00051240297,0.00015466294,0.005085149,0.001955465,0.755714,0.23074397,0.000058984,0.000087066765,0.00073929125],"about_ca_topic_score_codex":0.00011324646,"about_ca_topic_score_gemma":0.000037066224,"teacher_disagreement_score":0.9757859,"about_ca_system_score_codex":0.000056870384,"about_ca_system_score_gemma":0.00009724547,"threshold_uncertainty_score":0.92585677},"labels":[],"label_agreement":null},{"id":"W2114948162","doi":"10.1109/icassp.1996.540277","title":"HMM-based speech recognition using state-dependent, linear transforms on Mel-warped DFT features","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"TIMIT; Hidden Markov model; Computer science; Speech recognition; Word error rate; Pattern recognition (psychology); Mel-frequency cepstrum; Transformation (genetics); Feature extraction; Artificial intelligence; Feature (linguistics)","score_opus":0.0734056754320572,"score_gpt":0.2641613885171936,"score_spread":0.19075571308513642,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2114948162","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18746328,0.000059049387,0.7414941,0.0027127091,0.00087868597,0.0007803859,0.00006149427,0.0013676533,0.06518262],"genre_scores_gemma":[0.45530382,0.00009463482,0.534886,0.0054795193,0.0002194774,0.000029470262,0.0000314275,0.00006427692,0.0038913656],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9980746,0.00010538007,0.0003169838,0.00053004286,0.0005615733,0.00041140066],"domain_scores_gemma":[0.99900913,0.00017360355,0.00008534415,0.00042051912,0.00013395063,0.00017746186],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0002953275,0.00025372795,0.00023248783,0.0003125738,0.00019341845,0.000218522,0.00044969868,0.0001283291,0.002331793],"category_scores_gemma":[0.00006415854,0.0002070134,0.00016388073,0.00043257678,0.00003684878,0.00053348404,0.00002544755,0.00023680141,0.0011812571],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030219238,0.00029654443,0.000021477053,0.000016640706,0.000025852256,0.00008120115,0.00019172473,0.000106627325,0.0022187934,0.00007435261,0.0012197056,0.99571687],"study_design_scores_gemma":[0.0015741233,0.0002545177,0.00014992495,0.000090709706,0.00002548507,0.000088877125,0.00007059239,0.34327063,0.64984953,0.0019384731,0.002019997,0.00066711043],"about_ca_topic_score_codex":0.00010044053,"about_ca_topic_score_gemma":0.00010638744,"teacher_disagreement_score":0.9950498,"about_ca_system_score_codex":0.000076851175,"about_ca_system_score_gemma":0.00003278734,"threshold_uncertainty_score":0.9995964},"labels":[],"label_agreement":null},{"id":"W2115230584","doi":"","title":"A Critical Reassessment of Evaluation Baselines for Speech Summarization","year":2008,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":73,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Automatic summarization; Computer science; Speech recognition; Speech analytics; Voice activity detection; Natural language processing; Speech processing; Surprise; Speech synthesis; Artificial intelligence; Information retrieval","score_opus":0.08207451475019102,"score_gpt":0.35184597856050354,"score_spread":0.26977146381031253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115230584","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007965853,0.000012805683,0.98303527,0.0012196358,0.000147901,0.00023761297,0.0000032458343,0.000053903383,0.007323767],"genre_scores_gemma":[0.50658256,0.000009865508,0.49296546,0.00018472008,0.00003567849,0.000040421393,0.000008471302,0.0000028326292,0.00016996922],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992029,0.000059842605,0.00018247475,0.00015634763,0.00031149155,0.000086951884],"domain_scores_gemma":[0.998723,0.00035418273,0.000034055007,0.000169721,0.0006829477,0.000036099707],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005172376,0.00004927257,0.000083886946,0.00007452764,0.00005916994,0.000018460278,0.00011002728,0.00003066899,0.0002002511],"category_scores_gemma":[0.0008923948,0.000042709144,0.00004700626,0.0001556345,0.000025491743,0.00024516956,0.00002202798,0.000016234699,0.0000111836525],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011617212,0.00023656787,0.0006699987,0.00002808866,0.00001165114,0.000003032034,0.00009565261,0.000006299569,0.002221724,0.08293061,0.0049215765,0.9088632],"study_design_scores_gemma":[0.00062616554,0.00012903287,0.009475394,0.000024054829,0.000026048428,0.000056191395,0.000041080104,0.8575863,0.11039328,0.019878447,0.0015938642,0.00017012612],"about_ca_topic_score_codex":0.000011714456,"about_ca_topic_score_gemma":0.0000056352005,"teacher_disagreement_score":0.9086931,"about_ca_system_score_codex":0.000019400566,"about_ca_system_score_gemma":0.00010256359,"threshold_uncertainty_score":0.21926092},"labels":[],"label_agreement":null},{"id":"W2115328154","doi":"10.1109/icassp.2004.1325916","title":"Disentangling speaker and channel effects in speaker verification","year":2004,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":67,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Speaker recognition; Speaker diarisation; NIST; Computer science; Speaker verification; Speech recognition; Variation (astronomy); Task (project management); Channel (broadcasting); Factor (programming language); Construct (python library); Joint (building); Artificial intelligence; Telecommunications; Engineering","score_opus":0.011520597261380609,"score_gpt":0.21973349414653406,"score_spread":0.20821289688515346,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115328154","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5474977,0.000104752755,0.4346426,0.0022240155,0.00031178482,0.00025539674,3.8471458e-7,0.00017843157,0.014784912],"genre_scores_gemma":[0.9658953,0.000021244852,0.033527076,0.00042057555,0.000022998955,0.000009104547,8.4578625e-7,0.00000405893,0.00009882227],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9994563,0.000019928639,0.00009545634,0.00020966714,0.00009522189,0.00012346488],"domain_scores_gemma":[0.99971604,0.000045823395,0.000019641318,0.00015549449,0.000010326988,0.000052667125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010877287,0.00006521307,0.00007315282,0.00008545097,0.000031472817,0.00007033983,0.000113559065,0.000028431497,0.000011765744],"category_scores_gemma":[0.000036357127,0.000056942783,0.000018274708,0.00018389599,0.000015330981,0.00024935848,0.00003719224,0.000041979147,0.000102470345],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002399811,0.0005502065,0.0162093,0.00009119749,0.000030675532,0.00022833867,0.004423535,0.000109064305,0.0057313037,0.17501393,0.00025459807,0.79733384],"study_design_scores_gemma":[0.006305002,0.00021754148,0.48316184,0.0004571094,0.00002409951,0.00022294505,0.00064930075,0.13289416,0.22146414,0.15044454,0.0026844009,0.0014749337],"about_ca_topic_score_codex":0.000029512952,"about_ca_topic_score_gemma":0.00005472009,"teacher_disagreement_score":0.7958589,"about_ca_system_score_codex":0.00002944495,"about_ca_system_score_gemma":0.000011249667,"threshold_uncertainty_score":0.23220594},"labels":[],"label_agreement":null},{"id":"W2115599677","doi":"10.1109/jstsp.2010.2081790","title":"Diarization of Telephone Conversations Using Factor Analysis","year":2010,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Signal Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":141,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"Johns Hopkins University","keywords":"Speaker diarisation; Computer science; Cluster analysis; Speech recognition; Word error rate; Speaker recognition; NIST; Channel (broadcasting); Hierarchical clustering; Bayes' theorem; Exploit; Artificial intelligence; Pattern recognition (psychology); Telecommunications; Bayesian probability","score_opus":0.025827002893712158,"score_gpt":0.2748875302374324,"score_spread":0.24906052734372025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115599677","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49863514,0.000021113297,0.50107664,0.00008187309,0.00009780111,0.000023853327,8.003159e-7,0.000007547234,0.000055233697],"genre_scores_gemma":[0.90237796,0.0000062449312,0.09744916,0.000032707612,0.000118890384,3.3020856e-7,4.9529507e-7,0.000004152143,0.000010038923],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99885213,0.000060004026,0.0005295904,0.00011353098,0.0003150819,0.00012966809],"domain_scores_gemma":[0.99831706,0.0001045184,0.00055895245,0.00009086099,0.0008702298,0.000058346548],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002670704,0.00008259673,0.00025246022,0.0007486649,0.000063340914,0.000087684406,0.00030207538,0.00008730608,0.00006096669],"category_scores_gemma":[0.0001447933,0.000075740354,0.000082387254,0.0023881788,0.000038514063,0.00060099503,0.000013820204,0.00031689624,5.574376e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016782926,0.0002073649,0.029188635,0.00004174437,0.0001743309,0.00002110495,0.0016587963,0.0016084318,0.78911334,0.00016784991,0.0000083391715,0.17779328],"study_design_scores_gemma":[0.0005358754,0.000068190006,0.032196123,0.000093948656,0.00016731072,0.000075148746,0.000080255195,0.4514744,0.513439,0.0016181234,0.000044800116,0.00020686198],"about_ca_topic_score_codex":0.000012949213,"about_ca_topic_score_gemma":0.000031855147,"teacher_disagreement_score":0.44986597,"about_ca_system_score_codex":0.00003949958,"about_ca_system_score_gemma":0.0003165596,"threshold_uncertainty_score":0.30886018},"labels":[],"label_agreement":null},{"id":"W2115695999","doi":"10.1080/02699200500113590","title":"Techniques for field application of lingual ultrasound imaging","year":2005,"lang":"en","type":"article","venue":"Clinical Linguistics & Phonetics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria; University of British Columbia","funders":"National Institute on Deafness and Other Communication Disorders; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Tongue; Transducer; Ultrasound; Field (mathematics); Head (geology); Computer science; Ultrasound imaging; Acoustics; Presentation (obstetrics); Computer vision; Radiology; Medicine; Mathematics; Physics; Geology; Pathology","score_opus":0.028728005045375735,"score_gpt":0.36518292966211335,"score_spread":0.3364549246167376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115695999","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009827033,0.00009703806,0.99193853,0.00032247067,0.0006541398,0.0002551305,0.000013428663,0.00016745807,0.005569103],"genre_scores_gemma":[0.4074753,0.00006890667,0.5901057,0.00095989706,0.0012871,0.000017144805,0.0000061161695,0.000010497547,0.000069356436],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.998519,0.000052754956,0.00074479106,0.00031996175,0.00016902878,0.00019447134],"domain_scores_gemma":[0.99401176,0.004506013,0.00025086853,0.000493856,0.00063700153,0.000100479636],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0009148674,0.00011688072,0.00024418664,0.00006375895,0.00006464245,0.00004983607,0.00054179033,0.000121146055,0.000012329272],"category_scores_gemma":[0.017056761,0.000118997785,0.00015695152,0.00013653666,0.00008944881,0.000023708204,0.00008126473,0.00016714186,0.000023106877],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017708802,0.00022338147,0.0011530848,0.00001984514,0.000014340464,9.636971e-7,0.00008367695,0.0000026520333,0.0004900084,0.027069895,0.002221406,0.96870303],"study_design_scores_gemma":[0.00056517904,0.00033168454,0.0006897553,0.000067965564,0.00008146593,0.000009136427,0.000032866938,0.061385244,0.27573395,0.071232855,0.5894147,0.0004551426],"about_ca_topic_score_codex":0.000005057191,"about_ca_topic_score_gemma":0.000004648098,"teacher_disagreement_score":0.9682479,"about_ca_system_score_codex":0.000015108157,"about_ca_system_score_gemma":0.00006460099,"threshold_uncertainty_score":0.991223},"labels":[],"label_agreement":null},{"id":"W2115900223","doi":"10.1109/icassp.1994.389284","title":"Correcting complex false starts in spontaneous speech","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Utterance; Computer science; Speech recognition; Word (group theory); Identification (biology); Artificial intelligence; Natural language processing; Linguistics","score_opus":0.0633903589158387,"score_gpt":0.244796490937937,"score_spread":0.18140613202209832,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115900223","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5353319,0.00006337052,0.055324465,0.0021401236,0.0007015369,0.0002910422,0.0000021438627,0.00068914145,0.40545624],"genre_scores_gemma":[0.9225804,0.000006360645,0.07336184,0.0010154791,0.000029811983,0.000003855853,5.9371973e-7,0.0000059035647,0.0029957253],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99904585,0.000057639485,0.00019538034,0.0002630879,0.00018999117,0.0002480438],"domain_scores_gemma":[0.9993963,0.00019351182,0.000034712415,0.00026707357,0.000033735854,0.00007464439],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000180272,0.00009495387,0.00013280254,0.0001439814,0.00005791287,0.00011169147,0.0003504185,0.000037287078,0.0037340713],"category_scores_gemma":[0.0000907307,0.00008836301,0.00004117216,0.0003251162,0.000015468397,0.00018911703,0.000076873774,0.00009161795,0.0012023407],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001778407,0.00009157856,0.0005001918,0.0000026244284,0.0000029861503,0.0015219863,0.000331431,0.000003680646,0.00037982222,0.0009008377,0.003325714,0.9929374],"study_design_scores_gemma":[0.0016971573,0.00023599881,0.011808368,0.000101998565,0.000008529253,0.022886582,0.000971356,0.8761793,0.031824637,0.005147927,0.0476761,0.00146207],"about_ca_topic_score_codex":0.00010763283,"about_ca_topic_score_gemma":0.0005101532,"teacher_disagreement_score":0.9914753,"about_ca_system_score_codex":0.000043051987,"about_ca_system_score_gemma":0.0000062178706,"threshold_uncertainty_score":0.9995753},"labels":[],"label_agreement":null},{"id":"W2116168363","doi":"10.1109/ivtta.1998.727683","title":"Automation of locality recognition in ADAS Plus","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Nortel (Canada)","funders":"","keywords":"Directory; Phone; Computer science; Automation; Listing (finance); Service (business); Product (mathematics); Advanced driver assistance systems; Speech recognition; Database; World Wide Web; Operating system; Artificial intelligence; Engineering; Business","score_opus":0.06646115400023518,"score_gpt":0.24317356398463297,"score_spread":0.1767124099843978,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2116168363","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12755524,0.000027767739,0.7290358,0.0010979477,0.00015086954,0.00016171436,0.0000024688838,0.00020255378,0.14176567],"genre_scores_gemma":[0.92689246,0.000013331031,0.07252369,0.0002194631,0.000009336598,0.000006844895,0.0000014820235,0.0000018173042,0.00033156655],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99940664,0.000055808985,0.00019011977,0.00012855504,0.00013532005,0.00008357417],"domain_scores_gemma":[0.9996587,0.00006770781,0.00004717547,0.0001509248,0.000048693382,0.000026776504],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00018610785,0.000044131622,0.000084727515,0.00011035749,0.000014073657,0.000019678964,0.00014201931,0.000036777237,0.0013882554],"category_scores_gemma":[0.00006470641,0.000040850708,0.000028761122,0.0002911448,0.0000144692685,0.00028805557,0.000024430294,0.00003529563,0.00045998298],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001444511,0.000079979385,0.00018429,0.000010356446,0.0000023502967,0.0000032325386,0.00021646434,0.000005739931,0.00022269812,0.0017279276,0.000896085,0.99664944],"study_design_scores_gemma":[0.00053131516,0.000040249142,0.010419757,0.00004450194,0.00000251988,0.000012523526,0.000070310714,0.9400142,0.038725637,0.009487855,0.0004965281,0.00015463139],"about_ca_topic_score_codex":0.00005133955,"about_ca_topic_score_gemma":0.000042144555,"teacher_disagreement_score":0.9964948,"about_ca_system_score_codex":0.00003322938,"about_ca_system_score_gemma":0.0000067345286,"threshold_uncertainty_score":0.9995246},"labels":[],"label_agreement":null},{"id":"W2116375618","doi":"10.1109/chinsl.2004.1409573","title":"A comparative study on various confidence measures in large vocabulary speech recognition","year":2005,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Dictation; Vocabulary; Word error rate; Computer science; Speech recognition; Mandarin Chinese; Word (group theory); Task (project management); Artificial intelligence; A priori and a posteriori; Language model; Interpolation (computer graphics); Natural language processing; Pattern recognition (psychology); Mathematics","score_opus":0.0777816752275478,"score_gpt":0.3098407658864848,"score_spread":0.23205909065893698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2116375618","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80853146,0.000049520262,0.11822208,0.0014410382,0.00022395643,0.0010283688,0.000007488113,0.00039631588,0.0700998],"genre_scores_gemma":[0.9742985,0.000006947922,0.023994502,0.0012877177,0.000048673246,0.000048850863,0.0000024853018,0.00000590093,0.0003064302],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99819916,0.00028152784,0.00030900846,0.00046852778,0.00045035745,0.00029144128],"domain_scores_gemma":[0.9991246,0.00023347275,0.00006692504,0.0003634473,0.00012356172,0.000088034736],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00075251004,0.00016726847,0.0002610317,0.0002681896,0.00008938513,0.00014113053,0.00044002754,0.000057413898,0.00035228263],"category_scores_gemma":[0.0000815324,0.0001477893,0.000051678777,0.0004402658,0.000020817779,0.00049998146,0.000076884025,0.00019674169,0.0018594933],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010404994,0.006342642,0.004672864,0.0000064825053,0.00008667127,0.00034652822,0.01188476,0.000026292519,0.0008878661,0.0044807796,0.0030276754,0.9681334],"study_design_scores_gemma":[0.016987637,0.004823235,0.37620795,0.0005503618,0.000102407685,0.00051266444,0.021975301,0.17388281,0.3602699,0.022711365,0.01765184,0.004324522],"about_ca_topic_score_codex":0.00008347347,"about_ca_topic_score_gemma":0.0015555777,"teacher_disagreement_score":0.9638089,"about_ca_system_score_codex":0.00007467242,"about_ca_system_score_gemma":0.000051161685,"threshold_uncertainty_score":0.9989177},"labels":[],"label_agreement":null},{"id":"W2117817230","doi":"10.1109/issse.2007.4294413","title":"A Processing Method for Pitch Smoothing Based on Autocorrelation and Cepstral F0 Detection Approaches","year":2007,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Speech recognition; Pitch detection algorithm; Smoothing; Computer science; Discriminative model; Cepstrum; Autocorrelation; Intonation (linguistics); Mel-frequency cepstrum; Tone (literature); Artificial intelligence; Pattern recognition (psychology); Feature extraction; Speech processing; Mathematics; Computer vision","score_opus":0.06618200486706205,"score_gpt":0.2972780613994062,"score_spread":0.23109605653234416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2117817230","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028878357,0.0000045702345,0.99114794,0.00038312454,0.00007751385,0.00029628281,2.757905e-7,0.0001939162,0.0050085434],"genre_scores_gemma":[0.44516662,9.04914e-8,0.5545101,0.00019889935,0.000026303012,0.000020723666,5.9031544e-7,0.000004099873,0.000072576804],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992505,0.000035393172,0.00014632335,0.00026853886,0.00013528789,0.00016397683],"domain_scores_gemma":[0.9993956,0.00034697424,0.00005996521,0.0001029685,0.00003969709,0.00005476104],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010653262,0.00008406579,0.00008085617,0.00015323592,0.00017226544,0.00015807878,0.000090829475,0.00006957899,0.0000068451345],"category_scores_gemma":[0.00009607627,0.00007241487,0.000038230508,0.00018452045,0.000010702753,0.0003107377,0.000012788535,0.00007074504,0.0000027371777],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015614616,0.000023341012,0.00006365349,0.000016069418,0.0000017876456,4.3268182e-7,0.00017333063,0.0000762802,0.0008933639,0.0011965835,0.000005292741,0.9975343],"study_design_scores_gemma":[0.00025095508,0.0000642354,0.0026420425,0.000017018758,0.000005161796,0.000006221435,0.00008003254,0.9402481,0.054795664,0.0015529455,0.00023743568,0.00010021618],"about_ca_topic_score_codex":0.000010030452,"about_ca_topic_score_gemma":0.000019359975,"teacher_disagreement_score":0.997434,"about_ca_system_score_codex":0.000031081396,"about_ca_system_score_gemma":0.000022761484,"threshold_uncertainty_score":0.29529926},"labels":[],"label_agreement":null},{"id":"W2121415728","doi":"10.1109/tsa.2004.840940","title":"Eigenvoice modeling with sparse training data","year":2005,"lang":"en","type":"article","venue":"IEEE Transactions on Speech and Audio Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":472,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Speech recognition; Training set; Set (abstract data type); Adaptation (eye); Limit (mathematics); Training (meteorology); Maximum likelihood; Covariance matrix; Pattern recognition (psychology); Estimation theory; Artificial intelligence; Covariance; Speaker recognition; Algorithm; Mathematics; Statistics","score_opus":0.095794255220844,"score_gpt":0.2797844726229301,"score_spread":0.1839902174020861,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121415728","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017492907,0.00018972054,0.9787946,0.0013460086,0.000074152355,0.000100906036,0.000010164848,0.00025818223,0.0017334096],"genre_scores_gemma":[0.6683116,0.00008420311,0.33078218,0.0005898212,0.000070453134,0.000008308363,0.0000016205136,0.000014754653,0.00013704145],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99854887,0.00002995086,0.00021852333,0.0005894941,0.0002953285,0.00031781726],"domain_scores_gemma":[0.9991725,0.00005118871,0.00006399122,0.00048801026,0.00007161476,0.00015269272],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027267355,0.0001901879,0.00018799653,0.00016904477,0.00046530418,0.00035466283,0.00051251263,0.00006532085,0.000031959346],"category_scores_gemma":[0.0000055993773,0.0001617532,0.000030056452,0.0003566868,0.000048041868,0.0015509506,0.000005577777,0.00023922806,0.000038616985],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014846144,0.00006165026,0.0000010552537,0.000015373182,0.000015307585,0.000011781994,0.00065810827,0.0032551102,0.00045724414,0.000014673232,0.000011975427,0.99548286],"study_design_scores_gemma":[0.00046443217,0.000055920646,0.000004579971,0.00017382024,0.00003448621,0.00020314992,0.00031669726,0.9686379,0.028061546,0.0001262747,0.0016027045,0.0003185304],"about_ca_topic_score_codex":0.000010810015,"about_ca_topic_score_gemma":0.00008380025,"teacher_disagreement_score":0.99516433,"about_ca_system_score_codex":0.000026829186,"about_ca_system_score_gemma":0.00013308144,"threshold_uncertainty_score":0.6596104},"labels":[],"label_agreement":null},{"id":"W2123545720","doi":"10.1109/icassp.2009.4960580","title":"Unsupervised pronunciation validation","year":2009,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"IBM (Canada)","funders":"","keywords":"Computer science; Pronunciation; Vocabulary; Word error rate; Speech recognition; Lexicon; Artificial intelligence; Search engine indexing; Phone; Natural language processing; Word (group theory); Speech processing; Pattern recognition (psychology)","score_opus":0.018767538752516116,"score_gpt":0.233102594424234,"score_spread":0.2143350556717179,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2123545720","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020623613,0.0000061144096,0.8479519,0.004946063,0.00009105207,0.00010771128,1.863424e-7,0.00037387077,0.12589951],"genre_scores_gemma":[0.8484184,0.0000036348847,0.14892158,0.001680271,0.000034015007,0.0000036113552,0.000002691011,0.0000014243325,0.0009343591],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999569,0.000021933936,0.000080120095,0.000119696386,0.00013270594,0.000076532895],"domain_scores_gemma":[0.9997315,0.000017926732,0.000019114446,0.00014937136,0.00005149783,0.000030606745],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011569007,0.00003889614,0.000039364077,0.00005050077,0.000039634848,0.00008583011,0.00016114772,0.000022111917,0.00016704372],"category_scores_gemma":[0.000034943485,0.000032859112,0.000022790999,0.00016585285,0.000002347425,0.00037607635,0.000008320115,0.000020284027,0.00032981377],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.1931887e-7,0.000035757505,0.00006530892,5.894812e-7,0.0000013607587,9.3486653e-7,0.00007315159,0.0000016622673,0.0027567684,0.05523572,0.0010197803,0.9408081],"study_design_scores_gemma":[0.00086413044,0.0002451221,0.070404366,0.000018469325,0.000008965779,0.000023879116,0.00005371598,0.13893698,0.6573201,0.11647573,0.015116778,0.00053178833],"about_ca_topic_score_codex":0.0000018801534,"about_ca_topic_score_gemma":6.074671e-7,"teacher_disagreement_score":0.9402764,"about_ca_system_score_codex":0.000016168842,"about_ca_system_score_gemma":0.000014838092,"threshold_uncertainty_score":0.42391986},"labels":[],"label_agreement":null},{"id":"W2123781188","doi":"10.1109/icassp.1998.674432","title":"Specific language modelling for new-word detection in continuous-speech recognition","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Computer science; Keyword spotting; Vocabulary; Spotting; Word (group theory); Natural language processing; Speech recognition; Language model; Artificial intelligence; Transcription (linguistics); Process (computing); Linguistics","score_opus":0.06618264797328118,"score_gpt":0.24173339912606753,"score_spread":0.17555075115278634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2123781188","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045156397,0.0001015638,0.94083434,0.00036920764,0.00024743564,0.0002826213,0.000002176951,0.00022727964,0.01277898],"genre_scores_gemma":[0.43390107,0.00011062078,0.5616931,0.000322757,0.00023302519,0.000046971953,0.0000052310183,0.000017135977,0.0036701346],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990466,0.00003479383,0.0002278224,0.0003217567,0.00013683608,0.00023215172],"domain_scores_gemma":[0.9994699,0.00014148424,0.000051226958,0.00021021717,0.000055032004,0.00007219231],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002106052,0.00010662584,0.00013571125,0.0002163724,0.000058452697,0.00013214261,0.00020664195,0.00007637383,0.0005541529],"category_scores_gemma":[0.000033601213,0.0001056561,0.00007519222,0.00032612067,0.000008802447,0.00042213168,0.000022137694,0.00008629462,0.00041686816],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000059915214,0.00004008591,0.000005151565,0.000003086601,0.0000026308678,0.0000060538555,0.00029164244,0.000018136054,0.0020101091,0.00010338102,0.0010018442,0.9965119],"study_design_scores_gemma":[0.0008964508,0.00006301293,0.0000332947,0.00003074521,0.0000038185008,0.000034430595,0.00022759855,0.7399662,0.24386278,0.006160874,0.008424782,0.0002959771],"about_ca_topic_score_codex":0.00008343706,"about_ca_topic_score_gemma":0.00011854886,"teacher_disagreement_score":0.9962159,"about_ca_system_score_codex":0.000044731936,"about_ca_system_score_gemma":0.0000061335477,"threshold_uncertainty_score":0.60675853},"labels":[],"label_agreement":null},{"id":"W2123798005","doi":"10.1109/icassp.2010.5495646","title":"Multilingual acoustic modeling for speech recognition based on subspace Gaussian Mixture Models","year":2010,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":160,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Subspace topology; Computer science; Phone; Gaussian; Mixture model; Speech recognition; Set (abstract data type); Language model; Artificial intelligence; Acoustic model; Space (punctuation); Hidden Markov model; Natural language processing; Pattern recognition (psychology); Speech processing; Linguistics","score_opus":0.04797919133278814,"score_gpt":0.2764242881821557,"score_spread":0.22844509684936756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2123798005","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04771985,0.0000027749345,0.94124025,0.0011624441,0.0005957349,0.0005251132,0.000019486746,0.0003817787,0.0083525935],"genre_scores_gemma":[0.55573356,0.0000014088345,0.44294497,0.0008885824,0.000117239215,0.0000599417,0.000014850872,0.000015922482,0.00022354523],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985311,0.000037057478,0.00023317467,0.00054220227,0.00030352868,0.0003529551],"domain_scores_gemma":[0.9986911,0.00033469882,0.00006308531,0.0004938963,0.0002488419,0.00016839798],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004127781,0.00020804818,0.0001814518,0.00021070223,0.00018100374,0.0001941427,0.00044312736,0.00019644311,0.0001600793],"category_scores_gemma":[0.0002554482,0.00018004276,0.00014716851,0.00020833392,0.000021113714,0.0004200199,0.000034087596,0.00028048945,0.000102157705],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007507773,0.00028669255,0.0000045444417,0.000036297854,0.000015229962,0.000017020244,0.00018969615,0.01951184,0.02080236,0.0013076366,0.00060509,0.9571485],"study_design_scores_gemma":[0.0005239919,0.00005966036,0.000002340027,0.000026702108,0.000011779438,0.000011138752,0.000039787323,0.9110518,0.07773715,0.010174597,0.000108607695,0.00025244922],"about_ca_topic_score_codex":0.000022482662,"about_ca_topic_score_gemma":0.000189249,"teacher_disagreement_score":0.95689607,"about_ca_system_score_codex":0.000022919578,"about_ca_system_score_gemma":0.00009164342,"threshold_uncertainty_score":0.734193},"labels":[],"label_agreement":null},{"id":"W2125226720","doi":"10.1109/asru.2009.5373248","title":"Discriminative training of n-gram language models for speech recognition via linear programming","year":2009,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Discriminative model; Computer science; Speech recognition; Word error rate; Viterbi algorithm; Artificial intelligence; n-gram; Vocabulary; Language model; Metric (unit); Pattern recognition (psychology); Viterbi decoder; Hidden Markov model; Decoding methods; Algorithm","score_opus":0.0839183369757153,"score_gpt":0.30859773701399074,"score_spread":0.22467940003827544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125226720","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012502086,0.000016904905,0.97733885,0.0004464578,0.000062435895,0.00038462086,0.000007601104,0.0001896937,0.009051357],"genre_scores_gemma":[0.34797078,0.0000025765798,0.6516185,0.00019000717,0.00003761293,0.000021854585,0.000012332015,0.00000497057,0.00014139115],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990616,0.000034690107,0.00023874444,0.00026016543,0.0001786849,0.00022611335],"domain_scores_gemma":[0.99935496,0.00014010892,0.000096575415,0.00018238885,0.00016042066,0.00006552939],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030878794,0.000111984176,0.00018176988,0.00012891492,0.000060629078,0.000047111844,0.00025820953,0.000056538247,0.000028379554],"category_scores_gemma":[0.000091454815,0.000096568496,0.0001169046,0.00023065547,0.000023885435,0.00052710465,0.000021724494,0.000061040926,0.000010454535],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007729227,0.00008890814,4.996714e-7,0.000009672585,0.0000081022135,0.0000033593678,0.0026629472,0.000003039822,0.0016442572,0.0020970658,0.000029625102,0.9934448],"study_design_scores_gemma":[0.0007338928,0.0005739242,0.00005113503,0.00009455771,0.000029788316,0.000036686717,0.0031948045,0.59479654,0.31138906,0.08847375,0.0002548942,0.00037097884],"about_ca_topic_score_codex":0.000016698099,"about_ca_topic_score_gemma":0.000011267905,"teacher_disagreement_score":0.9930738,"about_ca_system_score_codex":0.000016472633,"about_ca_system_score_gemma":0.000024992847,"threshold_uncertainty_score":0.3937949},"labels":[],"label_agreement":null},{"id":"W2125964738","doi":"10.1109/icassp.2011.5947401","title":"Large vocabulary continuous speech recognition with context-dependent DBN-HMMS","year":2011,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":182,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Hidden Markov model; Computer science; Speech recognition; Word error rate; Mixture model; Artificial intelligence; Context (archaeology); Vocabulary; Phone; Pattern recognition (psychology); Sentence","score_opus":0.038738701807049386,"score_gpt":0.21732816535304594,"score_spread":0.17858946354599656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125964738","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11105913,0.00016479685,0.6135224,0.0003000859,0.0005108547,0.00057983934,0.00002200338,0.0010043953,0.2728365],"genre_scores_gemma":[0.86212826,0.000028244474,0.13186343,0.0021543703,0.00006532809,0.000044125365,0.000010384954,0.000023235443,0.0036826106],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983485,0.000093069204,0.00026261862,0.0004993215,0.0003899103,0.00040658575],"domain_scores_gemma":[0.9989167,0.00006815117,0.00009451789,0.0005391151,0.00020849668,0.00017302323],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00041102938,0.0002011354,0.00025383357,0.00014196843,0.00011886599,0.00012437905,0.0005281487,0.00009655349,0.0028768047],"category_scores_gemma":[0.000040837123,0.00015410333,0.00010025993,0.00023940903,0.000042446758,0.0006554207,0.00011830694,0.00014775095,0.0021458715],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005725509,0.00044904824,0.0012672005,0.000010233031,0.00010536427,0.00038610023,0.00094021537,2.4770598e-8,0.00021896178,0.0036075332,0.0023773347,0.99058074],"study_design_scores_gemma":[0.008849259,0.0023540487,0.015569236,0.0003238616,0.0002289254,0.0029750818,0.0060527166,0.004009959,0.8762734,0.029715294,0.050343864,0.0033043742],"about_ca_topic_score_codex":0.00015800635,"about_ca_topic_score_gemma":0.00024873143,"teacher_disagreement_score":0.9872764,"about_ca_system_score_codex":0.000029059513,"about_ca_system_score_gemma":0.000049306662,"threshold_uncertainty_score":0.99863106},"labels":[],"label_agreement":null},{"id":"W2126853534","doi":"10.1109/icalip.2008.4590005","title":"Comparison of frame margin probability training to other discriminative methods for multi-condition speech recognition","year":2008,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Discriminative model; Margin (machine learning); Computer science; Speech recognition; Pattern recognition (psychology); Frame (networking); Interpolation (computer graphics); Artificial intelligence; Maximum likelihood; Linear interpolation; Machine learning; Mathematics; Statistics","score_opus":0.40090993485312554,"score_gpt":0.46378618075651784,"score_spread":0.0628762459033923,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126853534","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05584176,0.000008043332,0.9398418,0.00040856557,0.00012975925,0.0007944595,0.000027689628,0.00012697965,0.0028209246],"genre_scores_gemma":[0.12770417,9.120284e-7,0.8715922,0.00030652896,0.000024161967,0.00015208228,0.000010523102,0.000010169816,0.0001992369],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985141,0.0002590304,0.00041225672,0.0004161835,0.00016941497,0.00022897327],"domain_scores_gemma":[0.9986006,0.00058480195,0.00014830682,0.00027018605,0.00029256952,0.00010350401],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008269956,0.00014530576,0.0003378862,0.00017047081,0.0001219978,0.000029343097,0.00029300834,0.00008673839,0.00024758617],"category_scores_gemma":[0.00068476156,0.0001288337,0.00013289807,0.00030596915,0.00007354288,0.0003593556,0.000052327858,0.00008756798,0.000041872303],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024670859,0.00038683173,0.00023770549,0.000026188069,0.000024937775,5.5810585e-7,0.0068285307,0.0000030491685,0.008649482,0.0020035624,0.00033518198,0.9814793],"study_design_scores_gemma":[0.0009249273,0.00039381295,0.0072664,0.00007682963,0.00002876541,0.00002102464,0.0014535056,0.0964272,0.8640655,0.026822368,0.002085558,0.00043407927],"about_ca_topic_score_codex":0.00003738745,"about_ca_topic_score_gemma":0.000034536573,"teacher_disagreement_score":0.98104525,"about_ca_system_score_codex":0.00005147176,"about_ca_system_score_gemma":0.000046775403,"threshold_uncertainty_score":0.5253686},"labels":[],"label_agreement":null},{"id":"W2128176957","doi":"10.1109/icassp.1982.1171437","title":"A composite scheme for text-independent speaker recognition","year":2005,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Speech recognition; Speaker recognition; Computer science; Cepstrum; Mel-frequency cepstrum; Inverse filter; Filter (signal processing); Pattern recognition (psychology); Feature (linguistics); Scheme (mathematics); Feature extraction; Linear prediction; Population; Inverse; Artificial intelligence; Mathematics","score_opus":0.037567609274671517,"score_gpt":0.2611128798612824,"score_spread":0.2235452705866109,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128176957","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021606058,0.000029106819,0.91143674,0.0049838983,0.00020081733,0.00034700584,0.0000085470765,0.00037844758,0.06100939],"genre_scores_gemma":[0.112568155,0.000008910684,0.88140565,0.0029574216,0.0002031527,0.00005924773,0.000011836854,0.00001019514,0.0027754216],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990858,0.000023728484,0.00018857686,0.0002950969,0.00018630688,0.00022053042],"domain_scores_gemma":[0.9994004,0.000106887535,0.000048301496,0.00023419074,0.00011433271,0.00009588362],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00021711885,0.00010348597,0.00011087552,0.00009677956,0.000095688,0.00015413093,0.0002998971,0.000055024273,0.0006879751],"category_scores_gemma":[0.00003165501,0.00009215456,0.00010035695,0.0001323565,0.000013537257,0.00044811674,0.000059249993,0.000056978628,0.0017793509],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009828414,0.00011029581,0.000053533266,0.0000053969943,0.000016259195,0.0000020219081,0.00006612647,8.253036e-7,0.0048196805,0.0036307122,0.005734963,0.98555034],"study_design_scores_gemma":[0.002864403,0.0001865007,0.0034551104,0.0000691357,0.000029544208,0.00017778599,0.0000951473,0.2236086,0.43485317,0.014931425,0.3187127,0.0010164536],"about_ca_topic_score_codex":0.000005965152,"about_ca_topic_score_gemma":0.000029612886,"teacher_disagreement_score":0.9845339,"about_ca_system_score_codex":0.000039465907,"about_ca_system_score_gemma":0.00002158561,"threshold_uncertainty_score":0.99899787},"labels":[],"label_agreement":null},{"id":"W2129269533","doi":"","title":"VARIABLE PRE-EMPHASIS LPC FOR MODELING VOCAL EFFORT IN THE SINGING VOICE","year":2006,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Formant; Spectral envelope; Speech recognition; Computer science; Envelope (radar); Singing; Phonation; Filter (signal processing); Linear predictive coding; Voice analysis; Breathy voice; Acoustics; Speech processing; Vowel; Telecommunications; Audiology; Physics","score_opus":0.023448755611974098,"score_gpt":0.2564090423091711,"score_spread":0.232960286697197,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129269533","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01557712,0.000028834287,0.95869905,0.00068418693,0.000097747965,0.00020829865,0.0000010353374,0.00009919996,0.024604512],"genre_scores_gemma":[0.5721469,0.0000010607716,0.42648283,0.00077775476,0.0000789223,0.000052342435,0.0000021265007,0.0000059039603,0.00045216488],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991125,0.000029156176,0.00019900313,0.0002338286,0.0001744061,0.0002510993],"domain_scores_gemma":[0.99939406,0.0002636367,0.000026155241,0.00024783885,0.00004620488,0.000022095332],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006603311,0.00008593312,0.000099333425,0.000085076674,0.00012545528,0.00020447788,0.00047195915,0.000043990774,0.000021041375],"category_scores_gemma":[0.000045293153,0.00006048071,0.000057063593,0.00030122095,0.000009226446,0.00028621446,0.000043262917,0.000057942765,0.000019172445],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003755041,0.0006479042,0.001513679,0.00006988796,0.000032737436,0.000019311383,0.0012574312,0.052275244,0.0015000228,0.48701546,0.0062782746,0.4493525],"study_design_scores_gemma":[0.00020723304,0.000013508462,0.00016053715,0.0000137607685,0.0000044084813,0.000011317822,0.000035338835,0.9706436,0.001129469,0.024928208,0.002753395,0.00009926672],"about_ca_topic_score_codex":0.00031507047,"about_ca_topic_score_gemma":0.0000841797,"teacher_disagreement_score":0.91836834,"about_ca_system_score_codex":0.000026074615,"about_ca_system_score_gemma":0.000035799243,"threshold_uncertainty_score":0.24663317},"labels":[],"label_agreement":null},{"id":"W2130509597","doi":"10.1109/tasl.2007.894523","title":"Environmental Independent ASR Model Adaptation/Compensation by Bayesian Parametric Representation","year":2007,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Computer science; Hidden Markov model; Normalization (sociology); Speech recognition; Adaptation (eye); Parametric statistics; Maximization; Parametric model; Bayesian probability; Artificial intelligence; Mathematics","score_opus":0.018098051288397823,"score_gpt":0.25645668791932236,"score_spread":0.23835863663092455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130509597","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0773535,0.0002573792,0.92120075,0.00017402097,0.000088798435,0.00017739611,0.000012103602,0.00016026373,0.0005757774],"genre_scores_gemma":[0.8929063,0.000056590547,0.10632833,0.0003226968,0.00002204368,0.000013898325,0.0000075174603,0.000014849056,0.0003277772],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99850094,0.000054308566,0.0002937663,0.00044564463,0.00043769594,0.00026762285],"domain_scores_gemma":[0.9993615,0.00011993892,0.00012780075,0.00021231163,0.000027650665,0.00015079167],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035284774,0.0001749855,0.00014845956,0.0003589499,0.00031182004,0.00021592196,0.00017811696,0.000104448205,0.00007677651],"category_scores_gemma":[0.000013662009,0.00017716787,0.0000613094,0.00044711566,0.000044123026,0.0006959373,0.000002986724,0.00021133853,0.000028367003],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021289734,0.00013644247,0.000027855589,0.000010968543,0.00001224101,0.000017705272,0.0013872405,0.0011348081,0.010494146,0.00000867278,0.000022770435,0.98672587],"study_design_scores_gemma":[0.00055143045,0.000053886102,0.0002938494,0.00003086135,0.000026030255,0.00008633896,0.0025271785,0.72168046,0.2742107,0.0002206756,0.000029320376,0.00028927298],"about_ca_topic_score_codex":0.00004121429,"about_ca_topic_score_gemma":0.000058081572,"teacher_disagreement_score":0.9864366,"about_ca_system_score_codex":0.000098278746,"about_ca_system_score_gemma":0.00003633258,"threshold_uncertainty_score":0.72246957},"labels":[],"label_agreement":null},{"id":"W2131525232","doi":"10.1109/asru.2005.1566525","title":"A constrained joint optimization method for large margin HMM estimation","year":2005,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Minimax; Margin (machine learning); Hidden Markov model; Computer science; Mathematical optimization; Optimization problem; Algorithm; Mathematics; Artificial intelligence; Machine learning","score_opus":0.03204761856645677,"score_gpt":0.29603580166454196,"score_spread":0.2639881830980852,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131525232","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00002523952,0.000005904074,0.9836609,0.0049356394,0.00007315301,0.0002580186,0.000006130908,0.00022423906,0.010810827],"genre_scores_gemma":[0.008274655,0.0000023740135,0.98952,0.0013262287,0.000040728646,0.000046938945,0.000012229421,0.0000053607505,0.00077147275],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992887,0.000050622017,0.00018350293,0.00020269265,0.00011245724,0.00016203901],"domain_scores_gemma":[0.9994866,0.00014176895,0.00005626568,0.00016591883,0.00009366203,0.000055770877],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005568949,0.0000757183,0.00010283086,0.00009748429,0.00008306433,0.000107345746,0.0001439467,0.000044401782,0.0006019837],"category_scores_gemma":[0.0001626849,0.000067392604,0.000062221945,0.00014335118,0.0000063970338,0.00036902638,0.000029545152,0.000028906074,0.000074264426],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000045135707,0.000084828986,0.0000029492148,0.000009217935,0.000012452277,6.52027e-7,0.00013955128,0.010808173,0.00035453416,0.13790202,0.0031598096,0.8475213],"study_design_scores_gemma":[0.00043578658,0.000018858773,0.000019275569,0.0000060792677,0.0000049259,0.000013781563,0.000018912626,0.9824625,0.011594111,0.0015279639,0.0038021556,0.00009563022],"about_ca_topic_score_codex":0.0000026182647,"about_ca_topic_score_gemma":0.0000062020836,"teacher_disagreement_score":0.97165436,"about_ca_system_score_codex":0.000028868246,"about_ca_system_score_gemma":0.00003410559,"threshold_uncertainty_score":0.6591299},"labels":[],"label_agreement":null},{"id":"W2131706900","doi":"10.1109/pacrim.2001.953719","title":"Pitch-excited ARMA lattice model for speech synthesis","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Vocal tract; Speech synthesis; Computer science; Speech recognition; Autoregressive–moving-average model; Lattice (music); Representation (politics); Pole–zero plot; Speech production; Speech processing; Autoregressive model; Acoustics; Transfer function; Mathematics; Physics; Engineering","score_opus":0.07871584020366355,"score_gpt":0.257007547745181,"score_spread":0.1782917075415174,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131706900","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021546104,0.000028000226,0.9375192,0.004351461,0.00012169846,0.00021421902,0.000007822276,0.00042770288,0.055175293],"genre_scores_gemma":[0.22546023,0.000039676703,0.7513972,0.0028328476,0.00007684779,0.00011734514,0.0000010349344,0.000021041298,0.020053778],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988048,0.000033282115,0.0002227435,0.0003824927,0.0002323773,0.00032430064],"domain_scores_gemma":[0.9988448,0.0004481646,0.000054193217,0.00039857673,0.00012186374,0.00013238106],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00022439228,0.00014805255,0.000178355,0.00014147579,0.0001294288,0.00016270802,0.00057521777,0.00007681539,0.0010290497],"category_scores_gemma":[0.000203842,0.00013007538,0.00013745391,0.000279245,0.00002432666,0.00040592055,0.00007414995,0.00006313532,0.0007758788],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006839267,0.0002448993,0.00002560937,0.000023784165,0.000043545566,0.000012761552,0.00025141952,0.00006193807,0.0007734823,0.02243004,0.046463702,0.929662],"study_design_scores_gemma":[0.00017317268,0.00001412298,0.00002533393,0.000009709689,0.000013510681,0.00002026457,0.00001633206,0.9752062,0.016469313,0.003883076,0.0039649196,0.00020402296],"about_ca_topic_score_codex":0.0000076214938,"about_ca_topic_score_gemma":0.0000070760325,"teacher_disagreement_score":0.97514427,"about_ca_system_score_codex":0.000027201537,"about_ca_system_score_gemma":0.000012511701,"threshold_uncertainty_score":0.9998841},"labels":[],"label_agreement":null},{"id":"W2132037657","doi":"10.1109/icassp.2011.5947700","title":"Learning a better representation of speech soundwaves using restricted boltzmann machines","year":2011,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":229,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Cepstrum; Speech recognition; Computer science; Mel-frequency cepstrum; Linear predictive coding; Boltzmann machine; Restricted Boltzmann machine; Representation (politics); Artificial intelligence; Speech coding; Pattern recognition (psychology); Artificial neural network; Feature extraction","score_opus":0.07598615674813156,"score_gpt":0.2849837548539779,"score_spread":0.20899759810584637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2132037657","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.72082794,0.000008825077,0.25263432,0.000100975514,0.0001072502,0.00007589275,3.863569e-7,0.00014362554,0.026100772],"genre_scores_gemma":[0.56556445,0.000005041177,0.43372563,0.00009507201,0.00003787461,0.0000018659958,0.0000013322261,0.000006181275,0.00056253816],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991367,0.00010208311,0.00022054117,0.00021894729,0.00018872657,0.00013301865],"domain_scores_gemma":[0.9994141,0.00008807412,0.00011408329,0.0002427587,0.00010035507,0.000040643186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010828535,0.00008017486,0.0001273152,0.00017997065,0.00006949467,0.00004629922,0.00025829152,0.000042039657,0.00035698208],"category_scores_gemma":[0.00013385795,0.00006902261,0.00006371013,0.0004229106,0.000030296793,0.00037821935,0.000091090515,0.00007691366,0.000037733753],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023252407,0.00011193016,0.06314261,0.00002050016,0.0000612131,0.00004666313,0.0027192829,0.0000131046545,0.048534386,0.0033446557,0.00027768026,0.88170475],"study_design_scores_gemma":[0.0006551478,0.00018296506,0.12518384,0.00006293895,0.000040205785,0.00015341873,0.00056941377,0.2876958,0.56735075,0.017119773,0.000480499,0.00050529407],"about_ca_topic_score_codex":0.00045516543,"about_ca_topic_score_gemma":0.000011365414,"teacher_disagreement_score":0.8811994,"about_ca_system_score_codex":0.00001003962,"about_ca_system_score_gemma":0.000017729788,"threshold_uncertainty_score":0.39087036},"labels":[],"label_agreement":null},{"id":"W2135433537","doi":"10.1109/89.928919","title":"A maximum a posteriori approach to speaker adaptation using the trended hidden Markov model","year":2001,"lang":"en","type":"article","venue":"IEEE Transactions on Speech and Audio Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Hidden Markov model; Maximum a posteriori estimation; Polynomial; Computer science; Speech recognition; Adaptation (eye); Security token; A priori and a posteriori; Gaussian; Pattern recognition (psychology); Mathematics; Algorithm; Artificial intelligence; Statistics; Maximum likelihood","score_opus":0.05320708971129079,"score_gpt":0.2664378542114752,"score_spread":0.2132307645001844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135433537","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036147676,0.000052800387,0.9583255,0.0012132336,0.00012184923,0.00025164674,0.000005343756,0.00015683877,0.0037250833],"genre_scores_gemma":[0.57822734,0.00002608892,0.4202063,0.00091823447,0.00003998042,0.000027787535,6.5829704e-7,0.000016617452,0.0005369633],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985241,0.00006172951,0.00025663013,0.0004846572,0.00034015515,0.00033268577],"domain_scores_gemma":[0.999324,0.000041237083,0.00008266661,0.00029825667,0.000099034856,0.00015475517],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024103181,0.0002172426,0.00019212482,0.00024207257,0.00058399147,0.0004749617,0.0003176592,0.00008044514,0.000016907192],"category_scores_gemma":[0.00000590863,0.00016771033,0.0000836563,0.0006973319,0.000048784183,0.0006195514,0.000005494212,0.0001974422,0.000015897713],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004618264,0.00010743531,0.0000018383887,0.000015755091,0.000014619167,0.000007775672,0.0014908025,0.0021295745,0.003275144,0.000011190945,0.000023229035,0.99287647],"study_design_scores_gemma":[0.00040635522,0.000052450403,0.000035631423,0.00008396919,0.000041469637,0.000436975,0.00060473266,0.9821218,0.014967337,0.00073501363,0.00020603531,0.00030820543],"about_ca_topic_score_codex":0.000025595176,"about_ca_topic_score_gemma":0.00002370208,"teacher_disagreement_score":0.99256825,"about_ca_system_score_codex":0.000062947176,"about_ca_system_score_gemma":0.00010643773,"threshold_uncertainty_score":0.68390286},"labels":[],"label_agreement":null},{"id":"W2135474356","doi":"10.1109/icassp.2002.5743869","title":"Auditory-based acoustic distinctive features and spectral cues for automatic speech recognition using a multi-stream paradigm","year":2002,"lang":"en","type":"article","venue":"IEEE International Conference on Acoustics Speech and Signal Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Computer science; Speech recognition; Bigram; Hidden Markov model; TIMIT; Word error rate; Artificial intelligence; Feature extraction; Pattern recognition (psychology)","score_opus":0.09560722869828778,"score_gpt":0.3126416919736763,"score_spread":0.21703446327538853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135474356","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.103645556,0.00007759076,0.893698,0.0006279801,0.00047127923,0.0003666152,0.00011081651,0.00018474067,0.0008174255],"genre_scores_gemma":[0.7254485,0.000031934585,0.27379924,0.00028144624,0.00028523756,0.000026059297,0.000014694989,0.000018084453,0.00009481802],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981655,0.000057161487,0.00035506053,0.0006049733,0.00046310626,0.00035420366],"domain_scores_gemma":[0.99866784,0.00034570473,0.00025722894,0.00013690251,0.000408858,0.00018344336],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00021146805,0.00032073556,0.00028569796,0.00028859026,0.0003484221,0.0008357766,0.0003417827,0.00014394044,0.00013985833],"category_scores_gemma":[0.00018817358,0.00030233775,0.000073915995,0.00015441947,0.00016259642,0.0005342643,0.00003878646,0.00025438232,0.0000131807565],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007292883,0.0003775812,0.00008610531,0.00018778608,0.000066085835,0.00009098449,0.00031028246,0.0002053572,0.037957672,0.0002902085,0.00033240757,0.9600226],"study_design_scores_gemma":[0.000897823,0.00018930275,0.00049322634,0.0004401915,0.000060198676,0.00018436063,0.00012226427,0.97941273,0.011081047,0.006713861,0.000016168195,0.00038879536],"about_ca_topic_score_codex":0.000013825929,"about_ca_topic_score_gemma":0.000017278866,"teacher_disagreement_score":0.9792074,"about_ca_system_score_codex":0.00011196948,"about_ca_system_score_gemma":0.000111124486,"threshold_uncertainty_score":0.9999429},"labels":[],"label_agreement":null},{"id":"W2136652457","doi":"10.1109/icassp.2004.1326116","title":"A Viterbi algorithm for a trajectory model derived from HMM with explicit relationship between static and dynamic features","year":2004,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Pratt and Whitney Canada","keywords":"Viterbi algorithm; Hidden Markov model; Soft output Viterbi algorithm; Forward algorithm; Computer science; Iterative Viterbi decoding; Trajectory; Speech recognition; Sequence (biology); Algorithm; State (computer science); Pattern recognition (psychology); Artificial intelligence; Markov model; Machine learning; Markov chain; Decoding methods; Variable-order Markov model","score_opus":0.03367362737486818,"score_gpt":0.2606226382829699,"score_spread":0.2269490109081017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136652457","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21600881,0.0000318538,0.78287643,0.0005400665,0.00001421259,0.00022392058,0.00003942261,0.000120505116,0.00014479163],"genre_scores_gemma":[0.4657724,0.000001855765,0.5338377,0.00020944324,0.0000094035195,0.00004281231,0.000012219625,0.000007294418,0.00010690643],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991843,0.000024234503,0.00013827787,0.00032994282,0.00014744548,0.0001758101],"domain_scores_gemma":[0.9991375,0.00045871135,0.000047883095,0.000211909,0.000044375025,0.00009962997],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008015899,0.00013062198,0.00015913777,0.00009814195,0.00012257393,0.00012842765,0.0001884802,0.00006007502,0.000005780396],"category_scores_gemma":[0.000027788266,0.000102787126,0.000039121864,0.00012513211,0.000027870235,0.00032693092,0.000029147302,0.00008102698,0.0000062766094],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004782096,0.00020057661,0.0039282,0.000052575906,0.00020927837,0.000022245627,0.007278976,0.00088192214,0.0021298684,0.010053169,0.0001789206,0.9750165],"study_design_scores_gemma":[0.002444379,0.00019334079,0.10494719,0.000084551044,0.00006537494,0.000017483064,0.000313761,0.7764768,0.004784265,0.110181205,0.000013013121,0.00047862547],"about_ca_topic_score_codex":0.00007266386,"about_ca_topic_score_gemma":0.00013395523,"teacher_disagreement_score":0.97453785,"about_ca_system_score_codex":0.00004360344,"about_ca_system_score_gemma":0.000068316695,"threshold_uncertainty_score":0.41915375},"labels":[],"label_agreement":null},{"id":"W2136836257","doi":"10.1109/89.979381","title":"A robust compensation strategy for extraneous acoustic variations in spontaneous speech recognition","year":2002,"lang":"en","type":"article","venue":"IEEE Transactions on Speech and Audio Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Hidden Markov model; Speech recognition; Computer science; Word error rate; Pattern recognition (psychology); Pronunciation; Bayesian probability; Artificial intelligence","score_opus":0.07417596438202625,"score_gpt":0.2557498206924044,"score_spread":0.18157385631037812,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136836257","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022445826,0.00009834931,0.974603,0.0006095877,0.00021849373,0.00051863276,0.000035215122,0.00022926307,0.0012416268],"genre_scores_gemma":[0.8611007,0.00013111747,0.1379099,0.0002756429,0.000055196637,0.000096343574,0.0000063856746,0.0000224318,0.00040233057],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99832064,0.000071311646,0.00041303286,0.0005532509,0.0002637974,0.00037797913],"domain_scores_gemma":[0.99907655,0.00029675866,0.00012601442,0.00020645032,0.00016736277,0.00012688631],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002652239,0.00024109408,0.0002608106,0.00042346976,0.00043678493,0.0003694833,0.00020339483,0.00015390068,0.00020430124],"category_scores_gemma":[0.000027774151,0.0002541964,0.000086036074,0.00056147994,0.000049342263,0.00068780966,0.0000017071558,0.0002550712,0.000060579467],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003222771,0.000283962,0.0000015468723,0.000067924404,0.000012342045,0.00015899935,0.0002983462,0.0028831437,0.0023685014,0.000014645954,0.000035618235,0.9938427],"study_design_scores_gemma":[0.001708645,0.0003676104,0.00009357221,0.00033333493,0.00008106489,0.0035798063,0.00022958114,0.9515975,0.037813358,0.0033344121,0.00018281865,0.0006782689],"about_ca_topic_score_codex":0.00002530018,"about_ca_topic_score_gemma":0.00030292413,"teacher_disagreement_score":0.9931645,"about_ca_system_score_codex":0.00010189184,"about_ca_system_score_gemma":0.00005533267,"threshold_uncertainty_score":0.999991},"labels":[],"label_agreement":null},{"id":"W2136879537","doi":"10.1109/tasl.2008.925147","title":"A Study of Interspeaker Variability in Speaker Verification","year":2008,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":591,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"NIST; Hyperparameter; Channel (broadcasting); Computer science; Word error rate; Task (project management); Joint (building); Speech recognition; Statistics; Function (biology); Error analysis; Pattern recognition (psychology); Artificial intelligence; Mathematics; Engineering; Applied mathematics","score_opus":0.02538206399158666,"score_gpt":0.2646189760404997,"score_spread":0.23923691204891306,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136879537","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5679823,0.000037008933,0.43104208,0.00006524957,0.000054693177,0.00015197854,0.0000016143593,0.000055762433,0.00060932746],"genre_scores_gemma":[0.98403335,0.000018062505,0.015739769,0.00008192321,0.000009028778,0.00002055272,3.8138282e-7,0.000007379836,0.00008955089],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99889123,0.00015239547,0.00027052808,0.00033686112,0.00020042827,0.00014854525],"domain_scores_gemma":[0.9994454,0.00009939809,0.00007974466,0.00027059132,0.0000480947,0.000056765515],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045432034,0.00011773812,0.00018222502,0.00022868098,0.00011150073,0.00003675378,0.00017453707,0.000050979073,0.00004838294],"category_scores_gemma":[0.00002653566,0.000108493754,0.00003693393,0.00048558952,0.00005319496,0.00032914348,0.0000025740642,0.00016293387,0.000007665747],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038045364,0.0012007027,0.0006156095,0.00003514249,0.0000145399235,0.00007188962,0.023717003,0.000029250403,0.0033290836,0.0000068083227,0.0000066899647,0.9709352],"study_design_scores_gemma":[0.010079352,0.0018194357,0.07528951,0.00084101147,0.00016299728,0.0018167484,0.04979117,0.11303864,0.74410343,0.00062931236,0.00020746734,0.002220928],"about_ca_topic_score_codex":0.00009309202,"about_ca_topic_score_gemma":0.00025104423,"teacher_disagreement_score":0.9687143,"about_ca_system_score_codex":0.000037265312,"about_ca_system_score_gemma":0.00004207305,"threshold_uncertainty_score":0.4424247},"labels":[],"label_agreement":null},{"id":"W2137137149","doi":"10.1109/icassp.1984.1172800","title":"Modelling of the laryngeal acoustic source by labile nonlinear oscillators","year":2005,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Phonation; Nonlinear system; Speech production; Dynamics (music); Acoustics; Computer science; Speech recognition; Physics; Audiology; Quantum mechanics","score_opus":0.017951610414642265,"score_gpt":0.2089034662436795,"score_spread":0.19095185582903723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2137137149","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.089158714,0.000043142558,0.90103316,0.00092076825,0.000090134585,0.000073001676,0.0000045614524,0.000090556394,0.00858599],"genre_scores_gemma":[0.8830347,0.000011090151,0.11330152,0.0006367346,0.00005700369,0.0000026619914,4.87656e-7,0.0000065477907,0.0029492287],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992778,0.000032653465,0.00015798319,0.00016400292,0.00022474407,0.00014281881],"domain_scores_gemma":[0.9994458,0.00009033206,0.000049795457,0.0003155938,0.000050009938,0.00004846169],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014198133,0.000071841365,0.00009439119,0.00002971444,0.00007235992,0.00003444732,0.00049114897,0.000040171653,0.00015068222],"category_scores_gemma":[0.00002191364,0.000046787703,0.000070602684,0.0001994877,0.00003400694,0.0001426558,0.00010506212,0.000067706824,0.00007522701],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009263041,0.00048094508,0.0010094565,0.000036642028,0.00005997044,0.0000016440822,0.0012734301,0.40627012,0.010792293,0.002232744,0.032272365,0.54556113],"study_design_scores_gemma":[0.00007702958,0.000007856472,0.000007835009,0.000006111666,0.0000037618224,0.0000033929462,0.000025282376,0.9527696,0.028413866,0.00008355718,0.018534996,0.00006671029],"about_ca_topic_score_codex":0.000032272932,"about_ca_topic_score_gemma":0.000011261623,"teacher_disagreement_score":0.793876,"about_ca_system_score_codex":0.000015802243,"about_ca_system_score_gemma":0.000028802682,"threshold_uncertainty_score":0.1907947},"labels":[],"label_agreement":null},{"id":"W2137587425","doi":"10.1109/asru.2001.1034628","title":"Out-of-vocabulary word modeling using multiple lexical fillers","year":2005,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Vocabulary; Word error rate; Computer science; Word (group theory); Natural language processing; Task (project management); Speech recognition; Artificial intelligence; Linguistics; Engineering","score_opus":0.09530444043216925,"score_gpt":0.28768958386833093,"score_spread":0.1923851434361617,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2137587425","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.112294726,0.000029714043,0.8810414,0.00044559553,0.00016381111,0.000050633087,6.471902e-7,0.000108718494,0.0058647613],"genre_scores_gemma":[0.5746856,0.0000043398327,0.42484805,0.0002731078,0.000045267683,0.0000010580403,3.809357e-7,0.0000037885786,0.00013846198],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991885,0.000029683542,0.00021231682,0.00020846276,0.00018526647,0.00017579123],"domain_scores_gemma":[0.9995098,0.0000809263,0.000034191176,0.00024598662,0.000051881052,0.00007719304],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014958347,0.000082769155,0.00012357283,0.00008739246,0.000059082235,0.00004098475,0.0003096942,0.000051092953,0.000205473],"category_scores_gemma":[0.000055402288,0.000072914365,0.000083829276,0.00012788581,0.000019911977,0.0003039033,0.000094011666,0.00006489591,0.000098247634],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010046944,0.00013404815,0.00031579944,0.000007839258,0.000026821852,0.000007820488,0.0005763052,0.021101987,0.003845679,0.0022692524,0.0004097336,0.97129464],"study_design_scores_gemma":[0.00015004826,0.000006120763,0.000020050216,0.000012644637,0.0000028736551,0.000004632089,0.00005393771,0.98946404,0.008998364,0.00023304249,0.0009504041,0.000103842794],"about_ca_topic_score_codex":0.00002695888,"about_ca_topic_score_gemma":0.000024456154,"teacher_disagreement_score":0.9711908,"about_ca_system_score_codex":0.000024344086,"about_ca_system_score_gemma":0.000033267723,"threshold_uncertainty_score":0.29733616},"labels":[],"label_agreement":null},{"id":"W2137743578","doi":"10.1109/34.845379","title":"Training hidden Markov models with multiple observations-a combinatorial method","year":2000,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":150,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal; Université Laval; SNC-Lavalin (Canada)","funders":"Natural Sciences and Engineering Research Council of Canada; Guangxi University; East China Institute of Technology","keywords":"Hidden Markov model; Computer science; Artificial intelligence; Markov chain; Lagrange multiplier; Generality; Handwriting; Independence (probability theory); Machine learning; Function (biology); Maximization; Pattern recognition (psychology); Algorithm; Mathematics; Mathematical optimization; Statistics","score_opus":0.06005585691777636,"score_gpt":0.2821406138225669,"score_spread":0.22208475690479051,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2137743578","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0043767393,0.000019840843,0.99404216,0.00045562285,0.00012320092,0.00014180716,0.00003803956,0.00013613909,0.00066644314],"genre_scores_gemma":[0.88326323,0.00014137951,0.11564748,0.0005434065,0.00001969405,0.00004286923,0.0000058370747,0.000012864798,0.00032321675],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982935,0.00016622296,0.00036013153,0.0005752897,0.00034668582,0.0002581631],"domain_scores_gemma":[0.99883085,0.00038215634,0.00007775506,0.00045929686,0.00009014766,0.00015976749],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032485378,0.00023925216,0.0003629132,0.00038972005,0.00028834378,0.00019686243,0.00041557575,0.00007424955,0.0007189052],"category_scores_gemma":[0.000004558187,0.00019790274,0.00021323837,0.001210967,0.000050097493,0.0004686539,0.0000027540011,0.00023762141,0.00003072151],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026896747,0.0001306334,0.00013019292,0.000004503069,0.0003601096,0.000009229564,0.0005573534,0.010381578,0.000039325794,0.00016939538,0.0000039064666,0.9881869],"study_design_scores_gemma":[0.0002545113,0.00012182094,0.00063890783,0.000025024874,0.0003810089,0.000025973883,0.00010522074,0.97643524,0.019728204,0.0018120846,0.00012732357,0.00034469567],"about_ca_topic_score_codex":0.0011318465,"about_ca_topic_score_gemma":0.0010958661,"teacher_disagreement_score":0.9878422,"about_ca_system_score_codex":0.000027986598,"about_ca_system_score_gemma":0.000030054423,"threshold_uncertainty_score":0.807024},"labels":[],"label_agreement":null},{"id":"W2137997377","doi":"10.1109/icassp.2013.6639126","title":"Multiple windowed spectral features for emotion recognition","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Institut National de la Recherche Scientifique; Computer Research Institute of Montréal","funders":"","keywords":"Multitaper; Mel-frequency cepstrum; Speech recognition; Computer science; Pattern recognition (psychology); Mixture model; Dynamic time warping; Feature (linguistics); Set (abstract data type); Artificial intelligence; Cepstrum; Feature extraction","score_opus":0.028112341929656913,"score_gpt":0.2315257983846509,"score_spread":0.20341345645499398,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2137997377","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11687597,0.000012773744,0.8558059,0.0027247574,0.0005228962,0.0008595279,0.000006947152,0.00051006966,0.022681197],"genre_scores_gemma":[0.5339994,0.0000055116125,0.46239653,0.0009873653,0.0001495467,0.0001436871,0.00002180674,0.0000087002645,0.002287478],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992905,0.000028226148,0.00012785463,0.00023929524,0.00011504379,0.00019905652],"domain_scores_gemma":[0.9994035,0.0001720393,0.000039772523,0.00018080932,0.00013086197,0.000073044874],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000103443286,0.00008856449,0.000089963694,0.00008673443,0.000093075156,0.00020314871,0.00021122202,0.00005766709,0.0006537815],"category_scores_gemma":[0.00013800402,0.00007403219,0.000088099194,0.00012519791,0.000013178159,0.0005958974,0.000025002468,0.00004840945,0.0008872403],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000058588457,0.00006985826,0.00018823198,0.000007688188,0.0000124701255,7.576224e-7,0.000105925865,6.17271e-7,0.0068517704,0.0017778409,0.017467072,0.97351193],"study_design_scores_gemma":[0.0030872622,0.000373711,0.15321758,0.00005718426,0.000023831779,0.0001005967,0.0003842521,0.11331108,0.579287,0.1421162,0.007053991,0.0009872828],"about_ca_topic_score_codex":0.00005244083,"about_ca_topic_score_gemma":0.000021716758,"teacher_disagreement_score":0.97252464,"about_ca_system_score_codex":0.000020819387,"about_ca_system_score_gemma":0.000013143461,"threshold_uncertainty_score":0.9998907},"labels":[],"label_agreement":null},{"id":"W2138632432","doi":"10.1109/icassp.2012.6289016","title":"Dealing with acoustic mismatch for training multilingual subspace Gaussian mixture models for speech recognition","year":2012,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Pronunciation; Subspace topology; Speech recognition; Acoustic model; Variation (astronomy); Mixture model; Similarity (geometry); Artificial intelligence; Gaussian; Speech corpus; Training set; Natural language processing; Language model; Hidden Markov model; Parametrization (atmospheric modeling); Speech processing; Speech synthesis; Linguistics","score_opus":0.09074219761707655,"score_gpt":0.2908651392679138,"score_spread":0.20012294165083724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2138632432","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03053955,0.000043365777,0.96447074,0.00061903585,0.0002565741,0.00072562194,0.00002634885,0.00027949334,0.0030392369],"genre_scores_gemma":[0.43621767,0.0000037089721,0.5628822,0.00030080296,0.0001733078,0.000099633085,0.000015886106,0.000020521516,0.00028630166],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985926,0.000027989128,0.00022987618,0.00036591562,0.00020780953,0.0005757661],"domain_scores_gemma":[0.99869585,0.0005250648,0.00010487928,0.00024036806,0.00022106004,0.00021278617],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005583953,0.00020689635,0.00023004763,0.00011982986,0.00022154259,0.00013511986,0.00026635124,0.00012435789,0.000042250205],"category_scores_gemma":[0.00012392251,0.0001658776,0.00011578169,0.00015637362,0.000024307432,0.00081866817,0.00002496666,0.00009323429,0.000016268397],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009813899,0.00012006595,0.00002237332,0.00008987939,0.000059638576,0.0000035200221,0.004151165,0.0002000922,0.003417155,0.0030720865,0.00037474814,0.98839116],"study_design_scores_gemma":[0.002008263,0.00022583894,0.000033252953,0.00016274145,0.00010623076,0.00018604824,0.0030527704,0.8234381,0.15564007,0.013064115,0.0013109716,0.00077158323],"about_ca_topic_score_codex":0.000012360488,"about_ca_topic_score_gemma":0.000068050744,"teacher_disagreement_score":0.9876196,"about_ca_system_score_codex":0.00003265686,"about_ca_system_score_gemma":0.000057967765,"threshold_uncertainty_score":0.6764293},"labels":[],"label_agreement":null},{"id":"W2139753501","doi":"10.1109/ispa.2003.1296424","title":"Online identification of hidden Semi-Markov models","year":2004,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Hidden Markov model; Hidden semi-Markov model; Algorithm; Computer science; Forward algorithm; Estimation theory; SIGNAL (programming language); Maximum-entropy Markov model; Parametric model; Exponential function; Parametric statistics; Constant (computer programming); Exponential distribution; Markov model; Markov chain; State (computer science); Pattern recognition (psychology); Mathematics; Artificial intelligence; Variable-order Markov model; Statistics; Machine learning","score_opus":0.032438083842129754,"score_gpt":0.2582246811897791,"score_spread":0.22578659734764933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139753501","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.062589556,0.000019785799,0.92634505,0.0011299618,0.0000946653,0.00006397017,0.000004878727,0.00010867852,0.00964346],"genre_scores_gemma":[0.8271373,0.000018016935,0.171901,0.00020070413,0.000015920517,0.0000029897847,0.0000040043906,0.000002995801,0.00071709807],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99936604,0.000014781083,0.00021100458,0.00015725776,0.0001687151,0.000082170474],"domain_scores_gemma":[0.99948716,0.000029122844,0.000065442364,0.00029212894,0.00008853917,0.00003759428],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012822884,0.00004979788,0.00007702846,0.000076930846,0.000024183382,0.000033375192,0.00034165737,0.000030332561,0.000055602293],"category_scores_gemma":[0.000026695816,0.000043618897,0.000043884716,0.00019621427,0.000016609702,0.00036689974,0.000048950096,0.000030094194,0.00006331945],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000044406606,0.0006300115,0.000041418883,0.000021213806,0.000028475952,0.000006146273,0.00058262015,0.0005518633,0.032530133,0.24345215,0.0006084631,0.7215431],"study_design_scores_gemma":[0.00059216336,0.000040098083,0.0025982289,0.000036437705,0.000010784581,0.000022430402,0.00013192411,0.21929374,0.5099351,0.26682484,0.0002605052,0.00025374605],"about_ca_topic_score_codex":0.000038745427,"about_ca_topic_score_gemma":0.00001586163,"teacher_disagreement_score":0.7645477,"about_ca_system_score_codex":0.000019615027,"about_ca_system_score_gemma":0.000035277684,"threshold_uncertainty_score":0.1778727},"labels":[],"label_agreement":null},{"id":"W2140046090","doi":"10.1109/icassp.2008.4518622","title":"Speaker diarization of French broadcast news","year":2008,"lang":"en","type":"article","venue":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Speaker diarisation; Computer science; Mel-frequency cepstrum; Cluster analysis; Speech recognition; Feature (linguistics); Test set; Word error rate; Set (abstract data type); Hierarchical clustering; Pattern recognition (psychology); Speaker recognition; Artificial intelligence; Segmentation; Feature extraction","score_opus":0.05214884939631418,"score_gpt":0.2664301578707716,"score_spread":0.21428130847445745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140046090","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6778025,0.00010644197,0.2419671,0.0028846767,0.0009870438,0.00044466672,0.000036370617,0.00014714194,0.07562404],"genre_scores_gemma":[0.9768173,0.00016236982,0.021960061,0.0002461906,0.00013919176,0.0000041446683,0.0000014448706,0.00001132713,0.0006579571],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983048,0.000011220027,0.0004559292,0.00034854593,0.00069419993,0.0001853167],"domain_scores_gemma":[0.99801654,0.000064803666,0.00050216174,0.00010002054,0.0012403771,0.00007607752],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020947204,0.00018867868,0.00024660377,0.00020046592,0.00016384953,0.00014769765,0.0008919937,0.00009325225,0.0000761275],"category_scores_gemma":[0.00016610297,0.00014666944,0.000083207575,0.00026283244,0.00026047527,0.00056708726,0.00013470315,0.00019816824,0.000006528559],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000096044496,0.0004994391,0.009625506,0.00031289726,0.000106652325,0.000009906807,0.0029062186,0.00008505538,0.4703931,0.028625153,0.0020308364,0.4853092],"study_design_scores_gemma":[0.0013522878,0.00033067667,0.013769429,0.0014997119,0.00008244223,0.0003411829,0.0011150843,0.46661523,0.47250065,0.04109757,0.0004645653,0.0008311635],"about_ca_topic_score_codex":0.000037070855,"about_ca_topic_score_gemma":0.0000016313599,"teacher_disagreement_score":0.48447803,"about_ca_system_score_codex":0.000035010526,"about_ca_system_score_gemma":0.00012893397,"threshold_uncertainty_score":0.5981006},"labels":[],"label_agreement":null},{"id":"W2141401351","doi":"10.1109/mmsp.2007.4412892","title":"Combining Vocal Source and MFCC Features for Enhanced Speaker Recognition Performance Using GMMs","year":2007,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":62,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Mel-frequency cepstrum; Speech recognition; Crest factor; Computer science; Cepstrum; Vocal tract; Mixture model; Pattern recognition (psychology); Artificial intelligence; Speaker recognition; Centroid; Feature extraction; Bandwidth (computing)","score_opus":0.039143575831901284,"score_gpt":0.2683018335022468,"score_spread":0.2291582576703455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2141401351","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39258733,0.000017768796,0.59995437,0.00007991228,0.0001397899,0.00011561702,6.915391e-7,0.00009694255,0.0070075765],"genre_scores_gemma":[0.6923848,0.0000138332425,0.3062475,0.00057546026,0.000080881175,0.0000055321943,0.0000032592438,0.0000094081215,0.0006793042],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99908185,0.00001710977,0.00018376473,0.0002866026,0.00014739865,0.00028325012],"domain_scores_gemma":[0.9994126,0.00020593534,0.00006401562,0.00014685243,0.00007748335,0.000093097966],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048584628,0.00011673588,0.00012910138,0.000112472044,0.00020272477,0.00013729451,0.00015308343,0.00007412345,0.00004971574],"category_scores_gemma":[0.000058797537,0.000104615196,0.000046340905,0.00016315801,0.00003790663,0.000402449,0.000059381706,0.00008321483,0.000027409598],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028134486,0.00002723535,0.000118281736,0.000017396052,0.000009841231,0.0000013788114,0.00034328338,0.0000035758455,0.010148844,0.0002520149,0.000113113914,0.9889369],"study_design_scores_gemma":[0.0013314716,0.00021368651,0.008628985,0.00013184707,0.000023722496,0.00016408983,0.00039342142,0.11069875,0.8730829,0.0016734051,0.0030910866,0.0005666716],"about_ca_topic_score_codex":0.000011975974,"about_ca_topic_score_gemma":0.00001800314,"teacher_disagreement_score":0.98837024,"about_ca_system_score_codex":0.000024099698,"about_ca_system_score_gemma":0.000017548335,"threshold_uncertainty_score":0.42660838},"labels":[],"label_agreement":null},{"id":"W2141778357","doi":"10.21437/interspeech.2010-304","title":"Investigation of full-sequence training of deep belief networks for speech recognition","year":2010,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":213,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Training (meteorology); Speech recognition; Sequence (biology); Artificial intelligence; Natural language processing","score_opus":0.08245940770069941,"score_gpt":0.2678514967899197,"score_spread":0.18539208908922028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2141778357","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23230661,0.0000064598203,0.764337,0.00025972782,0.00030019335,0.00020117349,0.000004922095,0.00006576775,0.0025181172],"genre_scores_gemma":[0.49046737,0.0000041731782,0.5092999,0.00013185288,0.000046829326,0.00001600662,0.000009575258,0.000004407423,0.000019903195],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991207,0.00003179996,0.00032555105,0.00020924957,0.00015911584,0.00015359592],"domain_scores_gemma":[0.998894,0.0003237624,0.00019362665,0.00023027479,0.00028862574,0.000069761154],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000538206,0.000084347506,0.00016089015,0.00011369391,0.000045532215,0.00002605716,0.00030094996,0.00009976496,0.00012774367],"category_scores_gemma":[0.0002495228,0.00007944139,0.00007799933,0.00027296887,0.000085949876,0.0003453089,0.000031049476,0.00009733804,0.000006933292],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000063910634,0.000011567196,0.000089750596,0.00001557578,0.000007865406,4.3659597e-7,0.00027872497,0.0000051805214,0.13032852,0.0034956527,0.000055810764,0.86570454],"study_design_scores_gemma":[0.00042566017,0.00018108005,0.0008492841,0.000053147014,0.000016728047,0.000044863285,0.00015317445,0.3228397,0.63247555,0.04262456,0.00012252496,0.00021372813],"about_ca_topic_score_codex":0.000016885146,"about_ca_topic_score_gemma":0.000107270615,"teacher_disagreement_score":0.8654908,"about_ca_system_score_codex":0.000006495889,"about_ca_system_score_gemma":0.00004559041,"threshold_uncertainty_score":0.32395262},"labels":[],"label_agreement":null},{"id":"W2142799607","doi":"10.1109/icassp.2006.1659970","title":"Improvements in Factor Analysis Based Speaker Verification","year":2006,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Speaker verification; Factor (programming language); Speech recognition; Speaker recognition; Programming language","score_opus":0.015071807643092246,"score_gpt":0.23138557314759944,"score_spread":0.2163137655045072,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142799607","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1960503,0.0000033091687,0.786043,0.0003908376,0.00004979286,0.00007658254,0.0000025182278,0.000088096334,0.017295564],"genre_scores_gemma":[0.9485715,4.3133346e-7,0.050488334,0.0002857182,0.000007713924,0.0000079874635,0.00000784425,0.0000018822711,0.00062859507],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9993858,0.000025636633,0.000144919,0.00019733165,0.00014027144,0.000106079664],"domain_scores_gemma":[0.999639,0.000030016072,0.000033552034,0.00024531138,0.000029257606,0.000022868295],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008478025,0.00005345504,0.00007900087,0.0002745557,0.000019458847,0.00006973179,0.00018921553,0.000024691783,0.00060901797],"category_scores_gemma":[0.000009590444,0.000046693774,0.000059936778,0.00083426473,0.000006008897,0.00016412894,0.000014738247,0.000024766941,0.00012904621],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009472334,0.00073921075,0.34065524,0.000009484684,0.000110421584,0.000014018841,0.00008367331,0.00026459637,0.02542311,0.012723299,0.0012143336,0.61875314],"study_design_scores_gemma":[0.0002442078,0.000008714644,0.6962492,0.0000015160865,0.000012155927,1.3640928e-7,0.0000063345437,0.26309967,0.038637944,0.00046016395,0.0011647508,0.000115197785],"about_ca_topic_score_codex":0.0004910926,"about_ca_topic_score_gemma":0.0004687777,"teacher_disagreement_score":0.75252116,"about_ca_system_score_codex":0.000032159587,"about_ca_system_score_gemma":0.0000147458195,"threshold_uncertainty_score":0.666832},"labels":[],"label_agreement":null},{"id":"W2143612262","doi":"10.1109/icassp.2013.6638947","title":"Speech recognition with deep recurrent neural networks","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":8837,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Recurrent neural network; Computer science; Connectionism; TIMIT; Speech recognition; Artificial intelligence; Deep learning; Context (archaeology); Benchmark (surveying); Time delay neural network; Artificial neural network; Hidden Markov model; Pattern recognition (psychology)","score_opus":0.021275216449558917,"score_gpt":0.21530829898896017,"score_spread":0.19403308253940127,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2143612262","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06591433,0.000040165865,0.88780254,0.0019709233,0.0004672232,0.0003925645,5.3667094e-7,0.00051127403,0.04290046],"genre_scores_gemma":[0.5914597,0.00003334468,0.40509075,0.0024415145,0.00018317963,0.00010954921,0.000010492777,0.000017106151,0.0006543544],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99903893,0.00005567944,0.00015342035,0.00029539652,0.00019619045,0.0002603716],"domain_scores_gemma":[0.99930376,0.00008247193,0.000051535044,0.00028005274,0.00015348305,0.00012867346],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0000998259,0.00012274313,0.00011001831,0.00007610119,0.000078417186,0.00026797756,0.00031633512,0.000049498783,0.0018620794],"category_scores_gemma":[0.000019498388,0.00008697183,0.000044764543,0.00029358463,0.000025352134,0.0007312722,0.000060495753,0.00011481655,0.0011173458],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000021553715,0.000033758075,0.00011969787,0.0000015810199,0.0000063390617,0.0000067427072,0.000020557944,0.000007122317,0.0000144245305,0.0001507641,0.0015064527,0.9981304],"study_design_scores_gemma":[0.00033714788,0.00016319139,0.0037693277,0.000021572798,0.000007934969,0.00015701272,0.000059357433,0.9898525,0.0023609458,0.0021049657,0.00082941697,0.00033664808],"about_ca_topic_score_codex":0.00005351136,"about_ca_topic_score_gemma":0.00004821649,"teacher_disagreement_score":0.99779373,"about_ca_system_score_codex":0.000019051839,"about_ca_system_score_gemma":0.000009647426,"threshold_uncertainty_score":0.9996604},"labels":[],"label_agreement":null},{"id":"W2144015346","doi":"10.5281/zenodo.43376","title":"Plsa Enhanced With A Long-Distance Bigram Language Model For Speech Recognition","year":2013,"lang":"en","type":"article","venue":"INFM-OAR (INFN Catania)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Perplexity; Bigram; Language model; Computer science; Probabilistic latent semantic analysis; Topic model; Natural language processing; Word error rate; Artificial intelligence; Speech recognition; Word (group theory); Hidden Markov model; Event (particle physics); Trigram; Linguistics","score_opus":0.02486412488034375,"score_gpt":0.24656600029035372,"score_spread":0.22170187541000996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144015346","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21187502,0.00008469402,0.78224826,0.0006077184,0.00016067298,0.00094146625,0.00008488928,0.00043535486,0.0035618914],"genre_scores_gemma":[0.69525814,0.000025353876,0.30107665,0.001139034,0.00012493314,0.0005813331,0.00008223754,0.000041334057,0.0016709956],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99803936,0.000044702192,0.00034993567,0.0006365684,0.00040694367,0.00052249525],"domain_scores_gemma":[0.99825346,0.00019600945,0.00018519691,0.0007562973,0.00040732708,0.00020171209],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00024979058,0.00028646833,0.00029551276,0.0001650086,0.00017306204,0.00036543744,0.0007104265,0.00014066865,0.00019043346],"category_scores_gemma":[0.00014362078,0.00025391977,0.00011754364,0.0004364189,0.00007650792,0.001121796,0.00008676849,0.000182787,0.0009676347],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006071074,0.00018032924,0.000059578277,0.00008633344,0.00006011367,0.00003142468,0.0018467045,0.000053769894,0.011668595,0.0006563459,0.003536133,0.98175997],"study_design_scores_gemma":[0.002923153,0.0004942644,0.0012254078,0.00036875872,0.00008217391,0.00017893121,0.0006284539,0.61633,0.36252123,0.011644896,0.0018326206,0.0017700975],"about_ca_topic_score_codex":0.00014541233,"about_ca_topic_score_gemma":0.00062918034,"teacher_disagreement_score":0.9799899,"about_ca_system_score_codex":0.00008949454,"about_ca_system_score_gemma":0.00012804434,"threshold_uncertainty_score":0.9999913},"labels":[],"label_agreement":null},{"id":"W2144325519","doi":"10.1109/ccece.2006.277694","title":"Robust Self-Training System for Spoken Query Information Retrieval using Pitch Range Variations","year":2006,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Computer science; Speech recognition; Variation (astronomy); Session (web analytics); Quality (philosophy); Range (aeronautics); Artificial intelligence; Natural language processing; World Wide Web; Engineering","score_opus":0.05296486172370055,"score_gpt":0.23293315386927527,"score_spread":0.17996829214557472,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144325519","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009927948,0.0000058507944,0.97451645,0.00021155806,0.00038451288,0.0003160477,0.0000093462195,0.0005666012,0.014061694],"genre_scores_gemma":[0.25344685,6.548039e-7,0.7461237,0.00014148287,0.00014893994,0.000008972281,0.000013871744,0.0000062517306,0.00010933011],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99905634,0.000037406637,0.00033071885,0.00014873409,0.00021322437,0.00021360404],"domain_scores_gemma":[0.9992379,0.00018019874,0.000127654,0.00020311655,0.00020483017,0.000046331323],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005135362,0.00009827837,0.0001328541,0.00018189063,0.0002303621,0.0003160971,0.0002289955,0.000075793534,0.000024299403],"category_scores_gemma":[0.000057380308,0.00009302788,0.00007873867,0.000352195,0.0000070226906,0.0014334242,0.00003674733,0.00004614186,0.00005464037],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007018041,0.00022408857,0.0012156733,0.00051363825,0.00015351805,0.0000113707265,0.0053449925,0.005239479,0.0016288095,0.9124441,0.004121978,0.06903216],"study_design_scores_gemma":[0.000561551,0.00001912361,0.0011687326,0.000039162634,0.000024087049,0.000044958862,0.00045035433,0.992186,0.002288763,0.0006280121,0.002376949,0.00021231137],"about_ca_topic_score_codex":0.00010594328,"about_ca_topic_score_gemma":0.0000113625365,"teacher_disagreement_score":0.9869465,"about_ca_system_score_codex":0.00013221246,"about_ca_system_score_gemma":0.00009905318,"threshold_uncertainty_score":0.37935668},"labels":[],"label_agreement":null},{"id":"W2144421128","doi":"10.1109/isspa.2010.5605556","title":"Text-independent distributed speaker identification and verification using GMM-UBM speaker models for mobile communications","year":2010,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec; Institut National de la Recherche Scientifique; Université de Moncton; Université du Québec à Montréal","funders":"","keywords":"Computer science; Speech recognition; Speaker recognition; Speaker diarisation; Mixture model; Maximum a posteriori estimation; Hidden Markov model; Speaker identification; Identification (biology); Artificial intelligence; Channel (broadcasting); Pattern recognition (psychology); Maximum likelihood","score_opus":0.053831147825318525,"score_gpt":0.29645053132652527,"score_spread":0.24261938350120674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144421128","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05774803,0.00003546183,0.93923664,0.0008389165,0.00023315678,0.000618687,0.00004957365,0.00016043987,0.001079081],"genre_scores_gemma":[0.79158396,0.000034226654,0.2077714,0.000086751694,0.000035352903,0.00013844736,0.000090259724,0.000011158446,0.00024841854],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99882233,0.000052211304,0.000340286,0.00039155412,0.00019587243,0.00019772872],"domain_scores_gemma":[0.99803185,0.00016825068,0.00014722648,0.0012775504,0.00026636609,0.000108747634],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049469585,0.00012944212,0.00013336673,0.00010801884,0.0003260609,0.00037206773,0.00072967145,0.00010196954,0.000060545517],"category_scores_gemma":[0.00007347561,0.00012500604,0.000063782114,0.00023207668,0.00008911742,0.00084529555,0.00018209833,0.00013734549,0.00004230593],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020810532,0.00059004704,0.00036640494,0.000039380775,0.000070174974,0.0000012299851,0.00084717246,0.0002764764,0.36278468,0.29725152,0.0014313685,0.33632073],"study_design_scores_gemma":[0.00033019827,0.000015528847,0.0026822346,0.000007975878,0.000024292978,0.000025679821,0.00014940857,0.9423687,0.03388615,0.012890052,0.007386627,0.00023318123],"about_ca_topic_score_codex":0.000047343336,"about_ca_topic_score_gemma":0.000110745736,"teacher_disagreement_score":0.9420922,"about_ca_system_score_codex":0.00003738885,"about_ca_system_score_gemma":0.000047662008,"threshold_uncertainty_score":0.50975984},"labels":[],"label_agreement":null},{"id":"W2147094156","doi":"10.1109/asru.2007.4430179","title":"Interpolative variable frame rate transmission of speech features for distributed speech recognition","year":2007,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"","keywords":"Computer science; Speech recognition; Voice activity detection; Speech coding; Word error rate; Linear predictive coding; Codec2; Frame (networking); Speech processing; Artificial intelligence; Computer network","score_opus":0.024571848015133235,"score_gpt":0.2716059338041716,"score_spread":0.24703408578903835,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147094156","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005731674,0.000023706401,0.9792707,0.0004894123,0.00021595562,0.00039117096,0.00007492031,0.0001583427,0.013644136],"genre_scores_gemma":[0.10652672,0.00001189624,0.89208645,0.0003425744,0.00007943845,0.0000134199245,0.000092416296,0.00001309005,0.00083399506],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986846,0.00006695762,0.0003825312,0.00035200725,0.00020510404,0.0003087959],"domain_scores_gemma":[0.99836695,0.00074869476,0.00014320471,0.00025257122,0.00036256717,0.00012601113],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010562632,0.00016250196,0.00024380398,0.00018117158,0.00008863883,0.00007155129,0.00037298273,0.00015565113,0.00038522383],"category_scores_gemma":[0.00024904296,0.00013508511,0.00013245361,0.00051737385,0.000039073348,0.0004118108,0.000043051168,0.00013163222,0.000029450171],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013129866,0.00010905986,0.000028771294,0.000034617013,0.00003586185,0.0000068050767,0.00015057153,6.460661e-7,0.03342684,0.0041324403,0.0015401735,0.9604029],"study_design_scores_gemma":[0.0006818612,0.00017920797,0.0008729584,0.000099909485,0.000021143454,0.000032692024,0.00011656977,0.010065019,0.934486,0.046964217,0.0062358757,0.00024459237],"about_ca_topic_score_codex":0.00004997057,"about_ca_topic_score_gemma":0.000011553819,"teacher_disagreement_score":0.96015835,"about_ca_system_score_codex":0.000042469026,"about_ca_system_score_gemma":0.000042777734,"threshold_uncertainty_score":0.55086106},"labels":[],"label_agreement":null},{"id":"W2147768505","doi":"10.1109/tasl.2011.2134090","title":"Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition","year":2011,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3077,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Microsoft Research; University of Toronto; Microsoft","keywords":"Hidden Markov model; Computer science; Speech recognition; Word error rate; Artificial intelligence; Artificial neural network; Context (archaeology); Mixture model; Deep neural networks; Sentence; Generalization; Phone; Deep learning; Pattern recognition (psychology); Vocabulary; Mathematics","score_opus":0.026434426717621164,"score_gpt":0.25310468969957234,"score_spread":0.22667026298195117,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147768505","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020647129,0.0010172761,0.9761406,0.0001596678,0.00041261237,0.0005434876,0.000033152588,0.00041845307,0.0006275875],"genre_scores_gemma":[0.9024936,0.000058309037,0.09574365,0.0011474402,0.00011346415,0.00012371672,0.000010459632,0.000036026064,0.00027335566],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99809474,0.000101131816,0.00036339226,0.0006283895,0.0002777333,0.00053462124],"domain_scores_gemma":[0.9990306,0.00014127379,0.0001397245,0.0003220957,0.00015456975,0.00021172692],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005294614,0.00029914145,0.0003100841,0.00023932732,0.00047886613,0.00024282192,0.0003321016,0.00018275499,0.00025499237],"category_scores_gemma":[0.000028010765,0.00028193792,0.00018381189,0.00031561428,0.000050204475,0.00077948166,0.0000057618995,0.00031347907,0.000020944448],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012461284,0.00023013308,0.0000057356183,0.00006138495,0.00004951068,0.000066036446,0.002243574,0.000021807631,0.00054577563,0.000009297858,0.000021340675,0.9966208],"study_design_scores_gemma":[0.002931606,0.000523607,0.0001702945,0.00021449926,0.00020801283,0.0006830064,0.0024685941,0.7359142,0.25488648,0.0007828609,0.00020526526,0.0010116248],"about_ca_topic_score_codex":0.000050186478,"about_ca_topic_score_gemma":0.00025576638,"teacher_disagreement_score":0.99560916,"about_ca_system_score_codex":0.000043899367,"about_ca_system_score_gemma":0.00003968916,"threshold_uncertainty_score":0.9999633},"labels":[],"label_agreement":null},{"id":"W2148177126","doi":"10.1109/icassp.2005.1416353","title":"Large Margin HMMs for Speech Recognition","year":2006,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Hidden Markov model; Margin (machine learning); Minimax; Computer science; Pattern recognition (psychology); Optimization problem; Artificial intelligence; Speech recognition; Mathematics; Algorithm; Mathematical optimization; Machine learning","score_opus":0.025622888386847717,"score_gpt":0.24311999577670307,"score_spread":0.21749710738985534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148177126","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009931501,0.00002093976,0.88790244,0.0009840102,0.00027218636,0.00025209197,0.00002162833,0.00033876376,0.10027643],"genre_scores_gemma":[0.08345556,0.0000070611923,0.8999234,0.0015618975,0.00030049763,0.0000948888,0.00006133259,0.000015207342,0.014580195],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991917,0.000022859442,0.00015749793,0.00024894357,0.0001353885,0.00024362595],"domain_scores_gemma":[0.9995027,0.000117654134,0.00003847822,0.00020298015,0.00009636567,0.00004183161],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025106844,0.00008491356,0.00009363227,0.00009131514,0.00009003555,0.000118927375,0.00023859068,0.00005287232,0.0005983108],"category_scores_gemma":[0.000037742193,0.00007580207,0.000085409934,0.00017588615,0.000008843178,0.00031066933,0.000038688973,0.00003625956,0.00073158985],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008685602,0.00022177496,0.00017211608,0.00001443792,0.000009379101,0.00001086532,0.00002645735,2.1769858e-7,0.0013723134,0.031069163,0.09995701,0.86713755],"study_design_scores_gemma":[0.0019168956,0.00011964859,0.0032208834,0.000031654996,0.000017429717,0.00008198587,0.00008746186,0.029686913,0.33258533,0.26485494,0.36671156,0.00068531407],"about_ca_topic_score_codex":0.000027559527,"about_ca_topic_score_gemma":0.00007329449,"teacher_disagreement_score":0.8664523,"about_ca_system_score_codex":0.000019141968,"about_ca_system_score_gemma":0.000016740449,"threshold_uncertainty_score":0.9403351},"labels":[],"label_agreement":null},{"id":"W2148424003","doi":"10.1109/icassp.2004.1326309","title":"A new signal model and identification algorithm for hidden semi-Markov signals","year":2004,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Hidden Markov model; Hidden semi-Markov model; SIGNAL (programming language); Algorithm; Identification (biology); Computer science; Markov model; Markov chain; Maximum-entropy Markov model; Estimation theory; Forward algorithm; Markov process; State (computer science); Constant (computer programming); Pattern recognition (psychology); Mathematics; Artificial intelligence; Variable-order Markov model; Machine learning; Statistics","score_opus":0.026753284819732943,"score_gpt":0.2586929159079327,"score_spread":0.23193963108819976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148424003","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009423632,0.000043705502,0.9958245,0.0014048842,0.0000527931,0.00021415875,0.0000057294856,0.00013160914,0.0013802161],"genre_scores_gemma":[0.039690897,0.000013802115,0.9565282,0.000526548,0.000055322154,0.000030602296,0.000003824414,0.0000070509104,0.0031437706],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991966,0.00001240938,0.00017766016,0.00029701888,0.00016069751,0.00015562917],"domain_scores_gemma":[0.99949056,0.000081365164,0.000049984443,0.00017729972,0.00007744577,0.00012334874],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020313344,0.000089256675,0.00010133653,0.00008251384,0.00008707317,0.000218013,0.00025069545,0.000050007457,0.00006653438],"category_scores_gemma":[0.000019788602,0.00008088758,0.00005217939,0.0001262357,0.0000134414,0.00041886733,0.00004811945,0.000034086195,0.00004100031],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014663669,0.000020427779,0.0000012225383,0.0000031673262,0.000008552212,8.895388e-7,0.00011586134,0.00006497893,0.0050083743,0.005706722,0.0014973956,0.98757094],"study_design_scores_gemma":[0.0004962178,0.000030145216,0.000051097173,0.000011471886,0.000008863875,0.000014020362,0.000024902589,0.8201525,0.06406471,0.114765845,0.00022908703,0.00015114932],"about_ca_topic_score_codex":0.000030486228,"about_ca_topic_score_gemma":0.000008049301,"teacher_disagreement_score":0.9874198,"about_ca_system_score_codex":0.00002601818,"about_ca_system_score_gemma":0.00010146291,"threshold_uncertainty_score":0.32985},"labels":[],"label_agreement":null},{"id":"W2148725087","doi":"10.5281/zenodo.43036","title":"Robust Speech Recognition Under Noisy Environments Using Asymmetric Tapers","year":2012,"lang":"en","type":"article","venue":"INFM-OAR (INFN Catania)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"","keywords":"Mel-frequency cepstrum; Computer science; Speech recognition; Feature extraction; Feature (linguistics); Constraint (computer-aided design); Pattern recognition (psychology); Distortion (music); Cepstrum; Hamming code; Artificial intelligence; Mathematics; Algorithm; Amplifier; Bandwidth (computing); Telecommunications","score_opus":0.10667732456096098,"score_gpt":0.25804151493059035,"score_spread":0.1513641903696294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148725087","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5495193,0.00073745253,0.41422498,0.000838607,0.0032105832,0.00081869506,0.00007871144,0.0004986438,0.030073034],"genre_scores_gemma":[0.8084251,0.00011248322,0.18846132,0.0019081641,0.00049467967,0.000026021915,0.00005060741,0.000055154404,0.0004664479],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9975693,0.00014305442,0.0004109869,0.0005005781,0.0006520142,0.00072405825],"domain_scores_gemma":[0.9985111,0.00020577779,0.00020190899,0.00067744957,0.000055510438,0.000348258],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00062001334,0.00029880187,0.0002688579,0.00045296512,0.00025339558,0.00020145782,0.0006464922,0.00020039591,0.0004697862],"category_scores_gemma":[0.00015929279,0.00031064296,0.00014909374,0.0009426356,0.00007924193,0.0017287584,0.0002443515,0.00025974878,0.003307828],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021049738,0.00065197673,0.005321867,0.00003550885,0.00015758259,0.00005421552,0.000640501,0.000159042,0.018641703,0.00066818687,0.0022617388,0.9713866],"study_design_scores_gemma":[0.005889204,0.0005210994,0.097473286,0.00047462698,0.00065153535,0.0027538966,0.0022125526,0.06413362,0.6625096,0.0064277104,0.14988562,0.0070672403],"about_ca_topic_score_codex":0.000105697945,"about_ca_topic_score_gemma":0.000012384208,"teacher_disagreement_score":0.9643194,"about_ca_system_score_codex":0.00033065965,"about_ca_system_score_gemma":0.000060003695,"threshold_uncertainty_score":0.99993455},"labels":[],"label_agreement":null},{"id":"W2148812765","doi":"10.1006/csla.1999.0136","title":"A path-stack algorithm for optimizing dynamic regimes in a statistical hidden dynamic model of speech","year":2000,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Hidden Markov model; Utterance; Speech recognition; Stack (abstract data type); Path (computing); Phone; Reduction (mathematics); Set (abstract data type); Segmentation; Algorithm; Artificial intelligence; Pattern recognition (psychology)","score_opus":0.013258436234086577,"score_gpt":0.2679317228246664,"score_spread":0.2546732865905798,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148812765","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036377884,0.00017782477,0.9610587,0.00024701792,0.00018648377,0.00051229063,0.00012170971,0.00020075259,0.0011173838],"genre_scores_gemma":[0.024504276,0.00004897817,0.97378933,0.0002568028,0.00005947689,0.000039499675,0.000051344177,0.000037080157,0.0012132298],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976202,0.00010725739,0.000587945,0.00072255154,0.00039090865,0.0005710861],"domain_scores_gemma":[0.9986186,0.00024693698,0.000132993,0.000748742,0.00009648323,0.00015626758],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00040081335,0.00031279487,0.0005353741,0.0003033039,0.00006809785,0.00014909286,0.0010226731,0.00014754075,0.00026031586],"category_scores_gemma":[0.000028836503,0.00031033752,0.00017561538,0.00040093518,0.00007899398,0.00035576342,0.00018906398,0.00022065452,0.00006613815],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015780834,0.000137913,0.0000051226466,0.00004656119,0.000024418281,0.0002284297,0.0011162563,0.0003163192,0.00027221916,0.00045585423,0.00031228526,0.9970688],"study_design_scores_gemma":[0.0009268452,0.00012143569,0.00011766316,0.000101024176,0.000014773281,0.00010639034,0.00008634266,0.9948061,0.00084171735,0.0024167066,0.00010320735,0.00035777566],"about_ca_topic_score_codex":0.00005844087,"about_ca_topic_score_gemma":0.000048278253,"teacher_disagreement_score":0.9967111,"about_ca_system_score_codex":0.00012811042,"about_ca_system_score_gemma":0.00011132272,"threshold_uncertainty_score":0.99993485},"labels":[],"label_agreement":null},{"id":"W2150722744","doi":"10.1109/cihsps.2005.1500624","title":"Speech accent identification with vocal tract variation trajectory tracking using neural networks","year":2005,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Stress (linguistics); Computer science; Speech recognition; Vocal tract; Artificial neural network; Identification (biology); Variation (astronomy); Speech processing; Trajectory; Speaker recognition; Artificial intelligence","score_opus":0.04051435498512875,"score_gpt":0.26696526079216515,"score_spread":0.2264509058070364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2150722744","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19268857,0.00001819614,0.80527645,0.00034549282,0.00019994,0.00013626246,3.8304583e-7,0.00019376112,0.0011409672],"genre_scores_gemma":[0.8894313,0.0000042326174,0.10988045,0.00034292936,0.00023220122,0.0000050498,0.00000247256,0.000010248546,0.00009114988],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987496,0.000083008854,0.00027836935,0.00034864343,0.00030081958,0.00023954436],"domain_scores_gemma":[0.99932545,0.00008131623,0.00012516261,0.00028567953,0.00010034252,0.000082016486],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034057238,0.00013046362,0.00011959701,0.000119987024,0.0001470416,0.0003959805,0.00031947004,0.00007043444,0.00016135516],"category_scores_gemma":[0.000016137406,0.000109336346,0.000058157402,0.00033506233,0.00001924195,0.0013321887,0.000024782705,0.00013083813,0.000030001995],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011300285,0.00017843979,0.00042028344,0.0000036265487,0.000015385198,0.000011740836,0.0003505567,0.018443288,0.003150319,0.0009157554,0.00004548554,0.97645384],"study_design_scores_gemma":[0.00021031155,0.000020155952,0.038159728,0.000008880939,0.000013753505,0.00011046264,0.000031939948,0.9545352,0.0065726857,0.000045235895,0.00012804508,0.00016363147],"about_ca_topic_score_codex":0.000040654675,"about_ca_topic_score_gemma":0.000058054942,"teacher_disagreement_score":0.97629017,"about_ca_system_score_codex":0.000101720085,"about_ca_system_score_gemma":0.000033651,"threshold_uncertainty_score":0.44586068},"labels":[],"label_agreement":null},{"id":"W2151120341","doi":"","title":"Automatic Syllabification with Structured SVMs for Letter-to-Phoneme Conversion","year":2008,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":61,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Syllabification; Computer science; Discriminative model; Artificial intelligence; Word error rate; Speech recognition; Natural language processing; German; Syllable; Linguistics","score_opus":0.024311775966838128,"score_gpt":0.22514287289706725,"score_spread":0.20083109693022913,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151120341","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17735855,0.0000027265778,0.8176207,0.0029840106,0.0001565115,0.00037669955,0.000002141112,0.0002874038,0.0012112355],"genre_scores_gemma":[0.5381365,0.0000012557908,0.4583394,0.0027410733,0.00004367272,0.000037431146,0.000003897901,0.000006352425,0.0006904798],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992802,0.00002138055,0.00012329195,0.00024446181,0.00018191937,0.00014874458],"domain_scores_gemma":[0.99939555,0.00008728313,0.000044824515,0.00029556244,0.0000942599,0.00008254835],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007900781,0.00008694246,0.00010225883,0.00009606023,0.00014042604,0.00004579577,0.00028483212,0.000036920814,0.00021514199],"category_scores_gemma":[0.00002991704,0.0000640589,0.000033350476,0.0002323717,0.000022962042,0.00019718568,0.000026547981,0.00003154771,0.00019208257],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008702122,0.00022750605,0.001299198,0.00014213755,0.00010519448,0.000044299002,0.003614974,0.00004297474,0.047129292,0.0123432055,0.23936528,0.6955989],"study_design_scores_gemma":[0.002774629,0.0006415426,0.036991168,0.00007403331,0.000029826173,0.00029420384,0.00017073998,0.38937807,0.50892204,0.0017086633,0.05799192,0.0010231991],"about_ca_topic_score_codex":0.0000085772745,"about_ca_topic_score_gemma":0.0000055131877,"teacher_disagreement_score":0.6945757,"about_ca_system_score_codex":0.000026306625,"about_ca_system_score_gemma":0.000032069864,"threshold_uncertainty_score":0.26122463},"labels":[],"label_agreement":null},{"id":"W2151936436","doi":"10.1109/tasl.2010.2072499","title":"Articulatory Knowledge in the Recognition of Dysarthric Speech","year":2010,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":105,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Vocal tract; Discriminative model; Dysarthria; Speech recognition; Computer science; Speech production; Manner of articulation; Generative grammar; Artificial intelligence; Natural language processing; Psychology","score_opus":0.017474742947774666,"score_gpt":0.2601078714734097,"score_spread":0.242633128525635,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151936436","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75985986,0.00040290153,0.23512432,0.00038194357,0.00028351118,0.00022024826,0.000006587151,0.00011127068,0.003609348],"genre_scores_gemma":[0.97266966,0.000029983314,0.026872333,0.00027211366,0.00004215398,0.00002342084,9.120265e-7,0.000009791057,0.000079631995],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99894613,0.00010259283,0.00025265015,0.00027801679,0.00020966298,0.00021095476],"domain_scores_gemma":[0.9993301,0.00017818769,0.000084742904,0.00026776097,0.00007641885,0.00006276715],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00062117976,0.00013998053,0.00016295376,0.0002704214,0.00015084342,0.00011249657,0.0002687574,0.00009608842,0.00010068188],"category_scores_gemma":[0.00002448338,0.000106206135,0.00006493639,0.00060588506,0.00008539064,0.0003489258,0.000002440863,0.00039995692,0.00004477305],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008119324,0.00019206514,0.000012922744,0.000038369893,0.000005090474,0.000025552807,0.0026051847,0.0000015788708,0.022979898,0.000015302212,0.000014329121,0.9741016],"study_design_scores_gemma":[0.0010348285,0.00013617032,0.0014618265,0.00026316545,0.000045718036,0.0005849483,0.0029105481,0.016408686,0.97534955,0.00096214766,0.00038346127,0.00045897652],"about_ca_topic_score_codex":0.000027238864,"about_ca_topic_score_gemma":0.00044477268,"teacher_disagreement_score":0.9736426,"about_ca_system_score_codex":0.000012307914,"about_ca_system_score_gemma":0.00006352256,"threshold_uncertainty_score":0.43309602},"labels":[],"label_agreement":null},{"id":"W2154037907","doi":"10.1109/icassp.1995.479399","title":"Analysis of acoustic-phonetic variations in fluent speech using TIMIT","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"TIMIT; Speech recognition; Computer science; Mel-frequency cepstrum; Context (archaeology); Phonetics; Variance (accounting); Cepstrum; Artificial intelligence; Hidden Markov model; Feature extraction; Linguistics; Biology","score_opus":0.04996774319873785,"score_gpt":0.26251441654567603,"score_spread":0.2125466733469382,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154037907","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10838934,0.00002046579,0.8799917,0.00020941332,0.00007406598,0.00006786353,0.0000028269376,0.000045750057,0.011198554],"genre_scores_gemma":[0.79091775,0.000009613491,0.20865555,0.00013165588,0.0000066767766,0.0000018210214,6.3739793e-7,0.0000023802725,0.0002738814],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99920475,0.00004847179,0.00024299162,0.0001845649,0.00018907011,0.00013015568],"domain_scores_gemma":[0.9994156,0.00013476225,0.00005773958,0.00029046426,0.00005943262,0.000042039374],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00016115174,0.0000633582,0.00017294404,0.0006231443,0.000028249788,0.000038778006,0.00024709819,0.00003560166,0.0030639519],"category_scores_gemma":[0.00007015081,0.00005932149,0.00008743084,0.0020852191,0.000015359494,0.00013072918,0.000050910192,0.00004053219,0.00005909668],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000062273507,0.0022243396,0.03874136,0.000041322564,0.0015722665,0.00012494021,0.003832758,0.056463614,0.046086125,0.011605663,0.0011357967,0.8381656],"study_design_scores_gemma":[0.00008854384,0.0000070784895,0.012211878,0.0000050629524,0.00010579079,0.00000288921,0.00002237791,0.98458123,0.0027306837,0.00014289052,0.000028522369,0.00007303843],"about_ca_topic_score_codex":0.00017024614,"about_ca_topic_score_gemma":0.00018344849,"teacher_disagreement_score":0.92811763,"about_ca_system_score_codex":0.000034393393,"about_ca_system_score_gemma":0.000009906495,"threshold_uncertainty_score":0.9978474},"labels":[],"label_agreement":null},{"id":"W2154162514","doi":"10.1109/asru.2007.4430082","title":"Exploiting complementary aspects of phonological features in automatic speech recognition","year":2007,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"University of Edinburgh","keywords":"Computer science; Mel-frequency cepstrum; Speech recognition; Feature (linguistics); Phone; Pattern recognition (psychology); Decoding methods; Artificial intelligence; Feature extraction; Frame (networking); Algorithm","score_opus":0.05129818448945806,"score_gpt":0.28484618720485627,"score_spread":0.23354800271539822,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154162514","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8366003,0.00002529347,0.059142206,0.00051988644,0.00015736159,0.00020378105,0.0000024710555,0.00024992556,0.10309876],"genre_scores_gemma":[0.69364244,0.000004585509,0.3059292,0.00037011987,0.000020905492,0.000003432903,0.0000048800725,0.0000031766026,0.000021273563],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99888754,0.000058288675,0.00035676442,0.00022749032,0.00022298135,0.00024695048],"domain_scores_gemma":[0.9992774,0.00035027694,0.00009006401,0.00017810884,0.000050068764,0.000054081163],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068351283,0.00009450946,0.0001698846,0.00025829906,0.000035442965,0.000031207408,0.0002984441,0.00005406151,0.0007779584],"category_scores_gemma":[0.000115903924,0.000081458784,0.00005313252,0.0004022044,0.000030095944,0.00026162068,0.00009139822,0.000106017964,0.00008271446],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000041544654,0.000113388836,0.0006789797,0.000011726196,0.0000064595533,0.0000657332,0.00015082558,1.159817e-7,0.0028399294,0.0034176174,0.0002104087,0.99250066],"study_design_scores_gemma":[0.0010465502,0.0001718953,0.13617803,0.00015708241,0.0000076759625,0.00019798032,0.0017057154,0.005419151,0.7933435,0.061232504,0.00016886824,0.00037103507],"about_ca_topic_score_codex":0.000111885565,"about_ca_topic_score_gemma":0.00035926857,"teacher_disagreement_score":0.9921296,"about_ca_system_score_codex":0.000043412398,"about_ca_system_score_gemma":0.000018144425,"threshold_uncertainty_score":0.8518099},"labels":[],"label_agreement":null},{"id":"W2154909174","doi":"10.1109/icassp.2004.1326054","title":"Estimating vocal-tract area functions from vowel sound signals over closed glottal phases","year":2004,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Vocal tract; Speech recognition; Vowel; Computer science; Acoustics; Glottis; Ideal (ethics); Mathematics; Larynx; Medicine; Physics; Anatomy","score_opus":0.041037723420219954,"score_gpt":0.27744566829149025,"score_spread":0.23640794487127031,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154909174","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24629207,0.000023473713,0.7408335,0.00040611377,0.00040742956,0.00008961422,0.000020585956,0.00036435176,0.011562876],"genre_scores_gemma":[0.77415967,0.0000010699227,0.22434473,0.0008910189,0.00014704624,0.000012177226,0.000013370989,0.000009149489,0.0004217671],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987116,0.000032357028,0.0002699112,0.00040458667,0.000317083,0.00026446834],"domain_scores_gemma":[0.9989743,0.00037680875,0.00008425877,0.00035289594,0.000067740926,0.0001439533],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000130665,0.0001682413,0.00017451623,0.000098417775,0.00022045903,0.00034714583,0.00035279413,0.00007146909,0.0025885834],"category_scores_gemma":[0.00016643842,0.00014496723,0.000134508,0.00026085527,0.000042597756,0.0006692038,0.0000718006,0.0001117416,0.0006620089],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007219846,0.004903843,0.004367959,0.000031298834,0.00052317616,0.0005696374,0.0031013992,0.00858598,0.0636288,0.012066872,0.02854146,0.8736074],"study_design_scores_gemma":[0.0073508164,0.0005514697,0.03609255,0.00032804758,0.00018218599,0.00026226023,0.00060614443,0.53502136,0.11762219,0.29593366,0.003568272,0.002481023],"about_ca_topic_score_codex":0.00036927804,"about_ca_topic_score_gemma":0.000092705886,"teacher_disagreement_score":0.87112635,"about_ca_system_score_codex":0.000056521483,"about_ca_system_score_gemma":0.00007763789,"threshold_uncertainty_score":0.9983232},"labels":[],"label_agreement":null},{"id":"W2155973539","doi":"10.1109/icassp.2006.1660066","title":"Speech Feature Estimation Under the Presence of Noise with a Switching Linear Dynamic Model","year":2006,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Feature (linguistics); Computer science; Speech recognition; Feature vector; Parametric statistics; Noise (video); Linear model; Compensation (psychology); Speech processing; Pattern recognition (psychology); Artificial intelligence; Algorithm; Mathematics; Machine learning","score_opus":0.011837635991456565,"score_gpt":0.23982426095168966,"score_spread":0.2279866249602331,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155973539","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.065101154,0.000013390407,0.9267195,0.0026704543,0.000022854969,0.00011629995,0.0000010198015,0.000082950435,0.005272395],"genre_scores_gemma":[0.5795749,0.0000013373788,0.41917595,0.00013796565,0.0000067109268,0.000003954269,8.8683214e-7,0.0000037187374,0.001094595],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999287,0.00002814423,0.000113306065,0.00018215536,0.00026767456,0.000121729325],"domain_scores_gemma":[0.99937284,0.000114534494,0.00006903177,0.00033876192,0.000082074366,0.000022763621],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015221242,0.00008562404,0.00008762432,0.000052662166,0.000079543555,0.00006526845,0.00038137886,0.000039033486,0.000011402787],"category_scores_gemma":[0.000015359923,0.00004774093,0.000034307453,0.0002483364,0.000027380089,0.00029066892,0.000054188953,0.000092937466,0.000014123385],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048341466,0.0003410646,0.0002867201,0.000060230333,0.000051950912,0.000018879435,0.00065024325,0.5942551,0.022281583,0.11223287,0.0020861453,0.26768687],"study_design_scores_gemma":[0.00011068195,0.000014091937,0.00092499034,0.000021645757,0.000005884197,0.000022687245,0.000034120003,0.98283064,0.006096124,0.009853236,0.00001109475,0.000074792035],"about_ca_topic_score_codex":0.00009794161,"about_ca_topic_score_gemma":0.00016168195,"teacher_disagreement_score":0.51447374,"about_ca_system_score_codex":0.00001701174,"about_ca_system_score_gemma":0.00004767577,"threshold_uncertainty_score":0.19468187},"labels":[],"label_agreement":null},{"id":"W2157458051","doi":"10.1109/icassp.1988.196631","title":"Modeling acoustic-phonetic detail in an HMM-based large vocabulary speech recognizer","year":2003,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Hidden Markov model; Computer science; Speech recognition; Word (group theory); Vocabulary; Context (archaeology); Vowel; Set (abstract data type); Artificial intelligence; Duration (music); Natural language processing; Acoustics; Linguistics","score_opus":0.03335114007634879,"score_gpt":0.2593127218804179,"score_spread":0.22596158180406908,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2157458051","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2122192,0.000043229644,0.7793927,0.00016400705,0.00020474449,0.00015794566,0.0000017929821,0.00020577296,0.007610585],"genre_scores_gemma":[0.72356117,0.0000071203153,0.27468842,0.0014503491,0.000017794888,0.000016437969,0.0000032731195,0.000015080131,0.0002403555],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99805975,0.00023478984,0.00034702016,0.0005458502,0.0003181581,0.000494447],"domain_scores_gemma":[0.9989672,0.00011157724,0.00003664811,0.0005808268,0.000118529344,0.00018525959],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008083299,0.00019240694,0.00021941875,0.0002803964,0.00009391868,0.000171756,0.00048951665,0.000121873716,0.00096995314],"category_scores_gemma":[0.0001989391,0.00018080248,0.00007745373,0.0005604493,0.000016540203,0.0004556596,0.000045416495,0.00018324354,0.00043509094],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001172924,0.0052093626,0.015477813,0.00016183082,0.00008858526,0.0016466206,0.0016759025,0.049207117,0.028881764,0.012951917,0.0017133658,0.8828684],"study_design_scores_gemma":[0.0007335047,0.0000472146,0.00018051041,0.000023526349,0.000006713301,0.000023115166,0.0001009784,0.9799303,0.01648965,0.001933671,0.00023389986,0.00029694775],"about_ca_topic_score_codex":0.00003936131,"about_ca_topic_score_gemma":0.0005889198,"teacher_disagreement_score":0.93072313,"about_ca_system_score_codex":0.00005013715,"about_ca_system_score_gemma":0.0001385391,"threshold_uncertainty_score":0.9999433},"labels":[],"label_agreement":null},{"id":"W2159112514","doi":"10.1109/tasl.2007.906178","title":"Approximate Test Risk Bound Minimization Through Soft Margin Estimation","year":2007,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"York University","keywords":"Discriminative model; Margin (machine learning); Computer science; Hidden Markov model; Artificial intelligence; Machine learning; Pattern recognition (psychology); Statistical learning theory; Support vector machine; Speech recognition","score_opus":0.012978543650113633,"score_gpt":0.25853970575772117,"score_spread":0.24556116210760753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159112514","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016080573,0.00032018992,0.9808987,0.0002722071,0.00016820451,0.00019665988,0.000013781037,0.00038341698,0.0016663088],"genre_scores_gemma":[0.64414304,0.00006913816,0.35498512,0.00036832056,0.000045035264,0.000013421989,0.0000042903066,0.0000191285,0.00035248723],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985912,0.000049969687,0.0003026994,0.0004266467,0.00029599154,0.00033352265],"domain_scores_gemma":[0.9991077,0.00028453796,0.00016692972,0.00024442517,0.00008487423,0.00011148947],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045861947,0.00020642985,0.000179314,0.00020798456,0.0005319597,0.00037731172,0.00020001538,0.00011469834,0.00008261747],"category_scores_gemma":[0.000073365,0.00019446631,0.00006222538,0.0005433591,0.00007020373,0.0009152896,0.0000030090307,0.00023551304,0.000043778982],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017038083,0.00013493809,0.000024616407,0.000052566455,0.000010770937,0.000027694827,0.0019282005,0.00016719902,0.0015314023,0.00001742244,0.000037458005,0.9960507],"study_design_scores_gemma":[0.0010688597,0.00014614165,0.00047236175,0.0002438761,0.000087399356,0.0002957533,0.0012815488,0.563399,0.4304436,0.0014351022,0.00046454958,0.00066179736],"about_ca_topic_score_codex":0.000048769445,"about_ca_topic_score_gemma":0.00008254035,"teacher_disagreement_score":0.9953889,"about_ca_system_score_codex":0.00005547924,"about_ca_system_score_gemma":0.000052784802,"threshold_uncertainty_score":0.7930106},"labels":[],"label_agreement":null},{"id":"W2160815625","doi":"10.1109/msp.2012.2205597","title":"Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups","year":2012,"lang":"en","type":"article","venue":"IEEE Signal Processing Magazine","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":10313,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; University of Toronto","funders":"","keywords":"Hidden Markov model; Speech recognition; Computer science; Mixture model; Artificial neural network; Margin (machine learning); Deep neural networks; Pattern recognition (psychology); Frame (networking); Artificial intelligence; Acoustic model; Gaussian; Speech processing; Machine learning","score_opus":0.20839778899800224,"score_gpt":0.34057804277739956,"score_spread":0.13218025377939732,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160815625","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02031341,0.00091159774,0.97658414,0.0005289396,0.00025958917,0.0005153987,0.0000038177827,0.00006613872,0.0008169915],"genre_scores_gemma":[0.95345956,0.000018053377,0.045555107,0.00023819198,0.0005299222,0.000111210495,0.000006930224,0.000023289871,0.00005775664],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976826,0.00026596125,0.00051262253,0.00034674595,0.00050276134,0.0006893348],"domain_scores_gemma":[0.99824965,0.0006515458,0.00014662708,0.00027457112,0.0005579449,0.00011968219],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002976074,0.00017692191,0.00027109688,0.00025542875,0.00026509838,0.0002093916,0.0007222341,0.00010894107,0.000059035287],"category_scores_gemma":[0.00021003299,0.0001341379,0.00010064139,0.0010086538,0.00008635533,0.00096653687,0.0000953727,0.00040009434,0.000035943354],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055932513,0.00012115429,0.000046115812,0.00011927735,0.000007951021,0.000006334105,0.00044391965,0.009850288,0.002607016,0.0000173319,0.00036490004,0.9863598],"study_design_scores_gemma":[0.00037200144,0.00006175757,0.000113276445,0.00015319417,0.000013121415,0.000049299895,0.000077996134,0.99487287,0.0012298499,0.0028103392,0.00007454011,0.00017176053],"about_ca_topic_score_codex":0.000006559229,"about_ca_topic_score_gemma":0.000051288283,"teacher_disagreement_score":0.986188,"about_ca_system_score_codex":0.000053654137,"about_ca_system_score_gemma":0.00007204313,"threshold_uncertainty_score":0.5469985},"labels":[],"label_agreement":null},{"id":"W2160978380","doi":"10.1109/icassp.2007.366915","title":"Integration of Multiple Feature Sets for Reducing Ambiguity in ASR","year":2007,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"University of Edinburgh","keywords":"Mel-frequency cepstrum; Hidden Markov model; Speech recognition; Computer science; Ambiguity; Feature (linguistics); Pattern recognition (psychology); Phone; Cepstrum; Feature extraction; Artificial intelligence; Artificial neural network","score_opus":0.044685774133151814,"score_gpt":0.30616157936479627,"score_spread":0.26147580523164443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160978380","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16119729,0.000011363298,0.83263284,0.00049166783,0.00013945978,0.00015759424,0.0000019458719,0.000045076984,0.0053227735],"genre_scores_gemma":[0.64363116,0.0000017292053,0.3560187,0.00009933933,0.000010938921,0.0000037557747,0.0000019726601,0.0000017915747,0.0002306027],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995055,0.000014856079,0.00013797112,0.00014145188,0.00008783977,0.000112343274],"domain_scores_gemma":[0.9995013,0.00021150369,0.000043148266,0.00014406009,0.00007228563,0.00002770067],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000523129,0.000047697697,0.00008213403,0.00011308924,0.000021731712,0.000014247464,0.00015949726,0.00005109467,0.000014416958],"category_scores_gemma":[0.00027228013,0.000039666153,0.000039928877,0.00020437117,0.000009218819,0.00016348495,0.000022970149,0.00004893753,0.000004041208],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014978697,0.00006548286,0.00068242534,0.000009925606,0.0000029973296,0.0000016112189,0.00043375877,0.0000033901083,0.043354217,0.002565611,0.0016585975,0.951207],"study_design_scores_gemma":[0.00047844215,0.000049598846,0.051646337,0.00005149387,0.0000019218405,0.000005329535,0.0002212675,0.081174225,0.86293507,0.0022811224,0.0010377839,0.00011743355],"about_ca_topic_score_codex":0.000115461604,"about_ca_topic_score_gemma":0.000789725,"teacher_disagreement_score":0.95108956,"about_ca_system_score_codex":0.000024859146,"about_ca_system_score_gemma":0.000016590424,"threshold_uncertainty_score":0.16175388},"labels":[],"label_agreement":null},{"id":"W2161345650","doi":"10.1109/isimp.2004.1434042","title":"ARMA lattice model for phoneme feature extraction","year":2005,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Mel-frequency cepstrum; Speech recognition; Computer science; Feature extraction; Autoregressive–moving-average model; Pattern recognition (psychology); Cepstrum; Hidden Markov model; Vowel; Autoregressive model; Noise (video); Artificial intelligence; Mathematics; Statistics","score_opus":0.041991741007474694,"score_gpt":0.29348150939653395,"score_spread":0.25148976838905923,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2161345650","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011946623,0.000020110088,0.9644295,0.011133244,0.00011978304,0.000110324836,0.0000019401157,0.00020209103,0.022788368],"genre_scores_gemma":[0.066526316,0.00000981111,0.90304863,0.0026188146,0.00012931132,0.000025975325,0.0000017065877,0.0000055046767,0.02763392],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99948287,0.000009411141,0.000078714875,0.00018271817,0.000108740554,0.00013757448],"domain_scores_gemma":[0.9996086,0.00006478503,0.000028836297,0.00018135725,0.00006231632,0.000054146276],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000117551106,0.000065156804,0.000062492654,0.000048536047,0.00007472671,0.00008174255,0.0002051763,0.00005135891,0.000113656686],"category_scores_gemma":[0.000027012824,0.000055828616,0.00005834008,0.00008687641,0.000006186899,0.0005066959,0.000021637994,0.000054459873,0.00021802215],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009234618,0.00009210364,0.0000043259183,0.0000061105875,0.000010298825,9.595014e-7,0.00019468367,0.00035922934,0.003403249,0.020497885,0.08248565,0.8929363],"study_design_scores_gemma":[0.0001679181,0.0000075203143,0.000046953384,0.0000024626127,0.0000037909022,0.0000124573935,0.000011511388,0.93070775,0.018526085,0.0018254037,0.04860261,0.00008554053],"about_ca_topic_score_codex":0.0000022050751,"about_ca_topic_score_gemma":0.000020886482,"teacher_disagreement_score":0.9303485,"about_ca_system_score_codex":0.000021998185,"about_ca_system_score_gemma":0.000021237083,"threshold_uncertainty_score":0.28023064},"labels":[],"label_agreement":null},{"id":"W2162638453","doi":"10.1109/icassp.2012.6289084","title":"Facilitating open vocabulary spoken term detection using a multiple pass hybrid search algorithm","year":2012,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Speech recognition; Vocabulary; Term (time); Word (group theory); Artificial intelligence; Artificial neural network; Pattern recognition (psychology); Natural language processing; Mathematics","score_opus":0.07957440462671649,"score_gpt":0.3096826233278061,"score_spread":0.2301082187010896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2162638453","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24914753,0.000020702279,0.7479469,0.000046309255,0.000244893,0.00023464527,0.0000050938884,0.00012969709,0.0022242367],"genre_scores_gemma":[0.5800467,0.0000012809062,0.41952688,0.0001332307,0.000070331625,0.000012719556,0.0000018077211,0.0000070591786,0.00019999214],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99862075,0.00016399,0.00020720038,0.00030004827,0.00027871906,0.00042929142],"domain_scores_gemma":[0.9990583,0.00029114037,0.000045578792,0.00034190965,0.00008285718,0.00018022273],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008174015,0.00012702783,0.00014939619,0.00012616857,0.00026635785,0.00036762492,0.00066601427,0.000040902698,0.0001315635],"category_scores_gemma":[0.00012260729,0.0001151911,0.00006402382,0.00024699408,0.00002565959,0.0015857029,0.00054145866,0.0001230878,0.0002549556],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000025858317,0.000055359505,0.0013682118,0.000005536586,0.000012543952,0.000006723403,0.00043199825,0.0000029443613,0.005800303,0.000023354536,0.000027404049,0.992263],"study_design_scores_gemma":[0.0003516656,0.00003097379,0.0042433976,0.000019465708,0.0000058845917,0.00014667616,0.00046101975,0.7387526,0.25500378,0.00007996927,0.00064876926,0.00025580238],"about_ca_topic_score_codex":0.0005069754,"about_ca_topic_score_gemma":0.000018122275,"teacher_disagreement_score":0.99200726,"about_ca_system_score_codex":0.000082502076,"about_ca_system_score_gemma":0.00003814359,"threshold_uncertainty_score":0.46973565},"labels":[],"label_agreement":null},{"id":"W2162965424","doi":"10.1109/tasl.2008.925882","title":"A Constrained Line Search Optimization Method for Discriminative Training of HMMs","year":2008,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Discriminative model; Hidden Markov model; Computer science; Pattern recognition (psychology); Metric (unit); Optimization problem; Artificial intelligence; Benchmark (surveying); Gaussian; Divergence (linguistics); Speech recognition; Algorithm; Engineering","score_opus":0.05546290634126556,"score_gpt":0.3191860795479861,"score_spread":0.26372317320672056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2162965424","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004118424,0.00015682544,0.99442106,0.00029832355,0.00006387135,0.000247446,0.000027392904,0.00010850227,0.0005581492],"genre_scores_gemma":[0.43208435,0.000026558495,0.56752235,0.000111867,0.000018011908,0.00002235264,0.0000021921524,0.000009174205,0.00020314215],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989514,0.000082411985,0.00023987112,0.00030714914,0.00020320437,0.00021599606],"domain_scores_gemma":[0.9992302,0.0002881153,0.000090487105,0.0001350039,0.00016530794,0.000090891204],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003751541,0.00014005347,0.00023385101,0.00023730271,0.00029343434,0.00005229045,0.00015643313,0.00006969975,0.000048809306],"category_scores_gemma":[0.000039541163,0.00012621058,0.000082630366,0.00035499074,0.0001080947,0.00032272565,0.0000019855133,0.00013366315,0.0000012108851],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035899033,0.000096672375,7.1970607e-7,0.000077133554,0.000023096403,0.000014691603,0.012771312,0.0026211406,0.006851532,0.000027557639,0.0000048593397,0.9774754],"study_design_scores_gemma":[0.0006836986,0.00015656152,0.000007808798,0.00010426129,0.00002636336,0.00019381267,0.0029035655,0.62637013,0.36931235,0.000064812535,0.000011046557,0.00016560836],"about_ca_topic_score_codex":0.000018950801,"about_ca_topic_score_gemma":0.000010452298,"teacher_disagreement_score":0.97730976,"about_ca_system_score_codex":0.000021518927,"about_ca_system_score_gemma":0.00012695156,"threshold_uncertainty_score":0.5146718},"labels":[],"label_agreement":null},{"id":"W2163376162","doi":"10.1109/icassp.1997.596213","title":"Speaker adaptation experiments using nonstationary-state hidden Markov models: a MAP approach","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Hidden Markov model; Polynomial; Adaptation (eye); Computer science; Gaussian; Speech recognition; Pattern recognition (psychology); State (computer science); Algorithm; Artificial intelligence; Mathematics","score_opus":0.1370463160265479,"score_gpt":0.2604941524964074,"score_spread":0.12344783646985949,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163376162","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0050540254,0.00008490859,0.9088752,0.00020024045,0.0001331396,0.00016851579,0.0000026755208,0.00016880497,0.085312486],"genre_scores_gemma":[0.18067199,0.000017012551,0.81540555,0.00037911828,0.000026080608,0.000020619525,0.000004883885,0.000010894912,0.0034638376],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987764,0.00007478416,0.00022580908,0.00035610862,0.0003425878,0.00022432541],"domain_scores_gemma":[0.99942595,0.000044734647,0.00006918194,0.0002817637,0.00008414628,0.000094232615],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012547344,0.0001333758,0.00011636867,0.00014622604,0.000117346484,0.00016932239,0.00030158565,0.000039056158,0.00065108686],"category_scores_gemma":[0.000007287487,0.00012438743,0.000060350052,0.0002362533,0.00002533159,0.0010389008,0.000056254183,0.000056845205,0.0003044276],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014313231,0.0006163299,0.00004697269,0.000023822227,0.00007574322,0.00003818156,0.009881041,0.0029035206,0.0010819508,0.01407384,0.00657912,0.9646652],"study_design_scores_gemma":[0.00024101295,0.0000111424215,0.000024308343,0.000008316262,0.0000037485247,0.000022701986,0.00037701117,0.9950351,0.0010205279,0.002695546,0.00038619665,0.00017439335],"about_ca_topic_score_codex":0.000055113444,"about_ca_topic_score_gemma":0.000002766912,"teacher_disagreement_score":0.9921316,"about_ca_system_score_codex":0.000058714442,"about_ca_system_score_gemma":0.000021157293,"threshold_uncertainty_score":0.71289444},"labels":[],"label_agreement":null},{"id":"W2163786726","doi":"10.1007/s11265-015-1012-6","title":"Speaker Adaptation of Hybrid NN/HMM Model for Speech Recognition Based on Singular Value Decomposition","year":2015,"lang":"en","type":"article","venue":"Journal of Signal Processing Systems","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Speech recognition; Singular value decomposition; TIMIT; Hidden Markov model; Adaptation (eye); Vocabulary; Speaker recognition; Pattern recognition (psychology); Artificial intelligence; Artificial neural network; Task (project management)","score_opus":0.08558740047888537,"score_gpt":0.293905759405991,"score_spread":0.20831835892710565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163786726","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039732646,0.00018617765,0.9588892,0.00018664579,0.00033528285,0.0002352688,0.000010660663,0.00003237701,0.00039177906],"genre_scores_gemma":[0.77911276,0.0000017662298,0.22053312,0.00010058996,0.00019939872,0.0000062675754,0.000007505947,0.000015150371,0.000023464478],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977693,0.0001655016,0.000851067,0.00021203863,0.0008171323,0.00018494003],"domain_scores_gemma":[0.9965522,0.00018785556,0.0012178939,0.00013412813,0.0017485399,0.00015937362],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019593155,0.00016093095,0.00037090987,0.00040184168,0.00009769736,0.00023329347,0.00030769178,0.00006487817,0.0000028536767],"category_scores_gemma":[0.0001608496,0.00014010315,0.00016450741,0.00023279186,0.000028331457,0.00092021027,0.000012622667,0.00013878963,0.0000069241223],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005603574,0.0005519521,0.000030908257,0.00045920975,0.000057006157,0.000063614934,0.00073006377,0.34150255,0.008323055,0.00019025082,0.00094110944,0.64658993],"study_design_scores_gemma":[0.0010705043,0.00050486776,0.000006450006,0.0011877253,0.00004745525,0.00025887103,0.00015425595,0.96675,0.026410034,0.0033745542,0.000075885226,0.00015937322],"about_ca_topic_score_codex":0.000009597158,"about_ca_topic_score_gemma":5.245669e-7,"teacher_disagreement_score":0.7393801,"about_ca_system_score_codex":0.00015736606,"about_ca_system_score_gemma":0.00048903364,"threshold_uncertainty_score":0.57132405},"labels":[],"label_agreement":null},{"id":"W2164517999","doi":"10.1109/icassp.1996.540320","title":"Clustering words for statistical language models based on contextual word similarity","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Perplexity; Computer science; Cluster analysis; Artificial intelligence; Word (group theory); Natural language processing; Similarity (geometry); Word error rate; Language model; Speech recognition; Mathematics","score_opus":0.06789550791532689,"score_gpt":0.280999772124081,"score_spread":0.2131042642087541,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2164517999","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006262175,0.000007773279,0.96533406,0.0009827848,0.00010837366,0.000167498,0.000028128616,0.00019092491,0.03255424],"genre_scores_gemma":[0.6279672,0.0000011158145,0.3681112,0.0029016628,0.000035388464,0.00002800739,0.0000035837695,0.000007241268,0.00094464223],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99911636,0.00004285988,0.00014795519,0.0002735163,0.00019306947,0.00022624983],"domain_scores_gemma":[0.99893373,0.00062795484,0.000024565781,0.00027345857,0.000036982176,0.00010329469],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00017171395,0.00010337509,0.00013098055,0.00007098641,0.00007874436,0.000120317236,0.00027853932,0.000049425176,0.0009962171],"category_scores_gemma":[0.00012230978,0.00008911222,0.000057292837,0.00009668087,0.00002307736,0.00016827745,0.000042925923,0.000072780305,0.00009057346],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029053243,0.00019943729,0.0000072938897,0.000016128788,0.000009805222,0.000026472575,0.0004437123,0.00077807467,0.000053509357,0.02404019,0.007646072,0.96675026],"study_design_scores_gemma":[0.00044870324,0.000063411426,0.000031076605,0.000011420416,0.0000030678805,0.0000021313008,0.000060895356,0.99669665,0.000624719,0.0013165892,0.0006117559,0.00012957735],"about_ca_topic_score_codex":0.000012824851,"about_ca_topic_score_gemma":0.000040867457,"teacher_disagreement_score":0.9959186,"about_ca_system_score_codex":0.000026567457,"about_ca_system_score_gemma":0.000009991694,"threshold_uncertainty_score":0.99991703},"labels":[],"label_agreement":null},{"id":"W2164898939","doi":"10.1109/pacrim.1991.160702","title":"Speaker-independent isolated-digit recognition based on hidden Markov models and multiple vocabulary specific vector quantization","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Codebook; Hidden Markov model; Vector quantization; Speech recognition; Computer science; Word (group theory); Artificial intelligence; Linde–Buzo–Gray algorithm; Vocabulary; Quantization (signal processing); Pattern recognition (psychology); Mathematics; Algorithm; Linguistics","score_opus":0.056052932594081194,"score_gpt":0.2169814565605006,"score_spread":0.1609285239664194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2164898939","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04575385,0.00009985478,0.8991016,0.0017153166,0.00042263948,0.00050817884,0.000020319538,0.00062881515,0.051749438],"genre_scores_gemma":[0.94595754,0.00015235243,0.05218203,0.0009079012,0.000072910996,0.000012276147,0.00002612822,0.000022117876,0.00066674454],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99830115,0.000114118615,0.0003007566,0.00059122586,0.00041454876,0.0002781868],"domain_scores_gemma":[0.99897015,0.00023851464,0.00009105889,0.00041949336,0.00012286086,0.00015792402],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00018354898,0.0002137038,0.00018663684,0.00025435453,0.0001463699,0.0003877187,0.00026742162,0.00012276116,0.0010661106],"category_scores_gemma":[0.00005334669,0.00020023389,0.0000780846,0.00032424708,0.000029510027,0.0008265485,0.00005879391,0.00013412077,0.00069618574],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005047058,0.00035590804,0.0002516933,0.00001730675,0.000020359887,0.000060730308,0.00018676798,0.000106294916,0.00086797745,0.0010338433,0.004028755,0.9930199],"study_design_scores_gemma":[0.00072936324,0.00012553109,0.00084601046,0.00004824851,0.000006652647,0.00002799786,0.000023177834,0.98909587,0.0065306555,0.0014432085,0.00081569253,0.0003076023],"about_ca_topic_score_codex":0.000019686953,"about_ca_topic_score_gemma":0.000016371141,"teacher_disagreement_score":0.9927123,"about_ca_system_score_codex":0.000051419698,"about_ca_system_score_gemma":0.000013590431,"threshold_uncertainty_score":0.99984705},"labels":[],"label_agreement":null},{"id":"W2165088481","doi":"10.1109/icassp.1981.1171129","title":"Text-independent speaker recognition using orthogonal linear prediction","year":2005,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Linear prediction; Speech recognition; Computer science; Speaker recognition; Set (abstract data type); Speaker verification; Pattern recognition (psychology); Feature (linguistics); Feature selection; Test set; Feature extraction; Artificial intelligence","score_opus":0.052873958658616584,"score_gpt":0.26356433678712865,"score_spread":0.21069037812851207,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2165088481","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17945707,0.000017575034,0.7890029,0.00081398943,0.0003941187,0.00015057353,0.000011021247,0.0004236677,0.029729094],"genre_scores_gemma":[0.4383989,0.000019451558,0.5589201,0.0011435831,0.0006316721,0.000008757272,0.000015644597,0.000013049012,0.00084887684],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99882126,0.00005469267,0.00024797954,0.00032369824,0.00033838852,0.00021398113],"domain_scores_gemma":[0.99944156,0.000045056036,0.000063052976,0.0002264367,0.000115610805,0.00010826909],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00028123116,0.000114232105,0.000100824334,0.00014239382,0.000119491626,0.000103526276,0.00021273109,0.0000802716,0.001676561],"category_scores_gemma":[0.000037445032,0.00010393686,0.00008045271,0.00022631246,0.000018021225,0.000767055,0.00006904364,0.00010980954,0.0013670281],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007262405,0.00012341901,0.0005252757,0.0000034892503,0.000017360057,0.000008599765,0.000077943885,0.00007369188,0.002344708,0.00070367224,0.00072029146,0.9953943],"study_design_scores_gemma":[0.0005873689,0.00005537594,0.0062914053,0.000034494744,0.00002074042,0.00028028848,0.00005339215,0.9322418,0.040999807,0.0014251536,0.017673211,0.00033697762],"about_ca_topic_score_codex":0.000012232968,"about_ca_topic_score_gemma":0.0000325134,"teacher_disagreement_score":0.9950573,"about_ca_system_score_codex":0.000072362636,"about_ca_system_score_gemma":0.00004921317,"threshold_uncertainty_score":0.9994105},"labels":[],"label_agreement":null},{"id":"W2165712617","doi":"10.1109/tasl.2007.914114","title":"Capturing Local Variability for Speaker Normalization in Speech Recognition","year":2008,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Hidden Markov model; Normalization (sociology); Image warping; Speech recognition; Computer science; Dynamic time warping; Artificial intelligence; Pattern recognition (psychology)","score_opus":0.023669024328760568,"score_gpt":0.24787706944188662,"score_spread":0.22420804511312606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2165712617","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11385157,0.00009138033,0.8844373,0.00021986983,0.00015360347,0.00030110238,0.00001355157,0.00017497114,0.0007566515],"genre_scores_gemma":[0.87053496,0.00005042997,0.12879787,0.00034215712,0.000049799604,0.000054850618,0.000006610913,0.000016778575,0.00014656824],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99858195,0.00009518374,0.00031654563,0.00047558208,0.00022183389,0.0003089027],"domain_scores_gemma":[0.99932677,0.0001670273,0.00008553981,0.00020313797,0.0001116702,0.0001058369],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054027385,0.00018829406,0.00021220758,0.000279741,0.00031063159,0.00010200493,0.00016119197,0.00012363188,0.00007518545],"category_scores_gemma":[0.000043999655,0.00018707081,0.0000743982,0.00045788332,0.00007745284,0.000743008,0.000002832083,0.00020270556,0.00002126614],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038902992,0.00014575222,0.000041807813,0.00007874354,0.00000728381,0.00005086334,0.0015434641,0.00007323622,0.0011922001,0.000005112658,0.000014253365,0.99680835],"study_design_scores_gemma":[0.0024628052,0.0001797655,0.0011149489,0.00038933454,0.000049000828,0.0010886329,0.0011396151,0.23541228,0.75539386,0.001567379,0.00029285182,0.00090950716],"about_ca_topic_score_codex":0.00009158885,"about_ca_topic_score_gemma":0.00020281745,"teacher_disagreement_score":0.9958989,"about_ca_system_score_codex":0.000093335606,"about_ca_system_score_gemma":0.00008440715,"threshold_uncertainty_score":0.7628526},"labels":[],"label_agreement":null},{"id":"W2165931417","doi":"10.1109/pacrim.1991.160778","title":"Development of a VQ-HMM continuous speech speaker-independent recognition system for small vocabularies","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hidden Markov model; Speech recognition; Computer science; Vector quantization; Viterbi algorithm; Vocabulary; Speaker recognition; Artificial intelligence; Pattern recognition (psychology); Linguistics","score_opus":0.06577192178803151,"score_gpt":0.22595863035787211,"score_spread":0.1601867085698406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2165931417","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10861365,0.00007206449,0.8569806,0.00024857503,0.00055744284,0.000779539,0.000013867623,0.00041030915,0.032323956],"genre_scores_gemma":[0.2714081,0.0000066074854,0.72666043,0.0001278185,0.000053022275,0.00008565701,0.0000083417,0.000014009905,0.0016360148],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984158,0.000048341142,0.00054421165,0.00038497866,0.00031012594,0.00029649358],"domain_scores_gemma":[0.9989386,0.00015469905,0.00018849486,0.00031673445,0.00029776045,0.000103699254],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047842826,0.00017282147,0.00030206091,0.0001640885,0.00013299362,0.0001293695,0.00043450212,0.00009865743,0.00027432604],"category_scores_gemma":[0.00008255081,0.0001545812,0.000120291064,0.00020159139,0.000027968968,0.00018817643,0.00009104224,0.00006283003,0.00037116228],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000113856195,0.00014286552,0.000041329553,0.00011430503,0.000054575554,0.000015220794,0.00081520603,2.1962579e-7,0.0017267759,0.0026346103,0.0005626888,0.9938808],"study_design_scores_gemma":[0.0018074712,0.00016956821,0.0005312244,0.0003028524,0.00004698156,0.00024293458,0.0017567166,0.015095981,0.9544157,0.0011583188,0.023758437,0.00071382994],"about_ca_topic_score_codex":0.000015870548,"about_ca_topic_score_gemma":0.00010232149,"teacher_disagreement_score":0.993167,"about_ca_system_score_codex":0.00008216146,"about_ca_system_score_gemma":0.000046336452,"threshold_uncertainty_score":0.6303638},"labels":[],"label_agreement":null},{"id":"W2166034902","doi":"","title":"New and Unified Templates for Canadian Acoustics Articles","year":2014,"lang":"en","type":"article","venue":"Canadian acoustics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Template; Acoustics; Computer science; Physics; Programming language","score_opus":0.022315707721196332,"score_gpt":0.21697454605867647,"score_spread":0.19465883833748013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2166034902","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034703203,0.00006835245,0.95536596,0.004497716,0.0006491162,0.00031025475,0.000113212234,0.00010733576,0.0041848477],"genre_scores_gemma":[0.84045774,0.000013651092,0.1553375,0.0029975765,0.0001883495,0.000008044571,0.0000091832535,0.00001962511,0.0009683427],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99880403,0.000024960042,0.00017714218,0.00029100434,0.000110237816,0.0005925971],"domain_scores_gemma":[0.9973518,0.00028751636,0.00003912735,0.00033557462,0.00013542718,0.0018505113],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002120451,0.00015312272,0.00016152395,0.00032517535,0.00031919518,0.0003539828,0.00039493115,0.00012848568,0.000065559885],"category_scores_gemma":[0.00052359153,0.0001628297,0.000036329304,0.0002312353,0.000044534474,0.00013577376,0.000023391152,0.000092956616,0.000059658887],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000045581933,0.0000111465315,0.0008230511,0.000051194635,0.000048300713,0.000054710243,0.0005475447,0.00021747334,0.007674607,0.062790886,0.1305201,0.7972564],"study_design_scores_gemma":[0.0012374351,0.00022102395,0.038046956,0.000080635284,0.00013664633,0.00014099039,0.00043130486,0.7533125,0.0014921831,0.051581882,0.15201464,0.0013038075],"about_ca_topic_score_codex":0.29569346,"about_ca_topic_score_gemma":0.50647974,"teacher_disagreement_score":0.80575454,"about_ca_system_score_codex":0.00017086789,"about_ca_system_score_gemma":0.0012933972,"threshold_uncertainty_score":0.7089966},"labels":[],"label_agreement":null},{"id":"W2166688768","doi":"10.1109/icassp.2011.5947435","title":"Well-calibrated heavy tailed Bayesian speaker verification for microphone speech","year":2011,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Computer Research Institute of Montréal","funders":"","keywords":"NIST; Normalization (sociology); Computer science; Speech recognition; Microphone; Softmax function; Speaker recognition; Speaker verification; Bayesian probability; Feature extraction; Linear discriminant analysis; Classifier (UML); Phone; Discriminative model; Pattern recognition (psychology); Artificial intelligence; Artificial neural network","score_opus":0.041925801157286766,"score_gpt":0.23291125610706576,"score_spread":0.19098545494977898,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2166688768","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012614227,0.000012526265,0.93255997,0.0007001202,0.00035145777,0.00035876775,0.0000036423007,0.00033453622,0.053064767],"genre_scores_gemma":[0.25207794,0.000012252642,0.74232614,0.0010799317,0.00005539995,0.00004789165,0.000010819108,0.000018316232,0.0043713017],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99895465,0.000046520654,0.0002419474,0.00038059242,0.000129152,0.00024715744],"domain_scores_gemma":[0.99918056,0.000055265533,0.00006921547,0.00047155714,0.00010783338,0.00011556131],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00020223917,0.00013065958,0.00014475429,0.00010484754,0.00009240953,0.000101049285,0.00046750973,0.00008161159,0.0023375272],"category_scores_gemma":[0.000031015275,0.000113677015,0.00008857289,0.00032629046,0.00003105939,0.00033713478,0.00004652004,0.000052648873,0.0011329966],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034726856,0.0013127584,0.0030718602,0.0000770761,0.00018614791,0.00005297689,0.0018914117,0.0000011949948,0.14508033,0.046848074,0.083807565,0.71732336],"study_design_scores_gemma":[0.0006471306,0.00009616741,0.0028246795,0.000012635872,0.000012280638,0.000036115252,0.000077249904,0.023420408,0.94456965,0.0048300154,0.023134315,0.00033933631],"about_ca_topic_score_codex":0.00007813853,"about_ca_topic_score_gemma":0.000029490166,"teacher_disagreement_score":0.7994893,"about_ca_system_score_codex":0.00002208378,"about_ca_system_score_gemma":0.00004151177,"threshold_uncertainty_score":0.99964476},"labels":[],"label_agreement":null},{"id":"W2167191127","doi":"10.1109/icassp.1989.266415","title":"A comparison of several acoustic representations for speech recognition with degraded and undegraded speech","year":2003,"lang":"en","type":"article","venue":"International Conference on Acoustics, Speech, and Signal Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":109,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Speech recognition; Cepstrum; Mel-frequency cepstrum; Computer science; Weighting; Noise (video); Filter (signal processing); Filter bank; Pattern recognition (psychology); Mathematics; Artificial intelligence; Feature extraction; Acoustics","score_opus":0.10345775018047919,"score_gpt":0.3427565667719608,"score_spread":0.2392988165914816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167191127","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09952361,0.00007561113,0.8930845,0.0007522169,0.00018829541,0.00044161102,0.00006997891,0.00009432064,0.0057698563],"genre_scores_gemma":[0.7847447,0.000047165246,0.21468028,0.00017905915,0.000052786065,0.00002357869,0.000031483796,0.000015245319,0.00022572484],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981011,0.00007925168,0.0004722827,0.00055749406,0.0005242187,0.00026561882],"domain_scores_gemma":[0.9981411,0.00037590208,0.000329916,0.0001614663,0.0008513931,0.00014023077],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003272082,0.00025293187,0.0003472191,0.00029150362,0.00022600467,0.00040094485,0.0002981034,0.00011608768,0.00011009516],"category_scores_gemma":[0.00028756706,0.00022667837,0.00005411427,0.00020767831,0.00019457976,0.0004969682,0.000043304048,0.00021425988,0.0000045247557],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003609279,0.0006856981,0.0022365516,0.00029540618,0.0001801319,0.000057414545,0.0012622845,0.00019538637,0.049589608,0.016052078,0.0003434296,0.9287411],"study_design_scores_gemma":[0.002860837,0.00084418216,0.0018361142,0.0008054633,0.00017559744,0.00047995552,0.0032713173,0.8128352,0.10366162,0.07219441,0.00017456747,0.0008607252],"about_ca_topic_score_codex":0.00002616599,"about_ca_topic_score_gemma":0.000032541127,"teacher_disagreement_score":0.92788035,"about_ca_system_score_codex":0.00004920146,"about_ca_system_score_gemma":0.00020215087,"threshold_uncertainty_score":0.92436755},"labels":[],"label_agreement":null},{"id":"W2167308595","doi":"10.1136/jnnp-2012-303538.27","title":"P10 Cultural effects on the perception of non-linguistic affective vocalisation by Japanese and Canadian subjects","year":2012,"lang":"en","type":"article","venue":"Journal of Neurology Neurosurgery & Psychiatry","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Psychology; Valence (chemistry); Disgust; Sadness; Arousal; Nonverbal communication; Anger; Affect (linguistics); Happiness; Surprise; Facial expression; Perception; Developmental psychology; Audiology; Social psychology; Communication; Medicine","score_opus":0.01221067154532821,"score_gpt":0.23974694187301535,"score_spread":0.22753627032768714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167308595","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.986431,0.0001087394,0.00017763351,0.007228585,0.0055698883,0.00012800057,0.0000030517967,0.0000113357455,0.00034178654],"genre_scores_gemma":[0.99240565,0.000048758335,0.00019668826,0.0068529756,0.000470377,0.0000035575358,7.345327e-7,0.000011085618,0.000010191225],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9983535,0.0005757884,0.00034727997,0.00017912668,0.00024125261,0.0003030666],"domain_scores_gemma":[0.9979875,0.0010411366,0.00038845168,0.00020365023,0.00013303998,0.00024621477],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006701142,0.0001594637,0.0002642218,0.0002653182,0.00014620874,0.000047256784,0.0002645884,0.000106781925,0.000013324908],"category_scores_gemma":[0.0006530831,0.000109042114,0.00013749734,0.0002355777,0.000089719775,0.00028088578,0.000024843295,0.00040717074,0.000010280272],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008010569,0.0011295464,0.7289614,0.00020585951,0.00024801475,0.00023599873,0.008932811,0.000022859585,0.08219579,0.001664457,0.104828976,0.070773244],"study_design_scores_gemma":[0.00050092285,0.0011182503,0.99178493,0.00006221128,0.00006316083,0.0015475346,0.00013269635,0.0008325935,0.0019185578,0.00044919614,0.0013631299,0.00022683026],"about_ca_topic_score_codex":0.00027952806,"about_ca_topic_score_gemma":0.00015202358,"teacher_disagreement_score":0.26282352,"about_ca_system_score_codex":0.000019975183,"about_ca_system_score_gemma":0.00009411602,"threshold_uncertainty_score":0.4446608},"labels":[],"label_agreement":null},{"id":"W2168166926","doi":"10.64152/10125/44034","title":"Establishing a methodology for benchmarking speech synthesis for computer-assisted language learning (CALL)","year":2005,"lang":"en","type":"article","venue":"Language learning & technology","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Benchmarking; Computer science; Benchmark (surveying); Pronunciation; Context (archaeology); Speech synthesis; Task (project management); Set (abstract data type); Artificial intelligence; Natural language processing; Programming language; Linguistics; Engineering","score_opus":0.03088655784593764,"score_gpt":0.29958428153839706,"score_spread":0.2686977236924594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2168166926","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09458516,0.000522847,0.89792395,0.0028841083,0.00037106808,0.0005990572,0.000007754283,0.0023348732,0.000771214],"genre_scores_gemma":[0.2127024,0.000016635126,0.7851581,0.00043762018,0.0005436991,0.00032492288,0.000027336428,0.000062791485,0.0007264976],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99661833,0.0004921673,0.0005779762,0.0010475499,0.00025817222,0.0010057949],"domain_scores_gemma":[0.9935427,0.0050692633,0.00042084217,0.00064575876,0.00019720466,0.00012425498],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0020851516,0.0003960196,0.0007299384,0.0010081799,0.0005693214,0.00030676628,0.0013959426,0.0006048497,0.000115697374],"category_scores_gemma":[0.005848415,0.00040734865,0.00030390415,0.0009040621,0.00012597366,0.0004265884,0.00044208686,0.000895158,0.00005450474],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028628641,0.00007023926,0.00034295255,0.000060888044,0.000084615625,0.00006190848,0.0022027611,0.00032595897,0.017295634,0.0017486063,0.000260887,0.97751695],"study_design_scores_gemma":[0.0031815835,0.0015209934,0.0007348533,0.0005023299,0.00028101722,0.0013885298,0.00946021,0.58095783,0.2530317,0.0013064778,0.14531688,0.0023176242],"about_ca_topic_score_codex":0.000079373705,"about_ca_topic_score_gemma":0.00015299146,"teacher_disagreement_score":0.9751993,"about_ca_system_score_codex":0.00016417394,"about_ca_system_score_gemma":0.00006864405,"threshold_uncertainty_score":0.9998378},"labels":[],"label_agreement":null},{"id":"W2168287019","doi":"10.1109/icassp.2008.4518745","title":"Adaptive score normalization for progressive model adaptation in text independent speaker verification","year":2008,"lang":"en","type":"article","venue":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Computer Research Institute of Montréal","funders":"","keywords":"Normalization (sociology); NIST; Speaker verification; Computer science; Speech recognition; Artificial intelligence; Speaker recognition","score_opus":0.10252485371504456,"score_gpt":0.2861246260957818,"score_spread":0.18359977238073727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2168287019","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20698008,0.000037974587,0.7864819,0.0009130413,0.00023000604,0.00068400934,0.000018287861,0.0000640198,0.0045906883],"genre_scores_gemma":[0.95574534,0.000059610098,0.043680098,0.00017930543,0.00006977707,0.00005797193,0.0000044866333,0.000013059523,0.00019037508],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99839276,0.000010749048,0.00041336697,0.00040665016,0.0005822626,0.00019420517],"domain_scores_gemma":[0.9979099,0.00005261351,0.0004758316,0.00007551252,0.001429016,0.00005709724],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028050595,0.00018456645,0.0001896827,0.00024235275,0.00020181827,0.00017206374,0.0005908603,0.00010339292,0.000012317876],"category_scores_gemma":[0.00013455967,0.00015338197,0.000059259088,0.00022224087,0.00014111843,0.0008592418,0.000068285524,0.00017638673,0.0000021431051],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013462269,0.0012569007,0.005488355,0.0005829802,0.00014871152,0.000013469241,0.015701434,0.02203388,0.17302018,0.16252755,0.00073521584,0.6171451],"study_design_scores_gemma":[0.0004777466,0.000084496976,0.0014120499,0.00035750098,0.000013207114,0.000035714602,0.00064403366,0.96017545,0.020859495,0.015755568,0.000005465821,0.00017925512],"about_ca_topic_score_codex":0.000011543065,"about_ca_topic_score_gemma":0.000004159634,"teacher_disagreement_score":0.9381416,"about_ca_system_score_codex":0.00009756503,"about_ca_system_score_gemma":0.00019504722,"threshold_uncertainty_score":0.62547356},"labels":[],"label_agreement":null},{"id":"W2168775301","doi":"10.1109/icassp.2001.940839","title":"Hypothesis-driven adaptation (Hydra): a flexible eigenvoice architecture","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Nuance Communications (Canada)","funders":"","keywords":"Computer science; Speech recognition; Utterance; Adaptation (eye); Construct (python library); Task (project management); Artificial intelligence; Architecture; Pattern recognition (psychology)","score_opus":0.06641560512875076,"score_gpt":0.21953062565536943,"score_spread":0.15311502052661868,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2168775301","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027081901,0.00007954301,0.8516179,0.0029589077,0.00014156848,0.00013077309,0.0000015720137,0.00055359345,0.14180799],"genre_scores_gemma":[0.33465478,0.000046686877,0.6519184,0.0022348242,0.00009889935,0.000028535964,0.000001002145,0.000014121242,0.011002748],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99896824,0.000065362154,0.00016018937,0.00031991076,0.00025556472,0.00023072593],"domain_scores_gemma":[0.99921393,0.0002005686,0.000048766797,0.00038511114,0.000048058508,0.000103536666],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000086857915,0.00012189676,0.00011764905,0.00015233806,0.00011389767,0.00014073368,0.00048251543,0.000058969472,0.0019137149],"category_scores_gemma":[0.00007739699,0.00010287855,0.00008411003,0.00036043287,0.000025532045,0.00028224912,0.000058607708,0.00009085988,0.002325322],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000017912527,0.000070064496,0.00001878746,0.000004517907,0.000014469193,0.000010538043,0.0008579905,0.00023615676,0.00072887144,0.0040669227,0.0032160461,0.99077386],"study_design_scores_gemma":[0.00055462,0.00012079612,0.0010380342,0.00003137413,0.000017120421,0.00012124923,0.0001819713,0.85327935,0.03411408,0.013251251,0.09667462,0.0006154965],"about_ca_topic_score_codex":0.000019609493,"about_ca_topic_score_gemma":0.000025203055,"teacher_disagreement_score":0.9901583,"about_ca_system_score_codex":0.000021856353,"about_ca_system_score_gemma":0.000011510518,"threshold_uncertainty_score":0.99899864},"labels":[],"label_agreement":null},{"id":"W2169890399","doi":"10.1007/978-3-642-25020-0_32","title":"Comparative Evaluation of Feature Normalization Techniques for Speaker Verification","year":2011,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal; Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"","keywords":"Normalization (sociology); NIST; Computer science; Speaker verification; Linear discriminant analysis; Speech recognition; Pattern recognition (psychology); Artificial intelligence; Probabilistic logic; Feature vector; Feature (linguistics); Speaker recognition","score_opus":0.07976696728653544,"score_gpt":0.3120268597436664,"score_spread":0.23225989245713097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169890399","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00005347446,0.00016667876,0.9877219,0.0001878352,0.0005457187,0.0010827107,0.000012303814,0.00010042497,0.010128935],"genre_scores_gemma":[0.13957225,0.000038851664,0.85958314,0.0003025694,0.00017439252,0.00007861241,0.00003802912,0.000021631417,0.00019051446],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974706,0.000065283544,0.000414822,0.00083189696,0.00096041925,0.00025696307],"domain_scores_gemma":[0.99689966,0.0002534506,0.0004822877,0.00077459187,0.0015247646,0.00006521314],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0017474624,0.00030295248,0.00042579512,0.0007025516,0.00012692541,0.00013205037,0.0012464097,0.0002912673,0.00004631543],"category_scores_gemma":[0.00013002947,0.00028010455,0.00011849938,0.00042060035,0.00031090598,0.0005607621,0.00018383376,0.00022659257,0.000011975355],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010584554,0.000034859895,0.000014054876,0.000032921078,0.000012967786,6.6604576e-7,0.0009676297,0.00042702936,0.0005519665,0.016586918,0.000073103016,0.9812873],"study_design_scores_gemma":[0.00034094907,0.00022752964,0.0003568655,0.0004299714,0.000056055178,0.000022826072,6.111506e-7,0.6143386,0.14376737,0.23722036,0.0026451221,0.0005937752],"about_ca_topic_score_codex":0.000009248796,"about_ca_topic_score_gemma":0.000046596302,"teacher_disagreement_score":0.9806935,"about_ca_system_score_codex":0.00021735494,"about_ca_system_score_gemma":0.00044428563,"threshold_uncertainty_score":0.99996513},"labels":[],"label_agreement":null},{"id":"W2170521850","doi":"10.1109/mwscas.2000.951427","title":"ARMA lattice modeling for isolated word speech recognition","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Autoregressive–moving-average model; Speech recognition; Lattice (music); Computer science; Autoregressive model; Artificial intelligence; Pattern recognition (psychology); Natural language processing; Mathematics; Statistics; Acoustics; Physics","score_opus":0.10108087647937199,"score_gpt":0.2618220852740568,"score_spread":0.16074120879468484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170521850","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019480452,0.00003594936,0.95160455,0.0013397798,0.00024420177,0.00023182182,0.0000038496214,0.00043677192,0.02662263],"genre_scores_gemma":[0.20429543,0.00006114535,0.7909206,0.0018461898,0.00011649331,0.000047205176,0.00000704007,0.00001654087,0.002689355],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99904275,0.000032255382,0.00021688773,0.00030963263,0.0001487484,0.00024973537],"domain_scores_gemma":[0.99930304,0.00015372735,0.000042207485,0.00024372555,0.00016968719,0.00008763579],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00020110997,0.00011067442,0.00011946303,0.00011972319,0.00012091669,0.00015573703,0.00029921206,0.00007077688,0.0010486149],"category_scores_gemma":[0.00009376834,0.000103371756,0.00008880381,0.00027985204,0.000008859,0.00054565904,0.00004109563,0.00007400189,0.0011017512],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000053331787,0.00006024252,0.0000024716903,0.00000652342,0.0000117567315,0.0000042559186,0.000078015444,0.00001196593,0.00029440477,0.00034073312,0.0021438284,0.99704045],"study_design_scores_gemma":[0.00031379669,0.000034619145,0.0000023418938,0.00001637384,0.000009082912,0.000031583513,0.000029431336,0.98323727,0.0059948466,0.008122878,0.0020307342,0.00017706776],"about_ca_topic_score_codex":0.000010644201,"about_ca_topic_score_gemma":0.0000071049676,"teacher_disagreement_score":0.9968634,"about_ca_system_score_codex":0.000021484344,"about_ca_system_score_gemma":0.000006690356,"threshold_uncertainty_score":0.9998646},"labels":[],"label_agreement":null},{"id":"W2172097686","doi":"10.1109/icassp.2012.6288863","title":"Understanding how Deep Belief Networks perform acoustic modelling","year":2012,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":270,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Deep belief network; TIMIT; Computer science; Hidden Markov model; Artificial intelligence; Artificial neural network; Similarity (geometry); Feature (linguistics); Pattern recognition (psychology); Speech recognition; Feature vector; Visualization; Representation (politics)","score_opus":0.15426382191673457,"score_gpt":0.23917869812238465,"score_spread":0.08491487620565008,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2172097686","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013275137,0.00010435218,0.9750746,0.00042958706,0.00042806307,0.00006323471,1.4498578e-7,0.00021163518,0.022360878],"genre_scores_gemma":[0.8830202,0.00004289324,0.11599101,0.00035018666,0.00018013609,0.000004635551,7.3836674e-7,0.000007900603,0.0004022517],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99908626,0.00002497252,0.00010047342,0.0001727339,0.00019285218,0.0004227101],"domain_scores_gemma":[0.99938506,0.00014579938,0.000035881258,0.00023822731,0.000027917176,0.00016711578],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003107303,0.00010768886,0.000104700295,0.00008127094,0.00019720288,0.00020872036,0.00029292298,0.00006777603,0.0002264961],"category_scores_gemma":[0.00001537388,0.00009066551,0.00005928898,0.00017675555,0.000019198076,0.0008190137,0.000083808416,0.0001099929,0.000079686986],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014300867,0.0003652952,0.002894316,0.000046957717,0.00013930732,0.000018550823,0.0027429024,0.16661382,0.00025949386,0.50512284,0.005332418,0.31644982],"study_design_scores_gemma":[0.00008202136,0.000010587979,0.00003501869,0.00000856034,0.00000728945,0.000016300824,0.00022338062,0.9972193,0.00022379223,0.0017810278,0.0002466897,0.00014600904],"about_ca_topic_score_codex":0.0000035506753,"about_ca_topic_score_gemma":0.0000050197436,"teacher_disagreement_score":0.8816927,"about_ca_system_score_codex":0.00010002689,"about_ca_system_score_gemma":0.000011321936,"threshold_uncertainty_score":0.36972323},"labels":[],"label_agreement":null},{"id":"W2178103884","doi":"10.48550/arxiv.1511.08400","title":"Regularizing RNNs by Stabilizing Activations","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Air Force Research Laboratory; Advanced Research Projects Agency; Defense Advanced Research Projects Agency; U.S. Department of Defense","keywords":"Recurrent neural network; TIMIT; Computer science; Term (time); Dropout (neural networks); Speech recognition; Task (project management); Language model; Artificial intelligence; Artificial neural network; Machine learning; Hidden Markov model","score_opus":0.1401149921742679,"score_gpt":0.19757555390488912,"score_spread":0.057460561730621224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2178103884","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14388554,0.000056838264,0.8395686,0.0005263904,0.00058124436,0.0002612713,0.000040718744,0.00052708766,0.01455228],"genre_scores_gemma":[0.9867766,0.000056901295,0.010684965,0.000142196,0.00005736118,0.000001579979,0.000032301214,0.000019641975,0.0022284794],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982509,0.00017070596,0.00018429132,0.00094589137,0.00013063513,0.00031757366],"domain_scores_gemma":[0.99800813,0.0001545112,0.00021630844,0.0011066538,0.00027699044,0.00023739641],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003473599,0.0002605886,0.0002782661,0.000259141,0.00019050774,0.00021260875,0.0014231009,0.00027617332,0.00007643049],"category_scores_gemma":[0.00013403909,0.00031363932,0.00017352875,0.00056301994,0.00006258526,0.0005558459,0.0012960811,0.00047940385,0.0001470869],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014216233,0.0018912081,0.006790345,0.0004910979,0.0013589263,0.001270325,0.00605848,0.04090518,0.009819313,0.68330514,0.16855837,0.07940942],"study_design_scores_gemma":[0.0012113722,0.00008656951,0.0004887052,0.0003302274,0.00018014533,0.000020601805,0.0014122451,0.67912054,0.009955195,0.27941826,0.025704306,0.0020718488],"about_ca_topic_score_codex":0.00011907935,"about_ca_topic_score_gemma":0.000021608705,"teacher_disagreement_score":0.84289104,"about_ca_system_score_codex":0.0003390917,"about_ca_system_score_gemma":0.00027821388,"threshold_uncertainty_score":0.9999316},"labels":[],"label_agreement":null},{"id":"W2178178359","doi":"10.1121/1.4934055","title":"Using automatic alignment on child speech: Directions for improvement","year":2015,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Western University","funders":"","keywords":"Speech recognition; Computer science; Limiting; Transcription (linguistics); Natural language processing; Training set; Speech production; Artificial intelligence; Linguistics","score_opus":0.049908043215891554,"score_gpt":0.2916734415916672,"score_spread":0.24176539837577565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2178178359","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005769606,0.00006047048,0.98144805,0.011578869,0.0004908391,0.00021009297,0.0000045812085,0.000018004397,0.0004194657],"genre_scores_gemma":[0.17822284,0.000089093584,0.81679696,0.004561853,0.0002393179,0.0000023805956,1.0791293e-7,0.000012042505,0.000075392425],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988052,0.00009362549,0.00033649232,0.00007785145,0.00051847816,0.00016829929],"domain_scores_gemma":[0.99856997,0.00044766144,0.00040180286,0.00029478726,0.00018510305,0.00010068492],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00080810295,0.000093618815,0.00020230687,0.000019306115,0.00019800369,0.000030395087,0.0007018873,0.00003109878,0.00001341334],"category_scores_gemma":[0.000263378,0.000047497128,0.00035506662,0.00021095741,0.00015375036,0.00008094256,0.00012950828,0.00015772869,0.0000033187719],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007448736,0.0007791368,0.000014577159,0.000044918223,0.00049309176,0.0000011538314,0.0018954813,0.0061319508,0.013118572,0.0001340895,0.05408911,0.92322344],"study_design_scores_gemma":[0.00051709445,0.0006216066,0.00007407781,0.00011075694,0.00018646769,0.00009894134,0.0012917763,0.9717463,0.017421009,0.0034184556,0.0044069714,0.000106545376],"about_ca_topic_score_codex":0.000019647932,"about_ca_topic_score_gemma":1.4424276e-7,"teacher_disagreement_score":0.9656143,"about_ca_system_score_codex":0.00013304998,"about_ca_system_score_gemma":0.00009053995,"threshold_uncertainty_score":0.19368766},"labels":[],"label_agreement":null},{"id":"W2179428711","doi":"10.1007/s11042-015-3039-x","title":"High quality voice conversion using prosodic and high-resolution spectral features","year":2015,"lang":"en","type":"article","venue":"Multimedia Tools and Applications","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Research (Canada)","funders":"","keywords":"Timbre; Autoencoder; Feature (linguistics); Focus (optics); Artificial neural network; Quality (philosophy); Pattern recognition (psychology)","score_opus":0.07011119276320464,"score_gpt":0.29739668727738267,"score_spread":0.227285494514178,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2179428711","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4570625,0.00045187352,0.53757894,0.0025846518,0.0002384881,0.0009771924,0.000098715784,0.00027768034,0.0007299341],"genre_scores_gemma":[0.72987235,0.00005522545,0.26945865,0.00020207335,0.0001756019,0.0000873,0.000033559136,0.000006597837,0.00010863922],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9991518,0.000054552045,0.00015689281,0.00031075103,0.0001705941,0.00015538056],"domain_scores_gemma":[0.99928534,0.00014365488,0.000076565026,0.00022519585,0.0000864566,0.00018276917],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023527883,0.00010123261,0.00012994748,0.00005244311,0.00018683894,0.00017900535,0.0001515825,0.0000688293,0.00000822957],"category_scores_gemma":[0.00006512628,0.00009122703,0.0000215674,0.00016916294,0.00009315088,0.0003418182,0.000088343244,0.0000871314,0.000033311386],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037897105,0.00031117164,0.0035659883,0.00007374387,0.000041897434,0.00000504024,0.0012286283,0.000045848472,0.022945821,0.06472065,0.0023216256,0.9047017],"study_design_scores_gemma":[0.0066095446,0.00026438123,0.5289638,0.00012116203,0.00016514244,0.00020631614,0.0011698334,0.28658035,0.08803505,0.04767155,0.038213547,0.0019993163],"about_ca_topic_score_codex":0.0003620975,"about_ca_topic_score_gemma":0.000018344415,"teacher_disagreement_score":0.9027024,"about_ca_system_score_codex":0.000034770626,"about_ca_system_score_gemma":0.000042361808,"threshold_uncertainty_score":0.37201303},"labels":[],"label_agreement":null},{"id":"W217970951","doi":"","title":"Roles of Pre-Training and Fine-Tuning in Context-Dependent DBN-HMMs for Real-World Speech Recognition","year":2010,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":193,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Hidden Markov model; Computer science; Artificial intelligence; Speech recognition; Context (archaeology); Deep belief network; Vocabulary; Deep learning; Pattern recognition (psychology)","score_opus":0.042077798734252304,"score_gpt":0.2835390570334626,"score_spread":0.2414612582992103,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W217970951","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9327809,0.00014772709,0.060340695,0.00027957963,0.0009138031,0.0010142059,0.000030070152,0.00026413135,0.0042288564],"genre_scores_gemma":[0.98935455,0.000006568281,0.010287962,0.00009001032,0.000059843,0.00008711599,0.000020713305,0.0000070240844,0.000086209],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99862456,0.00004144628,0.0006912945,0.00016809278,0.000268557,0.00020601698],"domain_scores_gemma":[0.99887896,0.00016595057,0.00044160886,0.00015824872,0.0002912193,0.00006403793],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000763245,0.00013326955,0.00025560663,0.00040244352,0.000118686105,0.00042456674,0.00022462089,0.00008703562,0.0000047290964],"category_scores_gemma":[0.00021138343,0.00012327297,0.000042696327,0.00030225824,0.000036455494,0.003209876,0.00004246485,0.00016935222,0.0000048422303],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016154781,0.000013073427,0.00040462875,0.00030898917,0.000005102698,6.750821e-7,0.0035015903,0.000034685094,0.001725116,0.00038816774,0.000033374254,0.9935684],"study_design_scores_gemma":[0.0016556703,0.00013932836,0.0033472718,0.00095485605,0.000020432415,0.00015720473,0.0039416845,0.95328325,0.031646553,0.0010319703,0.003318684,0.00050308],"about_ca_topic_score_codex":0.00015030542,"about_ca_topic_score_gemma":0.00062751805,"teacher_disagreement_score":0.99306536,"about_ca_system_score_codex":0.00002272735,"about_ca_system_score_gemma":0.0000696218,"threshold_uncertainty_score":0.5026926},"labels":[],"label_agreement":null},{"id":"W2188183693","doi":"10.21437/interspeech.2013-744","title":"Exploring convolutional neural network structures and optimization techniques for speech recognition","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":388,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Convolutional neural network; Speech recognition; Artificial neural network; Artificial intelligence; Recurrent neural network; Time delay neural network","score_opus":0.09942673034509407,"score_gpt":0.2529693359682053,"score_spread":0.15354260562311123,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2188183693","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013886516,0.000022515536,0.9829663,0.00079052075,0.00021259759,0.00043791436,0.0000028289644,0.00034600895,0.0013347664],"genre_scores_gemma":[0.045554344,0.000047409307,0.9533457,0.0005059658,0.00019319085,0.00026734732,0.000016502103,0.0000073429887,0.00006220349],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993136,0.000028740884,0.00014933453,0.00022709878,0.00010580761,0.00017543095],"domain_scores_gemma":[0.9994818,0.00013575806,0.00004689896,0.00010878192,0.00016599584,0.000060796374],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011809074,0.00009146586,0.000087490655,0.00006974306,0.00013838368,0.00020057517,0.00012670747,0.00004110316,0.0002426083],"category_scores_gemma":[0.000050519506,0.00008050597,0.000033840184,0.00012498893,0.000025467143,0.0012743828,0.00004977857,0.000044097706,0.000012545143],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000033280955,0.00000812804,0.000057205794,0.0000071540835,0.0000070851333,4.0670082e-7,0.000024418016,0.00021152219,0.00018396386,0.0036524013,0.0020109962,0.99383336],"study_design_scores_gemma":[0.0002812362,0.0000967355,0.0023080534,0.000025246949,0.000009572294,0.000063274456,0.00005263205,0.8970084,0.027042784,0.07169867,0.0010819415,0.00033144958],"about_ca_topic_score_codex":0.000024444927,"about_ca_topic_score_gemma":0.0000028116867,"teacher_disagreement_score":0.99350196,"about_ca_system_score_codex":0.000014806887,"about_ca_system_score_gemma":0.0000105929885,"threshold_uncertainty_score":0.32829383},"labels":[],"label_agreement":null},{"id":"W2189251954","doi":"","title":"Speech Inversion with Acoustic Classification","year":2012,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Hidden Markov model; Speech recognition; Computer science; Vocal tract; Acoustic model; Inversion (geology); Component (thermodynamics); Artificial intelligence; Speech processing","score_opus":0.04104107336699916,"score_gpt":0.2434795323085668,"score_spread":0.20243845894156764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2189251954","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048158184,0.0000116812,0.8517683,0.00091080135,0.00016786656,0.000076986864,2.544682e-7,0.0002287102,0.09867721],"genre_scores_gemma":[0.8536812,0.0000044572034,0.1447202,0.0005801808,0.000041452153,0.0000038954795,7.9542457e-7,0.0000029459782,0.00096487586],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995022,0.00002185822,0.00006105695,0.00011023515,0.00015720513,0.0001474435],"domain_scores_gemma":[0.999587,0.000045125456,0.000025929052,0.00021345115,0.000039326314,0.00008917972],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00012444939,0.000051813513,0.000046299214,0.00005727243,0.000051802726,0.000043535954,0.00018054774,0.000027426153,0.0002538543],"category_scores_gemma":[0.000018042323,0.000035982615,0.000015537245,0.00019019857,0.000014637033,0.00050888996,0.000030683223,0.00003707983,0.0008744454],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010005741,0.0002230081,0.011058269,0.000011561955,0.000016943231,0.0000056008853,0.00032040584,0.0000017609336,0.01818912,0.039990425,0.010352448,0.9198204],"study_design_scores_gemma":[0.0016731601,0.00032937076,0.2842103,0.000087726716,0.00007252177,0.0004367982,0.0014185687,0.32624835,0.3093054,0.0026316282,0.072110504,0.0014756889],"about_ca_topic_score_codex":0.000005382354,"about_ca_topic_score_gemma":0.0000040507043,"teacher_disagreement_score":0.91834474,"about_ca_system_score_codex":0.000021660097,"about_ca_system_score_gemma":0.000014267398,"threshold_uncertainty_score":0.9999035},"labels":[],"label_agreement":null},{"id":"W2189903590","doi":"10.1016/j.csl.2015.11.002","title":"Speech Production in Speech Technologies: Introduction to the CSL Special Issue","year":2015,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Rehabilitation Institute","funders":"","keywords":"Computer science; Speech production; Speech technology; Production (economics); Context (archaeology); Speech processing; Speech recognition; History","score_opus":0.01931376996621591,"score_gpt":0.2584920550608656,"score_spread":0.23917828509464967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2189903590","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31927097,0.0008910685,0.25967032,0.33352932,0.044469588,0.0053913016,0.000025046551,0.006128333,0.030624028],"genre_scores_gemma":[0.05519336,0.00005916265,0.8695256,0.0033239478,0.06545823,0.00016223463,0.0000324378,0.00010000866,0.006144986],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99678534,0.00021633516,0.0005121881,0.0011087572,0.0007498473,0.0006275215],"domain_scores_gemma":[0.9976559,0.00006623336,0.00014553074,0.0017109456,0.0002506951,0.00017067927],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0014078596,0.00035846612,0.00038409652,0.0006464616,0.00013857591,0.0004118594,0.001959138,0.00019188291,0.00020889554],"category_scores_gemma":[0.00056906603,0.0002828108,0.00011116434,0.0020535197,0.000089579946,0.00064155896,0.0008027959,0.0005011263,0.0023662488],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001646711,0.00011275676,0.000057298792,0.000007650131,0.000011084573,0.00022394303,0.0024164668,0.00004405549,0.00034710244,0.00027526828,0.18158141,0.8149065],"study_design_scores_gemma":[0.0008584791,0.00035324396,0.0012449368,0.000074708485,0.000019201996,0.0012333848,0.0035142465,0.0071989154,0.12615716,0.0022609876,0.85612315,0.0009615614],"about_ca_topic_score_codex":0.00012784844,"about_ca_topic_score_gemma":0.0004388917,"teacher_disagreement_score":0.81394494,"about_ca_system_score_codex":0.00029689143,"about_ca_system_score_gemma":0.00010760495,"threshold_uncertainty_score":0.9999624},"labels":[],"label_agreement":null},{"id":"W2235204424","doi":"10.48550/arxiv.1111.3182","title":"Context Tree Switching","year":2011,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Weighting; Tree (set theory); Context (archaeology); Markov chain; Computer science; Binary tree; Generalization; Mathematics; Class (philosophy); Markov process; Algorithm; Artificial intelligence; Machine learning; Statistics; Combinatorics; Geography","score_opus":0.14249565766110855,"score_gpt":0.16491138096625207,"score_spread":0.02241572330514352,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2235204424","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25951913,0.00000955496,0.6404207,0.0000418129,0.00017181851,0.00005708403,6.308503e-7,0.00022225457,0.09955706],"genre_scores_gemma":[0.9938813,0.000012393217,0.0044455887,0.00027995894,0.000015840751,1.6350356e-7,2.627652e-7,0.0000050111053,0.0013595021],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99931216,0.000050612565,0.00007766974,0.00033505118,0.000039130555,0.00018535773],"domain_scores_gemma":[0.99935347,0.000055413515,0.000051280942,0.00037877707,0.000049740658,0.00011131065],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000110792156,0.00009310469,0.00010013125,0.00011683868,0.00010559426,0.00003148671,0.0006520379,0.000047070967,0.00027518376],"category_scores_gemma":[0.00002289458,0.0000985433,0.000083089195,0.00034575208,0.00002763337,0.00051233044,0.0001248895,0.00008228697,0.00069730246],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025194988,0.00013776998,0.005234162,0.000005274007,0.000045824578,0.0005295615,0.0010688448,0.000011558132,0.00035177948,0.7938065,0.00045149826,0.19833201],"study_design_scores_gemma":[0.00443058,0.00048669166,0.06145737,0.00013879364,0.00015288286,0.00015656387,0.0034172256,0.5394596,0.050482165,0.32033676,0.017024882,0.0024564823],"about_ca_topic_score_codex":0.00009088854,"about_ca_topic_score_gemma":0.000079700454,"teacher_disagreement_score":0.7343621,"about_ca_system_score_codex":0.000031119525,"about_ca_system_score_gemma":0.000025427913,"threshold_uncertainty_score":0.8962645},"labels":[],"label_agreement":null},{"id":"W2248508985","doi":"10.21437/interspeech.2016-1297","title":"Automatic Dialect Detection in Arabic Broadcast Speech","year":2016,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Computer science; Modern Standard Arabic; Support vector machine; Artificial intelligence; Arabic; Classifier (UML); Speech recognition; Natural language processing; Language identification; Identification (biology); Linguistics; Natural language","score_opus":0.025306347845595212,"score_gpt":0.2544226352888353,"score_spread":0.22911628744324009,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2248508985","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13841994,0.00008720983,0.789383,0.0012238077,0.0023557912,0.0006494497,0.0000054137504,0.0011202485,0.066755146],"genre_scores_gemma":[0.9327797,0.00006562013,0.06508784,0.0002926548,0.00019302401,0.00012864018,0.0000021514143,0.000022914903,0.001427407],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99813807,0.0001792256,0.0003963118,0.00065995293,0.0003161048,0.00031031188],"domain_scores_gemma":[0.9986912,0.00021317498,0.00014403045,0.00079248595,0.00006779845,0.00009130128],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00043734297,0.0002482027,0.00032538752,0.00050252804,0.000045324658,0.00024325785,0.00086456735,0.00027126138,0.00069305865],"category_scores_gemma":[0.000175266,0.00019163036,0.00015443642,0.00028680477,0.000029222701,0.00022164089,0.0006102098,0.00032752243,0.0010940059],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000013066767,0.00003643502,0.00006833448,0.000033121818,0.000010069291,0.000028058956,0.00005875731,8.450464e-7,0.0006441931,0.00023614244,0.00013323323,0.9987495],"study_design_scores_gemma":[0.0013700929,0.00013717749,0.02271189,0.0014680546,0.00003568092,0.00032081234,0.000037967784,0.460896,0.3129795,0.19402444,0.0038166207,0.0022017655],"about_ca_topic_score_codex":0.000104703766,"about_ca_topic_score_gemma":0.00022280704,"teacher_disagreement_score":0.99654776,"about_ca_system_score_codex":0.00019291215,"about_ca_system_score_gemma":0.00012282768,"threshold_uncertainty_score":0.99968374},"labels":[],"label_agreement":null},{"id":"W2250185923","doi":"10.18653/v1/w15-5117","title":"Remote Speech Technology for Speech Professionals - the CloudCAST initiative","year":2015,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Rehabilitation Institute; University of Toronto","funders":"Leverhulme Trust","keywords":"Speech technology; Speech processing; Computer science; Speech recognition; Engineering","score_opus":0.09780048706451855,"score_gpt":0.32936750575030815,"score_spread":0.2315670186857896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2250185923","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0117678465,0.00011070702,0.7793143,0.08636691,0.0013239633,0.0013253188,0.000013934597,0.0008037373,0.118973315],"genre_scores_gemma":[0.081725135,0.000009324343,0.9046058,0.0067537786,0.00024016025,0.00006926212,0.0000048620573,0.000020604628,0.006571074],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987541,0.00009105161,0.00023073112,0.00033297593,0.00029421458,0.0002969619],"domain_scores_gemma":[0.9984375,0.0003975131,0.000098512166,0.00053950376,0.000426276,0.00010064923],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008243402,0.00013638192,0.00017094464,0.00016084668,0.00016741415,0.00008780312,0.0009860157,0.0001296248,0.00009494966],"category_scores_gemma":[0.00070683064,0.00008164905,0.000073376366,0.00059657096,0.00009268592,0.00023181552,0.0002782728,0.00015376322,0.00043349966],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017038183,0.00008536885,0.00004203163,0.00000490135,0.000029057974,0.000022680768,0.00036671752,2.9737885e-7,0.00019919808,0.06535712,0.05432404,0.87955153],"study_design_scores_gemma":[0.001406661,0.00031972994,0.0001343955,0.00007424141,0.000020337871,0.00044044587,0.0035776568,0.03015867,0.19863017,0.5978677,0.16683146,0.0005384737],"about_ca_topic_score_codex":0.000013103904,"about_ca_topic_score_gemma":0.000021246631,"teacher_disagreement_score":0.87901306,"about_ca_system_score_codex":0.00004250499,"about_ca_system_score_gemma":0.00018303322,"threshold_uncertainty_score":0.5571906},"labels":[],"label_agreement":null},{"id":"W2250268452","doi":"","title":"Identification of Speakers in Novels","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":63,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Task (project management); Identification (biology); Computer science; Natural language processing; Narrative; Artificial intelligence; Speech recognition; Linguistics; Engineering","score_opus":0.01587556571042371,"score_gpt":0.2291732713894288,"score_spread":0.2132977056790051,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2250268452","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45511818,0.0000076569395,0.49297357,0.0016977104,0.00014203964,0.00016904992,4.009983e-7,0.000062481966,0.049828913],"genre_scores_gemma":[0.97649413,0.0000020199486,0.02268155,0.00011440063,0.0000035406076,0.0000066093207,1.4984144e-7,0.0000010093825,0.0006965788],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9996372,0.000012073145,0.00014144591,0.00008254135,0.00007430742,0.000052442687],"domain_scores_gemma":[0.9997348,0.000031278676,0.000032840406,0.00014646948,0.000038252656,0.00001634047],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010543081,0.000023272809,0.000041495532,0.000074698735,0.000005606982,0.000030096116,0.00017937674,0.000013665772,0.00039139594],"category_scores_gemma":[0.0000306516,0.000019968256,0.000015318483,0.00017173128,0.00000917101,0.00027091868,0.000020534348,0.000015052448,0.00054611516],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.3518723e-7,0.00012122403,0.0032645732,0.000009034413,0.000005234447,0.0000010791952,0.00038833055,0.0000039823417,0.14651392,0.050611477,0.002113783,0.79696673],"study_design_scores_gemma":[0.00024063504,0.000013509603,0.2720037,0.000012171297,0.0000010588863,0.0000037200682,0.00014721279,0.06597822,0.6463164,0.0146902725,0.0004654943,0.00012758096],"about_ca_topic_score_codex":0.00008188421,"about_ca_topic_score_gemma":0.000011657115,"teacher_disagreement_score":0.7968391,"about_ca_system_score_codex":0.0000066670473,"about_ca_system_score_gemma":0.0000073828073,"threshold_uncertainty_score":0.7019388},"labels":[],"label_agreement":null},{"id":"W2266004465","doi":"","title":"Evaluating Bayesian and L1 Approaches for Sparse Unsupervised Learning .","year":2012,"lang":"en","type":"article","venue":"Cambridge University Engineering Department Publications Database","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Bayesian probability; Artificial intelligence; Unsupervised learning; Machine learning; Pattern recognition (psychology)","score_opus":0.08170086113538608,"score_gpt":0.2562536995249276,"score_spread":0.17455283838954153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2266004465","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03910385,0.00011771771,0.95862436,0.00048834085,0.000094216986,0.0003575942,0.00009077568,0.000357069,0.0007660632],"genre_scores_gemma":[0.45912346,0.00004151391,0.538672,0.00005898172,0.00009128838,0.000039913033,0.0007712985,0.000019097022,0.0011824755],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999094,0.000048419628,0.00011568303,0.0002953134,0.00013786061,0.00030872098],"domain_scores_gemma":[0.99902636,0.00020914678,0.000050162616,0.0003917851,0.000075724434,0.00024685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050586235,0.00012792699,0.000110433735,0.00026748242,0.0002606864,0.0001152742,0.0003058885,0.000037332495,0.0000081591925],"category_scores_gemma":[0.00024065729,0.00015113209,0.00004832669,0.0003701369,0.000020813754,0.0014064931,0.00018164828,0.000093190596,0.000013700781],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027938939,0.0006582027,0.0056767315,0.00022457555,0.00025254238,0.0000067557753,0.0005606496,0.0021320912,0.0028246888,0.8543732,0.010389082,0.12287353],"study_design_scores_gemma":[0.00057209225,0.00003456194,0.0047731916,0.000017365579,0.00005412744,0.00002241388,0.00015229314,0.85856986,0.0010184149,0.0000021966375,0.13448028,0.00030317158],"about_ca_topic_score_codex":0.000007304358,"about_ca_topic_score_gemma":7.315863e-7,"teacher_disagreement_score":0.8564378,"about_ca_system_score_codex":0.000088365334,"about_ca_system_score_gemma":0.000040058843,"threshold_uncertainty_score":0.61629874},"labels":[],"label_agreement":null},{"id":"W2292259253","doi":"10.1109/asru.2015.7404844","title":"Deep bottleneck features for i-vector based text-independent speaker verification","year":2015,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Speaker verification; NIST; Computer science; Speech recognition; Discriminative model; Bottleneck; Speaker recognition; Cepstrum; Mel-frequency cepstrum; Artificial intelligence; Artificial neural network; Pattern recognition (psychology); Feature extraction","score_opus":0.04303567032976717,"score_gpt":0.26536641523679655,"score_spread":0.22233074490702937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2292259253","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001140706,0.000040409363,0.9769712,0.0035260543,0.0004315132,0.00026297307,0.000002620207,0.00022394638,0.017400589],"genre_scores_gemma":[0.53828394,0.0000021467858,0.45694327,0.0017623937,0.000106908374,0.000083894236,0.0000131166025,0.000013065536,0.002791252],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990665,0.000039267936,0.00013780376,0.0003013082,0.0002690712,0.00018608793],"domain_scores_gemma":[0.9991253,0.000112408554,0.000049996397,0.00037785742,0.00017833765,0.00015607286],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002974093,0.000101865866,0.00010357345,0.00007922909,0.00005787242,0.00016262812,0.0003934937,0.00006576004,0.00015677248],"category_scores_gemma":[0.00016876211,0.00008378604,0.0000754998,0.00014506449,0.000014409608,0.00023109924,0.000031917494,0.00004697143,0.00031018374],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000115679766,0.00049662386,0.0007505118,0.000035227527,0.000058591948,0.000011014716,0.0005774212,0.0001478876,0.0041080285,0.13101633,0.111777216,0.75090545],"study_design_scores_gemma":[0.0033919993,0.0003503928,0.03593284,0.000028757051,0.000036881524,0.000046600795,0.00033328842,0.6001273,0.2002162,0.010213814,0.14836292,0.0009590116],"about_ca_topic_score_codex":0.000021498263,"about_ca_topic_score_gemma":0.00006927196,"teacher_disagreement_score":0.7499465,"about_ca_system_score_codex":0.000055382312,"about_ca_system_score_gemma":0.000085254396,"threshold_uncertainty_score":0.39868876},"labels":[],"label_agreement":null},{"id":"W2294245963","doi":"10.21437/interspeech.2014-82","title":"Manifold regularized deep neural networks","year":2014,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Artificial neural network; Bottleneck; Discriminative model; Feature extraction; Artificial intelligence; Pattern recognition (psychology); Speech recognition; Locality; Regularization (linguistics); Deep learning; Context (archaeology); Feature vector; Deep neural networks","score_opus":0.011047712830058188,"score_gpt":0.20318778475589586,"score_spread":0.19214007192583768,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2294245963","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013884746,0.000009466906,0.93520826,0.0010798625,0.0002952034,0.000046514364,4.2908436e-8,0.00028422574,0.061687965],"genre_scores_gemma":[0.82329375,0.0000025720897,0.17170022,0.003224079,0.00012624855,0.0000067485885,9.222963e-7,0.0000063477482,0.0016391213],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99927914,0.00007131013,0.00011686671,0.0002132783,0.00012974883,0.00018966827],"domain_scores_gemma":[0.9993828,0.00010664881,0.000029220466,0.00036462856,0.000032778797,0.0000839234],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021120434,0.00007690831,0.00009729945,0.000044200526,0.0000668038,0.00014066765,0.0004416566,0.00004617211,0.00034404304],"category_scores_gemma":[0.00003918465,0.000062236846,0.00006105861,0.00014811923,0.000010471408,0.000187846,0.00009050125,0.00006088941,0.00019156685],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027863905,0.000022561513,0.000107454696,0.0000015362027,0.000007043402,0.0000058846463,0.000023232991,0.000060200913,0.00014295118,0.16515617,0.0014493925,0.8330208],"study_design_scores_gemma":[0.0001723685,0.000017658373,0.00087673386,0.0000014809785,0.0000022026381,0.000019213905,0.0000038798703,0.99174595,0.00069334684,0.0031067526,0.0032598998,0.00010050232],"about_ca_topic_score_codex":0.000008436828,"about_ca_topic_score_gemma":0.000014414208,"teacher_disagreement_score":0.99168575,"about_ca_system_score_codex":0.000007101179,"about_ca_system_score_gemma":0.0000027822598,"threshold_uncertainty_score":0.376703},"labels":[],"label_agreement":null},{"id":"W2333871989","doi":"10.1109/taslp.2016.2546458","title":"Text-Dependent Speaker Recognition With Random Digit Strings","year":2016,"lang":"en","type":"article","venue":"IEEE/ACM Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Normalization (sociology); Speech recognition; Computer science; String (physics); Pattern recognition (psychology); Logistic regression; Numerical digit; Speaker recognition; Random forest; Digit recognition; Artificial intelligence; Statistics; Mathematics; Machine learning; Arithmetic; Artificial neural network","score_opus":0.016445153151105202,"score_gpt":0.23468969299936557,"score_spread":0.21824453984826037,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2333871989","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12033835,0.00020266205,0.87524295,0.001335601,0.00018310986,0.00027261535,0.000029555737,0.00043530168,0.0019598752],"genre_scores_gemma":[0.9282964,0.00015156463,0.068541944,0.00063662423,0.00012963521,0.000054719727,0.0000026844457,0.00003618229,0.0021502306],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9982916,0.000061499595,0.0002700637,0.000589445,0.0004041878,0.0003831998],"domain_scores_gemma":[0.9988637,0.00020801333,0.00012613363,0.00042246445,0.00017871035,0.00020098482],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022220382,0.00026687927,0.00025631415,0.00026663454,0.00031002588,0.00037487026,0.00035375924,0.00010195322,0.00031146],"category_scores_gemma":[0.0000787146,0.00017308748,0.00007833724,0.0003611361,0.000088141285,0.001004106,0.000009325637,0.00019046511,0.00016569489],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012130385,0.00009559336,0.000021670265,0.000030186213,0.00002947811,0.00007047351,0.0004540618,0.0000017379168,0.0069095735,0.000002490021,0.00003256111,0.9922309],"study_design_scores_gemma":[0.006013538,0.00034857175,0.000358233,0.0010318252,0.00010471498,0.00065584463,0.0007933077,0.00052722497,0.98665667,0.0011699377,0.0014083016,0.00093186373],"about_ca_topic_score_codex":0.00003320464,"about_ca_topic_score_gemma":0.0000981543,"teacher_disagreement_score":0.99129903,"about_ca_system_score_codex":0.00006427335,"about_ca_system_score_gemma":0.000080472695,"threshold_uncertainty_score":0.7058303},"labels":[],"label_agreement":null},{"id":"W2345781070","doi":"10.1121/1.4949912","title":"Towards real-time two-dimensional wave propagation for articulatory speech synthesis","year":2016,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Vocal tract; Computer science; Leverage (statistics); Speech production; Time domain; Acoustics; Aerodynamics; Speech recognition; Simulation; Artificial intelligence; Computer vision; Physics","score_opus":0.019691800717575154,"score_gpt":0.24917908959101695,"score_spread":0.2294872888734418,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2345781070","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02632291,0.000029909012,0.94800955,0.024725517,0.00024933176,0.00025306133,0.000012717895,0.00003014262,0.00036684566],"genre_scores_gemma":[0.35117763,0.00008001421,0.64711154,0.0011650193,0.00023839233,0.000006267729,1.1261796e-7,0.000015508578,0.00020548972],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983565,0.00021452188,0.00044378938,0.00012276003,0.00063312566,0.00022925793],"domain_scores_gemma":[0.99650836,0.0020922462,0.00051097665,0.00036456448,0.0004261191,0.00009771042],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001194906,0.00012389834,0.00028487682,0.000023084987,0.0001732866,0.000022826816,0.0007087467,0.000053119573,0.00010935668],"category_scores_gemma":[0.00086126896,0.000051541905,0.00051452155,0.00020313117,0.00039216728,0.00018083831,0.00016699151,0.00011747185,0.000018898834],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012263736,0.00017985974,0.0000118203325,0.00002108358,0.00022536759,0.0000017920371,0.00022197151,0.00023829799,0.327435,0.00011098545,0.016924664,0.6545065],"study_design_scores_gemma":[0.0012863148,0.0005121575,0.0025385623,0.0004521069,0.0005789398,0.00044601882,0.00028472967,0.63156605,0.3432033,0.01713037,0.0016071001,0.0003943665],"about_ca_topic_score_codex":0.000008317844,"about_ca_topic_score_gemma":8.5472e-8,"teacher_disagreement_score":0.65411216,"about_ca_system_score_codex":0.00008881088,"about_ca_system_score_gemma":0.00017461748,"threshold_uncertainty_score":0.21018179},"labels":[],"label_agreement":null},{"id":"W2357807430","doi":"","title":"A Comparative Study of MOS and PC Methods for Quality Evaluation of Text-to-Speech System in Mandarin","year":2006,"lang":"en","type":"article","venue":"Microcomputer applications","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mandarin Chinese; Computer science; Active listening; Impression; Prosody; Speech recognition; Test (biology); Word (group theory); Quality (philosophy); Mean opinion score; Natural language processing; Psychology; Linguistics; Communication","score_opus":0.08825679431518552,"score_gpt":0.4269068721197545,"score_spread":0.33865007780456896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2357807430","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23468634,0.000042779888,0.76215965,0.00004103305,0.000008105268,0.002613287,0.00001173967,0.000028936392,0.0004081175],"genre_scores_gemma":[0.46717054,2.7026542e-7,0.5318702,0.000010880734,0.000011451721,0.0009232647,0.0000035039461,0.0000030250392,0.0000068818604],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983647,0.00037592175,0.000566137,0.000372305,0.00020267534,0.00011826817],"domain_scores_gemma":[0.99859023,0.0003799656,0.0002033163,0.00033311968,0.00045781748,0.000035564055],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015384692,0.00010726027,0.0003420965,0.00023574024,0.000063144755,0.00003934265,0.00033231263,0.000039729108,0.0000020140208],"category_scores_gemma":[0.0000032443315,0.00010654392,0.00004274877,0.00052350364,0.000027047645,0.00008497549,0.00011512844,0.000043577933,0.0000031111967],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001491313,0.0010397147,0.0013158339,0.00010450539,0.00003238861,1.133092e-7,0.0025294502,0.00026246326,0.021568738,0.011351325,0.00011820553,0.96166235],"study_design_scores_gemma":[0.007109684,0.0005007697,0.25780126,0.00017030383,0.0001839117,0.000026298248,0.0038661566,0.42358735,0.28289866,0.013141649,0.009914016,0.0007999395],"about_ca_topic_score_codex":0.0002596063,"about_ca_topic_score_gemma":0.00017749287,"teacher_disagreement_score":0.9608624,"about_ca_system_score_codex":0.000066500164,"about_ca_system_score_gemma":0.000047094803,"threshold_uncertainty_score":0.4344735},"labels":[],"label_agreement":null},{"id":"W2358981474","doi":"10.1121/1.4948755","title":"Non-stationary Bayesian estimation of parameters from a body cover model of the vocal folds","year":2016,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Ontario Ministry of Research and Innovation; Comisión Nacional de Investigación Científica y Tecnológica; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Fundação Carlos Chagas Filho de Amparo à Pesquisa do Estado do Rio de Janeiro; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; National Institute on Deafness and Other Communication Disorders; Universidad Técnica Federico Santa María","keywords":"Bayesian probability; Computer science; Bayesian inference; Particle filter; Estimation theory; Mathematics; Algorithm; Artificial intelligence; Pattern recognition (psychology); Kalman filter","score_opus":0.014846652309159502,"score_gpt":0.23942487876254945,"score_spread":0.22457822645338996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2358981474","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05816229,0.000017966542,0.9351369,0.00637407,0.00012682803,0.00008113067,0.00002457741,0.0000042406573,0.00007199976],"genre_scores_gemma":[0.71546954,0.0000493001,0.28386733,0.00056383887,0.000018342087,6.7674324e-7,1.05859606e-7,0.000004754288,0.000026128158],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985027,0.00015512889,0.00048659605,0.00008578452,0.000639053,0.00013077269],"domain_scores_gemma":[0.9970032,0.0015755574,0.00076872465,0.000398503,0.00020121697,0.000052828225],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045062526,0.00009715314,0.00026327537,0.00001684718,0.00008354165,0.00001002484,0.0011053968,0.00005456861,0.00003422544],"category_scores_gemma":[0.0003423439,0.000039391518,0.0004495801,0.00021684116,0.00057342066,0.00017581081,0.00018994784,0.00014598663,0.0000026425032],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040657347,0.0009008509,0.00044570825,0.00007809091,0.0009556993,0.0000010770483,0.005103748,0.18302083,0.3099183,0.00024756088,0.03836147,0.46056008],"study_design_scores_gemma":[0.00029846054,0.0000972563,0.0018605785,0.00012390796,0.00011847456,0.000007348472,0.0001988348,0.96600527,0.021147275,0.010072926,0.000013341047,0.00005632683],"about_ca_topic_score_codex":0.00003679497,"about_ca_topic_score_gemma":1.5564746e-7,"teacher_disagreement_score":0.78298444,"about_ca_system_score_codex":0.00004273941,"about_ca_system_score_gemma":0.00014628322,"threshold_uncertainty_score":0.21127923},"labels":[],"label_agreement":null},{"id":"W2361883049","doi":"","title":"Design and Implementation of a Lightweight Telephone Voice Process Definition Language","year":2009,"lang":"en","type":"article","venue":"Microcomputer applications","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Process (computing); Mobile radio telephone; Flexibility (engineering); Telephone network; Telephony; Interactive voice response; Parsing; Voice over IP; Speech recognition; Telephone line; Telecommunications; Operating system; Programming language","score_opus":0.014962877190146703,"score_gpt":0.2782737371753436,"score_spread":0.2633108599851969,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2361883049","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018032582,0.00011097948,0.9800976,0.000685466,0.0000056339054,0.00056720333,0.0000046473,0.00011732879,0.00037856554],"genre_scores_gemma":[0.23246878,0.000023286564,0.7668478,0.00045917477,0.000033590055,0.00014032712,0.000012861852,0.000004656822,0.000009524543],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99922276,0.00003663672,0.00022550586,0.00027004202,0.000110624045,0.00013442167],"domain_scores_gemma":[0.99947023,0.0000701269,0.00010893594,0.00020179639,0.000094825555,0.000054068678],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012634709,0.00009941524,0.00011747886,0.00013122996,0.00009390021,0.00007029224,0.00027510308,0.00003806854,0.000015141062],"category_scores_gemma":[4.7253664e-7,0.00009752189,0.00002925119,0.00035783206,0.000019816991,0.00023037502,0.000032181608,0.000048241793,0.000038274233],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000021815024,0.0000997725,0.00003294882,0.000017398115,0.000009827056,0.000001070884,0.0016531053,0.000002907096,0.04962508,0.004685428,0.0002982822,0.943572],"study_design_scores_gemma":[0.0009950214,0.00018019401,0.010001339,0.00003919002,0.000035571094,0.00011812372,0.00037172926,0.0048742904,0.94660306,0.027607072,0.008729888,0.0004445206],"about_ca_topic_score_codex":0.0000071492636,"about_ca_topic_score_gemma":0.0000020895425,"teacher_disagreement_score":0.94312745,"about_ca_system_score_codex":0.000014454425,"about_ca_system_score_gemma":0.00003480764,"threshold_uncertainty_score":0.39768273},"labels":[],"label_agreement":null},{"id":"W2364974426","doi":"","title":"Phoneme modeling units design for Mandarin LVCSR systems","year":2011,"lang":"en","type":"article","venue":"Journal of Tsinghua University(Science and Technology)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Mandarin Chinese; Computer science; Set (abstract data type); Speech recognition; Salient; Vocabulary; Artificial intelligence; Vowel; Natural language processing; Linguistics; Programming language","score_opus":0.08201215340333769,"score_gpt":0.21423467727794082,"score_spread":0.13222252387460315,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2364974426","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.091599,0.000118796794,0.90617925,0.0004140685,0.00031854265,0.00011927158,0.0000011088422,0.000071006245,0.0011789339],"genre_scores_gemma":[0.8039402,0.000082651444,0.19580738,0.000031436317,0.000015852142,3.0098585e-7,3.9120504e-8,0.0000037323728,0.00011840079],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990773,0.000022474409,0.00018537023,0.00020532732,0.00026816214,0.00024133458],"domain_scores_gemma":[0.9980359,0.00004493309,0.00020917578,0.00019275631,0.0014118098,0.000105445215],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010346798,0.000090896014,0.00017958702,0.0013558703,0.00041339564,0.00009548869,0.0011112636,0.000095253665,0.0000028046002],"category_scores_gemma":[0.0002691484,0.00008176637,0.000031994918,0.0017887024,0.0003132292,0.0010100821,0.00016978763,0.0001449525,0.0000022877211],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037294038,0.00046478247,0.00095953996,0.00010216136,0.0002214496,0.0010577589,0.0044981386,0.0005340212,0.047334522,0.40738276,0.0019721705,0.53509974],"study_design_scores_gemma":[0.0030741696,0.0018245975,0.00013119148,0.00044991713,0.00015834115,0.0025073139,0.011231539,0.85027534,0.08524884,0.029465653,0.0147891715,0.0008439302],"about_ca_topic_score_codex":0.000012260679,"about_ca_topic_score_gemma":0.0000011616238,"teacher_disagreement_score":0.84974134,"about_ca_system_score_codex":0.0001010682,"about_ca_system_score_gemma":0.00045374283,"threshold_uncertainty_score":0.33343357},"labels":[],"label_agreement":null},{"id":"W2364980412","doi":"","title":"Development and Prospect for Speech Synthesis","year":2007,"lang":"en","type":"article","venue":"Microcomputer applications","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Generalization; Frame (networking); Speech synthesis; Property (philosophy); Speech recognition; Field (mathematics); Prosody; Basis (linear algebra); Development (topology); Noise (video); Harmonic; Artificial intelligence; Telecommunications; Acoustics; Mathematics","score_opus":0.019380997396341245,"score_gpt":0.25643524364916814,"score_spread":0.2370542462528269,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2364980412","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0049851215,0.00004925746,0.991695,0.00041551018,0.000015698206,0.0007782352,0.0000033129413,0.00020724925,0.0018506106],"genre_scores_gemma":[0.0067811003,0.000004457356,0.99192244,0.00037951785,0.00009011894,0.0006440217,0.0000036040803,0.000010342118,0.00016440055],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990078,0.0000073085394,0.00024233093,0.00039334377,0.000098325145,0.00025084388],"domain_scores_gemma":[0.99923193,0.00027178563,0.000059317434,0.00024781257,0.000085169304,0.00010398959],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039171698,0.00012022977,0.00012275507,0.00013072646,0.0002415735,0.00013780697,0.00039713903,0.000051328367,0.0000074637014],"category_scores_gemma":[0.000002311148,0.00011772357,0.00004595352,0.00022753162,0.000027695654,0.00011834684,0.000119371165,0.000046852685,0.000079760444],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001544757,0.000054003754,0.00005519005,0.000015184443,0.000012771195,0.0000010201437,0.00015244579,7.479298e-8,0.0030788975,0.013687183,0.0004554456,0.98248625],"study_design_scores_gemma":[0.00013262115,0.000006637407,0.001996272,0.0000101196065,0.000005775859,0.00004951492,0.0000178192,0.0004959958,0.24988216,0.0017128756,0.7455057,0.00018449783],"about_ca_topic_score_codex":0.0000016386795,"about_ca_topic_score_gemma":0.000009981496,"teacher_disagreement_score":0.9823017,"about_ca_system_score_codex":0.000040827585,"about_ca_system_score_gemma":0.000037284426,"threshold_uncertainty_score":0.48006275},"labels":[],"label_agreement":null},{"id":"W2397184916","doi":"","title":"Hybrid orthogonal projection and estimation (HOPE): a new framework to learn neural networks","year":2016,"lang":"en","type":"article","venue":"Journal of Machine Learning Research","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"MNIST database; Computer science; Artificial intelligence; TIMIT; Unsupervised learning; Projection (relational algebra); Artificial neural network; Machine learning; Feature (linguistics); Generative model; Pattern recognition (psychology); Generative grammar; Hidden Markov model; Algorithm","score_opus":0.048229047213752776,"score_gpt":0.353960200129276,"score_spread":0.3057311529155232,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2397184916","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17960778,0.00017394213,0.80757844,0.012135012,0.00018786153,0.000109913286,3.0171546e-7,0.000035999117,0.00017077063],"genre_scores_gemma":[0.90351737,0.00011961072,0.09455599,0.0001594739,0.00045961133,0.0000046472874,3.500604e-7,0.000015179118,0.0011677518],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976577,0.00063029985,0.00032600682,0.00022828099,0.0008154119,0.00034229094],"domain_scores_gemma":[0.9977841,0.0012637709,0.0001633901,0.00015824354,0.00030552008,0.00032496834],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003099784,0.00010440782,0.0001831749,0.0005684133,0.00025900992,0.00031091383,0.00040549246,0.00006214664,0.00012108652],"category_scores_gemma":[0.0042818994,0.00006797117,0.000070155256,0.00049054716,0.000044152952,0.00054664415,0.00019840454,0.0010505798,0.000042785323],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009675166,0.000025054318,0.004252437,0.0000044027965,0.000014815485,0.000049470786,0.00014786016,0.0013498395,0.00023601219,0.00040233255,0.0011907243,0.9922303],"study_design_scores_gemma":[0.000784846,0.001424884,0.01575617,0.00039422774,0.000008919439,0.0013373055,0.000032471802,0.9597686,0.0006181842,0.006664558,0.012990078,0.00021979169],"about_ca_topic_score_codex":0.000034229317,"about_ca_topic_score_gemma":0.00000563678,"teacher_disagreement_score":0.99201053,"about_ca_system_score_codex":0.00007364948,"about_ca_system_score_gemma":0.00013007024,"threshold_uncertainty_score":0.51261425},"labels":[],"label_agreement":null},{"id":"W2398971481","doi":"10.21437/interspeech.2015-95","title":"The reddots data collection for speaker recognition","year":2015,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":138,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"VoiceAge (Canada); Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Speech recognition; Speaker recognition; Data collection; Natural language processing; Artificial intelligence; Mathematics","score_opus":0.285855109260436,"score_gpt":0.32520872167374876,"score_spread":0.039353612413312755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2398971481","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005949394,0.000041093477,0.9318139,0.0064316574,0.0010115878,0.00032933266,0.0000106749885,0.00021148493,0.059555337],"genre_scores_gemma":[0.021511974,0.00010814303,0.9485435,0.002201212,0.00052598753,0.00016973187,0.00014877818,0.000022576474,0.026768083],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993081,0.00004866878,0.0001224952,0.00023292961,0.00015458006,0.0001332247],"domain_scores_gemma":[0.99884653,0.00026631128,0.000040907595,0.0005843577,0.0001908854,0.000070997754],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00082011864,0.00005400089,0.000052732437,0.000034499775,0.00019589363,0.00023467312,0.0006312935,0.000030181125,0.000025180407],"category_scores_gemma":[0.0005619041,0.000035315043,0.000023275781,0.00020602331,0.00001826683,0.00045902576,0.00013649388,0.00003286788,0.00026927594],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013293191,0.000017888855,0.000008513854,0.0000010077595,0.000007753501,5.3304257e-7,0.00004446095,1.11296465e-7,0.000028326207,0.0014909643,0.29506907,0.70331806],"study_design_scores_gemma":[0.0007545487,0.00011105101,0.0001885409,0.000009683736,0.000012414712,0.000045899644,0.00024239968,0.19933482,0.0074040936,0.057219237,0.73447126,0.00020604926],"about_ca_topic_score_codex":0.000019945515,"about_ca_topic_score_gemma":0.000101186946,"teacher_disagreement_score":0.703112,"about_ca_system_score_codex":0.000026695458,"about_ca_system_score_gemma":0.000072788076,"threshold_uncertainty_score":0.34610873},"labels":[],"label_agreement":null},{"id":"W2400893182","doi":"10.1109/icassp.2016.7472725","title":"Feature mapping, score-, and feature-level fusion for improved normal and whispered speech speaker verification","year":2016,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"","keywords":"Speech recognition; Computer science; Mel-frequency cepstrum; Word error rate; Feature (linguistics); Fusion; Vocal tract; Speaker verification; Sensor fusion; Complementarity (molecular biology); Feature extraction; Speaker recognition; Test data; Pattern recognition (psychology); Artificial intelligence","score_opus":0.03598910046254787,"score_gpt":0.2347791838794743,"score_spread":0.19879008341692644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2400893182","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12158607,0.00018173234,0.837086,0.035070546,0.00046461247,0.0008488583,0.00005364404,0.0002642815,0.004444252],"genre_scores_gemma":[0.16694014,0.0003140774,0.80074584,0.0016242496,0.0001992038,0.000056869103,0.000015473834,0.000026115382,0.030078009],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99905366,0.000026539072,0.000113134316,0.00045368128,0.00012046036,0.00023251331],"domain_scores_gemma":[0.99925786,0.000111474474,0.0000704154,0.0003080975,0.00012808741,0.000124041],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023070812,0.00015275851,0.00015070887,0.00010485628,0.0001442017,0.00017070702,0.00021147357,0.00013338761,0.000054060878],"category_scores_gemma":[0.000098192286,0.000096994576,0.00004435414,0.00013167427,0.000049894017,0.00047761263,0.00011001569,0.00006005396,0.000020020841],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027469488,0.000021708032,0.0006800889,0.000015899992,0.000012217617,0.0000011667803,0.00009684451,4.540907e-9,0.12053828,0.002314591,0.012084294,0.86420745],"study_design_scores_gemma":[0.00673531,0.0004621445,0.29278454,0.00030600658,0.00005452033,0.00048410022,0.00023105291,0.022656446,0.28648293,0.006000502,0.38219196,0.0016105158],"about_ca_topic_score_codex":0.000010092874,"about_ca_topic_score_gemma":0.000046747562,"teacher_disagreement_score":0.8625969,"about_ca_system_score_codex":0.000023337752,"about_ca_system_score_gemma":0.000027300715,"threshold_uncertainty_score":0.3955324},"labels":[],"label_agreement":null},{"id":"W2403731734","doi":"10.21437/interspeech.2013-336","title":"Rapid and effective speaker adaptation of convolutional neural network based models for speech recognition","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Speech recognition; TIMIT; Adaptation (eye); Convolutional neural network; Speaker recognition; Artificial neural network; Speaker diarisation; Hidden Markov model; Artificial intelligence; Pattern recognition (psychology)","score_opus":0.0454800610501761,"score_gpt":0.2299923264230991,"score_spread":0.184512265372923,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2403731734","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054295488,0.000050731305,0.9421092,0.00045926502,0.00015012488,0.0008140682,0.000009367346,0.000070266266,0.0020414768],"genre_scores_gemma":[0.5754495,0.0000061375977,0.42384627,0.00041253946,0.000060191313,0.00014967626,0.000019573965,0.000005607507,0.000050495888],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99919343,0.0000814024,0.00018733038,0.00023194337,0.00014516515,0.00016072576],"domain_scores_gemma":[0.99884576,0.0005770521,0.000084543986,0.00011600882,0.00031515778,0.000061491126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024569005,0.00009441309,0.00013595038,0.000072036986,0.00006912028,0.000055082834,0.000101013604,0.00005280401,0.00022154112],"category_scores_gemma":[0.00005524324,0.00008348827,0.000064228094,0.00014367806,0.00004108041,0.00065741385,0.000023956287,0.000040361047,0.00002596665],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020473914,0.000038060618,0.000050143448,0.0000162918,0.000014292701,3.246496e-7,0.000040808536,0.0010303293,0.00022092016,0.002427766,0.0011372129,0.9950034],"study_design_scores_gemma":[0.0005707574,0.00012094775,0.0024403397,0.000018176468,0.000008909882,0.000005841033,0.000028446879,0.956098,0.0044034417,0.03610034,0.000095853495,0.000108941786],"about_ca_topic_score_codex":0.00006045451,"about_ca_topic_score_gemma":0.000011542674,"teacher_disagreement_score":0.99489444,"about_ca_system_score_codex":0.00001568145,"about_ca_system_score_gemma":0.000025070161,"threshold_uncertainty_score":0.3404553},"labels":[],"label_agreement":null},{"id":"W2404260248","doi":"10.21437/interspeech.2013-610","title":"Automatic human utility evaluation of ASR systems: does WER really predict performance?","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; University of Toronto","funders":"","keywords":"Metric (unit); Computer science; Task (project management); Context (archaeology); Audit; Word error rate; Word (group theory); Speech recognition; Performance metric; Artificial intelligence; Natural language processing; Range (aeronautics); Machine learning; Mathematics; Engineering; Operations management","score_opus":0.04054442211315303,"score_gpt":0.27333764231025204,"score_spread":0.232793220197099,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2404260248","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92883414,0.000015283424,0.008048197,0.00014168306,0.0002656145,0.000545492,0.00000145478,0.00022018378,0.061927937],"genre_scores_gemma":[0.99325186,0.000003693698,0.006104193,0.000039036102,0.000025785403,0.00009842264,0.0000022821196,0.0000038774065,0.00047082698],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983839,0.00019944237,0.00036656926,0.00021456584,0.00068819843,0.00014732398],"domain_scores_gemma":[0.99874073,0.00007269074,0.00012848238,0.0004865932,0.0005103908,0.000061121296],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0014199835,0.00009064009,0.00016048878,0.000098546414,0.00008009377,0.000109301116,0.00038011983,0.000052264437,0.0030182956],"category_scores_gemma":[0.00008893591,0.000057755897,0.000047623605,0.00015426964,0.000036680238,0.00063586736,0.000064083026,0.000046668723,0.0002512726],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000012965334,0.00019936076,0.010805281,0.00025643944,0.000058676553,4.1888816e-7,0.00048277047,0.000015690375,0.0015070366,0.0033631343,0.0043828087,0.9789271],"study_design_scores_gemma":[0.00018467742,0.000038696402,0.15148279,0.000056048408,0.00001602972,0.0000030977449,0.00008135857,0.84322,0.00369461,0.0010841517,0.000060147882,0.000078376186],"about_ca_topic_score_codex":0.0002299775,"about_ca_topic_score_gemma":0.00001621876,"teacher_disagreement_score":0.9788487,"about_ca_system_score_codex":0.00003895596,"about_ca_system_score_gemma":0.000070147704,"threshold_uncertainty_score":0.9978931},"labels":[],"label_agreement":null},{"id":"W2410946393","doi":"10.1109/acpr.2015.7486451","title":"IAPR keynote lecture IV: Deep learning","year":2015,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Deep learning; Computer science; Artificial intelligence; Deep neural networks; Transfer of learning; Variety (cybernetics); Language understanding; Artificial neural network; Recurrent neural network; Competence (human resources); Cognitive science; Machine learning; Data science; Psychology","score_opus":0.03173245847646136,"score_gpt":0.2436212647191048,"score_spread":0.21188880624264345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2410946393","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005418416,0.00006356379,0.8654551,0.00127643,0.00021498643,0.000038560673,6.9162894e-8,0.00035876915,0.12717414],"genre_scores_gemma":[0.6631036,0.000009593974,0.3296945,0.0014378038,0.00010880221,0.0000056749054,0.0000012137741,0.000008904231,0.0056299325],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99930507,0.00005616835,0.000087187924,0.00019116799,0.00019605711,0.00016433388],"domain_scores_gemma":[0.99951214,0.00005221842,0.000025959409,0.00019355609,0.00007659196,0.00013951288],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00020522324,0.000069298185,0.00008046815,0.000060354563,0.00005911326,0.0001298685,0.00032579812,0.000047212405,0.00023108523],"category_scores_gemma":[0.00018498943,0.000057842946,0.000041076593,0.0002023462,0.000012846176,0.00021032864,0.00008527205,0.00011005638,0.001255453],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000028148056,0.000018010262,0.00045342252,0.0000014968151,0.0000075172497,0.000011828099,0.00045619623,0.000078407356,0.00021698237,0.004233055,0.0018132592,0.992707],"study_design_scores_gemma":[0.0010529076,0.00022274541,0.0033373614,0.000019693063,0.000012002956,0.00017216032,0.00034029596,0.59890187,0.038681578,0.026475888,0.33006385,0.00071963377],"about_ca_topic_score_codex":0.000015720609,"about_ca_topic_score_gemma":0.00001792166,"teacher_disagreement_score":0.99198735,"about_ca_system_score_codex":0.000021183954,"about_ca_system_score_gemma":0.000028917413,"threshold_uncertainty_score":0.9995222},"labels":[],"label_agreement":null},{"id":"W2437182874","doi":"10.1007/978-3-319-33618-3_20","title":"Speaker Classification via Supervised Hierarchical Clustering Using ICA Mixture Model","year":2016,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mixture model; Computer science; Cluster analysis; Pattern recognition (psychology); Artificial intelligence; TIMIT; Independent component analysis; Hierarchical clustering; Machine learning; Speech recognition; Hidden Markov model","score_opus":0.05107048488582587,"score_gpt":0.26526251848876903,"score_spread":0.21419203360294314,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2437182874","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001247717,0.000085311076,0.9903013,0.0015619918,0.0010433164,0.00034515536,0.000009222828,0.00021522901,0.0063137203],"genre_scores_gemma":[0.080580354,0.00003353275,0.9164236,0.0018494241,0.00057230145,0.00000863988,0.0000042524052,0.000054487202,0.00047339546],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99575025,0.0000626695,0.0006142973,0.001741088,0.0010974562,0.000734222],"domain_scores_gemma":[0.9973336,0.00041413849,0.00025320007,0.001443951,0.00027663726,0.00027848128],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00071220903,0.00057718105,0.00054351485,0.00090635376,0.00032933243,0.0005409172,0.0027552554,0.00050390937,0.00007449216],"category_scores_gemma":[0.00009030718,0.00046833555,0.00020747991,0.0004478608,0.000599776,0.0007621121,0.001052995,0.00074841967,0.000094659255],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008724505,0.00002473203,0.000008628981,0.000024645653,0.000010410042,0.00004246191,0.00029339764,0.006225091,0.00506172,0.0058733975,0.0000091205,0.98241764],"study_design_scores_gemma":[0.00021319577,0.00003340329,0.000030965293,0.00034295316,0.000008612136,0.00011185773,8.344604e-8,0.8948085,0.0013988737,0.10221669,0.000262568,0.0005723377],"about_ca_topic_score_codex":0.0000047966605,"about_ca_topic_score_gemma":0.000028871758,"teacher_disagreement_score":0.9818453,"about_ca_system_score_codex":0.0004291049,"about_ca_system_score_gemma":0.00051931775,"threshold_uncertainty_score":0.99977684},"labels":[],"label_agreement":null},{"id":"W2467063648","doi":"10.1016/j.scijus.2016.07.002","title":"Refining the relevant population in forensic voice comparison – A response to Hicks et alii (2015) The importance of distinguishing information from evidence/observations when formulating propositions","year":2016,"lang":"en","type":"letter","venue":"Science & Justice","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Stress (linguistics); Forensic science; Identity (music); Population; Psychology; Criminology; Computer science; Cognitive psychology; Speech recognition; Sociology; History; Acoustics","score_opus":0.08204880676153352,"score_gpt":0.33779118346657744,"score_spread":0.2557423767050439,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2467063648","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.046473183,0.00007640878,0.17517933,0.77569944,0.0010157996,0.0008591305,0.00009512749,0.00013338108,0.0004681809],"genre_scores_gemma":[0.4767774,0.000013356787,0.2200068,0.30173132,0.0008685077,0.00028336886,0.000113976406,0.00003594777,0.00016935157],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99548584,0.0006085283,0.0011838225,0.00059529167,0.0015375939,0.0005889046],"domain_scores_gemma":[0.99005926,0.006591274,0.0011897178,0.0012622753,0.00081604754,0.00008143593],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0066781305,0.00028071261,0.00035230248,0.0004678871,0.0010373925,0.0009290524,0.0024152119,0.00019091672,0.000012366247],"category_scores_gemma":[0.018266758,0.0001710962,0.00009508299,0.0017356907,0.00028213533,0.0043161227,0.00055198715,0.0008794492,0.00004173627],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005932707,0.0001565153,0.05714476,0.0007907592,0.00011674616,0.00009222585,0.13893907,0.0033349937,0.010909914,0.021954414,0.3946118,0.37135553],"study_design_scores_gemma":[0.0009776899,0.0004188219,0.5030418,0.0137694115,0.0005488575,0.00007635887,0.0053650406,0.303063,0.001413381,0.031989947,0.13712601,0.0022096522],"about_ca_topic_score_codex":0.0018544496,"about_ca_topic_score_gemma":0.0013200458,"teacher_disagreement_score":0.47396815,"about_ca_system_score_codex":0.00040179715,"about_ca_system_score_gemma":0.0005886587,"threshold_uncertainty_score":0.9900028},"labels":[],"label_agreement":null},{"id":"W2501000458","doi":"10.1109/ijcnn.1991.155435","title":"Global optimization of a neural network-hidden Markov model hybrid","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Hidden Markov model; TIMIT; Artificial neural network; Computer science; Speech recognition; Artificial intelligence; Sequence (biology); Markov model; Pattern recognition (psychology); SIGNAL (programming language); Markov chain; Machine learning","score_opus":0.026754927477651298,"score_gpt":0.22692734774199594,"score_spread":0.20017242026434465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2501000458","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002654519,0.00003907341,0.92121696,0.00052804535,0.00009989617,0.00006392239,0.000003041973,0.00011832113,0.075276226],"genre_scores_gemma":[0.36187097,0.000019795023,0.63683254,0.0005063468,0.000030218323,0.0000032808132,0.0000011160216,0.0000029517357,0.0007327614],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992823,0.000031911673,0.00016639293,0.00017961588,0.0001743682,0.00016540229],"domain_scores_gemma":[0.99955803,0.000027292219,0.00005284797,0.000237554,0.0000641325,0.00006014476],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008032969,0.00007436934,0.0001044066,0.000027321154,0.000039038983,0.000050043072,0.00033541565,0.000024250037,0.00058253313],"category_scores_gemma":[0.000019652158,0.000066478344,0.000059185906,0.00025169106,0.000018399856,0.00026618384,0.00008394266,0.00002488545,0.000031820153],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000040503733,0.00007303842,0.0003336052,0.000004380638,0.000012754355,0.000007578266,0.000026512387,0.36399683,0.0000051891125,0.004553694,0.027445024,0.6035373],"study_design_scores_gemma":[0.00012328857,0.000014810878,0.00009115171,0.0000040382965,0.000003479921,0.000020237903,0.0000021166024,0.9985353,0.00009729505,0.0009968542,0.00003302466,0.00007842855],"about_ca_topic_score_codex":0.000008577529,"about_ca_topic_score_gemma":0.000003675728,"teacher_disagreement_score":0.6345385,"about_ca_system_score_codex":0.000017424172,"about_ca_system_score_gemma":0.000008261105,"threshold_uncertainty_score":0.63783294},"labels":[],"label_agreement":null},{"id":"W2509141772","doi":"","title":"What Do Forced Alignment Likelihood Scores Tell Us About the Aligned Speech","year":2016,"lang":"en","type":"article","venue":"Canadian acoustics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Phone; Hidden Markov model; Speech recognition; TIMIT; Computer science; Formant; Duration (music); Variation (astronomy); Acoustics; Linguistics","score_opus":0.015315175636007542,"score_gpt":0.22509565489488684,"score_spread":0.2097804792588793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2509141772","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38404176,0.002522638,0.53450495,0.0380169,0.011794802,0.0020695487,0.00030168277,0.0006639825,0.02608374],"genre_scores_gemma":[0.97353995,0.0010735684,0.013520495,0.008674448,0.00034664045,0.000035421228,0.0000036473307,0.000033995944,0.0027718276],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982678,0.000070560425,0.00024966602,0.0003844465,0.00035200635,0.00067547825],"domain_scores_gemma":[0.9980217,0.00028594298,0.000079768375,0.00083398353,0.00014448131,0.00063410576],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003189546,0.00019987348,0.00016588159,0.0001672112,0.0002659077,0.0008053753,0.001116778,0.000112240916,0.0004012253],"category_scores_gemma":[0.00018214139,0.00012159229,0.00009371299,0.0002645893,0.0001080168,0.00043429818,0.00008995086,0.00006314741,0.00073560176],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000045330894,0.000026273578,0.0006295006,0.000011970321,0.0000599393,0.00023822588,0.00042119945,0.000008654169,0.017025238,0.0059569324,0.046025228,0.9295923],"study_design_scores_gemma":[0.0051719937,0.0007444325,0.08154587,0.0026495398,0.00045903132,0.0010570614,0.0031271959,0.031520817,0.17033042,0.0562889,0.64168763,0.005417123],"about_ca_topic_score_codex":0.0026072809,"about_ca_topic_score_gemma":0.0066839014,"teacher_disagreement_score":0.9241752,"about_ca_system_score_codex":0.00030751232,"about_ca_system_score_gemma":0.0005248922,"threshold_uncertainty_score":0.9454918},"labels":[],"label_agreement":null},{"id":"W2512343856","doi":"10.1016/j.forsciint.2016.08.017","title":"Use of relevant data, quantitative measurements, and statistical models to calculate a likelihood ratio for a Chinese forensic voice comparison case involving two sisters","year":2016,"lang":"en","type":"article","venue":"Forensic Science International","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Reliability (semiconductor); Conversation; Forensic science; Speech recognition; Statistics; Psychology; Natural language processing; Mathematics; Communication; History","score_opus":0.22378879477217886,"score_gpt":0.3800277103783245,"score_spread":0.15623891560614564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2512343856","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26509136,0.000013452354,0.73280966,0.0009524226,0.0004460832,0.0002891464,0.00032517046,0.000028939368,0.00004373476],"genre_scores_gemma":[0.59464765,0.00000236984,0.40510616,0.0001751465,0.00002198593,0.000018152794,0.000010097376,0.0000056814147,0.00001277059],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99759203,0.000054412947,0.00047349266,0.00071255624,0.0008468264,0.00032069997],"domain_scores_gemma":[0.99703133,0.0011255526,0.00019839377,0.00049647357,0.00093085546,0.00021741293],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010868312,0.00016638587,0.00024332317,0.0003421647,0.00018027269,0.0003157107,0.00086442515,0.000027224762,0.000009461599],"category_scores_gemma":[0.002447658,0.000115819756,0.00004317013,0.00038620597,0.00042137012,0.002561948,0.00053227774,0.000051001025,0.000010277333],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005041046,0.000421616,0.009541634,0.000054347038,0.00028058825,0.00016699315,0.0058655823,0.0010044047,0.08691337,0.20986918,0.004001365,0.6813768],"study_design_scores_gemma":[0.00070687843,0.00017450973,0.0013676083,0.00012763597,0.000017552851,0.00016300102,0.0001510234,0.9736048,0.007670838,0.015709767,0.00009385028,0.00021255034],"about_ca_topic_score_codex":0.00033600235,"about_ca_topic_score_gemma":0.0014545512,"teacher_disagreement_score":0.9726004,"about_ca_system_score_codex":0.000119011704,"about_ca_system_score_gemma":0.00018123348,"threshold_uncertainty_score":0.47229925},"labels":[],"label_agreement":null},{"id":"W2515097069","doi":"","title":"Interdisciplinary Approaches for Advancing Articulatory Speech Theory and Synthesis","year":2016,"lang":"en","type":"article","venue":"Canadian acoustics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Nvidia","keywords":"Speech synthesis; Vocal tract; Speech production; Computer science; Natural (archaeology); Speech technology; Speech recognition; Production (economics); Speech processing; Human–computer interaction","score_opus":0.02531939367293034,"score_gpt":0.23725416557429993,"score_spread":0.21193477190136958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2515097069","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04959901,0.00009665869,0.9448745,0.0023473275,0.00029227097,0.00022172416,0.000057284913,0.000086823246,0.0024243682],"genre_scores_gemma":[0.9194451,0.000012470775,0.07949847,0.00046861853,0.00009423006,0.00004885335,7.101345e-7,0.00001737557,0.00041417553],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990069,0.000060884446,0.00015054288,0.00030457458,0.0000884864,0.00038857924],"domain_scores_gemma":[0.9980255,0.0011275552,0.000041003463,0.00031472946,0.00005418381,0.00043706177],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055615086,0.00012515853,0.00014141174,0.00018442926,0.00018926372,0.00009075951,0.00029314082,0.00007633815,0.000043914893],"category_scores_gemma":[0.00074870745,0.000093951996,0.000052285206,0.00009567048,0.00009003639,0.00021260684,0.000103513674,0.0000446243,0.000033437176],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007272371,0.000013894865,0.00007604669,0.000024162071,0.000023336339,0.000030956748,0.00017169851,0.0000036488464,0.0034782572,0.029467326,0.0020802738,0.96462315],"study_design_scores_gemma":[0.0029393781,0.00045241322,0.03156873,0.0013612093,0.0005025119,0.0010646146,0.0053983256,0.20801704,0.057755187,0.66390795,0.022917815,0.0041148555],"about_ca_topic_score_codex":0.00005283506,"about_ca_topic_score_gemma":0.00065804215,"teacher_disagreement_score":0.9605083,"about_ca_system_score_codex":0.0001564988,"about_ca_system_score_gemma":0.00020201369,"threshold_uncertainty_score":0.38312513},"labels":[],"label_agreement":null},{"id":"W2530400070","doi":"10.1007/978-81-322-3592-7_9","title":"Robust Speaker Verification Using GFCC Based i-Vectors","year":2016,"lang":"en","type":"book-chapter","venue":"Lecture notes in electrical engineering","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Garron Family Cancer Centre","keywords":"Speaker verification; NIST; Computer science; Speech recognition; Speaker recognition; Session (web analytics); Speaker diarisation; Channel (broadcasting); Pattern recognition (psychology); Cepstrum; Artificial intelligence; Telecommunications","score_opus":0.028073170745591545,"score_gpt":0.20940429207523284,"score_spread":0.1813311213296413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2530400070","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00005315866,0.00035997914,0.9903871,0.0002518492,0.0003711492,0.00020002965,0.0000041242392,0.0002983693,0.008074266],"genre_scores_gemma":[0.27285662,0.00019369557,0.71958375,0.0012910686,0.0014788,0.00005901093,0.00003922913,0.00045890216,0.004038908],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981189,0.000021382202,0.00038227125,0.00063939794,0.00037397127,0.00046408325],"domain_scores_gemma":[0.99853677,0.000616527,0.000118913325,0.0005235043,0.00008232868,0.00012196794],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00017136245,0.0004248584,0.00041217255,0.0006783606,0.000046858862,0.00009356112,0.00053000497,0.00051348616,0.0001766392],"category_scores_gemma":[0.0004591158,0.00037542862,0.00018020069,0.0003087866,0.000020389629,0.00014173017,0.000050353214,0.0006198721,0.00007034379],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026042657,0.00006232056,0.00004753651,0.00010496642,0.00010414672,0.00015645997,0.000056395147,0.11818214,0.012495593,0.05447174,0.000047264046,0.8142454],"study_design_scores_gemma":[0.00028643102,0.000043321816,0.000054698434,0.00033212503,0.000024652558,0.000036420883,3.573727e-8,0.97633874,0.010101236,0.0043890546,0.0076340605,0.00075921987],"about_ca_topic_score_codex":0.0000059423014,"about_ca_topic_score_gemma":0.0000052195282,"teacher_disagreement_score":0.8581566,"about_ca_system_score_codex":0.00047353163,"about_ca_system_score_gemma":0.000121116194,"threshold_uncertainty_score":0.99986976},"labels":[],"label_agreement":null},{"id":"W2532585045","doi":"10.1109/nlpke.2003.1275932","title":"Performance improvement of automatic speech recognition systems via multiple language models produced by sentence-based clustering","year":2004,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Cluster analysis; Vocabulary; Artificial intelligence; Speech recognition; Language model; Sentence; Natural language processing; Grammar; Self-organizing map","score_opus":0.02378218736327504,"score_gpt":0.2199273004085662,"score_spread":0.19614511304529117,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2532585045","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5455413,0.000020770905,0.4530591,0.000105632134,0.00015748947,0.0003931375,0.000007115286,0.00021247558,0.00050297816],"genre_scores_gemma":[0.8961474,0.000006798679,0.103540555,0.00012882409,0.000021007363,0.00006611339,0.000011778558,0.000010955051,0.00006659456],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99859524,0.000031762727,0.00040080093,0.00035080154,0.0003688394,0.00025255457],"domain_scores_gemma":[0.99915165,0.000051757797,0.00016767914,0.0004116775,0.0001380316,0.00007922266],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032523082,0.00015790788,0.00021001052,0.00013087282,0.00007070971,0.000076220225,0.00031429864,0.000054739317,0.000028979724],"category_scores_gemma":[0.000033334887,0.00013759457,0.00006427038,0.00025647535,0.000023969249,0.00058056664,0.000065834436,0.000069503905,0.00006196813],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010298447,0.000257866,0.00006350502,0.00039441918,0.000023376455,0.000006916402,0.00033909891,0.0023801331,0.3026446,0.000012190266,0.000052890697,0.6938147],"study_design_scores_gemma":[0.00044814585,0.000075038275,0.000019268291,0.0001247552,0.000004499029,0.0000075145804,0.000085830725,0.561894,0.4371932,0.000034815264,0.0000019472668,0.00011095644],"about_ca_topic_score_codex":0.00040154174,"about_ca_topic_score_gemma":0.00002062196,"teacher_disagreement_score":0.6937038,"about_ca_system_score_codex":0.0001016987,"about_ca_system_score_gemma":0.00005770555,"threshold_uncertainty_score":0.5610944},"labels":[],"label_agreement":null},{"id":"W2539873419","doi":"10.1109/icscs.2009.5412479","title":"Comparison of GMM and fuzzy-GMM applied to phoneme classification","year":2009,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Keyword spotting; Speech recognition; Utterance; Classifier (UML); Vocabulary; Artificial intelligence; Mixture model; Spotting; Natural language; Hidden Markov model; Natural language processing; Word (group theory); Fuzzy logic; Linguistics","score_opus":0.06018352987154616,"score_gpt":0.32046603506690263,"score_spread":0.26028250519535645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2539873419","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15269454,0.000039470964,0.5853475,0.007562942,0.0001154972,0.0003129063,0.0000012884339,0.00022717519,0.2536987],"genre_scores_gemma":[0.8859287,0.000003900916,0.11310961,0.0007780115,0.000012702487,0.0000041932767,8.531802e-7,0.0000016315503,0.0001603736],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99937844,0.0000138255555,0.00017609014,0.0001921568,0.00014206371,0.00009739342],"domain_scores_gemma":[0.9995599,0.000045019297,0.00004879584,0.0002318208,0.000040953026,0.00007355013],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000110544286,0.00006104098,0.00013218816,0.00006936032,0.00003692963,0.00004541946,0.00021307087,0.000032728058,0.00004710408],"category_scores_gemma":[0.000017064089,0.000053499298,0.000018748548,0.00021802998,0.000013434333,0.00008029389,0.000030280742,0.00003315729,0.00010126832],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000067628093,0.00010479305,0.00042032567,0.0000031965656,0.0000034147197,2.233612e-7,0.00039410725,0.0000015687655,0.05605626,0.06972511,0.0042363536,0.8690479],"study_design_scores_gemma":[0.0007283206,0.00030515253,0.3497434,0.000025673029,0.000014173762,0.0000074341388,0.00077346846,0.035478815,0.5860381,0.01594511,0.010451053,0.0004892817],"about_ca_topic_score_codex":0.000003837736,"about_ca_topic_score_gemma":0.000004424703,"teacher_disagreement_score":0.8685586,"about_ca_system_score_codex":0.0000089766,"about_ca_system_score_gemma":0.000010555474,"threshold_uncertainty_score":0.2181638},"labels":[],"label_agreement":null},{"id":"W2539922005","doi":"10.1109/nnsp.1992.253696","title":"Maximum mutual information training of a neural predictive-based HMM speech recognition system","year":2003,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Hidden Markov model; Speech recognition; Computer science; Artificial intelligence; Mutual information; Artificial neural network; Pattern recognition (psychology); Scheme (mathematics); Training (meteorology); Machine learning; Mathematics","score_opus":0.03761875897832177,"score_gpt":0.2209160651004652,"score_spread":0.1832973061221434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2539922005","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08152104,0.000005540033,0.8248501,0.00010948463,0.00037727962,0.0002729653,0.00001707279,0.00036946303,0.09247708],"genre_scores_gemma":[0.8788907,6.988156e-7,0.12080343,0.00022308412,0.000016402173,0.00002032368,0.000013217625,0.0000045407023,0.000027604901],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988068,0.00013646985,0.0003795552,0.00015943723,0.00032231485,0.00019546192],"domain_scores_gemma":[0.9991938,0.00013580266,0.00016164474,0.00021757436,0.00021108474,0.000080080754],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045411562,0.00011486486,0.00016612113,0.00023797555,0.00006849312,0.00008814504,0.00021282998,0.00007232759,0.00013904962],"category_scores_gemma":[0.00017627858,0.000104237835,0.00008481453,0.00037201055,0.000028647692,0.0011827635,0.000016998267,0.00007919383,0.0001583934],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022641938,0.000047784928,0.000104841914,0.000075297205,0.00001712724,0.0000065421173,0.0007309434,0.000039887487,0.00027074938,0.003184701,0.00022038982,0.9952791],"study_design_scores_gemma":[0.0020966814,0.0004432042,0.001108853,0.00022160119,0.00003544116,0.00025221275,0.004360473,0.72537124,0.26154548,0.0020192782,0.0020239812,0.0005215322],"about_ca_topic_score_codex":0.000012647905,"about_ca_topic_score_gemma":0.0000030988042,"teacher_disagreement_score":0.99475753,"about_ca_system_score_codex":0.000049709222,"about_ca_system_score_gemma":0.00009764945,"threshold_uncertainty_score":0.42506957},"labels":[],"label_agreement":null},{"id":"W2544551282","doi":"10.1109/icscs.2009.5412292","title":"Combined speech decoders output for phoneme recognition enhancement","year":2009,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Speech recognition; Mel-frequency cepstrum; Robustness (evolution); Feature extraction; Pattern recognition (psychology); Normalization (sociology); Cepstrum; Artificial intelligence; Naive Bayes classifier; Classifier (UML); Support vector machine; Speaker recognition; Speech enhancement; Noise reduction","score_opus":0.04394314540733342,"score_gpt":0.26703860471609464,"score_spread":0.22309545930876123,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2544551282","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012122218,0.000011008793,0.94366366,0.0045850393,0.00037326018,0.00043912634,0.0000035603655,0.00028568073,0.03851644],"genre_scores_gemma":[0.19550654,0.000033631524,0.7924504,0.007210943,0.00008287327,0.00006566248,0.000027283659,0.000008742586,0.0046138675],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989187,0.000026944801,0.00023802862,0.00033881786,0.00020399697,0.0002734727],"domain_scores_gemma":[0.9993047,0.0001084955,0.000065354994,0.00028037743,0.0001425196,0.000098529534],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002644852,0.00012806723,0.00014835484,0.000114737464,0.00011077209,0.00013187548,0.000341157,0.000056089986,0.00040159255],"category_scores_gemma":[0.0000741828,0.00011754699,0.00010623209,0.0001862037,0.000012804091,0.00030654774,0.00002539083,0.000047044858,0.00054553937],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018490871,0.00014789565,0.0000040048885,0.0000035128621,0.000009679002,0.000002511078,0.000059296843,1.9077167e-7,0.0018934108,0.0017402016,0.012222036,0.98389876],"study_design_scores_gemma":[0.0027171236,0.001078324,0.000770198,0.000049548074,0.000025303596,0.000019689192,0.000115563016,0.038428273,0.8195334,0.11531464,0.021221228,0.00072672963],"about_ca_topic_score_codex":0.0000060841,"about_ca_topic_score_gemma":0.0000067953765,"teacher_disagreement_score":0.98317206,"about_ca_system_score_codex":0.0000403292,"about_ca_system_score_gemma":0.00003166587,"threshold_uncertainty_score":0.7011987},"labels":[],"label_agreement":null},{"id":"W2547760228","doi":"10.1109/icacci.2016.7732024","title":"Modified gammatone frequency cepstral coefficients to improve spoofing detection","year":2016,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Garron Family Cancer Centre; Tata Consultancy Services","keywords":"Spoofing attack; Mel-frequency cepstrum; Computer science; Cepstrum; Speech recognition; Discrete cosine transform; Pattern recognition (psychology); Detector; Speaker verification; Speaker recognition; Artificial intelligence; Feature extraction; Telecommunications; Computer security","score_opus":0.018526417548240755,"score_gpt":0.23695867241442642,"score_spread":0.21843225486618567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2547760228","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20095892,0.0000019914216,0.7893142,0.00064988324,0.0004440505,0.00012782398,0.0000023063506,0.0002580645,0.008242748],"genre_scores_gemma":[0.9546889,0.000001502153,0.04343655,0.00034451272,0.0000488066,0.00002037891,1.6775535e-7,0.0000068761974,0.0014523115],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989287,0.000032615997,0.00018399268,0.0003547366,0.00021935087,0.0002805596],"domain_scores_gemma":[0.9993079,0.000074381955,0.00003924884,0.00033831855,0.000081165446,0.0001590148],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00018266642,0.00010587795,0.00010270073,0.00014097948,0.0000854698,0.00009200444,0.0003737485,0.00005197869,0.00015436298],"category_scores_gemma":[0.00010452421,0.00007056269,0.000057556554,0.00026164943,0.000016798043,0.00032023675,0.000079497324,0.0000378257,0.0010029571],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000036322667,0.000024497065,0.000036088553,0.0000015922161,0.000004130992,0.000004298817,0.000038320803,0.0000014568461,0.28520805,0.003540123,0.000047396214,0.7110904],"study_design_scores_gemma":[0.0004277791,0.0000936016,0.0019452975,0.000025287207,0.0000033132628,0.000017993267,0.000016303922,0.004884025,0.98914194,0.002731841,0.00046405726,0.00024853746],"about_ca_topic_score_codex":0.000047037076,"about_ca_topic_score_gemma":0.000027947228,"teacher_disagreement_score":0.75372994,"about_ca_system_score_codex":0.0000612142,"about_ca_system_score_gemma":0.000022916503,"threshold_uncertainty_score":0.9997749},"labels":[],"label_agreement":null},{"id":"W2556512059","doi":"10.1121/1.4970196","title":"The native language benefit for voice recognition is not contingent on lexical access","year":2016,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Indexicality; Psychology; Linguistics; Comprehension; Identification (biology); American English; Duration (music); Contrast (vision); Audiology; Speech recognition; Computer science; Acoustics; Artificial intelligence; Biology; Medicine","score_opus":0.03966639049154784,"score_gpt":0.30400934189432266,"score_spread":0.2643429514027748,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2556512059","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018169569,0.000086131804,0.88068795,0.10001012,0.00036777908,0.0002497737,0.000051186667,0.00001750485,0.0003599668],"genre_scores_gemma":[0.884683,0.0010009299,0.08865769,0.024291804,0.0006096365,0.000014248035,2.9823283e-7,0.000024551291,0.0007178132],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99865824,0.00014386709,0.00035336532,0.000111091606,0.0005145388,0.00021891802],"domain_scores_gemma":[0.9940009,0.0047410615,0.000520459,0.00029913857,0.00036928285,0.000069128604],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009575068,0.000109366796,0.00020391743,0.000014232269,0.00034361542,0.00007019005,0.0014623316,0.000050214203,0.00004384589],"category_scores_gemma":[0.00091697153,0.00003946694,0.00044999103,0.00017756059,0.00037700238,0.00016548362,0.00020388454,0.00019913733,0.000013819237],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001977396,0.0000925346,0.0000058629657,0.000007848495,0.00015058032,3.9823092e-7,0.0009244557,0.000010238059,0.007892021,0.0000806105,0.021851832,0.9687859],"study_design_scores_gemma":[0.005266965,0.0030388413,0.006125915,0.0013123996,0.0009679179,0.00020799822,0.008806598,0.18996587,0.66929895,0.07156461,0.042437773,0.0010061389],"about_ca_topic_score_codex":0.00001038157,"about_ca_topic_score_gemma":7.888141e-7,"teacher_disagreement_score":0.96777976,"about_ca_system_score_codex":0.000059549537,"about_ca_system_score_gemma":0.00005137973,"threshold_uncertainty_score":0.27174005},"labels":[],"label_agreement":null},{"id":"W2560180799","doi":"10.1093/acrefore/9780199384655.013.108","title":"Learnability and Learning Algorithms in Phonology","year":2016,"lang":"en","type":"reference-entry","venue":"Oxford Research Encyclopedia of Linguistics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Learnability; Grammar; Computer science; Morpheme; Artificial intelligence; Phonology; Natural language processing; Rule-based machine translation; Linguistics; Language acquisition; Phonotactics; Grammar induction; Class (philosophy); Task (project management)","score_opus":0.06140302826450727,"score_gpt":0.34953947115092215,"score_spread":0.2881364428864149,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2560180799","genre_codex":"other","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006077808,0.0019344524,0.0044519845,0.0002697146,0.0017649033,0.0003881358,0.000046723344,0.00008124725,0.99045503],"genre_scores_gemma":[0.0016953287,0.85539323,0.06095502,0.00002633903,0.001922685,0.000083486586,0.000036355614,0.00006139421,0.079826154],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9953684,0.0011745037,0.0007291599,0.0008801131,0.000984184,0.0008636163],"domain_scores_gemma":[0.9934866,0.0040384578,0.00024992786,0.0007069435,0.001269602,0.0002484629],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0030294904,0.00030887165,0.0007197384,0.0010014215,0.00018258211,0.00009210203,0.001179367,0.000642523,0.0001409679],"category_scores_gemma":[0.037169524,0.00025452548,0.00010216114,0.000632039,0.0005113346,0.00006469854,0.0010299152,0.0024608702,0.000039043065],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014443151,0.000093919916,0.0021354244,0.0003037676,0.000022596574,0.00008574488,0.0002540501,3.4185103e-7,4.2383124e-7,0.0025675017,0.0040713963,0.9904504],"study_design_scores_gemma":[0.00034835614,0.00021397744,0.001008931,0.00053625694,0.0000076821325,0.000009140655,0.000082028215,0.0006677922,0.000023849012,0.013023815,0.9837888,0.0002893986],"about_ca_topic_score_codex":0.0001870229,"about_ca_topic_score_gemma":0.00007616285,"teacher_disagreement_score":0.990161,"about_ca_system_score_codex":0.00018919438,"about_ca_system_score_gemma":0.00093293336,"threshold_uncertainty_score":0.9999907},"labels":[],"label_agreement":null},{"id":"W2586956420","doi":"10.1109/slt.2016.7846264","title":"Modelling speaker and channel variability using deep neural networks for robust speaker verification","year":2016,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Computer Research Institute of Montréal","funders":"Nvidia","keywords":"Speaker verification; Computer science; Normalization (sociology); Word error rate; Speech recognition; Speaker recognition; Classifier (UML); Pattern recognition (psychology); Artificial neural network; Artificial intelligence; Discrete cosine transform; Deep neural networks","score_opus":0.07338699910887467,"score_gpt":0.2456055521845424,"score_spread":0.17221855307566772,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2586956420","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01969618,0.000016788154,0.97868407,0.0005665891,0.0002463018,0.0002133257,0.0000015409088,0.0001006786,0.00047455684],"genre_scores_gemma":[0.657755,0.000009864495,0.34192258,0.0001525332,0.00008527572,0.000010343068,8.7576154e-7,0.0000073638907,0.000056176024],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99903744,0.000057075897,0.00018848157,0.00039092186,0.00009808016,0.00022797393],"domain_scores_gemma":[0.9991785,0.00026950132,0.0000574455,0.0003022372,0.00010651354,0.00008577614],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000473088,0.000107987544,0.000118654054,0.00004530091,0.00011961907,0.000108405526,0.00018098114,0.000066232846,0.00004545742],"category_scores_gemma":[0.000055680193,0.000074543,0.000050183375,0.00011022916,0.000035655485,0.000470637,0.000057412617,0.000036351164,0.000005325167],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048028687,0.00011583749,0.00073458895,0.000025844955,0.000035455385,0.0000020657403,0.0002556867,0.24437054,0.0008931061,0.016370408,0.000093164716,0.7370553],"study_design_scores_gemma":[0.00021597934,0.000012155844,0.00019060922,0.0000087466815,0.000007437976,0.000010610279,0.000009801318,0.99577206,0.0003960216,0.0031695075,0.00007482192,0.00013226345],"about_ca_topic_score_codex":0.000023789084,"about_ca_topic_score_gemma":0.000005955347,"teacher_disagreement_score":0.7514015,"about_ca_system_score_codex":0.000032733627,"about_ca_system_score_gemma":0.0000098822875,"threshold_uncertainty_score":0.30397752},"labels":[],"label_agreement":null},{"id":"W2606954870","doi":"10.1017/s0025100317000159","title":"Revisions to the VoQS system for the transcription of voice quality","year":2017,"lang":"en","type":"article","venue":"Journal of the International Phonetic Association","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"Bangor University","keywords":"Phonation; Transcription (linguistics); Section (typography); Larynx; Quality (philosophy); Speech recognition; Computer science; Chart; Communication; Psychology; Audiology; Linguistics; Medicine; Mathematics; Statistics","score_opus":0.04588565896230793,"score_gpt":0.31908792235995737,"score_spread":0.2732022633976494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2606954870","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12845127,0.00017391371,0.5177054,0.33504906,0.014837488,0.00081779005,0.00007497804,0.000021138721,0.0028689825],"genre_scores_gemma":[0.9956473,0.000023621367,0.0027529637,0.00045162748,0.00039487405,0.000009001276,2.9906167e-7,0.0000036728716,0.0007166002],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9984236,0.00015391066,0.00048023442,0.00007995993,0.00077808276,0.00008422079],"domain_scores_gemma":[0.99613494,0.0009790995,0.0016354296,0.00037362883,0.00084931223,0.000027577687],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032217961,0.000059535163,0.00013008624,0.0000414325,0.00041294657,0.00025402545,0.0021977068,0.0000392469,0.00001091795],"category_scores_gemma":[0.0032479365,0.000028987059,0.00027122715,0.00006780363,0.000018356788,0.00024003482,0.0000904424,0.0001209749,0.000011830973],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00053959875,0.00063568034,0.016436685,0.00015525498,0.002554,0.0000034600046,0.010941073,0.002837339,0.08591686,0.05196662,0.17373616,0.65427727],"study_design_scores_gemma":[0.0017083619,0.00015202766,0.8392404,0.00064875133,0.00025606318,0.000057120244,0.0010397173,0.0298199,0.047039084,0.006468364,0.073332526,0.00023773438],"about_ca_topic_score_codex":0.00005449021,"about_ca_topic_score_gemma":0.000048941558,"teacher_disagreement_score":0.8671961,"about_ca_system_score_codex":0.00026942513,"about_ca_system_score_gemma":0.0000630666,"threshold_uncertainty_score":0.40839225},"labels":[],"label_agreement":null},{"id":"W2610699719","doi":"10.71781/9853","title":"Weighted finite-state transducers in speech recognition : a compaction algorithm for non-determinizable transducers","year":2002,"lang":"en","type":"dissertation","venue":"Open MIND","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Transducer; Finite state; Speech recognition; Compaction; State (computer science); Computer science; Algorithm; Acoustics; Engineering; Machine learning; Physics","score_opus":0.055050317056273335,"score_gpt":0.3028397106030366,"score_spread":0.24778939354676327,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2610699719","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36143324,0.00021498134,0.45509493,0.0012731963,0.008040253,0.015977897,0.002364688,0.00012512287,0.15547569],"genre_scores_gemma":[0.009247795,0.0004053259,0.96288663,0.0001730746,0.00017190663,0.0007675283,0.0042013023,0.00013644987,0.022009984],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970162,0.00013068483,0.000794232,0.0010974612,0.00039653984,0.00056486344],"domain_scores_gemma":[0.99842876,0.00033788566,0.00036239633,0.00045604949,0.0002451607,0.00016971793],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005603734,0.00049991155,0.00074229925,0.0007247675,0.00018610583,0.0007272188,0.0012112809,0.00041139248,0.0022303215],"category_scores_gemma":[0.0000397591,0.0005449969,0.00027829074,0.0008099132,0.00002735924,0.0012465843,0.00002336798,0.00038192084,0.00069368223],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000084814004,0.00017004511,9.036807e-7,0.00004431111,0.00004964994,0.00007239761,0.0026240512,0.0000022757097,0.00035870055,4.7828735e-7,0.00031657916,0.9962758],"study_design_scores_gemma":[0.008156973,0.0008343048,0.00026988485,0.0019864417,0.00031520156,0.0001197535,0.0028982651,0.5222807,0.41269916,0.0033126913,0.043862656,0.003263966],"about_ca_topic_score_codex":0.00018352158,"about_ca_topic_score_gemma":0.001183962,"teacher_disagreement_score":0.99301183,"about_ca_system_score_codex":0.0002351936,"about_ca_system_score_gemma":0.0002784691,"threshold_uncertainty_score":0.9997001},"labels":[],"label_agreement":null},{"id":"W2610924493","doi":"10.1016/j.compbiolchem.2017.03.012","title":"PECC: Correcting contigs based on paired-end read distribution","year":2017,"lang":"en","type":"article","venue":"Computational Biology and Chemistry","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"National Outstanding Youth Science Fund Project of National Natural Science Foundation of China; National Natural Science Foundation of China","keywords":"Computer science","score_opus":0.020562206355106173,"score_gpt":0.275028273531399,"score_spread":0.25446606717629283,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2610924493","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45929155,0.000044398574,0.5228957,0.0038316844,0.0004260571,0.00008955903,0.00013970668,0.00017217042,0.013109187],"genre_scores_gemma":[0.99498844,0.0000023763384,0.0041954713,0.00029968278,0.00007213794,0.0000069684397,0.00028046957,0.0000025106967,0.00015194416],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993903,0.000027097598,0.00011371834,0.0002750888,0.000071878036,0.00012189026],"domain_scores_gemma":[0.9992436,0.0002854177,0.000119742916,0.00021702146,0.0000750958,0.00005909171],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014787496,0.00009119012,0.00010317535,0.000011197966,0.00048597035,0.00010900817,0.00027197428,0.00009753702,0.000092782335],"category_scores_gemma":[0.00025531562,0.00008566699,0.000038374863,0.000024540846,0.00014856391,0.000078676414,0.00006540543,0.00010062735,0.000018734321],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049449078,0.00014019448,0.019317245,0.000036981728,0.00003568816,0.00002503978,0.000043711356,0.00006426615,0.005387067,0.0069946125,0.0011174781,0.9667883],"study_design_scores_gemma":[0.0022482004,0.00014250632,0.25426576,0.00017693185,0.000023786788,0.00018574815,0.000055528715,0.6212979,0.07204023,0.0398696,0.008878864,0.0008149478],"about_ca_topic_score_codex":0.0000040238856,"about_ca_topic_score_gemma":4.3265746e-7,"teacher_disagreement_score":0.9659733,"about_ca_system_score_codex":0.000018732899,"about_ca_system_score_gemma":0.00004350577,"threshold_uncertainty_score":0.37377402},"labels":[],"label_agreement":null},{"id":"W2611386872","doi":"10.2172/1289367","title":"Analysis of Pre-Trained Deep Neural Networks for Large-Vocabulary Automatic Speech Recognition","year":2016,"lang":"en","type":"report","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute of Circulatory and Respiratory Health; Lawrence Livermore National Laboratory; U.S. Department of Energy","keywords":"Convolutional neural network; Sensitivity (control systems); Computer science; Artificial neural network; Pattern recognition (psychology); Event (particle physics); Field (mathematics); Artificial intelligence; Detector; Selection (genetic algorithm); Speech recognition; Vocabulary; Particle (ecology); Nova (rocket); SIGNAL (programming language); Physics; Mathematics; Engineering; Astrophysics; Electronic engineering","score_opus":0.03970584771201347,"score_gpt":0.29763167030373283,"score_spread":0.25792582259171937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2611386872","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010010812,0.00023883954,0.9794715,0.00022632952,0.0011339879,0.0008737138,0.00021128343,0.00045547282,0.016387796],"genre_scores_gemma":[0.15339223,0.0018722278,0.8152501,0.0016093159,0.0023576035,0.0012277527,0.003954077,0.00029590103,0.02004078],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961384,0.00018399073,0.001198041,0.00088603963,0.0009960375,0.0005974767],"domain_scores_gemma":[0.99559855,0.0010181313,0.00093672157,0.0010353085,0.0012307133,0.0001805949],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0018412594,0.00044930194,0.0012967874,0.0012583011,0.000118430326,0.00014306404,0.0009601919,0.0005532542,0.0016023743],"category_scores_gemma":[0.0007046267,0.0003430493,0.0012738816,0.0014023586,0.00004291213,0.00039340692,0.00018887353,0.0002004139,0.000026076683],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011709425,0.000121062425,0.000120409626,0.00015074034,0.0017313422,0.000016993266,0.000033912613,0.000014011034,0.000011273786,0.00004805534,0.0032785945,0.9944619],"study_design_scores_gemma":[0.0004276676,0.000104556086,0.002066663,0.00015620881,0.0020773432,0.000050943527,0.000014343608,0.99115896,0.00044584705,0.00064038194,0.0023025288,0.0005545476],"about_ca_topic_score_codex":0.00004787226,"about_ca_topic_score_gemma":0.00022976923,"teacher_disagreement_score":0.99390733,"about_ca_system_score_codex":0.00015734464,"about_ca_system_score_gemma":0.00027079094,"threshold_uncertainty_score":0.9999021},"labels":[],"label_agreement":null},{"id":"W2620616604","doi":"","title":"Predicting the quality of processed speech by combining modulation-based features and model trees.","year":2016,"lang":"en","type":"article","venue":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Institut National de la Recherche Scientifique","funders":"","keywords":"Computer science; Quality (philosophy); Speech recognition; Modulation (music); Artificial intelligence; Pattern recognition (psychology); Acoustics","score_opus":0.03210785264559545,"score_gpt":0.2759148809231232,"score_spread":0.24380702827752776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2620616604","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4716694,0.00096836593,0.47645107,0.038937535,0.00061103416,0.0016597564,0.00033217427,0.0011590065,0.008211663],"genre_scores_gemma":[0.9740899,0.00010262817,0.022059614,0.0017623443,0.00013787531,0.00014822274,0.00003708707,0.000072314426,0.0015900113],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9942329,0.00056954287,0.0013298377,0.0013298013,0.0015480451,0.0009899081],"domain_scores_gemma":[0.9935366,0.0025196879,0.0008321519,0.0016982822,0.0009457835,0.00046751412],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0024921682,0.00065269496,0.0008622905,0.00044350966,0.00059547945,0.00048627623,0.002069364,0.00046524729,0.00018672874],"category_scores_gemma":[0.001827016,0.00042732127,0.00028274278,0.0012230353,0.00045645842,0.0016349083,0.00043997855,0.00056305446,0.000049546823],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005282126,0.0022490474,0.033906303,0.00080663833,0.0005737186,0.00001852002,0.0055960836,0.0009607351,0.09464727,0.039963227,0.049107864,0.7716424],"study_design_scores_gemma":[0.0074322196,0.0005306102,0.053343672,0.0007253983,0.00012639296,0.000055999953,0.0007179053,0.7510735,0.15335765,0.02167123,0.00852504,0.002440403],"about_ca_topic_score_codex":0.00025305722,"about_ca_topic_score_gemma":0.000113384434,"teacher_disagreement_score":0.769202,"about_ca_system_score_codex":0.00012368265,"about_ca_system_score_gemma":0.00044935275,"threshold_uncertainty_score":0.99981785},"labels":[],"label_agreement":null},{"id":"W2620638943","doi":"10.5445/ir/1000166279","title":"Phoneme Boundary Detection using Deep Bidirectional LSTMs","year":2016,"lang":"en","type":"article","venue":"KITopen","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Artificial intelligence; Speech recognition; Boundary (topology); Natural language processing; Pattern recognition (psychology); Mathematics","score_opus":0.030527414604483313,"score_gpt":0.2520615829131662,"score_spread":0.2215341683086829,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2620638943","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.126893,0.000051957584,0.86032337,0.00085034315,0.001585196,0.0001230604,0.000002238788,0.00023413463,0.009936722],"genre_scores_gemma":[0.9405994,0.000017136803,0.057143547,0.00044527283,0.00035828786,0.000019527703,5.5186575e-7,0.000013057174,0.0014032347],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992045,0.000057796515,0.00012749032,0.00024827832,0.00019512518,0.00016680705],"domain_scores_gemma":[0.99950254,0.0000853393,0.000050124196,0.00023180613,0.00006138485,0.00006883023],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018873638,0.00007978189,0.00008581138,0.000099638106,0.00019004423,0.00014867603,0.00030934182,0.0000471076,0.0005381815],"category_scores_gemma":[0.00006739683,0.000057519323,0.00005643243,0.00021070208,0.000032716453,0.00059124077,0.00010101294,0.000041904605,0.00070560124],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000054775364,0.000021080661,0.00023211882,0.00000146617,0.00001107937,0.0000062803997,0.000040747353,6.02113e-7,0.07498999,0.00029223453,0.00017748754,0.92422146],"study_design_scores_gemma":[0.0010067079,0.000083577535,0.017373681,0.00008351317,0.000017031198,0.0003782068,0.00003833596,0.022667026,0.70970386,0.011720205,0.23632158,0.00060626806],"about_ca_topic_score_codex":0.000065057604,"about_ca_topic_score_gemma":0.00006205456,"teacher_disagreement_score":0.92361516,"about_ca_system_score_codex":0.00009174792,"about_ca_system_score_gemma":0.000055966102,"threshold_uncertainty_score":0.9069312},"labels":[],"label_agreement":null},{"id":"W2624150886","doi":"10.1121/1.4989096","title":"Cross-register speaker identification: The case of infant and adult directed speech","year":2017,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Register (sociolinguistics); Computer science; Speech recognition; Classifier (UML); Speaker identification; Identification (biology); Speaker recognition; Artificial intelligence; Linguistics","score_opus":0.020827259953875438,"score_gpt":0.2903955218247226,"score_spread":0.26956826187084715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2624150886","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55490524,0.00033846297,0.3940711,0.048259452,0.0007325653,0.0003430275,0.000024416539,0.000029112922,0.0012966198],"genre_scores_gemma":[0.9499612,0.00028133354,0.048436824,0.00096213754,0.00011100527,8.2561985e-7,7.2099944e-8,0.0000064414344,0.00024014717],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987647,0.00016322128,0.00046905526,0.00010314028,0.0003556393,0.00014425839],"domain_scores_gemma":[0.99670976,0.00065190025,0.0011188673,0.0009245363,0.0005314918,0.000063438914],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009978274,0.000100045596,0.00024177895,0.000012286163,0.0005535388,0.00017129022,0.0015651162,0.000046380897,0.000043631295],"category_scores_gemma":[0.00094029336,0.000043678872,0.00028604167,0.00012822235,0.0015496868,0.00023124188,0.00040025375,0.00026119986,0.0000035968988],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023578516,0.00046537968,0.0025516367,0.0001418869,0.0008571835,0.00009922234,0.0073259966,0.00014847596,0.041319974,0.00031189647,0.045994285,0.9005483],"study_design_scores_gemma":[0.0023879157,0.00047954477,0.22843042,0.0004377466,0.0010762515,0.013938059,0.005196292,0.66184473,0.068518296,0.010721557,0.006323872,0.000645318],"about_ca_topic_score_codex":0.00017661601,"about_ca_topic_score_gemma":0.000004379572,"teacher_disagreement_score":0.89990294,"about_ca_system_score_codex":0.000016956055,"about_ca_system_score_gemma":0.00004951562,"threshold_uncertainty_score":0.5709886},"labels":[],"label_agreement":null},{"id":"W2678453873","doi":"10.1109/ccece.2017.7946643","title":"Feature fusion techniques based training MLP for speaker identification system","year":2017,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Feature (linguistics); Speech recognition; Artificial intelligence; Speaker identification; Identification (biology); Speaker recognition; Pattern recognition (psychology); Feature extraction; Speaker diarisation; Training (meteorology); Training set","score_opus":0.060063312929288896,"score_gpt":0.2943440950155201,"score_spread":0.2342807820862312,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2678453873","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010493672,0.0000056445183,0.9709856,0.004188524,0.00030698712,0.00032246206,0.0000044936132,0.00050257624,0.02263438],"genre_scores_gemma":[0.5894441,0.0000011562406,0.4077189,0.00021848152,0.00009533959,0.00007839405,0.000005015306,0.000007257368,0.0024313556],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993189,0.000023974466,0.00011289881,0.00026223552,0.00014814349,0.00013383965],"domain_scores_gemma":[0.998962,0.00006665444,0.00014166205,0.0006631736,0.00011846416,0.000048085476],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004766479,0.000080259015,0.000103808736,0.00007432574,0.00045321367,0.000596982,0.0006408762,0.0000744052,0.000018207329],"category_scores_gemma":[0.00011778482,0.00006575775,0.00007700293,0.000041869855,0.00001959605,0.00040778227,0.000047666665,0.00004286659,0.000038433584],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000056206754,0.000020765228,0.00004202632,0.000045128356,0.000005877948,0.0000034090676,0.00011070796,1.6433563e-7,0.017335385,0.021226225,0.006750699,0.954454],"study_design_scores_gemma":[0.00048378392,0.000063813866,0.005641522,0.00024830803,0.000019340114,0.000025803201,0.00033097665,0.20616588,0.72584075,0.0012115494,0.059568062,0.00040020596],"about_ca_topic_score_codex":0.000007071874,"about_ca_topic_score_gemma":0.000010557377,"teacher_disagreement_score":0.95405376,"about_ca_system_score_codex":0.000030334748,"about_ca_system_score_gemma":0.000030795545,"threshold_uncertainty_score":0.57567114},"labels":[],"label_agreement":null},{"id":"W2688145745","doi":"10.1109/ccece.2017.7946645","title":"Performance evaluation of mixtures of PLDA and conventional PLDA for a small-set speaker verification system","year":2017,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Speech recognition; Speaker verification; Signal-to-noise ratio (imaging); Set (abstract data type); Speech enhancement; Noise (video); Probabilistic logic; Pattern recognition (psychology); Speaker recognition; Artificial intelligence; Noise reduction; Telecommunications","score_opus":0.10954139473737029,"score_gpt":0.3081377052994708,"score_spread":0.19859631056210053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2688145745","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.918621,0.00003371264,0.07437894,0.00015387901,0.00018256514,0.0003639431,0.000013843927,0.000020505106,0.006231628],"genre_scores_gemma":[0.97362393,0.0000068469876,0.026195189,0.000010038817,0.000016257558,0.00003505928,0.0000059661634,0.000002346364,0.00010436221],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99932635,0.00003668474,0.00019011289,0.00014596539,0.00023785203,0.000063025196],"domain_scores_gemma":[0.99896663,0.00006139393,0.00024177179,0.00030828678,0.0003982872,0.000023635499],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00085123756,0.000051595336,0.00010536698,0.000050000654,0.00010481619,0.000047665664,0.00024252107,0.000034071207,0.00003027149],"category_scores_gemma":[0.00011805934,0.000043922384,0.000039288054,0.000026412825,0.00004745396,0.00021887895,0.000034465123,0.0000162578,0.0000040857985],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000112947186,0.00016673592,0.017239334,0.00089740264,0.00014051332,3.2577393e-7,0.0006480538,0.000032675605,0.023797357,0.10888183,0.00094057573,0.8471422],"study_design_scores_gemma":[0.0010605437,0.00007746293,0.17403305,0.00012868532,0.00004599204,0.000009218692,0.00009951748,0.692061,0.13162416,0.0005344197,0.00021962951,0.00010629024],"about_ca_topic_score_codex":0.00002319003,"about_ca_topic_score_gemma":0.000011082458,"teacher_disagreement_score":0.84703594,"about_ca_system_score_codex":0.000016146592,"about_ca_system_score_gemma":0.000050685783,"threshold_uncertainty_score":0.17911029},"labels":[],"label_agreement":null},{"id":"W2724202180","doi":"","title":"Development of the Vietnamese speech assessment","year":2018,"lang":"vi","type":"article","venue":"Charles Sturt University Research Output (CRO)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Vietnamese; Computer science; Speech recognition; Linguistics; Natural language processing","score_opus":0.12962657413773948,"score_gpt":0.3461056309661509,"score_spread":0.2164790568284114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2724202180","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7281843,0.0003243845,0.014605885,0.008478806,0.004549614,0.0022977507,0.00016391062,0.00021429201,0.24118105],"genre_scores_gemma":[0.8577489,0.00041510517,0.076432966,0.00016488651,0.0004734372,0.000004100684,0.0000051730012,0.000038313843,0.06471708],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9939767,0.0011213416,0.00043591205,0.0009251822,0.0024037412,0.0011371033],"domain_scores_gemma":[0.99532384,0.00047418592,0.00025169848,0.0014255766,0.002104473,0.00042021147],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0031453527,0.00033421698,0.00045218485,0.00059268496,0.0022608002,0.00027937803,0.0040374333,0.00024830984,0.0018235777],"category_scores_gemma":[0.00033929394,0.0002814197,0.000284578,0.002134593,0.0016980972,0.00050002994,0.004011516,0.00090146525,0.0007354687],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002504924,0.0017373678,0.0058526704,0.00034143843,0.00070775184,0.00027755686,0.03943312,8.73827e-7,0.006221148,0.013191158,0.071804956,0.86018145],"study_design_scores_gemma":[0.0016460893,0.00039770114,0.07056067,0.0007533945,0.00006421629,0.000025986235,0.020376168,0.0025979143,0.056089915,0.00045365942,0.84621817,0.00081613695],"about_ca_topic_score_codex":0.00019470956,"about_ca_topic_score_gemma":0.0007864958,"teacher_disagreement_score":0.85936534,"about_ca_system_score_codex":0.0010477707,"about_ca_system_score_gemma":0.0026066678,"threshold_uncertainty_score":0.9999638},"labels":[],"label_agreement":null},{"id":"W2735115738","doi":"","title":"Forced Alignment for Understudied Language Varieties: Testing Prosodylab-Aligner with Tongan Data.","year":2018,"lang":"en","type":"article","venue":"ScholarSpace (University of Hawaii at Manoa)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Process (computing); Speech recognition; Transcription (linguistics); Documentation; Natural language processing; Field (mathematics); Phonetic transcription; Segmentation; Artificial intelligence; Linguistics; Programming language","score_opus":0.0590055234052734,"score_gpt":0.2485947740864726,"score_spread":0.1895892506811992,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2735115738","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25594753,0.000086193846,0.6922896,0.0076730354,0.00029669167,0.0013386342,0.00011393538,0.0004931511,0.041761227],"genre_scores_gemma":[0.59319836,0.0000070625547,0.39796934,0.0002389423,0.00005820528,0.0000019833283,0.000028863256,0.000020108628,0.008477136],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9985418,0.0000667184,0.000093619026,0.0005984872,0.00036921067,0.00033017612],"domain_scores_gemma":[0.9982523,0.00019177154,0.00017438228,0.0009706407,0.00028952776,0.0001214016],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049039617,0.00016774832,0.00023630032,0.00012972184,0.00068099896,0.000089182606,0.0012181739,0.00007784195,0.00008942119],"category_scores_gemma":[0.00010384578,0.00017141717,0.000055510292,0.00041210593,0.00022248614,0.0009948798,0.00086560065,0.0000913075,0.00006619842],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027575656,0.002005995,0.017736768,0.0014158468,0.0034830438,0.000874063,0.08878697,0.00006000612,0.23507707,0.20623147,0.183828,0.2577432],"study_design_scores_gemma":[0.032233026,0.010309774,0.03239641,0.0016016843,0.0016442748,0.00047021333,0.3210152,0.07840885,0.19719687,0.0076429793,0.30978444,0.0072962604],"about_ca_topic_score_codex":0.000115105744,"about_ca_topic_score_gemma":0.0007803723,"teacher_disagreement_score":0.33725086,"about_ca_system_score_codex":0.00011565376,"about_ca_system_score_gemma":0.00009005462,"threshold_uncertainty_score":0.6990189},"labels":[],"label_agreement":null},{"id":"W2740120517","doi":"","title":"Learning Latent Space Models with Angular Constraints","year":2017,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Space (punctuation); Artificial intelligence","score_opus":0.06111164871674642,"score_gpt":0.29273717667035065,"score_spread":0.23162552795360425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2740120517","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048544157,0.000025028736,0.58111477,0.011518435,0.00047879652,0.00017697808,0.000006773609,0.00040870975,0.35772637],"genre_scores_gemma":[0.9711512,0.000051525116,0.025162885,0.00017584527,0.00006049692,0.000010674552,0.000011030096,0.0000137744055,0.00336258],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99856126,0.00010406215,0.00016560503,0.00042151252,0.00051818206,0.00022936375],"domain_scores_gemma":[0.99892944,0.00007979475,0.00027329137,0.00034898517,0.0002617833,0.0001066748],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030802275,0.00017572852,0.00016740727,0.00014466676,0.0005328725,0.0009642037,0.0011659858,0.000057304114,0.00064709026],"category_scores_gemma":[0.00023533592,0.0001539553,0.00006441435,0.000043258733,0.00013328699,0.0006860836,0.00021310263,0.00055734307,0.00021709235],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048327267,0.000060352195,0.008896877,0.000004779106,0.000089098765,0.0001621635,0.00043494668,0.003625212,0.00067311374,0.4549626,0.000021077962,0.5310214],"study_design_scores_gemma":[0.0006048146,0.0001897262,0.004134073,0.0001378378,0.0000061941464,0.00006769738,0.00007926946,0.98597264,0.0008415968,0.005985197,0.0017111134,0.00026982525],"about_ca_topic_score_codex":0.000106817955,"about_ca_topic_score_gemma":0.000024599427,"teacher_disagreement_score":0.9823474,"about_ca_system_score_codex":0.000044348075,"about_ca_system_score_gemma":0.00006668504,"threshold_uncertainty_score":0.9297838},"labels":[],"label_agreement":null},{"id":"W27446868","doi":"","title":"Speech analysis and synthesis based on ARMA lattice model.","year":2003,"lang":"en","type":"article","venue":"Scholarship at UWindsor (University of Windsor)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Speech recognition; Computer science; Speech synthesis; Natural language processing; Artificial intelligence","score_opus":0.025008954915785735,"score_gpt":0.21870487279382475,"score_spread":0.19369591787803903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W27446868","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8843927,0.000034405064,0.0927585,0.0012935922,0.00007061883,0.00017814369,0.0000354388,0.00015530165,0.021081312],"genre_scores_gemma":[0.87586766,0.000016650663,0.122656666,0.00036183748,0.0000072532816,6.485321e-7,0.000003024007,0.0000123249265,0.0010739199],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99775606,0.0003931606,0.00018892948,0.00068706373,0.0006064551,0.0003683037],"domain_scores_gemma":[0.9980512,0.0004836995,0.00018545959,0.00081469305,0.0001711613,0.00029375762],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010276176,0.0002441458,0.00043841705,0.00094186125,0.0004538825,0.00009417387,0.00080493913,0.00019672075,0.0005781125],"category_scores_gemma":[0.0003813616,0.0002886812,0.0003254003,0.0015544965,0.00014501244,0.000760963,0.00015023767,0.00027610958,0.00014297443],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016116512,0.0057364358,0.53429997,0.0005911973,0.0061872313,0.001739281,0.006371571,0.011177611,0.026451426,0.069735385,0.0019680692,0.3341302],"study_design_scores_gemma":[0.0038843374,0.00032445838,0.285681,0.00021224633,0.0024250506,0.000067312154,0.0009388067,0.5926144,0.10179017,0.0065704486,0.00337561,0.0021161349],"about_ca_topic_score_codex":0.000029035298,"about_ca_topic_score_gemma":0.000093023715,"teacher_disagreement_score":0.5814368,"about_ca_system_score_codex":0.0000934089,"about_ca_system_score_gemma":0.00009367814,"threshold_uncertainty_score":0.99995655},"labels":[],"label_agreement":null},{"id":"W2747874407","doi":"10.21437/interspeech.2017-1386","title":"Montreal Forced Aligner: Trainable Text-Speech Alignment Using Kaldi","year":2017,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1124,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Speech recognition; Natural language processing; Linguistics; Artificial intelligence","score_opus":0.04401314992965729,"score_gpt":0.2826153983171813,"score_spread":0.238602248387524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2747874407","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.058749415,0.000035210884,0.45184177,0.0026784947,0.00052463537,0.00034439063,0.0000045218703,0.0003659739,0.4854556],"genre_scores_gemma":[0.7617482,0.000014450066,0.22509503,0.00084162666,0.00011478662,0.000016287639,0.0000012335718,0.000015744194,0.012152635],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986419,0.000039020633,0.00020809837,0.00039980985,0.0003211566,0.00038998446],"domain_scores_gemma":[0.9985608,0.00005050286,0.00012877544,0.0010305139,0.00007166461,0.00015775138],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031477542,0.0001576163,0.00019046027,0.000079114405,0.0006521074,0.0007365605,0.0011548242,0.000072297385,0.00037977277],"category_scores_gemma":[0.00006845491,0.00013338155,0.00011423514,0.00006463321,0.000054481727,0.0007618038,0.00026057812,0.000054826756,0.00018045394],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007904634,0.00011269739,0.00021630485,0.000010347196,0.000048843714,0.00014185859,0.0003334622,0.000012933362,0.009439431,0.028434327,0.005293717,0.9559482],"study_design_scores_gemma":[0.0024718358,0.0001886413,0.007912846,0.00009378954,0.00006021287,0.00035724693,0.00053244235,0.4718942,0.44815266,0.03384263,0.033108015,0.0013854811],"about_ca_topic_score_codex":0.0011452339,"about_ca_topic_score_gemma":0.00014709997,"teacher_disagreement_score":0.95456266,"about_ca_system_score_codex":0.00006460335,"about_ca_system_score_gemma":0.000055465378,"threshold_uncertainty_score":0.71026695},"labels":[],"label_agreement":null},{"id":"W2756663932","doi":"10.3233/978-1-61499-798-6-322","title":"Cloud-Based Speech Technology for Assistive Technology Applications (CloudCAST)","year":2017,"lang":"en","type":"article","venue":"Studies in health technology and informatics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Rehabilitation Institute","funders":"","keywords":"Cloud computing; Assistive technology; Computer science; Speech technology; Multimedia; World Wide Web; Human–computer interaction; Speech synthesis; Speech recognition; Operating system","score_opus":0.0717944582266798,"score_gpt":0.3826523058363527,"score_spread":0.3108578476096729,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2756663932","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024014669,0.0055146297,0.79661506,0.16265672,0.0013495912,0.0041311304,0.00007126137,0.0021869144,0.0034600024],"genre_scores_gemma":[0.3408313,0.0021321469,0.65311676,0.0015294026,0.000056140103,0.0022142332,0.0000042929096,0.000018758066,0.00009697198],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981515,0.000018192886,0.0008214947,0.00030708112,0.00012125421,0.0005805021],"domain_scores_gemma":[0.997508,0.00022963062,0.0006982067,0.0011915829,0.00031460228,0.00005799083],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0006817413,0.0002301724,0.000559369,0.0018702109,0.0014491513,0.00005944619,0.0013330742,0.00048944517,0.0000020022828],"category_scores_gemma":[0.001182708,0.0002143679,0.000044008484,0.0010477515,0.0015364515,0.00028310405,0.00069746084,0.00044823135,0.000022212835],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009530073,0.000061191466,0.005901792,0.00035804225,0.000042499698,0.000003777294,0.00015670796,0.0000015073537,0.0000025401246,0.27936655,0.00062650145,0.7134694],"study_design_scores_gemma":[0.004102342,0.0018425507,0.0021387462,0.0009227427,0.000038234863,0.00032604765,0.013195702,0.029290624,0.0073603927,0.55875975,0.38084015,0.0011827083],"about_ca_topic_score_codex":0.0000044274725,"about_ca_topic_score_gemma":0.0000650281,"teacher_disagreement_score":0.71228665,"about_ca_system_score_codex":0.00014405379,"about_ca_system_score_gemma":0.00018673652,"threshold_uncertainty_score":0.9998508},"labels":[],"label_agreement":null},{"id":"W2757362440","doi":"10.3390/cryptography1030016","title":"A Text-Independent Speaker Authentication System for Mobile Devices","year":2017,"lang":"en","type":"article","venue":"Cryptography","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Computer science; Authentication (law); Classifier (UML); Biometrics; Naive Bayes classifier; Mobile device; Reliability (semiconductor); Artificial intelligence; Speaker recognition; Speech recognition; Data mining; Machine learning; Computer security; Support vector machine; World Wide Web","score_opus":0.023812572285493803,"score_gpt":0.274783175883733,"score_spread":0.2509706035982392,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2757362440","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06833901,0.00024900574,0.911963,0.0005025683,0.0012548587,0.0009533829,0.000022500588,0.00045551418,0.01626017],"genre_scores_gemma":[0.93273574,0.0000063878883,0.066772416,0.000074846386,0.00009169519,0.0002695838,0.0000035384799,0.000009252578,0.000036530768],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990483,0.000026551816,0.00017811194,0.00033511955,0.00020072337,0.00021119021],"domain_scores_gemma":[0.99862987,0.00007302745,0.00019357743,0.0008822311,0.00012776941,0.00009354928],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028139495,0.0001125893,0.00013717024,0.00016205573,0.0005392512,0.0006952565,0.0009958603,0.00006111263,0.00002669345],"category_scores_gemma":[0.000035855956,0.00009957747,0.00019622067,0.00010175503,0.00005469842,0.00044259566,0.000095769545,0.00004494554,0.00014054627],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034695997,0.00026718332,0.008887945,0.00025664846,0.0002832719,0.000012738924,0.00088442315,0.0000016629999,0.0044250945,0.24846032,0.0020909351,0.7343951],"study_design_scores_gemma":[0.0057151103,0.0009360172,0.30225864,0.00097330613,0.00051466917,0.00016173958,0.0028752321,0.070889175,0.13344622,0.051744185,0.4274595,0.0030262019],"about_ca_topic_score_codex":0.000011734927,"about_ca_topic_score_gemma":0.000014016775,"teacher_disagreement_score":0.86439675,"about_ca_system_score_codex":0.000014347975,"about_ca_system_score_gemma":0.00002046825,"threshold_uncertainty_score":0.67043746},"labels":[],"label_agreement":null},{"id":"W2766171655","doi":"10.1016/j.csl.2017.10.006","title":"Application of the pairwise variability index of speech rhythm with particle swarm optimization to the classification of native and non-native accents","year":2017,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick; Université de Moncton; Université du Québec à Trois-Rivières","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Particle swarm optimization; Support vector machine; Pairwise comparison; Metric (unit); Artificial intelligence; Speech recognition; Pattern recognition (psychology); Rhythm; Generalization; Point (geometry); Machine learning; Mathematics","score_opus":0.015791004986658013,"score_gpt":0.2634387689169221,"score_spread":0.24764776393026408,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2766171655","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36791927,0.000006124338,0.63039106,0.00075781404,0.00006357316,0.00047013952,0.000009875157,0.000014234351,0.00036790766],"genre_scores_gemma":[0.91535527,0.0000029570758,0.084474064,0.00007409378,0.00004346644,0.00002374622,0.000001997661,0.000006523304,0.000017890558],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99876934,0.00015389328,0.00029474494,0.00030997756,0.00034506337,0.00012695589],"domain_scores_gemma":[0.9977242,0.00016594627,0.0005354361,0.0011557563,0.0003676511,0.000051017883],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061641354,0.0001195088,0.00020552076,0.000050108207,0.00015282359,0.00007122984,0.0009076523,0.000044304892,0.000008299858],"category_scores_gemma":[0.00015240024,0.00007276427,0.000050026894,0.00028584944,0.00018694937,0.00028158375,0.00038128626,0.00008946082,0.0000018284738],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000061018225,0.000264091,0.02949327,0.000066802895,0.000072709176,0.0000028144889,0.007908875,0.0015413582,0.0030165208,0.0020240147,0.000060051825,0.9554885],"study_design_scores_gemma":[0.00036361042,0.0000649084,0.3627777,0.000048792892,0.00001613184,0.000008202548,0.00017571474,0.5086588,0.12754491,0.00022051705,0.000025855172,0.000094818985],"about_ca_topic_score_codex":0.00013380143,"about_ca_topic_score_gemma":0.00006481544,"teacher_disagreement_score":0.9553937,"about_ca_system_score_codex":0.000030495365,"about_ca_system_score_gemma":0.000047724556,"threshold_uncertainty_score":0.29672408},"labels":[],"label_agreement":null},{"id":"W2766244607","doi":"10.23919/eusipco.2017.8081177","title":"Spoofing detection employing infinite impulse response — constant Q transform-based feature representations","year":2017,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Spoofing attack; Computer science; Speech recognition; Infinite impulse response; Mel-frequency cepstrum; Bottleneck; Pattern recognition (psychology); Cepstrum; Speaker recognition; Artificial intelligence; Word error rate; Finite impulse response; Feature extraction; Filter (signal processing); Algorithm; Digital filter; Computer vision","score_opus":0.03334548812332466,"score_gpt":0.298301219258045,"score_spread":0.2649557311347203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2766244607","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.102588475,0.00001326039,0.85815245,0.009471161,0.0003981842,0.00027171266,0.0000076000215,0.00042476977,0.028672365],"genre_scores_gemma":[0.9436388,0.0000054371526,0.05489071,0.00054652354,0.00003202676,0.000025597916,0.0000014586236,0.0000096911135,0.0008497803],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99883837,0.00013771263,0.0001927178,0.00034776906,0.00024234156,0.00024106573],"domain_scores_gemma":[0.9983519,0.00041209953,0.00012217506,0.0008806181,0.00011615564,0.00011706363],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006258725,0.00013215207,0.00013785856,0.00020203608,0.001018955,0.00074993307,0.0005864453,0.00008850903,0.000100374804],"category_scores_gemma":[0.0006038426,0.00011853682,0.0001218,0.00016021523,0.00008089784,0.0008226568,0.000054231492,0.00015693028,0.000084124964],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003765263,0.00007410585,0.0020300918,0.000014249718,0.00003473181,0.00011750974,0.00053343654,0.00003212479,0.045391016,0.0023219686,0.00043559028,0.9486387],"study_design_scores_gemma":[0.0026373018,0.00022008749,0.09404655,0.00014080941,0.000042107476,0.00016664379,0.00035793486,0.12730928,0.75660366,0.0052425354,0.012371132,0.00086196826],"about_ca_topic_score_codex":0.00008472692,"about_ca_topic_score_gemma":0.0001852055,"teacher_disagreement_score":0.9477767,"about_ca_system_score_codex":0.000042746145,"about_ca_system_score_gemma":0.00010401098,"threshold_uncertainty_score":0.78370816},"labels":[],"label_agreement":null},{"id":"W2766944760","doi":"10.48550/arxiv.1711.00333","title":"An Experimental Analysis of the Power Consumption of Convolutional Neural Networks for Keyword Spotting","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Keyword spotting; Computer science; Proxy (statistics); Convolutional neural network; Predictive power; Inference; Spotting; Artificial intelligence; Footprint; Artificial neural network; Data mining; Machine learning; Geography","score_opus":0.10422870171118952,"score_gpt":0.23768537631068737,"score_spread":0.13345667459949784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2766944760","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.690936,0.00003552316,0.3082021,0.000016652315,0.0003482243,0.00017620868,0.000040395207,0.000025070163,0.00021979513],"genre_scores_gemma":[0.9980605,0.00001177805,0.0017612868,0.00002718754,0.000022607037,0.0000012599863,0.000020049527,0.0000058585047,0.00008944214],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989162,0.00012655651,0.00021254244,0.0004880645,0.00009526467,0.00016138956],"domain_scores_gemma":[0.99799037,0.00015436824,0.00061484217,0.00097082305,0.00020604554,0.0000635609],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025516454,0.00015180101,0.00033384078,0.00023429611,0.00018713111,0.000050341925,0.0013990424,0.00015679425,0.00007249169],"category_scores_gemma":[0.000036956855,0.00014431229,0.0005018446,0.00025059935,0.00021388175,0.00022520988,0.00052676455,0.00015561249,0.0000011278371],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025563344,0.00071990525,0.14990498,0.000093037655,0.0023173024,0.000023240622,0.000730749,0.72184974,0.0019863744,0.118530154,0.0001433357,0.0034455776],"study_design_scores_gemma":[0.00024751833,0.000029207948,0.033124134,0.000031806296,0.000315454,8.6300525e-7,0.000061124934,0.9634898,0.001732034,0.000809155,0.000011115776,0.00014780776],"about_ca_topic_score_codex":0.000050503568,"about_ca_topic_score_gemma":0.000019127672,"teacher_disagreement_score":0.3071245,"about_ca_system_score_codex":0.00006634729,"about_ca_system_score_gemma":0.000060708895,"threshold_uncertainty_score":0.58848846},"labels":[],"label_agreement":null},{"id":"W2770699629","doi":"10.1121/1.5014453","title":"Dialect contact and word-specific phonetics: North Koreans in Seoul","year":2017,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Voice-onset time; Vowel; Word (group theory); Phonetics; Linguistics; History; Audiology; Geography; Psychology; Medicine","score_opus":0.02116397393980148,"score_gpt":0.24484580763330033,"score_spread":0.22368183369349884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2770699629","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36045703,0.0006667252,0.6157112,0.021222008,0.000603821,0.0002277799,0.00000936207,0.000017700542,0.0010843569],"genre_scores_gemma":[0.9372891,0.0017733783,0.06002889,0.00077205326,0.000096773154,5.315061e-7,4.633085e-8,0.000005855358,0.00003334201],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9989617,0.00013259408,0.00030294148,0.0000920983,0.00033008138,0.00018059218],"domain_scores_gemma":[0.9982246,0.000646355,0.0004671335,0.00048811545,0.00009741229,0.00007636254],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051356695,0.000096999,0.00026016549,0.000017931803,0.00026510344,0.00008984051,0.0013808212,0.000038313356,0.000024362147],"category_scores_gemma":[0.00024126594,0.000051091414,0.00020441266,0.00012098067,0.0004858464,0.00015279948,0.00027725397,0.00032648473,0.0000038907992],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013583795,0.00027534532,0.008366579,0.000027199585,0.00017849913,0.000013324211,0.0039533284,0.00019434979,0.008176902,0.000051698134,0.018822026,0.9598049],"study_design_scores_gemma":[0.0020347985,0.0005641561,0.79449433,0.00031773816,0.00018196563,0.00033707955,0.0018758869,0.18066454,0.004724138,0.005649497,0.008709436,0.00044645357],"about_ca_topic_score_codex":0.000049816572,"about_ca_topic_score_gemma":0.0000065713652,"teacher_disagreement_score":0.95935845,"about_ca_system_score_codex":0.000031617354,"about_ca_system_score_gemma":0.000051474442,"threshold_uncertainty_score":0.25659326},"labels":[],"label_agreement":null},{"id":"W2773275010","doi":"","title":"A Biological Approach to Speech Spectrography","year":2017,"lang":"en","type":"article","venue":"CMBES Proceedings","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Natural language processing; Artificial intelligence; Speech recognition","score_opus":0.0544217407407934,"score_gpt":0.2710896909148267,"score_spread":0.2166679501740333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2773275010","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34059852,0.000027163596,0.027627923,0.0021420298,0.00019145696,0.00033010397,0.0000017591805,0.00048217195,0.62859887],"genre_scores_gemma":[0.69339657,0.000011990186,0.30565307,0.00054864236,0.00015121457,0.000041376876,4.487841e-7,0.000006874041,0.00018985778],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99880636,0.0000036784456,0.0001395699,0.0005065538,0.00020955392,0.00033427333],"domain_scores_gemma":[0.99922234,0.000017029713,0.00008764865,0.00034847428,0.00013066853,0.00019383909],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027942902,0.00014455931,0.00017514794,0.00014375904,0.00043971126,0.0009816226,0.0017157122,0.00008091662,0.000022130198],"category_scores_gemma":[0.0002704998,0.00011459342,0.000110253495,0.00020309813,0.00009095492,0.0004934133,0.0003888012,0.00011257104,0.0003005839],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028307973,0.00046326057,0.024071984,0.000036503796,0.000056770332,0.000021468622,0.0008053299,5.5736542e-8,0.017572047,0.49105573,0.020454863,0.44543368],"study_design_scores_gemma":[0.0018235713,0.0011090569,0.40536427,0.0001853857,0.000043424534,0.00090123917,0.0012481622,0.007202188,0.28910598,0.080991074,0.20914695,0.002878707],"about_ca_topic_score_codex":0.00000858452,"about_ca_topic_score_gemma":4.877564e-7,"teacher_disagreement_score":0.628409,"about_ca_system_score_codex":0.000017091754,"about_ca_system_score_gemma":0.000011845137,"threshold_uncertainty_score":0.94658095},"labels":[],"label_agreement":null},{"id":"W2791919658","doi":"","title":"Study by simulation of the acoustic characteristics of the vocal tract with losses","year":2005,"lang":"en","type":"article","venue":"Canadian acoustics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formant; Vocal tract; Acoustics; Transfer function; Lossy compression; Computer science; Physics; Engineering; Speech recognition","score_opus":0.015306049973742212,"score_gpt":0.2262474016236843,"score_spread":0.2109413516499421,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2791919658","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93287516,0.000014436788,0.06547598,0.00052056246,0.00022000968,0.00034515918,0.00012505066,0.000015971154,0.0004076861],"genre_scores_gemma":[0.9985004,0.0000019542538,0.0009154713,0.00035330807,0.0000472726,0.0000033720926,0.0000012242181,0.000009179282,0.00016780946],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9990768,0.000065427615,0.00023914443,0.00014594028,0.0002884829,0.00018423889],"domain_scores_gemma":[0.99884874,0.00020196945,0.00016719509,0.0004922527,0.00017441771,0.000115438444],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013199213,0.00010409218,0.00014711764,0.00005736965,0.00011982324,0.00004558285,0.00065177947,0.00005081697,0.00003066744],"category_scores_gemma":[0.00023345911,0.00006217979,0.00004560995,0.00033284663,0.00010612853,0.00009144125,0.00003817352,0.00011800214,0.000004996467],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006220764,0.0029566737,0.1715418,0.00023040923,0.0004122272,0.00008957885,0.009104047,0.20808952,0.042659763,0.00097641774,0.013356984,0.55052036],"study_design_scores_gemma":[0.00050531555,0.00016967046,0.6338676,0.00007837041,0.00016437509,0.000023737728,0.0005811141,0.36051968,0.0024683904,0.000053591426,0.0012918189,0.00027632323],"about_ca_topic_score_codex":0.000906972,"about_ca_topic_score_gemma":0.0031195015,"teacher_disagreement_score":0.55024403,"about_ca_system_score_codex":0.000094601106,"about_ca_system_score_gemma":0.00042311873,"threshold_uncertainty_score":0.25356182},"labels":[],"label_agreement":null},{"id":"W2793646841","doi":"10.1109/icassp.2018.8462037","title":"Extracting Domain Invariant Features by Unsupervised Learning for Robust Automatic Speech Recognition","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Autoencoder; Computer science; Robustness (evolution); Invariant (physics); Speech recognition; Word error rate; Artificial intelligence; Pattern recognition (psychology); Latent variable; Domain (mathematical analysis); Encoder; Natural language processing; Deep learning; Mathematics","score_opus":0.050654055380827755,"score_gpt":0.26840475806392855,"score_spread":0.2177507026831008,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2793646841","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019743513,0.00011617721,0.9566992,0.0015659899,0.001201263,0.0012573007,0.00003762005,0.0013904304,0.017988518],"genre_scores_gemma":[0.0058948034,0.000047389094,0.990518,0.00062624656,0.00041249837,0.00029391726,0.0003049901,0.000059008005,0.0018431507],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99683404,0.00035817357,0.0006297094,0.00114311,0.00048202818,0.0005529176],"domain_scores_gemma":[0.99731773,0.000952236,0.00046431783,0.0006973481,0.00037813402,0.00019023354],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015566251,0.00047271603,0.0005334698,0.00030658496,0.0004188742,0.0010942568,0.0011414313,0.0005729147,0.0009495032],"category_scores_gemma":[0.00090260635,0.0004438683,0.00031590665,0.00025252262,0.00005704313,0.00048383698,0.0006742286,0.0007981352,0.00029713448],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014038804,0.00013208723,0.000020369389,0.00028087676,0.00011467538,0.000018336956,0.0004399786,0.00002092427,0.0014355916,0.00014434778,0.03204831,0.9653305],"study_design_scores_gemma":[0.002150183,0.0003722806,0.00050805544,0.0019006961,0.00019714996,0.00036672765,0.0010951397,0.82255393,0.08149391,0.076103896,0.010255155,0.0030028652],"about_ca_topic_score_codex":0.00011016151,"about_ca_topic_score_gemma":0.00004038808,"teacher_disagreement_score":0.9623276,"about_ca_system_score_codex":0.0001372434,"about_ca_system_score_gemma":0.00018475426,"threshold_uncertainty_score":0.99996376},"labels":[],"label_agreement":null},{"id":"W2795552730","doi":"10.1177/0023830918765012","title":"Investigating Perceptual Biases, Data Reliability, and Data Discovery in a Methodology for Collecting Speech Errors From Audio Recordings","year":2018,"lang":"en","type":"article","venue":"Language and Speech","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Computer science; Speech recognition; Reliability (semiconductor); Perception; Sound quality; Sound recording and reproduction; Natural language processing; Psychology; Acoustics","score_opus":0.231578198380963,"score_gpt":0.3871973809097454,"score_spread":0.15561918252878243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2795552730","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9678424,0.00024139047,0.029597117,0.00090533996,0.00024436502,0.00030369256,0.00034558456,0.00008276013,0.00043734355],"genre_scores_gemma":[0.15955119,0.00005211399,0.838592,0.00087729207,0.00033987206,0.000009929631,0.0002638745,0.000018095949,0.00029565478],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997686,0.00031226035,0.0003520216,0.0011537973,0.00016669101,0.0003291775],"domain_scores_gemma":[0.99550736,0.0027246769,0.000120180106,0.0014854078,0.000052743115,0.00010963025],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024367394,0.00018021317,0.0003538972,0.00014900643,0.00019848149,0.00031615054,0.0012371516,0.00012486285,0.000055951823],"category_scores_gemma":[0.0076191477,0.00016407155,0.000023518951,0.00037432843,0.00020391284,0.0012202091,0.002004089,0.00018376016,0.0000065779122],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042055708,0.00007159427,0.014448134,0.000054762422,0.000043416938,0.000082588034,0.011832404,1.9853435e-7,0.014081808,0.00015629525,0.0052451505,0.9539416],"study_design_scores_gemma":[0.009100369,0.0015068271,0.054572057,0.0018314989,0.00041024815,0.0013408718,0.08015806,0.6693115,0.11182442,0.04749897,0.018161261,0.004283883],"about_ca_topic_score_codex":0.005035441,"about_ca_topic_score_gemma":0.0062626298,"teacher_disagreement_score":0.94965774,"about_ca_system_score_codex":0.000026592445,"about_ca_system_score_gemma":0.000079189675,"threshold_uncertainty_score":0.91213816},"labels":[],"label_agreement":null},{"id":"W2799789537","doi":"10.1109/icassp.2018.8462185","title":"Speech Prediction Using an Adaptive Recurrent Neural Network with Application to Packet Loss Concealment","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Computer science; Packet loss; Speech recognition; Artificial neural network; Recurrent neural network; Network packet; Time delay neural network; Artificial intelligence; Computer network","score_opus":0.058256994380363865,"score_gpt":0.29273672239706344,"score_spread":0.23447972801669958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2799789537","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.085163794,0.000016120337,0.91023517,0.00033376235,0.0010019218,0.0011767937,0.00003130112,0.0003795037,0.001661623],"genre_scores_gemma":[0.4435865,0.000014354056,0.55415064,0.0006726259,0.0011975986,0.00021340213,0.00006651303,0.000030055784,0.00006831032],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974523,0.00018321862,0.00036766272,0.0010893245,0.0005255488,0.00038191496],"domain_scores_gemma":[0.99801284,0.000046717287,0.0002538062,0.0010050252,0.00039435097,0.00028728406],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00042852084,0.00033067737,0.00031016214,0.00012475836,0.00017096598,0.00029142582,0.0007738493,0.00018900275,0.0000679084],"category_scores_gemma":[0.000010779167,0.0002773212,0.000073728384,0.00034620796,0.000068728536,0.00028952942,0.0006086189,0.00028931905,0.00007664827],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000273424,0.0004713855,0.001968145,0.00005567413,0.00017158415,0.000029257904,0.00094312703,0.02342658,0.00011984675,0.0034897304,0.004154549,0.9648967],"study_design_scores_gemma":[0.00021905743,0.0006825742,0.0021915948,0.00021317275,0.00004419349,0.000061464416,0.0000666717,0.9906074,0.0016575686,0.002490033,0.0012603927,0.0005058757],"about_ca_topic_score_codex":0.00015425707,"about_ca_topic_score_gemma":0.00013406217,"teacher_disagreement_score":0.96718085,"about_ca_system_score_codex":0.00025905776,"about_ca_system_score_gemma":0.00015378225,"threshold_uncertainty_score":0.9999679},"labels":[],"label_agreement":null},{"id":"W2801548882","doi":"10.1139/tcsme-2013-0049","title":"IMPROVING EIGENSPACE-BASED FUZZY LOGIC SYSTEM USING A LINEAR INTERPOLATION SCHEME FOR SPEECH PATTERN RECOGNITION","year":2013,"lang":"en","type":"article","venue":"Transactions of the Canadian Society for Mechanical Engineering","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Science Council","keywords":"Eigenvalues and eigenvectors; Scheme (mathematics); Interpolation (computer graphics); Fuzzy logic; Linear interpolation; Computer science; Pattern recognition (psychology); Artificial intelligence; Algorithm; Speech recognition; Mathematics; Image (mathematics)","score_opus":0.03236661978797357,"score_gpt":0.2210443307129645,"score_spread":0.18867771092499094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2801548882","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00553224,0.00000991067,0.99232095,0.00061377545,0.00043495776,0.00085720693,0.00010803239,0.000113700444,0.000009248343],"genre_scores_gemma":[0.43087572,4.800787e-7,0.5687581,0.00016426989,0.000043397242,0.00012562882,0.0000056477647,0.000018765873,0.000008027403],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99903464,0.000014132784,0.00027205504,0.00023143472,0.00013478915,0.0003129373],"domain_scores_gemma":[0.9991123,0.00013804532,0.00009452205,0.00026815312,0.00021985857,0.00016713262],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002683329,0.0001418862,0.00017107396,0.00008822922,0.00026754488,0.0000735371,0.00033257448,0.00016008953,0.00001891734],"category_scores_gemma":[0.00005589,0.00013105446,0.0005694882,0.0002580438,0.000014874031,0.00023296717,0.0000073468896,0.00013993795,0.0000039493716],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023377774,0.00015382572,0.000014691796,0.0028922523,0.0006602907,0.0000016259984,0.0006717445,0.020696811,0.40808573,0.004794385,0.00027274288,0.56173253],"study_design_scores_gemma":[0.00029768565,0.000034643886,0.0000043014325,0.000119527955,0.00004357322,0.0000073490132,0.000095633164,0.966627,0.032362785,0.00020285283,0.000052959604,0.00015170472],"about_ca_topic_score_codex":0.0076331887,"about_ca_topic_score_gemma":0.0029692017,"teacher_disagreement_score":0.9459302,"about_ca_system_score_codex":0.00040569485,"about_ca_system_score_gemma":0.00018938383,"threshold_uncertainty_score":0.99897504},"labels":[],"label_agreement":null},{"id":"W2801849754","doi":"10.5539/ijel.v8n5p27","title":"Acoustic Characteristics of Pakistani English Vowel Sounds","year":2018,"lang":"en","type":"article","venue":"International Journal of English Linguistics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Vowel; Formant; Duration (music); Speech recognition; Statistical analysis; Mid vowel; Acoustics; Space (punctuation); Mathematics; Computer science; Statistics; Physics","score_opus":0.01588246871818565,"score_gpt":0.2761914715595188,"score_spread":0.2603090028413331,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2801849754","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1114407,0.00018561048,0.48536834,0.00013406009,0.23192136,0.000224867,0.00026099084,0.00025843005,0.17020562],"genre_scores_gemma":[0.9436785,0.0000498542,0.033927362,0.0002209411,0.022017034,6.8864716e-7,0.000004066742,0.000014507185,0.000087042834],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99785376,0.000055562916,0.0008929301,0.0001645486,0.0008483615,0.00018486098],"domain_scores_gemma":[0.94122946,0.00044567336,0.00085089495,0.00024352339,0.057097934,0.00013249002],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0005980585,0.00014831722,0.00029061892,0.00031095455,0.00004955328,0.00019372013,0.0014022858,0.0000912852,0.0001567061],"category_scores_gemma":[0.09846366,0.00014051383,0.00016760733,0.00018363365,0.00014703115,0.00015786434,0.0001564292,0.0002400272,0.000014302768],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018114697,0.0058380407,0.032671854,0.0003611687,0.005021811,0.002323526,0.09047053,0.00018212773,0.0042324183,0.40328082,0.18887873,0.2649275],"study_design_scores_gemma":[0.0026583837,0.0011362508,0.011984068,0.0005849272,0.00020813085,0.0000567736,0.0015479154,0.00658321,0.019786406,0.013144817,0.9414488,0.00086030003],"about_ca_topic_score_codex":0.000005154649,"about_ca_topic_score_gemma":0.0000041675853,"teacher_disagreement_score":0.8322378,"about_ca_system_score_codex":0.00009094261,"about_ca_system_score_gemma":0.00020450301,"threshold_uncertainty_score":0.90913033},"labels":[],"label_agreement":null},{"id":"W2806367735","doi":"10.1609/aaai.v32i1.12140","title":"Towards Neural Speaker Modeling in Multi-Party Conversation: The Task, Dataset, and Models","year":2018,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Conversation; Computer science; Task (project management); Component (thermodynamics); Speaker diarisation; Speech recognition; Speaker recognition; Artificial intelligence; Natural language processing; Linguistics","score_opus":0.24178893384203265,"score_gpt":0.3237499481515659,"score_spread":0.08196101430953323,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2806367735","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47821793,0.00008128081,0.48023245,0.027961498,0.0012393586,0.0014443996,0.000096214266,0.00017657837,0.010550297],"genre_scores_gemma":[0.9933143,0.000034964276,0.005906825,0.0006322519,0.00005263921,0.000017839877,0.0000015051595,0.000007136995,0.000032489927],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985029,0.00002996813,0.00041976845,0.00043407033,0.00034738114,0.00026591925],"domain_scores_gemma":[0.99900484,0.00006857837,0.00016946308,0.00028834888,0.00040111798,0.000067641486],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006392052,0.00017395352,0.00018512935,0.000100641126,0.0001925282,0.0002845177,0.0012912847,0.00006559857,0.000056538116],"category_scores_gemma":[0.000248101,0.00011016967,0.000049794457,0.0004257846,0.00038003686,0.0006871814,0.00038502784,0.00022702312,0.000046358928],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001321558,0.0002528644,0.0001759591,0.0000397613,0.000026645157,0.0000017960353,0.01061661,0.00049549266,0.010628304,0.5653155,0.00047063007,0.41184428],"study_design_scores_gemma":[0.000035597328,0.00004908147,0.000056261528,0.00005911738,0.0000059784497,0.000006044065,0.00077086926,0.87896305,0.05744814,0.06243799,0.00004159706,0.00012629379],"about_ca_topic_score_codex":0.00016860222,"about_ca_topic_score_gemma":0.00009860878,"teacher_disagreement_score":0.87846756,"about_ca_system_score_codex":0.000025746967,"about_ca_system_score_gemma":0.00006156102,"threshold_uncertainty_score":0.44925886},"labels":[],"label_agreement":null},{"id":"W2887814324","doi":"10.1109/slt.2018.8639585","title":"Speaker Recognition from Raw Waveform with SincNet","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":94,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Compute Canada","keywords":"Computer science; Sinc function; Waveform; Convolutional neural network; Speech recognition; Speaker recognition; Filter (signal processing); Formant; Artificial intelligence; Pattern recognition (psychology); Convolution (computer science); Artificial neural network; Telecommunications; Computer vision","score_opus":0.0396549809171314,"score_gpt":0.23259951903919576,"score_spread":0.19294453812206436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2887814324","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03824553,0.0000343211,0.71971154,0.0014292835,0.0014111198,0.00046449917,0.00005979059,0.00081499957,0.23782888],"genre_scores_gemma":[0.114534386,0.00009229768,0.8778856,0.0028405306,0.0011094516,0.000096895266,0.0005167275,0.000055460678,0.0028686943],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979482,0.00007669192,0.00031552254,0.0009078092,0.0004505235,0.0003011956],"domain_scores_gemma":[0.99814934,0.00012461685,0.00020085511,0.0010887436,0.00027714725,0.00015928243],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00021670129,0.00033467283,0.00033932982,0.00016598353,0.00009168003,0.0004942781,0.00093836477,0.00030166513,0.004048522],"category_scores_gemma":[0.00004059442,0.00024588205,0.00012845104,0.00016671256,0.00008511487,0.00031515933,0.00078734785,0.0003352264,0.003838398],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055231976,0.0002042236,0.000174362,0.000039349594,0.00024573016,0.00009032014,0.00049969915,0.0000034060947,0.00012685871,0.000495645,0.021729428,0.97633576],"study_design_scores_gemma":[0.00344464,0.0008187801,0.014875671,0.0023768356,0.0003844658,0.00025553067,0.00033901577,0.14032505,0.263363,0.50719595,0.060545396,0.0060756495],"about_ca_topic_score_codex":0.00043831146,"about_ca_topic_score_gemma":0.00028453782,"teacher_disagreement_score":0.9702601,"about_ca_system_score_codex":0.000079924204,"about_ca_system_score_gemma":0.00015265065,"threshold_uncertainty_score":0.99999934},"labels":[],"label_agreement":null},{"id":"W2896779944","doi":"10.1121/1.5067620","title":"Do low intelligibility voices induce false memories?","year":2018,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Variation (astronomy); False memory; Intelligibility (philosophy); Priming (agriculture); Psychology; Computer science; Linguistics; Cognitive psychology; Recall","score_opus":0.024414868188692044,"score_gpt":0.2836451154918068,"score_spread":0.2592302473031148,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2896779944","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07892975,0.00014530569,0.90921545,0.010133641,0.0006818859,0.00010615206,0.0000036805084,0.000023308821,0.0007608452],"genre_scores_gemma":[0.84440863,0.00017947001,0.15216878,0.0028398966,0.00033346238,5.3133965e-7,3.780523e-8,0.0000066788057,0.000062515566],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983501,0.00025833974,0.00045036964,0.0001251872,0.0005995097,0.00021650118],"domain_scores_gemma":[0.99690807,0.0013753755,0.00053623464,0.0005913894,0.00048578286,0.00010312448],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013015434,0.00011987646,0.00027780703,0.00001762182,0.00022508322,0.00006131608,0.0019608454,0.00006337799,0.00012967408],"category_scores_gemma":[0.0010518947,0.00005817618,0.00039287627,0.00048376012,0.0012060849,0.00021486676,0.0003913888,0.00037131074,0.000029506236],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018167666,0.00063557434,0.00040309905,0.00006706712,0.0004476437,0.0000027096962,0.0074632764,0.00013414813,0.02518323,0.000142118,0.071769044,0.8935704],"study_design_scores_gemma":[0.0015466389,0.0025306256,0.012137292,0.00069699605,0.000765128,0.0006917314,0.014193107,0.50022095,0.35715666,0.07633561,0.0326799,0.0010453583],"about_ca_topic_score_codex":0.00001935378,"about_ca_topic_score_gemma":6.2436186e-7,"teacher_disagreement_score":0.8925251,"about_ca_system_score_codex":0.000047684825,"about_ca_system_score_gemma":0.00011401198,"threshold_uncertainty_score":0.444387},"labels":[],"label_agreement":null},{"id":"W2897820244","doi":"10.1121/1.5067810","title":"Computational medicine in voice research","year":2018,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Phonation; Visualization; Computational model; Process (computing); Workflow; Scale (ratio); Oscillation (cell signaling); Human–computer interaction; Simulation; Artificial intelligence; Medicine; Biology","score_opus":0.0566726847425565,"score_gpt":0.3497351986685679,"score_spread":0.2930625139260114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2897820244","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0068477914,0.00009418335,0.93544334,0.055589307,0.00023338353,0.00007611142,9.3858785e-7,0.000006876798,0.0017080586],"genre_scores_gemma":[0.7141185,0.00010333767,0.281984,0.0033577904,0.00034898057,5.419523e-7,6.304173e-8,0.0000050228114,0.00008177849],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998092,0.00041730015,0.00034800183,0.000073147596,0.00088470173,0.00018486545],"domain_scores_gemma":[0.9965341,0.0023563604,0.00020856094,0.00023490078,0.0006050862,0.00006096143],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025656763,0.000059393802,0.00017907089,0.00004310241,0.00016898097,0.0000138379355,0.001277538,0.00003406667,0.00009411892],"category_scores_gemma":[0.00077920087,0.000028142087,0.00012000634,0.0007942656,0.0015200851,0.00009362987,0.00023428249,0.00040660368,0.000021766136],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002012109,0.00055203255,0.00048447598,0.00004561121,0.0002274766,0.0000069112425,0.011616603,0.0030833294,0.012085268,0.00082855346,0.4564534,0.5144151],"study_design_scores_gemma":[0.0006115358,0.0006233212,0.009325521,0.00019164402,0.00003279596,0.00013599412,0.0024087483,0.9395912,0.001202946,0.040078726,0.005706104,0.00009142112],"about_ca_topic_score_codex":0.00005942025,"about_ca_topic_score_gemma":9.430751e-7,"teacher_disagreement_score":0.93650794,"about_ca_system_score_codex":0.00005079872,"about_ca_system_score_gemma":0.00011424521,"threshold_uncertainty_score":0.5600817},"labels":[],"label_agreement":null},{"id":"W2899147640","doi":"","title":"An Empirical Study of Methods for SPN Learning and Inference","year":2018,"lang":"en","type":"article","venue":"Probabilistic Graphical Models","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; University of Regina","funders":"","keywords":"Computer science; Inference; Artificial intelligence; Machine learning","score_opus":0.11016250390616814,"score_gpt":0.42599450067440925,"score_spread":0.31583199676824114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2899147640","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2475964,0.000012684388,0.7515795,0.000089974674,0.000047282196,0.00035153987,8.279422e-7,0.00007320826,0.00024854843],"genre_scores_gemma":[0.6433181,0.0000026645382,0.3565535,0.000044769342,0.000017801633,0.000054307915,3.8820136e-7,0.000004892453,0.0000035424628],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984918,0.0003901305,0.00029835792,0.00047178078,0.00014418138,0.00020370753],"domain_scores_gemma":[0.9980185,0.0011314868,0.000078538804,0.00030072045,0.0003195232,0.00015121534],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009544268,0.00012194559,0.00025519202,0.00013286894,0.0001385695,0.00007492325,0.00035981025,0.000077121804,0.0000111052705],"category_scores_gemma":[0.0009940241,0.000100284575,0.0000490056,0.0003552653,0.00020385976,0.00024724478,0.00011189572,0.00012676005,0.0000010928959],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000847971,0.0018626023,0.010786492,0.00008008005,0.000057637695,0.0000016002535,0.0038914129,0.00015833318,0.0010062909,0.18197003,0.000013997302,0.80008674],"study_design_scores_gemma":[0.000265058,0.0012330582,0.0015802415,0.000008608899,0.000015782196,0.0000026798375,0.000071300296,0.6221981,0.0001607835,0.37431687,0.000045350833,0.00010216954],"about_ca_topic_score_codex":0.000013594103,"about_ca_topic_score_gemma":0.000013474446,"teacher_disagreement_score":0.7999846,"about_ca_system_score_codex":0.0000072024473,"about_ca_system_score_gemma":0.00003258746,"threshold_uncertainty_score":0.40894863},"labels":[],"label_agreement":null},{"id":"W2899186436","doi":"","title":"AutoDL Challenge Design and Beta Tests-Towards automatic deep learning","year":2018,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Acadia University","funders":"Centre National de la Recherche Scientifique; Chinese Academy of Sciences","keywords":"Computer science; Deep learning; Baseline (sea); Schedule; Set (abstract data type); Artificial intelligence; Machine learning; Raw data; Data science; Labeled data; Data set","score_opus":0.02991579317343053,"score_gpt":0.24479446475496577,"score_spread":0.21487867158153523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2899186436","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010020165,0.0012263654,0.9378036,0.009158579,0.0002693876,0.00046077967,0.0000051174898,0.00094458845,0.04011141],"genre_scores_gemma":[0.272637,0.0011093401,0.72351956,0.00012492712,0.000040189112,0.00011902556,0.00004891052,0.000052485964,0.0023485848],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99040604,0.0069504213,0.00054081256,0.0010885445,0.00056239194,0.0004517804],"domain_scores_gemma":[0.99340975,0.002212668,0.0005224378,0.0020551833,0.0015152391,0.0002847018],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.007239792,0.00040880186,0.00045829284,0.00031458374,0.0005393964,0.0010674435,0.002105462,0.0003638987,0.00028216117],"category_scores_gemma":[0.002071273,0.00043348892,0.00017743128,0.0003735301,0.000284104,0.00029062768,0.0025133234,0.00072622387,0.00017459654],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000023301332,0.00027092212,0.00015729934,0.00016661861,0.00008619683,0.000012692943,0.008478432,0.000023784552,0.00019363845,0.01680472,0.00038949048,0.9734139],"study_design_scores_gemma":[0.0005393454,0.0000026430714,0.005173111,0.0021289268,0.00007329639,0.000057924462,0.000098968645,0.9408869,0.022235088,0.020232841,0.0076002707,0.0009706953],"about_ca_topic_score_codex":0.00018308463,"about_ca_topic_score_gemma":0.00014948325,"teacher_disagreement_score":0.97244316,"about_ca_system_score_codex":0.00009918385,"about_ca_system_score_gemma":0.00029596486,"threshold_uncertainty_score":0.99996954},"labels":[],"label_agreement":null},{"id":"W2900022717","doi":"10.1109/icassp.2019.8682064","title":"Generative Adversarial Speaker Embedding Networks for Domain Robust End-to-end Speaker Verification","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal; McGill University","funders":"","keywords":"Discriminator; Speaker verification; Computer science; NIST; Classifier (UML); Speech recognition; End-to-end principle; Adversarial system; Baseline (sea); Artificial intelligence; Generative grammar; Trigonometric functions; Embedding; Dimensionality reduction; Pattern recognition (psychology); Speaker recognition; Mathematics; Detector","score_opus":0.04339371839715384,"score_gpt":0.27868557334946464,"score_spread":0.2352918549523108,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2900022717","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015738339,0.000037021455,0.971379,0.0017808122,0.00511464,0.0016860828,0.000052941832,0.00026867935,0.018107016],"genre_scores_gemma":[0.06972704,0.000033820328,0.92304677,0.0015401624,0.0015340032,0.00031024008,0.00022711513,0.000053590404,0.0035272818],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968443,0.00019378643,0.000571704,0.0013924058,0.00045530553,0.00054251275],"domain_scores_gemma":[0.99754006,0.0003703761,0.0003029319,0.0012493059,0.00031333044,0.00022399714],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008709362,0.0004640962,0.0005389436,0.00027671855,0.00018667144,0.00068055885,0.0012154656,0.00046202316,0.0010111962],"category_scores_gemma":[0.00012551688,0.00043792033,0.00035945754,0.00026163532,0.000041936357,0.00032039775,0.00085848826,0.0004263934,0.00045049342],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027386026,0.0003447954,0.00014472067,0.00015611365,0.0006812689,0.000024680716,0.0031676434,0.44391075,0.001271205,0.07660459,0.08781907,0.3856013],"study_design_scores_gemma":[0.0007229314,0.000066060384,0.0003744838,0.00010767761,0.000049688842,0.000010796043,0.00015672097,0.9603734,0.002712568,0.0036686629,0.030897656,0.00085935026],"about_ca_topic_score_codex":0.00006224465,"about_ca_topic_score_gemma":0.00007092875,"teacher_disagreement_score":0.5164627,"about_ca_system_score_codex":0.00024464945,"about_ca_system_score_gemma":0.0002316272,"threshold_uncertainty_score":0.999902},"labels":[],"label_agreement":null},{"id":"W2900161882","doi":"10.1109/icassp.2019.8682611","title":"Adapting End-to-end Neural Speaker Verification to New Languages and Recording Conditions with Adversarial Training","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal; McGill University","funders":"","keywords":"Adversarial system; Computer science; NIST; Speaker verification; Speech recognition; Task (project management); Artificial neural network; Speaker recognition; Embedding; End-to-end principle; Margin (machine learning); Artificial intelligence; Training (meteorology); Speaker diarisation; Residual; Combing; Machine learning; Algorithm; Engineering","score_opus":0.05388103435155326,"score_gpt":0.29656352395245406,"score_spread":0.2426824896009008,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2900161882","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12863213,0.00002256212,0.83962643,0.0053967987,0.001008888,0.0007806809,0.000035909463,0.00039113616,0.02410547],"genre_scores_gemma":[0.67001605,0.000004146727,0.32709622,0.0009165849,0.00025694267,0.000028253759,0.000032282212,0.000018871686,0.0016306076],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99837923,0.00007496181,0.00025080837,0.0007456705,0.0002726994,0.00027660423],"domain_scores_gemma":[0.9988026,0.00022291382,0.0001234176,0.0005055362,0.00007846286,0.00026706903],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027040186,0.00023469064,0.00028741235,0.00027535745,0.00011321722,0.0004480945,0.00043664334,0.00011638411,0.00043217116],"category_scores_gemma":[0.00014170315,0.0002120943,0.00006174111,0.0002205146,0.000019184843,0.00027159747,0.0003934454,0.0002662882,0.00013841662],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004361928,0.000024478624,0.00043540882,0.000036836016,0.00009296699,0.000024593224,0.008017832,0.0015602123,0.0021517894,0.0040477645,0.0033954284,0.98016906],"study_design_scores_gemma":[0.010242011,0.002682529,0.11506948,0.006260287,0.0009938007,0.0015938831,0.052239344,0.64827615,0.03833453,0.010135497,0.1002784,0.013894076],"about_ca_topic_score_codex":0.00074525166,"about_ca_topic_score_gemma":0.00025576935,"teacher_disagreement_score":0.966275,"about_ca_system_score_codex":0.000055078148,"about_ca_system_score_gemma":0.00018503545,"threshold_uncertainty_score":0.8648954},"labels":[],"label_agreement":null},{"id":"W2900688537","doi":"10.1109/taslp.2018.2882731","title":"Privacy-Preserving iVector-Based Speaker Verification","year":2018,"lang":"en","type":"article","venue":"IEEE/ACM Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Password; Alphanumeric; Speaker recognition; Biometrics; Domain (mathematical analysis); Authentication (law); Speech recognition; Voice over IP; Computer security; World Wide Web; The Internet","score_opus":0.02376216840936063,"score_gpt":0.27477188364507155,"score_spread":0.2510097152357109,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2900688537","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09756935,0.00022039805,0.8975723,0.001557314,0.00028644377,0.00018354919,0.000007390688,0.00042712712,0.0021761358],"genre_scores_gemma":[0.79252285,0.000015464442,0.20602097,0.0008673102,0.00012487583,0.0000217034,0.0000026849727,0.000020529538,0.00040360764],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99848866,0.000075722885,0.00024399666,0.00054161524,0.00032023084,0.00032977024],"domain_scores_gemma":[0.99871796,0.00010802675,0.00010865798,0.00074679404,0.0001606117,0.00015793326],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025991214,0.00021274798,0.00018293844,0.00026748478,0.00050528155,0.0003793866,0.0006833546,0.00010482852,0.00040139514],"category_scores_gemma":[0.00009928511,0.00019945632,0.00007545898,0.00055879354,0.0001099769,0.0005764852,0.000014340621,0.00021078119,0.0001528998],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027661801,0.000108631226,0.00004404952,0.000050724168,0.00001487953,0.000018371207,0.0014992249,0.000008329409,0.021388238,0.000010818211,0.000106950465,0.9767221],"study_design_scores_gemma":[0.001109115,0.0002464789,0.0017291994,0.0003630527,0.000054964006,0.0001243336,0.0006510566,0.07049116,0.9198617,0.0006927885,0.003959957,0.0007162535],"about_ca_topic_score_codex":0.000051076524,"about_ca_topic_score_gemma":0.00006652746,"teacher_disagreement_score":0.97600585,"about_ca_system_score_codex":0.00005500197,"about_ca_system_score_gemma":0.00010506861,"threshold_uncertainty_score":0.81335926},"labels":[],"label_agreement":null},{"id":"W2900939497","doi":"10.1109/icassp.2019.8683713","title":"The Pytorch-kaldi Speech Recognition Toolkit","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Python (programming language); Plug-in; Software; Artificial intelligence; Deep learning; Artificial neural network; Exploit; Documentation; Flexibility (engineering); Programming language","score_opus":0.04602015729144891,"score_gpt":0.2592342611845588,"score_spread":0.21321410389310985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2900939497","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011043668,0.0004360719,0.44686702,0.013804656,0.011222104,0.0016459438,0.00006178795,0.0015364595,0.5133823],"genre_scores_gemma":[0.09224146,0.0036098298,0.7844602,0.009292044,0.0024467474,0.0005395512,0.0003023547,0.00018103498,0.1069268],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976507,0.00020053561,0.00041397064,0.00078308803,0.0005482959,0.00040342822],"domain_scores_gemma":[0.9971551,0.00063010945,0.00021830456,0.0016064441,0.00027802147,0.000112021226],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008777394,0.00030477054,0.00028741616,0.00012984517,0.0002246494,0.0011762923,0.0021662458,0.00032291617,0.0005708369],"category_scores_gemma":[0.00023169685,0.00020801487,0.00028554705,0.0001967592,0.000060750084,0.00028547252,0.0014809296,0.000631033,0.0067278896],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000466738,0.000027944814,0.000017260443,0.000017805187,0.000040141793,0.000010604283,0.000043930395,0.0000025258187,0.000027303384,0.0024626616,0.027096651,0.9702485],"study_design_scores_gemma":[0.001039879,0.00018841938,0.003023486,0.0005853129,0.00011685674,0.00025727536,0.00024043903,0.0717337,0.06256967,0.4302306,0.42693403,0.0030803413],"about_ca_topic_score_codex":0.00008362362,"about_ca_topic_score_gemma":0.000049721457,"teacher_disagreement_score":0.96716815,"about_ca_system_score_codex":0.000090918125,"about_ca_system_score_gemma":0.00022537193,"threshold_uncertainty_score":0.9998606},"labels":[],"label_agreement":null},{"id":"W2901025079","doi":"10.1109/icassp.2019.8682880","title":"Representation Mixing for TTS Synthesis","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Pronunciation; Character (mathematics); Mixing (physics); Representation (politics); Speech synthesis; Software deployment; Speech recognition; Parametric statistics; Inference; Artificial intelligence; Natural language processing; Encoder; Control (management); Linguistics; Mathematics","score_opus":0.07700848133495143,"score_gpt":0.31340455708140497,"score_spread":0.23639607574645355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2901025079","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016490261,0.000042305728,0.9569735,0.001524896,0.0014613097,0.0006941942,0.000015592082,0.00034604073,0.037293173],"genre_scores_gemma":[0.14715639,0.00006261326,0.8454131,0.0007044469,0.00025365176,0.00063185673,0.0000244567,0.000032046584,0.0057214745],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99843603,0.00007882812,0.00028794204,0.0007243755,0.00025096434,0.00022187157],"domain_scores_gemma":[0.9975656,0.0010659484,0.00017315133,0.0009664724,0.0001638983,0.00006487469],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037011004,0.00018767486,0.00032875102,0.00019180465,0.00006683753,0.00035368025,0.0009206798,0.00020968323,0.00019741259],"category_scores_gemma":[0.00053326826,0.00017517505,0.00028522924,0.00012491795,0.000012140432,0.00020151924,0.0006063975,0.00014008238,0.00032759755],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012636962,0.00007726521,0.00024871447,0.00025056387,0.00013203976,0.000005158329,0.00027669963,0.00020688192,0.00047443583,0.012278695,0.01857957,0.96745735],"study_design_scores_gemma":[0.00049775926,0.000046327383,0.0020510785,0.00052200863,0.00012037906,0.000022458325,0.00021613853,0.64276856,0.25953817,0.08047471,0.012322885,0.0014194888],"about_ca_topic_score_codex":0.000037960883,"about_ca_topic_score_gemma":0.000008242775,"teacher_disagreement_score":0.96603787,"about_ca_system_score_codex":0.000051778177,"about_ca_system_score_gemma":0.00009544021,"threshold_uncertainty_score":0.71434313},"labels":[],"label_agreement":null},{"id":"W2901997113","doi":"","title":"Char2Wav: End-to-End Speech Synthesis","year":2017,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":335,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique; Université de Montréal","funders":"","keywords":"End-to-end principle; Computer science; Speech synthesis; Speech recognition; Artificial intelligence","score_opus":0.09295328918588806,"score_gpt":0.3624233461629727,"score_spread":0.26947005697708465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2901997113","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06219863,0.0000042187016,0.07413485,0.05760833,0.0018428555,0.00032065721,0.00003528175,0.00043743962,0.80341774],"genre_scores_gemma":[0.97032285,0.000027533662,0.017524255,0.00039614973,0.0001789961,0.00010366675,0.00001114344,0.000013687293,0.011421741],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9981335,0.00011319511,0.00026344648,0.00057192,0.00067294517,0.00024504092],"domain_scores_gemma":[0.99789107,0.00043873317,0.00024118317,0.00084576115,0.0004083387,0.00017491747],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0003325211,0.00016459555,0.00016439489,0.00032427508,0.0007593175,0.0014956972,0.0020370178,0.00006336731,0.004040324],"category_scores_gemma":[0.003125869,0.00016752844,0.0001125875,0.000106860316,0.000088186294,0.0007289521,0.00034701574,0.00027898516,0.0026152546],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023381865,0.00013782339,0.0066311182,0.0000035907103,0.00010522902,0.00009531893,0.00086753396,0.000095941155,0.00429979,0.2218988,0.0017310727,0.7641104],"study_design_scores_gemma":[0.001684199,0.00038933687,0.43639773,0.00072137767,0.0000789178,0.0002966625,0.00187464,0.272077,0.12850676,0.04067498,0.115048476,0.0022499394],"about_ca_topic_score_codex":0.00022109825,"about_ca_topic_score_gemma":0.00004806055,"teacher_disagreement_score":0.9081242,"about_ca_system_score_codex":0.000065070926,"about_ca_system_score_gemma":0.00009426342,"threshold_uncertainty_score":0.99954087},"labels":[],"label_agreement":null},{"id":"W2902368158","doi":"10.21437/interspeech.2019-2380","title":"Learning Speaker Representations with Mutual Information","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Discriminator; Mutual information; Computer science; Artificial intelligence; Encoder; Speech recognition; Feature learning; Sentence; Joint probability distribution; Feature (linguistics); Pattern recognition (psychology); Natural language processing; Mathematics; Linguistics; Statistics","score_opus":0.018845371718182673,"score_gpt":0.24623960198073427,"score_spread":0.2273942302625516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2902368158","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0052734837,0.0000039121496,0.7355901,0.00070519105,0.0003132388,0.00024068948,0.0000023598222,0.0003415066,0.25752953],"genre_scores_gemma":[0.49958926,0.000042285963,0.48078975,0.0011911588,0.00013081312,0.000093144336,0.00018795379,0.000019600995,0.017956011],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989467,0.000064527856,0.00022971234,0.0002705095,0.0003367728,0.00015174945],"domain_scores_gemma":[0.998924,0.00010530961,0.00017424628,0.0005543573,0.0001840021,0.000058063753],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00017223113,0.00014432508,0.00015551968,0.00020335906,0.000073399,0.0005358368,0.000485849,0.00011514992,0.0004049513],"category_scores_gemma":[0.00008301789,0.00011456102,0.000066773006,0.00016076033,0.000019766785,0.00090765796,0.000513955,0.00038727812,0.0025317755],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035336758,0.00010966079,0.008029761,0.0002128273,0.00026200718,0.000024250023,0.008327322,0.022488361,0.0000321357,0.040345307,0.020204408,0.8999286],"study_design_scores_gemma":[0.0011610475,0.00024498932,0.022104405,0.00032378986,0.000063909516,0.0001317441,0.0021861945,0.8622874,0.0036921022,0.0046427287,0.10161419,0.0015475043],"about_ca_topic_score_codex":0.00006458508,"about_ca_topic_score_gemma":0.0000116227275,"teacher_disagreement_score":0.8983811,"about_ca_system_score_codex":0.000034611305,"about_ca_system_score_gemma":0.00014298344,"threshold_uncertainty_score":0.9982449},"labels":[],"label_agreement":null},{"id":"W2912129510","doi":"10.1109/icassp.2019.8683565","title":"Exploring Attention Mechanism for Acoustic-based Classification of Speech Utterances into System-directed and Non-system-directed","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Phrase; Mechanism (biology); Speech recognition; Word (group theory); Convolutional neural network; Artificial intelligence; Recurrent neural network; Natural language processing; Artificial neural network; Linguistics","score_opus":0.08203991703136106,"score_gpt":0.26620627261648083,"score_spread":0.1841663555851198,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2912129510","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09658328,0.00003539258,0.895867,0.0001969963,0.002027873,0.0018614213,0.00006004554,0.0015150108,0.0018529989],"genre_scores_gemma":[0.76233786,0.000023578774,0.2365647,0.0000262118,0.00012345181,0.00070767425,0.00007580603,0.000031366642,0.000109372486],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99694705,0.00020590491,0.00088656245,0.0011153161,0.0005291132,0.00031602583],"domain_scores_gemma":[0.99666643,0.00042861965,0.00076854357,0.00099542,0.0010233088,0.00011770392],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00078002585,0.00042014229,0.00079918926,0.0005726684,0.00014794432,0.00029425745,0.00074294984,0.00032801685,0.000008903488],"category_scores_gemma":[0.00013047757,0.00039364633,0.0002477936,0.00034042823,0.000038787002,0.00040708884,0.0002722865,0.00021861566,0.000030429992],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004136003,0.00056824135,0.0011162182,0.053846277,0.0010693559,0.000033945737,0.0016757088,0.00044624234,0.5582599,0.07057232,0.0011705146,0.31082767],"study_design_scores_gemma":[0.0007161662,0.00007217434,0.0023443715,0.0021212131,0.000109461165,0.000009216691,0.00052123866,0.88965994,0.103457816,0.00050585956,0.00002209535,0.0004604311],"about_ca_topic_score_codex":0.00020711876,"about_ca_topic_score_gemma":0.000044571094,"teacher_disagreement_score":0.88921374,"about_ca_system_score_codex":0.00024684833,"about_ca_system_score_gemma":0.00017397545,"threshold_uncertainty_score":0.9998515},"labels":[],"label_agreement":null},{"id":"W2912293245","doi":"10.1109/slt.2018.8639599","title":"MOS Naturalness and the Quest for Human-Like Speech","year":2018,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Naturalness; Computer science; Speech recognition; Physics","score_opus":0.02196593384210739,"score_gpt":0.27952470275844427,"score_spread":0.2575587689163369,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2912293245","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.103974596,0.0001871466,0.6944286,0.0186905,0.0021371588,0.0013454761,0.000005802416,0.00066207536,0.17856863],"genre_scores_gemma":[0.90198606,0.000007493376,0.08560437,0.004097186,0.00026611477,0.000044815642,0.0000010398769,0.00000682488,0.007986082],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99946284,0.000033289416,0.00009173673,0.00018907797,0.00009674306,0.00012628594],"domain_scores_gemma":[0.99938595,0.00020813619,0.000026602964,0.0002396733,0.000104533436,0.000035077235],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032526048,0.00006439853,0.000085313724,0.00002956332,0.00024536523,0.00017265684,0.0003512548,0.000032824602,0.00009355807],"category_scores_gemma":[0.00005082677,0.000035738958,0.00003660558,0.00009128337,0.00015844095,0.00015815395,0.00008534808,0.00003842947,0.00006410609],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018491188,0.000023346767,0.000040355535,0.0000075967664,0.000017795008,0.0000018065173,0.00035587998,1.2106174e-8,0.000512184,0.56331974,0.012670086,0.4230327],"study_design_scores_gemma":[0.0067640464,0.00036422102,0.0036516823,0.00006236931,0.000048775575,0.0002558534,0.00043884706,0.066679865,0.22578137,0.3919198,0.30304542,0.0009877594],"about_ca_topic_score_codex":0.00004290279,"about_ca_topic_score_gemma":0.00010477669,"teacher_disagreement_score":0.7980115,"about_ca_system_score_codex":0.0000056859535,"about_ca_system_score_gemma":0.00000970194,"threshold_uncertainty_score":0.18871757},"labels":[],"label_agreement":null},{"id":"W2912379194","doi":"10.1007/s11042-019-7154-y","title":"Multitaper chirp group delay Hilbert envelope coefficients for robust speaker verification","year":2019,"lang":"en","type":"article","venue":"Multimedia Tools and Applications","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Multitaper; Computer science; Envelope (radar); Chirp; Group delay and phase delay; Speaker verification; Speech recognition; Hilbert transform; Group (periodic table); Spectral envelope; Algorithm; Telecommunications; Bandwidth (computing); Physics; Radar; Speaker recognition","score_opus":0.030362367487512216,"score_gpt":0.24477554651597055,"score_spread":0.21441317902845833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2912379194","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010575155,0.00006862462,0.9841495,0.00064606796,0.000176376,0.0016580727,0.000082332066,0.00020873528,0.0024351396],"genre_scores_gemma":[0.28678253,0.00010314502,0.7087742,0.0007350402,0.00015863393,0.0019767156,0.00027154593,0.000038419385,0.0011597214],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988879,0.000020236852,0.00022873229,0.00048618022,0.0001547888,0.00022214247],"domain_scores_gemma":[0.9989115,0.0003100957,0.00008305938,0.00046719465,0.00010842742,0.00011971051],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017350186,0.00013959614,0.00015033502,0.00007157737,0.00018348984,0.00018707669,0.00035960184,0.00008165672,0.000061579296],"category_scores_gemma":[0.000049729857,0.00012798929,0.000062717954,0.0002153112,0.00004250419,0.00031757486,0.000068932444,0.000071062066,0.00064564275],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000072302582,0.00020411557,0.0016403254,0.00002165935,0.000019262816,2.1416972e-7,0.00021436556,0.00004173004,0.0029410196,0.008578848,0.0006666645,0.98566455],"study_design_scores_gemma":[0.001639761,0.000060882565,0.040535722,0.000028370132,0.000028625669,0.000015479305,0.00012969872,0.456745,0.0024334863,0.0004725604,0.4973501,0.0005603171],"about_ca_topic_score_codex":0.000011807028,"about_ca_topic_score_gemma":0.0000073423075,"teacher_disagreement_score":0.98510426,"about_ca_system_score_codex":0.000025681133,"about_ca_system_score_gemma":0.000023776132,"threshold_uncertainty_score":0.8298647},"labels":[],"label_agreement":null},{"id":"W2912971336","doi":"10.1145/3251778","title":"Session details: Speech & Auditory Interfaces","year":2015,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Session (web analytics); Computer science; Speech recognition; Multimedia; World Wide Web","score_opus":0.07738289082967917,"score_gpt":0.2933072861296628,"score_spread":0.2159243952999836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2912971336","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12475388,0.000108241715,0.6490238,0.0021208425,0.002542364,0.00011427872,8.5857215e-7,0.00071482256,0.22062095],"genre_scores_gemma":[0.45873097,0.000018128541,0.51913816,0.0010869509,0.0003093927,0.000009983524,0.0000018216285,0.000010769384,0.020693796],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99914,0.00006659091,0.00013579585,0.00023186745,0.0002674715,0.00015825135],"domain_scores_gemma":[0.99927044,0.00007105408,0.000040433166,0.00034503505,0.000110501365,0.00016252624],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00032220854,0.00008773029,0.00009834547,0.00008406397,0.00004384374,0.00014186403,0.00049566646,0.000050949253,0.00046521646],"category_scores_gemma":[0.00014057655,0.00006619653,0.000035828878,0.00016922099,0.000023805655,0.00045371905,0.00017435511,0.00007071121,0.004397639],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000052499386,0.00007129234,0.00031952935,0.0000041296207,0.00001044344,0.0000144522255,0.00036594176,0.0000017267299,0.0022920591,0.001448652,0.19792616,0.79754037],"study_design_scores_gemma":[0.00083044183,0.00012004009,0.0011830986,0.00009571073,0.000011157618,0.00017199892,0.0006343472,0.010363927,0.2379911,0.016978215,0.73091227,0.000707686],"about_ca_topic_score_codex":0.00002126052,"about_ca_topic_score_gemma":0.000045421766,"teacher_disagreement_score":0.7968327,"about_ca_system_score_codex":0.00003622655,"about_ca_system_score_gemma":0.0000606232,"threshold_uncertainty_score":0.9963775},"labels":[],"label_agreement":null},{"id":"W2914422976","doi":"10.48550/arxiv.1902.02375","title":"Centroid-based deep metric learning for speaker recognition","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Embedding; Computer science; Centroid; Speech recognition; Similarity (geometry); Task (project management); Artificial intelligence; Metric (unit); Set (abstract data type); Speaker recognition; Pattern recognition (psychology); Speaker diarisation; Natural language processing; Image (mathematics)","score_opus":0.09792118983636798,"score_gpt":0.1929767119206509,"score_spread":0.09505552208428293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2914422976","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03237444,0.000050229966,0.9615035,0.00011698661,0.0008385443,0.0006106955,0.000022092221,0.0003510173,0.004132465],"genre_scores_gemma":[0.97272545,0.00008218408,0.025006257,0.00028100875,0.00010499018,0.000004449527,0.0001408975,0.000030675423,0.0016240813],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99792385,0.00020931257,0.00021650923,0.0011182753,0.00012183949,0.00041019745],"domain_scores_gemma":[0.9979144,0.0005550182,0.00032769694,0.0007039006,0.0003384245,0.0001606055],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00037927995,0.000308448,0.00036474736,0.00072520215,0.00017147345,0.00018819912,0.0010219468,0.00032077718,0.00019136832],"category_scores_gemma":[0.0002700195,0.0003670075,0.0004273469,0.00079961127,0.000040928444,0.00029468542,0.00044344473,0.0004887137,0.00070232677],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003884725,0.0008057713,0.0076194154,0.00090505084,0.0006334352,0.00040025858,0.0003150077,0.6296287,0.0002616434,0.020094723,0.0019780605,0.33696944],"study_design_scores_gemma":[0.0009609934,0.00007805022,0.000420649,0.000095415555,0.00011136336,0.0000027214517,0.000053444324,0.9812662,0.0012834878,0.0114204325,0.0037600093,0.00054723624],"about_ca_topic_score_codex":0.00003459486,"about_ca_topic_score_gemma":0.000016256952,"teacher_disagreement_score":0.940351,"about_ca_system_score_codex":0.0002450929,"about_ca_system_score_gemma":0.00018591658,"threshold_uncertainty_score":0.99987817},"labels":[],"label_agreement":null},{"id":"W2917672101","doi":"","title":"Voice biometrics distinction between English and Arabic using Sound Cleaner Filtering and SpeechPro SIS II analysis","year":2018,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Formant; Vowel; Speech recognition; Computer science; Speaker recognition; Spectrogram; Software; Articulation (sociology); Sound quality; Arabic; Biometrics; Linguistics; Artificial intelligence","score_opus":0.05138435495405243,"score_gpt":0.27860034919462473,"score_spread":0.22721599424057232,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2917672101","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5995433,0.00001795026,0.3984497,0.00005244829,0.000103859675,0.00004535176,0.0000042018355,0.00009924979,0.0016839707],"genre_scores_gemma":[0.89246154,0.000011663499,0.10703644,0.00008095445,0.0002370643,0.0000013686389,0.0000030733936,0.00000675586,0.00016116403],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99884665,0.000049068538,0.0002183837,0.0004473593,0.00022135657,0.00021716821],"domain_scores_gemma":[0.99909544,0.00022075328,0.00008495745,0.0002687911,0.00019721134,0.000132823],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039136337,0.00013549044,0.00022400591,0.0009301991,0.0003782852,0.00037298896,0.00018630059,0.00007398613,0.00009745521],"category_scores_gemma":[0.00026038906,0.00012020368,0.000060559047,0.0027665051,0.00010942788,0.00052881107,0.00029572056,0.00006559132,0.000011377131],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000987223,0.00008232988,0.14201504,0.00003722881,0.000558626,0.000008915861,0.0016015432,0.0000050686176,0.00250852,0.0005246205,0.00016833021,0.85247993],"study_design_scores_gemma":[0.0013884241,0.00066282216,0.5042892,0.000067851135,0.0020216366,0.00007616416,0.0010327914,0.4096547,0.059881806,0.005321799,0.013525705,0.0020771201],"about_ca_topic_score_codex":0.00009099806,"about_ca_topic_score_gemma":0.000054795782,"teacher_disagreement_score":0.8504028,"about_ca_system_score_codex":0.00003383053,"about_ca_system_score_gemma":0.0000095955165,"threshold_uncertainty_score":0.49017638},"labels":[],"label_agreement":null},{"id":"W2919923656","doi":"10.1007/s42452-019-0305-y","title":"Multitaper MFCC and normalized multitaper phase-based features for speaker verification","year":2019,"lang":"en","type":"article","venue":"SN Applied Sciences","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Multitaper; Computer science; Mel-frequency cepstrum; Speech recognition; Mixture model; Cepstrum; Artificial intelligence; Pattern recognition (psychology); Feature extraction","score_opus":0.024312204561038043,"score_gpt":0.28563690154598187,"score_spread":0.2613246969849438,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2919923656","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.52813494,0.00028989336,0.3883621,0.0035555013,0.0013229966,0.0030018433,0.000047803187,0.000588043,0.07469685],"genre_scores_gemma":[0.79773086,0.0000056561275,0.20080161,0.0009963855,0.000030936804,0.00009288131,0.000006242997,0.000006470368,0.00032895477],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986295,0.000026925023,0.00017346056,0.0005646143,0.00032070748,0.0002848],"domain_scores_gemma":[0.99919295,0.0002896299,0.00007935551,0.0002858434,0.0000635061,0.000088687644],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005867186,0.00014251439,0.00017064679,0.0001483566,0.00027031766,0.0003129937,0.0005307785,0.00006536152,0.00013610773],"category_scores_gemma":[0.00005112776,0.00011206484,0.000058492755,0.00035329803,0.00018342133,0.0003436605,0.00004875591,0.00006104652,0.00016655594],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015978444,0.00042984763,0.0012537219,0.000080449354,0.000031726217,0.0000014586662,0.0012165126,0.00013023168,0.32948318,0.10796347,0.0027700556,0.5564796],"study_design_scores_gemma":[0.011691796,0.0006084919,0.010247409,0.00007022399,0.000043765325,0.000021292171,0.0010957,0.4361765,0.40412468,0.005440219,0.12895778,0.0015221376],"about_ca_topic_score_codex":0.000011373303,"about_ca_topic_score_gemma":0.000013298129,"teacher_disagreement_score":0.5549574,"about_ca_system_score_codex":0.000016769653,"about_ca_system_score_gemma":0.000071697876,"threshold_uncertainty_score":0.45698714},"labels":[],"label_agreement":null},{"id":"W2935267697","doi":"10.3758/s13414-019-01711-w","title":"Correction to: Gradient and categorical patterns of spoken-word recognition and processing of phonetic details","year":2019,"lang":"en","type":"erratum","venue":"Attention Perception & Psychophysics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Western University","funders":"","keywords":"Mistake; Computer science; Word (group theory); Natural language processing; Categorical variable; Speech recognition; Linguistics; Font; Artificial intelligence; Philosophy","score_opus":0.026920634063123446,"score_gpt":0.26057744604296557,"score_spread":0.23365681197984212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2935267697","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.59229356,0.00023633464,0.3710854,0.00053747365,0.031061327,0.0012633782,0.00010056472,0.00018123908,0.0032407208],"genre_scores_gemma":[0.96908903,0.0026174376,0.009502117,0.00043035593,0.00087361195,0.00010302298,0.00064349483,0.0000871475,0.01665381],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99779314,0.00013211546,0.00061812275,0.0007270093,0.0004933963,0.00023619067],"domain_scores_gemma":[0.9984241,0.00006608363,0.0005616463,0.0003847587,0.0004305326,0.00013283872],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00022837103,0.00031560074,0.0005114576,0.00038849513,0.0000918323,0.000117515534,0.00023210478,0.00025887688,0.00008474637],"category_scores_gemma":[0.000036273643,0.0003281151,0.00016509871,0.00046641222,0.000066492306,0.00042846485,0.000090768626,0.000372544,0.000103519444],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035277866,0.00022941393,0.0005618224,0.0005197791,0.00003552174,0.0000011685837,0.0008615176,0.0000014045804,0.008413808,0.000021446976,0.032412514,0.9569063],"study_design_scores_gemma":[0.0042708023,0.002676385,0.8940554,0.009363107,0.00097381754,0.00034221995,0.0034727817,0.049037434,0.0025910162,0.012967558,0.01635863,0.0038908054],"about_ca_topic_score_codex":0.00010906134,"about_ca_topic_score_gemma":0.000027839658,"teacher_disagreement_score":0.9530155,"about_ca_system_score_codex":0.000068983754,"about_ca_system_score_gemma":0.000062295956,"threshold_uncertainty_score":0.9999171},"labels":[],"label_agreement":null},{"id":"W2935542736","doi":"10.21437/interspeech.2019-2605","title":"Learning Problem-Agnostic Speech Representations from Multiple Self-Supervised Tasks","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Compute Canada","keywords":"Computer science; Encoder; Discriminator; Artificial intelligence; Speech recognition; Machine learning; Supervised learning; Construct (python library); SIGNAL (programming language); Adaptation (eye); Identity (music); Pattern recognition (psychology); Artificial neural network; Psychology","score_opus":0.030834728385458927,"score_gpt":0.26332052650836435,"score_spread":0.23248579812290543,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2935542736","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.085272945,0.00015130792,0.7812846,0.0025473381,0.0022058652,0.002282565,0.00008197597,0.0034412697,0.12273219],"genre_scores_gemma":[0.23944144,0.000114985116,0.754972,0.00038861574,0.00018470254,0.00015908142,0.00022991536,0.000040892948,0.004468369],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967805,0.00033131638,0.00055412535,0.0013404737,0.00058642804,0.00040717045],"domain_scores_gemma":[0.9961324,0.0016719076,0.00025992753,0.0014845137,0.00026864203,0.00018265516],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00033241688,0.0003916063,0.0004821144,0.00026887713,0.000183341,0.00070174405,0.0016004557,0.0003752374,0.0012954952],"category_scores_gemma":[0.0006210298,0.0003781666,0.0002838081,0.00028653047,0.000028533714,0.00033408057,0.0018390798,0.0009347132,0.003061553],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003651322,0.0014720084,0.07378094,0.0005239363,0.0012725093,0.00034159978,0.009942056,0.014949786,0.0034660026,0.0026061502,0.023696419,0.86791205],"study_design_scores_gemma":[0.0009860878,0.000059100592,0.006827567,0.00026533895,0.00009584768,0.000018639686,0.00029009033,0.96654093,0.008543901,0.010537749,0.0048078923,0.001026866],"about_ca_topic_score_codex":0.0015879228,"about_ca_topic_score_gemma":0.00011599797,"teacher_disagreement_score":0.95159113,"about_ca_system_score_codex":0.00009593952,"about_ca_system_score_gemma":0.0002615809,"threshold_uncertainty_score":0.999867},"labels":[],"label_agreement":null},{"id":"W2938134751","doi":"10.1109/icassp.2019.8683674","title":"Parametric Cepstral Mean Normalization for Robust Speech Recognition","year":2019,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Normalization (sociology); Computer science; Speech recognition; Robustness (evolution); Parametric statistics; Cepstrum; Training set; Mel-frequency cepstrum; Test data; Pattern recognition (psychology); Artificial intelligence; Feature extraction; Mathematics; Statistics","score_opus":0.047716202140227454,"score_gpt":0.24333760598170381,"score_spread":0.19562140384147636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2938134751","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0757704,0.000006039642,0.8933894,0.0003295526,0.00053925434,0.0005090666,0.000007455985,0.00028276836,0.029166063],"genre_scores_gemma":[0.23864162,0.000012828152,0.7579922,0.00065814593,0.00008172208,0.00003639125,0.000049011196,0.000012925517,0.0025151642],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990361,0.000035138197,0.00019784668,0.000308533,0.0001989555,0.00022344441],"domain_scores_gemma":[0.99924505,0.00017970878,0.000069722395,0.000259964,0.00017489893,0.000070667316],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002842907,0.000102154496,0.00012198652,0.00024712514,0.000060162827,0.00016002642,0.00029066598,0.00007265425,0.00082473765],"category_scores_gemma":[0.00008796697,0.00009315189,0.00009091324,0.0005957037,0.00000913963,0.0006662583,0.00003594385,0.00004765775,0.0012838875],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010257434,0.00007766186,0.0009646641,0.000024875342,0.000014470299,0.0000015500647,0.000054347744,0.000038759215,0.000336079,0.003676961,0.0021937883,0.9926066],"study_design_scores_gemma":[0.0022092091,0.00047127643,0.0061149243,0.000060449976,0.000037079273,0.00010037065,0.0002359818,0.7567574,0.20475832,0.018461665,0.009782762,0.0010105816],"about_ca_topic_score_codex":0.000018053983,"about_ca_topic_score_gemma":0.000021558404,"teacher_disagreement_score":0.991596,"about_ca_system_score_codex":0.000032025262,"about_ca_system_score_gemma":0.000027430415,"threshold_uncertainty_score":0.9994937},"labels":[],"label_agreement":null},{"id":"W2950689855","doi":"10.48550/arxiv.1303.5778","title":"Speech Recognition with Deep Recurrent Neural Networks","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Recurrent neural network; Computer science; Connectionism; TIMIT; Speech recognition; Artificial intelligence; Context (archaeology); Deep learning; Benchmark (surveying); Time delay neural network; Artificial neural network; Hidden Markov model","score_opus":0.0770478288527954,"score_gpt":0.17952142166561869,"score_spread":0.10247359281282328,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950689855","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24343978,0.000058613947,0.7488111,0.00015985781,0.0009967928,0.0005098666,0.000009346741,0.00047075687,0.005543856],"genre_scores_gemma":[0.9814563,0.00026911183,0.017202828,0.00025302585,0.00017817727,0.0000054845605,0.000054097334,0.000029190149,0.00055181736],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99775356,0.00021723188,0.00022379335,0.0012157692,0.0001318328,0.00045782785],"domain_scores_gemma":[0.99796396,0.00013739345,0.00029963537,0.0010019653,0.00033172456,0.00026529143],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00018831715,0.0004026408,0.0003631021,0.00029335654,0.00016312259,0.00029911462,0.0013227505,0.00033511632,0.0003579519],"category_scores_gemma":[0.000028537053,0.00040005316,0.00020834386,0.0005925998,0.00010063815,0.00061297487,0.0008721314,0.00076369586,0.00044329182],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009585132,0.00033363895,0.0012335604,0.00009570048,0.00024929803,0.001159529,0.00015976951,0.040605955,0.0000063152247,0.005955501,0.0013001872,0.9488047],"study_design_scores_gemma":[0.00040006055,0.00009233726,0.0006334358,0.00012973051,0.000079357706,0.000043225577,0.00004577823,0.9866071,0.000114108225,0.011013867,0.00021659421,0.0006244177],"about_ca_topic_score_codex":0.000108056585,"about_ca_topic_score_gemma":0.000093219875,"teacher_disagreement_score":0.94818026,"about_ca_system_score_codex":0.00016516489,"about_ca_system_score_gemma":0.00007334226,"threshold_uncertainty_score":0.99984515},"labels":[],"label_agreement":null},{"id":"W2956804760","doi":"10.1109/icc.2019.8761244","title":"Spoofing Attacks on Speaker Verification Systems Based Generated Voice using Genetic Algorithm","year":2019,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Spoofing attack; Speaker verification; Computer science; Genetic algorithm; Authentication (law); Speaker recognition; Speech recognition; Population; Algorithm; Pattern recognition (psychology); Artificial intelligence; Machine learning; Computer network; Computer security","score_opus":0.03678619749085209,"score_gpt":0.2540703735878523,"score_spread":0.21728417609700018,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2956804760","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1440873,0.000028738621,0.8490131,0.0000946073,0.00079270016,0.00024761568,0.0000024737585,0.00019083562,0.0055426206],"genre_scores_gemma":[0.50820106,0.0000040296914,0.48966214,0.0008438576,0.00011504974,0.000010964762,0.000008027039,0.000020480158,0.0011343983],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987419,0.00011157956,0.00022663764,0.00041105083,0.0002938629,0.00021494974],"domain_scores_gemma":[0.9991051,0.00008633977,0.00008581347,0.0005222713,0.00012230575,0.00007819898],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00021237927,0.00013387966,0.0001442084,0.0001461926,0.00007938086,0.00025432804,0.00031752532,0.00007110664,0.000165053],"category_scores_gemma":[0.000016362454,0.00011994514,0.000051200528,0.00035045852,0.000010560276,0.00018340161,0.000028528615,0.00007141344,0.0018042275],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027664748,0.00044551532,0.0034800745,0.00011658334,0.000107963875,0.00007026157,0.00024074268,0.054915983,0.09841798,0.0035860264,0.002332886,0.8362583],"study_design_scores_gemma":[0.00023110547,0.00003041363,0.0020423247,0.00003658234,0.0000053098406,0.00001545718,0.00001857915,0.97308993,0.02216844,0.000009404011,0.0021738815,0.0001785865],"about_ca_topic_score_codex":0.00010510648,"about_ca_topic_score_gemma":0.0000013141363,"teacher_disagreement_score":0.9181739,"about_ca_system_score_codex":0.00007886018,"about_ca_system_score_gemma":0.00006280969,"threshold_uncertainty_score":0.998973},"labels":[],"label_agreement":null},{"id":"W2962989420","doi":"10.21437/interspeech.2019-2240","title":"A Deep Neural Network for Short-Segment Speaker Recognition","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Speech recognition; Speaker recognition; Artificial neural network; Task (project management); Duration (music); Phone; Time delay neural network; Pattern recognition (psychology); Artificial intelligence; Engineering","score_opus":0.06662587784503783,"score_gpt":0.2763267100300315,"score_spread":0.2097008321849937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2962989420","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019013906,0.00012754438,0.97390175,0.0010159974,0.0037499287,0.0013769428,0.000021396465,0.00039349,0.017511545],"genre_scores_gemma":[0.046979867,0.00009351288,0.9451555,0.0034983698,0.0012930307,0.0006310759,0.0003130147,0.00005317858,0.0019824258],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99778324,0.00009229587,0.00043162683,0.0008926193,0.00032218304,0.00047801257],"domain_scores_gemma":[0.99838275,0.00027476787,0.00013491577,0.00085139036,0.00022124918,0.00013490037],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00044890368,0.00032943065,0.00039933718,0.00011931538,0.00009397855,0.00041860642,0.0008740352,0.00029298,0.00046365164],"category_scores_gemma":[0.000054517146,0.00029935277,0.0003898162,0.00013641074,0.000020522395,0.00019244963,0.0007538701,0.0003044217,0.00053139176],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018662073,0.00006995406,0.00010974893,0.00008456527,0.00007651503,0.0000063458024,0.00006940921,0.0018886081,0.000013611842,0.0006773547,0.013050084,0.9839351],"study_design_scores_gemma":[0.00029222367,0.00008495077,0.0006168083,0.000115797055,0.000053205116,0.00002098456,0.000022632363,0.9641141,0.0008634958,0.02634212,0.006787739,0.0006858897],"about_ca_topic_score_codex":0.000016994944,"about_ca_topic_score_gemma":0.000051167586,"teacher_disagreement_score":0.98324925,"about_ca_system_score_codex":0.00008475504,"about_ca_system_score_gemma":0.00006933713,"threshold_uncertainty_score":0.9999459},"labels":[],"label_agreement":null},{"id":"W2963403664","doi":"10.21437/interspeech.2016-1446","title":"Towards End-to-End Speech Recognition with Deep Convolutional Neural Networks","year":2016,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":341,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Institute for Advanced Research; Université de Montréal","funders":"","keywords":"End-to-end principle; Computer science; Speech recognition; Convolutional neural network; Deep learning; Artificial intelligence","score_opus":0.03436162498600204,"score_gpt":0.24910300660268944,"score_spread":0.2147413816166874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963403664","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038880245,0.00006163631,0.93731207,0.0044946494,0.0015509916,0.0005526043,0.000057951107,0.0005705494,0.05151155],"genre_scores_gemma":[0.3964386,0.00007535329,0.5947539,0.0047644824,0.0014025057,0.0003189176,0.00020297509,0.00007026733,0.0019729952],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968011,0.00018729619,0.00045693933,0.0011797369,0.0007759958,0.0005989544],"domain_scores_gemma":[0.99778336,0.00023498971,0.00021600383,0.00086616393,0.00051130453,0.0003881802],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00046645943,0.0004756674,0.00045539966,0.00033899938,0.00015266809,0.00043889057,0.0012204776,0.0003777322,0.0033379844],"category_scores_gemma":[0.00008715614,0.00034079186,0.00021469098,0.00032074883,0.00010756233,0.00039410935,0.001061439,0.0005347058,0.0007149164],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000388824,0.00006120616,0.000083088824,0.000015924787,0.00007794611,0.00006487328,0.000044263594,0.000113987524,0.000020598512,0.0015379125,0.0021774138,0.9957639],"study_design_scores_gemma":[0.002431087,0.0006259657,0.010390678,0.0010223752,0.00020119375,0.0012676313,0.000094937386,0.8698321,0.012364381,0.086746834,0.0106988475,0.00432396],"about_ca_topic_score_codex":0.00010186354,"about_ca_topic_score_gemma":0.00015290845,"teacher_disagreement_score":0.99143994,"about_ca_system_score_codex":0.00017979849,"about_ca_system_score_gemma":0.0002488281,"threshold_uncertainty_score":0.9999044},"labels":[],"label_agreement":null},{"id":"W2963596039","doi":"10.21437/interspeech.2017-556","title":"Dynamic Layer Normalization for Adaptive Neural Acoustic Modeling in Speech Recognition","year":2017,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":71,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Normalization (sociology); Computer science; Speech recognition; Artificial neural network; Deep neural networks; Acoustic model; Artificial intelligence; Pattern recognition (psychology); Speech processing","score_opus":0.12487949391130328,"score_gpt":0.31111239263630314,"score_spread":0.18623289872499987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963596039","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022982188,0.0000376776,0.97115445,0.00042400358,0.00096225255,0.0008519892,0.000046551853,0.00021019937,0.0033306796],"genre_scores_gemma":[0.6998113,0.00006395455,0.2992508,0.00018262402,0.00006157983,0.00020477756,0.00012847934,0.000023100409,0.00027341786],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981666,0.00008038048,0.00042191512,0.0007399893,0.00026307942,0.00032802517],"domain_scores_gemma":[0.99851733,0.00013200032,0.00025068969,0.00066398794,0.00036079087,0.0000752043],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00047303946,0.00027950187,0.00033544574,0.00037369976,0.00015487421,0.00044244484,0.0008889437,0.00032699577,0.0000506907],"category_scores_gemma":[0.0002549468,0.0002821514,0.00016831887,0.00009524722,0.000020699574,0.00062860124,0.00049308955,0.00032933068,0.000057705558],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047745685,0.000111450696,0.00002236175,0.00013113211,0.00003440178,0.000024469897,0.00023798073,0.046883132,0.00024519,0.00021032117,0.00013248531,0.9519193],"study_design_scores_gemma":[0.00031907318,0.000031258645,0.000054686956,0.00018679425,0.000022045382,0.000012882607,0.00004031322,0.9674042,0.00066667655,0.03089108,0.000009321854,0.00036167802],"about_ca_topic_score_codex":0.00020723345,"about_ca_topic_score_gemma":0.0009447568,"teacher_disagreement_score":0.95155764,"about_ca_system_score_codex":0.00015704815,"about_ca_system_score_gemma":0.00013383967,"threshold_uncertainty_score":0.99996305},"labels":[],"label_agreement":null},{"id":"W2963897404","doi":"10.63317/3bau89hm3k8v","title":"Towards Neural Speaker Modeling in Multi-Party Conversation: The Task, Dataset, and Models","year":2018,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Conversation; Computer science; Task (project management); Component (thermodynamics); Speaker recognition; Speaker diarisation; Speech recognition; Artificial intelligence; Data modeling; Natural language processing; Linguistics; Database","score_opus":0.13927681886795895,"score_gpt":0.2942934836241976,"score_spread":0.15501666475623865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963897404","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026133783,0.000031217103,0.96684647,0.0037105097,0.00018072363,0.00013633851,0.00002432785,0.00006235855,0.0028742722],"genre_scores_gemma":[0.944363,0.000012596199,0.053375512,0.002109408,0.000040746945,0.0000065054273,0.000012718235,0.0000036809613,0.000075848366],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992566,0.000058175243,0.00014628102,0.00024914875,0.00013815977,0.00015161895],"domain_scores_gemma":[0.99952024,0.000041539428,0.000022571596,0.0003154895,0.00004863813,0.000051494368],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028956798,0.00008066046,0.00008133334,0.00005116825,0.000084505074,0.00013994143,0.00032414595,0.000030884115,0.00010090118],"category_scores_gemma":[0.000025565467,0.000052126623,0.00001730318,0.000144933,0.00006553932,0.0006358657,0.00016670908,0.000068855035,0.00005904118],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000061378574,0.00033204263,0.000729941,0.00002778,0.00006664479,0.00006006975,0.015065506,0.0046954565,0.0008748434,0.04333567,0.022166064,0.9125846],"study_design_scores_gemma":[0.00025233423,0.000011299245,0.00014277517,0.0000036406993,0.0000021586322,0.000012292254,0.00014439481,0.9963865,0.00045549648,0.0019154098,0.00059072673,0.00008293874],"about_ca_topic_score_codex":0.0002788387,"about_ca_topic_score_gemma":0.00030500916,"teacher_disagreement_score":0.99169105,"about_ca_system_score_codex":0.000011874723,"about_ca_system_score_gemma":0.000023421664,"threshold_uncertainty_score":0.2125662},"labels":[],"label_agreement":null},{"id":"W2963905071","doi":"","title":"Twin Networks: Matching the Future for Sequence Generation","year":2018,"lang":"en","type":"article","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Polytechnique Montréal","funders":"","keywords":"Computer science; Inference; Task (project management); Sequence (biology); Forcing (mathematics); Generative grammar; Matching (statistics); Generative model; Artificial intelligence; Recurrent neural network; Simple (philosophy); Term (time); Algorithm; Machine learning; Artificial neural network; Mathematics","score_opus":0.023151838101433373,"score_gpt":0.2514149227999537,"score_spread":0.22826308469852033,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963905071","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010827214,0.00044629606,0.9731962,0.013226825,0.0006540529,0.00067910284,0.000011900617,0.00062596955,0.00033242066],"genre_scores_gemma":[0.3822361,0.00012795583,0.6028478,0.010910501,0.0027343251,0.0006595527,0.000015469288,0.00003621738,0.00043207733],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982491,0.00014755077,0.00032391842,0.00046151353,0.00026769802,0.00055020885],"domain_scores_gemma":[0.9983649,0.00017720874,0.0001669939,0.00092393195,0.0002158031,0.00015113503],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009687947,0.00023216552,0.00019227833,0.00015361345,0.00070832,0.00056173664,0.0011316085,0.0001903053,0.00003040847],"category_scores_gemma":[0.00009317025,0.00017762539,0.00015449502,0.000507057,0.000091982845,0.0005772688,0.00017846929,0.00022432744,0.000028888651],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029498618,0.00008464847,0.00038171434,0.000011424807,0.00004460169,0.000013239295,0.00064185157,0.00076547574,0.014725925,0.19455513,0.022649348,0.7660971],"study_design_scores_gemma":[0.0001900115,0.00009339949,0.00075844576,0.000018505354,0.000012768997,0.000095176125,0.00007595839,0.95502853,0.015794806,0.009484557,0.018172111,0.00027573484],"about_ca_topic_score_codex":0.00051909575,"about_ca_topic_score_gemma":0.0020012583,"teacher_disagreement_score":0.95426303,"about_ca_system_score_codex":0.00016932972,"about_ca_system_score_gemma":0.00012374153,"threshold_uncertainty_score":0.7243353},"labels":[],"label_agreement":null},{"id":"W2963912924","doi":"","title":"Sample-efficient adaptive text-to-speech","year":2018,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Naturalness; Speech recognition; Artificial neural network; Embedding; Benchmark (surveying); Similarity (geometry); Stochastic gradient descent; Speaker recognition; Mean opinion score; Gradient descent; Artificial intelligence; Sample (material); Speaker diarisation; Metric (unit)","score_opus":0.08424185677777325,"score_gpt":0.19215710942935177,"score_spread":0.10791525265157852,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963912924","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15144017,0.0000027762549,0.82936686,0.00016479334,0.00023675936,0.0001299065,0.0000073420224,0.00021121609,0.018440187],"genre_scores_gemma":[0.9669608,0.000003359874,0.031149969,0.00058293674,0.00007892779,4.9308517e-7,7.836389e-7,0.000008245101,0.0012145085],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987686,0.00007494458,0.00010721142,0.00061746815,0.000098159755,0.00033359695],"domain_scores_gemma":[0.9987102,0.00019597803,0.000055375447,0.00057208166,0.00022037202,0.00024597094],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00018375905,0.00014526909,0.00013915916,0.00024846787,0.00022121337,0.0000678203,0.00088400114,0.00006400372,0.00038297966],"category_scores_gemma":[0.000103422906,0.00015476177,0.00009049436,0.0011790176,0.00010922782,0.0002064594,0.00030191636,0.000088396504,0.0030686192],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008527226,0.00026429535,0.00087670266,0.0000043271634,0.000059230453,0.00026081083,0.00064478867,0.0011975502,0.00047766426,0.90820104,0.0027726446,0.085155696],"study_design_scores_gemma":[0.00059865677,0.0003710144,0.0034043514,0.000032868236,0.00002465009,0.000022353968,0.00029797337,0.95603603,0.010745323,0.012415025,0.015487918,0.00056384766],"about_ca_topic_score_codex":0.00008425512,"about_ca_topic_score_gemma":0.000032368334,"teacher_disagreement_score":0.95483845,"about_ca_system_score_codex":0.00010067497,"about_ca_system_score_gemma":0.00005706669,"threshold_uncertainty_score":0.9977076},"labels":[],"label_agreement":null},{"id":"W2964187693","doi":"10.1109/icassp.2018.8462688","title":"Deep Residual Learning for Small-Footprint Keyword Spotting","year":2018,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":227,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Keyword spotting; Computer science; Residual; Convolutional neural network; Deep learning; Footprint; Memory footprint; Benchmark (surveying); Artificial intelligence; Spotting; Machine learning; Speech recognition; Algorithm; Cartography","score_opus":0.041542598232747745,"score_gpt":0.26400828492633893,"score_spread":0.22246568669359118,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964187693","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032627698,0.00000834525,0.91154826,0.0007730432,0.00022831696,0.00011743584,8.8367635e-8,0.00032768122,0.05436911],"genre_scores_gemma":[0.32533866,0.0000023449145,0.67038107,0.0004422787,0.000326429,0.000020046426,7.2504014e-7,0.000009640082,0.0034787932],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99911827,0.00004479012,0.00016217177,0.00029447966,0.00011777196,0.00026253005],"domain_scores_gemma":[0.9992498,0.00025998152,0.00005304314,0.00021787088,0.0001445885,0.00007471046],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004389965,0.000087243745,0.000098722485,0.00008103303,0.00024036835,0.00016396839,0.00039827146,0.000045954795,0.0001751225],"category_scores_gemma":[0.00034528144,0.00007699701,0.000058849382,0.00015327567,0.00003492016,0.00008730525,0.00014096292,0.00007543112,0.00027310738],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007756544,0.000019373452,0.00044245867,0.0000057569437,0.000011247657,0.0000026336993,0.00033555678,0.0000063018374,0.0009498247,0.020594157,0.00022374502,0.9774012],"study_design_scores_gemma":[0.0012051932,0.0006628312,0.008610711,0.00007027026,0.000021348476,0.00006798679,0.00081029953,0.51466805,0.32841328,0.016700331,0.12788348,0.0008861953],"about_ca_topic_score_codex":0.00001528034,"about_ca_topic_score_gemma":0.000049369843,"teacher_disagreement_score":0.976515,"about_ca_system_score_codex":0.000017666522,"about_ca_system_score_gemma":0.000025463776,"threshold_uncertainty_score":0.3510334},"labels":[],"label_agreement":null},{"id":"W2964250984","doi":"10.1109/icassp.2018.8461624","title":"An Experimental Analysis of the Power Consumption of Convolutional Neural Networks for Keyword Spotting","year":2018,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Keyword spotting; Computer science; Proxy (statistics); Convolutional neural network; Inference; Predictive power; Artificial intelligence; Footprint; Memory footprint; Spotting; Energy consumption; Predictive modelling; Artificial neural network; Machine learning; Data mining","score_opus":0.034677122342771385,"score_gpt":0.2989291442651436,"score_spread":0.26425202192237224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964250984","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6620022,0.000016903965,0.33713782,0.00005249197,0.00017547817,0.00008341215,0.000004841313,0.000019642335,0.0005072134],"genre_scores_gemma":[0.977957,4.4809937e-7,0.021791283,0.0001740564,0.000028118791,0.0000057435,0.0000028798436,0.000002264152,0.00003816738],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99935615,0.000051462688,0.00019747202,0.00014970603,0.0001429915,0.00010222354],"domain_scores_gemma":[0.999344,0.00011759157,0.00011889594,0.00024475425,0.00014469573,0.000030056148],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019797456,0.00005486896,0.00012557907,0.00008963628,0.00007821644,0.0000195905,0.00030717772,0.000031669082,0.00044185037],"category_scores_gemma":[0.000021671338,0.000038615362,0.00014880457,0.00033104143,0.00013065519,0.00014958192,0.00004896229,0.000023129052,0.0000016589574],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042811333,0.0022066648,0.3475982,0.000038271435,0.0025661117,0.0000017280399,0.0050481516,0.0045913425,0.23989746,0.2658801,0.003114962,0.12862888],"study_design_scores_gemma":[0.00014458808,0.000071807015,0.047736954,0.0000036040465,0.00004388075,0.0000012318737,0.00008043741,0.88836324,0.063408576,0.00006282498,0.000029829976,0.00005299594],"about_ca_topic_score_codex":0.000012717523,"about_ca_topic_score_gemma":0.000012649328,"teacher_disagreement_score":0.88377196,"about_ca_system_score_codex":0.000011936939,"about_ca_system_score_gemma":0.000011961157,"threshold_uncertainty_score":0.48379517},"labels":[],"label_agreement":null},{"id":"W2970680405","doi":"10.18653/v1/d19-1201","title":"Modeling Personalization in Continuous Space for Response Generation via Augmented Wasserstein Autoencoders","year":2019,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China; National Science Foundation","keywords":"Personalization; Computer science; Chen; Joint (building); Space (punctuation); Artificial intelligence; Natural language processing; World Wide Web; Engineering; Operating system","score_opus":0.029475567868854604,"score_gpt":0.2524900829017831,"score_spread":0.2230145150329285,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2970680405","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26488134,0.000009934505,0.7331399,0.0009959592,0.00014452728,0.00030951947,7.843842e-7,0.00008258527,0.00043549234],"genre_scores_gemma":[0.8298736,0.000002627984,0.16759948,0.0003793249,0.000020739135,0.000034865934,0.000009584902,0.000008316524,0.0020714116],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990822,0.000112965805,0.00018263997,0.00029159934,0.00016042727,0.0001701836],"domain_scores_gemma":[0.99953353,0.0000996608,0.000037668,0.0001882518,0.00010119785,0.000039680344],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000590227,0.000088360735,0.000118478405,0.00017659235,0.00004721149,0.0001007119,0.0001692817,0.000057576082,0.000102337566],"category_scores_gemma":[0.00008797883,0.000085502215,0.000050699084,0.0002185232,0.0000052550454,0.00038564432,0.000024365883,0.000037238085,0.0000623426],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010316925,0.00042361466,0.0017717767,0.00009808221,0.00007754628,0.000015684445,0.006211359,0.15287898,0.7100931,0.034592234,0.0024512676,0.0903547],"study_design_scores_gemma":[0.00059477054,0.000058288104,0.00005761364,0.0000139088215,0.0000023312716,0.0000029159987,0.00022564713,0.98675567,0.011738484,0.0002604844,0.00017043624,0.00011944928],"about_ca_topic_score_codex":0.000055052777,"about_ca_topic_score_gemma":0.000116054536,"teacher_disagreement_score":0.83387667,"about_ca_system_score_codex":0.000085991,"about_ca_system_score_gemma":0.00005239002,"threshold_uncertainty_score":0.34866792},"labels":[],"label_agreement":null},{"id":"W2984770459","doi":"10.1121/1.5137272","title":"Improved vowel labeling for prenasal merger using customized forced alignment","year":2019,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Pronunciation; Vowel; Formant; Computer science; Speech recognition; Centroid; Linguistics; Artificial intelligence","score_opus":0.01871390558617517,"score_gpt":0.26021190191442783,"score_spread":0.24149799632825267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2984770459","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03519437,0.00008126926,0.96100175,0.002880819,0.00048525917,0.0002961562,0.0000042048505,0.000012944091,0.000043217162],"genre_scores_gemma":[0.2794145,0.00010531716,0.7181093,0.002069728,0.00013104873,0.000002315683,1.3811e-7,0.000014291448,0.00015336268],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986235,0.0001363997,0.00046167566,0.00011178302,0.00041508165,0.00025158701],"domain_scores_gemma":[0.9978039,0.0009223605,0.00059458305,0.00035389455,0.00025122266,0.000074040065],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009907349,0.00012265083,0.0003395183,0.00001789132,0.00015190744,0.00003401337,0.0010168639,0.00005652113,0.00003972246],"category_scores_gemma":[0.0002134869,0.00006248081,0.00060149486,0.00019883357,0.0001428591,0.00014468373,0.00021426262,0.00019918729,0.0000036381568],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003503936,0.00017509553,0.000025512585,0.0000563452,0.0005038395,3.0336125e-7,0.0014146391,0.006073744,0.91266495,0.00003344622,0.007113601,0.07158814],"study_design_scores_gemma":[0.0010273763,0.00014685873,0.000032257685,0.000059178306,0.00016284284,0.00002129248,0.0005250074,0.9695184,0.027135214,0.00056706707,0.0007058989,0.00009857423],"about_ca_topic_score_codex":0.000019393652,"about_ca_topic_score_gemma":9.8418646e-8,"teacher_disagreement_score":0.9634447,"about_ca_system_score_codex":0.00007205405,"about_ca_system_score_gemma":0.000109537694,"threshold_uncertainty_score":0.25478932},"labels":[],"label_agreement":null},{"id":"W2989571531","doi":"10.1109/sped.2019.8906599","title":"FoR: A Dataset for Synthetic Speech Detection","year":2019,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":169,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Speech recognition; Artificial intelligence; Natural language processing","score_opus":0.024817805764369195,"score_gpt":0.2639481081266526,"score_spread":0.2391303023622834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2989571531","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0039622923,0.0000047741664,0.99142814,0.00047319388,0.00039019354,0.000554185,0.0002224963,0.00009889796,0.0028658158],"genre_scores_gemma":[0.28005198,0.0000050112167,0.7133036,0.0018497264,0.0001114753,0.000259518,0.00019226826,0.000018899422,0.0042075086],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994123,0.000011646856,0.00009931066,0.00024552405,0.000083103776,0.00014814234],"domain_scores_gemma":[0.99928707,0.0002483911,0.000028877583,0.00035083023,0.00004584797,0.00003899339],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021481562,0.000062144034,0.00008315202,0.00006241952,0.000049861024,0.0000818887,0.00028144216,0.000035700294,0.00016601324],"category_scores_gemma":[0.00007209044,0.0000526136,0.00005945665,0.000081486476,0.0000061604023,0.00020893809,0.000036577527,0.000021355587,0.00047163176],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015705282,0.000037322476,0.000015195653,0.000027242208,0.000012299876,4.485088e-7,0.00001702728,8.6270995e-7,0.0073951986,0.00581796,0.0130118,0.97364897],"study_design_scores_gemma":[0.00064186845,0.00020192577,0.00005844301,0.000011726699,0.000011147211,0.0000361244,0.00003464519,0.15117075,0.38198984,0.0092820665,0.45633116,0.00023030314],"about_ca_topic_score_codex":0.000007228404,"about_ca_topic_score_gemma":0.000023017392,"teacher_disagreement_score":0.97341865,"about_ca_system_score_codex":0.000015025116,"about_ca_system_score_gemma":0.0000136157505,"threshold_uncertainty_score":0.6062029},"labels":[],"label_agreement":null},{"id":"W2990074387","doi":"10.1109/mlsp.2019.8918703","title":"End-To-End Detection Of Attacks To Automatic Speaker Recognizers With Time-Attentive Light Convolutional Neural Networks","year":2019,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Computer science; Speech recognition; Convolutional neural network; Benchmark (surveying); Microphone; Word error rate; Speaker recognition; Biometrics; Dimension (graph theory); Set (abstract data type); Spectrogram; Artificial intelligence; Pattern recognition (psychology); Mathematics","score_opus":0.009264250930136903,"score_gpt":0.21120651866321333,"score_spread":0.2019422677330764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2990074387","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41558886,0.000009304636,0.5663999,0.0015664541,0.0005436112,0.0006635477,0.000004895273,0.0002517794,0.014971684],"genre_scores_gemma":[0.9541602,6.5224657e-7,0.04187031,0.001063022,0.00005027361,0.00002327711,0.0000033643064,0.00001316986,0.0028157278],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985746,0.00008529782,0.00026722293,0.00041461244,0.0003713637,0.00028689377],"domain_scores_gemma":[0.99900824,0.00017171878,0.0000983437,0.0003341141,0.00020868696,0.00017887513],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00023296666,0.00016318657,0.00023895754,0.00021805869,0.000060321032,0.00007639899,0.0003319734,0.00006404149,0.0019515291],"category_scores_gemma":[0.000034562352,0.000128882,0.000081823884,0.00062508206,0.000026252339,0.0003141236,0.00010673681,0.00010051359,0.0018257785],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023763908,0.00035079737,0.005669545,0.000055598128,0.00037203144,0.000029875793,0.0010405506,0.0035928567,0.039596662,0.0010722871,0.006994111,0.94098806],"study_design_scores_gemma":[0.0005807359,0.0005028052,0.017708343,0.000078610654,0.000026128477,0.00006465887,0.00012225147,0.9454791,0.033711087,0.00006114792,0.0012768022,0.00038832624],"about_ca_topic_score_codex":0.000031717424,"about_ca_topic_score_gemma":0.00005279619,"teacher_disagreement_score":0.94188625,"about_ca_system_score_codex":0.00007945221,"about_ca_system_score_gemma":0.000036876016,"threshold_uncertainty_score":0.9989608},"labels":[],"label_agreement":null},{"id":"W2990506421","doi":"","title":"Speech Perception and The Role of Semantic Richness in Processing","year":2019,"lang":"en","type":"article","venue":"Canadian acoustics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Concreteness; Lexical decision task; Speech perception; Psychology; Valence (chemistry); Semantic property; Perception; Semantic memory; Cognitive psychology; Semantic similarity; Computer science; Speech recognition; Natural language processing; Cognition","score_opus":0.005660513892169393,"score_gpt":0.19439392822627233,"score_spread":0.18873341433410293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2990506421","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98405683,0.00012469916,0.008698967,0.0004564981,0.00009451292,0.00017901708,0.00000300028,0.000014550495,0.0063719056],"genre_scores_gemma":[0.99440736,0.000016332711,0.005217783,0.00023760206,0.000013773602,0.0000023789985,4.9997493e-7,0.000003873745,0.00010040263],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995172,0.000029524848,0.00010740952,0.00011690146,0.00009017721,0.00013878588],"domain_scores_gemma":[0.9996345,0.00005803446,0.000034570763,0.00015098669,0.00005010007,0.000071827075],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020748933,0.00005123336,0.00009900838,0.0001329443,0.000036242356,0.000066543624,0.00020043619,0.00003998035,0.000037202975],"category_scores_gemma":[0.00005196728,0.000039795894,0.000014345711,0.00022179782,0.000049958624,0.000097448195,0.000021375272,0.000066821136,0.000027389679],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000072796856,0.00001780221,0.021541232,0.000084938896,0.0000064740593,0.000018077006,0.0025941026,0.00007149842,0.015434333,0.005158226,0.00007168929,0.9549943],"study_design_scores_gemma":[0.0006602281,0.000017493318,0.1781023,0.0001042487,0.000014492327,0.000056058932,0.0021201076,0.8108702,0.0004262262,0.0069526806,0.00048475686,0.00019125902],"about_ca_topic_score_codex":0.00388018,"about_ca_topic_score_gemma":0.0025203803,"teacher_disagreement_score":0.9548031,"about_ca_system_score_codex":0.000046152098,"about_ca_system_score_gemma":0.00015924018,"threshold_uncertainty_score":0.5865697},"labels":[],"label_agreement":null},{"id":"W2991975083","doi":"","title":"Strategies to Enhance Whispered Speech Speaker Verification: A Comparative Analysis","year":2015,"lang":"en","type":"article","venue":"Canadian acoustics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Computer science; Speech recognition; Noise (video); Task (project management); Feature (linguistics); Speech enhancement; Speech technology; Speech processing; Background noise; Artificial intelligence; Linguistics; Engineering; Telecommunications","score_opus":0.05715611910217276,"score_gpt":0.31204669478241864,"score_spread":0.25489057568024587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2991975083","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052637402,0.000056083067,0.8707706,0.002245694,0.00041332358,0.00022846607,0.00006124271,0.00011995164,0.07346729],"genre_scores_gemma":[0.88084567,0.00000331284,0.11696268,0.0011422434,0.00006267794,0.000012715876,0.000014227725,0.000005304723,0.0009511454],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987723,0.00005564784,0.0002028411,0.00036448234,0.00026490874,0.00033979487],"domain_scores_gemma":[0.9978991,0.000051903808,0.000052780422,0.00057783455,0.00041638385,0.0010019554],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002008006,0.00014283539,0.00023621,0.0004726258,0.00009817721,0.00046817068,0.00061739195,0.000066081644,0.00018124214],"category_scores_gemma":[0.00009060529,0.00015025586,0.00006409343,0.0017139665,0.000041746123,0.00028434122,0.000034201646,0.00009390279,0.0009987481],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057795147,0.00032091784,0.0027315947,0.000045386845,0.0021240157,0.0009453317,0.03833617,0.02601695,0.017251674,0.114822514,0.58625287,0.21109477],"study_design_scores_gemma":[0.0008015514,0.00040679084,0.066975065,0.000068283,0.0009753382,0.00012968191,0.023678878,0.59219104,0.012802304,0.008061734,0.29080486,0.0031044334],"about_ca_topic_score_codex":0.008145008,"about_ca_topic_score_gemma":0.04518435,"teacher_disagreement_score":0.82820827,"about_ca_system_score_codex":0.00029931992,"about_ca_system_score_gemma":0.0010424382,"threshold_uncertainty_score":0.9997791},"labels":[],"label_agreement":null},{"id":"W3006824058","doi":"10.1109/asru46091.2019.9003792","title":"Development of Voice Spoofing Detection Systems for 2019 Edition of Automatic Speaker Verification and Countermeasures Challenge","year":2019,"lang":"en","type":"article","venue":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Spoofing attack; Computer science; Convolutional neural network; Speaker verification; Speech recognition; Mel-frequency cepstrum; Speaker recognition; Artificial intelligence; Frame (networking); Bottleneck; Pattern recognition (psychology); Classifier (UML); Replay attack; Biometrics; Feature extraction; Artificial neural network; Authentication (law); Computer security","score_opus":0.08200242944652283,"score_gpt":0.2663433709157091,"score_spread":0.18434094146918625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3006824058","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48791566,0.00032397467,0.5082202,0.00012966331,0.0012856144,0.0012507401,0.000035163655,0.00021069462,0.00062825717],"genre_scores_gemma":[0.9414563,0.00031444506,0.05783852,0.000035624427,0.00006930471,0.000068043526,0.000048791706,0.00003259495,0.00013635762],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99769443,0.00012360944,0.00086860737,0.00050120667,0.00050558697,0.00030654704],"domain_scores_gemma":[0.99792176,0.00068267906,0.00069846417,0.00033438992,0.00025351034,0.00010919651],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012497711,0.0002770513,0.00051420584,0.00047900595,0.00019442438,0.000176033,0.0002042321,0.00021643823,0.000046666763],"category_scores_gemma":[0.00013522309,0.00027477244,0.00009279136,0.00033865962,0.0000869167,0.00072368904,0.00004060131,0.00012949636,0.0000542686],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008173421,0.00030880226,0.0001317177,0.002970911,0.0002991848,0.0000022708127,0.0041827583,0.000014744979,0.024822298,0.0011015359,0.0009324028,0.9651516],"study_design_scores_gemma":[0.0054726023,0.0005617881,0.003987222,0.007819583,0.00033355653,0.00025356136,0.013459948,0.8598724,0.094687276,0.010919569,0.00096722395,0.0016652843],"about_ca_topic_score_codex":0.000017540107,"about_ca_topic_score_gemma":0.000028050075,"teacher_disagreement_score":0.9634864,"about_ca_system_score_codex":0.00022348958,"about_ca_system_score_gemma":0.000091768,"threshold_uncertainty_score":0.99997044},"labels":[],"label_agreement":null},{"id":"W3010128010","doi":"10.1007/s11042-020-08748-2","title":"Mixture linear prediction Gammatone Cepstral features for robust speaker verification under transmission channel noise","year":2020,"lang":"en","type":"article","venue":"Multimedia Tools and Applications","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Computer science; Additive white Gaussian noise; Speech recognition; Linear prediction; Mel-frequency cepstrum; Channel (broadcasting); Cepstrum; Rayleigh fading; Ranging; Noise (video); Word error rate; Pattern recognition (psychology); Artificial intelligence; Fading; Feature extraction; Telecommunications","score_opus":0.05204491654214465,"score_gpt":0.2542930151035971,"score_spread":0.20224809856145243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3010128010","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007460195,0.0001346147,0.9872404,0.010228053,0.000055615194,0.00089164096,0.0001786121,0.00021704659,0.00030800782],"genre_scores_gemma":[0.16580036,0.0004910103,0.82727176,0.002234229,0.0010428331,0.0018637406,0.00079447444,0.000045118333,0.00045646582],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99905336,0.00002118578,0.00020111188,0.00041302206,0.00014151017,0.00016981304],"domain_scores_gemma":[0.99930704,0.000117234515,0.00006572189,0.00020711828,0.00009083712,0.0002120296],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000080355756,0.0001358854,0.00013378954,0.000040582505,0.00021274124,0.00012127833,0.00021826828,0.000116774296,0.00002637523],"category_scores_gemma":[0.00002820828,0.00012185974,0.0000704321,0.00021783184,0.000040056297,0.00028573623,0.000023448574,0.00011226351,0.000031645162],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003840642,0.00016168073,0.00005320116,0.00008097346,0.000030768224,5.886063e-7,0.0010616919,0.00057543506,0.021852871,0.0028278339,0.004466222,0.9688503],"study_design_scores_gemma":[0.0010324734,0.0000740902,0.010146765,0.000027503365,0.000047754533,0.000013722722,0.00018045308,0.87502664,0.022085348,0.00093894155,0.09010465,0.00032168548],"about_ca_topic_score_codex":0.0000049875575,"about_ca_topic_score_gemma":0.0000019643057,"teacher_disagreement_score":0.9685286,"about_ca_system_score_codex":0.000013799602,"about_ca_system_score_gemma":0.0000277159,"threshold_uncertainty_score":0.4969296},"labels":[],"label_agreement":null},{"id":"W3012387963","doi":"10.1017/cbo9781139029377.006","title":"Computational Models of Spoken Word Recognition","year":2018,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":72,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Word (group theory); Computer science; Natural language processing; Artificial intelligence; Speech recognition; Linguistics; Philosophy","score_opus":0.05256983140844455,"score_gpt":0.20766540037962772,"score_spread":0.15509556897118315,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3012387963","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013855605,0.00002153917,0.13596326,0.000014388186,0.00018038352,0.00020996263,0.00023525793,0.00013913831,0.8630975],"genre_scores_gemma":[0.00089775684,0.000041445473,0.031961225,0.000092241185,0.00009876948,6.688406e-7,0.000090778245,0.00002621695,0.9667909],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99865395,0.00004521428,0.00024285645,0.0004923821,0.00038074944,0.00018484976],"domain_scores_gemma":[0.99844605,0.00013187763,0.00031985552,0.0004500724,0.00052353315,0.00012859145],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00012770838,0.0002582581,0.00034688367,0.00031308533,0.00011047804,0.000048938058,0.00078726123,0.0002697646,0.000038260212],"category_scores_gemma":[0.000008510526,0.0003158644,0.00022764209,0.000016960268,0.0002155159,0.00027113638,0.00035212078,0.00020182702,0.00008102636],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005429583,0.00002237094,2.0112786e-7,0.00006120778,0.0001499125,0.00009527302,0.000103394384,0.000021503234,0.000010514123,0.9067876,0.024277063,0.06841672],"study_design_scores_gemma":[0.002042099,0.00025184033,0.000023446964,0.0011760619,0.000404192,0.00012898742,0.000071492024,0.07568256,0.0033852065,0.020857275,0.89398193,0.001994924],"about_ca_topic_score_codex":0.000028242224,"about_ca_topic_score_gemma":9.0730106e-7,"teacher_disagreement_score":0.88593024,"about_ca_system_score_codex":0.00009607568,"about_ca_system_score_gemma":0.00013020755,"threshold_uncertainty_score":0.99992937},"labels":[],"label_agreement":null},{"id":"W3014279133","doi":"10.3233/jifs-179715","title":"Foreign accent classification using deep neural nets","year":2020,"lang":"en","type":"article","venue":"Journal of Intelligent & Fuzzy Systems","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Stress (linguistics); Convolutional neural network; Computer science; Architecture; Speech recognition; Spectrogram; Cascade; Deep learning; Artificial intelligence; Identification (biology); Artificial neural network; Convolution (computer science); Natural language processing; History; Engineering","score_opus":0.13553378409866199,"score_gpt":0.2953088282515196,"score_spread":0.15977504415285762,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3014279133","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043865964,0.0010329825,0.9479306,0.0017369153,0.0017224639,0.00023065241,0.0000013942272,0.000052544798,0.003426504],"genre_scores_gemma":[0.98814625,0.00007192764,0.0105978595,0.0006186399,0.0005336745,0.0000021956337,5.8006316e-7,0.000012131689,0.000016770582],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979848,0.00018395859,0.0008607232,0.00019795455,0.0005544391,0.0002181222],"domain_scores_gemma":[0.9982416,0.00011143442,0.00072112225,0.00021015637,0.0004237789,0.0002918828],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046690306,0.0001459066,0.00030760086,0.0001623863,0.00008179945,0.00034795867,0.000779433,0.00006903018,0.000031370575],"category_scores_gemma":[0.0001605055,0.00011618878,0.0002124263,0.0003532235,0.000020285977,0.00056281517,0.000068733134,0.00020706006,0.000076207885],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027839153,0.0005860244,0.008742539,0.00037855285,0.0006022823,0.00075829535,0.0057374537,0.017951008,0.03914506,0.0518616,0.00858185,0.86537695],"study_design_scores_gemma":[0.00020376487,0.00022841035,0.0005587136,0.00011259863,0.000029814573,0.000699307,0.0013351109,0.98252094,0.0072457353,0.0003521921,0.0065095336,0.00020386458],"about_ca_topic_score_codex":0.000010659116,"about_ca_topic_score_gemma":7.7622843e-7,"teacher_disagreement_score":0.9645699,"about_ca_system_score_codex":0.00012896243,"about_ca_system_score_gemma":0.0000689993,"threshold_uncertainty_score":0.4738041},"labels":[],"label_agreement":null},{"id":"W3015280134","doi":"10.1109/icassp40776.2020.9053831","title":"Improving Speech Recognition Using Consistent Predictions on Synthesized Speech","year":2020,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Speech recognition; Computer science; Audio mining; Voice activity detection; Acoustic model; Speech processing; Point (geometry); Speech synthesis; Speech coding; Natural language processing; Mathematics","score_opus":0.0889213252948868,"score_gpt":0.2574665341658127,"score_spread":0.16854520887092592,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3015280134","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.089289136,0.00002549133,0.8499635,0.007505929,0.0007835526,0.0006841648,0.00003028453,0.0016760888,0.050041873],"genre_scores_gemma":[0.2877926,0.000016847924,0.7053628,0.0062750657,0.00031372334,0.000022956883,0.000008741444,0.000029940093,0.00017736302],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99823767,0.00012560206,0.0003527345,0.0005779664,0.00039983445,0.00030618635],"domain_scores_gemma":[0.99884903,0.00029435987,0.00012638535,0.0003504707,0.000112103386,0.00026766057],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00025112426,0.00020048946,0.0002335663,0.0001456449,0.00022586076,0.00025137913,0.00039566413,0.00009877252,0.00060477736],"category_scores_gemma":[0.00055389374,0.00018523374,0.00016009538,0.000480647,0.00004117992,0.00046842397,0.00011894166,0.00018821267,0.0009108662],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002912206,0.00011218077,0.00004139594,0.000018393013,0.000039482286,0.00007755263,0.00011396368,0.00000770737,0.01497868,0.00036658774,0.0010404304,0.9831745],"study_design_scores_gemma":[0.00076721,0.0002338222,0.00010678499,0.000086150605,0.000059235637,0.00021565246,0.0002351494,0.6745013,0.3204057,0.0009098196,0.0019639386,0.00051527144],"about_ca_topic_score_codex":0.000077050405,"about_ca_topic_score_gemma":0.000009142824,"teacher_disagreement_score":0.9826592,"about_ca_system_score_codex":0.000080026584,"about_ca_system_score_gemma":0.00009422079,"threshold_uncertainty_score":0.999867},"labels":[],"label_agreement":null},{"id":"W3015774894","doi":"10.1109/icassp40776.2020.9054558","title":"An Ensemble Based Approach for Generalized Detection of Spoofing Attacks to Automatic Speaker Recognizers","year":2020,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Spoofing attack; Computer science; Speech recognition; Speaker verification; Spotting; Replay attack; A priori and a posteriori; Speaker recognition; Artificial intelligence; Speech synthesis; Machine learning; Authentication (law); Computer security","score_opus":0.05890024659451769,"score_gpt":0.27698860753137416,"score_spread":0.21808836093685646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3015774894","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.059907567,0.0000034135332,0.9371265,0.00061941915,0.00007465991,0.0004119591,0.000002888133,0.00026973363,0.0015838625],"genre_scores_gemma":[0.40610746,3.563588e-7,0.5919741,0.0018088548,0.00003179687,0.000037177237,0.0000033982813,0.000008217083,0.000028688422],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989423,0.00007641409,0.00025687108,0.00036103037,0.00017853722,0.00018482411],"domain_scores_gemma":[0.99926776,0.0000962502,0.00007318514,0.00026248445,0.000107209155,0.00019312788],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002728093,0.00011219106,0.00020281276,0.00010626206,0.00006230593,0.000076081655,0.00033158902,0.00005161811,0.00009115767],"category_scores_gemma":[0.0001422382,0.00010215455,0.00010306877,0.00040798087,0.000010197611,0.00021998462,0.000028365343,0.000038398026,0.000029953411],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048109163,0.00010706681,0.000034072906,0.0001254586,0.000022365293,0.0000012828544,0.00047409127,0.00096062827,0.24521378,0.00027090663,0.00055014156,0.7521921],"study_design_scores_gemma":[0.00034799107,0.00012885996,0.00005711338,0.000005811167,0.000009118626,0.0000013503422,0.00004754499,0.6640878,0.33488294,0.00006028376,0.00026663413,0.000104563485],"about_ca_topic_score_codex":0.000018091394,"about_ca_topic_score_gemma":0.000007088196,"teacher_disagreement_score":0.75208753,"about_ca_system_score_codex":0.000020447444,"about_ca_system_score_gemma":0.00003687258,"threshold_uncertainty_score":0.41657415},"labels":[],"label_agreement":null},{"id":"W3025427857","doi":"10.48550/arxiv.2005.08520","title":"Robust Training of Vector Quantized Bottleneck Models","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Infrastruktura PL-Grid; Johns Hopkins University; Canadian Institute for Advanced Research","keywords":"Bottleneck; Computer science; Training (meteorology); Artificial intelligence; Machine learning","score_opus":0.3594836041480978,"score_gpt":0.20217616659545884,"score_spread":0.15730743755263898,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3025427857","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.074793994,0.00003558713,0.91671336,0.0002630936,0.0003978682,0.00019401603,0.000029011248,0.00028002064,0.0072930297],"genre_scores_gemma":[0.9682105,0.00011407792,0.031225923,0.00010892339,0.000048315527,7.4537934e-7,0.0000087180115,0.000017793533,0.00026498863],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99826306,0.000148662,0.00026202627,0.0009287458,0.00012620958,0.00027131382],"domain_scores_gemma":[0.9983875,0.00016950215,0.00030372647,0.0007884793,0.00015608444,0.00019471775],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00019887615,0.0002674985,0.00051632524,0.00022828832,0.00007282794,0.00006932436,0.001605626,0.00024068239,0.00008503116],"category_scores_gemma":[0.00007032539,0.00031499646,0.00034696938,0.0005222886,0.00008243846,0.00032687455,0.0009872563,0.00038820755,0.00006399676],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011753109,0.000215283,0.00016141633,0.00030863562,0.0004176573,0.0006245912,0.0023769324,0.30043048,0.0010200063,0.68263555,0.00064531993,0.011046619],"study_design_scores_gemma":[0.00042245002,0.00003406331,0.00013411263,0.000119304634,0.00005780531,0.000003425322,0.00016708457,0.93477106,0.0012273476,0.06263231,0.000086371794,0.00034464814],"about_ca_topic_score_codex":0.00006609291,"about_ca_topic_score_gemma":0.000010456445,"teacher_disagreement_score":0.8934165,"about_ca_system_score_codex":0.000071656876,"about_ca_system_score_gemma":0.0002595165,"threshold_uncertainty_score":0.9999302},"labels":[],"label_agreement":null},{"id":"W3028638700","doi":"","title":"Developing Resources for Automated Speech Processing of Quebec French","year":2020,"lang":"en","type":"preprint","venue":"SERVAL (Université de Lausanne)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Syllabification; Phonotactics; Computer science; Lexicon; Speech segmentation; Pronunciation; Phonetic transcription; Segmentation; Speech recognition; Natural language processing; Artificial intelligence; Speech processing; Phonology; Process (computing); Software; Linguistics; Syllable","score_opus":0.038236760357029165,"score_gpt":0.25135523636217255,"score_spread":0.2131184760051434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3028638700","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4109667,0.0007187261,0.5644984,0.01165171,0.00056509924,0.0011105818,0.00014487645,0.002682391,0.007661541],"genre_scores_gemma":[0.121031925,0.00005678849,0.875681,0.0007132739,0.0001428506,0.00001715611,0.000068940826,0.0000457195,0.0022423891],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982666,0.000091919166,0.00028961967,0.0006602938,0.00033186103,0.00035970978],"domain_scores_gemma":[0.99856794,0.00013606311,0.00039090618,0.00040730496,0.00034459692,0.0001531923],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00025575326,0.0002764651,0.00046356363,0.00023944734,0.00024224838,0.00014867485,0.0015212358,0.00031931326,0.000052765186],"category_scores_gemma":[0.00007760137,0.000316237,0.00021715224,0.00047993785,0.000058183337,0.00026616565,0.0015723512,0.0002526124,0.000021983935],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017838541,0.00017985614,0.0011402018,0.0051979907,0.0006232727,0.0005046192,0.03392108,0.00043783072,0.007667959,0.011702806,0.01838772,0.92005825],"study_design_scores_gemma":[0.0015140695,0.00015447658,0.021345848,0.0030881618,0.00026304097,0.00008212214,0.001897793,0.868992,0.04081568,0.022806944,0.03723497,0.001804921],"about_ca_topic_score_codex":0.002128955,"about_ca_topic_score_gemma":0.00237405,"teacher_disagreement_score":0.91825336,"about_ca_system_score_codex":0.00043421346,"about_ca_system_score_gemma":0.0006476184,"threshold_uncertainty_score":0.99992895},"labels":[],"label_agreement":null},{"id":"W3029693316","doi":"","title":"Speech Transcription Challenges for Resource Constrained Indigenous Language Cree","year":2020,"lang":"en","type":"article","venue":"Workshop Spoken Language Technologies for Under-resourced Languages","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Word error rate; Transcription (linguistics); Speech recognition; Natural language processing; Word (group theory); Language model; Documentation; Artificial intelligence; Spoken language; Error analysis; Linguistics","score_opus":0.04157063800353791,"score_gpt":0.2814875973299665,"score_spread":0.23991695932642856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3029693316","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20164834,0.028042128,0.6749737,0.06465973,0.0002908505,0.006049866,0.0004943321,0.016977916,0.0068631023],"genre_scores_gemma":[0.80009115,0.00021646825,0.19460939,0.0026966527,0.00030406055,0.00073517027,0.00019318658,0.00014681667,0.0010071077],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.99659294,0.00008450293,0.0005901841,0.0012144704,0.00046021256,0.0010577065],"domain_scores_gemma":[0.9973195,0.0009271252,0.00029170385,0.0011393565,0.0001157816,0.00020652218],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00053512136,0.000606126,0.0007315861,0.00045162946,0.00044075146,0.00029286457,0.0022314803,0.0006558088,0.0000667932],"category_scores_gemma":[0.00089347514,0.0005646618,0.00048642495,0.0007150826,0.00031022364,0.00030197628,0.00028572886,0.00047869878,0.00003871632],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031649598,0.00014273047,0.000005800517,0.00026327465,0.0001963683,0.00017476916,0.030435147,0.00004346432,0.03728726,0.009048005,0.00146389,0.92062277],"study_design_scores_gemma":[0.008404784,0.0012174345,0.00009839588,0.00033363944,0.00027684224,0.00025125445,0.62167543,0.008532946,0.29357973,0.0030954182,0.059926856,0.002607276],"about_ca_topic_score_codex":0.000029164432,"about_ca_topic_score_gemma":0.00014644134,"teacher_disagreement_score":0.91801554,"about_ca_system_score_codex":0.00010896667,"about_ca_system_score_gemma":0.00006714156,"threshold_uncertainty_score":0.99968046},"labels":[],"label_agreement":null},{"id":"W3030267806","doi":"","title":"On The Performance of Time-Pooling Strategies for End-to-End Spoken Language Identification.","year":2020,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Pooling; Computer science; Benchmark (surveying); Artificial intelligence; Dimension (graph theory); Representation (politics); Set (abstract data type); Spoken language; Identification (biology); Machine learning; Selection (genetic algorithm); Language model; Natural language processing; Test set; Mathematics","score_opus":0.0337936629644121,"score_gpt":0.28381202723240906,"score_spread":0.25001836426799695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3030267806","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98614466,0.00022335013,0.010416672,0.0017008992,0.000026492224,0.0003523841,0.00001073084,0.000037868143,0.0010869495],"genre_scores_gemma":[0.99689966,0.0000090568155,0.0022800658,0.00059075677,0.00007462371,0.000041942032,0.000009801497,0.0000055018495,0.00008859824],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991698,0.000080331,0.00015946466,0.00018677655,0.00030592407,0.00009766883],"domain_scores_gemma":[0.9993379,0.0002729423,0.00008774473,0.0001801766,0.00007699589,0.000044245095],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00078153284,0.000070153284,0.00009105584,0.000049724775,0.00010404372,0.00014247822,0.00022625405,0.00002576356,0.00021144816],"category_scores_gemma":[0.00021811521,0.0000495952,0.000034824407,0.00016739975,0.000020152218,0.0001481586,0.000035769895,0.00004119432,0.000046282898],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008078053,0.00003887194,0.00007601148,0.000109693756,0.000044062734,0.0000015580857,0.08896527,0.0015222152,0.09817736,0.003704509,0.000872997,0.8064067],"study_design_scores_gemma":[0.00030026486,0.00017767784,0.0021961597,0.00005144296,0.000033235345,0.0000023737348,0.008244388,0.93428034,0.053732812,0.0003457523,0.00049948867,0.00013608721],"about_ca_topic_score_codex":0.000017901344,"about_ca_topic_score_gemma":0.000004471851,"teacher_disagreement_score":0.9327581,"about_ca_system_score_codex":0.000009531365,"about_ca_system_score_gemma":0.000023001588,"threshold_uncertainty_score":0.2315209},"labels":[],"label_agreement":null},{"id":"W3035183237","doi":"10.1109/access.2020.3001426","title":"Multi-Objective Optimization of Wavelet-Packet-Based Features in Pathological Diagnosis of Alzheimer Using Spontaneous Speech Signals","year":2020,"lang":"en","type":"article","venue":"IEEE Access","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Wavelet packet decomposition; Computer science; Wavelet; Pattern recognition (psychology); Entropy (arrow of time); Feature selection; Artificial intelligence; Speech recognition; Network packet; Frequency band; Wavelet transform; Feature extraction; Bandwidth (computing)","score_opus":0.10267228334105753,"score_gpt":0.3261930617415912,"score_spread":0.22352077840053364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3035183237","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.58615154,0.00012820488,0.41270664,0.00032417127,0.00012645827,0.00033193425,0.000019584879,0.00005695352,0.00015449256],"genre_scores_gemma":[0.790001,0.000016130505,0.20946038,0.0004761444,0.0000224486,0.000012772771,0.0000023637065,0.0000079014835,8.6950104e-7],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986593,0.00019831557,0.00035338674,0.0003470892,0.00026832314,0.0001735573],"domain_scores_gemma":[0.9989962,0.0003280656,0.00022466894,0.00019948413,0.00017809011,0.000073475814],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019774555,0.00014018378,0.00033421107,0.00016939537,0.00003079284,0.0000592266,0.0005916502,0.00011330884,0.00010221973],"category_scores_gemma":[0.0003020982,0.00012487255,0.00009637649,0.00067186734,0.00006175866,0.00032258482,0.000086356165,0.00011682795,0.000003107316],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005476343,0.0027936655,0.02363221,0.00027349425,0.000296084,0.0052416096,0.003767206,0.49711424,0.14083299,0.00011710584,0.00050385436,0.32487988],"study_design_scores_gemma":[0.0004157054,0.00007445825,0.0050221574,0.000056052057,0.000022274711,0.00003160165,0.000030669595,0.3712876,0.6228702,0.0000405278,0.0000029517287,0.00014574396],"about_ca_topic_score_codex":0.00010740712,"about_ca_topic_score_gemma":0.000025279378,"teacher_disagreement_score":0.48203725,"about_ca_system_score_codex":0.00002320511,"about_ca_system_score_gemma":0.00006395747,"threshold_uncertainty_score":0.5092155},"labels":[],"label_agreement":null},{"id":"W3039097787","doi":"10.5573/ieiespc.2020.9.3.185","title":"Adaptive Feature Generation for Speech Emotion Recognition","year":2020,"lang":"en","type":"article","venue":"IEIE Transactions on Smart Processing and Computing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Speech recognition; Mel-frequency cepstrum; Artificial intelligence; Classifier (UML); Feature (linguistics); Principal component analysis; Pattern recognition (psychology); Emotion recognition; Correlation; Emotion classification; Cepstrum; Sentiment analysis; Feature extraction; Mathematics","score_opus":0.07397113750810175,"score_gpt":0.2624858273158806,"score_spread":0.18851468980777886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3039097787","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019241946,0.000064755295,0.976086,0.0035400167,0.0001914629,0.00022861239,0.000008599963,0.00031621556,0.0003223818],"genre_scores_gemma":[0.7247434,0.0000125614015,0.27383718,0.0011651316,0.0001631674,0.000014624742,0.000009718129,0.000012082655,0.000042095246],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99893504,0.000056231693,0.00018625762,0.00046490473,0.00016664875,0.00019093096],"domain_scores_gemma":[0.99942964,0.00009155547,0.000094906056,0.00009573462,0.0001755509,0.0001125863],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019224624,0.00015375852,0.00015377851,0.00009517819,0.000622845,0.00030478003,0.00012633746,0.00009277698,0.000008517236],"category_scores_gemma":[0.000020769674,0.00015449051,0.000072654104,0.0003256464,0.000024624907,0.00041219234,0.0000038566995,0.00017995828,0.000016247737],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020212978,0.000038040234,0.0000025378545,0.000032430657,0.000010979941,0.0000015999348,0.0008138001,0.00017310228,0.0013320866,0.000027091919,0.00012526089,0.9974229],"study_design_scores_gemma":[0.00045112649,0.00022243567,0.00005937163,0.00009815276,0.000025900204,0.000034291206,0.00020884315,0.977486,0.020149482,0.0004316541,0.00060844864,0.00022428151],"about_ca_topic_score_codex":0.0000034309937,"about_ca_topic_score_gemma":0.0000033128495,"teacher_disagreement_score":0.9971986,"about_ca_system_score_codex":0.000025724974,"about_ca_system_score_gemma":0.00004198981,"threshold_uncertainty_score":0.62999403},"labels":[],"label_agreement":null},{"id":"W3082696729","doi":"10.21437/interspeech.2020-3132","title":"Neural Architecture Search for Keyword Spotting","year":2020,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Keyword spotting; Computer science; Convolutional neural network; Spotting; Artificial intelligence; Memory footprint; Architecture; Artificial neural network; Utterance; Speech recognition","score_opus":0.061623679488180434,"score_gpt":0.2687005166181165,"score_spread":0.20707683712993608,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3082696729","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012905675,0.000009858145,0.94760245,0.02723572,0.0000777332,0.00015044419,0.0000018121079,0.0002607548,0.011755557],"genre_scores_gemma":[0.5321329,0.0000010382302,0.45811513,0.009113427,0.00019253125,0.00001269796,0.0000014174295,0.000007717039,0.0004230999],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993561,0.00002616943,0.00008960045,0.000220925,0.00012625006,0.00018093431],"domain_scores_gemma":[0.9995391,0.0001709853,0.00001352898,0.00012168447,0.000038912167,0.00011579966],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000099487785,0.00006187621,0.00007725736,0.000031646174,0.00007151861,0.000107256834,0.0003827595,0.00002315895,0.00013555992],"category_scores_gemma":[0.000071724804,0.000049603103,0.00006768501,0.00018224341,0.000008578862,0.00009452184,0.00009022944,0.00007571359,0.00009074437],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008631196,0.000009547706,0.00012298448,0.000015262798,0.0000061482347,0.000006316362,0.00054972665,0.000033555163,0.0017367769,0.009165123,0.0019240336,0.9864219],"study_design_scores_gemma":[0.00053723814,0.00017133556,0.00065799605,0.000009180483,0.0000048242555,0.000027590851,0.0001588576,0.8557427,0.10217813,0.0019188421,0.038292624,0.00030067153],"about_ca_topic_score_codex":0.000003309014,"about_ca_topic_score_gemma":9.979622e-7,"teacher_disagreement_score":0.98612124,"about_ca_system_score_codex":0.0000045703314,"about_ca_system_score_gemma":0.00001735032,"threshold_uncertainty_score":0.20227557},"labels":[],"label_agreement":null},{"id":"W3082779874","doi":"","title":"Knowing What to Listen to: Early Attention for Deep Speech Representation Learning.","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Robustness (evolution); Speech recognition; Deep learning; Speaker recognition; Artificial intelligence; Deep neural networks; Speech processing; Task (project management); Emotion recognition; Feature learning","score_opus":0.12312090177717262,"score_gpt":0.23271275799311855,"score_spread":0.10959185621594593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3082779874","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20857179,0.000012762118,0.7867916,0.0013747704,0.00077738456,0.00075513776,0.000004323093,0.00029032357,0.0014219036],"genre_scores_gemma":[0.9502219,0.000070815295,0.04471775,0.0005917423,0.00019244019,0.000011082715,0.000037123114,0.000031586234,0.004125575],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99782664,0.00016244427,0.00022613702,0.0013238478,0.00014242013,0.00031853665],"domain_scores_gemma":[0.9983466,0.0002023002,0.00017046953,0.0006444062,0.00030299,0.00033317966],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00025724832,0.00025275577,0.00031228396,0.00037392962,0.00020076957,0.0007001158,0.0011223418,0.00019672618,0.0000374881],"category_scores_gemma":[0.00028761997,0.00032230123,0.00031496855,0.00081445836,0.000019266547,0.0008813711,0.0011844438,0.0003277678,0.0005760982],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047315587,0.00028877033,0.009186154,0.00036161684,0.00051179127,0.00077797926,0.0054067797,0.08522582,0.0033554982,0.031560984,0.0025952193,0.86025625],"study_design_scores_gemma":[0.0014527541,0.00063951325,0.01655869,0.0008370689,0.0002930063,0.000015199899,0.002946384,0.9242854,0.0064379782,0.031882387,0.012619483,0.0020321053],"about_ca_topic_score_codex":0.00009949366,"about_ca_topic_score_gemma":0.000045198794,"teacher_disagreement_score":0.85822415,"about_ca_system_score_codex":0.0001819194,"about_ca_system_score_gemma":0.000064284715,"threshold_uncertainty_score":0.99992293},"labels":[],"label_agreement":null},{"id":"W3086122814","doi":"","title":"Voice Biometrics Distinction Between English, French, Arabic and Spanish Using Sound Cleaner Filtering and SpeechPro SIS II Analysis for Same Individual Identification in Multilingual Societies","year":2020,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"CLIPS; Identity (music); Computer science; Biometrics; Tone (literature); Arabic; Identification (biology); Isolation (microbiology); Speech recognition; Linguistics; Natural language processing; Artificial intelligence; Acoustics","score_opus":0.10400442122408006,"score_gpt":0.2957507449012484,"score_spread":0.19174632367716837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3086122814","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6658362,0.00004303411,0.33353072,0.00021737014,0.00007661507,0.00014990778,0.000038186998,0.00007661585,0.00003129687],"genre_scores_gemma":[0.9173579,0.000018223189,0.08224027,0.00012971571,0.00016213578,0.000008893848,0.000035881603,0.000008743216,0.00003819221],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99853534,0.000056354595,0.0003824676,0.00054292014,0.0002686404,0.00021426035],"domain_scores_gemma":[0.99899864,0.00042781903,0.00015309126,0.00015182955,0.0001546836,0.00011390875],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053548574,0.00015229918,0.00027852718,0.0005881599,0.00024778376,0.00050725025,0.00022172641,0.00010298088,0.000012958828],"category_scores_gemma":[0.00064943294,0.00015397687,0.00008771677,0.0020652867,0.000072611314,0.000582278,0.00023280346,0.00010147432,0.0000013905386],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021231372,0.00017661386,0.33989257,0.0002656485,0.0007704247,0.000006118243,0.025666205,0.00019222235,0.0077345488,0.0001932219,0.00022553097,0.62485564],"study_design_scores_gemma":[0.0013465434,0.0002108095,0.5406128,0.00003307946,0.0008676232,0.0000055443465,0.0044842623,0.41712874,0.031008653,0.0025542646,0.0008244265,0.0009232142],"about_ca_topic_score_codex":0.000092587674,"about_ca_topic_score_gemma":0.000076846176,"teacher_disagreement_score":0.6239324,"about_ca_system_score_codex":0.000040540028,"about_ca_system_score_gemma":0.000019778548,"threshold_uncertainty_score":0.62789947},"labels":[],"label_agreement":null},{"id":"W3088605365","doi":"10.1109/icassp39728.2021.9414722","title":"Siamese Capsule Network for End-to-End Speaker Recognition in the Wild","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Similarity (geometry); Feature (linguistics); End-to-end principle; Routing (electronic design automation); Adaptive routing; Pattern recognition (psychology); Speaker verification; Artificial intelligence; Speech recognition; Network model; Speaker recognition; Image (mathematics); Computer network; Routing protocol; Link-state routing protocol","score_opus":0.05773507453495559,"score_gpt":0.2757500919791833,"score_spread":0.21801501744422774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3088605365","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018902585,0.00021736285,0.9116427,0.013180888,0.0023452037,0.0019682508,0.00006271595,0.00024335789,0.051436972],"genre_scores_gemma":[0.14799929,0.00016457953,0.82909507,0.018092575,0.0012738232,0.0012518032,0.0003354091,0.000047155067,0.0017403021],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976176,0.00029150883,0.00042543173,0.00082885596,0.0003867002,0.00044988608],"domain_scores_gemma":[0.9981751,0.00047188794,0.00012431145,0.0009422343,0.0001816064,0.000104901475],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012938702,0.00027652565,0.00035147707,0.00016110828,0.000108917455,0.0007015401,0.0011995995,0.00023859109,0.000986641],"category_scores_gemma":[0.00026104244,0.00021207491,0.00026231655,0.00050249853,0.000026692172,0.00018604107,0.0005968864,0.00043022007,0.00019121551],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001121237,0.00017433448,0.000052178355,0.000062595995,0.000054871027,0.00006217716,0.0015797223,0.00022815916,0.00005468831,0.0016102237,0.039584603,0.9565252],"study_design_scores_gemma":[0.0044607804,0.0006417671,0.023118978,0.004203777,0.00039769875,0.00052471284,0.0069913995,0.261338,0.0231504,0.32803053,0.33960912,0.0075328415],"about_ca_topic_score_codex":0.00022634877,"about_ca_topic_score_gemma":0.0009830662,"teacher_disagreement_score":0.9489924,"about_ca_system_score_codex":0.00006934121,"about_ca_system_score_gemma":0.00017343664,"threshold_uncertainty_score":0.99992657},"labels":[],"label_agreement":null},{"id":"W3089020900","doi":"10.18280/ria.340201x","title":"Retraction: MFCC-Based Feature Extraction Model for Long Time Period Emotion Speech Using CNN","year":2020,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":true,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mel-frequency cepstrum; Period (music); Computer science; Speech recognition; Feature extraction; Feature (linguistics); Emotion recognition; Artificial intelligence; Pattern recognition (psychology); Acoustics; Linguistics","score_opus":0.09829718061852849,"score_gpt":0.3027681411727362,"score_spread":0.20447096055420771,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3089020900","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009272667,0.00005527615,0.9818483,0.0069127157,0.00041456462,0.00042424703,0.000008215127,0.00026562816,0.00079835986],"genre_scores_gemma":[0.63228446,0.000018188884,0.36312637,0.0011874744,0.00051931513,0.000035793037,0.00002874131,0.00004236102,0.0027572585],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983487,0.000061491446,0.00036488305,0.0006323187,0.00026634222,0.00032625132],"domain_scores_gemma":[0.9988191,0.00014451325,0.00018882322,0.00041378508,0.00025621298,0.00017754875],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003550371,0.00020823907,0.00023061087,0.00011936647,0.00032630228,0.0002681803,0.00043418005,0.00021976618,0.00030129412],"category_scores_gemma":[0.0002526529,0.00022365288,0.00021499631,0.00057754864,0.000040640854,0.00066609896,0.00004536412,0.00029066924,0.0005738377],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013775863,0.0003468307,0.00007436164,0.00019123079,0.000043152006,0.00006554314,0.0019475567,0.41115782,0.08415361,0.0009807056,0.004342359,0.49655908],"study_design_scores_gemma":[0.000052970634,0.00006664986,0.000012079574,0.000047602047,0.000018092374,0.00005420966,0.00011121753,0.84194267,0.15583374,0.00031414063,0.0013242431,0.00022240968],"about_ca_topic_score_codex":0.0000036025122,"about_ca_topic_score_gemma":0.0000022329848,"teacher_disagreement_score":0.6230118,"about_ca_system_score_codex":0.0001059911,"about_ca_system_score_gemma":0.00010418264,"threshold_uncertainty_score":0.91203},"labels":[],"label_agreement":null},{"id":"W3095018479","doi":"10.48550/arxiv.2010.14230","title":"A Comparison of Discrete Latent Variable Models for Speech Representation Learning","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Latent variable; Speech recognition; Representation (politics); Variable (mathematics); Word (group theory); Word error rate; Latent variable model; Artificial intelligence; Encoding (memory); Pattern recognition (psychology); Mathematics","score_opus":0.22747979670419097,"score_gpt":0.2623826478792052,"score_spread":0.03490285117501421,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3095018479","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023492528,0.000019463258,0.971479,0.00015016271,0.0002274287,0.00040584765,0.000019579335,0.00017479577,0.004031168],"genre_scores_gemma":[0.9242217,0.000039287777,0.07490078,0.000031597883,0.000036430327,0.0000026295859,0.000041794658,0.000014215487,0.0007115681],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984148,0.00014293067,0.00028558224,0.0008286576,0.000113794194,0.00021421936],"domain_scores_gemma":[0.9984774,0.0002364256,0.00040747778,0.00052631734,0.00023319737,0.000119188146],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020709158,0.00019820717,0.0004493201,0.00016983089,0.0001088314,0.00008391631,0.0008870127,0.00018488913,0.000032277178],"category_scores_gemma":[0.00010787411,0.00023251236,0.00024049495,0.0004433245,0.000042919797,0.0003310361,0.00080627005,0.00034595525,0.000018389304],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009459923,0.00011527126,0.0024734535,0.00020632894,0.00017157,0.00003194445,0.0006794715,0.8169259,0.00046889062,0.17328727,0.00036649077,0.005178799],"study_design_scores_gemma":[0.00031124926,0.000058500704,0.00009089055,0.00007319404,0.00007191963,0.000001060696,0.00013170524,0.88301295,0.003377043,0.112511635,0.0001467268,0.00021315116],"about_ca_topic_score_codex":0.00012016763,"about_ca_topic_score_gemma":0.0000065092268,"teacher_disagreement_score":0.9007292,"about_ca_system_score_codex":0.00007757515,"about_ca_system_score_gemma":0.000112375,"threshold_uncertainty_score":0.9481579},"labels":[],"label_agreement":null},{"id":"W3097523643","doi":"10.3390/app10217522","title":"Robust Deep Speaker Recognition: Learning Latent Representation with Joint Angular Margin Loss","year":2020,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Softmax function; Speaker recognition; Speech recognition; Artificial intelligence; Biometrics; TIMIT; Pattern recognition (psychology); Codebook; Machine learning; Convolutional neural network; Hidden Markov model","score_opus":0.10564192273135432,"score_gpt":0.23738835881611736,"score_spread":0.13174643608476305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3097523643","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.213821,0.000060923132,0.71788275,0.008519362,0.00016567671,0.00046404227,0.0000016886296,0.00055422593,0.05853032],"genre_scores_gemma":[0.8296731,0.000018456461,0.16875681,0.0013311267,0.00010786644,0.000033578435,0.0000054230177,0.000008214895,0.00006543181],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982393,0.00006882338,0.00021111818,0.00064050796,0.00055837695,0.00028191294],"domain_scores_gemma":[0.9993998,0.000083649866,0.00011752362,0.00016729746,0.00007259301,0.00015916709],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040862762,0.00013765744,0.00017052556,0.00009212114,0.0003655252,0.00036729893,0.00046141606,0.00004024891,0.00032516374],"category_scores_gemma":[0.000061678365,0.00010805017,0.00004844875,0.0010870319,0.00020676162,0.00044333097,0.000116149335,0.00014534083,0.00050829933],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009231982,0.00022593547,0.006850819,0.00005984329,0.00008864399,0.00029295814,0.007937954,0.014960989,0.013377083,0.015900189,0.0015419903,0.9386713],"study_design_scores_gemma":[0.003763789,0.0017288484,0.026110765,0.00021950276,0.00012048559,0.0004479056,0.010190612,0.60230446,0.3181684,0.022626294,0.011166787,0.0031521586],"about_ca_topic_score_codex":0.000011148798,"about_ca_topic_score_gemma":0.000008286309,"teacher_disagreement_score":0.9355191,"about_ca_system_score_codex":0.000018460521,"about_ca_system_score_gemma":0.000050936633,"threshold_uncertainty_score":0.65333295},"labels":[],"label_agreement":null},{"id":"W3108699229","doi":"10.1121/1.5147765","title":"Developing a cross-platform federated code repository for speech research","year":2020,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Documentation; Scripting language; Python (programming language); Code (set theory); World Wide Web; Point (geometry); Open research; Open science; Source code; Data science; Process (computing); Open source; Set (abstract data type); Programming language; Software","score_opus":0.1147673965792893,"score_gpt":0.3587112357129718,"score_spread":0.2439438391336825,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3108699229","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00884277,0.00007458212,0.96014106,0.030235102,0.00017557447,0.00016878809,0.000003698063,0.000018946861,0.00033945712],"genre_scores_gemma":[0.24871892,0.00012236199,0.7453502,0.005364896,0.000299753,0.0000027164265,1.6950752e-7,0.000013159123,0.00012786065],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99821824,0.00017546509,0.00047141247,0.00012457382,0.0007296021,0.00028069766],"domain_scores_gemma":[0.99667585,0.0017559006,0.00034755399,0.00022580232,0.00087416446,0.00012074486],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014990534,0.00009607045,0.0002524527,0.000016805872,0.00061303104,0.00014251024,0.00145087,0.000064813124,0.000013022472],"category_scores_gemma":[0.0010695424,0.00005141254,0.00033480933,0.0005480941,0.0004935409,0.00018008008,0.00032582873,0.00047695517,0.0000058819123],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010604325,0.00039649138,0.00032257926,0.00038444332,0.0010365469,0.000021785518,0.008928926,0.0014707542,0.2357355,0.00073264964,0.24477622,0.5051336],"study_design_scores_gemma":[0.00089787686,0.0006559376,0.00086969207,0.00017197177,0.000089637266,0.0003246393,0.00275643,0.8300222,0.1404111,0.006464841,0.01709253,0.0002431597],"about_ca_topic_score_codex":0.000012002848,"about_ca_topic_score_gemma":1.9232277e-7,"teacher_disagreement_score":0.8285514,"about_ca_system_score_codex":0.000090184134,"about_ca_system_score_gemma":0.00033964164,"threshold_uncertainty_score":0.4715001},"labels":[],"label_agreement":null},{"id":"W3110458199","doi":"10.48550/arxiv.2011.11588","title":"The Zero Resource Speech Benchmark 2021: Metrics and baselines for\\n unsupervised spoken language modeling","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Benchmark (surveying); Computer science; Zero (linguistics); Spoken language; Speech recognition; Language model; Resource (disambiguation); Natural language processing; Artificial intelligence; Linguistics; Computer network","score_opus":0.09401508568117196,"score_gpt":0.20319821575805327,"score_spread":0.10918313007688131,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3110458199","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09729272,0.00050182495,0.89772475,0.0010379809,0.00028436465,0.00047685427,0.000050548373,0.00016857176,0.0024623752],"genre_scores_gemma":[0.9703841,0.0010064015,0.026868328,0.0004224662,0.00019869338,0.0000034570744,0.000042640335,0.000030165686,0.001043735],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99808455,0.00017473448,0.0002423031,0.0010130127,0.00014513303,0.0003402873],"domain_scores_gemma":[0.9977116,0.00084834936,0.00014886908,0.0008798475,0.00019502988,0.00021631029],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006136731,0.00030026984,0.00032836595,0.00025178364,0.00038150192,0.00033974127,0.0015279938,0.00022549725,0.000023191838],"category_scores_gemma":[0.00045738806,0.0002740049,0.00023408676,0.0007839241,0.00007056836,0.0001924572,0.0013911875,0.00040526484,0.000022950931],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007145158,0.0004012883,0.0021631212,0.0009511531,0.0013460563,0.00236251,0.0046963207,0.12160628,0.000700151,0.17972907,0.016603056,0.66872644],"study_design_scores_gemma":[0.00035662958,0.000025753332,0.000021633608,0.00005024271,0.00008025152,0.0000048499,0.0004553568,0.9750056,0.00029334758,0.020276278,0.0030905097,0.00033950602],"about_ca_topic_score_codex":0.00010538649,"about_ca_topic_score_gemma":0.000034465404,"teacher_disagreement_score":0.8730914,"about_ca_system_score_codex":0.00007386131,"about_ca_system_score_gemma":0.000113315036,"threshold_uncertainty_score":0.9999712},"labels":[],"label_agreement":null},{"id":"W3111767470","doi":"10.1016/j.dib.2020.106652","title":"Audio recordings dataset of genuine and replayed speech at both ends of a telecommunication channel","year":2020,"lang":"en","type":"article","venue":"Data in Brief","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Channel (broadcasting); Telecommunications; Computer science; Speech recognition","score_opus":0.07590754986961774,"score_gpt":0.2846322564540964,"score_spread":0.20872470658447867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3111767470","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8223039,0.0017760264,0.086005114,0.02645185,0.00043263513,0.0014312778,0.056657217,0.00030187817,0.0046401327],"genre_scores_gemma":[0.7148703,0.0013830786,0.26711395,0.002520664,0.000070185044,0.000013341223,0.013959492,0.000022040556,0.000046962625],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.999022,0.00006894345,0.00032778777,0.00033298292,0.00014406921,0.00010423527],"domain_scores_gemma":[0.9982113,0.00014015344,0.00018376374,0.0013784386,0.000028064154,0.00005826715],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047901663,0.000073761534,0.00019581738,0.000069727,0.000025988626,0.00002140428,0.0012956675,0.00003798521,0.00006041167],"category_scores_gemma":[0.00037682615,0.00007525107,0.000013400896,0.00032479898,0.000050283303,0.00043207986,0.0014590886,0.00007401211,0.000008848897],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018921267,0.00030679288,0.0042662527,0.00026129346,0.00008072038,0.000041931922,0.0018937342,0.000002753977,0.03066147,0.0006988294,0.2460004,0.7155966],"study_design_scores_gemma":[0.0035839877,0.0006286836,0.0399211,0.00034450187,0.00006986675,0.00022226902,0.00026517024,0.22057074,0.2030649,0.0009811713,0.5293938,0.0009537943],"about_ca_topic_score_codex":0.00027345237,"about_ca_topic_score_gemma":0.0001029991,"teacher_disagreement_score":0.7146428,"about_ca_system_score_codex":0.000011856975,"about_ca_system_score_gemma":0.000020518364,"threshold_uncertainty_score":0.30686495},"labels":[],"label_agreement":null},{"id":"W3111804057","doi":"","title":"Towards End-to-End Speech Recognitionwith Recurrent Neural Networks","year":2014,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Trigram; Word error rate; Connectionism; Speech recognition; Lexicon; Language model; Artificial intelligence; Recurrent neural network; Artificial neural network; Word (group theory); Natural language processing; Linguistics","score_opus":0.02795731698678126,"score_gpt":0.25350137254277816,"score_spread":0.2255440555559969,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3111804057","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006707983,0.000015767557,0.85578537,0.0040299385,0.0012753279,0.00020852283,0.000003263494,0.00045936258,0.13151447],"genre_scores_gemma":[0.72798944,0.000022440227,0.2629745,0.0071252226,0.00053380313,0.000048590027,0.000014068604,0.000022027714,0.0012699302],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99822193,0.00015756335,0.00028521524,0.0005285832,0.0003841833,0.00042251375],"domain_scores_gemma":[0.9987752,0.00017527268,0.000065714696,0.00051021395,0.00016091132,0.00031272077],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005384948,0.00019925737,0.00021555967,0.00017678375,0.00013576294,0.0002894021,0.0006850728,0.00008041457,0.0017730097],"category_scores_gemma":[0.00017405665,0.00016491053,0.0001136517,0.00052514905,0.000031470612,0.00033204808,0.0002051098,0.00017869555,0.00081120897],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000051126967,0.00004480529,0.000057321697,0.000002654465,0.000008164838,0.0000061610303,0.000043181146,0.0000183132,0.000021679849,0.003742726,0.0053708516,0.990679],"study_design_scores_gemma":[0.00066296593,0.00040392572,0.0050967494,0.000059060912,0.000023245224,0.0001735829,0.000048653677,0.9125598,0.0086670555,0.0058238846,0.065618545,0.0008625352],"about_ca_topic_score_codex":0.000046181278,"about_ca_topic_score_gemma":0.00006299978,"teacher_disagreement_score":0.9898165,"about_ca_system_score_codex":0.000037195434,"about_ca_system_score_gemma":0.000028013215,"threshold_uncertainty_score":0.9999668},"labels":[],"label_agreement":null},{"id":"W3119746889","doi":"10.48550/arxiv.2101.03027","title":"User-friendly automatic transcription of low-resource languages: Plugging ESPnet into Elpis","year":2020,"lang":"en","type":"preprint","venue":"SOAS Research Online (SOAS University of London)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; User Friendly; Front and back ends; Transcription (linguistics); Graphical user interface; Interface (matter); CUDA; User interface; Set (abstract data type); Speech recognition; Natural language processing; World Wide Web; Human–computer interaction; Programming language; Operating system","score_opus":0.04480315530894974,"score_gpt":0.31716670997572166,"score_spread":0.2723635546667719,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3119746889","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6177703,0.0011640658,0.34991315,0.01970152,0.0003875821,0.0022203363,0.0008550517,0.0010323309,0.006955655],"genre_scores_gemma":[0.6859415,0.0012392416,0.3098659,0.00016628203,0.0002210178,0.000004266861,0.00051651994,0.00007217866,0.0019730672],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9953587,0.0009417914,0.0005099657,0.00093388656,0.0016805037,0.0005751356],"domain_scores_gemma":[0.9967834,0.00059857516,0.0003698663,0.001164591,0.00071951305,0.00036405647],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012456255,0.00033745787,0.0007896902,0.0011305104,0.00025820787,0.0001059304,0.003308619,0.00038042176,0.00038583323],"category_scores_gemma":[0.00046943908,0.00039276906,0.0004528171,0.0011353387,0.00051890826,0.0004104975,0.002296255,0.001427338,0.00008252778],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00081843394,0.0035467371,0.00077494496,0.017698606,0.0016522252,0.0018451435,0.0428435,0.0010186044,0.07238235,0.011902856,0.032445855,0.8130708],"study_design_scores_gemma":[0.010181173,0.0028032411,0.008615137,0.014438983,0.0005737264,0.00008108121,0.058232665,0.61851585,0.10531814,0.016151838,0.16084333,0.004244864],"about_ca_topic_score_codex":0.0013529775,"about_ca_topic_score_gemma":0.0006665481,"teacher_disagreement_score":0.8088259,"about_ca_system_score_codex":0.00025875977,"about_ca_system_score_gemma":0.000765352,"threshold_uncertainty_score":0.9998524},"labels":[],"label_agreement":null},{"id":"W3126967250","doi":"10.1109/sped53181.2021.9587406","title":"Synthetic Speech Detection Using Neural Networks","year":2021,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Artificial neural network; Speech recognition; Voice activity detection; Artificial intelligence; Speech processing","score_opus":0.031453642283931126,"score_gpt":0.2469382779964581,"score_spread":0.21548463571252696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3126967250","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11027621,0.00004521331,0.8821992,0.00025006873,0.00058117,0.0000344198,1.4111882e-7,0.00018043841,0.0064331153],"genre_scores_gemma":[0.9136204,0.000006241336,0.08536513,0.0005489718,0.00008147686,0.0000017583126,3.428422e-7,0.000005739071,0.00036993122],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992394,0.00007354858,0.000119253375,0.00025832406,0.00013374416,0.00017577062],"domain_scores_gemma":[0.999458,0.00007528934,0.000027372587,0.00029604087,0.00008030989,0.00006295361],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001127851,0.00007377643,0.00008577819,0.000048833408,0.00010120391,0.00017468116,0.0001750402,0.000047749076,0.00033123777],"category_scores_gemma":[0.00005580196,0.000068872265,0.00006677101,0.00036017533,0.000013097325,0.00022403162,0.00009018123,0.00007848272,0.000053122734],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000115785,0.000027009053,0.000060861574,0.0000021734197,0.000007712436,0.000101003636,0.000016589345,0.00058202125,0.0047656293,0.00068530464,0.000027948216,0.9937226],"study_design_scores_gemma":[0.00005589365,0.000006654202,0.0001735925,0.0000050497865,0.0000043868986,0.0004321595,0.0000197215,0.899025,0.09951149,0.00035375886,0.00032108277,0.00009120937],"about_ca_topic_score_codex":0.000019778674,"about_ca_topic_score_gemma":0.000035880264,"teacher_disagreement_score":0.99363136,"about_ca_system_score_codex":0.000025828384,"about_ca_system_score_gemma":0.000019412639,"threshold_uncertainty_score":0.3626821},"labels":[],"label_agreement":null},{"id":"W3127781879","doi":"10.48550/arxiv.2102.01640","title":"SPEAK WITH YOUR HANDS Using Continuous Hand Gestures to control Articulatory Speech Synthesizer","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Vocal tract; Gesture; Computer science; Speech recognition; Spline (mechanical); Kinematics; Speech production; Speech synthesis; Wrist; Acoustics; Artificial intelligence; Engineering; Anatomy","score_opus":0.06921805763573322,"score_gpt":0.19292652973471655,"score_spread":0.12370847209898334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3127781879","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6199,0.000044387434,0.37816116,0.00010421296,0.00024001555,0.000299857,0.000009789709,0.00014003148,0.0011005318],"genre_scores_gemma":[0.9844964,0.000015813428,0.013950679,0.0005065161,0.000111435904,0.000001860899,0.0000045067673,0.000032952208,0.00087980623],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974605,0.0002365305,0.0002508977,0.0013563171,0.00019031804,0.0005054414],"domain_scores_gemma":[0.9975585,0.00018691878,0.00023138452,0.0012336642,0.00041329474,0.00037625566],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00029292444,0.00044796095,0.00065054937,0.00035305932,0.00025341945,0.00066285,0.0010859139,0.00029756888,0.00012240422],"category_scores_gemma":[0.00011048365,0.00044586012,0.0002609558,0.0005720167,0.00014179345,0.00033151626,0.00073009206,0.00045213584,0.00008318232],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027176456,0.00415528,0.05628829,0.0012174363,0.00864489,0.10196889,0.010918756,0.6298407,0.04969944,0.045275122,0.0041380166,0.08513556],"study_design_scores_gemma":[0.008474844,0.00063265965,0.017431732,0.0028235773,0.0019435122,0.0010239222,0.0024529789,0.85605705,0.09502721,0.0051716743,0.003244213,0.0057166116],"about_ca_topic_score_codex":0.00016480363,"about_ca_topic_score_gemma":0.00013243126,"teacher_disagreement_score":0.36459643,"about_ca_system_score_codex":0.00020964214,"about_ca_system_score_gemma":0.00033862167,"threshold_uncertainty_score":0.9997993},"labels":[],"label_agreement":null},{"id":"W3129129429","doi":"10.1007/s12559-020-09803-8","title":"Sigma-Lognormal Modeling of Speech","year":2021,"lang":"en","type":"article","venue":"Cognitive Computation","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"Ministerio de Asuntos Económicos y Transformación Digital, Gobierno de España; Universidad de Las Palmas de Gran Canaria; Interreg; Natural Sciences and Engineering Research Council of Canada; European Commission; Fundación General CSIC; Ministerio de Educación y Formación Profesional; Ministerio de Ciencia, Innovación y Universidades","keywords":"Log-normal distribution; Sigma; Computer science; Speech recognition; Artificial intelligence; Mathematics; Statistics; Physics","score_opus":0.04439650461314287,"score_gpt":0.28271323511148716,"score_spread":0.2383167304983443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3129129429","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.053734805,0.0001331027,0.9325743,0.0001743055,0.00019729658,0.000078716716,0.0000057120988,0.00008534959,0.013016445],"genre_scores_gemma":[0.9322474,0.000019810035,0.06735999,0.00022974625,0.000051316125,0.0000051812885,0.00002775559,0.0000063874286,0.000052380616],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99894446,0.000117374075,0.00024986014,0.0002883934,0.00025098954,0.00014892552],"domain_scores_gemma":[0.9985323,0.0002807511,0.0000876075,0.00006590678,0.00097624323,0.00005717996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018382438,0.000095608055,0.00015592786,0.0001148442,0.00007158395,0.000066359615,0.00011068324,0.000048540856,0.00006299059],"category_scores_gemma":[0.0003056855,0.000104311504,0.00008030042,0.0004434215,0.000028827279,0.00034319542,0.000107106345,0.00007898625,0.00003759609],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005908768,0.000061004328,0.00009714793,0.000015326883,0.000021835835,0.000049735285,0.00014656855,0.00089850585,0.00068691466,0.0006163093,0.000028361592,0.9973724],"study_design_scores_gemma":[0.00035708095,0.000028571598,0.00039011738,0.00007051029,0.000013030428,0.000053713593,0.00018667149,0.9466954,0.04734313,0.0047154706,0.000021277536,0.00012502118],"about_ca_topic_score_codex":0.000004732362,"about_ca_topic_score_gemma":0.0000035373964,"teacher_disagreement_score":0.99724734,"about_ca_system_score_codex":0.000014395609,"about_ca_system_score_gemma":0.00010975627,"threshold_uncertainty_score":0.42536995},"labels":[],"label_agreement":null},{"id":"W3131901777","doi":"10.71781/10868","title":"Advances in deep learning methods for speech recognition and understanding","year":2020,"lang":"en","type":"dissertation","venue":"Papyrus : Institutional Repository (Université de Montréal)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Samsung; Compute Canada","keywords":"Speech recognition; Deep learning; Computer science; Artificial intelligence","score_opus":0.02693497538385669,"score_gpt":0.24286779352638627,"score_spread":0.21593281814252957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3131901777","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01737462,0.033790685,0.8482031,0.000548724,0.0016625674,0.0010567365,0.00001993907,0.00042497428,0.09691861],"genre_scores_gemma":[0.09244486,0.012072967,0.88620603,0.00027177297,0.00026212996,0.00016097429,0.0008840359,0.0000791464,0.0076180818],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99845326,0.00018633323,0.00027308273,0.00058623776,0.00024203619,0.0002590434],"domain_scores_gemma":[0.99894655,0.00038788983,0.0002515293,0.00013584466,0.000114162576,0.00016400323],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0003013888,0.00024961663,0.0003155492,0.00036926937,0.002051938,0.00010981983,0.00028852766,0.00025165398,0.0000118015105],"category_scores_gemma":[0.00021198849,0.00029730986,0.00014121295,0.00034013242,0.000051787512,0.000771205,0.00007741761,0.00032172547,0.000011078164],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024915533,0.000035921523,0.00018670454,0.00017851393,0.00004806539,0.0002761437,0.009643384,0.000037199137,0.002286144,0.009292719,0.000016597949,0.97774947],"study_design_scores_gemma":[0.0069185537,0.0008631307,0.0044512143,0.0023476197,0.0006811785,0.0020977994,0.19205536,0.30553228,0.11629573,0.15577878,0.20874546,0.004232903],"about_ca_topic_score_codex":0.00046420217,"about_ca_topic_score_gemma":0.0017100344,"teacher_disagreement_score":0.9735165,"about_ca_system_score_codex":0.0020126635,"about_ca_system_score_gemma":0.00030275297,"threshold_uncertainty_score":0.9999479},"labels":[],"label_agreement":null},{"id":"W3135041399","doi":"10.1044/2020_jslhr-20-00268","title":"Performance of Forced-Alignment Algorithms on Children's Speech","year":2021,"lang":"en","type":"article","venue":"Journal of Speech Language and Hearing Research","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute on Deafness and Other Communication Disorders","keywords":"Sample (material); Segmentation; Two-alternative forced choice; Speech processing; Phonetics; Electroglottograph; Speech segmentation; Workflow; Interval (graph theory)","score_opus":0.0544063089136956,"score_gpt":0.3407107227794535,"score_spread":0.28630441386575795,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3135041399","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99504375,0.00057590206,0.00057821785,0.0008290897,0.00009960598,0.00007675069,0.0000023813323,0.000010425945,0.002783848],"genre_scores_gemma":[0.94746655,0.00072231505,0.050522055,0.00009613529,0.00029286652,0.0000012150646,0.0000010894096,0.000010691515,0.0008871081],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.997912,0.000129668,0.00035356364,0.00020295935,0.0010599166,0.00034189803],"domain_scores_gemma":[0.99871594,0.00023841261,0.00011800776,0.0003070771,0.00046020653,0.00016037925],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018495731,0.00009557512,0.00025379704,0.00036483412,0.00013729963,0.00013028306,0.00039536477,0.000065178785,0.0001212765],"category_scores_gemma":[0.00021651585,0.00007739411,0.00009304851,0.00043757365,0.00006245284,0.0002564121,0.0002446745,0.00047746982,0.000015879239],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034347853,0.00014689146,0.0036145174,0.00004421206,0.000057093843,0.00075251627,0.0010932103,0.0000056199224,0.016096942,0.00039409375,0.00042800547,0.97733253],"study_design_scores_gemma":[0.00080489035,0.0008190256,0.035804704,0.00045543775,0.000010183742,0.0020970467,0.0009849902,0.0019901628,0.9562298,0.00029269338,0.00035200754,0.00015903346],"about_ca_topic_score_codex":0.00003890192,"about_ca_topic_score_gemma":0.0000031502925,"teacher_disagreement_score":0.9771735,"about_ca_system_score_codex":0.000055058892,"about_ca_system_score_gemma":0.0001447171,"threshold_uncertainty_score":0.315604},"labels":[],"label_agreement":null},{"id":"W3135815897","doi":"10.1109/iscslp49672.2021.9362084","title":"Age-Invariant Speaker Embedding for Diarization of Cognitive Assessments","year":2021,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Speaker diarisation; Utterance; Computer science; Speech recognition; Embedding; Invariant (physics); Cognition; Adversarial system; Training set; Speaker recognition; Artificial intelligence; Psychology; Mathematics","score_opus":0.04708542641867467,"score_gpt":0.3360434326566122,"score_spread":0.2889580062379375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3135815897","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0050685876,0.000007780453,0.9677229,0.00017234671,0.00018164069,0.00012097471,0.000008489488,0.00004615596,0.026671108],"genre_scores_gemma":[0.5929077,0.000008297352,0.4047882,0.0004685138,0.000031717074,0.000021809188,0.000029021883,0.000006131565,0.0017385851],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993155,0.00004806729,0.00016481346,0.0002103708,0.00014653949,0.000114724084],"domain_scores_gemma":[0.99908686,0.00041348315,0.0000629135,0.00013295453,0.00026358815,0.00004022088],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016296197,0.00006181224,0.00011564009,0.000052834526,0.00004571677,0.00008157534,0.00012427452,0.000034916367,0.0002441364],"category_scores_gemma":[0.0003385183,0.000057557507,0.00006333508,0.00021943107,0.000013180745,0.00023812099,0.00006608989,0.000027212009,0.000018503857],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026208969,0.0007179904,0.0010496264,0.00008399655,0.00023535572,0.00014098246,0.0010086842,0.000016952039,0.024721589,0.24654303,0.0015294835,0.7239261],"study_design_scores_gemma":[0.0015157394,0.000114215414,0.0059756464,0.00020051128,0.000057163546,0.00003155782,0.0007835165,0.23945278,0.73522776,0.01505895,0.0012185173,0.00036361843],"about_ca_topic_score_codex":0.0000040883283,"about_ca_topic_score_gemma":0.000008809376,"teacher_disagreement_score":0.7235625,"about_ca_system_score_codex":0.000012316505,"about_ca_system_score_gemma":0.00007379932,"threshold_uncertainty_score":0.26731226},"labels":[],"label_agreement":null},{"id":"W3135892461","doi":"10.47839/ijc.6.3.445","title":"A ROBUST SPEECH RECOGNITION SYSTEM USING A GENERAL REGRESSION NEURAL NETWORK","year":2014,"lang":"en","type":"article","venue":"International Journal of Computing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Speech recognition; Artificial neural network; Robustness (evolution); Hidden Markov model; Artificial intelligence; Multilayer perceptron; Pattern recognition (psychology); Noise (video); Time delay neural network; Word recognition","score_opus":0.06130865123230914,"score_gpt":0.2828049857427917,"score_spread":0.2214963345104826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3135892461","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44554132,0.00003061214,0.55002946,0.0002748383,0.0031407156,0.000033312008,5.970748e-7,0.000047361194,0.00090177805],"genre_scores_gemma":[0.6340814,0.0000027473052,0.36334515,0.00023724127,0.0023148635,1.7905322e-7,0.000001225799,0.000007819408,0.000009348079],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99805546,0.00024817896,0.00062312913,0.00018068326,0.0006803725,0.00021220681],"domain_scores_gemma":[0.9979358,0.00023839006,0.0007764716,0.00013264711,0.00081241375,0.00010428783],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001132748,0.00013275181,0.00022870993,0.00024359215,0.00012383018,0.00031362617,0.00083986984,0.000059054237,0.000016356682],"category_scores_gemma":[0.00016609959,0.00011179026,0.00017701388,0.00019496567,0.000019123787,0.00052583485,0.0001729283,0.00021875618,0.000016523914],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031639156,0.000042034233,0.0007176582,0.000010782509,0.000081928716,0.00019624652,0.00012926341,0.026854528,0.001057907,0.0010461372,0.00053009647,0.96930176],"study_design_scores_gemma":[0.00048056428,0.000050335188,0.0008586464,0.00066426577,0.00001343484,0.003655119,0.000036054218,0.99069995,0.002244907,0.0007916425,0.0003669849,0.00013809055],"about_ca_topic_score_codex":0.000011939279,"about_ca_topic_score_gemma":0.00000114369,"teacher_disagreement_score":0.9691637,"about_ca_system_score_codex":0.00014932478,"about_ca_system_score_gemma":0.000051630206,"threshold_uncertainty_score":0.45586744},"labels":[],"label_agreement":null},{"id":"W3139133216","doi":"10.1002/trc2.12147","title":"Multilingual automation of transcript preprocessing in Alzheimer's disease detection","year":2021,"lang":"en","type":"article","venue":"Alzheimer s & Dementia Translational Research & Clinical Interventions","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Preprocessor; Computer science; Pipeline (software); Natural language processing; Normalization (sociology); Scalability; Task (project management); Context (archaeology); Data pre-processing; Information extraction; Artificial intelligence; Machine learning; Programming language; Biology; Database","score_opus":0.34858535451689876,"score_gpt":0.4959002253631045,"score_spread":0.14731487084620576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3139133216","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15016654,0.05487495,0.7833081,0.006149623,0.0012464023,0.0013087359,0.000101000674,0.00026847905,0.0025761747],"genre_scores_gemma":[0.96903706,0.00014175316,0.030507427,0.00005831379,0.00006798637,0.00009774279,0.000054779513,0.000014695192,0.000020235335],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9949125,0.0013522251,0.0015738134,0.0007208525,0.0010397856,0.0004008166],"domain_scores_gemma":[0.9967436,0.001312345,0.00018311187,0.00049412996,0.0010059789,0.00026080245],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037019716,0.00016077828,0.00029807258,0.0004716532,0.00023328951,0.00016555385,0.0005460578,0.0001332405,0.0007293851],"category_scores_gemma":[0.00097532984,0.00017597154,0.000696241,0.0011833131,0.00023603629,0.0008818306,0.00009817583,0.0005233268,0.000074540505],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008876327,0.002077218,0.0069876965,0.00005618907,0.0016884756,0.00004276551,0.00029735419,0.00010639984,0.0014841692,0.0034161874,0.000069725815,0.9836851],"study_design_scores_gemma":[0.004582898,0.00041473916,0.5449957,0.0016969292,0.0027454041,0.000024149584,0.00038262413,0.25350276,0.13340847,0.054284625,0.003091309,0.0008703987],"about_ca_topic_score_codex":0.000046989462,"about_ca_topic_score_gemma":0.0005625135,"teacher_disagreement_score":0.98281467,"about_ca_system_score_codex":0.000013478606,"about_ca_system_score_gemma":0.00040557346,"threshold_uncertainty_score":0.7986255},"labels":[],"label_agreement":null},{"id":"W3143367551","doi":"10.21437/interspeech.2021-941","title":"ECAPA-TDNN Embeddings for Speaker Diarization","year":2021,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":92,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Speaker diarisation; Computer science; Speaker recognition; Robustness (evolution); Speech recognition; Artificial neural network; Discriminative model; Artificial intelligence; Time delay neural network; Pattern recognition (psychology)","score_opus":0.01856822171074096,"score_gpt":0.2489785712134402,"score_spread":0.23041034950269923,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3143367551","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017842964,0.00001670563,0.9361389,0.0017542868,0.00024908755,0.00006678385,0.0000016395222,0.0001323568,0.059855934],"genre_scores_gemma":[0.099640235,0.000018978044,0.87401664,0.003927133,0.00013779048,0.000031124768,0.000017439745,0.000011422687,0.022199253],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994611,0.000016919681,0.000097643075,0.00020674069,0.00009836752,0.00011918785],"domain_scores_gemma":[0.9995005,0.00010575605,0.000022820295,0.00018906847,0.00013501098,0.000046850873],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000076628465,0.00005258124,0.000068027366,0.000035491503,0.00005852559,0.00014309162,0.00015356351,0.000032456133,0.0005129673],"category_scores_gemma":[0.00014149543,0.0000481044,0.000057226916,0.00019148826,0.000007426982,0.00024508047,0.000048702797,0.000022204973,0.00017224],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000281791,0.00009134694,0.00014516232,0.000014927338,0.000021757445,0.000015212682,0.00030376663,0.0000036172084,0.013452439,0.38156843,0.02094325,0.58343726],"study_design_scores_gemma":[0.0005593571,0.00003214106,0.0017199994,0.000019616418,0.000012355296,0.000047114398,0.00012891201,0.14898962,0.60840124,0.033405323,0.20634331,0.000341011],"about_ca_topic_score_codex":0.0000020195284,"about_ca_topic_score_gemma":0.000005972178,"teacher_disagreement_score":0.5949488,"about_ca_system_score_codex":0.000012087233,"about_ca_system_score_gemma":0.000036439647,"threshold_uncertainty_score":0.5616632},"labels":[],"label_agreement":null},{"id":"W3147246185","doi":"10.21203/rs.3.rs-16425/v1","title":"WITHDRAWN: A robust speaker recognition based on Data augmentation","year":2020,"lang":"en","type":"preprint","venue":"Research Square","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"National Natural Science Foundation of China; Fundamental Research Funds for the Central Universities; National Science Foundation","keywords":"Computer science; Speech recognition; Artificial intelligence","score_opus":0.4058160311411746,"score_gpt":0.42449921906336013,"score_spread":0.01868318792218554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3147246185","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031628187,0.00016471297,0.90047944,0.037757196,0.0013247174,0.003825898,0.00169531,0.0011726164,0.050417278],"genre_scores_gemma":[0.45426118,0.0004376937,0.5230215,0.0039148033,0.0020903149,0.0010435791,0.014154168,0.00020707662,0.000869651],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99395883,0.0011592546,0.00038912735,0.0017145012,0.002221863,0.0005564078],"domain_scores_gemma":[0.9953662,0.0008071874,0.00015086615,0.0026923183,0.0006415148,0.00034190115],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0022745784,0.0003028596,0.0003243728,0.0006657159,0.0002906227,0.0011115657,0.0029215408,0.00028494824,0.00084238907],"category_scores_gemma":[0.0013954393,0.00029541334,0.00012594114,0.00090520515,0.00010195788,0.00047041234,0.0027667396,0.0015383001,0.002449577],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027441073,0.0007542114,0.00019441075,0.0012386525,0.00011155606,0.00047784453,0.0005768401,0.0008773315,0.00026392183,0.00073652243,0.084410615,0.9100837],"study_design_scores_gemma":[0.0008549321,0.0003654304,0.0019061998,0.0016795787,0.000021463899,0.000007320594,0.00021279258,0.9744899,0.0028113967,0.009452907,0.0075708157,0.0006272446],"about_ca_topic_score_codex":0.0001262001,"about_ca_topic_score_gemma":0.000053883992,"teacher_disagreement_score":0.9736126,"about_ca_system_score_codex":0.0002698764,"about_ca_system_score_gemma":0.0007662986,"threshold_uncertainty_score":0.9999498},"labels":[],"label_agreement":null},{"id":"W3149444771","doi":"10.18280/ts.380124","title":"Classification of Pitch and Gender of Speakers for Forensic Speaker Recognition from Disguised Voices Using Novel Features Learned by Deep Convolutional Neural Networks","year":2021,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Spectrogram; Mel-frequency cepstrum; Speech recognition; Convolutional neural network; Computer science; Pattern recognition (psychology); Support vector machine; Artificial intelligence; Classifier (UML); Feature extraction; Artificial neural network","score_opus":0.08201919839413377,"score_gpt":0.27523834011215603,"score_spread":0.19321914171802226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3149444771","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36134824,0.0002653432,0.6376602,0.00020581104,0.00012355833,0.00018389866,0.00011614728,0.000019266829,0.00007749253],"genre_scores_gemma":[0.91857237,0.000017510085,0.08085836,0.00014744418,0.000093200506,0.000013386867,0.00027870192,0.000009517952,0.00000950933],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987773,0.000070587965,0.00036160648,0.00034633325,0.00026772707,0.00017646799],"domain_scores_gemma":[0.99896955,0.0003031585,0.00024644483,0.00013349309,0.00028264854,0.00006472172],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019635439,0.0001341282,0.00021235946,0.00006290888,0.000081103775,0.000059204212,0.00013691578,0.000076619646,0.00014939747],"category_scores_gemma":[0.000045110894,0.0001331859,0.00010097109,0.00016274727,0.00008821186,0.00024252813,0.00003906568,0.00006863343,5.569895e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038632294,0.0007671088,0.005238331,0.00014535159,0.00046706467,0.0000041754815,0.0013706614,0.00133751,0.6479244,0.0029450417,0.0011614563,0.33825254],"study_design_scores_gemma":[0.0017053488,0.00006884849,0.053279832,0.000041919942,0.00009924594,0.000011009926,0.0003188297,0.9094834,0.03202733,0.0026471592,0.00010190468,0.00021521257],"about_ca_topic_score_codex":0.00003120805,"about_ca_topic_score_gemma":0.000033522763,"teacher_disagreement_score":0.90814584,"about_ca_system_score_codex":0.000031932672,"about_ca_system_score_gemma":0.00004145297,"threshold_uncertainty_score":0.54311633},"labels":[],"label_agreement":null},{"id":"W3157651102","doi":"10.3389/fnagi.2021.635945","title":"Comparing Pre-trained and Feature-Based Models for Prediction of Alzheimer's Disease Based on Speech","year":2021,"lang":"en","type":"article","venue":"Frontiers in Aging Neuroscience","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":92,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Computer science; Artificial intelligence; Transfer of learning; Speech recognition; Natural language processing; Encoder; Set (abstract data type); Feature (linguistics); Speech processing; Machine learning","score_opus":0.04272635931665986,"score_gpt":0.2557115942008928,"score_spread":0.21298523488423293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3157651102","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012497081,0.00012660335,0.9847974,0.001087569,0.0009097763,0.00025761366,0.000035670353,0.00008072654,0.00020756281],"genre_scores_gemma":[0.79711115,0.000007150084,0.20188881,0.000913046,0.000014688194,0.000025310685,0.000005188155,0.000007498176,0.000027157712],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998561,0.000089771835,0.00018945853,0.0005799252,0.00033439347,0.00024540682],"domain_scores_gemma":[0.99923366,0.00010928178,0.00008578843,0.0003646808,0.00007206933,0.0001345043],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032210205,0.0001268436,0.00019758422,0.00025631906,0.00011576144,0.00011914027,0.00034565825,0.000032762484,7.7063254e-7],"category_scores_gemma":[0.0002471145,0.0001305292,0.00006440299,0.00055243884,0.00011387033,0.00034197318,0.000056301153,0.000100455254,1.2648398e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00066174695,0.0022245457,0.27659374,0.0006519326,0.000035477853,0.00046110636,0.0010301585,0.33885252,0.046094164,0.006244122,0.0114097595,0.31574073],"study_design_scores_gemma":[0.0005516378,0.000041713734,0.038564365,0.000105647756,0.000011593277,0.000002210756,0.000009055399,0.93865156,0.020481141,0.0013658059,0.00011096809,0.00010432151],"about_ca_topic_score_codex":0.0000029266146,"about_ca_topic_score_gemma":0.0000013297672,"teacher_disagreement_score":0.7846141,"about_ca_system_score_codex":0.0000272314,"about_ca_system_score_gemma":0.00016069159,"threshold_uncertainty_score":0.5322826},"labels":[],"label_agreement":null},{"id":"W3160325739","doi":"10.1109/icassp39728.2021.9414670","title":"A Capsule Network Based Approach for Detection of Audio Spoofing Attacks","year":2021,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":80,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Spoofing attack; Computer science; Replay attack; Convolutional neural network; Generalization; Artificial intelligence; Speech recognition; Computer security; Authentication (law)","score_opus":0.030080943366938517,"score_gpt":0.23999549081306323,"score_spread":0.20991454744612473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3160325739","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028770284,0.000035271984,0.98636127,0.00012768795,0.00014764165,0.000101410595,0.0000012368795,0.000077169454,0.010271306],"genre_scores_gemma":[0.41640764,0.000001380467,0.5828354,0.00027961785,0.000057098674,0.000023578226,0.0000029122555,0.0000040882846,0.00038833363],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99933636,0.00004143566,0.00014408045,0.00021696794,0.000111710106,0.00014946311],"domain_scores_gemma":[0.99944603,0.00009914585,0.000049726656,0.00023277344,0.00013302015,0.000039281767],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023754257,0.000060619055,0.000117404175,0.000036589343,0.000068922156,0.000042345328,0.00015027846,0.00004358188,0.000057883924],"category_scores_gemma":[0.00007406889,0.000056771794,0.00009773676,0.00031705297,0.000010902542,0.00009652915,0.000034973502,0.000034905468,0.0000059379427],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019882675,0.0002646632,0.00020683941,0.00012678989,0.000061637926,0.000008120161,0.00012088567,0.0032478906,0.08100697,0.007428183,0.0026769517,0.9048312],"study_design_scores_gemma":[0.00021892635,0.000020656418,0.0002274472,0.000008570958,0.0000058746414,0.0000065659196,0.000023117567,0.5258175,0.47181225,0.0003882901,0.0013957238,0.00007506745],"about_ca_topic_score_codex":0.0000075195094,"about_ca_topic_score_gemma":0.000010348802,"teacher_disagreement_score":0.9047561,"about_ca_system_score_codex":0.000015391939,"about_ca_system_score_gemma":0.00005595844,"threshold_uncertainty_score":0.23150866},"labels":[],"label_agreement":null},{"id":"W3161411634","doi":"10.1109/icassp39728.2021.9413680","title":"A Comparison of Discrete Latent Variable Models for Speech Representation Learning","year":2021,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Latent variable; Speech recognition; Artificial intelligence; Representation (politics); Encoding (memory); Word error rate; Variable (mathematics); Latent variable model; Word (group theory); Pattern recognition (psychology); Mathematics","score_opus":0.09678490460931576,"score_gpt":0.3466243956047883,"score_spread":0.24983949099547254,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3161411634","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0048470157,0.000029260724,0.974301,0.0003577638,0.00009313137,0.000097985765,0.0000014672859,0.00006978039,0.020202637],"genre_scores_gemma":[0.39546,0.000006312659,0.6019814,0.0000570099,0.00001382863,0.000012567709,0.000009404983,0.0000040574364,0.0024553814],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992178,0.000056745706,0.00021800814,0.00022513265,0.00016323263,0.00011906371],"domain_scores_gemma":[0.9992723,0.00020024185,0.00007816933,0.00020706996,0.0002042832,0.000037956852],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017372704,0.000053488795,0.00016004301,0.000042548876,0.000059590293,0.00006775785,0.00015549724,0.000033527984,0.000118832555],"category_scores_gemma":[0.00012486697,0.000051388382,0.0000667477,0.000243288,0.000009267276,0.00027859028,0.000076546836,0.000049392478,0.000009789179],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035129593,0.0003688643,0.0048897415,0.00010013297,0.0001186555,0.000011204739,0.0016600165,0.030174665,0.040344033,0.39096883,0.0025873687,0.52874136],"study_design_scores_gemma":[0.00016908256,0.000025032534,0.00011538809,0.000012916545,0.0000066888847,0.0000046720925,0.00015510891,0.778223,0.20492032,0.015824959,0.00048152803,0.000061337145],"about_ca_topic_score_codex":0.000029885512,"about_ca_topic_score_gemma":0.000006146691,"teacher_disagreement_score":0.7480483,"about_ca_system_score_codex":0.000011526089,"about_ca_system_score_gemma":0.000041779822,"threshold_uncertainty_score":0.20955575},"labels":[],"label_agreement":null},{"id":"W3162773681","doi":"10.18280/ts.380232","title":"HMM Based Language Identification from Speech Utterances of Popular Indic Languages Using Spectral and Prosodic Features","year":2021,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Hidden Markov model; Utterance; Computer science; Speech recognition; Mel-frequency cepstrum; Feature (linguistics); Artificial intelligence; Identification (biology); Natural language processing; Feature extraction; Linguistics","score_opus":0.01633622496964346,"score_gpt":0.25978347560542053,"score_spread":0.24344725063577707,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3162773681","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96341056,0.00074362743,0.035074055,0.00031533197,0.00007690314,0.0001232385,0.000046270452,0.00004977171,0.00016023406],"genre_scores_gemma":[0.9496955,0.00000795427,0.04991759,0.00021110056,0.00007913988,0.0000052297073,0.00003253344,0.0000061236638,0.000044779597],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99892324,0.00010015407,0.00022937219,0.00029786635,0.00030645795,0.0001429209],"domain_scores_gemma":[0.9995442,0.00004770527,0.0001168829,0.00019005325,0.00005032316,0.00005081538],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018199926,0.00010782875,0.00015684367,0.00009889538,0.00006716328,0.00014969264,0.00019791747,0.00004194483,0.00037025264],"category_scores_gemma":[0.000024138053,0.00010148322,0.000057496956,0.00020374026,0.000038566406,0.0002189571,0.0000351386,0.00006778688,0.0000052104983],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014871095,0.00016909272,0.006543743,0.000057934187,0.000051925927,0.00018860557,0.0020398477,0.00002009391,0.8273332,0.0005320164,0.00008721613,0.16296147],"study_design_scores_gemma":[0.00051055336,0.000029822633,0.079517566,0.00008838199,0.000033826385,0.000025323254,0.00075219263,0.008271513,0.9101613,0.0004034174,0.00003671636,0.00016939215],"about_ca_topic_score_codex":0.00009993357,"about_ca_topic_score_gemma":0.000052796946,"teacher_disagreement_score":0.16279207,"about_ca_system_score_codex":0.000019496947,"about_ca_system_score_gemma":0.000046367244,"threshold_uncertainty_score":0.41383657},"labels":[],"label_agreement":null},{"id":"W3162841994","doi":"10.18653/v1/2021.findings-acl.312","title":"Learning Robust Latent Representations for Controllable Speech Synthesis","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vanguard College","funders":"","keywords":"Computer science; Transformer; Speech recognition; Latent variable; Artificial intelligence; Encoder; Probabilistic latent semantic analysis; Mutual information; Pattern recognition (psychology)","score_opus":0.058973699644019335,"score_gpt":0.28078634362666927,"score_spread":0.22181264398264994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3162841994","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0041187294,0.00016578821,0.9546327,0.004031605,0.001071809,0.0008433282,0.000018834247,0.0006388694,0.03447833],"genre_scores_gemma":[0.07087207,0.00021832662,0.9103381,0.0004756908,0.00022009111,0.0009794009,0.00006693334,0.00004329049,0.0167861],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99753344,0.00022026034,0.00047547382,0.0010114632,0.00036935855,0.0003899825],"domain_scores_gemma":[0.9967094,0.0014223834,0.0002382668,0.00092786574,0.00055528485,0.0001468047],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00062552496,0.00028697526,0.0005379784,0.00021561238,0.00026164955,0.0011220297,0.0009049176,0.00027354175,0.0009713783],"category_scores_gemma":[0.0015801933,0.00027877607,0.00046078494,0.00024746038,0.000029848881,0.00024666687,0.00086428045,0.00039792003,0.00009923424],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048670616,0.0006137789,0.0012855419,0.0005135544,0.0011662871,0.00022547241,0.0010522146,0.034199204,0.002103881,0.010594641,0.019776711,0.92842007],"study_design_scores_gemma":[0.0008537098,0.00006291829,0.0006749979,0.00039879308,0.00022967461,0.00007011992,0.00092338637,0.9032774,0.07968661,0.004925396,0.007685137,0.0012118318],"about_ca_topic_score_codex":0.00018520701,"about_ca_topic_score_gemma":0.000073267875,"teacher_disagreement_score":0.9272082,"about_ca_system_score_codex":0.000087754495,"about_ca_system_score_gemma":0.0002695514,"threshold_uncertainty_score":0.99996644},"labels":[],"label_agreement":null},{"id":"W3163865502","doi":"10.1109/icassp39728.2021.9413952","title":"Multi-Dialect Speech Recognition in English Using Attention on Ensemble of Experts","year":2021,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Task (project management); Word error rate; Artificial intelligence; Speech recognition; Ensemble forecasting; Baseline (sea); Variety (cybernetics); Ensemble learning; Language model; Word (group theory); Natural language processing; Training set; Machine learning; Linguistics","score_opus":0.085878234083952,"score_gpt":0.28859020752999937,"score_spread":0.20271197344604736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3163865502","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9056378,0.000019607343,0.08645443,0.00006593772,0.00042953817,0.00009939988,0.0000018438919,0.0000890441,0.007202428],"genre_scores_gemma":[0.68563277,0.000021328146,0.31386173,0.00021420284,0.00004570009,0.000005806226,0.0000072786866,0.0000067531523,0.00020443178],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99901485,0.00013298815,0.00024398002,0.00025602157,0.00019542353,0.0001567206],"domain_scores_gemma":[0.9992997,0.00011971821,0.00006380057,0.00023431682,0.0002406172,0.000041852145],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021435691,0.000088227716,0.00014807329,0.00018599357,0.00003287515,0.000053298278,0.00013026668,0.00006776572,0.00021766576],"category_scores_gemma":[0.00019227604,0.00008925637,0.00007729358,0.00045513114,0.000012531654,0.00030596787,0.000048049755,0.000058839196,0.000036203073],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012210735,0.0005408621,0.0014912434,0.000018758088,0.000012779375,0.00008720148,0.0008126532,0.000008761683,0.26613796,0.00014228877,0.00017958936,0.7305557],"study_design_scores_gemma":[0.0007367634,0.000043647407,0.0037082871,0.00016476825,0.000004981941,0.000030867366,0.0006274857,0.04924039,0.94467896,0.0004371874,0.00012499931,0.00020166408],"about_ca_topic_score_codex":0.000092435876,"about_ca_topic_score_gemma":0.00027308025,"teacher_disagreement_score":0.730354,"about_ca_system_score_codex":0.00004910092,"about_ca_system_score_gemma":0.000052052626,"threshold_uncertainty_score":0.36397693},"labels":[],"label_agreement":null},{"id":"W3165143153","doi":"10.31234/osf.io/bm2uq","title":"How do voices become familiar? Speech intelligibility and voice recognition are differentially sensitive to voice training","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Intelligibility (philosophy); Psychology; Speech recognition; Computer science","score_opus":0.09017087775657101,"score_gpt":0.28423595413564184,"score_spread":0.19406507637907083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3165143153","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31029668,0.000054860076,0.6571661,0.020931698,0.0016123562,0.0014734808,0.00031581646,0.0010691975,0.0070797754],"genre_scores_gemma":[0.7959566,0.00017227429,0.1994174,0.0032502105,0.00046885925,0.0000901404,0.00008446447,0.000053522675,0.0005065403],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.995282,0.00047064916,0.0006247365,0.0023273134,0.0007194483,0.00057583913],"domain_scores_gemma":[0.99648196,0.00088145083,0.0004348008,0.0009547173,0.0006238782,0.0006232067],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007124733,0.000725729,0.0010049389,0.00039172077,0.00020836241,0.0022127926,0.0010807298,0.000480332,0.000051245865],"category_scores_gemma":[0.0012048042,0.00069496845,0.00030976295,0.00048141097,0.000112630405,0.0005701766,0.0022616656,0.0009974686,0.0003679468],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054109052,0.000115300725,0.00021778561,0.0003113208,0.00019132484,0.00013880678,0.0047998116,0.0000025542518,0.0012678016,0.00017010457,0.0006424168,0.9920887],"study_design_scores_gemma":[0.0046102614,0.0018273556,0.15013081,0.008570133,0.0015185078,0.0010603473,0.059162952,0.15863255,0.35043254,0.22421694,0.021799993,0.01803761],"about_ca_topic_score_codex":0.00020819457,"about_ca_topic_score_gemma":0.0009138663,"teacher_disagreement_score":0.97405106,"about_ca_system_score_codex":0.00013997822,"about_ca_system_score_gemma":0.00015177655,"threshold_uncertainty_score":0.99955016},"labels":[],"label_agreement":null},{"id":"W3167533889","doi":"10.48550/arxiv.2106.04624","title":"SpeechBrain: A General-Purpose Speech Toolkit","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":513,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; McGill University","funders":"","keywords":"Computer science; Scripting language; Python (programming language); Inference; Architecture; Speech processing; Speech recognition; Speech technology; Natural language processing; Artificial intelligence; Programming language","score_opus":0.09161433237207015,"score_gpt":0.1896422480167848,"score_spread":0.09802791564471466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3167533889","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4423765,0.00013822159,0.52261156,0.0005802608,0.0016142176,0.00044291207,0.00002850206,0.0007183857,0.03148945],"genre_scores_gemma":[0.8825709,0.00060668023,0.0947567,0.0014456187,0.0003708986,0.0000032939122,0.000071228045,0.000054932847,0.020119704],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99689853,0.00028456727,0.00030231223,0.0017533513,0.00022231006,0.0005389405],"domain_scores_gemma":[0.9969086,0.00015488708,0.00024995857,0.0020288466,0.0003297044,0.00032797872],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00037058446,0.00047350858,0.00054692046,0.00040030942,0.00018223248,0.0006191783,0.002723122,0.00047340602,0.0007557536],"category_scores_gemma":[0.00011598337,0.0005692933,0.00052846933,0.0009357447,0.000102198035,0.00056787976,0.0030668848,0.00073895074,0.00054884976],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015649892,0.0022719763,0.0046248073,0.0007855138,0.001753132,0.06155245,0.0019226555,0.021378065,0.0038595537,0.4709179,0.025519831,0.4052576],"study_design_scores_gemma":[0.00250103,0.00017713926,0.0034252093,0.00070433895,0.00042052515,0.0005242071,0.0006165836,0.8069736,0.03166083,0.11200649,0.036276717,0.0047133532],"about_ca_topic_score_codex":0.0001535114,"about_ca_topic_score_gemma":0.0000798135,"teacher_disagreement_score":0.78559554,"about_ca_system_score_codex":0.0002551013,"about_ca_system_score_gemma":0.00042494244,"threshold_uncertainty_score":0.99967587},"labels":[],"label_agreement":null},{"id":"W3175990969","doi":"10.21428/594757db.930ce165","title":"Learning to Model Prosodic and Spectral Features for Non-parallel Emotive Speech Conversion","year":2021,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; Dalhousie University","funders":"Vector Institute; Natural Sciences and Engineering Research Council of Canada; Government of Canada; Canadian Institute for Advanced Research","keywords":"Emotive; Computer science; Speech recognition; Generative grammar; Speech synthesis; Artificial neural network; Convolutional neural network; Kernel (algebra); Artificial intelligence; Speech enhancement","score_opus":0.0176946675514212,"score_gpt":0.25114540375258565,"score_spread":0.23345073620116444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3175990969","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.112595856,0.000019075991,0.8696139,0.0028965792,0.000107566586,0.00030344384,0.0000022200193,0.00011509864,0.014346292],"genre_scores_gemma":[0.25726634,0.000016020545,0.72632265,0.0011109413,0.000035105633,0.000015233287,0.0000032332061,0.0000069356875,0.015223532],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991998,0.000021993825,0.00009065432,0.00035393456,0.00013583989,0.00019776361],"domain_scores_gemma":[0.9995206,0.0000873697,0.000023140754,0.00013720385,0.00011560659,0.00011610651],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011651035,0.00009412328,0.00012474948,0.000062877865,0.00013317777,0.00015339271,0.00015377915,0.000047139987,0.000049190723],"category_scores_gemma":[0.000094618474,0.00008369413,0.000053578944,0.0001510012,0.000014580325,0.00018805507,0.00012225745,0.00008530824,0.00003933388],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023600078,0.00044130586,0.0021980647,0.00023662543,0.00016796644,0.00025948402,0.013088539,0.0028443108,0.0803828,0.045656875,0.057048775,0.7974393],"study_design_scores_gemma":[0.00076228357,0.00019673463,0.002248412,0.00003820265,0.000011084674,0.00009335476,0.0007146846,0.7441844,0.24498084,0.0054569277,0.001000041,0.00031306254],"about_ca_topic_score_codex":0.0000069953167,"about_ca_topic_score_gemma":0.000012313715,"teacher_disagreement_score":0.7971262,"about_ca_system_score_codex":0.000020611918,"about_ca_system_score_gemma":0.000062359526,"threshold_uncertainty_score":0.34129477},"labels":[],"label_agreement":null},{"id":"W3176272988","doi":"10.23641/asha.14167058.v1","title":"Forced alignment of child speech (Mahr et al., 2021)","year":2021,"lang":"en","type":"article","venue":"Figshare","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Speech recognition; Phone; Two-alternative forced choice; Sample (material); Segmentation; Natural language processing; Artificial intelligence; Linguistics; Mathematics; Statistics","score_opus":0.03463776890904033,"score_gpt":0.26468767655305236,"score_spread":0.23004990764401204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3176272988","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011444987,0.001544705,0.0044890987,0.069720365,0.0008811699,0.0009512533,0.15317953,0.0005574964,0.7675319],"genre_scores_gemma":[0.33710608,0.00036984283,0.2596259,0.22892791,0.000695543,0.0008684715,0.15222697,0.00021282247,0.019966433],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990666,0.00005523266,0.00016620704,0.00027218764,0.00028173282,0.00015802322],"domain_scores_gemma":[0.99917686,0.00011013816,0.00007271638,0.0004291192,0.00013946186,0.00007170551],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000060292725,0.00009230628,0.00013619536,0.00004632877,0.00004303883,0.00007187662,0.00036324398,0.00003909679,0.17034148],"category_scores_gemma":[0.00040650318,0.00009040595,0.00010419579,0.00025806134,0.000002870927,0.00016741626,0.00023851176,0.00007684824,0.0021769484],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011502876,0.00005852304,0.0000049324135,0.000023920778,0.00001986984,0.000083645624,0.0000705646,0.000002303768,0.0005923693,0.0005555555,0.9012106,0.09737655],"study_design_scores_gemma":[0.00021326874,0.000022270007,0.00042780722,0.00066861935,0.0000027091824,0.00006570889,0.000026794034,0.0013296593,0.3295394,0.00025860977,0.6672859,0.00015925258],"about_ca_topic_score_codex":0.0000029598539,"about_ca_topic_score_gemma":0.0000074172563,"teacher_disagreement_score":0.74756545,"about_ca_system_score_codex":0.000017120366,"about_ca_system_score_gemma":0.00007053458,"threshold_uncertainty_score":0.99859995},"labels":[],"label_agreement":null},{"id":"W3176722102","doi":"10.18429/jacow-linac2018-tu1a03","title":"Status and Issues (Microphonics, LFD, MPS) with TRIUMF ARIEL e-Linac Commissioning","year":2018,"lang":"en","type":"article","venue":"JACOW","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"TRIUMF","funders":"","keywords":"Microphonics; Linear particle accelerator; Nuclear engineering; Nuclear physics; Physics; Engineering; Beam (structure)","score_opus":0.01715254033419223,"score_gpt":0.2598099494333721,"score_spread":0.24265740909917988,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3176722102","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73202115,0.0018186034,0.20746987,0.008809368,0.0011116309,0.0004670836,0.000014570768,0.00074603595,0.047541667],"genre_scores_gemma":[0.74083537,0.00019862421,0.253215,0.0012163881,0.00024135543,0.000009241521,0.0000026121136,0.000019734665,0.0042616595],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990966,0.000049663267,0.00012739115,0.00029081845,0.0001715245,0.00026401054],"domain_scores_gemma":[0.99926347,0.00008935264,0.000059373848,0.00032562905,0.00011093683,0.00015124938],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001680908,0.00011599858,0.00014521803,0.00007637291,0.00021472452,0.00022015403,0.00025323522,0.0000553672,0.00019433197],"category_scores_gemma":[0.00006283181,0.0000876459,0.000023739802,0.0002055475,0.00012105044,0.00022830271,0.000120804034,0.00010112386,0.00015981475],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013087138,0.00021987139,0.009144585,0.00004255443,0.00008864184,0.00008847779,0.005712894,0.000001238185,0.013574009,0.011263169,0.028115219,0.93161845],"study_design_scores_gemma":[0.0017649624,0.00079120806,0.016738536,0.00020202434,0.000029049992,0.00012020177,0.0007251325,0.0091585135,0.23477583,0.0046599023,0.7302811,0.00075355056],"about_ca_topic_score_codex":0.000107318665,"about_ca_topic_score_gemma":0.000037771813,"teacher_disagreement_score":0.93086493,"about_ca_system_score_codex":0.000020069734,"about_ca_system_score_gemma":0.00006192012,"threshold_uncertainty_score":0.3574096},"labels":[],"label_agreement":null},{"id":"W3177268625","doi":"10.21467/proceedings.115.20","title":"End-to-End Speech Recognition Using Recurrent Neural Network (RNN)","year":2021,"lang":"en","type":"article","venue":"AIJR Proceedings","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University of Edmonton","funders":"","keywords":"Computer science; Recurrent neural network; End-to-end principle; Deep learning; Speech recognition; Artificial intelligence; Long short term memory; Language model; Artificial neural network; Deep neural networks; Voice activity detection; Acoustic model; Speech processing","score_opus":0.056511863445194516,"score_gpt":0.27158804131575,"score_spread":0.21507617787055547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3177268625","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93554676,0.00026091104,0.030951997,0.0052529303,0.002950747,0.0005076791,0.000013733575,0.00073428167,0.023780981],"genre_scores_gemma":[0.34713316,0.00007558341,0.6462411,0.0046438035,0.0013611785,0.000045718618,0.00001997797,0.000047146226,0.00043231528],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9979658,0.00002983691,0.00033591338,0.00067947665,0.00044799453,0.000540995],"domain_scores_gemma":[0.9988113,0.00008171552,0.00012406518,0.0001958771,0.0005381405,0.00024890582],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004137385,0.00021938475,0.00024365656,0.00013823553,0.00024365788,0.0004937713,0.00044143427,0.00010035477,0.0004779315],"category_scores_gemma":[0.0002581423,0.00023094472,0.00012564994,0.0012328412,0.00002927011,0.00085903675,0.000296213,0.00022925324,0.00039268032],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009215598,0.00006524808,0.00051254785,0.00002515058,0.000020186653,0.0000536557,0.00029400713,0.0000045786896,0.004088194,0.0007020188,0.006714737,0.98751044],"study_design_scores_gemma":[0.0023002354,0.00071493123,0.009002789,0.001639547,0.0002543871,0.004591093,0.0013178982,0.2442068,0.5190843,0.04116903,0.17176124,0.003957772],"about_ca_topic_score_codex":0.000015018496,"about_ca_topic_score_gemma":0.000007866493,"teacher_disagreement_score":0.9835527,"about_ca_system_score_codex":0.00009220794,"about_ca_system_score_gemma":0.00008573364,"threshold_uncertainty_score":0.9417652},"labels":[],"label_agreement":null},{"id":"W3178196694","doi":"10.18280/ria.350307","title":"Usage of Prosody Modification and Acoustic Adaptation for Robust Automatic Speech Recognition (ASR) System","year":2021,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Prosody; Speech recognition; Naturalness; Computer science; Word error rate; Adaptation (eye); Speech processing; Psychology","score_opus":0.10538573665782153,"score_gpt":0.27794781039062283,"score_spread":0.1725620737328013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3178196694","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038271543,0.00012870337,0.9596095,0.0002621573,0.00022715473,0.000474175,0.000017252703,0.00013105036,0.00087842694],"genre_scores_gemma":[0.6838922,0.00005378241,0.31557333,0.000031922264,0.0000379154,0.000097943775,0.000025711508,0.000011330852,0.0002758555],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99860895,0.000094821284,0.0005139434,0.00041947642,0.00017233544,0.00019050596],"domain_scores_gemma":[0.998448,0.000406026,0.00022358708,0.0003913361,0.0004618399,0.000069202564],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000512115,0.00012499224,0.00021765546,0.00012361689,0.0001331465,0.00011445126,0.00020922057,0.000080697006,0.000045520595],"category_scores_gemma":[0.000404676,0.00013218132,0.00007870443,0.000457394,0.000045384113,0.00033842833,0.000047981273,0.000066054046,0.00007676835],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000068435393,0.000120325996,0.00001149634,0.00062522176,0.000016137057,0.000008572615,0.00085268694,0.003603858,0.021711899,0.002561845,0.00006142941,0.9704197],"study_design_scores_gemma":[0.00004277518,0.000045112298,0.000033346852,0.00022747446,0.000021562922,0.000069883514,0.0014652607,0.7375674,0.25914833,0.0012148247,0.00005103456,0.00011293853],"about_ca_topic_score_codex":0.000010917055,"about_ca_topic_score_gemma":0.000013252975,"teacher_disagreement_score":0.97030675,"about_ca_system_score_codex":0.00005113792,"about_ca_system_score_gemma":0.00007112487,"threshold_uncertainty_score":0.53901976},"labels":[],"label_agreement":null},{"id":"W3184647894","doi":"10.3390/s21155097","title":"A Two-Level Speaker Identification System via Fusion of Heterogeneous Classifiers and Complementary Feature Cooperation","year":2021,"lang":"en","type":"article","venue":"Sensors","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Mel-frequency cepstrum; Classifier (UML); Mixture model; Discriminative model; Artificial intelligence; Pattern recognition (psychology); Computer science; Speech recognition; Support vector machine; Speaker recognition; Feature extraction","score_opus":0.03279552816942155,"score_gpt":0.2527752848545654,"score_spread":0.21997975668514386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3184647894","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90780854,0.00012652522,0.089311205,0.0010553648,0.00044927016,0.00019939855,0.00003599832,0.00009081605,0.00092287135],"genre_scores_gemma":[0.9708597,0.000019661342,0.028600235,0.00013627947,0.000033775945,0.0000036473982,0.000037541402,0.0000064021892,0.00030272425],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990637,0.00013812546,0.0002121951,0.00027914238,0.000195032,0.00011184181],"domain_scores_gemma":[0.99934465,0.000047959034,0.00009564149,0.00027382295,0.00018097424,0.00005694084],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015289542,0.00008895031,0.00013476217,0.00006930293,0.00010190009,0.00008173894,0.00010977002,0.000043111224,0.000033534274],"category_scores_gemma":[0.000020714086,0.00008584825,0.00004342195,0.00020564206,0.000028501105,0.000112830036,0.00006492748,0.00005469766,0.00002353012],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042296535,0.00018529808,0.0011336721,0.0002732571,0.00015696105,0.00027062627,0.0019845015,0.0004463354,0.67729884,0.010382453,0.0014025378,0.3064232],"study_design_scores_gemma":[0.00090282963,0.000049741055,0.008159399,0.00012774993,0.00004509971,0.00078996195,0.0012968151,0.3198807,0.66694856,0.00017662016,0.0012991248,0.00032336838],"about_ca_topic_score_codex":0.000027781141,"about_ca_topic_score_gemma":0.000083398525,"teacher_disagreement_score":0.31943437,"about_ca_system_score_codex":0.000038471233,"about_ca_system_score_gemma":0.00002554817,"threshold_uncertainty_score":0.350079},"labels":[],"label_agreement":null},{"id":"W3186939564","doi":"10.18280/isi.260304","title":"Optimized Features Extraction from Spectral and Temporal Features for Identifying the Telugu Dialects by Using GMM and HMM","year":2021,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Telugu; Mel-frequency cepstrum; Hidden Markov model; Computer science; Artificial intelligence; Dimensionality reduction; Speech recognition; Feature extraction; Pattern recognition (psychology); Curse of dimensionality; Identification (biology); Feature (linguistics); Linguistics","score_opus":0.0278661034268363,"score_gpt":0.2684506857284297,"score_spread":0.24058458230159344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3186939564","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3695146,0.001795653,0.6260819,0.0004254491,0.00058357936,0.00042005023,0.000053808362,0.00014663368,0.000978329],"genre_scores_gemma":[0.8302765,0.00014525672,0.16885333,0.00037656043,0.00011377202,0.00003814797,0.0001053964,0.000009556263,0.0000814931],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990519,0.00008434483,0.0002864401,0.00018309077,0.0001919635,0.00020220285],"domain_scores_gemma":[0.99911034,0.0002933577,0.00020171504,0.00018411431,0.00014636782,0.00006410979],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00028633428,0.00014670032,0.00017455446,0.00009470303,0.0005105816,0.0014113354,0.00015088821,0.000100274425,0.00001255829],"category_scores_gemma":[0.00030932305,0.000119149336,0.00005797621,0.00020269639,0.00007380842,0.0030153187,0.00007819872,0.00012084761,0.0000024559652],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016211682,0.00006629185,0.0009278521,0.0003304589,0.0002221688,0.000016279682,0.018752435,0.00013401518,0.030326335,0.0034295544,0.00806443,0.93756807],"study_design_scores_gemma":[0.006457177,0.00024895952,0.078584306,0.0010731342,0.00034499032,0.0024443502,0.014539209,0.270053,0.5440608,0.06676644,0.013204138,0.0022235042],"about_ca_topic_score_codex":0.00017352682,"about_ca_topic_score_gemma":0.000029772611,"teacher_disagreement_score":0.9353446,"about_ca_system_score_codex":0.00007475432,"about_ca_system_score_gemma":0.00005852032,"threshold_uncertainty_score":0.99962527},"labels":[],"label_agreement":null},{"id":"W3187244867","doi":"10.21437/interspeech.2021-1755","title":"The Zero Resource Speech Challenge 2021: Spoken Language Modelling","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Agence Nationale de la Recherche","keywords":"Computer science; Encoder; Natural language processing; ABX test; Zero (linguistics); Coding (social sciences); Speech recognition; Pipeline (software); Artificial intelligence; Baseline (sea); Word (group theory); Language model; Linguistics; Mathematics","score_opus":0.03830097918852758,"score_gpt":0.25625806829496617,"score_spread":0.21795708910643857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3187244867","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0048729526,0.0029574295,0.7864925,0.005339069,0.000748843,0.0002885486,0.0000059493823,0.00031175764,0.19898294],"genre_scores_gemma":[0.1896691,0.0067182803,0.7522148,0.002057426,0.0012946767,0.00018733142,0.00008807634,0.00012502586,0.047645293],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975439,0.00023001978,0.00037374918,0.0008586113,0.0005741652,0.00041957255],"domain_scores_gemma":[0.99725646,0.00045586904,0.00014927033,0.0018633987,0.00013734517,0.00013766372],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0008132044,0.00030419577,0.0003166043,0.00010111475,0.00027150544,0.0011422873,0.0020818214,0.000284354,0.000430188],"category_scores_gemma":[0.0000859976,0.00022085446,0.0002950625,0.00018974447,0.00004743383,0.00013498751,0.0021738526,0.0007220411,0.0002653314],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000056884146,0.0000865045,0.0000031812542,0.000046320412,0.000110045265,0.00037295866,0.0025692414,0.0012435432,0.000046010908,0.008372829,0.0041897614,0.9829539],"study_design_scores_gemma":[0.00026301056,0.000027026943,0.000013909373,0.00032188348,0.000040125193,0.000075323864,0.002736467,0.89347714,0.009528986,0.0128331045,0.07966123,0.0010217852],"about_ca_topic_score_codex":0.00019126564,"about_ca_topic_score_gemma":0.00009520086,"teacher_disagreement_score":0.9819321,"about_ca_system_score_codex":0.00006269461,"about_ca_system_score_gemma":0.0001447085,"threshold_uncertainty_score":0.9998946},"labels":[],"label_agreement":null},{"id":"W3191044189","doi":"10.48550/arxiv.2107.14642","title":"Practical Attacks on Voice Spoofing Countermeasures","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Spoofing attack; Computer science; Computer security; Authentication (law); Adversarial system; Key (lock); Vulnerability (computing); Artificial intelligence","score_opus":0.17514551471353124,"score_gpt":0.23951261841909008,"score_spread":0.06436710370555884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3191044189","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24050829,0.000029317542,0.7278079,0.0008598064,0.0013316552,0.00022948919,0.000012566041,0.00041183646,0.028809194],"genre_scores_gemma":[0.98912203,0.000114772905,0.008645713,0.00071432634,0.00010656355,9.481615e-7,0.000010932877,0.000017729262,0.0012670067],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977959,0.00028253134,0.00018552513,0.0011973957,0.0001999375,0.00033875645],"domain_scores_gemma":[0.99773496,0.0004220307,0.0002024199,0.0011704692,0.00027210257,0.00019801443],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003456964,0.00030115474,0.00033383272,0.00022709135,0.00016622289,0.00039969603,0.0010645818,0.00031739724,0.00018418935],"category_scores_gemma":[0.00027782106,0.00034757922,0.00027446283,0.00039323108,0.0000775006,0.00042653046,0.0010733898,0.0007767842,0.0004957468],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000709187,0.0049041403,0.014228757,0.0010916785,0.0026514085,0.063164614,0.0031375363,0.05988841,0.000979818,0.72831744,0.038762365,0.08216467],"study_design_scores_gemma":[0.0017599261,0.00024318097,0.009489705,0.001490863,0.0003866628,0.00025200105,0.0010662483,0.9421316,0.006938686,0.016389497,0.016846353,0.0030052844],"about_ca_topic_score_codex":0.00005573144,"about_ca_topic_score_gemma":0.000050722025,"teacher_disagreement_score":0.88224316,"about_ca_system_score_codex":0.0002192196,"about_ca_system_score_gemma":0.00034959646,"threshold_uncertainty_score":0.9998976},"labels":[],"label_agreement":null},{"id":"W3195948749","doi":"10.1109/jiot.2021.3097266","title":"Efficient and Privacy-Preserving Speaker Recognition for Cybertwin-Driven 6G","year":2021,"lang":"en","type":"article","venue":"IEEE Internet of Things Journal","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Computer science; Euclidean distance; Biometrics; Speaker recognition; Cosine similarity; Random projection; Computation; Computer security; Speech recognition; Data mining; Artificial intelligence; Algorithm; Pattern recognition (psychology)","score_opus":0.03617530084013353,"score_gpt":0.2618438795747483,"score_spread":0.22566857873461477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3195948749","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5627132,0.00013854758,0.43288535,0.0015742822,0.0010229705,0.00009216625,0.0000031943205,0.000033860277,0.0015364527],"genre_scores_gemma":[0.68566674,0.00004908831,0.312755,0.00072804105,0.00018924128,0.000005487102,0.0000017792703,0.000014981449,0.00058966345],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988068,0.00008125306,0.00037820247,0.0002449894,0.00027835864,0.00021039584],"domain_scores_gemma":[0.9987144,0.00026320238,0.00025534417,0.00020698583,0.00043444254,0.0001256162],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005047872,0.00011555219,0.00020262951,0.00013355525,0.00007500454,0.00030387324,0.0005345894,0.000063463136,0.00015596059],"category_scores_gemma":[0.00054048636,0.00010468434,0.00015215954,0.00011621288,0.000032533055,0.0003277747,0.00020703029,0.00020344456,0.000016795835],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015278869,0.0005803154,0.00090983097,0.00025136507,0.00045424528,0.00038300199,0.014343028,0.00016800512,0.13803616,0.00097419624,0.025973475,0.8177736],"study_design_scores_gemma":[0.0016764048,0.00022304436,0.0013049301,0.001146871,0.00006843884,0.003457916,0.0003015928,0.46482217,0.5066293,0.013478955,0.006432609,0.00045776946],"about_ca_topic_score_codex":0.000011312456,"about_ca_topic_score_gemma":0.0000027053163,"teacher_disagreement_score":0.8173158,"about_ca_system_score_codex":0.00003300904,"about_ca_system_score_gemma":0.0000574971,"threshold_uncertainty_score":0.42689034},"labels":[],"label_agreement":null},{"id":"W3198750786","doi":"","title":"Malayalam three-way rhotics contrast: Articulatory modelling based on MRI data","year":2020,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; University of Toronto","funders":"","keywords":"Malayalam; Contrast (vision); Computer science; Artificial intelligence; Speech recognition; Natural language processing","score_opus":0.0532952881399329,"score_gpt":0.2398904879386189,"score_spread":0.186595199798686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3198750786","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024725206,0.00019334644,0.9517446,0.023052474,0.0003832388,0.00046680184,0.00013558267,0.0005503945,0.02100101],"genre_scores_gemma":[0.49802032,0.00012967666,0.49988836,0.00084197155,0.000045518053,0.00004185353,0.0005455813,0.00005297645,0.00043374064],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9935273,0.0029152073,0.00065979786,0.0016147456,0.0008263294,0.0004566404],"domain_scores_gemma":[0.9895965,0.002180513,0.0004967907,0.0061279256,0.0012306788,0.00036761825],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.004428803,0.00044985532,0.0005024761,0.00022393109,0.00033502327,0.00097045326,0.004950149,0.0003214639,0.00015061739],"category_scores_gemma":[0.001188971,0.00047669027,0.00023018864,0.00043471603,0.00016393898,0.00029108144,0.0030310454,0.0009057673,0.00021834431],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009009755,0.003876519,0.0023633216,0.00083952426,0.0005669831,0.00019679981,0.006531984,0.064399354,0.0018440653,0.44344884,0.0116028,0.4642397],"study_design_scores_gemma":[0.00036958524,5.255884e-7,0.00043938123,0.0009605438,0.000041243286,0.000004115804,0.000013329545,0.9763197,0.0107631,0.0069194017,0.0037055053,0.0004635991],"about_ca_topic_score_codex":0.00016016749,"about_ca_topic_score_gemma":0.0002674678,"teacher_disagreement_score":0.9119203,"about_ca_system_score_codex":0.0001079347,"about_ca_system_score_gemma":0.00043471175,"threshold_uncertainty_score":0.9997685},"labels":[],"label_agreement":null},{"id":"W3200111860","doi":"10.1007/978-3-030-87802-3_1","title":"Text-Independent Speaker Verification Employing CNN-LSTM-TDNN Hybrid Networks","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Speech recognition; NIST; Artificial neural network; Time delay neural network; Speaker recognition; Artificial intelligence; Pattern recognition (psychology); Utterance; Pooling; Convolutional neural network","score_opus":0.023570762265196613,"score_gpt":0.2391657481355195,"score_spread":0.21559498587032289,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3200111860","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012945013,0.00058626774,0.9880734,0.0008424201,0.0030234854,0.00035804271,0.000004674845,0.000264183,0.0067180735],"genre_scores_gemma":[0.23543456,0.0004440437,0.75400513,0.0059232293,0.0017228732,0.000041473762,0.00005330967,0.00013214961,0.002243195],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99487954,0.000085233085,0.0007118948,0.002149998,0.0013512454,0.0008220586],"domain_scores_gemma":[0.9965207,0.0005709992,0.0003761151,0.0018436394,0.0004118393,0.00027672725],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0010750932,0.000628653,0.0006295698,0.0007429136,0.00038314072,0.0012589057,0.0029922903,0.00035232038,0.00025182535],"category_scores_gemma":[0.00016779467,0.0006206222,0.000250478,0.00070438016,0.00039666292,0.0007117553,0.001165944,0.0010529356,0.00020795398],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000037695445,0.00003822729,0.000047771282,0.000017395061,0.000018928726,0.0002529488,0.00014260176,0.009033263,0.00011044142,0.006198794,0.00008203068,0.98405385],"study_design_scores_gemma":[0.00036569277,0.00009287488,0.00048236523,0.00069943623,0.000024379186,0.00051912206,6.5681866e-7,0.944918,0.0046607335,0.038922634,0.007948338,0.0013657806],"about_ca_topic_score_codex":0.00002173269,"about_ca_topic_score_gemma":0.000063488784,"teacher_disagreement_score":0.98268807,"about_ca_system_score_codex":0.00042232548,"about_ca_system_score_gemma":0.00054853834,"threshold_uncertainty_score":0.99977785},"labels":[],"label_agreement":null},{"id":"W3200812870","doi":"","title":"Alzheimers Dementia Detection using Acoustic & Linguistic features and Pre-Trained BERT.","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Computer science; Dementia; Task (project management); Artificial intelligence; Set (abstract data type); Feature (linguistics); Natural language processing; Conjunction (astronomy); Speech recognition; Linguistics; Disease; Medicine; Engineering","score_opus":0.06678901600204276,"score_gpt":0.2035636742655412,"score_spread":0.13677465826349844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3200812870","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4480965,0.00025721954,0.55022675,0.00001527207,0.0006098643,0.00015612104,0.0000043556356,0.00014530949,0.0004885765],"genre_scores_gemma":[0.989825,0.00014135722,0.009693438,0.00007373348,0.00008210678,7.154923e-7,0.0000075656294,0.000015648679,0.00016044828],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99840516,0.00014662223,0.00015699024,0.0009248629,0.0000963119,0.00027003733],"domain_scores_gemma":[0.99880457,0.00013318239,0.0001728059,0.00054384535,0.00018991118,0.00015568874],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00016209009,0.00026525522,0.0002663412,0.00025200756,0.00022854707,0.0002895952,0.0005117975,0.0002453568,0.000040649356],"category_scores_gemma":[0.00014831725,0.00032072273,0.00014904776,0.00037049816,0.00008096638,0.00019754296,0.00080303155,0.00037353573,0.0000055377895],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00068527897,0.0018975235,0.014410029,0.0026717966,0.013913121,0.014003344,0.013257121,0.53033316,0.062635064,0.034154627,0.0004462842,0.31159264],"study_design_scores_gemma":[0.00044108968,0.000041240695,0.0067852763,0.00021063584,0.00092355616,0.00008344846,0.00021426594,0.9813297,0.0045971405,0.004643821,0.0000678839,0.0006619882],"about_ca_topic_score_codex":0.000248657,"about_ca_topic_score_gemma":0.0002611895,"teacher_disagreement_score":0.54172844,"about_ca_system_score_codex":0.000095170915,"about_ca_system_score_gemma":0.00014353027,"threshold_uncertainty_score":0.9999245},"labels":[],"label_agreement":null},{"id":"W3201237299","doi":"10.1007/978-3-030-87802-3_2","title":"End-to-End Voice Spoofing Detection Employing Time Delay Neural Networks and Higher Order Statistics","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Spoofing attack; Speech recognition; Artificial neural network; Higher-order statistics; Artificial intelligence; Computer network; Telecommunications; Signal processing","score_opus":0.018339856872574663,"score_gpt":0.23781070371785273,"score_spread":0.21947084684527807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3201237299","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00023237287,0.0003162092,0.99571943,0.00043578108,0.001947605,0.00025117063,0.000010326253,0.0001646479,0.0009224784],"genre_scores_gemma":[0.07080721,0.000044627224,0.92317224,0.004063025,0.0007569782,0.000012270939,0.00001204607,0.00006331287,0.001068298],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99652255,0.000077627206,0.0004747734,0.0014875381,0.00078380556,0.00065369037],"domain_scores_gemma":[0.99736625,0.0010165739,0.00020212337,0.000745377,0.00039501168,0.00027464537],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006353265,0.0004977408,0.00049864815,0.0006307174,0.00038838966,0.00105378,0.0011428305,0.00029973534,0.0001766876],"category_scores_gemma":[0.00015874636,0.0004890654,0.000073859796,0.0008604219,0.0003198902,0.00047729196,0.0010206908,0.00074322574,0.00005965741],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000041878325,0.000009786354,0.00001731104,0.000013139449,0.000011989758,0.00018022417,0.00013481935,0.012318789,0.00017791754,0.00073709735,0.000016927179,0.98637784],"study_design_scores_gemma":[0.00017704743,0.000109401604,0.00036410164,0.00021718952,0.000019322493,0.00025526623,1.9823929e-7,0.9890025,0.0008062407,0.006085284,0.0022414066,0.0007220156],"about_ca_topic_score_codex":0.000036249763,"about_ca_topic_score_gemma":0.00016224326,"teacher_disagreement_score":0.9856558,"about_ca_system_score_codex":0.00018498377,"about_ca_system_score_gemma":0.00017906689,"threshold_uncertainty_score":0.99998325},"labels":[],"label_agreement":null},{"id":"W3201401182","doi":"10.3390/app11188412","title":"Accented Speech Recognition Based on End-to-End Domain Adversarial Training of Neural Networks","year":2021,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Speech recognition; Computer science; Classifier (UML); Artificial neural network; Stress (linguistics); Connectionism; Artificial intelligence","score_opus":0.05449696249940805,"score_gpt":0.2641169772131821,"score_spread":0.20962001471377406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3201401182","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3506256,0.000027858205,0.5278426,0.0034209618,0.0019690136,0.00058752677,0.000027126618,0.00031303187,0.11518632],"genre_scores_gemma":[0.85135967,0.000001825173,0.14669667,0.0017849366,0.0001112982,0.000018173405,0.000009228102,0.0000055228934,0.000012690355],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979251,0.00012180745,0.00029946826,0.0006108788,0.0006617543,0.0003809958],"domain_scores_gemma":[0.99884236,0.00050501083,0.00011760109,0.0002955042,0.000093694245,0.00014584551],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00095403905,0.00015252887,0.00023601313,0.00022733968,0.00025839658,0.00019582284,0.00068433187,0.00007170746,0.00042893484],"category_scores_gemma":[0.00013038988,0.00014013148,0.00009509241,0.0016012049,0.00017133426,0.00023849524,0.0001089852,0.0001344912,0.00004580864],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036448106,0.00009945643,0.000058128804,0.0000044755425,0.000008606739,0.000028841841,0.00041547662,0.0017665166,0.0057748663,0.0037612487,0.00018984625,0.9878561],"study_design_scores_gemma":[0.0018559385,0.00038774297,0.0017528452,0.00012198737,0.000026247291,0.000045823046,0.0025530015,0.7031672,0.27863663,0.009342829,0.0013168068,0.00079293933],"about_ca_topic_score_codex":0.000010334678,"about_ca_topic_score_gemma":0.00002560008,"teacher_disagreement_score":0.98706317,"about_ca_system_score_codex":0.000027469077,"about_ca_system_score_gemma":0.00017005597,"threshold_uncertainty_score":0.5714396},"labels":[],"label_agreement":null},{"id":"W3202995775","doi":"10.48550/arxiv.2110.00678","title":"Speech Technology for Everyone: Automatic Speech Recognition for Non-Native English with Transfer Learning","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Speech recognition; Computer science; Transfer of learning; Transfer (computing); Natural language processing; Speech technology; Artificial intelligence; Speech processing","score_opus":0.05550620059544906,"score_gpt":0.1950521161755607,"score_spread":0.13954591558011165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3202995775","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34656727,0.000017106304,0.6502643,0.000062088475,0.00038209025,0.0011788358,0.000038207574,0.00048529793,0.0010047947],"genre_scores_gemma":[0.81108606,0.00009265076,0.18637982,0.00010580088,0.00014637146,0.000062251915,0.00014486091,0.000057813926,0.001924401],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99745965,0.0001543262,0.0003128899,0.0014105367,0.00013502776,0.0005275809],"domain_scores_gemma":[0.99684596,0.0006966908,0.0002197539,0.00066663505,0.0014427166,0.00012822881],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00042404167,0.0004316595,0.00061703636,0.0006950357,0.00032394746,0.00016884913,0.0010176175,0.00064916955,0.000095116244],"category_scores_gemma":[0.00040216724,0.0004773413,0.000343412,0.0010005834,0.00013060584,0.0005438625,0.00035982192,0.00078077073,0.000023850838],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00091375224,0.0016508346,0.004075146,0.004180336,0.0036329892,0.0021892365,0.0091345515,0.010247513,0.0012497843,0.011869864,0.0016108572,0.94924515],"study_design_scores_gemma":[0.0055777114,0.0009134981,0.00057918,0.0017620502,0.000825074,0.00007101386,0.006690156,0.8956666,0.047215365,0.036277268,0.002034723,0.0023873358],"about_ca_topic_score_codex":0.00001928078,"about_ca_topic_score_gemma":0.00007886583,"teacher_disagreement_score":0.9468578,"about_ca_system_score_codex":0.00021166904,"about_ca_system_score_gemma":0.0003837075,"threshold_uncertainty_score":0.99976784},"labels":[],"label_agreement":null},{"id":"W3206189675","doi":"10.1109/icassp43922.2022.9747814","title":"Large-Scale Self-Supervised Speech Representation Learning for Automatic Speaker Verification","year":2022,"lang":"en","type":"article","venue":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":102,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Generalizability theory; Computer science; Speech recognition; Word error rate; Speaker recognition; Artificial intelligence; Representation (politics); Artificial neural network; Scale (ratio); Feature (linguistics); Pattern recognition (psychology); Machine learning; Mathematics","score_opus":0.0517667352431102,"score_gpt":0.3075118367600685,"score_spread":0.2557451015169583,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3206189675","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13228124,0.00012503666,0.84909356,0.0056130146,0.0019218501,0.0012109014,0.0002562636,0.00094613276,0.0085519785],"genre_scores_gemma":[0.90634346,0.00010671446,0.08928773,0.0009742996,0.00032646017,0.00036281106,0.00025229267,0.000055937173,0.0022903245],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956914,0.00031854762,0.0007503577,0.001128938,0.0015517352,0.00055901025],"domain_scores_gemma":[0.9977696,0.00041304258,0.00051502266,0.0004122565,0.0006603603,0.00022972432],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012689029,0.000387335,0.00041581428,0.00049758295,0.0011387962,0.00091490784,0.001139939,0.00013035037,0.002280774],"category_scores_gemma":[0.00028059722,0.00042159768,0.00017574875,0.00058654515,0.000081978345,0.0006909479,0.0003248943,0.0007746368,0.000070715476],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032987352,0.0015270776,0.0009077172,0.0002445513,0.00026671155,0.00020171677,0.004040523,0.0016398415,0.08344477,0.0052010403,0.008806953,0.8933892],"study_design_scores_gemma":[0.0011266299,0.00034288235,0.00040906682,0.00006620648,0.00006133707,0.00017899314,0.0024694663,0.98267555,0.0035582844,0.0046188813,0.003977077,0.0005156475],"about_ca_topic_score_codex":0.000019350695,"about_ca_topic_score_gemma":0.000007875948,"teacher_disagreement_score":0.9810357,"about_ca_system_score_codex":0.0003448308,"about_ca_system_score_gemma":0.00033234977,"threshold_uncertainty_score":0.9998236},"labels":[],"label_agreement":null},{"id":"W3207572704","doi":"10.1109/icassp43922.2022.9746260","title":"Continual Learning Using Lattice-Free MMI for Speech Recognition","year":2022,"lang":"en","type":"article","venue":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"NeuroRx Research (Canada)","funders":"","keywords":"Forgetting; Computer science; Regularization (linguistics); Artificial neural network; Exploit; Speech recognition; Word error rate; Artificial intelligence; Acoustic model; Domain adaptation; Machine learning; Speech processing","score_opus":0.09276504634484213,"score_gpt":0.3157352333647936,"score_spread":0.22297018701995147,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3207572704","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19449572,0.0003247609,0.77556545,0.006320996,0.0040913317,0.00147259,0.0012150508,0.0008423034,0.015671777],"genre_scores_gemma":[0.8670032,0.0001121499,0.12697735,0.0014989944,0.00079862896,0.00022313569,0.00020861583,0.0000846725,0.0030932282],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9954802,0.00030638478,0.0007829735,0.0011592392,0.0016001927,0.0006710199],"domain_scores_gemma":[0.9971681,0.0006217792,0.0006196291,0.00039751444,0.00091430737,0.00027865337],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0014485641,0.00046608504,0.00050036405,0.00060609356,0.0012871432,0.001068986,0.0015720804,0.00016322017,0.00225299],"category_scores_gemma":[0.0006666324,0.0005147185,0.0002045393,0.0005093396,0.00016660124,0.0007854298,0.000597404,0.001118538,0.000045960773],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044554286,0.0005357982,0.00014715848,0.00010812986,0.00017420313,0.00034167097,0.0005208462,0.00052144343,0.07491359,0.0024281926,0.004662226,0.9152012],"study_design_scores_gemma":[0.0019978646,0.0007385536,0.000080952406,0.00018165271,0.00011136861,0.0005976132,0.0018098817,0.95257914,0.01001969,0.024837999,0.0060904287,0.0009548264],"about_ca_topic_score_codex":0.00004558901,"about_ca_topic_score_gemma":0.000010433494,"teacher_disagreement_score":0.9520577,"about_ca_system_score_codex":0.0003654388,"about_ca_system_score_gemma":0.00042851604,"threshold_uncertainty_score":0.999968},"labels":[],"label_agreement":null},{"id":"W3208368542","doi":"10.5281/zenodo.4309193","title":"Humelo/Prosody-API-Document: First release for zenodo connect test","year":2020,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Humber College","funders":"","keywords":"Prosody; Test (biology); Computer science; Natural language processing; Speech recognition; Geology","score_opus":0.045376276028887316,"score_gpt":0.23300364903911477,"score_spread":0.18762737301022747,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3208368542","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0064110695,0.0002820188,0.6863746,0.05079924,0.0004978064,0.003078367,0.0009596705,0.0076904492,0.2439068],"genre_scores_gemma":[0.95997846,0.00023359485,0.027149364,0.005942639,0.0007188681,7.371124e-7,0.0013249276,0.0027315882,0.0019198032],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99797213,0.00016004333,0.00032405052,0.00068950263,0.00039716976,0.00045709134],"domain_scores_gemma":[0.9982235,0.00016864983,0.0001336966,0.0005474518,0.0005157885,0.0004109218],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0004764079,0.00019589267,0.00020772924,0.00015051068,0.002295406,0.001593751,0.001988078,0.000071989714,0.009501636],"category_scores_gemma":[0.0028904597,0.00020713075,0.00011465713,0.0006862894,0.00010346443,0.0005766452,0.0011847847,0.00020032072,0.013426109],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009060564,0.00024755034,0.0000049766227,0.00017465648,0.00006394164,0.000044700133,0.0021523975,0.000024092815,0.0037966985,0.022934629,0.49047172,0.47999403],"study_design_scores_gemma":[0.000792378,0.00045839272,0.00007693815,0.000028761007,0.000013309308,0.000066494926,0.00012431746,0.009050806,0.005314085,0.0008454246,0.9829426,0.00028650378],"about_ca_topic_score_codex":0.000006058243,"about_ca_topic_score_gemma":2.7219116e-7,"teacher_disagreement_score":0.9535674,"about_ca_system_score_codex":0.00009594738,"about_ca_system_score_gemma":0.000006584497,"threshold_uncertainty_score":0.9994427},"labels":[],"label_agreement":null},{"id":"W3209371554","doi":"10.1109/icassp43922.2022.9747760","title":"Optimizing Alignment of Speech and Language Latent Spaces for End-To-End Speech Recognition and Understanding","year":2022,"lang":"en","type":"article","venue":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Speech recognition; Encoder; Language model; Embedding; Word error rate; Context (archaeology); Connectionism; End-to-end principle; Task (project management); Natural language processing; Artificial intelligence; Artificial neural network","score_opus":0.10644103280632176,"score_gpt":0.3075885950457152,"score_spread":0.2011475622393934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3209371554","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40174997,0.00065432186,0.5790682,0.008729313,0.0014493971,0.0015311196,0.0014537413,0.00027125102,0.005092709],"genre_scores_gemma":[0.9208187,0.00023532101,0.077487744,0.0005894297,0.00018018587,0.00009622949,0.00007810635,0.000033688877,0.00048058288],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968516,0.0001387062,0.00057376595,0.00088414276,0.0011202979,0.00043145986],"domain_scores_gemma":[0.9983953,0.00043852377,0.00038905506,0.00021895453,0.00029252513,0.00026563765],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010686622,0.00034900583,0.00042994757,0.0005630247,0.00053715863,0.0006623314,0.0005410781,0.000099369216,0.000805891],"category_scores_gemma":[0.00015722103,0.00036265576,0.00008929951,0.00032383337,0.00016160856,0.00042131104,0.00042169212,0.0004127426,0.000006770495],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040121202,0.00031891352,0.00014221699,0.00021880002,0.00019008134,0.0002740487,0.0026379533,0.0001815547,0.16249911,0.0032553326,0.0010351071,0.8288457],"study_design_scores_gemma":[0.004133193,0.00266385,0.00031037742,0.00091253273,0.00030089487,0.0012665049,0.023434341,0.79906255,0.11439197,0.04958993,0.001803517,0.002130356],"about_ca_topic_score_codex":0.00006215956,"about_ca_topic_score_gemma":0.000018422263,"teacher_disagreement_score":0.8267153,"about_ca_system_score_codex":0.0002967579,"about_ca_system_score_gemma":0.00016728841,"threshold_uncertainty_score":0.9998825},"labels":[],"label_agreement":null},{"id":"W3209976096","doi":"10.1109/icassp43922.2022.9746832","title":"Pseudo-Labeling for Massively Multilingual Speech Recognition","year":2022,"lang":"en","type":"article","venue":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Natural language processing; Speech recognition; Artificial intelligence; Language model","score_opus":0.08598030702419207,"score_gpt":0.3185981659794001,"score_spread":0.23261785895520803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3209976096","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20251589,0.00046376945,0.7569371,0.010836176,0.0069039646,0.0022520064,0.0024868692,0.0011771745,0.01642704],"genre_scores_gemma":[0.8362169,0.00019370942,0.15738033,0.002160683,0.0007818451,0.00039717756,0.00027004426,0.00007991,0.0025193545],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9952542,0.00022267444,0.00085100875,0.0013180166,0.0016584587,0.0006956261],"domain_scores_gemma":[0.99709433,0.00060309644,0.00058376073,0.0003671684,0.001038551,0.00031307616],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012819808,0.00050432683,0.0004952953,0.0006453044,0.0011707386,0.00097342767,0.0014411134,0.00017175631,0.0018357045],"category_scores_gemma":[0.0004871654,0.00054537185,0.00021257915,0.0005084452,0.00015915446,0.00068631995,0.00044453063,0.0009769145,0.000080541475],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029981395,0.00048235653,0.00003833366,0.000072245195,0.000106503205,0.00027957463,0.00033807172,0.00016577319,0.08278895,0.0010340037,0.0027219416,0.9116724],"study_design_scores_gemma":[0.0020810866,0.0007859121,0.00007947147,0.00019430462,0.00009493511,0.0005887453,0.0016383389,0.93641776,0.029749691,0.022946876,0.004309768,0.0011131067],"about_ca_topic_score_codex":0.000032520067,"about_ca_topic_score_gemma":0.000008942017,"teacher_disagreement_score":0.936252,"about_ca_system_score_codex":0.00035928024,"about_ca_system_score_gemma":0.00050932047,"threshold_uncertainty_score":0.9996998},"labels":[],"label_agreement":null},{"id":"W3210306132","doi":"10.1109/rteict52294.2021.9573848","title":"Emotional Speech Cloning using GANs","year":2021,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Speech recognition; Discriminator; Sadness; Speech synthesis; Context (archaeology); Generator (circuit theory); Cloning (programming); Artificial neural network; Anger; Active listening; Field (mathematics); Natural language processing; Artificial intelligence; Psychology; Telecommunications","score_opus":0.05172122108534818,"score_gpt":0.2743723135183435,"score_spread":0.22265109243299533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3210306132","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.068238206,0.000023882143,0.8597228,0.0010747705,0.00030470203,0.000020709864,7.803669e-7,0.00013559531,0.070478536],"genre_scores_gemma":[0.102947675,0.000004651542,0.8931963,0.0012075565,0.000084461804,6.951473e-7,0.0000017549442,0.0000043641826,0.002552547],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99936116,0.00003536764,0.0000982977,0.00019806456,0.00017598318,0.00013115187],"domain_scores_gemma":[0.99957913,0.000058440295,0.000018779121,0.00019010167,0.00009993021,0.00005359528],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00010050856,0.000052858224,0.000065136206,0.000043399286,0.00008770418,0.00013523077,0.00016631138,0.000028004906,0.0016106062],"category_scores_gemma":[0.000057621783,0.00005078289,0.000051708783,0.00025830313,0.0000102038175,0.00021476766,0.00008897558,0.000048620546,0.00022359256],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020328112,0.0002358411,0.0033033763,0.0000170218,0.000060230224,0.0008410154,0.00031197685,0.00007055301,0.07149669,0.21618517,0.0037674834,0.7037086],"study_design_scores_gemma":[0.00036245442,0.000014889158,0.0058061825,0.000059643364,0.00000945226,0.0015286849,0.00018561773,0.30227193,0.66504747,0.013198193,0.011104707,0.00041076174],"about_ca_topic_score_codex":0.0000078651,"about_ca_topic_score_gemma":0.0000109537,"teacher_disagreement_score":0.70329785,"about_ca_system_score_codex":0.000021845493,"about_ca_system_score_gemma":0.000088186236,"threshold_uncertainty_score":0.999302},"labels":[],"label_agreement":null},{"id":"W3210530853","doi":"10.1109/icassp43922.2022.9746484","title":"A Comparison of Discrete and Soft Speech Units for Improved Voice Conversion","year":2022,"lang":"en","type":"article","venue":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":107,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ubisoft (Canada)","funders":"","keywords":"Computer science; Speech recognition","score_opus":0.07575626700609553,"score_gpt":0.3305673919311458,"score_spread":0.2548111249250503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3210530853","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13595666,0.0005758097,0.84633785,0.007157706,0.0022955514,0.0014085586,0.0015194983,0.0003415402,0.0044068326],"genre_scores_gemma":[0.9754838,0.000083964784,0.022382682,0.0006140259,0.00014844934,0.00008501425,0.000097576994,0.000030888612,0.0010736071],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99696743,0.0001546307,0.00068107387,0.0008330672,0.00095025037,0.00041357148],"domain_scores_gemma":[0.99755716,0.00055467227,0.00056709116,0.00028345615,0.00080755487,0.00023003793],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00077734276,0.00034638346,0.0005210258,0.00040374295,0.00062361243,0.00042067497,0.0009886975,0.00011589476,0.00047539469],"category_scores_gemma":[0.00028871253,0.000352157,0.00010029485,0.00044903124,0.00021683626,0.00042104704,0.00048011894,0.00059787085,0.0000055418523],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00088099233,0.00071231474,0.0005985901,0.0003119206,0.00022096136,0.00008678042,0.0012981017,0.00020941037,0.236731,0.0047963182,0.0063058753,0.74784774],"study_design_scores_gemma":[0.001331668,0.0008682678,0.00015000177,0.0001114045,0.0000694652,0.00012263308,0.0019026087,0.9682258,0.018899359,0.0040309913,0.0037717957,0.00051601283],"about_ca_topic_score_codex":0.000040327177,"about_ca_topic_score_gemma":0.000008437909,"teacher_disagreement_score":0.9680164,"about_ca_system_score_codex":0.00014331452,"about_ca_system_score_gemma":0.00031603672,"threshold_uncertainty_score":0.99989307},"labels":[],"label_agreement":null},{"id":"W3214993239","doi":"10.1121/10.0008538","title":"APhL aligner: A neural network forced-alignment system","year":2021,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Phone; Speech recognition; Interval (graph theory); Interpolation (computer graphics); Pronunciation; Boundary (topology); Artificial neural network; Point (geometry); TIMIT; Artificial intelligence; Acoustics; Hidden Markov model; Mathematics; Linguistics","score_opus":0.014738017954428346,"score_gpt":0.23123460596303078,"score_spread":0.21649658800860244,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3214993239","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035269645,0.00047451133,0.9815515,0.012810494,0.0007022114,0.000089339126,0.0000027620415,0.000026033644,0.0008161289],"genre_scores_gemma":[0.67696774,0.00027437523,0.31636176,0.005697555,0.00046804667,0.000001785732,1.9102004e-7,0.000013160647,0.00021541143],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981294,0.00036099885,0.00046713883,0.00011062014,0.0006588461,0.00027298662],"domain_scores_gemma":[0.9979938,0.0007094583,0.00047228512,0.00046687777,0.00025109627,0.00010645336],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00073603675,0.00012017437,0.00031889553,0.000009075716,0.00022748517,0.00005231161,0.0011577861,0.00005002862,0.000037383415],"category_scores_gemma":[0.0001180317,0.00006208409,0.00061097444,0.00045255967,0.00022010664,0.00010466252,0.0003745606,0.00025743782,0.0000076169226],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015904837,0.0005604012,0.00023964903,0.00025925096,0.0015584182,0.00007882263,0.003454757,0.058440965,0.030709408,0.0020406262,0.4299539,0.47254476],"study_design_scores_gemma":[0.00044057693,0.00018537094,0.0003814428,0.00022291146,0.00028335967,0.0010031175,0.0033717789,0.9802359,0.006780659,0.0015360151,0.005376695,0.00018222356],"about_ca_topic_score_codex":0.000009908046,"about_ca_topic_score_gemma":2.0539392e-7,"teacher_disagreement_score":0.9217949,"about_ca_system_score_codex":0.00007548607,"about_ca_system_score_gemma":0.00010831272,"threshold_uncertainty_score":0.25317156},"labels":[],"label_agreement":null},{"id":"W3217533145","doi":"10.1121/10.0008580","title":"Exploring the variable efficacy of Google speech-to-text with spontaneous bilingual speech in Cantonese and English","year":2021,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Context (archaeology); Variation (astronomy); Variable (mathematics); Matching (statistics); Speech recognition; Multilingualism; Natural language processing; Linguistics; Psychology; Mathematics; History; Statistics","score_opus":0.026358114819322445,"score_gpt":0.23888731842026484,"score_spread":0.2125292036009424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3217533145","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91004837,0.00018161998,0.08446567,0.0042776405,0.00030471236,0.00018124783,0.0000054469892,0.000013551014,0.00052172836],"genre_scores_gemma":[0.71208495,0.00041146248,0.2862418,0.0009970407,0.00015256724,0.0000013870783,1.112206e-7,0.000013403106,0.000097267846],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983392,0.00026191637,0.00043114353,0.00014580371,0.0005777304,0.00024423553],"domain_scores_gemma":[0.99660796,0.0021346929,0.00029582667,0.00045682327,0.00040547244,0.00009920921],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010239808,0.00013088554,0.00036124632,0.000029458892,0.00012286638,0.00004427142,0.00091078057,0.000034840272,0.000046384233],"category_scores_gemma":[0.001172344,0.00006175693,0.0001604114,0.00088247197,0.0003469435,0.00014369018,0.00034294263,0.00039828033,0.0000014574753],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00079412037,0.0012782777,0.0004997727,0.0001478802,0.00062745,0.0004443144,0.034117416,0.01142247,0.06129222,0.00021988763,0.0024566136,0.88669956],"study_design_scores_gemma":[0.010494458,0.0049787876,0.0448708,0.0043164645,0.0021872462,0.03356371,0.1272256,0.42214352,0.3217142,0.0067649507,0.019243248,0.0024970307],"about_ca_topic_score_codex":0.00015300888,"about_ca_topic_score_gemma":0.0000132284285,"teacher_disagreement_score":0.88420254,"about_ca_system_score_codex":0.00005246591,"about_ca_system_score_gemma":0.00030265344,"threshold_uncertainty_score":0.25183743},"labels":[],"label_agreement":null},{"id":"W4200004927","doi":"10.1109/pst52912.2021.9647775","title":"SegmentPerturb: Effective Black-Box Hidden Voice Attack on Commercial ASR Systems via Selective Deletion","year":2021,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Voice command device; Speech recognition; Voice activity detection; Speaker recognition; Black box; Control (management); Mobile device; Smartwatch; Human–computer interaction; Speech processing; Artificial intelligence; Embedded system; Operating system","score_opus":0.025661827251802424,"score_gpt":0.26884072239596746,"score_spread":0.24317889514416502,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200004927","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08636613,0.00009239225,0.823313,0.002317205,0.001577863,0.00090521557,0.000011451496,0.00058099243,0.084835716],"genre_scores_gemma":[0.98078334,0.000022067345,0.011763345,0.00294527,0.00033371992,0.00011590077,0.000017580309,0.00002446234,0.0039943405],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9978367,0.00053346046,0.00025026448,0.00060562184,0.00044415295,0.00032980007],"domain_scores_gemma":[0.9982411,0.00070123246,0.000091927104,0.00043402205,0.00038968428,0.00014203075],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00030086,0.0002233421,0.00028968602,0.00012173578,0.00019103712,0.00035648918,0.00036044122,0.00013405374,0.00011064924],"category_scores_gemma":[0.00015481359,0.0001990405,0.00013238046,0.00057822047,0.00004104003,0.00046299875,0.00012909221,0.00021274743,0.0015248633],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013650487,0.001218654,0.000997256,0.000120067816,0.00050349283,0.00032362418,0.0025013755,0.00016059399,0.013130443,0.018904598,0.06538232,0.89662105],"study_design_scores_gemma":[0.0039886134,0.0014388358,0.038950697,0.0004716605,0.00015242257,0.00054372975,0.0011324624,0.24006957,0.6694731,0.0017108154,0.039743014,0.0023250745],"about_ca_topic_score_codex":0.000112709866,"about_ca_topic_score_gemma":0.00008999171,"teacher_disagreement_score":0.89441717,"about_ca_system_score_codex":0.00024402316,"about_ca_system_score_gemma":0.00007658527,"threshold_uncertainty_score":0.99925256},"labels":[],"label_agreement":null},{"id":"W4200153536","doi":"10.31234/osf.io/y6gnh","title":"Intelligibility benefit for familiar voices does not depend on better discrimination of fundamental frequency or vocal tract length","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Timbre; Psychology; Formant; Vocal tract; Intelligibility (philosophy); Perception; Acoustics; Audiology; Cognitive psychology; Speech recognition; Vowel; Computer science; Musical","score_opus":0.06553322139946756,"score_gpt":0.31607531447158044,"score_spread":0.2505420930721129,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200153536","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7603296,0.000023032355,0.23296753,0.001608482,0.0012460789,0.0007725017,0.0002662193,0.0001295806,0.0026569786],"genre_scores_gemma":[0.86269027,0.00007811202,0.1359017,0.00059965503,0.00010435909,0.00012377411,0.00009771636,0.000017363143,0.00038705036],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9973227,0.00010095858,0.0006973825,0.0010653331,0.0005339323,0.00027972466],"domain_scores_gemma":[0.9975847,0.0008802719,0.00030737318,0.0008580699,0.00026799284,0.000101570935],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005060666,0.00035310982,0.0005194461,0.00019582348,0.00008890135,0.0003213436,0.00094226416,0.0002992335,0.00048578953],"category_scores_gemma":[0.00027105404,0.00023188956,0.00040851993,0.00011324974,0.0000674703,0.00041127778,0.00044929644,0.0003369147,0.000016851687],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010366418,0.0012343358,0.0012195591,0.00071262894,0.00014076116,0.000018284363,0.001230726,0.000015844547,0.0025998286,0.0051271045,0.00006326311,0.987534],"study_design_scores_gemma":[0.0008969951,0.0006527539,0.030005734,0.0008608987,0.00017084405,0.000020220148,0.0019258034,0.03497769,0.88339525,0.04542395,0.00035065674,0.001319214],"about_ca_topic_score_codex":0.00041804303,"about_ca_topic_score_gemma":0.0021108622,"teacher_disagreement_score":0.98621476,"about_ca_system_score_codex":0.00015311888,"about_ca_system_score_gemma":0.0001428726,"threshold_uncertainty_score":0.94561815},"labels":[],"label_agreement":null},{"id":"W4200300291","doi":"10.21105/joss.03958","title":"Phonemizer: Text to Phones Transcription for Multiple Languages in Python","year":2021,"lang":"en","type":"article","venue":"The Journal of Open Source Software","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":82,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Agence Nationale de la Recherche; Canadian Institute for Advanced Research; Microsoft Research","keywords":"Python (programming language); Computer science; Transcription (linguistics); Programming language; World Wide Web; Linguistics; Philosophy","score_opus":0.034780526084438636,"score_gpt":0.30247217448345226,"score_spread":0.2676916483990136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200300291","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18706933,0.00048241034,0.80658305,0.0050408235,0.00027546455,0.00032103749,0.000008833601,0.000033138018,0.00018594899],"genre_scores_gemma":[0.6572593,0.00009387298,0.3381392,0.0024676456,0.00016844446,0.000021011898,0.000002585846,0.000028062608,0.0018198668],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99895626,0.00019636798,0.00032304204,0.00013020438,0.00021961021,0.00017448931],"domain_scores_gemma":[0.99862206,0.00066030957,0.00014688763,0.00026058982,0.0002255154,0.000084638756],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010636464,0.00009584673,0.00023495535,0.000104454615,0.000112066075,0.00023955066,0.0011328657,0.000040902207,0.00009893067],"category_scores_gemma":[0.00075504597,0.000067493296,0.000110771354,0.00036091288,0.00001562704,0.00043162753,0.00015154333,0.0001371733,0.00002875751],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003523631,0.00023273488,0.0014351776,0.000033227865,0.000056295787,0.00007144406,0.016247386,0.0005805076,0.03742747,0.00006368713,0.00960903,0.9338907],"study_design_scores_gemma":[0.011999546,0.00077244133,0.028217798,0.0013898105,0.00017279795,0.0024657242,0.031218303,0.0051292754,0.6591315,0.005547997,0.2526922,0.001262589],"about_ca_topic_score_codex":0.000051153867,"about_ca_topic_score_gemma":0.000142308,"teacher_disagreement_score":0.9326281,"about_ca_system_score_codex":0.000039097464,"about_ca_system_score_gemma":0.00009127984,"threshold_uncertainty_score":0.2752297},"labels":[],"label_agreement":null},{"id":"W4200482297","doi":"10.1145/3494987","title":"SpeeChin","year":2021,"lang":"en","type":"article","venue":"Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Speech recognition; Session (web analytics); Convolutional neural network; Natural language processing; Syllable; Chin; Artificial intelligence; World Wide Web","score_opus":0.013344885097684268,"score_gpt":0.2456831710635254,"score_spread":0.23233828596584113,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200482297","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9769568,0.00042016024,0.000081440994,0.0057576303,0.00026328236,0.0002433352,0.0000040612435,0.0005429486,0.015730355],"genre_scores_gemma":[0.9784609,0.00037878484,0.020073837,0.0001917996,0.000017468288,0.00008539871,1.391984e-7,0.000010114025,0.0007815705],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989569,0.000009778609,0.00019853436,0.00040030674,0.00022029941,0.00021414443],"domain_scores_gemma":[0.9986998,0.00021987244,0.0001753212,0.0005988989,0.0002833457,0.000022764663],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001491977,0.00015476352,0.00022677281,0.0001348492,0.00014538267,0.00015332334,0.0019214193,0.00010883398,0.000018117384],"category_scores_gemma":[0.0021197165,0.00010658599,0.000098036886,0.0004842621,0.00014461644,0.00041281086,0.0021451726,0.00030623382,0.000018118475],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042037114,0.00026760163,0.0006633347,0.00007271338,0.00008390589,0.000012476044,0.00040458533,0.0000014700653,0.20798855,0.014810722,0.003499654,0.77215296],"study_design_scores_gemma":[0.0001264749,0.00014420558,0.00046539566,0.00020601272,0.000008130844,0.00009797884,0.0022902733,0.00015506659,0.9274625,0.06592895,0.0029919364,0.00012307198],"about_ca_topic_score_codex":0.0000064803735,"about_ca_topic_score_gemma":0.0000017734673,"teacher_disagreement_score":0.7720299,"about_ca_system_score_codex":0.000035588997,"about_ca_system_score_gemma":0.000027538927,"threshold_uncertainty_score":0.43464506},"labels":[],"label_agreement":null},{"id":"W4205101752","doi":"10.18280/ts.380623","title":"Dialect Identification in Telugu Language Speech Utterance Using Modified Features with Deep Neural Network","year":2021,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Telugu; Computer science; Mel-frequency cepstrum; Hidden Markov model; Artificial neural network; Artificial intelligence; Identification (biology); Speech recognition; Language identification; Utterance; Natural language processing; Feature (linguistics); Feature extraction; Natural language; Linguistics","score_opus":0.020629811216508243,"score_gpt":0.245858799548895,"score_spread":0.22522898833238675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205101752","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7182466,0.0002712774,0.27991235,0.00039319706,0.00017216214,0.00019383045,0.000002865451,0.000086497756,0.00072124216],"genre_scores_gemma":[0.96460885,0.0000055690725,0.034538116,0.00055173936,0.00017441782,0.000018251412,0.000012540606,0.000010397915,0.0000801261],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99860173,0.00015407984,0.00024700828,0.00038283653,0.00032179858,0.00029254847],"domain_scores_gemma":[0.9994494,0.000084859006,0.000086679625,0.00025050095,0.000068161105,0.00006042762],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002588865,0.00014089415,0.00016428907,0.00008636328,0.00010013215,0.00025800418,0.00028813278,0.000042892305,0.00016850984],"category_scores_gemma":[0.000016119595,0.00012806088,0.00005303559,0.00056625786,0.000025206624,0.0003333361,0.000046424724,0.00012440908,0.000011662135],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014413265,0.0004914904,0.0061914725,0.0000704844,0.00010111205,0.0017100363,0.004056126,0.04419919,0.123983644,0.0023803827,0.00058562914,0.8160863],"study_design_scores_gemma":[0.00177118,0.00008441979,0.09227634,0.0001486814,0.000037536058,0.00034697092,0.00036941748,0.77289385,0.13049492,0.00081554055,0.000120014025,0.0006410994],"about_ca_topic_score_codex":0.00004310178,"about_ca_topic_score_gemma":0.00028976754,"teacher_disagreement_score":0.8154452,"about_ca_system_score_codex":0.00004509094,"about_ca_system_score_gemma":0.000041609783,"threshold_uncertainty_score":0.52221715},"labels":[],"label_agreement":null},{"id":"W4210486131","doi":"10.1109/asru51503.2021.9687877","title":"Hybrid Network with Multi-Level Global-Local Statistics Pooling for Robust Text-Independent Speaker Recognition","year":2021,"lang":"en","type":"article","venue":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Pooling; NIST; Speech recognition; Speaker recognition; Context (archaeology); Artificial intelligence; Set (abstract data type); Speaker diarisation; Hybrid system; Pattern recognition (psychology); Machine learning","score_opus":0.14976837305959667,"score_gpt":0.283479670430947,"score_spread":0.13371129737135035,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210486131","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005572857,0.00018637002,0.98895556,0.00074777775,0.0012232619,0.0008257079,0.00061528705,0.00039316574,0.0014800287],"genre_scores_gemma":[0.050737433,0.0003070811,0.9462575,0.0010078149,0.0003842754,0.00012802646,0.0006258152,0.000078270954,0.00047379333],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9957984,0.00030443133,0.00088876515,0.0012278646,0.0007803403,0.0010002134],"domain_scores_gemma":[0.9967382,0.0012312281,0.0004328483,0.00054728676,0.0005966197,0.000453826],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.000938574,0.0006010835,0.0007138127,0.0002188092,0.00074992183,0.0010701999,0.0003517642,0.00026824413,0.0008274872],"category_scores_gemma":[0.00039361732,0.00059424277,0.0002066345,0.0009665541,0.00019384599,0.000792545,0.0001303599,0.00038704972,0.0002045372],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007845852,0.00031726304,0.000056377066,0.00019213418,0.0003239382,0.0005049088,0.00016803326,0.00026458042,0.000057193378,0.0010905248,0.006517045,0.9904295],"study_design_scores_gemma":[0.006788206,0.00029013536,0.0005687224,0.0027495625,0.00060085114,0.002985824,0.0054189772,0.84751827,0.0058046742,0.124577776,0.0005071507,0.0021898802],"about_ca_topic_score_codex":0.000018651073,"about_ca_topic_score_gemma":0.00046362917,"teacher_disagreement_score":0.98823965,"about_ca_system_score_codex":0.0007081748,"about_ca_system_score_gemma":0.000357952,"threshold_uncertainty_score":0.9999668},"labels":[],"label_agreement":null},{"id":"W4213101158","doi":"10.5220/0010816800003122","title":"Dynamic Latent Scale for GAN Inversion","year":2022,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Inversion (geology); Computer science; Scale (ratio); Geology; Physics; Geomorphology","score_opus":0.018830950667661762,"score_gpt":0.23235755396200458,"score_spread":0.2135266032943428,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4213101158","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.082076356,0.000015938465,0.88986236,0.006624822,0.0007055512,0.00030450695,0.000010602858,0.00033234217,0.020067554],"genre_scores_gemma":[0.84320635,0.0000034413772,0.14724545,0.0021908085,0.000008050173,0.000071382965,0.000006625494,0.00000518817,0.007262715],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995449,0.00002169469,0.000062712395,0.00014735,0.00012394367,0.000099402794],"domain_scores_gemma":[0.9997422,0.0000409956,0.000017324783,0.000145239,0.000017895738,0.000036340363],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012677367,0.000036284913,0.000045814624,0.00005511978,0.00018088252,0.00002972356,0.00028277872,0.000009098941,0.00062472123],"category_scores_gemma":[0.000006551587,0.000033400054,0.00004975769,0.00012344935,0.000005955673,0.000083304316,0.000120429024,0.000032051936,0.00006340858],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021858468,0.0002562739,0.0005816314,0.00001557293,0.000016618502,0.000010434193,0.0005469654,0.00011325349,0.0069121392,0.012411282,0.047555167,0.9315588],"study_design_scores_gemma":[0.00037018306,0.000113560505,0.000696887,0.0000020362377,0.0000037251634,0.000015128204,0.0001685102,0.9274963,0.009251659,0.0060745114,0.05566003,0.00014744031],"about_ca_topic_score_codex":0.00000778439,"about_ca_topic_score_gemma":0.00000891129,"teacher_disagreement_score":0.9314114,"about_ca_system_score_codex":0.000042293683,"about_ca_system_score_gemma":0.00001546134,"threshold_uncertainty_score":0.68402594},"labels":[],"label_agreement":null},{"id":"W4213234291","doi":"10.1186/s13634-022-00844-9","title":"Free resources for forced phonetic alignment in Brazilian Portuguese based on Kaldi toolkit","year":2022,"lang":"en","type":"article","venue":"EURASIP Journal on Advances in Signal Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Pró-Reitoria de Pesquisa e Pós-Graduação, Universidade Federal do Pará; Nvidia; Universidade Federal do Pará; Fundação Amazônia Paraense de Amparo à Pesquisa; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Computer science; Scripting language; Speech recognition; Phone; Portuguese; Natural language processing; Process (computing); Intersection (aeronautics); Artificial intelligence; Brazilian Portuguese; Linguistics; Programming language","score_opus":0.017650564225092733,"score_gpt":0.2759942747064355,"score_spread":0.25834371048134275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4213234291","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20697823,0.010541034,0.7425965,0.01260095,0.0021189821,0.0018960182,0.00007222936,0.00034392063,0.022852125],"genre_scores_gemma":[0.9638351,0.00006829594,0.031138591,0.0045080055,0.00014787419,0.00012227891,0.0000023587809,0.00003083922,0.00014665553],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971777,0.00028605835,0.00063941494,0.00048485704,0.00092513004,0.00048680423],"domain_scores_gemma":[0.9986067,0.0005241502,0.00038503946,0.00026808196,0.00006860231,0.00014745124],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001434288,0.00023632361,0.0003036327,0.0006530767,0.00044189152,0.0002390659,0.0011561546,0.00003995706,0.00017430737],"category_scores_gemma":[0.00019974263,0.00021906864,0.00012394792,0.0007433303,0.000045126704,0.0007879059,0.00011732332,0.00057681155,0.0000048091297],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044602758,0.0003693503,0.00036501558,0.00004393082,0.0000042071474,0.00029066496,0.00057515124,0.03720433,0.0008539603,0.00022417624,0.0002658477,0.9593573],"study_design_scores_gemma":[0.011058547,0.004407191,0.00590594,0.0019894836,0.00002257544,0.0004164276,0.0024379038,0.8165523,0.012238708,0.052578684,0.09071882,0.0016734562],"about_ca_topic_score_codex":0.0000017785497,"about_ca_topic_score_gemma":0.000008107282,"teacher_disagreement_score":0.95768386,"about_ca_system_score_codex":0.0003365684,"about_ca_system_score_gemma":0.0001572058,"threshold_uncertainty_score":0.89333594},"labels":[],"label_agreement":null},{"id":"W4220982091","doi":"10.1080/15434303.2022.2038172","title":"Investigating the Effects of Task Type and Linguistic Background on Accuracy in Automated Speech Recognition Systems: Implications for Use in Language Assessment of Young Learners","year":2022,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Christian Studies; University of Toronto","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Task (project management); Computer science; Natural language processing; Artificial intelligence; Meaning (existential); Task analysis; Language proficiency; Test (biology); Psychology; Speech recognition","score_opus":0.03373161378752211,"score_gpt":0.33916975486964335,"score_spread":0.30543814108212125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220982091","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9951417,0.000090349524,0.0030441184,0.00011552484,0.00024281653,0.00095241255,0.000050214447,0.000084512976,0.0002783866],"genre_scores_gemma":[0.9772757,0.0000055446485,0.022194156,0.00009742351,0.00002048904,0.00030248833,0.00007095152,0.000013802397,0.00001940587],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9983001,0.00048524424,0.00044690174,0.0003127513,0.00025158952,0.00020342355],"domain_scores_gemma":[0.9968898,0.0022623956,0.00032458946,0.0003838889,0.000097594326,0.000041679457],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00079018733,0.0001376777,0.00025781782,0.00026324554,0.00009964306,0.00011978824,0.00031342683,0.00004047323,0.000007160274],"category_scores_gemma":[0.0004106816,0.00012087931,0.000041517083,0.000671074,0.00003731088,0.00021870252,0.00005566734,0.00020942511,7.998246e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007194033,0.0021771556,0.09075653,0.0023646506,0.00028932068,0.00021007737,0.07732934,0.0003813506,0.23979762,0.01711576,0.00050451874,0.56900173],"study_design_scores_gemma":[0.0038118262,0.003415609,0.5500887,0.0010225836,0.00010740898,0.00008704417,0.05579581,0.38040322,0.003116983,0.0013612872,0.00004726583,0.00074224157],"about_ca_topic_score_codex":0.0011615376,"about_ca_topic_score_gemma":0.00026694938,"teacher_disagreement_score":0.5682595,"about_ca_system_score_codex":0.00014996201,"about_ca_system_score_gemma":0.00013464934,"threshold_uncertainty_score":0.49293151},"labels":[],"label_agreement":null},{"id":"W4221140961","doi":"10.1109/jstsp.2022.3200909","title":"Are Discrete Units Necessary for Spoken Language Modeling?","year":2022,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Signal Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Grand Équipement National De Calcul Intensif; Agence Nationale de la Recherche; École des Hautes Etudes en Sciences Sociales; Canadian Institute for Advanced Research","keywords":"Computer science; Spoken language; Natural language processing; Linguistics","score_opus":0.04163231579509832,"score_gpt":0.2834469320030519,"score_spread":0.24181461620795355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221140961","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33952415,0.0007416249,0.6578439,0.0011735717,0.00027703546,0.00012471735,0.00000688571,0.00004024116,0.00026790658],"genre_scores_gemma":[0.9736285,0.000008380566,0.025428833,0.00049079495,0.0003039247,0.000010214475,0.0000014136059,0.000012853874,0.00011505809],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99864805,0.000111233596,0.0004415649,0.00016694819,0.0003992718,0.0002329108],"domain_scores_gemma":[0.99876004,0.00009737162,0.00047052113,0.00009339083,0.00050949043,0.00006919086],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054336793,0.00011096732,0.00023238701,0.0003178404,0.00022773705,0.00013190476,0.00063818356,0.000042722615,0.000028037795],"category_scores_gemma":[0.00013089755,0.00010410938,0.00005736223,0.0010704052,0.000013735715,0.00048231918,0.00005841618,0.00043396745,4.916855e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003968725,0.0005004467,0.0022516276,0.00034721728,0.00011587838,0.0009953964,0.009654868,0.05828054,0.020545416,0.00049015856,0.0017845454,0.90463704],"study_design_scores_gemma":[0.0010207498,0.00021415288,0.00023982872,0.00020408415,0.00002311026,0.00037136517,0.0018064993,0.9791167,0.010494369,0.0053791916,0.0008444281,0.00028552502],"about_ca_topic_score_codex":0.0000047977956,"about_ca_topic_score_gemma":0.0000070528677,"teacher_disagreement_score":0.92083615,"about_ca_system_score_codex":0.00010971396,"about_ca_system_score_gemma":0.00031045752,"threshold_uncertainty_score":0.42454574},"labels":[],"label_agreement":null},{"id":"W4224917505","doi":"10.1109/icassp43922.2022.9747452","title":"Robust Self-Supervised Speaker Representation Learning Via Instance Mix Regularization","year":2022,"lang":"en","type":"article","venue":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Embedding; Regularization (linguistics); Speech recognition; Feature learning; Utterance; Artificial intelligence; Supervised learning; Speaker recognition; Pattern recognition (psychology); Machine learning; Artificial neural network","score_opus":0.05941694244909695,"score_gpt":0.2801079894117903,"score_spread":0.22069104696269337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224917505","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029580392,0.00015965827,0.9476438,0.0039611957,0.0015657067,0.0005288467,0.00008191281,0.00064307643,0.015835425],"genre_scores_gemma":[0.9340276,0.00019245353,0.060250096,0.0010543833,0.00036574848,0.00012980668,0.00017312988,0.00005411437,0.0037526654],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99533474,0.00041992308,0.0007155594,0.001168109,0.0018687758,0.0004928759],"domain_scores_gemma":[0.99792874,0.00024971765,0.0005216041,0.0003944318,0.0006693169,0.00023621871],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00091478275,0.00040230318,0.00038850584,0.00053362374,0.0010754177,0.0009464646,0.0011707876,0.0001342936,0.002364568],"category_scores_gemma":[0.00021853611,0.00044321347,0.00013180154,0.0008233876,0.00011757842,0.00091701763,0.0004273545,0.0010287036,0.00006444933],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039849692,0.0011069631,0.0011524862,0.00012946811,0.00026181937,0.00069633935,0.0022401884,0.013673038,0.12615308,0.010416442,0.0042868485,0.8394848],"study_design_scores_gemma":[0.0008424856,0.00027492354,0.0003683492,0.000076074415,0.000043404107,0.00024274454,0.00095018523,0.98536986,0.0035988996,0.0056501273,0.0020120442,0.0005708759],"about_ca_topic_score_codex":0.000030342482,"about_ca_topic_score_gemma":0.0000068727663,"teacher_disagreement_score":0.97169685,"about_ca_system_score_codex":0.00038038575,"about_ca_system_score_gemma":0.00031694627,"threshold_uncertainty_score":0.99980193},"labels":[],"label_agreement":null},{"id":"W4229455725","doi":"10.1121/10.0010882","title":"Evaluating the accuracy of forced alignment across Mandarin varieties","year":2022,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mandarin Chinese; Variety (cybernetics); Computer science; Phone; Variation (astronomy); Speech recognition; Beijing; Artificial intelligence; Acoustics; Linguistics; History; Physics; Philosophy","score_opus":0.04716307972668853,"score_gpt":0.33734243633737404,"score_spread":0.2901793566106855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4229455725","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09110521,0.00023503107,0.88616204,0.021494832,0.00046572794,0.00024711757,0.000017721368,0.000013983802,0.00025836006],"genre_scores_gemma":[0.902895,0.00011709658,0.09400735,0.002750717,0.000069197944,0.0000051969823,1.325573e-7,0.000008032568,0.00014727355],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99741745,0.0005588005,0.00050964725,0.00008938736,0.0012065609,0.0002181531],"domain_scores_gemma":[0.99596864,0.0023917195,0.00091593975,0.0004768459,0.00020344729,0.000043389322],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030355365,0.00010016088,0.00025379233,0.000009697513,0.0007115928,0.000040048544,0.0021267256,0.000023095274,0.00015499206],"category_scores_gemma":[0.00062421546,0.000046154084,0.00046637072,0.00035026408,0.00051771605,0.000100075384,0.0011071771,0.0004157621,0.0000013922953],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039929253,0.00052159594,0.00011556821,0.00007276169,0.0008384274,0.0000023416817,0.036028326,0.046250053,0.07608048,0.00042060323,0.03077633,0.8084942],"study_design_scores_gemma":[0.00085635926,0.001250362,0.0013933654,0.000056320383,0.00028746238,0.00022662383,0.025707647,0.93580025,0.017806597,0.0119538745,0.0044650882,0.00019604062],"about_ca_topic_score_codex":0.000042350188,"about_ca_topic_score_gemma":1.7240276e-7,"teacher_disagreement_score":0.8895502,"about_ca_system_score_codex":0.000073014424,"about_ca_system_score_gemma":0.0001302842,"threshold_uncertainty_score":0.54730684},"labels":[],"label_agreement":null},{"id":"W4229458071","doi":"10.18280/ts.390235","title":"Speaker Identification Based on Physical Variation of Speech Signal","year":2022,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mel-frequency cepstrum; Speech recognition; Cepstrum; Speaker recognition; Computer science; Variation (astronomy); Identification (biology); Classifier (UML); Pattern recognition (psychology); Feature (linguistics); SIGNAL (programming language); Artificial intelligence; Feature extraction","score_opus":0.020835860932413106,"score_gpt":0.23737903835082555,"score_spread":0.21654317741841245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4229458071","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2192411,0.0000043504283,0.77469844,0.0014796722,0.00027729626,0.0004200148,0.000045981855,0.0001458372,0.003687328],"genre_scores_gemma":[0.99257565,2.8901894e-7,0.006739474,0.00038209208,0.00011986846,0.00006179355,0.0000249676,0.000008117753,0.000087728324],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981947,0.00020914157,0.00029085175,0.0003172221,0.00083049375,0.00015762309],"domain_scores_gemma":[0.99927413,0.00016647467,0.00017770685,0.0002531877,0.00007581242,0.00005269976],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005896373,0.000111357724,0.00013991202,0.0001846619,0.0001622934,0.000060868442,0.00043793218,0.000018634157,0.0022839198],"category_scores_gemma":[0.000013705078,0.0001139283,0.00011447531,0.00038267157,0.000022045975,0.00017396227,0.000063626285,0.00010699548,0.00007242501],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022191647,0.0029079963,0.0004393738,0.000048149053,0.000093694565,0.000044018005,0.00222121,0.013363827,0.28624162,0.040890884,0.0024106887,0.6511166],"study_design_scores_gemma":[0.0008020298,0.0003968882,0.019715618,0.00001066211,0.000023374922,0.0000055750784,0.000058667883,0.8881187,0.08661926,0.0025891957,0.0014486761,0.00021139273],"about_ca_topic_score_codex":0.000010726515,"about_ca_topic_score_gemma":7.686022e-7,"teacher_disagreement_score":0.87475485,"about_ca_system_score_codex":0.000085455256,"about_ca_system_score_gemma":0.000059995265,"threshold_uncertainty_score":0.99862814},"labels":[],"label_agreement":null},{"id":"W4230248116","doi":"10.1007/978-1-4899-7502-7_984-1","title":"Privacy-Preserving Speech Recognition","year":2021,"lang":"en","type":"book-chapter","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Computer science; Biometrics; Cloud computing; Internet privacy; Authentication (law); Computer security; Information privacy; Process (computing); World Wide Web","score_opus":0.059787939742645575,"score_gpt":0.24620604243606511,"score_spread":0.18641810269341955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4230248116","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000012092297,0.00018758157,0.034394536,0.0013027263,0.00056502374,0.00016902357,0.0000122969595,0.00042187903,0.96293485],"genre_scores_gemma":[0.000018942046,0.0003143174,0.24670972,0.001194604,0.00023389005,0.000007969222,0.00006371335,0.000036343485,0.7514205],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99810123,0.000032507363,0.00037232807,0.0007365836,0.0004974521,0.0002598678],"domain_scores_gemma":[0.9980369,0.00018451443,0.0001660653,0.0011537762,0.00031130892,0.000147408],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00022533012,0.00032068614,0.00036109102,0.00023878954,0.000099555655,0.0003663286,0.0012079186,0.00035490136,0.021157706],"category_scores_gemma":[0.00014852853,0.00031881235,0.00027204538,0.00007439639,0.00002808408,0.00042339522,0.0009110886,0.00034308335,0.004264542],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000012693947,0.000014723625,5.8673436e-7,0.000026727641,0.000049306596,0.00022625644,0.000021594884,2.1298202e-8,0.00005544283,0.046335045,0.026085287,0.92718375],"study_design_scores_gemma":[0.00020163694,0.000032644908,0.0000088699935,0.00046660213,0.00003858696,0.00026899486,0.000010484823,0.00084113615,0.010840724,0.21605995,0.77039146,0.0008389353],"about_ca_topic_score_codex":0.000011713117,"about_ca_topic_score_gemma":0.000023407212,"teacher_disagreement_score":0.9263448,"about_ca_system_score_codex":0.0000688478,"about_ca_system_score_gemma":0.00012581424,"threshold_uncertainty_score":0.9999264},"labels":[],"label_agreement":null},{"id":"W4231504173","doi":"10.31234/osf.io/y8xcf","title":"Mixed-effects design analysis for experimental phonetics","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Statistical power; Sample size determination; Sign (mathematics); Phonetics; Null hypothesis; Magnitude (astronomy); Type I and type II errors; Statistics; Value (mathematics); Econometrics; Null (SQL); Sample (material); Computer science; Mathematics; Psychology; Linguistics; Data mining","score_opus":0.09505999670829285,"score_gpt":0.3023379607484315,"score_spread":0.20727796404013865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4231504173","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025058456,0.00013776784,0.9925811,0.000104907755,0.0012240694,0.00068370067,0.000008046145,0.00026992595,0.0024845793],"genre_scores_gemma":[0.16557583,0.000011340296,0.8329081,0.00032592483,0.00014636488,0.00032902777,0.000016078742,0.00001387869,0.000673462],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983174,0.00014287826,0.00026261815,0.0007311874,0.00026930374,0.0002765626],"domain_scores_gemma":[0.9982299,0.0004945315,0.00013521245,0.0008634897,0.00014847792,0.00012837663],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003650118,0.0002616696,0.0004239798,0.00036616085,0.000096360534,0.00033318947,0.0010538348,0.0002274702,0.0002542818],"category_scores_gemma":[0.00008569764,0.00023525127,0.0004920841,0.0003490251,0.000047671776,0.000077462435,0.00069530687,0.00010790281,0.00016514334],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001953241,0.0034845723,0.0007030005,0.0007471221,0.015602991,0.000111111876,0.0046352344,0.0023218687,0.017498791,0.03145586,0.25036314,0.67288095],"study_design_scores_gemma":[0.00022884629,0.00012857154,0.00027234064,0.000022669901,0.0002548775,0.00000218438,0.000025677671,0.3372299,0.6556046,0.0051328107,0.0006855221,0.00041198288],"about_ca_topic_score_codex":0.000017204207,"about_ca_topic_score_gemma":0.000004518895,"teacher_disagreement_score":0.672469,"about_ca_system_score_codex":0.000066399574,"about_ca_system_score_gemma":0.00006924298,"threshold_uncertainty_score":0.9593268},"labels":[],"label_agreement":null},{"id":"W4233027766","doi":"10.1109/tasl.2013.2273045","title":"IEEE Transactions on Audio, Speech, and Language Processing publication information","year":2013,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"University of Texas at Dallas; Korea Advanced Institute of Science and Technology; Hong Kong Polytechnic University; Tsinghua University; Aalborg Universitet; Nanyang Technological University; York University; Ben-Gurion University of the Negev; Bar-Ilan University; University of Cambridge; National Cheng Kung University; Institut national de recherche en informatique et en automatique (INRIA); Ohio State University","keywords":"Computer science; Speech recognition; Natural language processing","score_opus":0.012180034270205904,"score_gpt":0.2406691442479533,"score_spread":0.2284891099777474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4233027766","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045905553,0.0005135534,0.9475708,0.0018184653,0.00024386923,0.00058556284,0.000028309358,0.0006278528,0.0027060343],"genre_scores_gemma":[0.9486502,0.0001504681,0.0477062,0.0020916567,0.00007669062,0.00017021394,0.000010636242,0.000036286263,0.0011076741],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9977298,0.00010394158,0.000531999,0.00058599416,0.00053530646,0.0005130059],"domain_scores_gemma":[0.9985932,0.0001276297,0.00026324997,0.00041072338,0.0002962293,0.00030897162],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00039936526,0.0003984837,0.00033363886,0.00068736734,0.0008028483,0.0014848105,0.0003480343,0.00022786786,0.00036773278],"category_scores_gemma":[0.00003041248,0.00036834346,0.0001079848,0.0008481229,0.00012242595,0.0041626403,0.0000026263908,0.0005241837,0.00025684913],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001950613,0.00013372407,0.000002786381,0.00015275767,0.00002254669,0.000010063671,0.004583503,0.000038381775,0.004576696,0.0000065530594,0.00014392391,0.99030954],"study_design_scores_gemma":[0.0026634114,0.00043388805,0.0005070667,0.0009202305,0.0001870219,0.0007385857,0.008773044,0.23058556,0.75132775,0.00029228567,0.0017453419,0.0018257932],"about_ca_topic_score_codex":0.00018324601,"about_ca_topic_score_gemma":0.000084741216,"teacher_disagreement_score":0.9884838,"about_ca_system_score_codex":0.00010559632,"about_ca_system_score_gemma":0.00013614271,"threshold_uncertainty_score":0.99987686},"labels":[],"label_agreement":null},{"id":"W4233734240","doi":"10.3390/cryptography1020016","title":"A Text-Independent Speaker Authentication System for Mobile Devices","year":2017,"lang":"en","type":"article","venue":"Cryptography","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Computer science; Authentication (law); Classifier (UML); Biometrics; Naive Bayes classifier; Reliability (semiconductor); Mobile device; Artificial intelligence; Speaker recognition; Speech recognition; Data mining; Computer security; Support vector machine; World Wide Web","score_opus":0.023812572285493803,"score_gpt":0.274783175883733,"score_spread":0.2509706035982392,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4233734240","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06833901,0.00024900574,0.911963,0.0005025683,0.0012548587,0.0009533829,0.000022500588,0.00045551418,0.01626017],"genre_scores_gemma":[0.93273574,0.0000063878883,0.066772416,0.000074846386,0.00009169519,0.0002695838,0.0000035384799,0.000009252578,0.000036530768],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990483,0.000026551816,0.00017811194,0.00033511955,0.00020072337,0.00021119021],"domain_scores_gemma":[0.99862987,0.00007302745,0.00019357743,0.0008822311,0.00012776941,0.00009354928],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028139495,0.0001125893,0.00013717024,0.00016205573,0.0005392512,0.0006952565,0.0009958603,0.00006111263,0.00002669345],"category_scores_gemma":[0.000035855956,0.00009957747,0.00019622067,0.00010175503,0.00005469842,0.00044259566,0.000095769545,0.00004494554,0.00014054627],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034695997,0.00026718332,0.008887945,0.00025664846,0.0002832719,0.000012738924,0.00088442315,0.0000016629999,0.0044250945,0.24846032,0.0020909351,0.7343951],"study_design_scores_gemma":[0.0057151103,0.0009360172,0.30225864,0.00097330613,0.00051466917,0.00016173958,0.0028752321,0.070889175,0.13344622,0.051744185,0.4274595,0.0030262019],"about_ca_topic_score_codex":0.000011734927,"about_ca_topic_score_gemma":0.000014016775,"teacher_disagreement_score":0.86439675,"about_ca_system_score_codex":0.000014347975,"about_ca_system_score_gemma":0.00002046825,"threshold_uncertainty_score":0.67043746},"labels":[],"label_agreement":null},{"id":"W4233773279","doi":"10.1007/978-0-387-39940-9_2076","title":"Audio Parsing","year":2009,"lang":"en","type":"book-chapter","venue":"Encyclopedia of Database Systems","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Parsing; Natural language processing","score_opus":0.02394974643188112,"score_gpt":0.2335670174814805,"score_spread":0.2096172710495994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4233773279","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000061382207,0.002184073,0.025743138,0.00009208331,0.0017902885,0.0003855217,0.00034080978,0.000193169,0.9692648],"genre_scores_gemma":[0.00039553,0.0049401326,0.04382122,0.00018761565,0.0013520145,0.000025233658,0.00040169992,0.000086349944,0.9487902],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975074,0.00006149901,0.0007730332,0.00065730675,0.00070036825,0.0003003858],"domain_scores_gemma":[0.9974109,0.00021116118,0.00057244743,0.0014560807,0.0001639613,0.00018547206],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004682751,0.00039419517,0.0007004977,0.00034934844,0.00007745903,0.00008694258,0.0010272919,0.000249918,0.00019527611],"category_scores_gemma":[0.000079118865,0.00037974643,0.00021258107,0.00008170213,0.000057688932,0.00043209037,0.00020838324,0.00029980775,0.0006447082],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009834652,0.000076571436,0.000010938284,0.0004513187,0.00015243718,0.00036557575,0.0001906164,0.000003822983,0.00007495206,0.36195433,0.09532349,0.5413861],"study_design_scores_gemma":[0.00017589761,0.000051775685,0.000010732616,0.001234346,0.000047403366,0.000092487375,0.000010526669,0.0004735632,0.00008637047,0.0015327822,0.9957911,0.0004930634],"about_ca_topic_score_codex":0.00004509868,"about_ca_topic_score_gemma":0.00000828745,"teacher_disagreement_score":0.9004676,"about_ca_system_score_codex":0.00006669801,"about_ca_system_score_gemma":0.00018781004,"threshold_uncertainty_score":0.9998655},"labels":[],"label_agreement":null},{"id":"W4236361712","doi":"10.1121/1.3654817","title":"Perception of speaker sex in children's voices","year":2011,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Sentence; Psychology; Perception; Context (archaeology); Phrase; Age groups; Audiology; Linguistics; Medicine; Demography","score_opus":0.01817659713404111,"score_gpt":0.2361441229514645,"score_spread":0.2179675258174234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4236361712","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45237827,0.00007505108,0.5442756,0.0019992788,0.00014037258,0.00011286716,0.0000029204682,0.000009874115,0.0010057683],"genre_scores_gemma":[0.83369946,0.00019764587,0.16546395,0.0005606141,0.000044858847,2.6720423e-7,4.262008e-8,0.0000038236294,0.000029347828],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9989291,0.00016386229,0.0003582219,0.000066397355,0.0003534431,0.00012900533],"domain_scores_gemma":[0.9989798,0.00021375837,0.00040694268,0.00025214482,0.000105438696,0.00004188994],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006266615,0.00007479707,0.00021353355,0.000023920491,0.00004871944,0.00000787384,0.0009536241,0.00004090971,0.00013293487],"category_scores_gemma":[0.000095534066,0.00003823837,0.00027747493,0.0002702471,0.00034225493,0.00013375586,0.00014605379,0.00022402604,0.000005856467],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001782961,0.0014457016,0.034743328,0.000059359467,0.00054402545,0.0000025112852,0.028151613,0.000485539,0.04336838,0.0000922005,0.014363358,0.8765657],"study_design_scores_gemma":[0.0011744669,0.0007771892,0.78983593,0.0002643129,0.00032169002,0.0003699209,0.014777441,0.16797897,0.016650071,0.0071775503,0.00031359287,0.00035888483],"about_ca_topic_score_codex":0.00010528874,"about_ca_topic_score_gemma":3.9521996e-7,"teacher_disagreement_score":0.8762068,"about_ca_system_score_codex":0.000023630724,"about_ca_system_score_gemma":0.0000402843,"threshold_uncertainty_score":0.17720868},"labels":[],"label_agreement":null},{"id":"W4236397392","doi":"10.1145/1979742.1979724","title":"Performance","year":2011,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Emily Carr University of Art and Design; University of British Columbia","funders":"","keywords":"Computer science","score_opus":0.06481581633554469,"score_gpt":0.20672975120550138,"score_spread":0.14191393486995668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4236397392","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04830136,0.0000020029256,0.117877565,0.00005490779,0.00008798082,0.000014871367,3.125748e-8,0.00014806051,0.8335132],"genre_scores_gemma":[0.7550647,0.0000045985703,0.24264725,0.00035586496,0.0000066033604,0.0000020458926,3.1337787e-8,9.490576e-7,0.0019179443],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99978244,0.0000048177776,0.00003688589,0.000068451154,0.000045845773,0.000061550236],"domain_scores_gemma":[0.99981266,0.000006187853,0.0000069011157,0.00013475522,0.00001381679,0.00002565205],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000045933633,0.000022775243,0.000022874163,0.000023302233,0.000022026565,0.000011285465,0.000214506,0.000009468838,0.0011064174],"category_scores_gemma":[0.000003989754,0.000017353193,0.0000126486875,0.00006725205,0.000006202702,0.00018953923,0.000029887542,0.000014131003,0.0013824465],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.275072e-7,0.000021053267,0.0022628405,0.0000011368093,0.0000020176751,0.000002638277,0.00020622135,1.03786295e-8,0.00008157801,0.031986967,0.0009699254,0.96446496],"study_design_scores_gemma":[0.0003955601,0.00018357126,0.29059595,0.000016328635,0.0000046086307,0.00011636852,0.00008105036,0.11455386,0.5489738,0.009273291,0.035250086,0.00055556156],"about_ca_topic_score_codex":0.0000042222464,"about_ca_topic_score_gemma":7.092813e-7,"teacher_disagreement_score":0.96390945,"about_ca_system_score_codex":0.000002229418,"about_ca_system_score_gemma":0.0000053480862,"threshold_uncertainty_score":0.9998067},"labels":[],"label_agreement":null},{"id":"W4236464389","doi":"10.1109/tasl.2013.2273049","title":"IEEE Transactions on Audio, Speech, and Language Processing publication information","year":2013,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"University of Texas at Dallas; Korea Advanced Institute of Science and Technology; Hong Kong Polytechnic University; Tsinghua University; Aalborg Universitet; Nanyang Technological University; York University; Ben-Gurion University of the Negev; Bar-Ilan University; University of Cambridge; National Cheng Kung University; Institut national de recherche en informatique et en automatique (INRIA); Ohio State University","keywords":"Computer science; Speech recognition; Audio mining; Speech processing; Natural language processing; Voice activity detection","score_opus":0.012180034270205904,"score_gpt":0.2406691442479533,"score_spread":0.2284891099777474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4236464389","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045905553,0.0005135534,0.9475708,0.0018184653,0.00024386923,0.00058556284,0.000028309358,0.0006278528,0.0027060343],"genre_scores_gemma":[0.9486502,0.0001504681,0.0477062,0.0020916567,0.00007669062,0.00017021394,0.000010636242,0.000036286263,0.0011076741],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9977298,0.00010394158,0.000531999,0.00058599416,0.00053530646,0.0005130059],"domain_scores_gemma":[0.9985932,0.0001276297,0.00026324997,0.00041072338,0.0002962293,0.00030897162],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00039936526,0.0003984837,0.00033363886,0.00068736734,0.0008028483,0.0014848105,0.0003480343,0.00022786786,0.00036773278],"category_scores_gemma":[0.00003041248,0.00036834346,0.0001079848,0.0008481229,0.00012242595,0.0041626403,0.0000026263908,0.0005241837,0.00025684913],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001950613,0.00013372407,0.000002786381,0.00015275767,0.00002254669,0.000010063671,0.004583503,0.000038381775,0.004576696,0.0000065530594,0.00014392391,0.99030954],"study_design_scores_gemma":[0.0026634114,0.00043388805,0.0005070667,0.0009202305,0.0001870219,0.0007385857,0.008773044,0.23058556,0.75132775,0.00029228567,0.0017453419,0.0018257932],"about_ca_topic_score_codex":0.00018324601,"about_ca_topic_score_gemma":0.000084741216,"teacher_disagreement_score":0.9884838,"about_ca_system_score_codex":0.00010559632,"about_ca_system_score_gemma":0.00013614271,"threshold_uncertainty_score":0.99987686},"labels":[],"label_agreement":null},{"id":"W4238168884","doi":"10.1109/tasl.2013.2263986","title":"IEEE Transactions on Audio, Speech, and Language Processing publication information","year":2013,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"University of Texas at Dallas; Korea Advanced Institute of Science and Technology; Hong Kong Polytechnic University; Tsinghua University; Aalborg Universitet; Nanyang Technological University; York University; Ben-Gurion University of the Negev; Bar-Ilan University; University of Cambridge; National Cheng Kung University; Institut national de recherche en informatique et en automatique (INRIA); Ohio State University","keywords":"Computer science; Speech recognition; Speech processing; Audio mining; Natural language processing; Voice activity detection","score_opus":0.012180034270205904,"score_gpt":0.2406691442479533,"score_spread":0.2284891099777474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4238168884","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045905553,0.0005135534,0.9475708,0.0018184653,0.00024386923,0.00058556284,0.000028309358,0.0006278528,0.0027060343],"genre_scores_gemma":[0.9486502,0.0001504681,0.0477062,0.0020916567,0.00007669062,0.00017021394,0.000010636242,0.000036286263,0.0011076741],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9977298,0.00010394158,0.000531999,0.00058599416,0.00053530646,0.0005130059],"domain_scores_gemma":[0.9985932,0.0001276297,0.00026324997,0.00041072338,0.0002962293,0.00030897162],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00039936526,0.0003984837,0.00033363886,0.00068736734,0.0008028483,0.0014848105,0.0003480343,0.00022786786,0.00036773278],"category_scores_gemma":[0.00003041248,0.00036834346,0.0001079848,0.0008481229,0.00012242595,0.0041626403,0.0000026263908,0.0005241837,0.00025684913],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001950613,0.00013372407,0.000002786381,0.00015275767,0.00002254669,0.000010063671,0.004583503,0.000038381775,0.004576696,0.0000065530594,0.00014392391,0.99030954],"study_design_scores_gemma":[0.0026634114,0.00043388805,0.0005070667,0.0009202305,0.0001870219,0.0007385857,0.008773044,0.23058556,0.75132775,0.00029228567,0.0017453419,0.0018257932],"about_ca_topic_score_codex":0.00018324601,"about_ca_topic_score_gemma":0.000084741216,"teacher_disagreement_score":0.9884838,"about_ca_system_score_codex":0.00010559632,"about_ca_system_score_gemma":0.00013614271,"threshold_uncertainty_score":0.99987686},"labels":[],"label_agreement":null},{"id":"W4239839560","doi":"10.1109/tasl.2013.2264640","title":"IEEE Transactions on Audio, Speech, and Language Processing publication information","year":2013,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"University of Texas at Dallas; Korea Advanced Institute of Science and Technology; Hong Kong Polytechnic University; Tsinghua University; Aalborg Universitet; Nanyang Technological University; York University; Ben-Gurion University of the Negev; Bar-Ilan University; University of Cambridge; National Cheng Kung University; Institut national de recherche en informatique et en automatique (INRIA); Ohio State University","keywords":"Computer science; Speech recognition; Audio mining; Speech processing; Natural language processing; Voice activity detection","score_opus":0.012180034270205904,"score_gpt":0.2406691442479533,"score_spread":0.2284891099777474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4239839560","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045905553,0.0005135534,0.9475708,0.0018184653,0.00024386923,0.00058556284,0.000028309358,0.0006278528,0.0027060343],"genre_scores_gemma":[0.9486502,0.0001504681,0.0477062,0.0020916567,0.00007669062,0.00017021394,0.000010636242,0.000036286263,0.0011076741],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9977298,0.00010394158,0.000531999,0.00058599416,0.00053530646,0.0005130059],"domain_scores_gemma":[0.9985932,0.0001276297,0.00026324997,0.00041072338,0.0002962293,0.00030897162],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00039936526,0.0003984837,0.00033363886,0.00068736734,0.0008028483,0.0014848105,0.0003480343,0.00022786786,0.00036773278],"category_scores_gemma":[0.00003041248,0.00036834346,0.0001079848,0.0008481229,0.00012242595,0.0041626403,0.0000026263908,0.0005241837,0.00025684913],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001950613,0.00013372407,0.000002786381,0.00015275767,0.00002254669,0.000010063671,0.004583503,0.000038381775,0.004576696,0.0000065530594,0.00014392391,0.99030954],"study_design_scores_gemma":[0.0026634114,0.00043388805,0.0005070667,0.0009202305,0.0001870219,0.0007385857,0.008773044,0.23058556,0.75132775,0.00029228567,0.0017453419,0.0018257932],"about_ca_topic_score_codex":0.00018324601,"about_ca_topic_score_gemma":0.000084741216,"teacher_disagreement_score":0.9884838,"about_ca_system_score_codex":0.00010559632,"about_ca_system_score_gemma":0.00013614271,"threshold_uncertainty_score":0.99987686},"labels":[],"label_agreement":null},{"id":"W4241475234","doi":"10.1002/0471219282.eot138","title":"Speech Processing","year":2003,"lang":"en","type":"other","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Naturalness; Computer science; Speech recognition; Voice activity detection; Speech synthesis; Speech technology; Vocabulary; Speech processing; Speech corpus; Speech analytics; Natural (archaeology); Natural language processing; Artificial intelligence; Linguistics","score_opus":0.021271344167064023,"score_gpt":0.2468486355925819,"score_spread":0.22557729142551788,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4241475234","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.8178435e-8,0.00019732378,0.21243414,0.00015867934,0.000195843,0.000059673923,6.3137895e-7,0.0005398588,0.7864138],"genre_scores_gemma":[0.0000013131217,0.000021393718,0.31833562,0.00084866496,0.00005342079,0.0000037173568,5.6109104e-7,0.00006942844,0.68066585],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99930227,0.000022576602,0.00008368832,0.00027607766,0.00017021486,0.00014518503],"domain_scores_gemma":[0.9995541,0.000009611378,0.000062053565,0.0003034441,0.000017308172,0.00005346345],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000066480054,0.00012656883,0.00013523035,0.00017379403,0.000022068629,0.00012747472,0.00041069614,0.00013432927,0.012669492],"category_scores_gemma":[0.000014769484,0.000103851686,0.000045298297,0.00018239448,0.000013920953,0.000054855464,0.000037394515,0.00006980601,0.0025969367],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.5327698e-8,0.000008436058,7.1382595e-7,0.000008899565,0.0000031829595,0.0000093231565,0.0000028686954,1.3182464e-9,0.00000239442,0.0019727128,0.5693271,0.4286643],"study_design_scores_gemma":[0.00004512876,0.0000034753848,0.0000014287406,0.000053202377,0.0000025844638,0.00002910809,0.0000028859654,0.00019552957,0.00051604945,0.0006028167,0.99838257,0.00016521612],"about_ca_topic_score_codex":0.000016020815,"about_ca_topic_score_gemma":0.000019296775,"teacher_disagreement_score":0.42905545,"about_ca_system_score_codex":0.000010625075,"about_ca_system_score_gemma":0.000052950018,"threshold_uncertainty_score":0.9981797},"labels":[],"label_agreement":null},{"id":"W4246248617","doi":"10.31234/osf.io/jb4wh","title":"Evaluating generalised additive mixed modelling strategies for dynamic speech analysis","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Set (abstract data type); Range (aeronautics); Formant; Focus (optics); Data set; Data mining; Artificial intelligence; Speech recognition","score_opus":0.1663628758113608,"score_gpt":0.36711043957423445,"score_spread":0.20074756376287364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4246248617","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009902077,0.000053558364,0.9837164,0.0009834832,0.0004099459,0.0006818978,0.00022242658,0.00046791846,0.0035622409],"genre_scores_gemma":[0.17499796,0.000037227357,0.8235505,0.00036172327,0.00010828364,0.00024223978,0.00038317472,0.000023594728,0.00029529686],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969606,0.0002133676,0.0005845685,0.0013012611,0.00056395604,0.00037626777],"domain_scores_gemma":[0.99772435,0.00047965156,0.00035000176,0.0007746927,0.00051119673,0.00016010279],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00064278673,0.0004019793,0.00073397235,0.00046685152,0.00016549534,0.0010169734,0.0012537888,0.00026305788,0.0002708468],"category_scores_gemma":[0.00011493934,0.00038569106,0.0008341412,0.0007378925,0.000032473286,0.00030880596,0.0006792938,0.00034078184,0.000044403165],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035504196,0.000094221425,0.0000046089067,0.00017087888,0.0032383963,0.000026691128,0.001118733,0.6055956,0.0011379446,0.018943302,0.0009688097,0.36866534],"study_design_scores_gemma":[0.00020532102,0.000036583482,0.000018322798,0.000030279734,0.000558062,0.0000014055524,0.0002978206,0.9269488,0.0023006985,0.069097124,0.00006012537,0.0004454779],"about_ca_topic_score_codex":0.00014435768,"about_ca_topic_score_gemma":0.0001485538,"teacher_disagreement_score":0.36821988,"about_ca_system_score_codex":0.000118022064,"about_ca_system_score_gemma":0.00046559577,"threshold_uncertainty_score":0.9998595},"labels":[],"label_agreement":null},{"id":"W4247179283","doi":"10.1109/tasl.2013.2282066","title":"IEEE Transactions on Audio, Speech, and Language Processing publication information","year":2013,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Texas at Dallas; Korea Advanced Institute of Science and Technology; Hong Kong Polytechnic University; Tsinghua University; Institute for Infocomm Research; Aalborg Universitet; York University; Bar-Ilan University; Facebook; National Cheng Kung University; Institut national de recherche en informatique et en automatique (INRIA); Ohio State University; Nanyang Technological University; Ben-Gurion University of the Negev; University of Missouri; RWTH Aachen University; Microsoft Research","keywords":"Computer science; Speech recognition; Speech processing","score_opus":0.012180034270205904,"score_gpt":0.2406691442479533,"score_spread":0.2284891099777474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4247179283","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045905553,0.0005135534,0.9475708,0.0018184653,0.00024386923,0.00058556284,0.000028309358,0.0006278528,0.0027060343],"genre_scores_gemma":[0.9486502,0.0001504681,0.0477062,0.0020916567,0.00007669062,0.00017021394,0.000010636242,0.000036286263,0.0011076741],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9977298,0.00010394158,0.000531999,0.00058599416,0.00053530646,0.0005130059],"domain_scores_gemma":[0.9985932,0.0001276297,0.00026324997,0.00041072338,0.0002962293,0.00030897162],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00039936526,0.0003984837,0.00033363886,0.00068736734,0.0008028483,0.0014848105,0.0003480343,0.00022786786,0.00036773278],"category_scores_gemma":[0.00003041248,0.00036834346,0.0001079848,0.0008481229,0.00012242595,0.0041626403,0.0000026263908,0.0005241837,0.00025684913],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001950613,0.00013372407,0.000002786381,0.00015275767,0.00002254669,0.000010063671,0.004583503,0.000038381775,0.004576696,0.0000065530594,0.00014392391,0.99030954],"study_design_scores_gemma":[0.0026634114,0.00043388805,0.0005070667,0.0009202305,0.0001870219,0.0007385857,0.008773044,0.23058556,0.75132775,0.00029228567,0.0017453419,0.0018257932],"about_ca_topic_score_codex":0.00018324601,"about_ca_topic_score_gemma":0.000084741216,"teacher_disagreement_score":0.9884838,"about_ca_system_score_codex":0.00010559632,"about_ca_system_score_gemma":0.00013614271,"threshold_uncertainty_score":0.99987686},"labels":[],"label_agreement":null},{"id":"W4248245387","doi":"10.1109/tasl.2013.2282071","title":"IEEE Transactions on Audio, Speech, and Language Processing publication information","year":2013,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Texas at Dallas; Korea Advanced Institute of Science and Technology; Hong Kong Polytechnic University; Tsinghua University; Institute for Infocomm Research; Aalborg Universitet; York University; Bar-Ilan University; Facebook; National Cheng Kung University; Institut national de recherche en informatique et en automatique (INRIA); Ohio State University; Nanyang Technological University; Ben-Gurion University of the Negev; University of Missouri; RWTH Aachen University; Microsoft Research","keywords":"Computer science; Speech recognition; Audio mining; Speech processing; Multimedia; Voice activity detection","score_opus":0.012180034270205904,"score_gpt":0.2406691442479533,"score_spread":0.2284891099777474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4248245387","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045905553,0.0005135534,0.9475708,0.0018184653,0.00024386923,0.00058556284,0.000028309358,0.0006278528,0.0027060343],"genre_scores_gemma":[0.9486502,0.0001504681,0.0477062,0.0020916567,0.00007669062,0.00017021394,0.000010636242,0.000036286263,0.0011076741],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9977298,0.00010394158,0.000531999,0.00058599416,0.00053530646,0.0005130059],"domain_scores_gemma":[0.9985932,0.0001276297,0.00026324997,0.00041072338,0.0002962293,0.00030897162],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00039936526,0.0003984837,0.00033363886,0.00068736734,0.0008028483,0.0014848105,0.0003480343,0.00022786786,0.00036773278],"category_scores_gemma":[0.00003041248,0.00036834346,0.0001079848,0.0008481229,0.00012242595,0.0041626403,0.0000026263908,0.0005241837,0.00025684913],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001950613,0.00013372407,0.000002786381,0.00015275767,0.00002254669,0.000010063671,0.004583503,0.000038381775,0.004576696,0.0000065530594,0.00014392391,0.99030954],"study_design_scores_gemma":[0.0026634114,0.00043388805,0.0005070667,0.0009202305,0.0001870219,0.0007385857,0.008773044,0.23058556,0.75132775,0.00029228567,0.0017453419,0.0018257932],"about_ca_topic_score_codex":0.00018324601,"about_ca_topic_score_gemma":0.000084741216,"teacher_disagreement_score":0.9884838,"about_ca_system_score_codex":0.00010559632,"about_ca_system_score_gemma":0.00013614271,"threshold_uncertainty_score":0.99987686},"labels":[],"label_agreement":null},{"id":"W4250163740","doi":"10.1109/tasl.2013.2253678","title":"IEEE Transactions on Audio, Speech, and Language Processing publication information","year":2013,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"University of Texas at Dallas; Korea Advanced Institute of Science and Technology; Hong Kong Polytechnic University; Tsinghua University; Aalborg Universitet; Nanyang Technological University; York University; Ben-Gurion University of the Negev; Bar-Ilan University; University of Cambridge; National Cheng Kung University; Ohio State University; Institut national de recherche en informatique et en automatique (INRIA); Northwestern University","keywords":"Computer science; Speech recognition; Audio mining; Speech processing; Multimedia; Natural language processing; World Wide Web; Voice activity detection","score_opus":0.012180034270205904,"score_gpt":0.2406691442479533,"score_spread":0.2284891099777474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4250163740","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045905553,0.0005135534,0.9475708,0.0018184653,0.00024386923,0.00058556284,0.000028309358,0.0006278528,0.0027060343],"genre_scores_gemma":[0.9486502,0.0001504681,0.0477062,0.0020916567,0.00007669062,0.00017021394,0.000010636242,0.000036286263,0.0011076741],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9977298,0.00010394158,0.000531999,0.00058599416,0.00053530646,0.0005130059],"domain_scores_gemma":[0.9985932,0.0001276297,0.00026324997,0.00041072338,0.0002962293,0.00030897162],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00039936526,0.0003984837,0.00033363886,0.00068736734,0.0008028483,0.0014848105,0.0003480343,0.00022786786,0.00036773278],"category_scores_gemma":[0.00003041248,0.00036834346,0.0001079848,0.0008481229,0.00012242595,0.0041626403,0.0000026263908,0.0005241837,0.00025684913],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001950613,0.00013372407,0.000002786381,0.00015275767,0.00002254669,0.000010063671,0.004583503,0.000038381775,0.004576696,0.0000065530594,0.00014392391,0.99030954],"study_design_scores_gemma":[0.0026634114,0.00043388805,0.0005070667,0.0009202305,0.0001870219,0.0007385857,0.008773044,0.23058556,0.75132775,0.00029228567,0.0017453419,0.0018257932],"about_ca_topic_score_codex":0.00018324601,"about_ca_topic_score_gemma":0.000084741216,"teacher_disagreement_score":0.9884838,"about_ca_system_score_codex":0.00010559632,"about_ca_system_score_gemma":0.00013614271,"threshold_uncertainty_score":0.99987686},"labels":[],"label_agreement":null},{"id":"W4251756105","doi":"10.31234/osf.io/97jp4","title":"Performance of forced-alignment algorithms on children’s speech","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Speech recognition; Two-alternative forced choice; Sample (material); Phone; Electroglottograph; Natural language processing; Artificial intelligence; Algorithm; Mathematics; Audiology; Linguistics; Statistics; Phonation","score_opus":0.033852122633258354,"score_gpt":0.2521861475258069,"score_spread":0.21833402489254858,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4251756105","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3503302,0.00010627147,0.4599745,0.007830342,0.003059726,0.0021333706,0.00015550652,0.0013019299,0.17510816],"genre_scores_gemma":[0.70071995,0.00015950881,0.29646719,0.0013717276,0.00021936532,0.00004521138,0.0000355571,0.000024556108,0.00095695816],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9980017,0.000049204944,0.00039902632,0.0006841527,0.0006019179,0.00026403094],"domain_scores_gemma":[0.99866754,0.00006137518,0.0002117756,0.00084625784,0.00007854105,0.0001345108],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019661599,0.00027641267,0.00039107105,0.00014721516,0.000052242973,0.00008593316,0.0013431051,0.0001747932,0.0002917515],"category_scores_gemma":[0.00002921761,0.0002378993,0.00021450767,0.00015352425,0.000033520897,0.000092151306,0.0011939047,0.00033201667,0.00027983816],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016173464,0.00019612839,0.00056045305,0.00009706521,0.00014835974,0.00001441193,0.00029533496,0.00019009325,0.00019080352,0.0056503997,0.0050631417,0.9875776],"study_design_scores_gemma":[0.0006395852,0.0006268601,0.014604109,0.0004318634,0.000045377034,0.00004637166,0.000025672922,0.3656512,0.61248326,0.0036487416,0.0007479809,0.0010489476],"about_ca_topic_score_codex":0.000041786076,"about_ca_topic_score_gemma":0.0000010812778,"teacher_disagreement_score":0.9865287,"about_ca_system_score_codex":0.00006384877,"about_ca_system_score_gemma":0.000091653754,"threshold_uncertainty_score":0.9701252},"labels":[],"label_agreement":null},{"id":"W4253290035","doi":"10.1121/2.0000395","title":"Towards real-time two-dimensional wave propagation for articulatory speech synthesis","year":2016,"lang":"en","type":"article","venue":"Proceedings of meetings on acoustics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Nvidia","keywords":"Computer science; Formant; Solver; Discretization; Speech recognition; Speech enhancement; Acoustics; Artificial intelligence","score_opus":0.02041344907479455,"score_gpt":0.2419891075239956,"score_spread":0.22157565844920105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4253290035","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9493982,0.000009313995,0.023468252,0.0033112604,0.00031746287,0.00094551116,0.000046315385,0.0005723395,0.0219313],"genre_scores_gemma":[0.68390024,0.000013005784,0.31515414,0.00019592218,0.00017052129,0.0000950911,9.781222e-7,0.00003414803,0.00043593798],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99793863,0.000011599846,0.00048171365,0.0005173952,0.0006678941,0.00038276022],"domain_scores_gemma":[0.9971844,0.0007462313,0.0004183182,0.00016584015,0.0013320411,0.00015319868],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010300722,0.00023581131,0.00032839063,0.00022343165,0.00012719512,0.00010054,0.00041731913,0.00011992752,0.000059263497],"category_scores_gemma":[0.0033299273,0.0001700278,0.00013303339,0.00026820545,0.00009576268,0.00036459434,0.000119668366,0.0000706894,0.00007816809],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000709941,0.00014486133,0.000055902005,0.000089245856,0.000032992393,0.0000022670033,0.00006891069,0.000005656353,0.8411814,0.009259138,0.0024638434,0.1466248],"study_design_scores_gemma":[0.00067104644,0.0002380412,0.0007939404,0.0005254044,0.0000718613,0.00003255012,0.000040130595,0.031452306,0.95935315,0.0061687035,0.00027891053,0.00037393556],"about_ca_topic_score_codex":0.000003652719,"about_ca_topic_score_gemma":8.71777e-8,"teacher_disagreement_score":0.29168588,"about_ca_system_score_codex":0.00010509518,"about_ca_system_score_gemma":0.00009229969,"threshold_uncertainty_score":0.69335324},"labels":[],"label_agreement":null},{"id":"W4255090931","doi":"10.22215/etd/2011-09074","title":"A speech recognition enabled ambulance call report system for paramedics","year":2011,"lang":"en","type":"dissertation","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Heritage; Library and Archives Canada","funders":"","keywords":"Engineering; Computer science; Telecommunications; Speech recognition; Aeronautics","score_opus":0.043796933631790595,"score_gpt":0.27081536340810214,"score_spread":0.22701842977631154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4255090931","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014582185,0.0002213041,0.4240665,0.00017356586,0.010334869,0.0031078092,0.00008712639,0.002270074,0.54515654],"genre_scores_gemma":[0.011624425,0.00016295277,0.7998894,0.0005215528,0.00087824056,0.0017923643,0.0038673044,0.0001445639,0.18111919],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9974174,0.000064844455,0.0007673567,0.0008734806,0.00046630626,0.00041064588],"domain_scores_gemma":[0.9974753,0.00020612021,0.00062803185,0.00078063604,0.00073556945,0.00017433251],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006882007,0.00035792877,0.0005443918,0.00026415405,0.00014715114,0.000191847,0.00071261346,0.00051340443,0.00015949245],"category_scores_gemma":[0.0003524094,0.00032820072,0.0002815916,0.00027412848,0.000016475822,0.00032275246,0.000030752937,0.00022764588,0.00044963794],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000112431015,0.00014746004,0.000017063452,0.0012186344,0.00016505057,0.0007749849,0.00041048735,7.629261e-8,0.000338737,0.0028434345,0.016113266,0.97785836],"study_design_scores_gemma":[0.0052616876,0.0010170977,0.001831893,0.0075409035,0.0011828368,0.008450555,0.0042883717,0.024712887,0.72721547,0.046576995,0.16411057,0.007810736],"about_ca_topic_score_codex":0.00019013575,"about_ca_topic_score_gemma":0.00028268865,"teacher_disagreement_score":0.97004765,"about_ca_system_score_codex":0.000107836655,"about_ca_system_score_gemma":0.00029309926,"threshold_uncertainty_score":0.99991703},"labels":[],"label_agreement":null},{"id":"W4255779616","doi":"10.1121/1.4800662","title":"Nonlinearities in block-type reduced-order vocal fold models with asymmetric tissue properties","year":2013,"lang":"en","type":"article","venue":"Proceedings of meetings on acoustics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Phonation; Vocal folds; Fold (higher-order function); Nonlinear system; Bifurcation; Sensitivity (control systems); Control theory (sociology); Computer science; Speech recognition; Mathematics; Physics; Artificial intelligence; Larynx; Engineering","score_opus":0.02415733067456152,"score_gpt":0.22200372047738967,"score_spread":0.19784638980282815,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4255779616","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9673252,0.00012143142,0.004014494,0.001331923,0.00015635681,0.0006189844,0.000002520752,0.00024345753,0.026185632],"genre_scores_gemma":[0.8387098,0.00005862744,0.16031085,0.00029799296,0.00006348156,0.000041786072,5.6067944e-7,0.000026600259,0.0004903422],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99810714,0.0000085513575,0.00042468566,0.00043834292,0.0006125476,0.00040874112],"domain_scores_gemma":[0.99778026,0.000116610754,0.00022529202,0.00014322775,0.0016168895,0.00011769387],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034189518,0.0002495848,0.0003441063,0.00052072894,0.00007838343,0.0002696655,0.00065371057,0.00013608983,0.000013371729],"category_scores_gemma":[0.00078803353,0.00019465756,0.000030506468,0.0014511213,0.00013060437,0.0006962973,0.0001486295,0.00025862586,0.00004007208],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00049638585,0.003316839,0.002947529,0.0021699467,0.00024117342,0.000038081926,0.009593938,0.0043744543,0.5816069,0.037735146,0.019347548,0.33813202],"study_design_scores_gemma":[0.0012470655,0.0014895556,0.0010531739,0.0011937922,0.000055007356,0.00008451839,0.002998955,0.57273334,0.4131831,0.004490063,0.00045693625,0.0010144686],"about_ca_topic_score_codex":0.00010933184,"about_ca_topic_score_gemma":0.0000016616507,"teacher_disagreement_score":0.5683589,"about_ca_system_score_codex":0.000051591964,"about_ca_system_score_gemma":0.0000894101,"threshold_uncertainty_score":0.7937905},"labels":[],"label_agreement":null},{"id":"W4255932031","doi":"10.1075/bct.16.15kan","title":"Speech transformation solutions","year":2008,"lang":"en","type":"book-chapter","venue":"Benjamins current topics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cape Breton University","funders":"","keywords":"Transformation (genetics); Computer science; Speech recognition; Biology","score_opus":0.08945794588131091,"score_gpt":0.2647568369040798,"score_spread":0.1752988910227689,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4255932031","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000012839671,0.0018455504,0.12868242,0.0010716337,0.0022527939,0.00035244387,0.00006950129,0.00035494423,0.8653579],"genre_scores_gemma":[0.0007623592,0.03621884,0.047871485,0.0007407213,0.0032335338,0.00007736862,0.0005478645,0.00013594868,0.9104119],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983819,0.000018615954,0.00042694178,0.00039640072,0.00047528822,0.00030086347],"domain_scores_gemma":[0.99894655,0.00004187526,0.0001575801,0.00057909475,0.00014560616,0.00012928218],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001002237,0.00030718482,0.00029228692,0.00027224727,0.00023544973,0.00009781063,0.000643388,0.00025688027,0.00038144033],"category_scores_gemma":[0.00001855023,0.00031510336,0.0002743835,0.000066689616,0.000060675993,0.00033942272,0.00010637589,0.0004065559,0.0009800742],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.8620446e-7,0.000027377964,5.936893e-7,0.000025064499,0.000014043588,0.000010994007,0.00017316359,3.4971538e-7,0.000001110895,0.20974353,0.014098414,0.7759048],"study_design_scores_gemma":[0.00015698264,0.000025108247,0.000049715964,0.000115308656,0.000023635335,0.000081529324,0.0000027707613,0.0012969674,0.000070044094,0.008082449,0.9897269,0.00036858855],"about_ca_topic_score_codex":0.0000031591567,"about_ca_topic_score_gemma":0.000023609657,"teacher_disagreement_score":0.9756285,"about_ca_system_score_codex":0.00011380747,"about_ca_system_score_gemma":0.00014643604,"threshold_uncertainty_score":0.9999301},"labels":[],"label_agreement":null},{"id":"W4285242026","doi":"10.51542/ijscia.v3i3.25","title":"ArmSpeech: Armenian Spoken Language Corpus","year":2022,"lang":"en","type":"article","venue":"International Journal Of Scientific Advances","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Armenian; Stress (linguistics); The Republic; Diaspora; Linguistics; Speech corpus; Spoken language; Identification (biology); History; Computer science; Natural language processing; Artificial intelligence; Political science; Speech synthesis; Law","score_opus":0.014031201442583113,"score_gpt":0.27713340186773505,"score_spread":0.2631022004251519,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285242026","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7956835,0.0031878331,0.1332428,0.009409476,0.042579524,0.00019353179,0.0001023732,0.00013919317,0.015461787],"genre_scores_gemma":[0.9568743,0.00004144231,0.040003188,0.00042452756,0.00026016662,0.0000048030793,0.0000047588883,0.0000062614695,0.0023805548],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99796855,0.000070407514,0.00034029307,0.00019775571,0.0012799513,0.00014306343],"domain_scores_gemma":[0.9988881,0.00010228275,0.0003977222,0.0001690232,0.00035815113,0.0000847324],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00084897934,0.00007692591,0.00011616265,0.00045398436,0.00022253853,0.00036595407,0.00193877,0.000011201862,0.0006618514],"category_scores_gemma":[0.00011270156,0.00006811324,0.00012053892,0.00035402982,0.000079555175,0.00096973445,0.0002809365,0.00017795185,0.000042611216],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000457113,0.00021476943,0.0007625065,0.0000024386236,0.000060891285,0.0008029544,0.0013711047,0.00027834927,0.010318998,0.0041525355,0.0035547495,0.978435],"study_design_scores_gemma":[0.0010712558,0.0002045377,0.0012629431,0.00003980727,0.000013028957,0.0031090605,0.0023299246,0.0038575951,0.044574983,0.013849722,0.9293659,0.00032125606],"about_ca_topic_score_codex":0.0000031494533,"about_ca_topic_score_gemma":0.0000051826046,"teacher_disagreement_score":0.9781137,"about_ca_system_score_codex":0.00013386564,"about_ca_system_score_gemma":0.00011339528,"threshold_uncertainty_score":0.72468084},"labels":[],"label_agreement":null},{"id":"W4285813846","doi":"10.1109/iwcmc55113.2022.9824220","title":"A Study Of Voiceprint Recognition Technology Based on Deep Learning","year":2022,"lang":"en","type":"article","venue":"2022 International Wireless Communications and Mobile Computing (IWCMC)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Computer science; Realization (probability); Process (computing); Facial recognition system; Artificial intelligence; Feature extraction","score_opus":0.02877269869195719,"score_gpt":0.285629063645942,"score_spread":0.2568563649539848,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285813846","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9542909,0.00012352358,0.040347695,0.0010762039,0.00028421555,0.00047128444,0.0000069736757,0.00022925822,0.003169933],"genre_scores_gemma":[0.989775,0.000070682574,0.009596607,0.00014688884,0.0000152474695,0.00030281875,0.000039465842,0.000012186178,0.00004107434],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99834925,0.0003713864,0.00039381185,0.00035252396,0.0003898041,0.00014321294],"domain_scores_gemma":[0.9980754,0.0005119541,0.0002925194,0.0008519183,0.00022608203,0.000042089694],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000606763,0.00012640058,0.00018562068,0.00059536763,0.00069970783,0.000072059665,0.0017139887,0.000036700334,0.00012805613],"category_scores_gemma":[0.000075870805,0.00014339911,0.000061694656,0.00059092615,0.00007344,0.000087849665,0.0018936989,0.0004969248,0.00001034534],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016485674,0.0016365143,0.0037961653,0.000005772539,0.00005802401,0.0000065404047,0.0014052541,0.005179109,0.00039188718,0.0038407543,0.000020441248,0.98364305],"study_design_scores_gemma":[0.0008061608,0.000720098,0.0022490385,0.00003742019,0.000012483839,0.000034297485,0.0053085056,0.98370093,0.0003247623,0.00064454816,0.00595928,0.00020245659],"about_ca_topic_score_codex":0.000049424776,"about_ca_topic_score_gemma":0.00002052036,"teacher_disagreement_score":0.9834406,"about_ca_system_score_codex":0.00009811569,"about_ca_system_score_gemma":0.00003763534,"threshold_uncertainty_score":0.5847646},"labels":[],"label_agreement":null},{"id":"W4287591426","doi":"10.48550/arxiv.2011.11588","title":"The Zero Resource Speech Benchmark 2021: Metrics and baselines for unsupervised spoken language modeling","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; University of Toronto","funders":"","keywords":"Computer science; Natural language processing; Benchmark (surveying); Artificial intelligence; Cluster analysis; Spoken language; Language model; Syntax; Speech recognition; Concatenation (mathematics); Pipeline (software); Representation (politics)","score_opus":0.0971620928814873,"score_gpt":0.20497678732253022,"score_spread":0.10781469444104291,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4287591426","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.086108714,0.00046245073,0.9093757,0.0010601621,0.0002754461,0.00050863856,0.00005930089,0.00015851005,0.0019910752],"genre_scores_gemma":[0.96534204,0.00092791946,0.031885076,0.00043552514,0.0002089899,0.0000040974924,0.000047132,0.000030947067,0.0011182905],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981572,0.00016220256,0.00023402947,0.0009829529,0.00013568488,0.00032793058],"domain_scores_gemma":[0.9977451,0.00087929156,0.00014415586,0.00083196815,0.00019262756,0.00020686178],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005978468,0.0002879392,0.00031888104,0.00024030982,0.00036928774,0.00032536077,0.0014629185,0.00021525787,0.000023532251],"category_scores_gemma":[0.00046861236,0.0002614928,0.0002305853,0.0007310829,0.00006630334,0.00018238365,0.0012912706,0.00037241535,0.00002213099],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00079526263,0.00041645463,0.0016144217,0.001028606,0.0013378124,0.0021016034,0.004542322,0.112911895,0.00074750715,0.16720632,0.017524807,0.68977296],"study_design_scores_gemma":[0.00036496678,0.000026411482,0.000017303806,0.000047853857,0.000079740166,0.000004315165,0.00044382224,0.9768644,0.00031830603,0.018128864,0.0033797934,0.0003242391],"about_ca_topic_score_codex":0.00009480162,"about_ca_topic_score_gemma":0.000031993943,"teacher_disagreement_score":0.8792333,"about_ca_system_score_codex":0.00006995367,"about_ca_system_score_gemma":0.00011044599,"threshold_uncertainty_score":0.9999837},"labels":[],"label_agreement":null},{"id":"W4287692747","doi":"10.48550/arxiv.2008.01504","title":"\"This is Houston. Say again, please\". The Behavox system for the\\n Apollo-11 Fearless Steps Challenge (phase II)","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ventix (Canada)","funders":"","keywords":"Computer science; Speech recognition; Word error rate; Apollo; Variety (cybernetics); Ranking (information retrieval); Lexicon; Segmentation; Baseline (sea); Word (group theory); Speaker diarisation; Vocal tract; Artificial intelligence; Natural language processing; Speaker recognition; Linguistics","score_opus":0.13355590728972452,"score_gpt":0.2203934630769101,"score_spread":0.08683755578718558,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4287692747","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041232217,0.0008285345,0.9209785,0.01621463,0.0031081191,0.0038417503,0.0007143941,0.0013393392,0.011742503],"genre_scores_gemma":[0.99291533,0.00035405767,0.0011417372,0.0010915542,0.00027601913,0.000028666067,0.000019128121,0.000049319093,0.0041241897],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970628,0.0003030948,0.00035771742,0.0014694819,0.00025998926,0.00054689293],"domain_scores_gemma":[0.99618924,0.00074566115,0.00045722723,0.0020059806,0.0003126991,0.00028918323],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005968851,0.00052121293,0.0005590221,0.00020501592,0.001069152,0.00031512635,0.004072192,0.00038456402,0.0001458236],"category_scores_gemma":[0.00008926951,0.00040599136,0.0007166108,0.0005921225,0.00020461876,0.0002628015,0.0023371547,0.0006674316,0.00024401082],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00097932,0.0028490068,0.00032181336,0.0025428627,0.0033416762,0.002656795,0.020412564,0.0045536403,0.00023127749,0.6438832,0.13254678,0.18568103],"study_design_scores_gemma":[0.004603605,0.0006369639,0.00013376342,0.00065235957,0.0012749468,0.000043715496,0.004879905,0.8930808,0.0025718687,0.007719506,0.08224035,0.0021622374],"about_ca_topic_score_codex":0.0003101073,"about_ca_topic_score_gemma":0.00010603848,"teacher_disagreement_score":0.9516831,"about_ca_system_score_codex":0.00029973724,"about_ca_system_score_gemma":0.00029397896,"threshold_uncertainty_score":0.9998392},"labels":[],"label_agreement":null},{"id":"W4287889742","doi":"10.18653/v1/2022.deeplo-1.9","title":"Punctuation Restoration in Spanish Customer Support Transcripts using Transfer Learning","year":2022,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Stornoway Diamond (Canada)","funders":"","keywords":"Punctuation; Transfer of learning; Computer science; Natural language processing; Artificial intelligence","score_opus":0.04942122317982497,"score_gpt":0.2564283702834163,"score_spread":0.20700714710359133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4287889742","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35718805,0.00000693961,0.6268642,0.00057621143,0.00034326888,0.00018351735,0.0000012261311,0.00017487374,0.014661688],"genre_scores_gemma":[0.9891218,0.0000029493199,0.0097558275,0.00041729058,0.000017336506,0.00002492956,0.000008346737,0.0000075042726,0.00064401794],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99886453,0.00019613163,0.00020390585,0.00023771444,0.0003354668,0.00016226711],"domain_scores_gemma":[0.99975294,0.00003573396,0.000019549554,0.00012206303,0.000031805368,0.000037937454],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005232271,0.00007479682,0.00009658953,0.00023297712,0.000201357,0.00007920806,0.00020310334,0.00002700914,0.0017828229],"category_scores_gemma":[0.000017880831,0.00008179105,0.00004865909,0.0005233655,0.000009645336,0.0005219342,0.000025416473,0.0001808421,0.0000556646],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007720451,0.0005273831,0.007314191,0.000030098312,0.00003157868,0.0001611743,0.0147497095,0.01949412,0.16369547,0.04196159,0.001251649,0.75070584],"study_design_scores_gemma":[0.0019240553,0.00034261364,0.017672012,0.000017684206,0.000027234546,0.00017730302,0.0025269627,0.8765613,0.02852614,0.0015447277,0.069788225,0.0008917716],"about_ca_topic_score_codex":0.00008935291,"about_ca_topic_score_gemma":0.00006144438,"teacher_disagreement_score":0.85706717,"about_ca_system_score_codex":0.00011806435,"about_ca_system_score_gemma":0.00007934711,"threshold_uncertainty_score":0.99912965},"labels":[],"label_agreement":null},{"id":"W4288087689","doi":"10.48550/arxiv.1910.13923","title":"Lightweight and Efficient End-to-End Speech Recognition Using Low-Rank\\n Transformer","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Transformer; End-to-end principle; Inference; Computer science; Language model; Software deployment; Artificial neural network; Speech recognition; Artificial intelligence; Engineering","score_opus":0.07597558586763042,"score_gpt":0.1964255653594453,"score_spread":0.12044997949181488,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4288087689","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.61327744,0.0000307,0.3803973,0.00012222599,0.00065524084,0.0004777586,0.000047268542,0.00015172915,0.0048403754],"genre_scores_gemma":[0.98358095,0.00015515156,0.015349302,0.0002539816,0.00008789065,0.000001371107,0.000022729144,0.000028621482,0.00051999],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99748796,0.0001609633,0.0002844862,0.0013998093,0.0001976808,0.00046907453],"domain_scores_gemma":[0.9983169,0.00016630128,0.00017725183,0.00080512685,0.00021596976,0.00031845106],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003617206,0.00041741517,0.0004570011,0.0006609888,0.00019533224,0.00023226891,0.00087033096,0.00036695332,0.00033989694],"category_scores_gemma":[0.000030915944,0.0004615012,0.00025218946,0.0006681645,0.00008835253,0.00033296086,0.000478826,0.0004741755,0.0006029274],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00068741216,0.0020214752,0.004497924,0.001912799,0.0013048231,0.0035679736,0.004644156,0.10152412,0.010239104,0.019199032,0.0010826213,0.84931856],"study_design_scores_gemma":[0.0015495099,0.00012316412,0.0015034995,0.00092671777,0.00033705475,0.00011094653,0.00021202545,0.9477568,0.03379854,0.010200157,0.0015373393,0.0019442351],"about_ca_topic_score_codex":0.000120514764,"about_ca_topic_score_gemma":0.000043459593,"teacher_disagreement_score":0.8473743,"about_ca_system_score_codex":0.00022385287,"about_ca_system_score_gemma":0.00018717516,"threshold_uncertainty_score":0.9997837},"labels":[],"label_agreement":null},{"id":"W4288107168","doi":"10.48550/arxiv.1909.06805","title":"Many-to-Many Voice Conversion using Cycle-Consistent Variational\\n Autoencoder with Multiple Decoders","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Autoencoder; Computer science; Speech recognition; Path (computing); Task (project management); Consistency (knowledge bases); Artificial intelligence; Deep learning; Engineering","score_opus":0.07116699081042,"score_gpt":0.19414457001423718,"score_spread":0.12297757920381719,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4288107168","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17261489,0.000009658523,0.8238003,0.0001988327,0.0006587286,0.00050549593,0.000026918648,0.00023131282,0.0019538424],"genre_scores_gemma":[0.89642555,0.00002129344,0.10175547,0.00059083063,0.000048688027,0.0000017310654,0.00001930975,0.00003005656,0.0011070786],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974419,0.000181797,0.0002578089,0.001425144,0.000248837,0.000444509],"domain_scores_gemma":[0.99748087,0.00034650345,0.00032336242,0.0011800639,0.00037026624,0.00029894355],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00027759752,0.00041154335,0.00042797613,0.00051913934,0.000245819,0.00020503666,0.0013416468,0.00029656978,0.00013530497],"category_scores_gemma":[0.00006812118,0.0004409945,0.0002394446,0.00059553154,0.00007821348,0.0004956879,0.0012461928,0.00042289592,0.000753788],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013129895,0.0002077035,0.013035708,0.000122103,0.00033506696,0.0003299031,0.00041528526,0.9698077,0.00009207439,0.014334657,0.00036235352,0.0008261558],"study_design_scores_gemma":[0.00083953695,0.00004562752,0.0051827976,0.0001829044,0.00012130428,0.00001999372,0.00013359087,0.990334,0.00021133809,0.0016751315,0.0006397727,0.0006140269],"about_ca_topic_score_codex":0.00036629802,"about_ca_topic_score_gemma":0.00006255215,"teacher_disagreement_score":0.7238107,"about_ca_system_score_codex":0.00048591522,"about_ca_system_score_gemma":0.00043083893,"threshold_uncertainty_score":0.9998042},"labels":[],"label_agreement":null},{"id":"W4289792473","doi":"10.1109/jstsp.2022.3196562","title":"L-Mix: A Latent-Level Instance Mixup Regularization for Robust Self-Supervised Speaker Representation Learning","year":2022,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Signal Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Feature learning; Embedding; Speech recognition; Artificial intelligence; Regularization (linguistics); Speaker recognition; Pattern recognition (psychology); Supervised learning; Semi-supervised learning; Machine learning; Artificial neural network","score_opus":0.05517068553173211,"score_gpt":0.2693890251686757,"score_spread":0.2142183396369436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4289792473","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0767728,0.00017750806,0.9215386,0.0007976821,0.00026705273,0.00018444555,0.0000015294942,0.000059055983,0.00020135398],"genre_scores_gemma":[0.6282171,0.000028015851,0.3707991,0.00023396262,0.00029561593,0.000020761992,0.0000067363344,0.000020129291,0.00037857553],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99819773,0.0002321828,0.0005846494,0.00023683978,0.0005167488,0.0002318392],"domain_scores_gemma":[0.9984915,0.00012818795,0.0005292705,0.00009277465,0.0006989633,0.000059256385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007147576,0.00012021826,0.00022560601,0.00036073974,0.00034875833,0.00019108126,0.00041870636,0.000057228364,0.000028427972],"category_scores_gemma":[0.00016209949,0.00012488989,0.00007442977,0.0012971341,0.000014785725,0.00079699693,0.000043766307,0.00046315655,8.216085e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002647232,0.0005601365,0.005761649,0.00018463482,0.0000919447,0.00013747258,0.0064768284,0.071969084,0.036803737,0.0006096379,0.0004747392,0.8766654],"study_design_scores_gemma":[0.0017204056,0.00030094903,0.0025035504,0.00015460278,0.000031466534,0.00028469384,0.00036321647,0.97224873,0.017248543,0.003904882,0.0009616309,0.0002773414],"about_ca_topic_score_codex":0.00000259287,"about_ca_topic_score_gemma":0.000004023483,"teacher_disagreement_score":0.90027964,"about_ca_system_score_codex":0.00021347663,"about_ca_system_score_gemma":0.00033015103,"threshold_uncertainty_score":0.50928617},"labels":[],"label_agreement":null},{"id":"W4291746033","doi":"10.3390/app12094419","title":"Automatic Speech Recognition (ASR) Systems for Children: A Systematic Literature Review","year":2022,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":124,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Speech recognition; Computer science; Task (project management); Speech technology; Field (mathematics); Process (computing); Speech processing; Engineering","score_opus":0.028251749218005794,"score_gpt":0.2559027336825049,"score_spread":0.22765098446449908,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4291746033","genre_codex":"review","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0631846,0.53442425,0.22396731,0.014189357,0.011824347,0.06807246,0.0008885911,0.0071696504,0.076279454],"genre_scores_gemma":[0.41558766,0.01565513,0.5105351,0.021811469,0.0007598614,0.033778973,0.00030016192,0.000117310265,0.0014543264],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975089,0.0002368496,0.0005130036,0.0005959859,0.0008012702,0.0003440287],"domain_scores_gemma":[0.9986847,0.0004131806,0.00029944247,0.00042672033,0.000088868794,0.000087113054],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030688778,0.00018450413,0.00045068347,0.00024657644,0.000943297,0.0005420791,0.0013610256,0.00003676836,0.00010415841],"category_scores_gemma":[0.00016115964,0.0001481212,0.00013668295,0.0017821776,0.00006912838,0.00036601452,0.00019280791,0.00013728427,0.00010894685],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014506923,0.00068417,0.00006330006,0.16336945,0.00026122914,0.00006326629,0.0021502685,0.000055825687,0.00097570085,0.093632,0.079497606,0.6592327],"study_design_scores_gemma":[0.005234964,0.002729354,0.00059047504,0.23298852,0.0012713014,0.0134220235,0.005579991,0.63226414,0.009286805,0.07794252,0.010775966,0.00791397],"about_ca_topic_score_codex":0.0000033560439,"about_ca_topic_score_gemma":6.260048e-7,"teacher_disagreement_score":0.6513187,"about_ca_system_score_codex":0.00006328703,"about_ca_system_score_gemma":0.000092295246,"threshold_uncertainty_score":0.72551733},"labels":[],"label_agreement":null},{"id":"W4295308567","doi":"10.1109/jstsp.2022.3206084","title":"Self-Supervised Language Learning From Raw Audio: Lessons From the Zero Resource Speech Challenge","year":2022,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Signal Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto; Connaught Fund; Agence Nationale de la Recherche; École des Hautes Etudes en Sciences Sociales","keywords":"Computer science; Speech recognition; Zero (linguistics); Resource (disambiguation); Artificial intelligence; Natural language processing; Linguistics","score_opus":0.030685832581785723,"score_gpt":0.26361765352844096,"score_spread":0.23293182094665524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4295308567","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84626025,0.006356912,0.12812366,0.015657224,0.0006755281,0.00024734027,0.00000862108,0.00022509288,0.0024453504],"genre_scores_gemma":[0.97235453,0.000070814465,0.026133783,0.0006581428,0.000619373,0.000006101849,0.0000046010105,0.00002075876,0.00013191921],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973969,0.00064402417,0.0005677892,0.00029200656,0.0007913809,0.0003078919],"domain_scores_gemma":[0.99838036,0.0006184356,0.00049328525,0.00019985458,0.00021643157,0.00009165846],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008284162,0.0001757933,0.00031987252,0.00018187323,0.00051218626,0.00026846258,0.0012364691,0.00008140576,0.00018151826],"category_scores_gemma":[0.00015579576,0.00014305455,0.00010548127,0.0008692889,0.000030760184,0.00039778583,0.00015687398,0.0014696383,0.0000052851924],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008554436,0.0003628676,0.0011211763,0.000023073484,0.00012335746,0.00071212836,0.022819107,0.001725334,0.018358044,0.000081580816,0.0009342124,0.9536536],"study_design_scores_gemma":[0.008175573,0.0014338228,0.011292362,0.0013295076,0.00034275796,0.001107535,0.01959295,0.7535428,0.12479451,0.022125551,0.05401676,0.0022458928],"about_ca_topic_score_codex":0.00007655907,"about_ca_topic_score_gemma":0.000036731348,"teacher_disagreement_score":0.9514077,"about_ca_system_score_codex":0.00017788153,"about_ca_system_score_gemma":0.00034554416,"threshold_uncertainty_score":0.6384929},"labels":[],"label_agreement":null},{"id":"W4297804082","doi":"10.55630/dipp.2020.10.5","title":"Cross-Cultural Emotion Recognition and Comparison Using Convolutional Neural Networks","year":2020,"lang":"en","type":"article","venue":"Digital Presentation and Preservation of Cultural and Scientific Heritage","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Convolutional neural network; Emotion recognition; Computer science; Task (project management); Feature (linguistics); Subject (documents); Speech recognition; Natural language processing; Cultural heritage; Psychology; Artificial intelligence; Linguistics; History","score_opus":0.18286233500905522,"score_gpt":0.32968336606741977,"score_spread":0.14682103105836455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297804082","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.977765,0.00025108946,0.020338986,0.0007893766,0.00017868586,0.00020126751,0.000054208136,0.000063626576,0.00035774318],"genre_scores_gemma":[0.99699754,0.000019222123,0.002346038,0.00010935875,0.000058163638,0.000004572288,0.00025879155,0.000004228148,0.00020211242],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987455,0.000066035216,0.00035766678,0.00039059142,0.0002878009,0.00015242031],"domain_scores_gemma":[0.9990928,0.00008980367,0.00016603069,0.00008331535,0.0003996298,0.00016839511],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00015950818,0.0001314814,0.00016938797,0.000052070285,0.00031204044,0.0021234544,0.00012953588,0.000064925734,0.000035046152],"category_scores_gemma":[0.00020390327,0.00010989006,0.000041788182,0.00029868525,0.00035206988,0.005822817,0.00013582528,0.00008915524,0.0000029549587],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040719364,0.00033357073,0.2254223,0.0006308964,0.00016428775,0.000011215677,0.027295811,0.0028400072,0.043788522,0.010229616,0.0035195071,0.6853571],"study_design_scores_gemma":[0.00055868225,0.00006171448,0.04519755,0.000023176442,0.000009149952,0.000018413379,0.0012929627,0.9503027,0.00085131347,0.0007427971,0.0007517334,0.00018981594],"about_ca_topic_score_codex":0.000021336497,"about_ca_topic_score_gemma":0.0000030205567,"teacher_disagreement_score":0.9474627,"about_ca_system_score_codex":0.000008260345,"about_ca_system_score_gemma":0.000010748648,"threshold_uncertainty_score":0.99891245},"labels":[],"label_agreement":null},{"id":"W4297841830","doi":"10.21437/interspeech.2022-11066","title":"SoundChoice: Grapheme-to-Phoneme Models with Semantic Disambiguation","year":2022,"lang":"en","type":"article","venue":"Interspeech 2022","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; Université de Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Grapheme; Computer science; Natural language processing; Artificial intelligence","score_opus":0.01880117531733043,"score_gpt":0.23215500689416602,"score_spread":0.21335383157683557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297841830","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11086264,0.00006651214,0.8707237,0.0070368936,0.0007619806,0.00050139375,0.00001942812,0.00048213446,0.0095452955],"genre_scores_gemma":[0.9490138,0.0000062160325,0.04511077,0.0033745156,0.000052196985,0.0003047211,0.000014131215,0.000029002878,0.0020946008],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980057,0.00013853256,0.00022865683,0.0005497168,0.00075391855,0.00032346757],"domain_scores_gemma":[0.9989725,0.00009459046,0.000088397705,0.0006099125,0.0000988285,0.00013578261],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00038444652,0.00017263593,0.0001769186,0.00035677213,0.00036015036,0.00018011783,0.0010381632,0.000024230776,0.001244545],"category_scores_gemma":[0.00003214419,0.00016521798,0.00009836292,0.0011190748,0.000030123183,0.00042592382,0.00050166703,0.00024287103,0.00018963843],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004918166,0.0019700646,0.0011091107,0.00008226929,0.00056980114,0.00075670646,0.026122602,0.009879524,0.022862148,0.13122024,0.12586449,0.67907125],"study_design_scores_gemma":[0.004395087,0.0032189195,0.0019257849,0.0001894835,0.00015237159,0.0014457603,0.013964999,0.67451304,0.03725662,0.15017377,0.10910386,0.003660271],"about_ca_topic_score_codex":0.00011049683,"about_ca_topic_score_gemma":0.00007115402,"teacher_disagreement_score":0.8381512,"about_ca_system_score_codex":0.00017509022,"about_ca_system_score_gemma":0.00006554546,"threshold_uncertainty_score":0.9996685},"labels":[],"label_agreement":null},{"id":"W4297841867","doi":"10.21437/interspeech.2022-10761","title":"Daft-Exprt: Cross-Speaker Prosody Transfer on Any Text for Expressive Speech Synthesis","year":2022,"lang":"en","type":"article","venue":"Interspeech 2022","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ubisoft (Canada)","funders":"","keywords":"Prosody; Computer science; Speech synthesis; Speech recognition; Transfer (computing); Natural language processing","score_opus":0.02503636111819494,"score_gpt":0.28065545976882816,"score_spread":0.2556190986506332,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297841867","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.59537286,0.0004750758,0.2971759,0.015318927,0.007928592,0.00591102,0.001752002,0.0022934373,0.073772155],"genre_scores_gemma":[0.95982546,0.000019872545,0.024098989,0.0034367284,0.00029581424,0.0031958038,0.000032489887,0.00010612616,0.008988721],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9963897,0.0002781676,0.00052930263,0.001169008,0.0009239573,0.0007099057],"domain_scores_gemma":[0.9974507,0.0009381259,0.00011586435,0.0010824369,0.00020646882,0.00020642062],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008573191,0.0003929927,0.0004294277,0.00042462107,0.00068592286,0.00041872406,0.0020495828,0.000104227656,0.005776633],"category_scores_gemma":[0.00034103214,0.00039059806,0.00047149078,0.00062800344,0.000108084016,0.0004684788,0.0004892619,0.0004905102,0.0003491863],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012658646,0.0026469175,0.0003986921,0.00014325064,0.00050716696,0.0008311617,0.007060428,0.00017577203,0.06669888,0.02606915,0.11626756,0.77793515],"study_design_scores_gemma":[0.0018263167,0.0010906863,0.00054106495,0.00010857885,0.000057522862,0.00033112327,0.0024077585,0.0068698316,0.7281638,0.0038558508,0.25342673,0.0013207768],"about_ca_topic_score_codex":0.00002306814,"about_ca_topic_score_gemma":0.0000074496174,"teacher_disagreement_score":0.77661437,"about_ca_system_score_codex":0.00034286958,"about_ca_system_score_gemma":0.00012545768,"threshold_uncertainty_score":0.99985456},"labels":[],"label_agreement":null},{"id":"W4298028408","doi":"10.48550/arxiv.1803.02551","title":"Extracting Domain Invariant Features by Unsupervised Learning for Robust\\n Automatic Speech Recognition","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Autoencoder; Computer science; Robustness (evolution); Invariant (physics); Speech recognition; Word error rate; Artificial intelligence; Pattern recognition (psychology); Latent variable; Encoder; Domain (mathematical analysis); Deep learning; Mathematics","score_opus":0.093970308576222,"score_gpt":0.20312589556715785,"score_spread":0.10915558699093585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4298028408","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2075502,0.000044918896,0.78620124,0.00020803881,0.00062003365,0.0007012939,0.000035742207,0.00070067385,0.003937832],"genre_scores_gemma":[0.5828132,0.0001585104,0.4129918,0.00033855982,0.0003482742,0.000017052733,0.00028263353,0.00008113403,0.0029688198],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99729174,0.00038494845,0.00032826644,0.001324285,0.00015860498,0.00051212846],"domain_scores_gemma":[0.9976143,0.000641344,0.00046332105,0.0007333101,0.00033789122,0.00020978128],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00085120037,0.00042337325,0.00044948058,0.00037642996,0.0004671014,0.000409469,0.0013013722,0.00050286565,0.0002568305],"category_scores_gemma":[0.0003840413,0.0004900212,0.00033025336,0.00050013966,0.00009308737,0.0006314098,0.0007052761,0.0007293131,0.0002093943],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034231073,0.0012084179,0.0011558066,0.0016987624,0.0013247387,0.0012866642,0.0026421049,0.010635495,0.0036561626,0.009214503,0.03886311,0.9279719],"study_design_scores_gemma":[0.001332144,0.00016337831,0.0003509521,0.00058753183,0.00018442202,0.000061024264,0.0005491862,0.92399204,0.005165153,0.06478957,0.0016054066,0.0012191879],"about_ca_topic_score_codex":0.00009352849,"about_ca_topic_score_gemma":0.000036039448,"teacher_disagreement_score":0.92675275,"about_ca_system_score_codex":0.00023482669,"about_ca_system_score_gemma":0.00017216324,"threshold_uncertainty_score":0.99975514},"labels":[],"label_agreement":null},{"id":"W4299884656","doi":"10.1007/978-3-031-01599-1_5","title":"Speech Synthesis","year":2016,"lang":"en","type":"book-chapter","venue":"Synthesis lectures on assistive, rehabilitative, and health-preserving technologies","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Toronto Rehabilitation Institute","funders":"","keywords":"Phone; Speech synthesis; Computer science; Symbol (formal); Speech recognition; Section (typography); Linguistics; Programming language; Philosophy","score_opus":0.040224558404532165,"score_gpt":0.2880119932924299,"score_spread":0.24778743488789773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4299884656","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002204456,0.008517852,0.011500904,0.1505514,0.0008207263,0.0026261348,0.00063342444,0.007529624,0.8175995],"genre_scores_gemma":[0.14795527,0.045545477,0.59933203,0.0055700312,0.0008546063,0.0046468927,0.000025937354,0.0013147373,0.19475503],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9930039,0.00047053042,0.0013104808,0.0027342883,0.0011874856,0.001293283],"domain_scores_gemma":[0.98099107,0.01402683,0.0011279036,0.003080035,0.00043861757,0.00033554915],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.0018752438,0.0014743813,0.0021936165,0.0018711779,0.0010398774,0.00039683428,0.003436584,0.0014555855,0.00055443135],"category_scores_gemma":[0.010315577,0.0011175622,0.00062159356,0.00031554958,0.0013939504,0.0004661707,0.0015945819,0.0013248221,0.00032369792],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006295415,0.00008301653,0.000073363386,0.00044291685,0.00024541013,0.00004025652,0.00013989166,3.1068086e-7,0.000063442116,0.19931765,0.010730459,0.78880036],"study_design_scores_gemma":[0.00048194025,0.0011791819,0.00498859,0.008397035,0.00013898974,0.00007602948,0.00050290994,0.00016031739,0.009856114,0.81832826,0.15296562,0.0029250078],"about_ca_topic_score_codex":0.000058173726,"about_ca_topic_score_gemma":0.00013976757,"teacher_disagreement_score":0.7858753,"about_ca_system_score_codex":0.0007715186,"about_ca_system_score_gemma":0.0004651105,"threshold_uncertainty_score":0.99984074},"labels":[],"label_agreement":null},{"id":"W4307680525","doi":"10.1162/tacl_a_00545","title":"Generative Spoken Dialogue Language Modeling","year":2023,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Centre National de la Recherche Scientifique; Agence Nationale de la Recherche; École des Hautes Etudes en Sciences Sociales; Canadian Institute for Advanced Research","keywords":"Paralanguage; Computer science; Transformer; Spoken language; Generative grammar; Speech recognition; Natural language processing; Laughter; Language model; Artificial intelligence; Communication; Psychology","score_opus":0.03106876500409547,"score_gpt":0.2777580017736145,"score_spread":0.246689236769519,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307680525","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026197801,0.000008111875,0.9939814,0.00074266706,0.0010412465,0.0001927447,0.00022754264,0.00015305266,0.001033427],"genre_scores_gemma":[0.89606196,0.0000044924436,0.102542266,0.00011297422,0.00016236398,0.000027208984,0.000050872284,0.000009641694,0.0010282442],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990723,0.000058048525,0.00025625908,0.00014638268,0.00032772042,0.00013927567],"domain_scores_gemma":[0.9981995,0.0007700344,0.00016242263,0.00014799347,0.0006903863,0.000029613517],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037885763,0.00007701094,0.00011995999,0.00011909651,0.00026679542,0.00004750771,0.00032060978,0.000057770387,0.0000064012584],"category_scores_gemma":[0.0011929813,0.00006874448,0.00016839194,0.000494014,0.000013098409,0.000048485912,0.000014995077,0.00007721843,0.000026375836],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005890661,0.00005781431,0.00012470609,0.000016929505,0.00010341155,4.3495615e-7,0.000975523,0.9443718,0.00009044241,0.049263537,0.00078013353,0.004209383],"study_design_scores_gemma":[0.00023263063,0.000013668203,0.00033954228,0.00000975468,0.000027076716,5.019593e-7,0.00006681948,0.9604092,0.00084836956,0.037255306,0.00071579585,0.00008129659],"about_ca_topic_score_codex":0.000018345107,"about_ca_topic_score_gemma":0.000012839455,"teacher_disagreement_score":0.89344215,"about_ca_system_score_codex":0.00010090839,"about_ca_system_score_gemma":0.00009153716,"threshold_uncertainty_score":0.28033182},"labels":[],"label_agreement":null},{"id":"W4307783259","doi":"10.48550/arxiv.2210.15775","title":"Evaluating context-invariance in unsupervised speech representations","year":2022,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Connaught Fund; Agence Nationale de la Recherche; Natural Sciences and Engineering Research Council of Canada; Morgan Family Foundation","keywords":"Computer science; Context (archaeology); Benchmark (surveying); Word (group theory); Independence (probability theory); Artificial intelligence; Speech recognition; Natural language processing; Linguistics; Mathematics","score_opus":0.23756314595082362,"score_gpt":0.2724413548986045,"score_spread":0.034878208947780875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307783259","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73935753,0.00010051454,0.23446038,0.00072410674,0.0012778152,0.00086540094,0.000047302638,0.00045835716,0.022708602],"genre_scores_gemma":[0.9821956,0.00009460294,0.01467832,0.00033156114,0.0000419976,0.000009085494,0.000028108308,0.000017988836,0.0026027022],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972728,0.0005888933,0.0003122787,0.001287708,0.00020098647,0.00033735164],"domain_scores_gemma":[0.99777806,0.00041439975,0.00023253824,0.0013041103,0.0001456004,0.0001252915],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000749003,0.00025425496,0.00033715158,0.0004751599,0.0002200497,0.0001495632,0.001879207,0.00016235611,0.0011649953],"category_scores_gemma":[0.00025128917,0.00033510284,0.00020348173,0.0011495326,0.00006210238,0.00038317195,0.0019798486,0.0007209481,0.00013889969],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018896669,0.0012545234,0.035684504,0.00027069778,0.00038859254,0.0062630894,0.004720371,0.3123739,0.00062144815,0.415152,0.0017855976,0.22129631],"study_design_scores_gemma":[0.0011446842,0.000049089944,0.0057249567,0.00009953677,0.000042705335,0.000012720881,0.0009284165,0.9328069,0.00038142104,0.057698607,0.00052306213,0.00058787473],"about_ca_topic_score_codex":0.00065382227,"about_ca_topic_score_gemma":0.00029951692,"teacher_disagreement_score":0.62043303,"about_ca_system_score_codex":0.0003624489,"about_ca_system_score_gemma":0.00034417753,"threshold_uncertainty_score":0.9999101},"labels":[],"label_agreement":null},{"id":"W4310184971","doi":"10.3390/app122312159","title":"Arabic Emotional Voice Conversion Using English Pre-Trained StarGANv2-VC-Based Model","year":2022,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"King Saud University","keywords":"Prosody; Computer science; Speech recognition; Identity (music); Arabic; Natural language processing; Generative grammar; Artificial intelligence; Psychology; Linguistics","score_opus":0.040328397784666285,"score_gpt":0.25196903258446324,"score_spread":0.21164063479979695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310184971","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39127117,0.000017916158,0.59889597,0.0004748745,0.00046134664,0.0002516604,0.000018418948,0.0002667428,0.0083419],"genre_scores_gemma":[0.9007399,8.1677405e-7,0.09784198,0.0012301413,0.000045134122,0.000027335731,0.000004400244,0.0000053171057,0.000104999526],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979033,0.0000778908,0.00019817597,0.0005599373,0.00093267,0.00032801254],"domain_scores_gemma":[0.9992827,0.00018755111,0.00010259861,0.00024405323,0.00008075925,0.00010231601],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009693716,0.00013148648,0.00014100829,0.00022036275,0.0012435479,0.00019547624,0.0011089379,0.00003150273,0.00032474805],"category_scores_gemma":[0.000046388614,0.00012631979,0.00006958888,0.0009588491,0.00020994704,0.00035492828,0.00026086168,0.00014283652,0.000024607953],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011386656,0.0010166146,0.0012639285,0.000065410626,0.000050343337,0.000030434756,0.007846974,0.68243986,0.08705813,0.17000498,0.0048055546,0.045303892],"study_design_scores_gemma":[0.00030591903,0.000046827412,0.00018646475,0.000004538362,0.000005121737,0.000004314951,0.00043202678,0.98635757,0.00824013,0.0033943162,0.000821592,0.00020119443],"about_ca_topic_score_codex":0.00001435494,"about_ca_topic_score_gemma":0.0000034270115,"teacher_disagreement_score":0.50946873,"about_ca_system_score_codex":0.00009540139,"about_ca_system_score_gemma":0.00042938793,"threshold_uncertainty_score":0.95644903},"labels":[],"label_agreement":null},{"id":"W4310892144","doi":"10.14705/rpnet.2022.61.1459","title":"Using Google Voice Typing to automatically assess pronunciation","year":2022,"lang":"en","type":"book-chapter","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal; Concordia University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Pronunciation; Typing; Computer science; Speech recognition; Natural language processing; Test (biology); Artificial intelligence; Linguistics","score_opus":0.12220048908798234,"score_gpt":0.30215750724548485,"score_spread":0.1799570181575025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310892144","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000013082212,0.000010211226,0.38350567,0.00044216064,0.0003004284,0.00024968703,0.0000044659023,0.00029843225,0.61517584],"genre_scores_gemma":[0.00025630445,0.000006645409,0.6655639,0.0023545376,0.0001548822,0.000030294623,0.000010944569,0.000047244062,0.33157524],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99846905,0.0000353511,0.00032737484,0.00047461718,0.00048254576,0.00021108097],"domain_scores_gemma":[0.9989568,0.00015906001,0.00015143804,0.00046731776,0.00014189046,0.00012352351],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00035638578,0.0002127466,0.00025746596,0.00026256088,0.00018115772,0.00023791434,0.0006289725,0.00012710689,0.0043933],"category_scores_gemma":[0.000100089244,0.00021424673,0.000112453294,0.00010082903,0.00001073698,0.00030947884,0.00041528742,0.0002117346,0.0010410589],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000026680436,0.00002539745,0.0000028143563,0.000037723014,0.0000489375,0.000022515163,0.00012918553,0.000039128343,0.00020165177,0.7700486,0.0020943743,0.22734697],"study_design_scores_gemma":[0.00018238211,0.00010486673,0.000084087165,0.00024312985,0.000063876585,0.00008166987,0.000022149488,0.17191446,0.0005372142,0.035547968,0.7901019,0.0011162973],"about_ca_topic_score_codex":0.000017202088,"about_ca_topic_score_gemma":0.000016967777,"teacher_disagreement_score":0.7880075,"about_ca_system_score_codex":0.00031124882,"about_ca_system_score_gemma":0.00021446629,"threshold_uncertainty_score":0.9997367},"labels":[],"label_agreement":null},{"id":"W4312330812","doi":"10.56828/jser.2022.1.1.3","title":"Voiceprint Recognition based on Machine Learning Methods","year":2022,"lang":"en","type":"article","venue":"Journal of Science and Engineering Research","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"","keywords":"Computer science; Speech recognition; Speaker recognition; Identification (biology); Feature (linguistics); Biometrics; Task (project management); Artificial intelligence; Pattern recognition (psychology); Engineering","score_opus":0.10591997324467936,"score_gpt":0.3791078615026312,"score_spread":0.2731878882579518,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312330812","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36455703,0.0003052965,0.6250222,0.0055101034,0.0010635074,0.00019282172,0.0000023153484,0.00009263968,0.0032541156],"genre_scores_gemma":[0.7777312,0.00003830703,0.22202192,0.00010573928,0.000048394104,0.0000073097103,1.5857735e-7,0.0000055106143,0.000041478357],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977661,0.00022234119,0.00017479689,0.00017010774,0.0014034173,0.00026323055],"domain_scores_gemma":[0.9985683,0.0006415937,0.00005827098,0.00012547703,0.0004487244,0.00015765619],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016490342,0.00005511986,0.000098607044,0.0012154486,0.00057753496,0.00019948413,0.0006459425,0.000013637662,0.00007700672],"category_scores_gemma":[0.0021191603,0.00004752538,0.000034884797,0.0016192019,0.00011520984,0.00035497374,0.00024295168,0.0007840529,0.0000060013917],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023435941,0.00007769483,0.00012652892,0.000015460182,0.0000054877664,0.00006158213,0.00043116606,0.014683798,0.060189575,0.0004649814,0.000101319936,0.92381895],"study_design_scores_gemma":[0.00020519653,0.00049687456,0.0013662635,0.000032453892,0.0000015168703,0.0001489186,0.00020613935,0.9712716,0.017737081,0.0004500644,0.0079986425,0.000085289634],"about_ca_topic_score_codex":0.000006102657,"about_ca_topic_score_gemma":1.0977558e-7,"teacher_disagreement_score":0.95658773,"about_ca_system_score_codex":0.00016168707,"about_ca_system_score_gemma":0.00021294628,"threshold_uncertainty_score":0.57152563},"labels":[],"label_agreement":null},{"id":"W4312451460","doi":"10.1109/aike55402.2022.00016","title":"The Effects of Model Capacity in Modelling Variability between Training and Testing Environments for Automatic Speech Recognition","year":2022,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Computer science; Automation; Training (meteorology); Training set; Human–computer interaction; Home automation; Degradation (telecommunications); Speech recognition; Artificial intelligence; Engineering","score_opus":0.14311974578024658,"score_gpt":0.2510602895614192,"score_spread":0.1079405437811726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312451460","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46991804,0.0000038628386,0.52946955,0.000043478532,0.000025592573,0.00026760568,0.000005335074,0.000023779578,0.00024277],"genre_scores_gemma":[0.6184543,0.0000017003587,0.38141155,0.000024284553,0.000005100434,0.00008740699,0.0000012254163,0.0000036282106,0.0000108272725],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989378,0.00018849495,0.00026653672,0.00024091458,0.00019060005,0.0001756493],"domain_scores_gemma":[0.99581367,0.0038655337,0.000096043346,0.00017388002,0.000014937773,0.000035948502],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017237858,0.00007953425,0.00015302395,0.000058527414,0.00026695136,0.00003348635,0.00021979865,0.00002516821,0.0000038023406],"category_scores_gemma":[0.0005450673,0.000067284986,0.00003358816,0.0001623696,0.000035186134,0.00016755819,0.00012077681,0.00010627456,4.7612457e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000019046114,0.00004459105,0.00065362087,0.00005528963,0.000009529172,5.03094e-7,0.0008184717,0.0019689489,0.0008562242,0.0002883087,0.0000023847963,0.99530023],"study_design_scores_gemma":[0.00023094148,0.00005158517,0.00050421705,0.000018481165,0.000008418003,0.0000026875832,0.00007538738,0.92127323,0.0054108878,0.07234263,0.00000482617,0.00007671872],"about_ca_topic_score_codex":0.000025439438,"about_ca_topic_score_gemma":0.0000024410829,"teacher_disagreement_score":0.9952235,"about_ca_system_score_codex":0.000056960893,"about_ca_system_score_gemma":0.000026741558,"threshold_uncertainty_score":0.2743802},"labels":[],"label_agreement":null},{"id":"W4312729122","doi":"10.1121/2.0001664","title":"The Speech and Language Resource Bank: A central index of resources for speech science research and education","year":2020,"lang":"en","type":"article","venue":"Proceedings of meetings on acoustics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Documentation; Resource (disambiguation); Field (mathematics); Fragmentation (computing); Data science; World Wide Web","score_opus":0.030542299761338536,"score_gpt":0.3016588962468001,"score_spread":0.27111659648546155,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312729122","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9891759,0.00017035518,0.00046346302,0.0037560177,0.00004223962,0.00037989317,0.000005466152,0.00003925139,0.005967417],"genre_scores_gemma":[0.963707,0.00007397284,0.035679407,0.00025936597,0.000112679576,0.000013052063,2.54615e-7,0.000011072363,0.00014321593],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9982633,0.000011130917,0.00026999362,0.0003883241,0.00071691733,0.0003503208],"domain_scores_gemma":[0.9977867,0.00067951216,0.0002107649,0.00010735009,0.001036815,0.00017888396],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018975434,0.00010679776,0.00016199509,0.00018557566,0.0003525997,0.00033678566,0.0007362043,0.000057974106,0.0000014836206],"category_scores_gemma":[0.004847095,0.00008318662,0.00002359608,0.0008093623,0.0006429295,0.0001904322,0.00029479884,0.0001838977,6.4652994e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025566333,0.0001828143,0.0031839486,0.000602773,0.000018393752,0.0000012072311,0.0127988,0.0000016458275,0.37709886,0.016279811,0.007368275,0.5822078],"study_design_scores_gemma":[0.0012628294,0.0019241897,0.014604878,0.0008140594,0.000049622504,0.00006621402,0.044754777,0.06622075,0.84346056,0.011184662,0.015072612,0.0005848475],"about_ca_topic_score_codex":0.000014424647,"about_ca_topic_score_gemma":5.49095e-7,"teacher_disagreement_score":0.58162296,"about_ca_system_score_codex":0.000025653724,"about_ca_system_score_gemma":0.00012327889,"threshold_uncertainty_score":0.58027756},"labels":[],"label_agreement":null},{"id":"W4312904577","doi":"10.1007/978-3-031-20980-2_29","title":"An Analytic Study on Clustering-Based Pseudo-labels for Self-supervised Deep Speaker Verification","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Overfitting; Computer science; Cluster analysis; Discriminative model; Artificial intelligence; Embedding; Pattern recognition (psychology); Set (abstract data type); Speaker recognition; Scheme (mathematics); Speech recognition; Machine learning; Artificial neural network; Mathematics","score_opus":0.03380490464928443,"score_gpt":0.2764592676533605,"score_spread":0.24265436300407606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312904577","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011225997,0.00002303892,0.99421483,0.00049514894,0.0012455017,0.0015281517,0.000013732695,0.00035701387,0.000999967],"genre_scores_gemma":[0.38074073,0.0000061116016,0.6155217,0.0031044378,0.0002819099,0.00016682142,0.000028701872,0.00007213679,0.00007741858],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99539155,0.00012713631,0.0005892832,0.0020636055,0.0012383327,0.0005900946],"domain_scores_gemma":[0.99639773,0.0007475256,0.00029064956,0.0020684584,0.00027598525,0.00021965589],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014186972,0.00056113617,0.0005607706,0.0011785654,0.00052182295,0.00068946794,0.0033538628,0.00018985882,0.00015638236],"category_scores_gemma":[0.000093784394,0.0005455418,0.00018710364,0.0007647499,0.00016224862,0.0005553966,0.0003856573,0.0005324956,0.000043046224],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005633134,0.0008600366,0.00016333991,0.00005622844,0.000049210106,0.0000749119,0.0019718572,0.06861929,0.00019120175,0.0019487818,0.0000141575565,0.92599463],"study_design_scores_gemma":[0.0007754933,0.001347855,0.00037644434,0.000061918756,0.00003040761,0.000015307325,0.0000021118312,0.9901259,0.00044003237,0.0054937084,0.0006674683,0.0006633308],"about_ca_topic_score_codex":0.000015430833,"about_ca_topic_score_gemma":0.00016819719,"teacher_disagreement_score":0.9253313,"about_ca_system_score_codex":0.0005210024,"about_ca_system_score_gemma":0.00043476833,"threshold_uncertainty_score":0.9996996},"labels":[],"label_agreement":null},{"id":"W4313042211","doi":"10.1109/ijcnn55064.2022.9892054","title":"Fine-grained Early Frequency Attention for Deep Speaker Recognition","year":2022,"lang":"en","type":"article","venue":"2022 International Joint Conference on Neural Networks (IJCNN)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Focus (optics); Deep neural networks; Deep learning; Artificial intelligence; Key (lock); Artificial neural network; Speech recognition; Pattern recognition (psychology)","score_opus":0.054296543505739286,"score_gpt":0.2565625299664059,"score_spread":0.2022659864606666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313042211","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04104658,0.0000266698,0.9125664,0.017703012,0.0068548685,0.0041033314,0.00022708846,0.0006249438,0.016847054],"genre_scores_gemma":[0.97427964,0.000012403433,0.014978637,0.0024747874,0.00070439494,0.0053546,0.0005132386,0.000043013977,0.0016392563],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99738985,0.00017768904,0.0005341503,0.0007227422,0.00076894264,0.00040662877],"domain_scores_gemma":[0.99856263,0.00021929474,0.0003195655,0.00036284694,0.0004034755,0.0001322007],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004521145,0.0002742956,0.00024493464,0.00031750734,0.00040808422,0.00036282447,0.0009809788,0.000074085576,0.0038498389],"category_scores_gemma":[0.0001304409,0.00028382067,0.00029743416,0.00035558586,0.000044657583,0.00054441113,0.00031471145,0.00044920555,0.00009361592],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046037088,0.0010523066,0.00077081413,0.000023293294,0.00026976631,0.00015182853,0.0003470566,0.0048437947,0.005578844,0.15673502,0.015019793,0.8147471],"study_design_scores_gemma":[0.0014421328,0.0004771664,0.0035696938,0.000050348815,0.000015044355,0.00010545328,0.000060598795,0.96798545,0.00020754003,0.023253618,0.0023672706,0.00046567214],"about_ca_topic_score_codex":0.000031413376,"about_ca_topic_score_gemma":0.000048715625,"teacher_disagreement_score":0.9631417,"about_ca_system_score_codex":0.00018950013,"about_ca_system_score_gemma":0.000051937186,"threshold_uncertainty_score":0.9999614},"labels":[],"label_agreement":null},{"id":"W4313148067","doi":"10.1007/978-3-031-20980-2_21","title":"CRIM’s Speech Recognition System for OpenASR21 Evaluation with Conformer and Voice Activity Detector Embeddings","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Speech recognition; Computer science; Hidden Markov model; Mel-frequency cepstrum; Word error rate; Sentence; Artificial intelligence; Language model; Natural language processing; Pattern recognition (psychology); Feature extraction","score_opus":0.04380244650141289,"score_gpt":0.27454648629349643,"score_spread":0.23074403979208352,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313148067","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031072006,0.00011874871,0.98914564,0.0003319299,0.0010420907,0.0016680564,0.000038087925,0.00017220456,0.0043760263],"genre_scores_gemma":[0.32762054,0.000030793788,0.67060554,0.000821221,0.00034772712,0.00031429855,0.000029648181,0.0000661184,0.00016409022],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962498,0.00008471597,0.00037756393,0.0014675529,0.0013261794,0.0004941721],"domain_scores_gemma":[0.997351,0.0007425577,0.00040671218,0.0006913022,0.00064563495,0.00016282422],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0021961844,0.00046353354,0.00051078975,0.00071543746,0.00053067104,0.00071219023,0.0011668174,0.00021357427,0.00010266922],"category_scores_gemma":[0.0001906726,0.00040785776,0.00009888218,0.0004406235,0.00029712848,0.0012675336,0.00051976764,0.0004938811,0.000023313758],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039626135,0.000016388047,0.000004421893,0.00009836348,0.000017147717,0.000016658943,0.00023363727,0.000110361325,0.00048734457,0.00040347935,0.000009369009,0.99856323],"study_design_scores_gemma":[0.0019369558,0.0010742978,0.00017588181,0.001071467,0.00014122784,0.00091244024,0.00000588352,0.8680178,0.10057294,0.020938346,0.0034048632,0.0017478995],"about_ca_topic_score_codex":0.000047500504,"about_ca_topic_score_gemma":0.00012668838,"teacher_disagreement_score":0.9968153,"about_ca_system_score_codex":0.000654576,"about_ca_system_score_gemma":0.00062298373,"threshold_uncertainty_score":0.99983734},"labels":[],"label_agreement":null},{"id":"W4313228380","doi":"10.1561/116.00000017","title":"An Application-Oriented Taxonomy on Spoofing, D isguise and Countermeasures in Speaker Recognition","year":2022,"lang":"en","type":"article","venue":"APSIPA Transactions on Signal and Information Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Spoofing attack; Taxonomy (biology); Computer science; Speaker recognition; Speech recognition; Computer security; Biology; Botany","score_opus":0.019150673068162115,"score_gpt":0.22176721218037682,"score_spread":0.2026165391122147,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313228380","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043570496,0.000030092398,0.9512847,0.0004574081,0.00006996129,0.00037831618,0.000029208772,0.00012398604,0.0040558544],"genre_scores_gemma":[0.99251527,0.000019424944,0.0051141176,0.0019226191,0.000012512086,0.0003614133,0.000031669522,0.0000049383807,0.000018051289],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99902266,0.000062213214,0.00029731388,0.00020541556,0.0002726176,0.0001397555],"domain_scores_gemma":[0.99955356,0.000046036344,0.00012012882,0.00011977457,0.00008549041,0.000075031276],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033106704,0.00011901811,0.000107873915,0.00040655534,0.0005503322,0.00022097095,0.00012385227,0.00003587926,0.00014009788],"category_scores_gemma":[0.000006023098,0.00012111956,0.000022781094,0.00040576447,0.00003512203,0.0030386013,0.0000064015517,0.00020130734,0.00002258146],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052463434,0.00010965252,0.000053399086,0.000021382622,0.0000039270294,8.1088785e-7,0.000872594,0.00043138355,0.00009960405,0.00053135183,0.000017439303,0.997806],"study_design_scores_gemma":[0.0026553844,0.00086898514,0.00567058,0.00019129096,0.000031484127,0.00016172424,0.0041421806,0.89532304,0.00836679,0.002800975,0.07888051,0.0009070427],"about_ca_topic_score_codex":0.000024397554,"about_ca_topic_score_gemma":0.000006776099,"teacher_disagreement_score":0.99689895,"about_ca_system_score_codex":0.000057865178,"about_ca_system_score_gemma":0.000048481972,"threshold_uncertainty_score":0.49391124},"labels":[],"label_agreement":null},{"id":"W4315645596","doi":"10.18280/isi.270614","title":"Indonesian Automatic Speech Recognition with XLSR-53","year":2022,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Indonesian; Word error rate; Speech recognition; Computer science; MAGIC (telescope); Word (group theory); Natural language processing; Language model; Training set; Artificial intelligence; Linguistics","score_opus":0.01775987249685566,"score_gpt":0.21229777143432518,"score_spread":0.19453789893746953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4315645596","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5636976,0.00003636457,0.37577358,0.0006332805,0.0007365425,0.0009720636,0.000058137077,0.0015477509,0.0565447],"genre_scores_gemma":[0.8745731,0.000005778293,0.12373142,0.001056926,0.00004088818,0.00035166473,0.0001434534,0.000014859905,0.000081927916],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99833494,0.00013714527,0.00046795353,0.00017692726,0.0005817199,0.0003013069],"domain_scores_gemma":[0.9989649,0.000083272185,0.00031572187,0.0003564428,0.00018450143,0.000095182535],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055997603,0.00017343962,0.00018809634,0.0004622731,0.00064890535,0.00042666116,0.00049676036,0.00004917071,0.0005084591],"category_scores_gemma":[0.00008982255,0.00016398731,0.000062767656,0.0009660475,0.00005825128,0.004256032,0.00016902588,0.00018646377,0.0004211778],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013543129,0.000035297966,0.00021050776,0.000069192414,0.000022383858,0.00001486322,0.0029691132,0.000026678805,0.00003062543,0.000799351,0.0004270022,0.9953814],"study_design_scores_gemma":[0.0077224798,0.0032655676,0.04632855,0.0009494725,0.00020354075,0.010799026,0.021112531,0.70148987,0.038745157,0.06676506,0.09774349,0.0048752446],"about_ca_topic_score_codex":0.00004755872,"about_ca_topic_score_gemma":0.0000064975743,"teacher_disagreement_score":0.9905062,"about_ca_system_score_codex":0.00032759682,"about_ca_system_score_gemma":0.00013098479,"threshold_uncertainty_score":0.66872084},"labels":[],"label_agreement":null},{"id":"W4315700151","doi":"","title":"I-vector based Representation of Highly Imperfect Automatic Transcriptions","year":2014,"lang":"en","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Imperfect; Representation (politics); Artificial intelligence; Natural language processing; Linguistics","score_opus":0.015819957402144164,"score_gpt":0.2273022812769938,"score_spread":0.21148232387484964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4315700151","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08407303,0.000042376723,0.8816462,0.0073928935,0.000107510554,0.00018719345,0.000007843149,0.00031085676,0.026232108],"genre_scores_gemma":[0.7903506,0.00001464929,0.20876674,0.000118399366,0.000007119013,0.000028135037,0.000024707135,0.00001145017,0.00067817053],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9951675,0.0034819525,0.00039775294,0.00039286632,0.0003536431,0.00020630637],"domain_scores_gemma":[0.99545467,0.0019860421,0.00023367052,0.0013057612,0.0008985289,0.000121324556],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026221527,0.00014254409,0.00022740668,0.00020839625,0.00020015858,0.00017041682,0.00086387363,0.00007466153,0.00019820199],"category_scores_gemma":[0.0014797167,0.00014398471,0.00017462656,0.0007244005,0.00010930317,0.00031124838,0.000083038896,0.0001113613,0.000063194966],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005675992,0.00069822156,0.0012773192,0.00009814837,0.0000460579,0.000001760855,0.0038695293,0.000026673788,0.11326268,0.30668852,0.0008599802,0.5731654],"study_design_scores_gemma":[0.0005986713,0.0000011575163,0.01153425,0.00029138706,0.00002191913,0.000006510346,0.00003344214,0.44443694,0.5378083,0.0027466537,0.002307123,0.00021366759],"about_ca_topic_score_codex":0.00023841766,"about_ca_topic_score_gemma":0.00020640754,"teacher_disagreement_score":0.7062776,"about_ca_system_score_codex":0.000035190587,"about_ca_system_score_gemma":0.00009012545,"threshold_uncertainty_score":0.5871526},"labels":[],"label_agreement":null},{"id":"W4318003022","doi":"10.1109/gcaiot57150.2022.10019087","title":"Mitigating the effects of temporal distortion in a copy-detection based playback attack detector","year":2022,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Distortion (music); Computer science; Detector; Similarity (geometry); Speech recognition; Measure (data warehouse); Channel (broadcasting); Similarity measure; Artificial intelligence; Pattern recognition (psychology); Data mining; Telecommunications; Bandwidth (computing)","score_opus":0.014833054637465586,"score_gpt":0.2341417956944769,"score_spread":0.2193087410570113,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318003022","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8853052,0.000024442843,0.11315017,0.00025225297,0.00035317382,0.00027545594,0.0000017593723,0.00008217797,0.0005553195],"genre_scores_gemma":[0.9952031,5.017984e-7,0.0043564164,0.0002535749,0.000013488491,0.00010124874,0.0000013351917,0.000004956389,0.00006538181],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989432,0.00026645573,0.00020963332,0.0001857775,0.00027094886,0.00012396053],"domain_scores_gemma":[0.9991342,0.0004815575,0.000104623745,0.00022783654,0.000024619569,0.000027177517],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039522356,0.00007116723,0.00010180364,0.000103613114,0.0001531822,0.000028546696,0.00029136482,0.00002047043,0.00013476674],"category_scores_gemma":[0.00013363794,0.00005530471,0.00006606073,0.00048263287,0.000024210312,0.00011232402,0.00008600543,0.00012612279,0.00000938639],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000104308165,0.000550896,0.027334258,0.0002448478,0.000038209757,0.000053614993,0.0018998367,0.00071411807,0.12797488,0.00049889775,0.00085370336,0.8397324],"study_design_scores_gemma":[0.0011127144,0.00049149897,0.036061,0.000044950655,0.000009502832,0.00001522549,0.00025488838,0.28477716,0.675804,0.00030305443,0.0008800482,0.0002459013],"about_ca_topic_score_codex":0.000119313205,"about_ca_topic_score_gemma":0.000145749,"teacher_disagreement_score":0.83948654,"about_ca_system_score_codex":0.000091907226,"about_ca_system_score_gemma":0.00003567498,"threshold_uncertainty_score":0.22552606},"labels":[],"label_agreement":null},{"id":"W4318148717","doi":"10.1109/tai.2023.3240113","title":"Fine-Grained Early Frequency Attention for Deep Speaker Representation Learning","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Artificial Intelligence","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Robustness (evolution); Speech recognition; Deep learning; Convolutional neural network; Artificial intelligence; Speaker recognition; Feature learning; Speech processing; Transfer of learning","score_opus":0.09106019514806173,"score_gpt":0.32258037748894486,"score_spread":0.23152018234088312,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318148717","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030832063,0.000003548522,0.96560925,0.0009615134,0.0011095864,0.00038377408,0.000008933852,0.0006569756,0.00043432275],"genre_scores_gemma":[0.9679639,0.00001656432,0.030654058,0.00007074758,0.00009241971,0.00020009503,0.000009020876,0.000021715643,0.00097151526],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99835944,0.000083603554,0.00041484172,0.000509484,0.00030183987,0.00033081853],"domain_scores_gemma":[0.99883616,0.00045063117,0.00009929799,0.00032537716,0.00019202555,0.000096518954],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00038098296,0.00015987361,0.00015284422,0.00039959088,0.0004481005,0.0002183443,0.00034553377,0.00009238617,0.00015449314],"category_scores_gemma":[0.00009186889,0.0001696977,0.00021781272,0.0012190484,0.00005334342,0.0004650655,0.0000026546525,0.00020203236,0.0014159972],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003571836,0.00014185371,0.00001828887,0.000010375947,0.000030427016,0.0000074019526,0.00071086135,0.010859254,0.033705905,0.0063263504,0.000042755346,0.9481108],"study_design_scores_gemma":[0.00009657309,0.00027895975,0.0005101381,0.000044322303,0.000029553055,0.000010040824,0.0004245621,0.5634347,0.39675996,0.037801344,0.0002298248,0.0003799958],"about_ca_topic_score_codex":0.00006607993,"about_ca_topic_score_gemma":0.00020752149,"teacher_disagreement_score":0.94773084,"about_ca_system_score_codex":0.000048189322,"about_ca_system_score_gemma":0.000029630584,"threshold_uncertainty_score":0.9993615},"labels":[],"label_agreement":null},{"id":"W4319862473","doi":"10.1109/slt54892.2023.10022470","title":"A Comprehensive Study on Self-Supervised Distillation for Speaker Representation Learning","year":2023,"lang":"en","type":"article","venue":"2022 IEEE Spoken Language Technology Workshop (SLT)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Benchmark (surveying); Representation (politics); Speaker recognition; Speech recognition; Artificial intelligence; Word error rate; Training set; Feature learning; Machine learning","score_opus":0.037294017843743366,"score_gpt":0.32256218263729897,"score_spread":0.2852681647935556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319862473","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96011466,0.000065660824,0.031475354,0.0014572798,0.0006073194,0.001358081,0.000008685136,0.0039847777,0.00092816894],"genre_scores_gemma":[0.98562986,0.00002381792,0.012194232,0.0001997926,0.00013086376,0.00037187847,0.000052850486,0.000041266456,0.0013554149],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979411,0.00015372637,0.00034030052,0.0007766965,0.00034976902,0.00043842464],"domain_scores_gemma":[0.9982219,0.00064865267,0.00015239533,0.0007808403,0.00013083917,0.00006538912],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002943006,0.00024544421,0.00032955984,0.000897788,0.0003188644,0.00010393142,0.0006520097,0.00021765636,0.00007054593],"category_scores_gemma":[0.00039762596,0.00024278164,0.00012716441,0.0024737285,0.000053661493,0.00019770865,0.00018901107,0.00040182896,0.00041656374],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019278891,0.00091855373,0.0127081,0.000070734925,0.00050759735,0.0008852363,0.021178469,0.0012396824,0.021902855,0.0037572342,0.010011953,0.9266268],"study_design_scores_gemma":[0.009836495,0.002268631,0.08648338,0.00026677563,0.00031755658,0.00016133787,0.18105401,0.654527,0.04160882,0.0056816884,0.014970621,0.0028236937],"about_ca_topic_score_codex":0.000014083491,"about_ca_topic_score_gemma":0.000023962031,"teacher_disagreement_score":0.9238031,"about_ca_system_score_codex":0.000086169995,"about_ca_system_score_gemma":0.000027150783,"threshold_uncertainty_score":0.99003476},"labels":[],"label_agreement":null},{"id":"W4319862706","doi":"10.1109/slt54892.2023.10022986","title":"Flow-ER: A Flow-Based Embedding Regularization Strategy for Robust Speech Representation Learning","year":2023,"lang":"en","type":"article","venue":"2022 IEEE Spoken Language Technology Workshop (SLT)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Embedding; Computer science; Regularization (linguistics); Artificial intelligence; Machine learning; Deep learning; Speech recognition; Representation (politics); Feature learning; Bottleneck; Task (project management)","score_opus":0.03353607308453113,"score_gpt":0.30544206453765,"score_spread":0.2719059914531189,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319862706","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08357388,0.00014863664,0.90681905,0.0027652148,0.000731878,0.0008052749,0.000019646406,0.004271099,0.00086533633],"genre_scores_gemma":[0.40599573,0.00007892247,0.580592,0.0004460055,0.00043358028,0.0007223342,0.000610472,0.00014889396,0.010972075],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99740285,0.0001401072,0.00046238356,0.0009251652,0.0004022735,0.00066725316],"domain_scores_gemma":[0.9982321,0.00038448095,0.00023015447,0.00089127844,0.00016800409,0.00009395161],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00078883895,0.0003021235,0.0003758432,0.0013187075,0.00043113696,0.00022436815,0.0009338796,0.00048011867,0.00024423754],"category_scores_gemma":[0.0009493889,0.00032504712,0.00018661097,0.0038245977,0.00010349817,0.00038217645,0.00017191417,0.0005407744,0.00025321357],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046582438,0.00008159614,0.00032391545,0.00005193235,0.00008116487,0.000355288,0.0007726929,0.14048637,0.012983515,0.0013379232,0.005775098,0.83770394],"study_design_scores_gemma":[0.0007272897,0.000072280265,0.000088283996,0.00007656162,0.000031816337,0.000036322897,0.0027477492,0.9545882,0.039046746,0.0016393021,0.0005752031,0.00037023946],"about_ca_topic_score_codex":0.000011536282,"about_ca_topic_score_gemma":0.00005518499,"teacher_disagreement_score":0.8373337,"about_ca_system_score_codex":0.00012203709,"about_ca_system_score_gemma":0.00009946498,"threshold_uncertainty_score":0.9999201},"labels":[],"label_agreement":null},{"id":"W4320086272","doi":"10.48550/arxiv.2206.01685","title":"Toward a realistic model of speech processing in the brain with\\n self-supervised learning","year":2022,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; University of Toronto","funders":"","keywords":"Computer science; Functional magnetic resonance imaging; Artificial intelligence; Hierarchy; Speech recognition; Benchmark (surveying); Neuroimaging; Natural language processing; Machine learning; Psychology; Neuroscience","score_opus":0.13240354466124338,"score_gpt":0.20674851802463984,"score_spread":0.07434497336339646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4320086272","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43997496,0.000059209684,0.5398253,0.0009101425,0.00012393345,0.00096565566,0.000025057896,0.0002033251,0.017912425],"genre_scores_gemma":[0.9811032,0.00020138148,0.017359754,0.00027845043,0.000039245468,0.000006870783,0.000016507323,0.000037616723,0.0009569907],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9953128,0.0013104449,0.0005719265,0.0016837217,0.00047889352,0.0006422232],"domain_scores_gemma":[0.99704444,0.0005806825,0.0006933186,0.0011819187,0.00033509923,0.00016454606],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0018671658,0.0005607913,0.00072934723,0.00070291414,0.0005100304,0.00025392103,0.0033644577,0.00027184392,0.00028965407],"category_scores_gemma":[0.00021375525,0.00053018937,0.00030941877,0.0026066261,0.00025280795,0.00054946664,0.0014911287,0.0017638222,0.00001904288],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030334157,0.00062883,0.002464246,0.00075145136,0.00011532429,0.001562248,0.019233966,0.91326445,0.00009914344,0.018074054,0.000038279602,0.04346469],"study_design_scores_gemma":[0.0010014822,0.00019193269,0.00035742833,0.00032502317,0.00016726671,0.00005028926,0.005489228,0.9842938,0.00007802879,0.0072561996,0.00016997675,0.0006193474],"about_ca_topic_score_codex":0.00040789443,"about_ca_topic_score_gemma":0.000111143716,"teacher_disagreement_score":0.5411282,"about_ca_system_score_codex":0.00039702197,"about_ca_system_score_gemma":0.0010918343,"threshold_uncertainty_score":0.999715},"labels":[],"label_agreement":null},{"id":"W4321513043","doi":"10.1007/978-3-031-11035-1_2","title":"Improving Automatic Speech Recognition for Non-native English with Transfer Learning and Language Model Decoding","year":2022,"lang":"en","type":"book-chapter","venue":"Signals and communication technology","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Decoding methods; Computer science; Speech recognition; Transfer of learning; Voice activity detection; Acoustic model; Language model; Speech processing; Set (abstract data type); Natural language processing; Artificial intelligence; Telecommunications","score_opus":0.020601723571282447,"score_gpt":0.24169538823306397,"score_spread":0.2210936646617815,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321513043","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019898353,0.0039365618,0.831579,0.0018851447,0.00008939565,0.002662465,0.00010891136,0.0017996688,0.13804047],"genre_scores_gemma":[0.17532669,0.005085561,0.802637,0.0004119514,0.000047620168,0.00093443954,0.00021805135,0.00013943507,0.015199258],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998932,0.000055448756,0.00029361574,0.00039561006,0.00013830802,0.00018503935],"domain_scores_gemma":[0.9986766,0.0004453458,0.00019789157,0.00042190854,0.00021664031,0.000041618554],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043598117,0.00022493562,0.00033743223,0.00044321344,0.00050108717,0.00007860031,0.000468256,0.0002914099,0.00012312524],"category_scores_gemma":[0.00009679974,0.00022177606,0.000050066243,0.00009565382,0.00014322685,0.0002450952,0.00030289355,0.0006529495,0.000002325767],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008301488,0.000011103878,0.0000036621755,0.00006550535,0.000050001312,0.0000023906227,0.0011613623,0.0000023885125,0.00040746626,0.025815967,0.000014767202,0.9724571],"study_design_scores_gemma":[0.0021700102,0.0008848249,0.000004966442,0.00093215617,0.00027761408,0.00012285018,0.005127769,0.77531934,0.011588892,0.19271672,0.009372568,0.0014823197],"about_ca_topic_score_codex":0.00000766892,"about_ca_topic_score_gemma":0.000023099492,"teacher_disagreement_score":0.97097474,"about_ca_system_score_codex":0.0000410364,"about_ca_system_score_gemma":0.00005995165,"threshold_uncertainty_score":0.9043765},"labels":[],"label_agreement":null},{"id":"W4324269592","doi":"10.1007/978-981-19-6406-0_9","title":"Overview of Incorporating Nonlinear Functions into Recurrent Neural Network Models","year":2022,"lang":"en","type":"book-chapter","venue":"Springer proceedings in mathematics & statistics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Recurrent neural network; Computer science; Artificial neural network; Artificial intelligence; Range (aeronautics); Nonlinear system; Time delay neural network; Long short term memory; Machine learning; Speech recognition; Engineering","score_opus":0.06969708072922273,"score_gpt":0.28067170098954985,"score_spread":0.21097462026032712,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4324269592","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020509973,0.0017480578,0.65672475,0.00022597423,0.0017504875,0.0015573455,0.00041297593,0.00038502706,0.33699027],"genre_scores_gemma":[0.00028282762,0.0007394984,0.99094856,0.00006126184,0.00015376318,0.000068670386,0.000039226696,0.00009442008,0.0076117935],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99688184,0.000014176038,0.0012967467,0.00059038826,0.00085929316,0.00035754556],"domain_scores_gemma":[0.9974596,0.000355449,0.0012476614,0.00039842707,0.0004226156,0.00011627549],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00084134296,0.00046538576,0.00080515473,0.0003606704,0.00018432736,0.00014879784,0.00093213737,0.00018481475,0.00028496224],"category_scores_gemma":[0.00020492723,0.0005002877,0.00015343506,0.00023637501,0.000104103136,0.00033882164,0.0008488053,0.00079753454,0.000032567514],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000038751887,0.00009352793,0.000011297298,0.001464867,0.000048173566,0.00001873036,0.00089542515,0.00031588442,0.0000055956484,0.9538435,0.0010444465,0.042254694],"study_design_scores_gemma":[0.00013242943,0.000081072605,0.0000036348172,0.0007755313,0.00005952354,0.000016483173,0.00006047278,0.3383604,0.000010496013,0.6536783,0.0064112945,0.00041035473],"about_ca_topic_score_codex":0.000011517691,"about_ca_topic_score_gemma":0.000017673192,"teacher_disagreement_score":0.33804452,"about_ca_system_score_codex":0.0002079957,"about_ca_system_score_gemma":0.00014943613,"threshold_uncertainty_score":0.9997449},"labels":[],"label_agreement":null},{"id":"W4324386959","doi":"10.1007/s11042-023-14412-2","title":"The voice as a material clue: a new forensic Algerian Corpus","year":2023,"lang":"en","type":"article","venue":"Multimedia Tools and Applications","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Computer science; Stress (linguistics); Arabic; Session (web analytics); Speech recognition; Natural language processing; Feature (linguistics); Linguistics; World Wide Web","score_opus":0.02979908837243485,"score_gpt":0.26438318273401457,"score_spread":0.2345840943615797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4324386959","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12728073,0.00088301435,0.6929397,0.115068175,0.004253704,0.0080955,0.0006651001,0.0058191083,0.04499497],"genre_scores_gemma":[0.3769547,0.005690941,0.53346074,0.009356251,0.007995448,0.011451053,0.0008779135,0.000234745,0.053978194],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99921584,0.000024138077,0.0001554415,0.00025234243,0.00013854462,0.00021366891],"domain_scores_gemma":[0.9989912,0.0004069444,0.000052274263,0.00036442507,0.00003975782,0.00014539738],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000145811,0.000092650516,0.000090455374,0.00004208985,0.00039297223,0.00046194362,0.000372753,0.000045591183,0.000035567828],"category_scores_gemma":[0.00007965089,0.00006774779,0.000038525246,0.00038538023,0.000066748325,0.00014902434,0.0001303413,0.000056501554,0.0013888216],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000029123894,0.000008777927,0.000015713735,0.0000019941942,0.000007433305,0.0000016580567,0.00012230343,3.329263e-7,0.0014488561,0.008572783,0.0078433715,0.9819739],"study_design_scores_gemma":[0.00044419273,0.000029710349,0.006774227,0.000012389913,0.000014233369,0.000033751927,0.00012446466,0.021615557,0.009260961,0.024279008,0.9371671,0.00024442407],"about_ca_topic_score_codex":0.000060723323,"about_ca_topic_score_gemma":0.000037836635,"teacher_disagreement_score":0.98172945,"about_ca_system_score_codex":0.000009943383,"about_ca_system_score_gemma":0.000060548344,"threshold_uncertainty_score":0.9993887},"labels":[],"label_agreement":null},{"id":"W4361795437","doi":"10.2139/ssrn.4394373","title":"Domain-General Vs. Domain-Specific Pre-Trained Models Binary Patch Grouping for Improved WSI Representation","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"William Osler Health System; University of Waterloo; McMaster University","funders":"","keywords":"Domain (mathematical analysis); Representation (politics); Binary number; Computer science; Artificial intelligence; Pattern recognition (psychology); Mathematics; Arithmetic; Mathematical analysis","score_opus":0.04305255522905972,"score_gpt":0.2867782409578404,"score_spread":0.24372568572878067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4361795437","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06092416,0.00090232794,0.92892855,0.005256195,0.0020916967,0.0011552942,0.000034715875,0.00043292233,0.00027413157],"genre_scores_gemma":[0.18599717,0.026397098,0.77071047,0.0009750026,0.0062769647,0.0013496006,0.00050569366,0.0004950253,0.0072929654],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99342656,0.00038726587,0.00106659,0.0013145494,0.0006554023,0.0031496058],"domain_scores_gemma":[0.9971924,0.00030215437,0.00081725436,0.001033131,0.00041133282,0.00024376929],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0037254093,0.0005900777,0.0007250742,0.0006364495,0.00062288006,0.00084239093,0.0020429024,0.00047002605,0.000016468988],"category_scores_gemma":[0.000043869022,0.0005790681,0.00081865356,0.0005131028,0.00006982408,0.0007317432,0.00073472614,0.0029733875,0.000030081168],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007040588,0.00036037542,0.000060564482,0.00014090678,0.0012262053,0.00006718345,0.0025863517,0.003200919,0.010358875,0.6873757,0.00294081,0.29097804],"study_design_scores_gemma":[0.0013352953,0.0003064311,0.00015903692,0.00012261202,0.000038368427,0.00029051647,0.0005192639,0.07562276,0.00046834096,0.91829586,0.0021919566,0.00064959057],"about_ca_topic_score_codex":0.00012481752,"about_ca_topic_score_gemma":0.00027623237,"teacher_disagreement_score":0.29032847,"about_ca_system_score_codex":0.0017388636,"about_ca_system_score_gemma":0.0024343717,"threshold_uncertainty_score":0.9996661},"labels":[],"label_agreement":null},{"id":"W4362558814","doi":"10.58837/chula.the.2020.141","title":"Using automatic speech recognition to assess Thai speech language fluency in montreal cognitive assessment (MoCA)","year":2020,"lang":"en","type":"dissertation","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Speech recognition; Hidden Markov model; Fluency; Language model; Artificial intelligence; Natural language processing; Test set; Psychology","score_opus":0.072513247186501,"score_gpt":0.35510322075969214,"score_spread":0.28258997357319116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362558814","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7547568,0.00006285016,0.05103944,0.0003916327,0.0012398171,0.002049571,0.00009679089,0.00074277073,0.18962032],"genre_scores_gemma":[0.23471782,0.000052529573,0.75693643,0.0020678688,0.00030176208,0.00031539498,0.0017523322,0.00013548297,0.0037204055],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.995756,0.00036182348,0.0009159589,0.001277341,0.0010604744,0.0006284129],"domain_scores_gemma":[0.99791974,0.00047746676,0.0003902835,0.00048255292,0.00036903302,0.0003608988],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005549971,0.0006455529,0.0008516914,0.0009489324,0.0001425349,0.0005801527,0.0008802636,0.00043946595,0.0014852992],"category_scores_gemma":[0.00046736232,0.00066305546,0.00024570554,0.0015271401,0.000018614455,0.00080290134,0.00014855889,0.00067031727,0.00090898527],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002665587,0.00026342066,0.00023383099,0.00017309186,0.00008263918,0.0008010813,0.0024155267,9.885334e-7,0.0023196195,0.000066424174,0.00030066082,0.99331605],"study_design_scores_gemma":[0.005749838,0.001120178,0.12947746,0.008823055,0.0009122294,0.00056350615,0.05866758,0.3891286,0.38652682,0.010860593,0.00020875163,0.007961409],"about_ca_topic_score_codex":0.0013243271,"about_ca_topic_score_gemma":0.0053022434,"teacher_disagreement_score":0.98535466,"about_ca_system_score_codex":0.00037623112,"about_ca_system_score_gemma":0.00049604505,"threshold_uncertainty_score":0.9998689},"labels":[],"label_agreement":null},{"id":"W4367145625","doi":"10.1121/10.0019208","title":"Using the Corpus of North American Spoken English to explore regional variation in millions of eɪ diphthongs","year":2023,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; American English; Python (programming language); Diphthong; Speech recognition; Speech corpus; Coarticulation; Natural language processing; Variation (astronomy); Variety (cybernetics); Artificial intelligence; Speech synthesis; Linguistics; Vowel","score_opus":0.06297583373034152,"score_gpt":0.2886126725932716,"score_spread":0.2256368388629301,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367145625","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5957384,0.000019898223,0.39718926,0.0066472813,0.00020863426,0.00014356463,0.000010040422,0.000012318769,0.00003058267],"genre_scores_gemma":[0.8945886,0.00025212043,0.10400273,0.0010166477,0.00011638442,0.0000016495283,2.8076602e-7,0.000008904217,0.000012710403],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982501,0.0002720466,0.0005346049,0.00009882018,0.00065157097,0.0001928329],"domain_scores_gemma":[0.99712044,0.0012951446,0.00076038303,0.00036248192,0.00039455405,0.00006697728],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008458487,0.00010009953,0.00032736838,0.000065829496,0.000107485735,0.000013266701,0.0011704832,0.00002503468,0.000007276832],"category_scores_gemma":[0.0006225885,0.000052037078,0.00031733396,0.0019949824,0.00051622634,0.000106898915,0.00026820536,0.00025198603,0.0000014654516],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007794948,0.001600739,0.016718982,0.000202576,0.0012516594,0.0000150932065,0.14238696,0.1529465,0.09975946,0.00033320813,0.06096805,0.5230373],"study_design_scores_gemma":[0.00063041,0.00057610107,0.34135708,0.00029863178,0.00028029035,0.000059912814,0.014256423,0.63515407,0.004125635,0.0016514204,0.0013273827,0.00028263568],"about_ca_topic_score_codex":0.0001984184,"about_ca_topic_score_gemma":0.0000060462703,"teacher_disagreement_score":0.52275467,"about_ca_system_score_codex":0.000050018163,"about_ca_system_score_gemma":0.00011577127,"threshold_uncertainty_score":0.21750684},"labels":[],"label_agreement":null},{"id":"W4367280348","doi":"10.1121/10.0018553","title":"Perception error variation in masking contexts","year":2023,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Masking (illustration); Noise (video); Confusion; Variation (astronomy); Perception; Speech perception; Speech recognition; Computer science; Word (group theory); Mathematics; Psychology; Artificial intelligence; Physics","score_opus":0.024518950563863617,"score_gpt":0.2736917242615607,"score_spread":0.24917277369769708,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367280348","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039013937,0.000019856316,0.9451696,0.015269174,0.00026305622,0.000075197706,0.0000011997686,0.000020557603,0.00016737056],"genre_scores_gemma":[0.9120896,0.00014764049,0.086319834,0.0012941387,0.00007608246,7.9254795e-7,9.400072e-8,0.000004767282,0.00006706724],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99892175,0.00019568704,0.00030050767,0.0000637363,0.0003778321,0.00014045651],"domain_scores_gemma":[0.99881643,0.00057942455,0.00027819222,0.0001881287,0.00010378833,0.00003401576],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010057304,0.00006113202,0.00015394029,0.000033107477,0.00009450539,0.000022051512,0.0006544113,0.0000388742,0.00004302856],"category_scores_gemma":[0.00027556054,0.000033098517,0.00020584793,0.0005919594,0.0001244521,0.00014279192,0.00013319604,0.00021972168,0.000021620603],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000081399936,0.00023454975,0.0004981621,0.000043117543,0.00014460605,0.0000054213374,0.014508787,0.0095341755,0.102285095,0.00013358289,0.02916519,0.8433659],"study_design_scores_gemma":[0.00028811535,0.0000793444,0.069471434,0.00007754614,0.00003855883,0.00003730408,0.0022704683,0.9229913,0.00032998627,0.003903355,0.00043935317,0.00007328509],"about_ca_topic_score_codex":0.000024431696,"about_ca_topic_score_gemma":4.7808265e-7,"teacher_disagreement_score":0.9134571,"about_ca_system_score_codex":0.000054624412,"about_ca_system_score_gemma":0.000046150988,"threshold_uncertainty_score":0.13497183},"labels":[],"label_agreement":null},{"id":"W4367627905","doi":"10.3390/electronics12092055","title":"Knowledge-Based Features for Speech Analysis and Classification: Pronunciation Diagnoses","year":2023,"lang":"en","type":"article","venue":"Electronics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Pronunciation; Computer science; Articulation (sociology); Speech recognition; Speech production; Natural language processing; Artificial intelligence; Linguistics","score_opus":0.03250779710277582,"score_gpt":0.2931780798860759,"score_spread":0.26067028278330007,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367627905","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.079088934,0.0048395935,0.8981281,0.011113885,0.0003412148,0.001157546,0.00002633088,0.001435253,0.0038691587],"genre_scores_gemma":[0.8716645,0.0013886493,0.12063989,0.0007154563,0.000280753,0.00071187975,0.00024054394,0.000037214333,0.0043211104],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991588,0.000044303746,0.00012347706,0.0002952105,0.00013518882,0.00024304225],"domain_scores_gemma":[0.9990909,0.00042861357,0.00006061106,0.0002395429,0.00013176113,0.000048566788],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034438976,0.000088583445,0.00012994143,0.00033031814,0.00014430025,0.00013783743,0.00021143536,0.000061118015,0.0000099260305],"category_scores_gemma":[0.00021410309,0.00008346252,0.00008996715,0.0016293833,0.0000163639,0.00012810963,0.000024423854,0.00006562473,0.000050226365],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007429748,0.000059607475,0.0013713759,0.000019416742,0.00011488836,0.000001277888,0.00012665377,0.00001579256,0.0007904433,0.014570747,0.0056700394,0.9772523],"study_design_scores_gemma":[0.0008031345,0.00025237378,0.13530752,0.000016524928,0.00031680329,0.0000053850167,0.00005136496,0.6083903,0.07367861,0.012784685,0.1678933,0.0005000141],"about_ca_topic_score_codex":0.0000013108432,"about_ca_topic_score_gemma":0.00024602248,"teacher_disagreement_score":0.97675234,"about_ca_system_score_codex":0.000068159265,"about_ca_system_score_gemma":0.00014006767,"threshold_uncertainty_score":0.34035027},"labels":[],"label_agreement":null},{"id":"W4372259784","doi":"10.1109/icassp49357.2023.10095515","title":"Grad-StyleSpeech: Any-Speaker Adaptive Text-to-Speech Synthesis with Diffusion Models","year":2023,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Speech recognition; Speech synthesis; Similarity (geometry); Speech processing; Generative grammar; Generative model; Artificial intelligence","score_opus":0.04366180071214854,"score_gpt":0.23850837105092526,"score_spread":0.19484657033877673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4372259784","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.077572055,0.000017840315,0.8136438,0.007775473,0.00025952628,0.00070784445,0.000022988035,0.0026858835,0.09731457],"genre_scores_gemma":[0.67315066,0.00006423508,0.31444967,0.0018274063,0.00010113535,0.0002103027,0.0000051033794,0.000064824206,0.010126656],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972326,0.0001271344,0.0003100277,0.0008728429,0.0007997001,0.0006576953],"domain_scores_gemma":[0.99793714,0.0005328591,0.000079063626,0.0008708923,0.00020211686,0.0003779191],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00046877464,0.00033127764,0.00035622518,0.0005958579,0.0002537225,0.00026639685,0.0009987116,0.000118549986,0.00034946005],"category_scores_gemma":[0.000110257686,0.0002440763,0.00013237212,0.0021457337,0.000060576018,0.00070708507,0.0004196232,0.00016032037,0.0038257453],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010333925,0.0002760973,0.00019558395,0.00001765112,0.000103120336,0.0004281145,0.0011169004,0.0002949962,0.0032247268,0.057754125,0.018858697,0.9176266],"study_design_scores_gemma":[0.0011895413,0.0006020367,0.008932268,0.00038088424,0.0000771183,0.0003048591,0.0016022131,0.8124199,0.1302924,0.022601992,0.01929575,0.0023010424],"about_ca_topic_score_codex":0.000096521144,"about_ca_topic_score_gemma":0.00011347351,"teacher_disagreement_score":0.9153256,"about_ca_system_score_codex":0.00007121971,"about_ca_system_score_gemma":0.00007525466,"threshold_uncertainty_score":0.9969499},"labels":[],"label_agreement":null},{"id":"W4372266975","doi":"10.1109/icassp49357.2023.10096406","title":"On Unsupervised Uncertainty-Driven Speech Pseudo-Label Filtering and Model Calibration","year":2023,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Calibration; Speech recognition; Artificial intelligence; Pattern recognition (psychology); Mathematics; Statistics","score_opus":0.0494052664186122,"score_gpt":0.26795665898778115,"score_spread":0.21855139256916895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4372266975","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49215722,0.0000034192708,0.49196514,0.003013598,0.00015352435,0.00018640097,0.0000073807187,0.0009244047,0.011588896],"genre_scores_gemma":[0.7482622,0.000058411028,0.2452439,0.002368606,0.00004980494,0.000033019995,0.000016944958,0.000021087571,0.0039460273],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99913335,0.000033149245,0.00013395325,0.00030798756,0.0002006981,0.00019085009],"domain_scores_gemma":[0.99947184,0.00013769101,0.000022304974,0.00025108174,0.000029581628,0.00008747178],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013483137,0.00010389778,0.00010421625,0.00015726768,0.000107859465,0.00017389962,0.00024068245,0.00004987763,0.00008876554],"category_scores_gemma":[0.00004686211,0.000089818146,0.000026931613,0.00033747827,0.000017898525,0.00031899533,0.0001228217,0.00006233228,0.00019135463],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035439214,0.00017141213,0.00018123352,0.000055493136,0.00005058537,0.00010677585,0.0015309015,0.022083798,0.056391206,0.1725378,0.018554622,0.72830075],"study_design_scores_gemma":[0.00025972183,0.000032476582,0.000091632406,0.000015036018,0.0000019911265,0.000006122412,0.00002932875,0.9821898,0.007131439,0.010067836,0.000050954444,0.00012366405],"about_ca_topic_score_codex":0.000020503478,"about_ca_topic_score_gemma":0.000015758063,"teacher_disagreement_score":0.960106,"about_ca_system_score_codex":0.000018124614,"about_ca_system_score_gemma":0.000025886678,"threshold_uncertainty_score":0.36626777},"labels":[],"label_agreement":null},{"id":"W4375869393","doi":"10.1109/icassp49357.2023.10096040","title":"Hybrid Neural Network with Cross- and Self-Module Attention Pooling for Text-Independent Speaker Verification","year":2023,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Pooling; Time delay neural network; Artificial neural network; Artificial intelligence; Speech recognition; Feature extraction; Pattern recognition (psychology); Convolutional neural network; Hybrid neural network; Neocognitron; Speaker recognition","score_opus":0.020656171329763155,"score_gpt":0.25866326936253015,"score_spread":0.23800709803276698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4375869393","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.663661,0.000013119842,0.3334747,0.00063396734,0.00025048788,0.00028514984,0.0000026303694,0.0005472661,0.0011317166],"genre_scores_gemma":[0.9455224,0.000013620317,0.053200077,0.00021237263,0.00010732996,0.00004520244,0.000014762145,0.000011154771,0.00087307976],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99909043,0.000023505549,0.00014143706,0.00033597264,0.00017140708,0.00023721787],"domain_scores_gemma":[0.999504,0.00008159827,0.00005431367,0.00020877268,0.000086179316,0.000065098735],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003127419,0.00009193131,0.000090504,0.000063301246,0.00019801363,0.0003226104,0.00016328545,0.000027177062,0.000020737043],"category_scores_gemma":[0.000016481037,0.00007502698,0.000037975442,0.00021045492,0.000017724762,0.0003737413,0.00005470493,0.00004450448,0.00008383154],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001707541,0.0003574609,0.07799982,0.00016571878,0.00023146141,0.00006810511,0.0005092293,0.0045536496,0.0026738872,0.05012043,0.01175012,0.85139936],"study_design_scores_gemma":[0.00055970135,0.00007858961,0.21905881,0.000015225639,0.000012967967,0.00005941007,0.000024676854,0.77385116,0.0018697714,0.0022573874,0.002010914,0.00020138508],"about_ca_topic_score_codex":0.000009161916,"about_ca_topic_score_gemma":0.00001176405,"teacher_disagreement_score":0.85119796,"about_ca_system_score_codex":0.0000179524,"about_ca_system_score_gemma":0.000015257167,"threshold_uncertainty_score":0.31109396},"labels":[],"label_agreement":null},{"id":"W4376869488","doi":"10.18280/isi.280208","title":"Comparative Study of CNN Structures for Arabic Speech Recognition","year":2023,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Arabic; Speech recognition; Computer science; Natural language processing; Linguistics; Artificial intelligence; Philosophy","score_opus":0.06243161467872856,"score_gpt":0.2909166329288379,"score_spread":0.22848501825010933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376869488","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91722506,0.000007637149,0.07643763,0.000027900956,0.00032833221,0.0009979482,0.000039408354,0.00034594553,0.0045901467],"genre_scores_gemma":[0.97807187,0.000005655576,0.021548508,0.00005171136,0.00003358176,0.00015626528,0.00009847201,0.000005161489,0.000028765564],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99868876,0.00007823122,0.00054989476,0.0001455443,0.00032445096,0.00021312169],"domain_scores_gemma":[0.9985878,0.00023068221,0.0003271905,0.00024762357,0.0005541932,0.00005252928],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000507517,0.00013542372,0.0002582587,0.0005558952,0.00019550619,0.00020288942,0.00034080533,0.00006621874,0.000028489925],"category_scores_gemma":[0.00025849108,0.00012511863,0.00007077065,0.00097029255,0.00004710413,0.0026020755,0.00007104227,0.000063791376,0.00018261584],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058297705,0.000102738755,0.00035755304,0.00022026035,0.00009352219,0.0000021447465,0.029850734,0.00012720338,0.0003967279,0.002163701,0.0019540903,0.96467304],"study_design_scores_gemma":[0.0067219078,0.0033341257,0.11095826,0.00047612563,0.00014961902,0.00011599571,0.07782103,0.2253386,0.2036222,0.365943,0.003783044,0.0017360633],"about_ca_topic_score_codex":0.000030020246,"about_ca_topic_score_gemma":0.000014803211,"teacher_disagreement_score":0.96293694,"about_ca_system_score_codex":0.000067539564,"about_ca_system_score_gemma":0.000046350244,"threshold_uncertainty_score":0.510219},"labels":[],"label_agreement":null},{"id":"W4378505314","doi":"10.48550/arxiv.2305.15096","title":"Dynamic Masking Rate Schedules for MLM Pretraining","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Samsung; York University; Samsung Advanced Institute of Technology","keywords":"Masking (illustration); Computer science; Speedup; Transformer; Pareto principle; Schedule; Speech recognition; Real-time computing; Parallel computing; Mathematical optimization; Mathematics; Operating system; Engineering; Electrical engineering; Voltage","score_opus":0.1660565028958392,"score_gpt":0.22019851642282345,"score_spread":0.05414201352698425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378505314","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08174628,0.00001962384,0.914777,0.0002418861,0.00097622635,0.00037016615,0.000038365288,0.0007199245,0.0011105724],"genre_scores_gemma":[0.9317078,0.000107040985,0.065180555,0.0001108151,0.000051979223,0.000005871817,0.000031256313,0.000037078695,0.0027676267],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980848,0.000121848316,0.00020013098,0.0011102926,0.0000746187,0.00040832892],"domain_scores_gemma":[0.9981986,0.0004662161,0.00022208161,0.00082501856,0.00015354287,0.00013452386],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00054983207,0.00028136137,0.00031602706,0.00040873702,0.00021825846,0.00022493937,0.0014796384,0.00027843795,0.000031090178],"category_scores_gemma":[0.00018793071,0.0003403304,0.00030697705,0.00048416792,0.00006598953,0.00029255208,0.0010816384,0.0004046226,0.00020154605],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014976054,0.00026036706,0.0020228673,0.0010288546,0.001026569,0.0013252555,0.0014299722,0.1524745,0.0005765971,0.7486663,0.00086316426,0.090175845],"study_design_scores_gemma":[0.00029495425,0.00002203784,0.0006239251,0.00017927815,0.00004606177,0.000001973453,0.00015823696,0.87669885,0.0002617593,0.12109377,0.00023881829,0.0003803348],"about_ca_topic_score_codex":0.000022438755,"about_ca_topic_score_gemma":0.00004913419,"teacher_disagreement_score":0.8499615,"about_ca_system_score_codex":0.00016229367,"about_ca_system_score_gemma":0.0001800049,"threshold_uncertainty_score":0.9999049},"labels":[],"label_agreement":null},{"id":"W4380449787","doi":"10.5267/j.ijdns.2023.5.004","title":"A framework for pronunciation error detection and correction for non-native Arab speakers of English language","year":2023,"lang":"en","type":"article","venue":"International Journal of Data and Network Science","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Pronunciation; Computer science; Classifier (UML); Artificial intelligence; Speech recognition; Natural language processing; Confusion; Decision tree; Confusion matrix; Error detection and correction; Construct (python library); Linguistics; Psychology; Algorithm","score_opus":0.042945068011124465,"score_gpt":0.3388800272419896,"score_spread":0.29593495923086516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380449787","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13220249,0.00004796449,0.8638997,0.00028479166,0.0032956237,0.00017232972,0.000032961336,0.000015614198,0.000048529768],"genre_scores_gemma":[0.89060473,0.00009200112,0.108491555,0.000072575356,0.0007006867,0.0000075191806,0.0000074699174,0.000003632649,0.00001980681],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99908733,0.000017423348,0.00023247134,0.00019590039,0.0003483441,0.00011853293],"domain_scores_gemma":[0.9980184,0.0005705281,0.000334511,0.00012211947,0.0009028085,0.000051628595],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015610423,0.00005578644,0.00010481113,0.00022325134,0.00010533784,0.00013529178,0.0006404974,0.00003122275,0.0000014563421],"category_scores_gemma":[0.002246442,0.000048180158,0.00002869325,0.00041854015,0.0000904744,0.0012492251,0.0001491084,0.0000676388,3.5490814e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018010565,0.000040751027,0.0007884848,0.000019782387,0.00006203741,0.000003054154,0.004291705,0.0002657111,0.0024176324,0.0015456558,0.0014964732,0.9888886],"study_design_scores_gemma":[0.00073276914,0.00032696343,0.0104747005,0.00028529076,0.000023920233,0.000039189585,0.0014665005,0.9644834,0.011273817,0.008754137,0.0020031254,0.00013622815],"about_ca_topic_score_codex":0.000003601908,"about_ca_topic_score_gemma":0.000013645667,"teacher_disagreement_score":0.98875237,"about_ca_system_score_codex":0.000031706255,"about_ca_system_score_gemma":0.00008609148,"threshold_uncertainty_score":0.2689363},"labels":[],"label_agreement":null},{"id":"W4382053133","doi":"10.1109/iwbf57495.2023.10157564","title":"On the Use of Cross-module Attention Statistics Pooling for Speaker Verification","year":2023,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Computer science; Pooling; Artificial neural network; Speech recognition; Artificial intelligence; Time delay neural network; Feature extraction; Pattern recognition (psychology); Convolutional neural network; Speaker recognition","score_opus":0.1666763134449241,"score_gpt":0.33124857941475017,"score_spread":0.16457226596982608,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382053133","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10299482,5.138454e-7,0.8955563,0.00059827266,0.00015885444,0.00014991757,0.000030365629,0.00008229509,0.0004286863],"genre_scores_gemma":[0.69368553,0.0000109134435,0.30116865,0.0005960871,0.000033134645,0.000048026453,0.00004136861,0.000011086603,0.0044051954],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995003,0.000024017105,0.00012939189,0.00012710254,0.00013066285,0.00008853743],"domain_scores_gemma":[0.99890244,0.0006598802,0.000053637985,0.00023216072,0.00013521117,0.000016693532],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023125194,0.000041086074,0.000048317946,0.000053734053,0.00008085307,0.00013073315,0.00015518712,0.000019901598,0.00006062783],"category_scores_gemma":[0.00038013828,0.000028359198,0.00003481953,0.00019416815,0.000022258824,0.00016801679,0.00002276571,0.000022566914,0.00017984386],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012795113,0.00004744189,0.0004933302,0.0000159622,0.000015735468,6.996529e-7,0.000087834494,0.0002457328,0.0033654238,0.84800136,0.020361427,0.12735228],"study_design_scores_gemma":[0.0002101009,0.000054110507,0.054066733,0.000018869008,0.000006339807,0.0000012111597,0.000027279528,0.8855183,0.019415837,0.034971498,0.0056004385,0.0001092972],"about_ca_topic_score_codex":0.000010607632,"about_ca_topic_score_gemma":0.000004600424,"teacher_disagreement_score":0.88527256,"about_ca_system_score_codex":0.000009028108,"about_ca_system_score_gemma":0.000010709783,"threshold_uncertainty_score":0.2311589},"labels":[],"label_agreement":null},{"id":"W4382053191","doi":"10.1109/iwbf57495.2023.10157651","title":"On the influence of the quality of pseudo-labels on the self-supervised speaker verification task: a thorough analysis","year":2023,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Overfitting; Computer science; Discriminative model; Task (project management); Artificial intelligence; Noise (video); Memorization; Speech recognition; Quality (philosophy); Cluster analysis; Embedding; Pattern recognition (psychology); Machine learning; Artificial neural network; Mathematics; Image (mathematics); Engineering","score_opus":0.05485249341111849,"score_gpt":0.294590206193768,"score_spread":0.23973771278264955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382053191","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98142666,0.0000020491495,0.002782194,0.009700015,0.000049422528,0.00027341014,0.000010918733,0.000098491706,0.0056568584],"genre_scores_gemma":[0.99680096,0.000016702246,0.001279474,0.0015663339,0.000007553048,0.000029119023,0.0000012648178,0.0000045057254,0.00029407494],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99786913,0.0006687297,0.0003877871,0.00027865754,0.000641306,0.00015437057],"domain_scores_gemma":[0.9961416,0.0019713813,0.00022339358,0.0014551525,0.00018100401,0.000027426668],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018429265,0.000114392366,0.00019698043,0.00010801633,0.00016502035,0.00005654819,0.0013138301,0.000047223148,0.00018081722],"category_scores_gemma":[0.00064990047,0.00004907613,0.00023350908,0.0028812517,0.00009381678,0.00011472451,0.00013670973,0.00011448417,0.00014958618],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056889065,0.00064621534,0.008488889,0.00004744624,0.0010746089,0.0000013189735,0.006800189,0.0022236079,0.043039937,0.8918062,0.004321062,0.041493636],"study_design_scores_gemma":[0.00025916632,0.0000750522,0.7840594,0.000048839272,0.00015173064,8.4307027e-7,0.0008957845,0.12384363,0.07916097,0.010961843,0.00030207785,0.00024066237],"about_ca_topic_score_codex":0.00017244421,"about_ca_topic_score_gemma":0.00005550594,"teacher_disagreement_score":0.88084435,"about_ca_system_score_codex":0.000021133863,"about_ca_system_score_gemma":0.000048945254,"threshold_uncertainty_score":0.24414451},"labels":[],"label_agreement":null},{"id":"W4382862298","doi":"10.3390/electronics12132887","title":"Review of Advances in Speech Processing with Focus on Artificial Neural Networks","year":2023,"lang":"en","type":"article","venue":"Electronics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Focus (optics); Computer science; Speech processing; Artificial neural network; Hidden Markov model; Coding (social sciences); Artificial intelligence; Speech recognition","score_opus":0.019845192751302896,"score_gpt":0.2754517902035622,"score_spread":0.2556065974522593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382862298","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048940636,0.7954342,0.1260452,0.012115112,0.00052088645,0.0014663751,0.0000035567987,0.0010611649,0.014412871],"genre_scores_gemma":[0.7119158,0.27010828,0.014058598,0.00333807,0.00025528416,0.00010591181,0.000013241395,0.00005434936,0.00015045701],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990805,0.000048901602,0.00018911542,0.00020660849,0.00018727854,0.0002875942],"domain_scores_gemma":[0.9995945,0.00007235681,0.00008554167,0.0001727347,0.000047457095,0.00002739958],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030603187,0.00008529826,0.00016540589,0.00010005599,0.000035610734,0.000025841222,0.00025462135,0.000027716362,0.000009264594],"category_scores_gemma":[0.00004499471,0.00006789035,0.00003148383,0.001186013,0.000018318511,0.00020683387,0.00002557899,0.00015554862,0.000014388052],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000928576,0.000021658749,0.000027937107,0.00013457036,0.0000015666208,0.000010961106,0.000014934062,0.0001768868,0.000022086439,0.0012575343,0.00011328756,0.9982093],"study_design_scores_gemma":[0.00072703423,0.00146699,0.0006964136,0.010300732,0.000030467934,0.00010149819,0.000049181646,0.8720497,0.037332192,0.023324635,0.05301784,0.00090333726],"about_ca_topic_score_codex":7.9091643e-7,"about_ca_topic_score_gemma":0.00008254356,"teacher_disagreement_score":0.9973059,"about_ca_system_score_codex":0.000032967804,"about_ca_system_score_gemma":0.00007485423,"threshold_uncertainty_score":0.27684882},"labels":[],"label_agreement":null},{"id":"W4383217247","doi":"10.22541/au.168857312.29438464/v1","title":"Bidirectional Long short-term memory and Recurrent Neural Network model for speech recognition","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"International Development Research Centre; Styrelsen för Internationellt Utvecklingssamarbete","keywords":"Computer science; Recurrent neural network; Speech recognition; Word error rate; Artificial neural network; Long short term memory; Term (time); Short-term memory; Transformer; Artificial intelligence; Language model; Working memory; Cognition","score_opus":0.13743307712226754,"score_gpt":0.3105569811471613,"score_spread":0.17312390402489375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383217247","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.049832,0.00019877584,0.938436,0.001404807,0.0053518196,0.0012844107,0.00013052624,0.0012400523,0.0021216583],"genre_scores_gemma":[0.063146584,0.0012288523,0.92124516,0.0009820749,0.0026976638,0.0014164613,0.0008424364,0.00014720333,0.008293582],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976358,0.00008476877,0.0004510137,0.0010485235,0.0003558865,0.00042402488],"domain_scores_gemma":[0.99863863,0.00034930184,0.00012793018,0.00046546516,0.00024385969,0.00017481731],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00064212637,0.0003417039,0.00037404694,0.00023575859,0.00020792802,0.00041054163,0.0005081412,0.00029965283,0.00005980419],"category_scores_gemma":[0.00008770191,0.00033683132,0.00025154834,0.00019800487,0.000045618144,0.0002676142,0.0008395224,0.00039648233,0.00005669764],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018208402,0.00004746743,0.00021235597,0.000110750436,0.00005953391,0.000012773237,0.00006369228,0.0014404214,0.000014081347,0.000106805914,0.00959263,0.9883213],"study_design_scores_gemma":[0.00016245725,0.000030221874,0.0014401937,0.00017021233,0.000041556526,0.000046263973,0.000008043888,0.9684863,0.0006163983,0.028491547,0.00004900432,0.00045780203],"about_ca_topic_score_codex":0.000016612203,"about_ca_topic_score_gemma":0.00016058882,"teacher_disagreement_score":0.9878635,"about_ca_system_score_codex":0.000075395976,"about_ca_system_score_gemma":0.00011444193,"threshold_uncertainty_score":0.9999084},"labels":[],"label_agreement":null},{"id":"W4383746897","doi":"10.1109/memea57477.2023.10171898","title":"Performance of Speech Recognition Algorithms in Musical Speech used for Speech-Language Pathology Rehabilitation","year":2023,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Speech recognition; Speech processing; Natural language processing; Artificial intelligence","score_opus":0.03338750530970448,"score_gpt":0.28691131119752716,"score_spread":0.2535238058878227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383746897","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9850391,0.000005451972,0.010935165,0.0011372002,0.000376269,0.0006190486,0.000024556073,0.000297641,0.0015655472],"genre_scores_gemma":[0.44428667,0.000024955345,0.5547182,0.00018369783,0.00012169922,0.0001238189,0.000070814924,0.000020823718,0.00044931882],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9980937,0.0001411812,0.00053077494,0.0005252539,0.00032772406,0.00038133922],"domain_scores_gemma":[0.99814814,0.0010341726,0.0001279171,0.00042579754,0.00019141212,0.000072571616],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013833313,0.00016710119,0.0003181005,0.0006292838,0.000057139787,0.00003913468,0.00040032552,0.000159857,0.00017768283],"category_scores_gemma":[0.00066046044,0.00015999103,0.00013339223,0.0012191791,0.000077822835,0.000476962,0.00010319116,0.00013024644,0.00033308085],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025613757,0.00010640407,0.00094924914,0.00006997613,0.0000062568192,0.000052860414,0.0010387787,0.0000027826454,0.011367704,0.00013650773,0.00048711887,0.98575675],"study_design_scores_gemma":[0.0033305804,0.0016200271,0.052564833,0.00022271181,0.000025532878,0.00022885484,0.002291111,0.43096402,0.49818578,0.008794041,0.0009211448,0.00085133547],"about_ca_topic_score_codex":0.00004745856,"about_ca_topic_score_gemma":0.00011205791,"teacher_disagreement_score":0.9849054,"about_ca_system_score_codex":0.00005679409,"about_ca_system_score_gemma":0.00005510656,"threshold_uncertainty_score":0.6524245},"labels":[],"label_agreement":null},{"id":"W4384615840","doi":"10.48550/arxiv.2307.07359","title":"From Multilayer Perceptron to GPT: A Reflection on Deep Learning Research for Wireless Physical Layer","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Division of Electrical, Communications and Cyber Systems; Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Wireless; Computer science; Wireless network; Physical layer; Wireless broadband; Perceptron; Context (archaeology); Artificial intelligence; Machine learning; Empirical research; Telecommunications; Artificial neural network","score_opus":0.37201008105183087,"score_gpt":0.32566992425717856,"score_spread":0.04634015679465231,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384615840","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6248034,0.000001774342,0.37247592,0.0003547757,0.00047643954,0.00047103703,0.000014711384,0.00038641426,0.0010155209],"genre_scores_gemma":[0.99074876,0.000024426112,0.003924875,0.000086578046,0.00042737808,0.000018607412,0.000024609248,0.00004214111,0.0047026495],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99712676,0.00042834724,0.00015202208,0.001530538,0.00024992818,0.00051239936],"domain_scores_gemma":[0.9975136,0.0010091179,0.00009299249,0.0007906476,0.00036437993,0.00022927955],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00055685185,0.00026817192,0.0003311458,0.00062976184,0.00039786828,0.00021861179,0.0011778332,0.000278259,0.000042694377],"category_scores_gemma":[0.0002305666,0.00030332452,0.00027781926,0.0008319761,0.00005435567,0.00018344574,0.0011310148,0.0010117557,0.0014077848],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022936328,0.0023138183,0.0024147562,0.00038717993,0.0009921116,0.0010051524,0.025606655,0.4307693,0.028788421,0.0705005,0.010939831,0.42398864],"study_design_scores_gemma":[0.000468879,0.00025446428,0.0016064402,0.00016948914,0.00003321941,6.5901946e-7,0.00070866605,0.9676273,0.0039690984,0.022625264,0.0020687229,0.00046779876],"about_ca_topic_score_codex":0.0004876503,"about_ca_topic_score_gemma":0.0001894366,"teacher_disagreement_score":0.536858,"about_ca_system_score_codex":0.0004185965,"about_ca_system_score_gemma":0.0000866971,"threshold_uncertainty_score":0.9999419},"labels":[],"label_agreement":null},{"id":"W4384828046","doi":"10.1057/s41599-023-01931-4","title":"Using a forced aligner for prosody research","year":2023,"lang":"en","type":"article","venue":"Humanities and Social Sciences Communications","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Georgia Institute of Technology","keywords":"Computer science; Prosody; Mandarin Chinese; Syllable; Phrase; Natural language processing; Speech recognition; Sentence; Annotation; Artificial intelligence; Linguistics","score_opus":0.7762389046443241,"score_gpt":0.5030580593464857,"score_spread":0.27318084529783837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384828046","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3330918,0.001460389,0.11949958,0.10042663,0.0011019474,0.00497494,0.00015948639,0.0026228752,0.43666238],"genre_scores_gemma":[0.89705515,0.0002911694,0.09843238,0.00100791,0.00014382317,0.00035082913,0.000014347433,0.000012014088,0.0026923872],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99902576,0.00016538531,0.00012409642,0.00017065453,0.0002413302,0.00027276215],"domain_scores_gemma":[0.99885595,0.00061417685,0.00003702888,0.0003020899,0.00017311156,0.000017673905],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0014810177,0.000052393923,0.00008217476,0.00020671352,0.0054890704,0.0005440883,0.0011998866,0.000033667,0.000009918773],"category_scores_gemma":[0.00007461272,0.000048386184,0.000040757874,0.00067086815,0.00094662356,0.00034490944,0.00057512836,0.000072562485,0.000013227304],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.34266e-7,0.00001494223,0.000026122882,0.000007525402,0.000004351437,1.5521346e-7,0.0082057705,6.6245957e-7,0.00034257155,0.97583896,0.0019204712,0.013637842],"study_design_scores_gemma":[0.00046030653,0.00018062064,0.0015156053,0.000052984356,0.000015104621,0.000007767115,0.034952827,0.2567735,0.000505434,0.36231172,0.34274086,0.0004832868],"about_ca_topic_score_codex":0.000107034786,"about_ca_topic_score_gemma":0.00017580861,"teacher_disagreement_score":0.61352724,"about_ca_system_score_codex":0.000024752411,"about_ca_system_score_gemma":0.00008392829,"threshold_uncertainty_score":0.9958056},"labels":[],"label_agreement":null},{"id":"W4384936706","doi":"10.1016/j.csl.2023.101538","title":"Trends and developments in automatic speech recognition research","year":2023,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"","keywords":"Computer science; Discriminative model; Exploit; Variety (cybernetics); Artificial intelligence; Speech recognition; Natural language; Deep learning; SIGNAL (programming language); Machine learning; Natural language processing","score_opus":0.07391361334822268,"score_gpt":0.34104259928551184,"score_spread":0.2671289859372892,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384936706","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97556067,0.00012973863,0.006037708,0.0017617504,0.0006576153,0.00032562463,0.000009703552,0.0011501685,0.014367012],"genre_scores_gemma":[0.29214296,0.00010150339,0.7042043,0.00066983,0.00030840485,0.00008513875,0.00008256574,0.00004857274,0.002356677],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99754417,0.000295027,0.0003502129,0.0006142408,0.00058911514,0.0006072287],"domain_scores_gemma":[0.99890125,0.0003253058,0.00005623363,0.0004597447,0.000099162615,0.00015830579],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015975459,0.00018940735,0.0002513594,0.0018149376,0.0001452407,0.0003407403,0.000667863,0.00011365057,0.00019347329],"category_scores_gemma":[0.00009735337,0.00018576012,0.000052728654,0.0030368879,0.00006037616,0.00046565072,0.00059969013,0.00030925887,0.0014031902],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000019702995,0.00004629283,0.00039877027,0.000023360286,0.000010092153,0.0008334327,0.0017019032,2.3326959e-7,0.00027087578,0.00010287195,0.0030238307,0.99358636],"study_design_scores_gemma":[0.0038963398,0.0004025449,0.54430455,0.0008895153,0.000018859057,0.0013021353,0.0014406905,0.3763992,0.047010444,0.010029419,0.012208048,0.0020982567],"about_ca_topic_score_codex":0.00006987071,"about_ca_topic_score_gemma":0.00010440405,"teacher_disagreement_score":0.9914881,"about_ca_system_score_codex":0.00008988334,"about_ca_system_score_gemma":0.000058476988,"threshold_uncertainty_score":0.99937433},"labels":[],"label_agreement":null},{"id":"W4385080277","doi":"10.1109/sp46215.2023.10179374","title":"Breaking Security-Critical Voice Authentication","year":2023,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Spoofing attack; Computer science; Computer security; Vulnerability (computing); Authentication (law); Adversarial system; Key (lock); Task (project management); Artificial intelligence","score_opus":0.028324428021169017,"score_gpt":0.29898535245972496,"score_spread":0.27066092443855594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385080277","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035428397,0.00001611892,0.7860249,0.027208678,0.0009997534,0.00015178097,0.000003054638,0.003127116,0.14704019],"genre_scores_gemma":[0.97574455,0.000004460662,0.022620331,0.0006187854,0.00005098072,0.000010448238,0.0000020358611,0.0000044183603,0.00094399427],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993193,0.000038082846,0.000101865,0.00019402993,0.00017677221,0.00016991013],"domain_scores_gemma":[0.99932736,0.00030875785,0.000012014524,0.00023357572,0.000055078865,0.00006320826],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00024072055,0.0000500099,0.000055050867,0.00010867099,0.000086928085,0.00013233427,0.00029226762,0.000031381824,0.00020924798],"category_scores_gemma":[0.0002540548,0.00004562136,0.000036880236,0.00049071794,0.000022114313,0.00026930394,0.000097451695,0.00004735858,0.005428076],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000012391175,0.00006151318,0.00017330454,0.00001839208,0.000009670256,0.000031883737,0.0010529453,5.7324365e-7,0.0018471788,0.7291015,0.0105706295,0.2571312],"study_design_scores_gemma":[0.00028319273,0.000039045524,0.012539213,0.00004802998,0.000014650564,0.0000878298,0.00033163143,0.6349572,0.02807827,0.27332684,0.049806383,0.00048768232],"about_ca_topic_score_codex":0.000009141187,"about_ca_topic_score_gemma":0.0000043816904,"teacher_disagreement_score":0.94031614,"about_ca_system_score_codex":0.000010608293,"about_ca_system_score_gemma":0.000014770819,"threshold_uncertainty_score":0.9953463},"labels":[],"label_agreement":null},{"id":"W4385489013","doi":"10.1109/icasspw59220.2023.10193304","title":"Investigation Of The Quality Of Pseudo-Labels For The Self-Supervised Speaker Verification Task","year":2023,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Computer science; Overfitting; Cluster analysis; Discriminative model; Artificial intelligence; Task (project management); Speech recognition; Noise (video); Speaker recognition; Speaker verification; Pattern recognition (psychology); Embedding; Quality (philosophy); Machine learning; Artificial neural network","score_opus":0.10024304657006006,"score_gpt":0.2985688427223572,"score_spread":0.19832579615229712,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385489013","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83384734,0.000013162759,0.14987119,0.012845366,0.0004020421,0.0008456385,0.000021357017,0.00023684664,0.0019170488],"genre_scores_gemma":[0.95922214,0.000016230086,0.03990438,0.000424397,0.00001899511,0.000047808586,0.0000037260013,0.0000047225344,0.00035760805],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99914205,0.00012693474,0.00027161304,0.00013907925,0.00023470513,0.000085618434],"domain_scores_gemma":[0.9985401,0.00063862925,0.00013905307,0.0004947042,0.00016678311,0.000020712389],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009847446,0.0000529183,0.000091085116,0.000037948896,0.00008326444,0.0000232098,0.0005147146,0.000032605578,0.000024757941],"category_scores_gemma":[0.00023852252,0.000028996885,0.0000835135,0.00057655363,0.0000545528,0.00012776277,0.000062716135,0.000030454888,0.00002303296],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025761592,0.000115429764,0.014270541,0.00024853818,0.00016140008,1.2507245e-7,0.0067456267,0.000037491718,0.45129094,0.28137347,0.013348444,0.23238224],"study_design_scores_gemma":[0.00047994542,0.000031257863,0.27935022,0.000022283664,0.000024372586,9.0976096e-7,0.0004104444,0.22477837,0.47776946,0.01592374,0.0010797924,0.00012917904],"about_ca_topic_score_codex":0.000052625648,"about_ca_topic_score_gemma":0.000017683633,"teacher_disagreement_score":0.26544973,"about_ca_system_score_codex":0.000010142816,"about_ca_system_score_gemma":0.00005792398,"threshold_uncertainty_score":0.11824587},"labels":[],"label_agreement":null},{"id":"W4385573061","doi":"10.18653/v1/2022.emnlp-industry.29","title":"SpeechNet: Weakly Supervised, End-to-End Speech Recognition at Industrial Scale","year":2022,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"End-to-end principle; Computer science; Speech recognition; Scale (ratio); Natural language processing; Artificial intelligence; Cartography; Geography","score_opus":0.05790377424567948,"score_gpt":0.24210331265645219,"score_spread":0.1841995384107727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385573061","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7603413,0.000029675295,0.012964666,0.010017044,0.0030212796,0.0011466808,0.0002155037,0.0011708462,0.21109304],"genre_scores_gemma":[0.5150953,0.000040569077,0.41700864,0.01651481,0.0015458079,0.00066577364,0.00033486533,0.00013315778,0.04866109],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971775,0.00027106606,0.000394498,0.0007525483,0.0009084296,0.000495972],"domain_scores_gemma":[0.99865717,0.00020385851,0.00008330339,0.0006546543,0.00009643149,0.00030455593],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0008257673,0.00023022809,0.00026023234,0.00040753078,0.0005767041,0.00020279658,0.0010712135,0.00010323312,0.047688853],"category_scores_gemma":[0.00009876734,0.00023805164,0.00016570155,0.0011245286,0.000038335467,0.00043796605,0.001144058,0.00034123586,0.004700941],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040658768,0.00014288315,0.00033548474,0.000002487097,0.00001678473,0.000060647406,0.00018014331,0.0000028903237,0.0048930207,0.00017176842,0.046147022,0.9480062],"study_design_scores_gemma":[0.002562726,0.0006777386,0.0013348252,0.00003214773,0.000048001497,0.0009836691,0.00090969796,0.005888413,0.46025088,0.0049149096,0.5208666,0.0015303815],"about_ca_topic_score_codex":0.00017862876,"about_ca_topic_score_gemma":0.00015600842,"teacher_disagreement_score":0.9464758,"about_ca_system_score_codex":0.00030932782,"about_ca_system_score_gemma":0.000113431015,"threshold_uncertainty_score":0.996074},"labels":[],"label_agreement":null},{"id":"W4385822952","doi":"10.21437/interspeech.2023-1087","title":"Speech Self-Supervised Representation Benchmarking: Are We Doing it Right?","year":2023,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"Grand Équipement National De Calcul Intensif","keywords":"Benchmarking; Computer science; Representation (politics); Artificial intelligence; Speech recognition; Natural language processing","score_opus":0.05260799574573499,"score_gpt":0.29073518130807524,"score_spread":0.23812718556234025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385822952","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06975109,0.000047294317,0.35586497,0.06349503,0.002540143,0.00080539886,0.000006914068,0.0071484335,0.5003407],"genre_scores_gemma":[0.15962969,0.0004340499,0.8284182,0.0025994945,0.00048584145,0.000063557694,0.000022022277,0.00003368337,0.0083134845],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99856055,0.00008639686,0.0002337028,0.00044846133,0.000390518,0.0002803682],"domain_scores_gemma":[0.9990068,0.00025541688,0.00007091974,0.0004736059,0.00009094413,0.000102317346],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00032704655,0.0001229447,0.00014567596,0.00025927954,0.00017599911,0.0002650857,0.0004975687,0.00006489752,0.00117541],"category_scores_gemma":[0.00004193,0.00010745762,0.00009516026,0.0011680865,0.000013337263,0.00049581967,0.00017695894,0.000085348875,0.0018497397],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005267623,0.000113453236,0.0021557403,0.00004258353,0.00006447695,0.00039858546,0.0016177531,0.000025319912,0.002032657,0.007914457,0.10924309,0.87638664],"study_design_scores_gemma":[0.00087980204,0.000049278424,0.009165164,0.00014189332,0.000024962234,0.00010809747,0.0013047263,0.7602191,0.067865886,0.008672309,0.15079223,0.00077657547],"about_ca_topic_score_codex":0.000024914045,"about_ca_topic_score_gemma":0.000033647633,"teacher_disagreement_score":0.87561005,"about_ca_system_score_codex":0.00003364221,"about_ca_system_score_gemma":0.000030293242,"threshold_uncertainty_score":0.9997377},"labels":[],"label_agreement":null},{"id":"W4386074659","doi":"10.11159/mhci23.111","title":"GAN-Based Fine-Grained Feature Modeling For Zero-Shot Voice Cloning","year":2023,"lang":"en","type":"article","venue":"Proceedings of the World Congress on Electrical Engineering and Computer Systems and Science","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Cloning (programming); Computer science; Zero (linguistics); Shot (pellet); Feature (linguistics); Speech recognition; Materials science; Programming language","score_opus":0.019463419043084445,"score_gpt":0.23164629502604334,"score_spread":0.2121828759829589,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386074659","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40226766,0.0008363651,0.58268404,0.005324052,0.005105241,0.0016235062,0.000011629843,0.0012767331,0.0008707235],"genre_scores_gemma":[0.9923026,0.000007564048,0.0070952196,0.00009895816,0.00010203111,0.000042631764,2.4047395e-7,0.000010543876,0.0003402169],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985458,0.0000056513563,0.00021217146,0.00046269057,0.00037963645,0.00039401892],"domain_scores_gemma":[0.9991293,0.000264729,0.000093333656,0.00013599651,0.00024685365,0.00012978545],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067792693,0.00017175311,0.00024693957,0.00045454837,0.00030422653,0.00045228066,0.0007172467,0.000044523964,1.09287036e-7],"category_scores_gemma":[0.00015030974,0.00012332348,0.000064686785,0.0019026493,0.00006616692,0.00022396275,0.00009662451,0.00016340645,6.827347e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014676675,0.00021325501,0.0014823593,0.001858005,0.0001539475,0.000011890679,0.0007514746,0.33744025,0.087396026,0.40209875,0.01175877,0.1566885],"study_design_scores_gemma":[0.00024077692,0.00007833624,0.00021590952,0.0003039078,0.0000062306517,0.000012087111,0.000003684619,0.9920177,0.006240129,0.00013240875,0.0005874384,0.00016139525],"about_ca_topic_score_codex":0.0000055197806,"about_ca_topic_score_gemma":5.619328e-7,"teacher_disagreement_score":0.65457743,"about_ca_system_score_codex":0.000026883996,"about_ca_system_score_gemma":0.0000420676,"threshold_uncertainty_score":0.5028986},"labels":[],"label_agreement":null},{"id":"W4386105229","doi":"10.1109/is3c57901.2023.00051","title":"Performance Evaluation of Indonesian Language Forced Alignment Using Montreal Forced Aligner","year":2023,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Indonesian; Speech recognition; Transcription (linguistics); Natural language processing; Segmentation; Language model; Process (computing); Speech corpus; Set (abstract data type); Artificial intelligence; Speech synthesis; Linguistics; Programming language","score_opus":0.05697551244489023,"score_gpt":0.3030025896258461,"score_spread":0.24602707718095584,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386105229","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9594534,0.00000791689,0.021827715,0.00009342266,0.00011691081,0.00023182866,0.000001800448,0.00015960743,0.018107418],"genre_scores_gemma":[0.9899041,0.000006421612,0.009514856,0.00007807789,0.000024803123,0.00002121602,0.000006750251,0.000007080356,0.00043666802],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986821,0.00008382304,0.00021553319,0.00020600656,0.00061708037,0.00019546632],"domain_scores_gemma":[0.99939126,0.000051562238,0.0000816927,0.0002998708,0.00012375083,0.000051861953],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008445897,0.000090317364,0.00012674952,0.00019052983,0.00006626328,0.000033637945,0.00025486836,0.000043641114,0.00015297507],"category_scores_gemma":[0.000035271863,0.000076619,0.00005891248,0.00048200318,0.000015868418,0.00028026692,0.00008246514,0.000026499032,0.00007833921],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012206937,0.000048063983,0.0011237945,0.000026265352,0.00004939579,0.0000068518107,0.0025916668,0.0017525102,0.079299286,0.0012395356,0.00040224323,0.91344815],"study_design_scores_gemma":[0.00042700346,0.000024727377,0.010135535,0.000018674833,0.00001788768,0.0000045091115,0.00038898244,0.8442974,0.14445284,0.00012357753,0.000011512537,0.00009737207],"about_ca_topic_score_codex":0.00016193655,"about_ca_topic_score_gemma":0.000033762026,"teacher_disagreement_score":0.9133508,"about_ca_system_score_codex":0.0000546832,"about_ca_system_score_gemma":0.00005762886,"threshold_uncertainty_score":0.31244323},"labels":[],"label_agreement":null},{"id":"W4386273179","doi":"10.2139/ssrn.4733627","title":"Speech Self-Supervised Representations Benchmarking: A Case for Larger Probing Heads","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Benchmarking; Computer science; Ranking (information retrieval); Inference; Downstream (manufacturing); Task (project management); Generalization; Feature (linguistics); Set (abstract data type); Artificial intelligence; Architecture; Machine learning; Natural language processing; Engineering; Mathematics; Geography","score_opus":0.02543416354791751,"score_gpt":0.2923444770256426,"score_spread":0.2669103134777251,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386273179","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.060898192,0.0063646063,0.91068256,0.010286585,0.0045706467,0.002159368,0.00005931241,0.0010001975,0.003978561],"genre_scores_gemma":[0.52165735,0.0047975713,0.46471798,0.00060338655,0.003997791,0.0007084171,0.00006503622,0.00021099435,0.0032414736],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.995367,0.00021487458,0.0006811845,0.00091596675,0.00046532226,0.002355657],"domain_scores_gemma":[0.99818784,0.00026419555,0.0002935343,0.0007083644,0.00035244206,0.00019361403],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0032452121,0.00040455986,0.0004298006,0.00055066746,0.00050645426,0.0011876272,0.001076354,0.00030669538,0.00006043168],"category_scores_gemma":[0.0001396631,0.00037525911,0.00064209383,0.0004295187,0.000026841435,0.00026201026,0.0008045622,0.004103676,0.00007460984],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003424321,0.00040107706,0.00006008533,0.00039487885,0.0017896692,0.0021430585,0.0028561521,0.00010402678,0.00034656437,0.22458105,0.002958432,0.76433074],"study_design_scores_gemma":[0.0006439643,0.0001578625,0.0000057814277,0.000254255,0.00026649245,0.0383865,0.00081365014,0.1290011,0.0006569182,0.82654065,0.0025922507,0.00068057736],"about_ca_topic_score_codex":0.00007380334,"about_ca_topic_score_gemma":0.000454091,"teacher_disagreement_score":0.7636502,"about_ca_system_score_codex":0.0013090363,"about_ca_system_score_gemma":0.005549154,"threshold_uncertainty_score":0.99986994},"labels":[],"label_agreement":null},{"id":"W4386609311","doi":"10.1109/lsp.2023.3313515","title":"Rhythm Modeling for Voice Conversion","year":2023,"lang":"en","type":"article","venue":"IEEE Signal Processing Letters","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ubisoft (Canada)","funders":"","keywords":"Speech recognition; Rhythm; Computer science; Prosody; Speech processing; Artificial intelligence; Pattern recognition (psychology); Acoustics","score_opus":0.04954250797524673,"score_gpt":0.2673340634600034,"score_spread":0.21779155548475665,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386609311","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.059802987,0.00001922065,0.933506,0.005571658,0.00030181927,0.00012547825,0.000002413588,0.0005231567,0.00014725782],"genre_scores_gemma":[0.9466329,0.0000038500225,0.046900712,0.0060219304,0.0002461676,0.00004084858,0.0000052163136,0.000020294288,0.0001280593],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99889284,0.000026267544,0.00017073672,0.00034554597,0.00024811813,0.00031648384],"domain_scores_gemma":[0.99951434,0.00012641044,0.00006119779,0.00013836639,0.000087292094,0.000072408606],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031721743,0.000117991694,0.00012208869,0.00017936624,0.00026917146,0.00022130148,0.0003369691,0.000046871486,0.000008134726],"category_scores_gemma":[0.000021638889,0.000114774055,0.00008121091,0.00044575168,0.000026038015,0.00050139305,0.000035129942,0.00008460719,0.00024869211],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036025285,0.000038359005,0.000022872768,0.00030387397,0.000030791423,0.00008219927,0.0010468714,0.015533942,0.1917007,0.00011119472,0.027513577,0.7635796],"study_design_scores_gemma":[0.0002358388,0.000014649532,0.0000060990737,0.00006697581,0.000006470396,0.000014257766,0.00003644538,0.973832,0.023712704,0.00056865107,0.0013352676,0.00017063643],"about_ca_topic_score_codex":0.0000046183386,"about_ca_topic_score_gemma":3.4585534e-7,"teacher_disagreement_score":0.9582981,"about_ca_system_score_codex":0.00003113027,"about_ca_system_score_gemma":0.00004622604,"threshold_uncertainty_score":0.468035},"labels":[],"label_agreement":null},{"id":"W4386626719","doi":"10.18280/isi.280429","title":"A Fractional Ebola Optimization Search Algorithm Approach for Enhanced Speaker Diarization","year":2023,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Speaker diarisation; Computer science; Algorithm; Speech recognition; Speaker verification; Speaker recognition","score_opus":0.025713677455891173,"score_gpt":0.2521937344669724,"score_spread":0.22648005701108123,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386626719","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00094375905,0.0000058909286,0.9876256,0.000080786296,0.0003196292,0.0005723964,0.00003284498,0.0005979162,0.009821206],"genre_scores_gemma":[0.09142999,0.000036982816,0.906045,0.00024501074,0.00014637086,0.00041426183,0.0013316002,0.000016961209,0.00033379527],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985956,0.00006149265,0.00043046603,0.00020232759,0.00040294495,0.00030719943],"domain_scores_gemma":[0.99886686,0.00014041201,0.00016959307,0.00023088175,0.00051055104,0.000081734914],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006491649,0.00014588106,0.00015178719,0.0005000084,0.00038526184,0.0005225264,0.00029399106,0.00012295296,0.0000584667],"category_scores_gemma":[0.00028210736,0.0001484203,0.00008472136,0.0011374812,0.00004642171,0.0043230057,0.00007529668,0.00008819049,0.00026220665],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021753804,0.000046159403,0.000024966404,0.0001555935,0.000042080377,6.619717e-7,0.0035775986,0.069258876,0.00033478346,0.0049259723,0.0012937196,0.9203178],"study_design_scores_gemma":[0.0003778526,0.000036719004,0.00049251574,0.000023154857,0.0000060630655,0.000011249939,0.00040076257,0.99015546,0.0056183115,0.0015344511,0.0011570571,0.00018642758],"about_ca_topic_score_codex":0.000010835559,"about_ca_topic_score_gemma":4.5169827e-7,"teacher_disagreement_score":0.9208966,"about_ca_system_score_codex":0.00016394489,"about_ca_system_score_gemma":0.00010374791,"threshold_uncertainty_score":0.6052404},"labels":[],"label_agreement":null},{"id":"W4386729029","doi":"10.1007/978-3-031-42823-4_20","title":"A Novel Self-supervised Representation Learning Model for an Open-Set Speaker Recognition","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Speaker recognition; Speech recognition; Artificial intelligence; Cluster analysis; Biometrics; Feature learning; Pattern recognition (psychology); Generalization; Cosine similarity; Representation (politics)","score_opus":0.1366916856664875,"score_gpt":0.32034331849955155,"score_spread":0.18365163283306404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386729029","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000112571885,0.00001219163,0.99373364,0.00051471865,0.00090383284,0.0011621002,0.00003567348,0.00057347736,0.0029518118],"genre_scores_gemma":[0.0047483384,0.000037607806,0.99217474,0.0013185473,0.0003304431,0.00010156347,0.00011787867,0.00007629378,0.0010945956],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99593556,0.000058661826,0.00058889616,0.001985872,0.0008233433,0.0006076784],"domain_scores_gemma":[0.99711967,0.00077269156,0.0003274551,0.0010323927,0.0005325122,0.00021529935],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0015564376,0.0004717804,0.0005223377,0.0008794047,0.0004631105,0.0015874449,0.0032953927,0.00034195543,0.000023728617],"category_scores_gemma":[0.0003284315,0.0004759702,0.00014253236,0.0007236769,0.00017283863,0.0018418385,0.0012055306,0.00057643437,0.00011420641],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018273993,0.00006686422,0.0000052548853,0.000033384364,0.000017845396,0.000012844131,0.0016176325,0.026194094,0.0007087876,0.002128051,0.000052812084,0.96914417],"study_design_scores_gemma":[0.0005368145,0.00019393233,0.000016384196,0.00019656845,0.000014796966,0.000037185604,0.0000011526078,0.8656634,0.0009753248,0.13162956,0.00017726616,0.00055763003],"about_ca_topic_score_codex":0.000043614968,"about_ca_topic_score_gemma":0.00020128097,"teacher_disagreement_score":0.9685865,"about_ca_system_score_codex":0.00021452665,"about_ca_system_score_gemma":0.0004889421,"threshold_uncertainty_score":0.9997692},"labels":[],"label_agreement":null},{"id":"W4386764306","doi":"10.1109/waspaa58266.2023.10248132","title":"Robust Audio Anti-Spoofing System Based on Low-Frequency Sub-Band Information","year":2023,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Spectrogram; Discriminative model; Spoofing attack; Computer science; Robustness (evolution); Detector; Focus (optics); Speech recognition; Artificial intelligence; Computer security; Telecommunications","score_opus":0.02636678921615326,"score_gpt":0.20617658468781888,"score_spread":0.17980979547166562,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386764306","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1067006,0.0000040379264,0.76036566,0.0013003543,0.00086013955,0.0002887421,0.00000809992,0.0022678876,0.12820448],"genre_scores_gemma":[0.98669976,0.0000039395927,0.012357394,0.00072698627,0.000038394697,0.00002000772,0.000014947739,0.0000061431724,0.0001324076],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989508,0.00004855688,0.00025000644,0.00018121039,0.0003379671,0.0002314721],"domain_scores_gemma":[0.99924743,0.00014930715,0.00007460868,0.00035799827,0.00009223582,0.000078416466],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00042416123,0.00011072921,0.000128526,0.0003628354,0.00014450941,0.00026772695,0.00035406332,0.00005997571,0.000060942923],"category_scores_gemma":[0.00008292661,0.000094127805,0.000066289365,0.0007959985,0.000012654249,0.0008356446,0.000031040126,0.00006966533,0.0032852162],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041368916,0.00027128577,0.006723353,0.0013848048,0.00010065613,0.00034027014,0.0016200051,0.023656953,0.011962464,0.14992991,0.05171648,0.75225246],"study_design_scores_gemma":[0.00045116158,0.000043476266,0.009561113,0.00021106658,0.000004666572,0.000011107082,0.00014893511,0.9328722,0.055865727,0.000113497736,0.00045065777,0.0002664208],"about_ca_topic_score_codex":0.000021308233,"about_ca_topic_score_gemma":0.000004038672,"teacher_disagreement_score":0.9092152,"about_ca_system_score_codex":0.000071049144,"about_ca_system_score_gemma":0.00006055603,"threshold_uncertainty_score":0.9974908},"labels":[],"label_agreement":null},{"id":"W4387800211","doi":"10.48550/arxiv.2310.11541","title":"MUST&P-SRL: Multi-lingual and Unified Syllabification in Text and Phonetic Domains for Speech Representation Learning","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Syllabification; Computer science; Natural language processing; Artificial intelligence; Representation (politics); Speech recognition; Stress (linguistics); Linguistics; Syllable","score_opus":0.2157484087785792,"score_gpt":0.25914638130662127,"score_spread":0.04339797252804206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387800211","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.68252885,0.000026214375,0.31615213,0.00013599322,0.00017429302,0.0006098093,0.000007858695,0.00019098079,0.00017389376],"genre_scores_gemma":[0.97171223,0.00044031965,0.024766453,0.000027830934,0.00003641195,0.000008862894,0.00004363477,0.000021777609,0.0029424555],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982879,0.00017851646,0.00022179114,0.0009995248,0.00007764819,0.00023459061],"domain_scores_gemma":[0.99866116,0.00045494104,0.00020231439,0.00044935461,0.00013010611,0.00010212868],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004338514,0.00020130881,0.00026165968,0.00048437674,0.00015019905,0.00016728883,0.00037848463,0.00022574577,0.00000843352],"category_scores_gemma":[0.00033482452,0.00024945036,0.00006859455,0.00052746333,0.00008479218,0.00020599861,0.0005011921,0.00032781702,0.00002998418],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000785174,0.0012516688,0.14650649,0.0020852888,0.00067053386,0.0012750525,0.02051693,0.13472432,0.01064974,0.083051436,0.0007467884,0.5977366],"study_design_scores_gemma":[0.002180912,0.000062174484,0.04414771,0.00025334986,0.00007711214,0.000017457758,0.0014572181,0.9268414,0.0014800963,0.022173902,0.0005958805,0.0007127861],"about_ca_topic_score_codex":0.0002676089,"about_ca_topic_score_gemma":0.00048301357,"teacher_disagreement_score":0.79211706,"about_ca_system_score_codex":0.000082025406,"about_ca_system_score_gemma":0.000067971734,"threshold_uncertainty_score":0.99999577},"labels":[],"label_agreement":null},{"id":"W4388097452","doi":"10.18280/ts.400518","title":"A Comprehensive Examination of Phoneme Recognition in Automatic Speech Recognition Systems","year":2023,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Speech recognition; Computer science; Artificial intelligence; Pattern recognition (psychology); Natural language processing","score_opus":0.06636515426379523,"score_gpt":0.25613746559120476,"score_spread":0.18977231132740952,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388097452","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9802143,0.00003134179,0.016111594,0.00015757755,0.0003551408,0.00069203606,0.00003913678,0.00038861818,0.002010262],"genre_scores_gemma":[0.98743415,0.00004623382,0.012007972,0.00008367729,0.00006515757,0.00015500572,0.00014841228,0.000014283735,0.000045123874],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99791795,0.00033304232,0.0006136905,0.00034545304,0.00051814417,0.00027172864],"domain_scores_gemma":[0.9989217,0.00035673968,0.00022629683,0.00018840247,0.00024130021,0.00006555563],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008254981,0.00016375839,0.0002744672,0.00073186174,0.000059881702,0.00008621899,0.00027147014,0.000082855324,0.0003229026],"category_scores_gemma":[0.00005454869,0.00017090769,0.0000795319,0.0012193485,0.00003539215,0.00050998584,0.000055334232,0.0000964144,0.000660743],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009143227,0.0001795567,0.00007758592,0.00019334286,0.000026144295,0.000045665256,0.0007994211,0.00002724896,0.010673258,0.00009298096,0.000404977,0.9874707],"study_design_scores_gemma":[0.0030118576,0.0004296579,0.1093055,0.0010504305,0.000043923457,0.00009134394,0.0020676171,0.8148595,0.06413662,0.0037877206,0.0005025576,0.00071327225],"about_ca_topic_score_codex":0.000063046056,"about_ca_topic_score_gemma":0.000012929607,"teacher_disagreement_score":0.9867574,"about_ca_system_score_codex":0.00008498315,"about_ca_system_score_gemma":0.000037427708,"threshold_uncertainty_score":0.84927344},"labels":[],"label_agreement":null},{"id":"W4388104645","doi":"10.18280/ts.400529","title":"A Comprehensive Review on Machine Learning Approaches for Enhancing Human Speech Recognition","year":2023,"lang":"en","type":"review","venue":"Traitement du signal","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Speech recognition; Artificial intelligence; Machine learning; Natural language processing","score_opus":0.30327594934148594,"score_gpt":0.3540698144114672,"score_spread":0.05079386506998124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388104645","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000014889636,0.9689346,0.026024783,0.00012467778,0.00021219118,0.0031811516,0.00010244406,0.00053274794,0.0008859116],"genre_scores_gemma":[0.0000019569418,0.9856604,0.010827668,0.0004407834,0.00033316208,0.0012659434,0.0009889695,0.00008867188,0.00039245028],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962747,0.0005556556,0.0011396228,0.0009886642,0.00054418034,0.0004971576],"domain_scores_gemma":[0.9975704,0.0010532256,0.0006881328,0.00039449145,0.00014649835,0.00014727913],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011464439,0.0006364719,0.0017670119,0.00044231725,0.00037684012,0.00020184278,0.0008066326,0.00019925022,0.00030970055],"category_scores_gemma":[0.00012205652,0.0005413799,0.00093821797,0.0006355426,0.000035396046,0.00019542356,0.0001500516,0.0005198453,0.00084361894],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000025872262,0.00008389993,4.2609383e-8,0.044410408,0.00017206639,0.000019345422,0.000029207167,9.472549e-7,0.00000228146,0.0001668681,0.001150646,0.95396173],"study_design_scores_gemma":[0.000313955,0.00031004526,5.058052e-7,0.07101804,0.000519923,0.000050428425,0.000013959874,0.0011772633,0.000053100575,0.0004139811,0.9254521,0.0006766596],"about_ca_topic_score_codex":0.0000087540975,"about_ca_topic_score_gemma":0.000009706155,"teacher_disagreement_score":0.95328504,"about_ca_system_score_codex":0.00015446701,"about_ca_system_score_gemma":0.000121480305,"threshold_uncertainty_score":0.9999343},"labels":[],"label_agreement":null},{"id":"W4388380244","doi":"10.1007/s10772-023-10059-4","title":"Attention-based factorized TDNN for a noise-robust and spoof-aware speaker verification system","year":2023,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Spoofing attack; Speech recognition; Speaker verification; Encoder; Speaker recognition; Artificial neural network; Context (archaeology); Mel-frequency cepstrum; Artificial intelligence; Word error rate; Frame (networking); Pattern recognition (psychology); Feature extraction; Telecommunications","score_opus":0.02756174976548047,"score_gpt":0.27208361846283263,"score_spread":0.24452186869735215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388380244","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29438448,0.000056110406,0.6832986,0.01892824,0.002364073,0.0002768076,0.000037920057,0.00046541434,0.0001883597],"genre_scores_gemma":[0.92135566,0.0000366927,0.078125685,0.00010343066,0.00019346585,0.000021994061,0.000011996741,0.000014245533,0.00013680129],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986997,0.000027979859,0.000464781,0.00022815625,0.00040416847,0.00017518605],"domain_scores_gemma":[0.99821573,0.00019342279,0.00040206636,0.00020194409,0.00092645554,0.000060365477],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046116035,0.00012067762,0.00021658884,0.0011735887,0.000070471644,0.0001216444,0.0008685119,0.0001488878,0.000019247818],"category_scores_gemma":[0.0002633495,0.00010990888,0.00012631243,0.00047242813,0.000062825406,0.0002712327,0.00008216001,0.0001566538,0.00005577456],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024847014,0.0001948172,0.0102312565,0.00010680648,0.00049861305,0.00053480593,0.00012695498,0.000111559806,0.04920394,0.04741565,0.0036130878,0.887714],"study_design_scores_gemma":[0.018497419,0.0015110481,0.051767968,0.002071849,0.00026950767,0.007869053,0.0037462828,0.5049473,0.2740705,0.035527807,0.09776163,0.001959623],"about_ca_topic_score_codex":0.0000053359904,"about_ca_topic_score_gemma":0.000003883126,"teacher_disagreement_score":0.8857544,"about_ca_system_score_codex":0.000140732,"about_ca_system_score_gemma":0.00009189431,"threshold_uncertainty_score":0.4481954},"labels":[],"label_agreement":null},{"id":"W4388483000","doi":"10.1109/ase56229.2023.00107","title":"ASTER: Automatic Speech Recognition System Accessibility Testing for Stutterers","year":2023,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Research Foundation Singapore; Neurosciences Research Foundation","keywords":"Computer science; Stuttering; Advanced Spaceborne Thermal Emission and Reflection Radiometer; Speech recognition; Test (biology); Rendering (computer graphics); Natural language processing; Artificial intelligence","score_opus":0.1166057641101622,"score_gpt":0.3060882649432736,"score_spread":0.1894825008331114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388483000","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6862632,0.0000053015706,0.2732071,0.0008726108,0.000972418,0.0010915163,0.000022853985,0.005700544,0.031864483],"genre_scores_gemma":[0.45261168,5.410295e-7,0.54624707,0.00029643698,0.00009316099,0.00017902482,0.0000148946465,0.000015456559,0.0005417103],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99858415,0.00008402022,0.00034258582,0.0004370175,0.00024009071,0.00031211955],"domain_scores_gemma":[0.99831665,0.0009006157,0.00010724991,0.0003939803,0.00019176342,0.00008974097],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009853417,0.00012820399,0.00018174009,0.00019737276,0.00017680517,0.00030997657,0.00048792543,0.000059511316,0.000062297164],"category_scores_gemma":[0.00055381714,0.00011080743,0.000086524444,0.0009776305,0.000017436512,0.000602006,0.00012939793,0.000054970493,0.001122197],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014187185,0.000018321634,0.00050089846,0.00016029895,0.000010254802,0.000008531739,0.000050309773,2.973345e-7,0.0004270228,0.00012336193,0.0012894929,0.9974098],"study_design_scores_gemma":[0.0007709397,0.00015341866,0.02086308,0.00034997697,0.000028507997,0.0000873871,0.0009053863,0.9271321,0.042093776,0.0067917323,0.00030587727,0.00051779667],"about_ca_topic_score_codex":0.00001860328,"about_ca_topic_score_gemma":0.000009107803,"teacher_disagreement_score":0.996892,"about_ca_system_score_codex":0.00007309203,"about_ca_system_score_gemma":0.000046092082,"threshold_uncertainty_score":0.99965554},"labels":[],"label_agreement":null},{"id":"W4388854325","doi":"10.1007/978-3-031-48312-7_44","title":"Self-supervised Speaker Verification Employing Augmentation Mix and Self-augmented Training-Based Clustering","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Cluster analysis; Embedding; Artificial intelligence; Dependency (UML); Noise (video); Speaker recognition; Representation (politics); Pattern recognition (psychology); Data mining; Machine learning; Speech recognition; Image (mathematics)","score_opus":0.0421863035107793,"score_gpt":0.25844806115425595,"score_spread":0.21626175764347666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388854325","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00079901644,0.00005661538,0.9947997,0.0007366954,0.001156724,0.00053041766,0.000005855317,0.0008960098,0.0010189892],"genre_scores_gemma":[0.053074352,0.00007759354,0.94503087,0.0013668204,0.00020607703,0.00003485501,0.000022119873,0.000064734515,0.0001225579],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965718,0.00006804935,0.0005367407,0.0014238397,0.00086693786,0.00053265406],"domain_scores_gemma":[0.99805146,0.00054709177,0.000257238,0.00076886365,0.00018860077,0.00018674598],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009577818,0.00046757548,0.00042048024,0.0009829241,0.0003420464,0.0007439449,0.0011820035,0.00025598297,0.000023352028],"category_scores_gemma":[0.00007544667,0.0004767172,0.00010408103,0.0006935995,0.00018283709,0.00059601094,0.00040844735,0.00040027616,0.000074476695],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008431377,0.000052666826,0.00006284612,0.00012276319,0.000031734387,0.000054690794,0.0033268097,0.0036345501,0.0003688854,0.0008589694,0.000009735838,0.9914679],"study_design_scores_gemma":[0.00052669446,0.00009722934,0.0003427862,0.00033554042,0.000020599606,0.000037450878,0.000002207173,0.99104726,0.0013498324,0.005291906,0.00039530272,0.000553215],"about_ca_topic_score_codex":0.000014681143,"about_ca_topic_score_gemma":0.00008030272,"teacher_disagreement_score":0.9909147,"about_ca_system_score_codex":0.00031526,"about_ca_system_score_gemma":0.00036492135,"threshold_uncertainty_score":0.99976844},"labels":[],"label_agreement":null},{"id":"W4388878572","doi":"10.1007/978-3-031-48312-7_36","title":"Multi-task Learning over Mixup Variants for the Speaker Verification Task","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Speech recognition; Robustness (evolution); Artificial intelligence; Regularization (linguistics); Machine learning","score_opus":0.041228708833597756,"score_gpt":0.2696667201367999,"score_spread":0.22843801130320213,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388878572","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000028300947,0.00013678729,0.99434334,0.0011226225,0.0026915278,0.00066061114,0.000013161606,0.00028382285,0.00071980624],"genre_scores_gemma":[0.048208456,0.00024816341,0.94044155,0.003093911,0.0010188873,0.00012572834,0.000028758466,0.00012863653,0.0067059025],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966921,0.00005574668,0.00045932303,0.0013961733,0.00079969567,0.0005969361],"domain_scores_gemma":[0.99618113,0.0019803708,0.00030483492,0.0011500719,0.00026287974,0.00012070252],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014534554,0.00042471747,0.0003723795,0.0005228237,0.00058788486,0.0007647174,0.0027339559,0.00028457763,0.000040564788],"category_scores_gemma":[0.0005145677,0.00032467494,0.0002021888,0.00063909066,0.00039140877,0.00043843978,0.00062224973,0.00067764544,0.00025447473],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000071342256,0.000024927058,0.000033622913,0.000024286199,0.000027083715,0.000019712517,0.0006612765,0.0050675245,0.0008197479,0.004463671,0.000125724,0.9887253],"study_design_scores_gemma":[0.00035572753,0.00007299677,0.0013794041,0.00019142451,0.000019035624,0.000030193809,6.837724e-7,0.9662025,0.00063302513,0.01857404,0.012013673,0.00052731123],"about_ca_topic_score_codex":0.000029211084,"about_ca_topic_score_gemma":0.00008117255,"teacher_disagreement_score":0.988198,"about_ca_system_score_codex":0.00016641886,"about_ca_system_score_gemma":0.00028679823,"threshold_uncertainty_score":0.99992055},"labels":[],"label_agreement":null},{"id":"W4388878685","doi":"10.1007/978-3-031-48312-7_25","title":"Audio DeepFake Detection Employing Multiple Parametric Exponential Linear Units","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Activation function; Parametric statistics; Process (computing); Residual; Exponential function; Artificial intelligence; Speech recognition; Function (biology); Deep learning; Task (project management); Parametric model; Sign (mathematics); Pattern recognition (psychology); Artificial neural network; Algorithm; Mathematics","score_opus":0.052630643896907775,"score_gpt":0.2539528112894271,"score_spread":0.20132216739251932,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388878685","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010807944,0.000084035346,0.9928921,0.00016881901,0.003914043,0.0004000294,0.0000073896044,0.0006817022,0.0007711129],"genre_scores_gemma":[0.47983426,0.00013399917,0.5164607,0.000963548,0.001335072,0.000043576136,0.000016008535,0.00012978318,0.0010830114],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956635,0.00007386849,0.00061064755,0.001641538,0.001245239,0.0007651988],"domain_scores_gemma":[0.99640787,0.0014504798,0.0003176483,0.001138364,0.000451067,0.00023454975],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010374535,0.00054517813,0.0005331118,0.0024651797,0.00045155833,0.00058365177,0.002358389,0.00044829093,0.00002820635],"category_scores_gemma":[0.0009828141,0.0005363936,0.00017600233,0.003112957,0.00035376576,0.00062673277,0.001050446,0.0008804662,0.0004606861],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000064885844,0.000018207955,0.00005015356,0.000021658674,0.00001460072,0.000114746224,0.00021974585,0.0045525846,0.00044769922,0.00043464394,0.000008392033,0.99411106],"study_design_scores_gemma":[0.00044326772,0.00017265829,0.00043499222,0.00034277345,0.000017812154,0.00012395612,5.5550777e-7,0.94671065,0.024024423,0.025464103,0.0012712309,0.0009935553],"about_ca_topic_score_codex":0.000052222604,"about_ca_topic_score_gemma":0.0003069444,"teacher_disagreement_score":0.9931175,"about_ca_system_score_codex":0.00029086604,"about_ca_system_score_gemma":0.00036676944,"threshold_uncertainty_score":0.9997088},"labels":[],"label_agreement":null},{"id":"W4389115567","doi":"10.48550/arxiv.2311.15077","title":"Multilingual self-supervised speech representations improve the speech recognition of low-resource African languages with codeswitching","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institute for Advanced Research; National Science Foundation","keywords":"Computer science; Bespoke; Code (set theory); Natural language processing; Artificial intelligence; Speech recognition; Language model; Scratch; Programming language","score_opus":0.07033471131280217,"score_gpt":0.22219515293901865,"score_spread":0.15186044162621648,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389115567","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9021213,0.000018064768,0.08808164,0.0003768024,0.00029406193,0.00090569834,0.00013473653,0.00085804565,0.0072096675],"genre_scores_gemma":[0.95840305,0.00005203148,0.040066965,0.000086067135,0.000109153705,0.000006116894,0.00005987303,0.000042729167,0.0011740121],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976209,0.0003337592,0.00033082094,0.001090534,0.00025855488,0.0003654275],"domain_scores_gemma":[0.99691314,0.00076070474,0.00043941615,0.0013718875,0.00037568694,0.00013916382],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00055995653,0.00034351164,0.00039225022,0.00038720368,0.00025372367,0.00016933634,0.0015973633,0.00022217467,0.00005495993],"category_scores_gemma":[0.00020101751,0.00029419817,0.00024887195,0.0010126864,0.0001436186,0.0002950908,0.0009838687,0.00063241593,0.00010548706],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011243115,0.0033366904,0.01165765,0.002436124,0.0044802404,0.009613018,0.037984345,0.05039525,0.0087489085,0.009106701,0.0020623798,0.8590544],"study_design_scores_gemma":[0.0027023854,0.00025573865,0.0022642163,0.0009144058,0.0005955239,0.00009320366,0.018753406,0.83025426,0.124019675,0.018110555,0.00026812163,0.0017684969],"about_ca_topic_score_codex":0.0006294089,"about_ca_topic_score_gemma":0.00027298852,"teacher_disagreement_score":0.85728586,"about_ca_system_score_codex":0.00011821695,"about_ca_system_score_gemma":0.0002277121,"threshold_uncertainty_score":0.999951},"labels":[],"label_agreement":null},{"id":"W4389191800","doi":"10.22215/etd/2023-15803","title":"Differentiation of Dry and Wet Cough Sounds using A Deep Learning Model and Data Augmentation","year":2023,"lang":"en","type":"dissertation","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"AGE-WELL","keywords":"Reverberation; Dry cough; Noise (video); Computer science; Speech recognition; Deep learning; Task (project management); Artificial intelligence; Test data; Training set; Machine learning; Pattern recognition (psychology); Image (mathematics); Engineering; Medicine","score_opus":0.08115625648407646,"score_gpt":0.32814461729633004,"score_spread":0.2469883608122536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389191800","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.56868064,0.00010224587,0.42973915,0.000021676553,0.00020373617,0.00014611361,0.000012852599,0.00011281631,0.0009807354],"genre_scores_gemma":[0.8124727,0.00087300496,0.17675903,0.000050526094,0.000052954754,0.000016179014,0.0032303783,0.000049771796,0.006495459],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989434,0.00004861955,0.00024440544,0.00040802037,0.00025123323,0.000104304425],"domain_scores_gemma":[0.9992846,0.00011024629,0.00021487937,0.00026886465,0.00008221887,0.000039188122],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021159762,0.0001316881,0.00018882453,0.00020210825,0.00011442774,0.0001709436,0.00024469194,0.00011470725,0.000016962365],"category_scores_gemma":[0.0000773729,0.00013081096,0.000020771111,0.000158464,0.000015003454,0.0004950328,0.00012923809,0.000104446466,0.0000030454735],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049530365,0.00008474088,0.002654913,0.00070904987,0.00019527454,0.000004187605,0.008256828,0.0008363683,0.012189925,0.0033016147,0.00011748457,0.97160006],"study_design_scores_gemma":[0.00017866459,0.000012902764,0.0069932635,0.000079330166,0.000051919647,0.0000011481102,0.0009969941,0.9887279,0.0008668582,0.0019462506,0.0000051057077,0.00013962865],"about_ca_topic_score_codex":0.000107743894,"about_ca_topic_score_gemma":0.00042757325,"teacher_disagreement_score":0.98789155,"about_ca_system_score_codex":0.00001683165,"about_ca_system_score_gemma":0.00004046782,"threshold_uncertainty_score":0.53343165},"labels":[],"label_agreement":null},{"id":"W4389518264","doi":"10.18653/v1/2023.calcs-1.8","title":"Multilingual self-supervised speech representations improve the speech recognition of low-resource African languages with codeswitching","year":2023,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institute for Advanced Research; National Science Foundation","keywords":"Computer science; Bespoke; Code (set theory); Natural language processing; Artificial intelligence; Speech recognition; Language model; Programming language","score_opus":0.023251246850451306,"score_gpt":0.27282881387348334,"score_spread":0.24957756702303205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389518264","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9256777,0.000014972405,0.020361237,0.0022447647,0.0001411189,0.0007199175,0.000035985544,0.0013358364,0.04946847],"genre_scores_gemma":[0.7389375,0.000013859388,0.25904799,0.00038176967,0.00011375347,0.00005472913,0.00003202681,0.000028646255,0.001389695],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983151,0.00016141678,0.00031293495,0.00043001387,0.00047835358,0.00030219377],"domain_scores_gemma":[0.9981573,0.0007690006,0.000140228,0.00063648756,0.000209807,0.0000871783],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006147415,0.00016677487,0.00019694727,0.0002225324,0.00020659943,0.00015051775,0.00063643156,0.000060577862,0.00014799315],"category_scores_gemma":[0.00024287778,0.00010905228,0.000096987795,0.0011663598,0.00006419112,0.0003060898,0.00016530282,0.00016873034,0.00019284098],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029333303,0.00016094101,0.00037567655,0.000045333487,0.00009347225,0.00009480187,0.0053310967,0.000024178113,0.01308265,0.00021285383,0.00074604,0.9798036],"study_design_scores_gemma":[0.001150517,0.00015210836,0.0016912614,0.000096259006,0.00004911698,0.00010788293,0.01850311,0.11410702,0.8619091,0.0011611832,0.0006283279,0.0004441095],"about_ca_topic_score_codex":0.0002138264,"about_ca_topic_score_gemma":0.00011617227,"teacher_disagreement_score":0.9793595,"about_ca_system_score_codex":0.000024617417,"about_ca_system_score_gemma":0.0000751504,"threshold_uncertainty_score":0.4447023},"labels":[],"label_agreement":null},{"id":"W4389518357","doi":"10.18653/v1/2023.arabicnlp-1.38","title":"VoxArabica: A Robust Dialect-Aware Arabic Speech Recognition System","year":2023,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Alliance de recherche numérique du Canada; Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Arabic; Computer science; Upload; Natural language processing; Interface (matter); Speech recognition; Range (aeronautics); Artificial intelligence; Language model; Linguistics; World Wide Web; Engineering","score_opus":0.05897081501115145,"score_gpt":0.23440623216464804,"score_spread":0.1754354171534966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389518357","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16369216,0.000051151797,0.5554057,0.005589459,0.003466448,0.0011593816,0.000047710117,0.014024452,0.25656357],"genre_scores_gemma":[0.90250975,0.00007652818,0.08582593,0.0010803168,0.00049441744,0.00023202975,0.000078140685,0.000057836896,0.009645034],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982337,0.00013347277,0.00030298016,0.0005313905,0.0003854015,0.00041305477],"domain_scores_gemma":[0.9988699,0.0002354851,0.000077249686,0.00049094745,0.00016486092,0.00016156047],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00049331103,0.00017914808,0.00022289371,0.00037021795,0.00019026086,0.000242985,0.00056402985,0.000113671675,0.00035806277],"category_scores_gemma":[0.0001068341,0.00015857577,0.00013555016,0.0015076831,0.000029580702,0.00051280134,0.00014347282,0.00013180044,0.014913468],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000073425663,0.000057330544,0.00015816328,0.00007658731,0.000036518064,0.0002551021,0.00013435268,0.000013244358,0.0004853751,0.0021866974,0.02727837,0.96931094],"study_design_scores_gemma":[0.0032699967,0.00048040616,0.015733387,0.0010171133,0.00012479667,0.0017069627,0.0029707362,0.7036155,0.22886801,0.012120136,0.026477903,0.0036150655],"about_ca_topic_score_codex":0.000040711013,"about_ca_topic_score_gemma":0.00003117434,"teacher_disagreement_score":0.96569586,"about_ca_system_score_codex":0.00008569067,"about_ca_system_score_gemma":0.000057831152,"threshold_uncertainty_score":0.98585355},"labels":[],"label_agreement":null},{"id":"W4389518772","doi":"10.18653/v1/2023.emnlp-main.323","title":"PromptMix: A Class Boundary Augmentation Method for Large Language Model Distillation","year":2023,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; McGill University; Canadian Institute for Advanced Research","funders":"","keywords":"Class (philosophy); Distillation; Computer science; Boundary (topology); Programming language; Artificial intelligence; Mathematics; Chemistry; Chromatography; Mathematical analysis","score_opus":0.03956160061057078,"score_gpt":0.34672870365444136,"score_spread":0.30716710304387057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389518772","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004113917,0.000006367184,0.9882335,0.0012715013,0.00012125514,0.00030882933,0.000027079992,0.00054029486,0.0053772326],"genre_scores_gemma":[0.104143634,0.0000035553974,0.8888209,0.0007455946,0.000050566137,0.00015571652,0.00009107388,0.000012010961,0.0059769833],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99922603,0.00004148892,0.00013749981,0.00023985213,0.00016605035,0.00018909795],"domain_scores_gemma":[0.9995122,0.00016072021,0.000042237956,0.00018518367,0.000053612643,0.00004607964],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048680676,0.00007271936,0.00008583916,0.00012002911,0.00013485452,0.00014017297,0.00017076533,0.000039191622,0.000052754505],"category_scores_gemma":[0.00007427225,0.000064276464,0.00006247377,0.00030747923,0.0000051874713,0.0003062045,0.00005502299,0.000031080202,0.00015589809],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002067271,0.00008267468,0.000059070768,0.000055291766,0.00003310205,0.0000060413217,0.0029953565,0.00045052072,0.010227095,0.15999606,0.02113991,0.8049342],"study_design_scores_gemma":[0.0003057151,0.00001607537,0.00028708676,0.000004655854,0.000004977841,0.0000018955683,0.00018402399,0.9776,0.0070798183,0.011823089,0.0025991509,0.000093541195],"about_ca_topic_score_codex":0.000008091257,"about_ca_topic_score_gemma":0.000031236355,"teacher_disagreement_score":0.9771494,"about_ca_system_score_codex":0.00003099798,"about_ca_system_score_gemma":0.00004185314,"threshold_uncertainty_score":0.2621118},"labels":[],"label_agreement":null},{"id":"W4389519335","doi":"10.18653/v1/2023.emnlp-industry.8","title":"MUST&P-SRL: Multi-lingual and Unified Syllabification in Text and Phonetic Domains for Speech Representation Learning","year":2023,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Syllabification; Natural language processing; Artificial intelligence; Speech recognition; Representation (politics); Stress (linguistics); Linguistics; Syllable","score_opus":0.08676770552050438,"score_gpt":0.3358065862145701,"score_spread":0.2490388806940657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389519335","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8565636,0.000025077463,0.14096612,0.00086140673,0.00008679736,0.0004968629,0.0000014185431,0.0002618319,0.00073687366],"genre_scores_gemma":[0.8150858,0.00013774338,0.18093161,0.000109311135,0.000033188753,0.00008641622,0.000021458924,0.000012741375,0.0035816657],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990994,0.000073723386,0.00018924286,0.00035299722,0.00011789745,0.00016676508],"domain_scores_gemma":[0.99925935,0.00040808602,0.00005356499,0.0001656992,0.000058493642,0.000054816177],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043853675,0.000078967714,0.000112584225,0.0002462551,0.00010398785,0.00014290362,0.00011120376,0.000055583034,0.00001600158],"category_scores_gemma":[0.0004185966,0.0000797892,0.000019880963,0.0005044415,0.000031447038,0.00018588745,0.00006554064,0.000071031376,0.000044873388],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015725673,0.000044513446,0.004587799,0.000031448813,0.0000085459715,0.0000069152247,0.002347962,0.00006155674,0.015956862,0.0019840293,0.00019979713,0.97475487],"study_design_scores_gemma":[0.0035140498,0.00012250205,0.2249599,0.00008457514,0.000017548924,0.00006125197,0.0039955443,0.7148372,0.040777113,0.0054838355,0.0055497815,0.0005967056],"about_ca_topic_score_codex":0.00007667156,"about_ca_topic_score_gemma":0.00021609536,"teacher_disagreement_score":0.97415817,"about_ca_system_score_codex":0.000014204271,"about_ca_system_score_gemma":0.00001742247,"threshold_uncertainty_score":0.3253709},"labels":[],"label_agreement":null},{"id":"W4389524018","doi":"10.18653/v1/2023.emnlp-main.182","title":"Generative Spoken Language Model based on continuous word-sized audio tokens","year":2023,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Grand Équipement National De Calcul Intensif; Agence Nationale de la Recherche; Canadian Institute for Advanced Research","keywords":"Computer science; Natural language processing; Language model; Word (group theory); Speech recognition; Artificial intelligence; Generative grammar; Spoken language; Generative model; Bridging (networking); Linguistics","score_opus":0.027014318475177688,"score_gpt":0.26470486781931507,"score_spread":0.2376905493441374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389524018","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06584118,0.000007768737,0.8122622,0.0050744554,0.00026482393,0.0002616141,0.000017082097,0.0014400585,0.114830844],"genre_scores_gemma":[0.686569,0.000009382259,0.27046368,0.008762923,0.00010965876,0.000069915615,0.000020552721,0.000024696797,0.03397022],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988919,0.00007138566,0.0001524675,0.00033836399,0.00027760703,0.00026829352],"domain_scores_gemma":[0.99917364,0.00021225946,0.000039028957,0.00041851558,0.000056043846,0.00010050759],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00022368469,0.00013215179,0.00017604661,0.0001873309,0.00009281471,0.0001265124,0.0003923238,0.00005360688,0.00040348386],"category_scores_gemma":[0.00010000279,0.000107270076,0.00009604045,0.00046744396,0.000020759768,0.00013236151,0.00007504071,0.00008468959,0.0016394686],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007932885,0.00029689205,0.0001454451,0.000016538666,0.0000708097,0.0005052831,0.0032535926,0.010216806,0.019764422,0.020923315,0.12209522,0.8226324],"study_design_scores_gemma":[0.0004455358,0.00002745274,0.0001949293,0.000009858609,0.0000033691,0.000001731934,0.00010358345,0.9650495,0.03288324,0.00053404213,0.00058530265,0.00016142576],"about_ca_topic_score_codex":0.000017703704,"about_ca_topic_score_gemma":0.000024309804,"teacher_disagreement_score":0.95483273,"about_ca_system_score_codex":0.000029271401,"about_ca_system_score_gemma":0.0000671773,"threshold_uncertainty_score":0.9991379},"labels":[],"label_agreement":null},{"id":"W4390037801","doi":"10.1162/tacl_a_00627","title":"AfriSpeech-200: Pan-African Accented Speech Dataset for Clinical and General Domain ASR","year":2023,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Benchmark (surveying); Computer science; Speech recognition; Domain (mathematical analysis); Set (abstract data type); Productivity; Natural language processing; Test set; Test (biology); Artificial intelligence; Biology","score_opus":0.05812305070298272,"score_gpt":0.34878724945583334,"score_spread":0.2906641987528506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390037801","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004646251,0.0000127705525,0.9822262,0.0024006818,0.001841101,0.0007155606,0.0077104303,0.00013544245,0.00031159775],"genre_scores_gemma":[0.35934556,0.000052782114,0.6367134,0.0004424211,0.0005730782,0.00010620885,0.0015428051,0.00003146881,0.0011922971],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99848443,0.000114318675,0.0005347872,0.00027904252,0.00037190493,0.00021549054],"domain_scores_gemma":[0.99603134,0.002563846,0.0003467819,0.00023151998,0.0007614666,0.00006503862],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011142275,0.00011910739,0.0002262917,0.00013752948,0.00035474583,0.0000871831,0.00042157035,0.00010797433,0.0000062935574],"category_scores_gemma":[0.0022359372,0.00010881566,0.00021186458,0.00047747197,0.00005942516,0.00006553385,0.000031969354,0.000113811875,0.000010210983],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005093823,0.0021406019,0.022171088,0.00045516738,0.0026034927,0.00000748578,0.0015130311,0.03347242,0.0002495657,0.36198834,0.3560663,0.21882313],"study_design_scores_gemma":[0.0031283628,0.00019909881,0.03233039,0.000039141392,0.00024087749,0.0000068514782,0.00012918987,0.53453594,0.0006791473,0.20516138,0.22309673,0.000452887],"about_ca_topic_score_codex":0.000013066066,"about_ca_topic_score_gemma":0.000016748594,"teacher_disagreement_score":0.5010635,"about_ca_system_score_codex":0.00007179853,"about_ca_system_score_gemma":0.00012300904,"threshold_uncertainty_score":0.44373736},"labels":[],"label_agreement":null},{"id":"W4390126565","doi":"10.18280/isi.280612","title":"Enhanced Dialectal Speech Recognition in Punjabi Using Pitch-Based Acoustic Modeling","year":2023,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Speech recognition; Computer science; Acoustic model; Natural language processing; Acoustics; Speech processing; Physics","score_opus":0.0453817229647579,"score_gpt":0.25765321074589137,"score_spread":0.21227148778113347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390126565","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45975843,0.0000049535993,0.5378039,0.000026944468,0.0003374691,0.00019836213,0.000006959591,0.00035658196,0.001506448],"genre_scores_gemma":[0.96412945,0.000012477639,0.035473287,0.0001680268,0.000048891907,0.000058360438,0.00008618207,0.000011813882,0.000011501845],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982656,0.00011551756,0.0006337378,0.00020838794,0.000364173,0.00041253644],"domain_scores_gemma":[0.9991014,0.00013635524,0.00018404884,0.00025263912,0.00024422182,0.00008134094],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008062748,0.00018368811,0.00021127929,0.0009526199,0.00020637995,0.0003928158,0.00031160927,0.00012990704,0.000039532537],"category_scores_gemma":[0.0005240905,0.00019861317,0.00008187942,0.0016973793,0.000034035296,0.003962439,0.00007431191,0.0001479104,0.0005437141],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022621964,0.000031610893,0.000071276874,0.00018937717,0.000011966593,0.000016709211,0.0024967757,0.043731254,0.0074029192,0.00013291863,0.000037552603,0.945855],"study_design_scores_gemma":[0.00039537344,0.000029714036,0.0003298334,0.00023358072,0.0000065556087,0.000018685787,0.00032831464,0.972624,0.021317521,0.004449662,0.000013770546,0.00025298417],"about_ca_topic_score_codex":0.00010150374,"about_ca_topic_score_gemma":0.000043198146,"teacher_disagreement_score":0.94560206,"about_ca_system_score_codex":0.00033927234,"about_ca_system_score_gemma":0.00016063728,"threshold_uncertainty_score":0.809921},"labels":[],"label_agreement":null},{"id":"W4390912555","doi":"10.21437/speechprosody.2010-77","title":"Whispered speech prosody modeling for TTS synthesis","year":2010,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Prosody; Computer science; Speech synthesis; Speech recognition","score_opus":0.031759349840083335,"score_gpt":0.25995687634559256,"score_spread":0.22819752650550923,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390912555","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.053126138,0.000005617996,0.91483617,0.0018981972,0.0005832133,0.00036545377,0.000004567268,0.00041839157,0.028762233],"genre_scores_gemma":[0.4487206,0.0000025140948,0.54984725,0.00031696048,0.000097922544,0.00010193499,7.700034e-7,0.000010609711,0.0009014483],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989411,0.00001784874,0.00019825398,0.0003738002,0.00019244182,0.0002765044],"domain_scores_gemma":[0.9989508,0.0002514752,0.000036902125,0.00048749225,0.00015842397,0.00011490662],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035652955,0.00012437628,0.00015976187,0.000104278035,0.00013800866,0.00020552854,0.0006248571,0.000093292074,0.0003799463],"category_scores_gemma":[0.00042133935,0.000103600985,0.000112284135,0.00016005641,0.000017932742,0.00035773774,0.00007799626,0.00010681299,0.00022295123],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010792497,0.00012736133,0.00006694639,0.0000198878,0.00002448234,0.000005677836,0.000114832044,0.000014011109,0.041089367,0.046233054,0.0018891802,0.9104044],"study_design_scores_gemma":[0.00015313123,0.00001599625,0.000022255968,0.0000089764535,0.000007671117,0.000025326468,0.000024678915,0.81602454,0.17191352,0.008483359,0.0031109424,0.00020960318],"about_ca_topic_score_codex":0.000019110961,"about_ca_topic_score_gemma":0.00007045331,"teacher_disagreement_score":0.9101948,"about_ca_system_score_codex":0.000010566301,"about_ca_system_score_gemma":0.00005042672,"threshold_uncertainty_score":0.42247257},"labels":[],"label_agreement":null},{"id":"W4390913029","doi":"10.21437/iscslp.2008-51","title":"Subword Latent Semantic Analysis for TextTiling-based Automatic Story Segmentation of Chinese Broadcast News","year":2008,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Science North","funders":"","keywords":"Bigram; Computer science; Artificial intelligence; Speech recognition; Latent semantic analysis; Natural language processing; Robustness (evolution); Mandarin Chinese; Sentence; Treebank; Hidden Markov model; Segmentation; Character (mathematics); Text segmentation; Trigram; Annotation; Linguistics","score_opus":0.03312502395368702,"score_gpt":0.27234236591370903,"score_spread":0.239217341960022,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390913029","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4484667,0.000017891269,0.55074155,0.00030063454,0.000059344264,0.00016466166,0.000002699885,0.00009516827,0.00015135822],"genre_scores_gemma":[0.8334804,0.000006019908,0.16594742,0.00025362882,0.000012735153,0.00002681706,0.0000091344755,0.000005682265,0.00025815977],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99897295,0.00007161873,0.00029801883,0.0002524356,0.0002514136,0.0001535656],"domain_scores_gemma":[0.9990464,0.0002809198,0.00015050072,0.0003299212,0.00012421247,0.00006803226],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002201656,0.00012025122,0.00027343625,0.00039825705,0.00010966099,0.000026751455,0.0002646774,0.00003861848,0.0002243483],"category_scores_gemma":[0.00007549617,0.00009490133,0.00027262708,0.00086759834,0.00003355789,0.00017899492,0.000024110297,0.00003855165,0.00002843834],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039751292,0.00087756047,0.3693389,0.00024259389,0.0009159941,0.00002393349,0.0021412612,0.0061485576,0.0065677306,0.00026130574,0.0010886182,0.6123538],"study_design_scores_gemma":[0.00046822842,0.000056777128,0.09351538,0.000008462947,0.00008131679,0.000004110637,0.000038138794,0.8998253,0.005739326,0.00009052791,0.000040389827,0.00013204197],"about_ca_topic_score_codex":0.000057622023,"about_ca_topic_score_gemma":0.0000903992,"teacher_disagreement_score":0.89367676,"about_ca_system_score_codex":0.0000330096,"about_ca_system_score_gemma":0.0000715112,"threshold_uncertainty_score":0.3869964},"labels":[],"label_agreement":null},{"id":"W4390917297","doi":"10.3389/fnins.2023.1351848","title":"Speaker-turn aware diarization for speech-based cognitive assessments","year":2024,"lang":"en","type":"article","venue":"Frontiers in Neuroscience","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Dalhousie University","funders":"Shenzhen University; National Natural Science Foundation of China","keywords":"Speaker diarisation; Computer science; Speech recognition; Cluster analysis; Channel (broadcasting); Microphone; Feature (linguistics); Similarity (geometry); Artificial intelligence; Speaker recognition; Telecommunications","score_opus":0.03173854922503484,"score_gpt":0.3128822342037598,"score_spread":0.281143684978725,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390917297","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022510218,0.00007388599,0.990051,0.00066921196,0.005324153,0.0004220435,0.00003732249,0.0002286633,0.0009427159],"genre_scores_gemma":[0.7692725,0.000037911548,0.22716306,0.0025272775,0.00009679095,0.00014144783,0.000014964646,0.000026242817,0.00071976706],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982292,0.00008231302,0.000220309,0.0007404537,0.00037557393,0.0003521689],"domain_scores_gemma":[0.99933916,0.00021331503,0.000050933762,0.00022637378,0.00007420105,0.000095984935],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039356545,0.00015253383,0.00015407991,0.0004292391,0.00012786937,0.00053438277,0.0006484705,0.0000595979,0.000008425166],"category_scores_gemma":[0.00034805827,0.00014722608,0.00008094248,0.0012768504,0.00011887939,0.0008299282,0.00007324585,0.00013857697,0.0000151979475],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003061893,0.00021333409,0.0073733693,0.000116364805,0.000007019561,0.00024837677,0.00019934363,0.000095074094,0.0032895443,0.0027288988,0.011642455,0.9740556],"study_design_scores_gemma":[0.0003340594,0.00010621057,0.0038887444,0.0001461146,0.000008159274,0.000010652287,0.00004786014,0.97257537,0.010874618,0.0031087259,0.00866072,0.0002387852],"about_ca_topic_score_codex":0.000003832916,"about_ca_topic_score_gemma":0.0000035276219,"teacher_disagreement_score":0.9738168,"about_ca_system_score_codex":0.0000794159,"about_ca_system_score_gemma":0.00020746027,"threshold_uncertainty_score":0.6003705},"labels":[],"label_agreement":null},{"id":"W4390956048","doi":"10.1121/10.0024345","title":"Documenting and modeling the acoustic variability of intervocalic alveolar taps in conversational Peninsular Spanish","year":2024,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Social Sciences and Humanities Research Council; Social Sciences and Humanities Research Council of Canada","keywords":"Pronunciation; Categorical variable; Speech recognition; Computer science; Speech production; Linguistics","score_opus":0.017694126137270325,"score_gpt":0.2563845217135089,"score_spread":0.23869039557623856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390956048","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07645618,0.0003058204,0.9163266,0.0065511917,0.00018354093,0.00009186822,0.0000035104124,0.000008495354,0.000072831535],"genre_scores_gemma":[0.9491075,0.00019997389,0.050087493,0.000536735,0.000051062256,8.6153625e-7,9.7840335e-8,0.000005311667,0.0000109410785],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984187,0.00034031778,0.00050870166,0.000114580005,0.00046445237,0.00015327323],"domain_scores_gemma":[0.9975476,0.0017721369,0.0002318853,0.00025185596,0.00015370372,0.000042765394],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024910616,0.00009557824,0.00023103949,0.000024751076,0.00010363217,0.000060298316,0.0007910482,0.000043548785,0.000043583645],"category_scores_gemma":[0.00055781455,0.000046661575,0.00026582927,0.00035152704,0.00042130105,0.00018615751,0.0003106943,0.00041433668,0.0000012523075],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004251493,0.0013684384,0.004032197,0.0017786961,0.0030657589,0.000031357966,0.059591815,0.29413137,0.1683893,0.0039393473,0.012239914,0.45100665],"study_design_scores_gemma":[0.00013179291,0.000044770244,0.0004600312,0.00014812456,0.0001101633,0.000057092457,0.0012809071,0.9890045,0.00053638464,0.00808572,0.00008834793,0.000052162053],"about_ca_topic_score_codex":0.000053354088,"about_ca_topic_score_gemma":5.5392684e-7,"teacher_disagreement_score":0.87265134,"about_ca_system_score_codex":0.000051732964,"about_ca_system_score_gemma":0.00011764366,"threshold_uncertainty_score":0.19028038},"labels":[],"label_agreement":null},{"id":"W4391021767","doi":"10.1109/asru57964.2023.10389758","title":"CAMSAT: Augmentation Mix and Self-Augmented Training Clustering for Self-Supervised Speaker Recognition","year":2023,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Computer science; Cluster analysis; Dependency (UML); Embedding; Representation (politics); Artificial intelligence; Variety (cybernetics); Pattern recognition (psychology); Speaker recognition; Speech recognition; Data mining; Machine learning","score_opus":0.06898587806828843,"score_gpt":0.27424666113269125,"score_spread":0.20526078306440282,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391021767","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34684643,0.000018914297,0.63976204,0.0017666549,0.0006569474,0.001005351,0.000021377793,0.0030314396,0.006890833],"genre_scores_gemma":[0.17162473,0.00013026453,0.8257941,0.0012780242,0.0001577697,0.00025951868,0.00010413906,0.00003476899,0.00061669335],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988599,0.00005519415,0.00023923093,0.0003802443,0.00018205933,0.00028338964],"domain_scores_gemma":[0.99937373,0.00022956835,0.00005664785,0.00015604991,0.00008199232,0.000101992504],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043272405,0.00013664154,0.00014383304,0.00021552945,0.00018687751,0.00021183574,0.00015506269,0.000060895247,0.00009124049],"category_scores_gemma":[0.000044467022,0.00013423078,0.000061249404,0.00040062633,0.00001001373,0.00051688106,0.00007731844,0.00004820553,0.00016370176],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014526112,0.000071835224,0.00009327844,0.00007677492,0.000072384595,0.000009276336,0.0048194937,0.000004742537,0.003223757,0.00025734425,0.0013632925,0.9899933],"study_design_scores_gemma":[0.0018754626,0.0001241767,0.0019223904,0.00005606546,0.000040116178,0.00003855483,0.0021729972,0.97872806,0.010137157,0.0016399916,0.0028881738,0.000376845],"about_ca_topic_score_codex":0.000012464505,"about_ca_topic_score_gemma":0.00003905531,"teacher_disagreement_score":0.98961645,"about_ca_system_score_codex":0.0000437079,"about_ca_system_score_gemma":0.000029609691,"threshold_uncertainty_score":0.5473772},"labels":[],"label_agreement":null},{"id":"W4391326347","doi":"10.1016/j.patrec.2024.01.024","title":"An analytic study on clustering driven self-supervised speaker verification","year":2024,"lang":"en","type":"article","venue":"Pattern Recognition Letters","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Computer science; Cluster analysis; Overfitting; Discriminative model; Artificial intelligence; Speaker verification; Noise (video); Pattern recognition (psychology); Embedding; Speaker recognition; Speech recognition; Machine learning; Artificial neural network","score_opus":0.041907874587752796,"score_gpt":0.27724486008457644,"score_spread":0.23533698549682364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391326347","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.61894804,0.000005621828,0.37613216,0.0023968162,0.0006680486,0.0004104819,0.000013732903,0.0009093421,0.00051575317],"genre_scores_gemma":[0.9865311,0.000007448594,0.008410686,0.004633552,0.00021297639,0.00010548821,0.000052814037,0.000034068864,0.000011870463],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979022,0.0002701769,0.00033378133,0.0007850084,0.00041572988,0.00029307447],"domain_scores_gemma":[0.9990199,0.00013553078,0.00005907048,0.0005837109,0.000060692913,0.00014108034],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00034312392,0.00023680387,0.00018512069,0.00044319555,0.00013171103,0.0007394057,0.00047820449,0.00005733364,0.0003006583],"category_scores_gemma":[0.000016447746,0.00023167933,0.0001169484,0.0004612499,0.000018486358,0.0008466475,0.000049834547,0.00020772926,0.002709026],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010391722,0.0005822669,0.003506466,0.000056256027,0.00014992453,0.00021635072,0.0033640754,0.000052117313,0.0076597044,0.000007828871,0.000740242,0.9836544],"study_design_scores_gemma":[0.00093403674,0.0005189439,0.04025663,0.0002772556,0.00013128483,0.00008105085,0.00069114397,0.9515277,0.0037816442,0.00013300973,0.0007715929,0.00089568156],"about_ca_topic_score_codex":0.000026322201,"about_ca_topic_score_gemma":0.000020176143,"teacher_disagreement_score":0.9827587,"about_ca_system_score_codex":0.0001158172,"about_ca_system_score_gemma":0.00002130933,"threshold_uncertainty_score":0.9980675},"labels":[],"label_agreement":null},{"id":"W4391331185","doi":"10.1109/smc53992.2023.10394252","title":"Assessing the Vulnerability of Self-Supervised Speech Representations for Keyword Spotting Under White-Box Adversarial Attacks","year":2023,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Keyword spotting; Computer science; Adversarial system; Robustness (evolution); Speech recognition; Transferability; Artificial intelligence; Task (project management); White noise; Machine learning; Natural language processing; Telecommunications","score_opus":0.07714874044791163,"score_gpt":0.36170200470024877,"score_spread":0.2845532642523371,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391331185","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23716237,0.000004536926,0.732798,0.007257054,0.0007252382,0.0006555831,0.00000820744,0.0007036591,0.020685371],"genre_scores_gemma":[0.6171949,0.0000040503646,0.381182,0.00039947213,0.00015930837,0.000059442158,0.000011128181,0.000014062796,0.0009756598],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984095,0.00020414894,0.00038170957,0.00039931625,0.00033212264,0.00027319812],"domain_scores_gemma":[0.9971188,0.001833419,0.00011587778,0.00063009915,0.00024103996,0.000060808117],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014176625,0.000119112265,0.00018226153,0.00012330626,0.0003567894,0.00028762594,0.0005990006,0.00006731879,0.00020112087],"category_scores_gemma":[0.0005301921,0.000086826636,0.00017472463,0.00091166823,0.0000536509,0.00061592035,0.00018648851,0.000107691434,0.000050779097],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005358967,0.0007423683,0.0343288,0.00025357434,0.00042715663,0.000023071767,0.0077665304,0.0018899917,0.011653778,0.04849424,0.024270985,0.8700959],"study_design_scores_gemma":[0.0019024513,0.00007103448,0.06148484,0.000052849824,0.000083629915,0.00002205755,0.00787317,0.8538475,0.047071688,0.025374368,0.0016980062,0.00051840197],"about_ca_topic_score_codex":0.00004336038,"about_ca_topic_score_gemma":0.00002126985,"teacher_disagreement_score":0.8695775,"about_ca_system_score_codex":0.000037285216,"about_ca_system_score_gemma":0.00011370845,"threshold_uncertainty_score":0.35406876},"labels":[],"label_agreement":null},{"id":"W4391683008","doi":"10.3991/ijim.v18i03.43013","title":"Convolutional Neural Network Architectures for Gender, Emotional Detection from Speech and Speaker Diarization","year":2024,"lang":"en","type":"article","venue":"International Journal of Interactive Mobile Technologies (iJIM)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Speaker diarisation; Convolutional neural network; Speech recognition; Computer science; Speaker recognition; Artificial intelligence","score_opus":0.018665437822444866,"score_gpt":0.2789606270943671,"score_spread":0.26029518927192224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391683008","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31214717,0.0013764445,0.6799152,0.0017367684,0.0039618667,0.00025737373,0.00007969529,0.0003316934,0.00019381702],"genre_scores_gemma":[0.954808,0.000117364245,0.044183087,0.00014125615,0.0006415805,0.00004555794,0.000014296108,0.000015153372,0.000033680833],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984162,0.000063784166,0.0004885249,0.00034852562,0.00048526563,0.00019771094],"domain_scores_gemma":[0.99779844,0.0010699959,0.00028886634,0.0001447925,0.0006518473,0.00004607392],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028840927,0.00019308837,0.0002157188,0.0005300198,0.00009127933,0.00040330717,0.000741266,0.00013731256,0.00007403918],"category_scores_gemma":[0.0005099219,0.00016236794,0.00020745928,0.00022056224,0.00013147038,0.00050029287,0.00023166684,0.0004217828,0.000012364722],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020092446,0.00009500082,0.00055433414,0.000012856123,0.00058360264,0.00012218997,0.0002625736,0.0017507026,0.008062587,0.0043714135,0.0010957392,0.9828881],"study_design_scores_gemma":[0.0015363531,0.0007725952,0.011892915,0.00059040333,0.00010298096,0.0031727368,0.0010390299,0.534498,0.118886866,0.30843043,0.018387867,0.00068983325],"about_ca_topic_score_codex":0.0000117481295,"about_ca_topic_score_gemma":0.000012883511,"teacher_disagreement_score":0.98219824,"about_ca_system_score_codex":0.00022076428,"about_ca_system_score_gemma":0.00007455842,"threshold_uncertainty_score":0.66211724},"labels":[],"label_agreement":null},{"id":"W4391831786","doi":"10.4995/eurocall2023.2023.17007","title":"Evaluating the effectiveness of Microsoft Transcribe for automating the assessment of pronunciation in language proficiency tests","year":2023,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Concordia University","funders":"Université du Québec à Montréal","keywords":"Computer science; Pronunciation; Natural language processing; Test (biology); Automation; Reliability (semiconductor); Artificial intelligence; Linguistics; Engineering","score_opus":0.0713846181357021,"score_gpt":0.4181764047821827,"score_spread":0.3467917866464806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391831786","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8749464,0.000012427844,0.1225773,0.00034294467,0.000059490525,0.0011009914,0.0000036536826,0.00006773073,0.00088906294],"genre_scores_gemma":[0.96518534,6.29434e-7,0.0345239,0.00002435358,0.0000060000452,0.00022692652,0.0000017616763,0.0000037098573,0.000027353211],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988719,0.00037319105,0.00023677485,0.00014039397,0.00025339326,0.00012433631],"domain_scores_gemma":[0.9966709,0.0029097747,0.00010911461,0.00019521457,0.00010692919,0.000008050678],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005536079,0.000055839264,0.00010977498,0.000069728485,0.000071090726,0.000025237254,0.0003392533,0.000021277026,0.000004688017],"category_scores_gemma":[0.0006650136,0.000029957666,0.000055274413,0.0006186112,0.000025412177,0.00009668172,0.000036039328,0.000044688026,0.0000013129677],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000975753,0.000103783976,0.0077490057,0.00035637672,0.00001386422,4.643322e-7,0.0040235207,0.00067507155,0.71290386,0.009993286,0.000010500586,0.2641605],"study_design_scores_gemma":[0.00026170653,0.000105945444,0.29554823,0.00009863186,0.0000052953883,8.136336e-7,0.0005023252,0.5501445,0.15226756,0.0010200567,0.0000011007315,0.000043850767],"about_ca_topic_score_codex":0.000036878722,"about_ca_topic_score_gemma":0.000023540773,"teacher_disagreement_score":0.5606363,"about_ca_system_score_codex":0.000027089782,"about_ca_system_score_gemma":0.00009755242,"threshold_uncertainty_score":0.19187056},"labels":[],"label_agreement":null},{"id":"W4391896879","doi":"10.2196/56245","title":"Investigation of Deepfake Voice Detection Using Speech Pause Patterns: Algorithm Development and Validation","year":2024,"lang":"en","type":"article","venue":"JMIR Biomedical Engineering","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Glycemic Index Laboratories","funders":"","keywords":"Preprint; Computer science; Speech recognition; World Wide Web","score_opus":0.024097442042768515,"score_gpt":0.2441410869546239,"score_spread":0.22004364491185538,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391896879","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39763436,0.000040971874,0.6018562,0.00003872496,0.0002336244,0.00006438095,0.0000013386194,0.00012740232,0.0000030359565],"genre_scores_gemma":[0.6648999,0.00000980112,0.33493072,0.000019750087,0.00009618096,0.000018830196,0.000007272789,0.000011081028,0.0000064599376],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99915487,0.000016830087,0.0002290659,0.0002111744,0.00026278928,0.00012528771],"domain_scores_gemma":[0.9996661,0.000079995574,0.000030491618,0.00009244993,0.0000308872,0.0001000586],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024790497,0.00009383222,0.00009418025,0.00028588533,0.00003103048,0.000086043314,0.00009750642,0.0000787005,0.000007017633],"category_scores_gemma":[0.000040351,0.00008962306,0.000022228,0.0004163375,0.000019434927,0.0002814355,0.000055570956,0.00008946525,0.000008230233],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.4361394e-7,0.0000057948346,0.000041086943,0.00015750992,0.000017786195,0.000015243818,0.00034895854,0.000010524182,0.06652493,0.000039683182,0.000003241573,0.9328348],"study_design_scores_gemma":[0.000075244454,0.000017444538,0.0016006543,0.00023012856,0.000005630854,0.000055910983,0.000013057654,0.666294,0.3302898,0.00004856998,0.001260624,0.000108921544],"about_ca_topic_score_codex":0.000011557172,"about_ca_topic_score_gemma":0.0000011404584,"teacher_disagreement_score":0.93272585,"about_ca_system_score_codex":0.00005858283,"about_ca_system_score_gemma":0.000038743863,"threshold_uncertainty_score":0.36547226},"labels":[],"label_agreement":null},{"id":"W4392411857","doi":"10.1109/ijcb57857.2023.10449225","title":"Benchmark Dataset Dynamics, Bias and Privacy Challenges in Voice Biometrics Research","year":2023,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; University of Toronto","funders":"","keywords":"Biometrics; Computer science; Benchmark (surveying); Information privacy; Dynamics (music); Internet privacy; Data science; Speech recognition; Data mining; Artificial intelligence; Psychology","score_opus":0.42622501651506584,"score_gpt":0.4011914368871123,"score_spread":0.02503357962795355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392411857","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.54391384,0.0077281175,0.033712737,0.22975914,0.0022472155,0.0026549646,0.00233576,0.0027888662,0.17485936],"genre_scores_gemma":[0.8310353,0.04199938,0.12099186,0.00094677374,0.00019578931,0.00013273013,0.0015347974,0.000057402525,0.0031059664],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984666,0.0002005298,0.00016410436,0.000419736,0.0004120725,0.00033695096],"domain_scores_gemma":[0.9978998,0.0014029839,0.000021428155,0.0005036847,0.00006972911,0.00010242625],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026832756,0.000077574194,0.00011242758,0.001999792,0.00008352401,0.00017012804,0.0006761656,0.000061799,0.000049694754],"category_scores_gemma":[0.0011960567,0.0000684645,0.000014909821,0.004212445,0.00005825453,0.00032459287,0.0007785571,0.00015311122,0.0005919468],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000021741298,0.00006444926,0.0014280928,0.000031214757,0.0000060035713,0.00007135445,0.00028217756,3.2534558e-7,0.00003254599,0.0236265,0.02546168,0.9489935],"study_design_scores_gemma":[0.0010664148,0.00025468122,0.15618442,0.000112000045,0.0000047665144,0.0000601599,0.0027593772,0.44599187,0.0017731468,0.039967615,0.35101655,0.000808975],"about_ca_topic_score_codex":0.000118219155,"about_ca_topic_score_gemma":0.00043630353,"teacher_disagreement_score":0.9481845,"about_ca_system_score_codex":0.00004549381,"about_ca_system_score_gemma":0.000033581833,"threshold_uncertainty_score":0.7608476},"labels":[],"label_agreement":null},{"id":"W4392903183","doi":"10.1109/icassp48485.2024.10446486","title":"End-To-End Real Time Tracking of Children’s Reading with Pointer Network","year":2024,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"National Science Foundation","keywords":"Computer science; Pointer (user interface); Ground truth; Speech recognition; BitTorrent tracker; TIMIT; Artificial neural network; End-to-end principle; Training set; Artificial intelligence; Reading (process); Eye tracking; Hidden Markov model","score_opus":0.011905208322205181,"score_gpt":0.2316135383811359,"score_spread":0.21970833005893073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392903183","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15693869,0.0000767088,0.4387512,0.0027982136,0.0004917542,0.0003617263,0.00000941966,0.0011545754,0.39941773],"genre_scores_gemma":[0.86189836,0.000009318174,0.13426396,0.00041945008,0.00018755581,0.0000065310314,0.000002831676,0.000016442744,0.0031955277],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990825,0.000033652424,0.00016989798,0.000299059,0.00020190518,0.00021295606],"domain_scores_gemma":[0.9994681,0.00014861576,0.000025681853,0.00023929999,0.00003728059,0.0000810257],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002549086,0.00010036385,0.00014198132,0.00012117001,0.000040685994,0.00018027259,0.00029761862,0.00003204027,0.0010241242],"category_scores_gemma":[0.000010158403,0.00007266231,0.000060471208,0.00040574642,0.00002030462,0.00027500742,0.00007678476,0.00007431126,0.00043311427],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029770152,0.00006029876,0.0019514887,0.000027256587,0.00020017807,0.00009628308,0.0012277085,0.000072974755,0.0036281713,0.046455007,0.022554211,0.92369664],"study_design_scores_gemma":[0.0024092596,0.002110129,0.12849094,0.0054908427,0.00031799925,0.0026218116,0.00030732405,0.32109478,0.49529096,0.0103093125,0.027722387,0.0038342574],"about_ca_topic_score_codex":0.00006023522,"about_ca_topic_score_gemma":0.000019469033,"teacher_disagreement_score":0.9198624,"about_ca_system_score_codex":0.000016771923,"about_ca_system_score_gemma":0.000032749005,"threshold_uncertainty_score":0.9998891},"labels":[],"label_agreement":null},{"id":"W4392904518","doi":"10.1109/icassp48485.2024.10447101","title":"Self-Supervised Speaker Verification Employing A Novel Clustering Algorithm","year":2024,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Cluster analysis; Computer science; Discriminative model; Artificial intelligence; Pattern recognition (psychology); Embedding; Correlation clustering; Speaker recognition; Representation (politics); Canopy clustering algorithm; Dependency (UML); Machine learning; Data mining","score_opus":0.03312310008655405,"score_gpt":0.25627538350246315,"score_spread":0.2231522834159091,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392904518","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006391062,0.00005880227,0.9758716,0.00084725866,0.00054681563,0.00010163891,0.0000018212821,0.0013226925,0.020610254],"genre_scores_gemma":[0.02323751,0.000021977226,0.97547543,0.00039360058,0.00008697342,0.000018690755,0.0000023112689,0.000012706747,0.0007507706],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991224,0.00001830278,0.00015827069,0.00034257106,0.0001868404,0.00017164009],"domain_scores_gemma":[0.99952316,0.000072321614,0.000013420526,0.00028346275,0.00004056282,0.00006705676],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001979739,0.00009760844,0.00008231874,0.0001282843,0.00007157334,0.00048936164,0.00030657067,0.000042999545,0.00015277673],"category_scores_gemma":[0.0000134057955,0.00008583924,0.00006448742,0.00036798874,0.000008150452,0.00052901125,0.00009504494,0.00007465145,0.0007931457],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.3881315e-7,0.000035844714,0.000007901559,0.000026377,0.000021668902,0.000011449841,0.0004917068,0.0000018977989,0.0022886512,0.004248115,0.00043198367,0.99243397],"study_design_scores_gemma":[0.00009156312,0.000010110932,0.00012521016,0.00002941834,0.000005742324,0.00005869255,0.00003996636,0.9736156,0.0038181113,0.00020076195,0.021869158,0.00013566778],"about_ca_topic_score_codex":0.00001806095,"about_ca_topic_score_gemma":0.000005372987,"teacher_disagreement_score":0.9922983,"about_ca_system_score_codex":0.000045023728,"about_ca_system_score_gemma":0.0000393406,"threshold_uncertainty_score":0.99998486},"labels":[],"label_agreement":null},{"id":"W4392908955","doi":"10.1109/icassp48485.2024.10446327","title":"Unsupervised Speech Recognition with N-skipgram and Positional Unigram Matching","year":2024,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada); Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Artificial intelligence; Speech recognition; Pattern recognition (psychology); Matching (statistics); Mathematics","score_opus":0.016749356415947825,"score_gpt":0.2276625302010225,"score_spread":0.21091317378507468,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392908955","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33529276,0.00024568857,0.59885204,0.0059257904,0.00030519965,0.00028950922,0.000019092908,0.0015121,0.057557847],"genre_scores_gemma":[0.47637275,0.000067354245,0.521383,0.0011617397,0.00009215768,0.000024483928,0.000028804558,0.000017750974,0.0008519549],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990743,0.000043282525,0.00012515877,0.0003523861,0.00023593348,0.0001689547],"domain_scores_gemma":[0.99952054,0.0001567985,0.000013409061,0.00015027539,0.000061884995,0.00009711693],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001851491,0.000119457065,0.00009606709,0.00018453068,0.00010261414,0.0006277385,0.00015342103,0.000048770245,0.00033827554],"category_scores_gemma":[0.000007860855,0.000089995665,0.00003663245,0.00038394486,0.000034529585,0.00069606636,0.00005057216,0.00011424395,0.0002851228],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000062986796,0.000033871635,0.00003544115,0.000028970777,0.000030300502,0.00012759928,0.00017884852,5.0889787e-7,0.0008126727,0.0163399,0.000532418,0.98187315],"study_design_scores_gemma":[0.002701525,0.0012659604,0.014133011,0.0021305524,0.00020516818,0.010490575,0.0014845447,0.2339843,0.10736946,0.59559107,0.027396506,0.0032473435],"about_ca_topic_score_codex":0.00004476963,"about_ca_topic_score_gemma":0.000030248964,"teacher_disagreement_score":0.97862583,"about_ca_system_score_codex":0.00002063562,"about_ca_system_score_gemma":0.000046716777,"threshold_uncertainty_score":0.6053297},"labels":[],"label_agreement":null},{"id":"W4393043884","doi":"10.3390/s24061996","title":"Self-Supervised Open-Set Speaker Recognition with Laguerre–Voronoi Descriptors","year":2024,"lang":"en","type":"article","venue":"Sensors","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Speaker recognition; Pattern recognition (psychology); Speech recognition; Artificial intelligence; Open set; Feature extraction; Cluster analysis; Set (abstract data type); Feature (linguistics); Artificial neural network; Biometrics; Speaker diarisation; Voronoi diagram; Neural gas; Time delay neural network; Mathematics","score_opus":0.046830119155900594,"score_gpt":0.2578130349466004,"score_spread":0.2109829157906998,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393043884","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7809768,0.00037941057,0.036132265,0.0040671313,0.0027123946,0.001327943,0.00006919979,0.0033647039,0.17097017],"genre_scores_gemma":[0.6044796,0.00017023497,0.38865912,0.0015756342,0.00040284323,0.00009587729,0.000063875166,0.0001016876,0.004451131],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99842715,0.0001318911,0.00021760285,0.00059679087,0.00029758824,0.00032898987],"domain_scores_gemma":[0.9991524,0.00012772107,0.00003698224,0.00043099863,0.00009329183,0.00015860685],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00031563512,0.00021030122,0.00019423393,0.00018731314,0.00012867957,0.0010051392,0.0006504261,0.00008305131,0.00051178434],"category_scores_gemma":[0.000032633037,0.00016778203,0.000078089324,0.000606151,0.00003897289,0.00081453857,0.00015415139,0.00017157363,0.0025100186],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055704197,0.00021601982,0.00022834864,0.00015132761,0.00026620374,0.0008175413,0.0044010747,0.00000998485,0.00060673716,0.007217213,0.015712857,0.970317],"study_design_scores_gemma":[0.00235223,0.0006827186,0.0017660912,0.0009634,0.00022221555,0.0011781878,0.0020107762,0.5166388,0.052479416,0.0079101445,0.41129228,0.0025037436],"about_ca_topic_score_codex":0.00007946936,"about_ca_topic_score_gemma":0.00007121162,"teacher_disagreement_score":0.96781325,"about_ca_system_score_codex":0.00007397165,"about_ca_system_score_gemma":0.0001006911,"threshold_uncertainty_score":0.99826664},"labels":[],"label_agreement":null},{"id":"W4393068745","doi":"10.55041/ijsrem29567","title":"SPEECH RECOGNITION SYSTEM","year":2024,"lang":"en","type":"article","venue":"INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Robustness (evolution); Software deployment; Implementation; Adaptability; Field (mathematics); Data science; Artificial intelligence; Human–computer interaction; Software engineering","score_opus":0.06810367408651197,"score_gpt":0.3209838351931863,"score_spread":0.25288016110667433,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393068745","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5154464,0.0036755172,0.45666593,0.0038830221,0.010270074,0.00053577044,0.000011062242,0.0002255625,0.009286658],"genre_scores_gemma":[0.97448796,0.00016219806,0.024944177,0.000005508324,0.00008365358,0.000007779609,0.0000010036471,0.000005417651,0.00030229817],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985453,0.000061847924,0.0002944642,0.0002084921,0.0006926486,0.00019723513],"domain_scores_gemma":[0.9994156,0.00019764407,0.000023813684,0.00009400069,0.00019069976,0.00007827995],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003975761,0.00006258817,0.00009255459,0.0019437566,0.00005996602,0.00094289315,0.00030380263,0.00002230435,0.0000126317145],"category_scores_gemma":[0.000036193163,0.00005293692,0.00005661686,0.0008888404,0.000044191165,0.00054561585,0.00011512585,0.00023781674,0.000055628432],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010143076,0.000044554658,0.000010780492,0.00080039457,0.000059521684,0.0014753132,0.00012531616,0.0000827815,0.0008725364,0.025516458,0.0013209812,0.9696812],"study_design_scores_gemma":[0.0015544414,0.00034980202,0.0038581556,0.033835106,0.00003957019,0.005364117,0.0015624525,0.83708525,0.01209846,0.013028602,0.0905676,0.00065641187],"about_ca_topic_score_codex":0.000002580782,"about_ca_topic_score_gemma":7.447947e-7,"teacher_disagreement_score":0.96902484,"about_ca_system_score_codex":0.00009970603,"about_ca_system_score_gemma":0.000024141082,"threshold_uncertainty_score":0.90923405},"labels":[],"label_agreement":null},{"id":"W4393147067","doi":"10.1609/aaai.v38i16.29747","title":"UniCATS: A Unified Context-Aware Text-to-Speech Framework with Contextual VQ-Diffusion and Vocoding","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Context (archaeology); Computer science; Linguistics; Psychology; Speech recognition; Natural language processing; Biology; Paleontology","score_opus":0.06781807521491127,"score_gpt":0.29374818100819655,"score_spread":0.22593010579328526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393147067","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.56457853,0.00030174135,0.3666732,0.042894833,0.0011501852,0.0022027267,0.000033807697,0.00097585784,0.021189112],"genre_scores_gemma":[0.98876953,0.00007832235,0.009905331,0.0007757467,0.00006332347,0.000045528257,3.9519324e-7,0.000021713959,0.00034009427],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99777085,0.000028579598,0.0004893464,0.00076897285,0.00055871095,0.00038356005],"domain_scores_gemma":[0.9982868,0.00044861904,0.00016521278,0.0003442533,0.00055647077,0.00019865985],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052691804,0.0003046528,0.00033956423,0.00027221334,0.00025319934,0.00081683556,0.0014443261,0.00014867647,0.00011734932],"category_scores_gemma":[0.00053173455,0.00020610754,0.000093626055,0.0011215743,0.00032227533,0.00044772582,0.0004574464,0.00047378129,0.00016890862],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007033168,0.000051252802,0.00006538776,0.00004210929,0.000019836549,0.0000039388715,0.001368468,7.8731733e-7,0.0061658532,0.59944755,0.00011049182,0.392654],"study_design_scores_gemma":[0.00009685914,0.0007895549,0.00023995215,0.004976886,0.00005810654,0.00010354777,0.0058441935,0.09282404,0.6740576,0.21744195,0.0027066793,0.0008606582],"about_ca_topic_score_codex":0.000038150356,"about_ca_topic_score_gemma":0.000035053363,"teacher_disagreement_score":0.66789174,"about_ca_system_score_codex":0.000053907857,"about_ca_system_score_gemma":0.00012584346,"threshold_uncertainty_score":0.8404821},"labels":[],"label_agreement":null},{"id":"W4393370699","doi":"","title":"Automatic Speech Recognition : from hybrid to end-to-end approach","year":2021,"lang":"fr","type":"preprint","venue":"theses.fr (ABES)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"End-to-end principle; Speech recognition; Computer science; Artificial intelligence","score_opus":0.07805801844596885,"score_gpt":0.2708289829992054,"score_spread":0.19277096455323653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393370699","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5331303,0.0005357404,0.28334275,0.005440653,0.005528098,0.0027024858,0.0011413334,0.0011347991,0.16704386],"genre_scores_gemma":[0.41732168,0.0002047091,0.5761375,0.0029416797,0.0011512544,0.00052501797,0.00070373656,0.00014524032,0.0008691943],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99022824,0.0015099716,0.0016068338,0.0032454915,0.001892915,0.0015165521],"domain_scores_gemma":[0.9925305,0.001575192,0.0005698747,0.0031770326,0.000804799,0.0013425485],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["metaepi_narrow","insufficient_payload"],"category_scores_codex":[0.0019326163,0.0013347398,0.0017956621,0.0007507523,0.00042197492,0.0022643863,0.0031868818,0.00063855137,0.01955368],"category_scores_gemma":[0.0016337361,0.0014434884,0.00084923947,0.0013874194,0.00020120126,0.0008638392,0.0032176385,0.0014230494,0.018107217],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027438547,0.0008551733,0.00006031709,0.00023720063,0.00039897035,0.00047813065,0.007930951,0.0000622497,0.0017198729,0.0012360297,0.0010802448,0.9859134],"study_design_scores_gemma":[0.0030348357,0.0007655987,0.013260212,0.012017769,0.0019518125,0.002377504,0.018204672,0.31933147,0.4036096,0.056367654,0.15801023,0.011068638],"about_ca_topic_score_codex":0.00839023,"about_ca_topic_score_gemma":0.00040872078,"teacher_disagreement_score":0.97484475,"about_ca_system_score_codex":0.0006258569,"about_ca_system_score_gemma":0.000661405,"threshold_uncertainty_score":0.9999404},"labels":[],"label_agreement":null},{"id":"W4393401667","doi":"10.5281/zenodo.1219621","title":"A Canadian French Emotional Speech Dataset","year":2018,"lang":"en","type":"dataset","venue":"Figshare","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Speech recognition; Computer science; Psychology","score_opus":0.04705013687903825,"score_gpt":0.26654014039925505,"score_spread":0.2194900035202168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393401667","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[5.0877954e-8,0.000032606924,0.000003074456,0.00026052314,0.00034547425,0.00016751992,0.9983752,0.000059873197,0.00075570546],"genre_scores_gemma":[1.3706803e-7,0.000004079777,0.0021194532,0.0021210387,0.00057435106,0.00008017488,0.9948676,0.000011184298,0.00022196212],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981192,0.00006572697,0.00023308072,0.00065420795,0.00046182112,0.0004659861],"domain_scores_gemma":[0.99771917,0.00012266259,0.0001318163,0.001356632,0.00018844493,0.0004813005],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000080189464,0.00029199806,0.00023662919,0.0004110881,0.00019249353,0.00044377256,0.0024902432,0.00036087795,0.71712065],"category_scores_gemma":[0.0008902342,0.00029438132,0.00009465363,0.00034894087,0.0000087500775,0.00027625237,0.00041302183,0.0003207838,0.121914715],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.6364183e-7,0.000014780316,1.258755e-7,0.000046901452,0.000016375216,0.0002050725,0.0000018194746,2.0550765e-8,3.9504833e-8,9.274492e-7,0.99604124,0.0036725374],"study_design_scores_gemma":[0.00006489881,0.000020059895,0.000051519037,0.00067651976,0.000006529191,0.00012588176,4.746711e-7,0.000093541326,0.00001709544,0.00005887098,0.9985252,0.00035939197],"about_ca_topic_score_codex":0.03082012,"about_ca_topic_score_gemma":0.21632254,"teacher_disagreement_score":0.59520596,"about_ca_system_score_codex":0.00019604289,"about_ca_system_score_gemma":0.001147852,"threshold_uncertainty_score":0.9999508},"labels":[],"label_agreement":null},{"id":"W4393475061","doi":"10.5281/zenodo.1478765","title":"A Canadian French Emotional Speech Dataset","year":2018,"lang":"en","type":"dataset","venue":"Figshare","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Speech recognition; Computer science; Psychology; Natural language processing","score_opus":0.04705013687903825,"score_gpt":0.26654014039925505,"score_spread":0.2194900035202168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393475061","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[5.0877954e-8,0.000032606924,0.000003074456,0.00026052314,0.00034547425,0.00016751992,0.9983752,0.000059873197,0.00075570546],"genre_scores_gemma":[1.3706803e-7,0.000004079777,0.0021194532,0.0021210387,0.00057435106,0.00008017488,0.9948676,0.000011184298,0.00022196212],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981192,0.00006572697,0.00023308072,0.00065420795,0.00046182112,0.0004659861],"domain_scores_gemma":[0.99771917,0.00012266259,0.0001318163,0.001356632,0.00018844493,0.0004813005],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000080189464,0.00029199806,0.00023662919,0.0004110881,0.00019249353,0.00044377256,0.0024902432,0.00036087795,0.71712065],"category_scores_gemma":[0.0008902342,0.00029438132,0.00009465363,0.00034894087,0.0000087500775,0.00027625237,0.00041302183,0.0003207838,0.121914715],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.6364183e-7,0.000014780316,1.258755e-7,0.000046901452,0.000016375216,0.0002050725,0.0000018194746,2.0550765e-8,3.9504833e-8,9.274492e-7,0.99604124,0.0036725374],"study_design_scores_gemma":[0.00006489881,0.000020059895,0.000051519037,0.00067651976,0.000006529191,0.00012588176,4.746711e-7,0.000093541326,0.00001709544,0.00005887098,0.9985252,0.00035939197],"about_ca_topic_score_codex":0.03082012,"about_ca_topic_score_gemma":0.21632254,"teacher_disagreement_score":0.59520596,"about_ca_system_score_codex":0.00019604289,"about_ca_system_score_gemma":0.001147852,"threshold_uncertainty_score":0.9999508},"labels":[],"label_agreement":null},{"id":"W4393644288","doi":"10.5281/zenodo.7803315","title":"SASS-E: The Steelpan Audio Sample Set for Evaluation","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Sass; Sample (material); Set (abstract data type); Computer science; World Wide Web; Chemistry; Programming language; Chromatography","score_opus":0.11111893059939838,"score_gpt":0.31064814488988435,"score_spread":0.19952921429048598,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393644288","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000119930755,0.00004399033,0.02601029,0.002108499,0.000596269,0.0015574736,0.96624047,0.0009544445,0.0024765648],"genre_scores_gemma":[0.00004568406,0.00015456822,0.001297113,0.00040240688,0.00035102412,0.000001193999,0.9964457,0.0007676618,0.0005346032],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9965593,0.0008472841,0.00037737767,0.00073516957,0.0010046862,0.00047617816],"domain_scores_gemma":[0.99658287,0.0004406143,0.00025785618,0.0013692162,0.0011942891,0.00015516544],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.003244682,0.00024826522,0.00023868463,0.00037235767,0.002882003,0.002191245,0.0037827676,0.00016274457,0.005283501],"category_scores_gemma":[0.004841911,0.00021314863,0.00014453699,0.0009391997,0.00011794014,0.0002994951,0.0018471121,0.00036840682,0.03158086],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011546895,0.000037194077,2.3114877e-8,0.000050992938,0.00005133639,0.0000025113422,0.000118186384,0.000009607574,0.000018019593,0.0004948387,0.86485714,0.13434863],"study_design_scores_gemma":[0.00044648346,0.00013283317,0.000033759003,0.00004160707,0.00005547394,0.000036917627,0.00011184262,0.0037040599,0.00004606996,0.00093089865,0.9942071,0.00025299258],"about_ca_topic_score_codex":0.00007743031,"about_ca_topic_score_gemma":0.0000063716166,"teacher_disagreement_score":0.13409564,"about_ca_system_score_codex":0.00024209332,"about_ca_system_score_gemma":0.000023973578,"threshold_uncertainty_score":0.99884456},"labels":[],"label_agreement":null},{"id":"W4393657923","doi":"10.1109/o-cocosda60357.2023.10482992","title":"Fine-tuning the Wav2Vec2 Model for Automatic Speech Emotion Recognition System","year":2023,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Speech recognition; Emotion recognition; Artificial intelligence","score_opus":0.08142040918939211,"score_gpt":0.2696513453232329,"score_spread":0.18823093613384081,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393657923","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032465935,0.0000038956523,0.95569754,0.00214282,0.00035325132,0.00045831103,0.00000863409,0.0017352132,0.0071343887],"genre_scores_gemma":[0.6435912,0.000006315266,0.35070065,0.00045621037,0.00015085533,0.00027718022,0.000041764066,0.00002765857,0.00474812],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989339,0.00006731973,0.00024431333,0.00026725282,0.00023762406,0.00024956753],"domain_scores_gemma":[0.9990361,0.0003647577,0.000077172466,0.00034282717,0.0001270044,0.000052188203],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00080487266,0.000110075765,0.00012658094,0.00015380868,0.0002751593,0.00019914439,0.00040688828,0.00005866421,0.000035531313],"category_scores_gemma":[0.00014274921,0.00007584922,0.000106697364,0.0005230738,0.000015297506,0.00031317785,0.000078183635,0.000062799714,0.00089530105],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000017384884,0.000014233376,0.0000049859545,0.00007587328,0.000014436825,0.000003824431,0.0003440059,0.00015089507,0.00037151264,0.0055379155,0.006502601,0.986978],"study_design_scores_gemma":[0.00017162382,0.000016581382,0.000087549364,0.00007063467,0.00001103377,0.000026398733,0.00027390264,0.98893434,0.0033885746,0.00678907,0.000112016656,0.000118248405],"about_ca_topic_score_codex":0.000008149331,"about_ca_topic_score_gemma":0.00001596144,"teacher_disagreement_score":0.9887835,"about_ca_system_score_codex":0.00004980559,"about_ca_system_score_gemma":0.00003745115,"threshold_uncertainty_score":0.99988264},"labels":[],"label_agreement":null},{"id":"W4393770136","doi":"10.5281/zenodo.7356907","title":"LJ Speech - Aligned IPA transcriptions","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Speech recognition; Computer science; Natural language processing; Linguistics; Philosophy","score_opus":0.06039329554808336,"score_gpt":0.26344515785158457,"score_spread":0.2030518623035012,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393770136","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000012770191,0.000042376854,0.011175537,0.0016068144,0.0006795821,0.0005469966,0.9665603,0.002628105,0.016747523],"genre_scores_gemma":[0.000033603927,0.00043571644,0.0018056768,0.00041163867,0.00027846446,1.6228203e-7,0.9938699,0.0011098498,0.0020550003],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968689,0.00052137056,0.00041972534,0.0008528084,0.0007713299,0.00056586525],"domain_scores_gemma":[0.9975469,0.000069241534,0.00016520284,0.0013603931,0.0005533311,0.00030490584],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00089840364,0.0002988989,0.00030225934,0.000750556,0.0022296922,0.0022148897,0.0040804753,0.00022582112,0.01237241],"category_scores_gemma":[0.0007390332,0.0003247648,0.00017073791,0.0014071605,0.00013754788,0.00041860016,0.0015193609,0.00039632074,0.18485463],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000070231144,0.000103112856,1.0950155e-8,0.000059232047,0.00005088589,0.00008460433,0.000088854045,9.856858e-7,0.00015854502,0.0005149704,0.9217545,0.07717728],"study_design_scores_gemma":[0.00027388733,0.00011191021,0.000017679484,0.00006250406,0.000030183126,0.00020584284,0.000052019383,0.00019348056,0.00017373795,0.00030974747,0.99821526,0.0003537254],"about_ca_topic_score_codex":0.00008601343,"about_ca_topic_score_gemma":0.000003877317,"teacher_disagreement_score":0.1724822,"about_ca_system_score_codex":0.00016023738,"about_ca_system_score_gemma":0.00001188486,"threshold_uncertainty_score":0.9999204},"labels":[],"label_agreement":null},{"id":"W4393812211","doi":"10.5281/zenodo.7356908","title":"LJ Speech - Aligned IPA transcriptions","year":2022,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Speech recognition; Computer science; Linguistics; Philosophy","score_opus":0.04805114250293462,"score_gpt":0.2514240244594909,"score_spread":0.20337288195655628,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393812211","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000131308325,0.000080511934,0.008398917,0.0013235593,0.0005662311,0.0005514206,0.9602217,0.0013298044,0.027514711],"genre_scores_gemma":[0.000051244475,0.0003401599,0.0016351995,0.0006307131,0.0001661492,2.4051084e-7,0.99511945,0.0008173586,0.0012394678],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9965366,0.0007815875,0.00040939116,0.0008561703,0.00089545135,0.000520761],"domain_scores_gemma":[0.9976666,0.000054375643,0.0001861592,0.0014111879,0.00040106676,0.00028061928],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00092859607,0.00029073088,0.00029236721,0.0006697934,0.0034912576,0.0018934945,0.0046691988,0.0001530378,0.38049904],"category_scores_gemma":[0.00048127852,0.00032933083,0.00017527539,0.0011453273,0.00012407127,0.0004257024,0.0022041677,0.00051345874,0.01832971],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010177375,0.00017175057,1.2504606e-8,0.000044189874,0.000047379464,0.00007869761,0.00012504487,0.0000015937193,0.0001390725,0.00068338076,0.91175824,0.08694046],"study_design_scores_gemma":[0.00029761627,0.00016562383,0.0000072375256,0.000021388376,0.000031458414,0.00038574458,0.00007719854,0.00010710355,0.00013138431,0.00020708522,0.99820703,0.00036111183],"about_ca_topic_score_codex":0.000054632957,"about_ca_topic_score_gemma":0.0000015643956,"teacher_disagreement_score":0.36216933,"about_ca_system_score_codex":0.0002466582,"about_ca_system_score_gemma":0.000014130284,"threshold_uncertainty_score":0.9999159},"labels":[],"label_agreement":null},{"id":"W4393818778","doi":"10.5281/zenodo.1219620","title":"A Canadian French Emotional Speech Dataset","year":2018,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Natural language processing; Speech recognition; Psychology; Computer science; Linguistics; Philosophy","score_opus":0.039420087785468606,"score_gpt":0.250193715978695,"score_spread":0.2107736281932264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393818778","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000008633677,0.000020813539,0.001540734,0.0009893887,0.00037888114,0.00030222378,0.98393774,0.00037035017,0.012451217],"genre_scores_gemma":[0.000024369596,0.0000750843,0.0024682807,0.00080810866,0.0004078525,5.1386802e-8,0.99537605,0.00046487167,0.00037530853],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99706405,0.00042000887,0.00033725917,0.0008532874,0.0007042855,0.0006210966],"domain_scores_gemma":[0.99697065,0.000039225855,0.0001600614,0.0015279546,0.0006903699,0.0006117226],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0008459027,0.0002795335,0.00023876368,0.0008366338,0.0024523286,0.0023303127,0.0047119716,0.00022651082,0.07625043],"category_scores_gemma":[0.00081026414,0.00030427874,0.000078245896,0.0008089539,0.00015926689,0.00041968937,0.0020043068,0.00048205708,0.08023379],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000023620107,0.00005988465,7.141952e-8,0.00003096537,0.000036537618,0.000086411164,0.000027679951,1.9451888e-7,0.00000645796,0.00015744605,0.9584906,0.04110136],"study_design_scores_gemma":[0.00018139476,0.00010746843,0.000039503535,0.00005151294,0.000015235145,0.00048616488,0.000008510777,0.00014598545,0.00003100085,0.00020702423,0.998391,0.00033520808],"about_ca_topic_score_codex":0.009113736,"about_ca_topic_score_gemma":0.0010249668,"teacher_disagreement_score":0.04076615,"about_ca_system_score_codex":0.00043911816,"about_ca_system_score_gemma":0.00005254119,"threshold_uncertainty_score":0.99994093},"labels":[],"label_agreement":null},{"id":"W4393886693","doi":"10.5281/zenodo.7803316","title":"SASS-E: The Steelpan Audio Sample Set for Evaluation","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Sass; Sample (material); Set (abstract data type); Computer science; World Wide Web; Programming language; Physics","score_opus":0.11111893059939838,"score_gpt":0.31064814488988435,"score_spread":0.19952921429048598,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393886693","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000119930755,0.00004399033,0.02601029,0.002108499,0.000596269,0.0015574736,0.96624047,0.0009544445,0.0024765648],"genre_scores_gemma":[0.00004568406,0.00015456822,0.001297113,0.00040240688,0.00035102412,0.000001193999,0.9964457,0.0007676618,0.0005346032],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9965593,0.0008472841,0.00037737767,0.00073516957,0.0010046862,0.00047617816],"domain_scores_gemma":[0.99658287,0.0004406143,0.00025785618,0.0013692162,0.0011942891,0.00015516544],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.003244682,0.00024826522,0.00023868463,0.00037235767,0.002882003,0.002191245,0.0037827676,0.00016274457,0.005283501],"category_scores_gemma":[0.004841911,0.00021314863,0.00014453699,0.0009391997,0.00011794014,0.0002994951,0.0018471121,0.00036840682,0.03158086],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011546895,0.000037194077,2.3114877e-8,0.000050992938,0.00005133639,0.0000025113422,0.000118186384,0.000009607574,0.000018019593,0.0004948387,0.86485714,0.13434863],"study_design_scores_gemma":[0.00044648346,0.00013283317,0.000033759003,0.00004160707,0.00005547394,0.000036917627,0.00011184262,0.0037040599,0.00004606996,0.00093089865,0.9942071,0.00025299258],"about_ca_topic_score_codex":0.00007743031,"about_ca_topic_score_gemma":0.0000063716166,"teacher_disagreement_score":0.13409564,"about_ca_system_score_codex":0.00024209332,"about_ca_system_score_gemma":0.000023973578,"threshold_uncertainty_score":0.99884456},"labels":[],"label_agreement":null},{"id":"W4394168003","doi":"10.6084/m9.figshare.21431332","title":"Creating a Large-Scale Audio-Aligned Parsed Corpus of Bilingual Russian Child and Child-Directed Speech (BiRCh): Challenges, Solutions, and Implications for Research","year":2022,"lang":"en","type":"dataset","venue":"Figshare","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Parsing; Scale (ratio); Linguistics; Computer science; Psychology; Natural language processing; Geography; Cartography","score_opus":0.12727723665928403,"score_gpt":0.3427014884403706,"score_spread":0.2154242517810866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394168003","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000066465623,0.0050152596,0.00001723148,0.0015946062,0.00006033065,0.0011122562,0.99075305,0.00015613053,0.0012844707],"genre_scores_gemma":[0.00008457193,0.0011360967,0.0033895732,0.00010088046,0.00014727844,0.0009898772,0.9940764,0.000029536792,0.00004583271],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99711907,0.00036945363,0.00047195048,0.0009578991,0.00045468225,0.0006269423],"domain_scores_gemma":[0.9969622,0.0011855795,0.0003256569,0.0010001821,0.00030865576,0.00021773786],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008089015,0.0002944108,0.0004884735,0.00055633736,0.001347051,0.0001910639,0.0009447327,0.00028298402,0.020371456],"category_scores_gemma":[0.0027699952,0.00030625306,0.00012526958,0.0006284604,0.000044148615,0.00016251353,0.0011205422,0.00047254033,0.00003321314],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001222886,0.00017901578,0.0000013934676,0.00059856905,0.00005509881,0.000005901669,0.00020627773,2.0046997e-7,0.0000054952593,0.00028102475,0.9758413,0.022813527],"study_design_scores_gemma":[0.00057775143,0.0001555306,0.0007517897,0.0014571131,0.000029210487,0.00015879392,0.00017540716,0.00050881406,0.0001239074,0.00046680917,0.9952248,0.00037008015],"about_ca_topic_score_codex":0.000059479647,"about_ca_topic_score_gemma":0.00045125958,"teacher_disagreement_score":0.022443445,"about_ca_system_score_codex":0.00007517972,"about_ca_system_score_gemma":0.00028219383,"threshold_uncertainty_score":0.99995303},"labels":[],"label_agreement":null},{"id":"W4394938944","doi":"10.1109/tifs.2024.3390990","title":"On the Impact of Voice Anonymization on Speech Diagnostic Applications: A Case Study on COVID-19 Detection","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Information Forensics and Security","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Institut national de la recherche scientifique","keywords":"Computer science; Speech recognition; Coronavirus disease 2019 (COVID-19); Artificial intelligence; Medicine","score_opus":0.021931389801271156,"score_gpt":0.28886692742062026,"score_spread":0.2669355376193491,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394938944","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20406635,0.000006074815,0.7935588,0.00033474958,0.00023462906,0.000979277,0.000099881116,0.0001596548,0.0005606368],"genre_scores_gemma":[0.99901,0.000040341056,0.00020039266,0.0004938796,0.000021383306,0.00021217446,0.0000065604518,0.0000075926096,0.000007675534],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99878913,0.00011630315,0.00037685345,0.00022512302,0.00035211293,0.00014045875],"domain_scores_gemma":[0.9974482,0.0017835734,0.00011769768,0.0003922929,0.0001362435,0.00012198671],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040899843,0.00018625423,0.00014700757,0.00043109915,0.00044442725,0.00029629254,0.00014993889,0.00008619318,0.000037842026],"category_scores_gemma":[0.000116735726,0.00013190985,0.00013077252,0.00072618114,0.0000559951,0.00064284116,0.00000306612,0.00028591004,0.000106841646],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018478907,0.0010893261,0.000026370424,0.0001530634,0.00024399473,0.00008555104,0.015640767,0.01921458,0.000040263145,0.022093492,0.0008727969,0.940355],"study_design_scores_gemma":[0.0022260295,0.006260996,0.00050815346,0.00025626007,0.00019034713,0.0015509247,0.0062722615,0.9164703,0.019607067,0.04296885,0.002725965,0.00096286513],"about_ca_topic_score_codex":0.00029103903,"about_ca_topic_score_gemma":0.00011186376,"teacher_disagreement_score":0.93939215,"about_ca_system_score_codex":0.0001677675,"about_ca_system_score_gemma":0.0000967207,"threshold_uncertainty_score":0.5379128},"labels":[],"label_agreement":null},{"id":"W4394983439","doi":"10.4995/eurocall2023.2023.16987","title":"Assessing Google Translate ASR for feedback on L2 pronunciation errors in unpredictable sentence contexts","year":2023,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Concordia University; Université du Québec à Trois-Rivières","funders":"","keywords":"Pronunciation; Sentence; Computer science; Speech recognition; Transcription (linguistics); Vowel; Context (archaeology); Natural language processing; Phonetic transcription; Corrective feedback; Word (group theory); Psychology; Artificial intelligence; Linguistics","score_opus":0.05796951542897077,"score_gpt":0.31790759372116867,"score_spread":0.2599380782921979,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394983439","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37057832,0.00002725686,0.5791359,0.010356315,0.0011553481,0.001347197,0.000016810305,0.0012917899,0.036091056],"genre_scores_gemma":[0.96516025,0.000011846707,0.031124165,0.0006961607,0.000039578077,0.00010348924,0.000012013182,0.000013775228,0.0028387194],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987923,0.000060698425,0.0002366936,0.00034924923,0.00025011864,0.0003109746],"domain_scores_gemma":[0.999339,0.00026750047,0.00005897249,0.00020060419,0.0000725312,0.000061429244],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006118356,0.00011024546,0.00014819975,0.00021295629,0.00009955376,0.00021552425,0.00027930085,0.00007086772,0.00004394887],"category_scores_gemma":[0.00014168794,0.0000983849,0.000064449436,0.0006686012,0.00001636875,0.00079736597,0.000025771935,0.00008509754,0.00023993746],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035042165,0.00019925801,0.0019794563,0.00006437941,0.000020990856,0.00002466045,0.0013242476,0.00035110445,0.0064234356,0.007884904,0.0057792463,0.9759133],"study_design_scores_gemma":[0.00212703,0.00016538464,0.040968597,0.00029050442,0.000010359614,0.000008185827,0.00090006494,0.8893683,0.050843947,0.0091542965,0.005644532,0.0005188303],"about_ca_topic_score_codex":0.000036248213,"about_ca_topic_score_gemma":0.00011552975,"teacher_disagreement_score":0.9753944,"about_ca_system_score_codex":0.000057995258,"about_ca_system_score_gemma":0.00006571834,"threshold_uncertainty_score":0.401202},"labels":[],"label_agreement":null},{"id":"W4395110276","doi":"10.18280/ria.380218","title":"ASER: An Exhaustive Survey for Speech Recognition based on Methods, Datasets, Challenges, Future Scope","year":2024,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Scope (computer science); Computer science; Speech recognition; Artificial intelligence; Pattern recognition (psychology); Data science; Machine learning","score_opus":0.18043312639973536,"score_gpt":0.3757627437728945,"score_spread":0.19532961737315913,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395110276","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00038324238,0.0019639325,0.9891507,0.0023257113,0.0019364964,0.0007290621,0.0008112433,0.00045578709,0.0022438252],"genre_scores_gemma":[0.04179907,0.002308365,0.94899833,0.0014885162,0.0013010236,0.00042183703,0.0028892239,0.00011973048,0.0006739157],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99717087,0.0005050481,0.0004751913,0.0011387123,0.00026356126,0.0004466456],"domain_scores_gemma":[0.99680066,0.0016212472,0.00009243285,0.0010458116,0.00022780371,0.00021202567],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0032810548,0.0002990012,0.00030183783,0.00034426892,0.00021844,0.00042058833,0.0008230903,0.00018000058,0.00045030974],"category_scores_gemma":[0.00042680404,0.00028153358,0.0001628593,0.0007495499,0.000057642595,0.0007045957,0.000079564736,0.00028262287,0.0011373125],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004606879,0.00020190605,0.0000022409245,0.000118743235,0.00001875312,0.00003298709,0.00022295155,0.00017996685,0.00030008436,0.0023060208,0.0035069736,0.99306333],"study_design_scores_gemma":[0.000057621484,0.0006074187,0.000044363842,0.0003045615,0.000020160125,0.000028733677,0.00041959062,0.78086674,0.12761176,0.0042552315,0.085317574,0.00046626167],"about_ca_topic_score_codex":0.000041995863,"about_ca_topic_score_gemma":0.00010028259,"teacher_disagreement_score":0.99259704,"about_ca_system_score_codex":0.00007920035,"about_ca_system_score_gemma":0.00012001996,"threshold_uncertainty_score":0.9999637},"labels":[],"label_agreement":null},{"id":"W4398228866","doi":"10.21437/odyssey.2024-9","title":"A Phonetic Analysis of Speaker Verification Systems through Phoneme selection and Integrated Gradients","year":2024,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Grand Équipement National De Calcul Intensif; European Commission; Johns Hopkins University","keywords":"Computer science; Speaker verification; Selection (genetic algorithm); Speech recognition; Natural language processing; Artificial intelligence; Speaker recognition","score_opus":0.021236749597744672,"score_gpt":0.25224738282100323,"score_spread":0.23101063322325854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398228866","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26654097,0.00033463875,0.7293837,0.00011333533,0.00034589134,0.00011305739,0.000004926683,0.00020999317,0.0029534744],"genre_scores_gemma":[0.98698306,0.00008284044,0.012390073,0.000026043921,0.000009022014,0.000011046341,0.000008393562,0.0000039419137,0.00048555233],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99924177,0.00005509993,0.00019819953,0.00026598477,0.00014871355,0.00009025165],"domain_scores_gemma":[0.99963516,0.000060688577,0.000038225593,0.00015141001,0.00008435532,0.000030189367],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015239244,0.00007440885,0.00015260733,0.00032398815,0.00003206017,0.00016314228,0.000110230474,0.00003817188,0.00010222603],"category_scores_gemma":[0.00001952093,0.000058660073,0.00006071411,0.0023062478,0.00001882799,0.0002671399,0.000018441695,0.000045001936,0.000040991556],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051268904,0.00065050815,0.010264053,0.00057911885,0.007081686,0.000028882016,0.015118585,0.000763424,0.10291071,0.21077648,0.007929836,0.64384544],"study_design_scores_gemma":[0.00006966607,0.000030343876,0.006694593,0.000038952337,0.00021275929,0.000013944947,0.00019370604,0.9813797,0.00881218,0.00024935332,0.0022035053,0.00010129306],"about_ca_topic_score_codex":0.00057752995,"about_ca_topic_score_gemma":0.0000825074,"teacher_disagreement_score":0.9806163,"about_ca_system_score_codex":0.000030663166,"about_ca_system_score_gemma":0.000021183017,"threshold_uncertainty_score":0.23920883},"labels":[],"label_agreement":null},{"id":"W4399527282","doi":"10.1109/taffc.2024.3412152","title":"Controllable Multi-Speaker Emotional Speech Synthesis With an Emotion Representation of High Generalization Capability","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Affective Computing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Natural Science Foundation of Anhui Province; National Natural Science Foundation of China","keywords":"Generalization; Speech recognition; Emotion recognition; Representation (politics); Speaker recognition; Computer science; Emotion classification; Psychology; Artificial intelligence; Mathematics","score_opus":0.02894511557105801,"score_gpt":0.27953085991835863,"score_spread":0.25058574434730063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399527282","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30026624,0.000011595248,0.69834274,0.00012047651,0.0004844794,0.00031987575,0.00001880265,0.00030764006,0.00012814107],"genre_scores_gemma":[0.88845134,0.0000064280766,0.11133684,0.00004089041,0.00006289653,0.00002530721,0.000006025202,0.000021972248,0.000048280075],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977871,0.0005216506,0.00034109436,0.0007011369,0.00042029377,0.00022872207],"domain_scores_gemma":[0.9981914,0.0008471977,0.00011723139,0.00039709284,0.00035442587,0.00009263898],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051075936,0.00021903125,0.00030211182,0.00037683328,0.0002545738,0.00018934911,0.00021883276,0.000097736534,0.00010564073],"category_scores_gemma":[0.000048700345,0.00019673444,0.00014249494,0.0009886007,0.00008219524,0.00076543464,0.0000035741598,0.00019189165,0.0000343946],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011253256,0.0008635604,0.00023759787,0.00012285051,0.0002529285,0.000024269764,0.0010091054,0.09840456,0.011774783,0.001575596,0.000026234879,0.885596],"study_design_scores_gemma":[0.00045108987,0.0002100698,0.0054371874,0.00020962104,0.000052807718,0.000046582623,0.00009137305,0.7537588,0.23917584,0.00035776995,0.0000060734033,0.00020277465],"about_ca_topic_score_codex":0.0002683714,"about_ca_topic_score_gemma":0.00012230416,"teacher_disagreement_score":0.8853932,"about_ca_system_score_codex":0.0001851404,"about_ca_system_score_gemma":0.000083970925,"threshold_uncertainty_score":0.80225974},"labels":[],"label_agreement":null},{"id":"W4400041227","doi":"10.18280/ts.410344","title":"Effect of Data Augmentation, Cross-Validation Methods in Robustness of Explainable Speech Based Emotion Recognition","year":2024,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Robustness (evolution); Speech recognition; Emotion recognition; Computer science; Artificial intelligence; Pattern recognition (psychology)","score_opus":0.07659052623993555,"score_gpt":0.3903428242834736,"score_spread":0.31375229804353805,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400041227","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24746281,0.00003722417,0.7515525,0.00008674811,0.0002036439,0.00032946275,0.00003969402,0.00006256326,0.00022531871],"genre_scores_gemma":[0.6631778,0.000009119225,0.33630925,0.000021076214,0.00005438459,0.000046202666,0.0003456133,0.000011827473,0.00002470831],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99782795,0.0006818289,0.0005471637,0.00041612406,0.00036839192,0.0001585696],"domain_scores_gemma":[0.9985934,0.0007624642,0.000143557,0.0003366242,0.00012567003,0.000038293518],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004059993,0.00013338875,0.00022169243,0.0004032325,0.00003961043,0.00012981506,0.00045628284,0.00006259739,0.00064984715],"category_scores_gemma":[0.00011485864,0.00012429345,0.00006554926,0.00070194836,0.000040971863,0.0012948572,0.00007535032,0.00007831127,0.000012817003],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007571552,0.00014387861,0.00033590867,0.00057543226,0.0000286033,0.000009176073,0.00015869568,0.0014847651,0.025546884,0.00012548432,0.00015337995,0.97136205],"study_design_scores_gemma":[0.00063147215,0.00019603422,0.00073306647,0.00021630501,0.000025773528,0.000004348534,0.000022631688,0.46777827,0.529999,0.00023080275,0.000066743545,0.00009551458],"about_ca_topic_score_codex":0.00003572901,"about_ca_topic_score_gemma":0.000004318024,"teacher_disagreement_score":0.97126657,"about_ca_system_score_codex":0.00006595018,"about_ca_system_score_gemma":0.00007192237,"threshold_uncertainty_score":0.71153706},"labels":[],"label_agreement":null},{"id":"W4400255094","doi":"10.20944/preprints202406.2082.v1","title":"TIPAA-SSL: Text Independent Phone-to-Audio Alignment based on Self-Supervised Learning and Knowledge Transfer","year":2024,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Phone; Speech recognition; Artificial intelligence; TIMIT; Classifier (UML); Transfer of learning; Natural language processing; Frame (networking); Hidden Markov model","score_opus":0.07535121666241719,"score_gpt":0.3170469676804163,"score_spread":0.24169575101799912,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400255094","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8447241,0.00038387606,0.032361347,0.0029767517,0.0025045043,0.0020890643,0.000032181582,0.0022213547,0.11270679],"genre_scores_gemma":[0.9899939,0.00015368535,0.0061698626,0.00065384846,0.00017102931,0.00048070098,0.0000127575195,0.00008206261,0.0022821897],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.995143,0.000505329,0.00064894016,0.0022942342,0.00081183383,0.0005966588],"domain_scores_gemma":[0.9975889,0.00031412914,0.000083893254,0.0013573433,0.00016159067,0.00049418357],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0014716544,0.0006722818,0.0006522934,0.00063408917,0.00019811852,0.00028219598,0.0013354513,0.00046080374,0.0010834555],"category_scores_gemma":[0.0001557914,0.00066834665,0.0003539706,0.0004191588,0.00004900708,0.00010434181,0.0030891658,0.0015970761,0.009298033],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005863565,0.0057210797,0.10567657,0.0053893737,0.0024983152,0.0009918304,0.053926658,0.0056105023,0.043001927,0.009059978,0.0020325317,0.7655049],"study_design_scores_gemma":[0.0042488696,0.00044529495,0.07436269,0.004555157,0.0006108448,0.00010380982,0.0006037394,0.42247346,0.38748738,0.008618666,0.090975754,0.0055143447],"about_ca_topic_score_codex":0.000060744995,"about_ca_topic_score_gemma":0.000023437899,"teacher_disagreement_score":0.7599905,"about_ca_system_score_codex":0.0003531782,"about_ca_system_score_gemma":0.00040426716,"threshold_uncertainty_score":0.9998297},"labels":[],"label_agreement":null},{"id":"W4400285258","doi":"10.1121/10.0027483","title":"Perception of speaker identity for bilingual voices","year":2024,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Identity (music); Perception; Linguistics; Psychology; Communication; Speech recognition; Computer science; Art; Aesthetics","score_opus":0.022300024452987864,"score_gpt":0.2975020187165441,"score_spread":0.27520199426355624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400285258","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033659037,0.00021235192,0.9604982,0.0050059073,0.0004237524,0.00008102415,0.000006680216,0.000012221302,0.00010079268],"genre_scores_gemma":[0.66524273,0.00035563097,0.33333987,0.0006853229,0.0002519244,6.706563e-7,1.2866037e-7,0.0000075182234,0.00011623454],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989689,0.000090443384,0.0003403706,0.000075141164,0.00040970626,0.000115439594],"domain_scores_gemma":[0.9984161,0.00089506875,0.00023778663,0.00019881799,0.00021373974,0.00003844498],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009312875,0.00006917356,0.00018686737,0.000021274822,0.00008249071,0.000042797576,0.0008075,0.000037385216,0.000058866735],"category_scores_gemma":[0.0002686182,0.000034202567,0.00052525016,0.00028823604,0.00030117034,0.00024748818,0.00012682083,0.00017307259,0.0000055065857],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000095605916,0.00029425774,0.000074952186,0.00034219513,0.0005168731,0.000001701787,0.0068934765,0.0007311328,0.13550258,0.00046022912,0.042447623,0.81263936],"study_design_scores_gemma":[0.0003566931,0.0004970957,0.0021189202,0.00034912882,0.00050417625,0.00014358202,0.008175513,0.95393956,0.0100032985,0.017588023,0.0061455276,0.00017851125],"about_ca_topic_score_codex":0.000018677258,"about_ca_topic_score_gemma":4.6198713e-7,"teacher_disagreement_score":0.9532084,"about_ca_system_score_codex":0.00003081419,"about_ca_system_score_gemma":0.00010651116,"threshold_uncertainty_score":0.15005493},"labels":[],"label_agreement":null},{"id":"W4400285553","doi":"10.1121/10.0027487","title":"Detecting ringed seal vocalizations in multiple environments using deep learning","year":2024,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Dalhousie University; Wildlife Conservation Society Canada; University of Victoria","funders":"","keywords":"Seal (emblem); Computer science; Deep learning; Artificial intelligence; Human–computer interaction; Geography; Archaeology","score_opus":0.025504177123565903,"score_gpt":0.2571948778182838,"score_spread":0.23169070069471792,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400285553","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.044113006,0.00020496774,0.95460826,0.00082482526,0.00015243654,0.000047004116,4.4911403e-7,0.000010760431,0.000038272905],"genre_scores_gemma":[0.84731054,0.00013575082,0.15225843,0.00021584157,0.000053500742,3.8081956e-7,3.9370683e-8,0.000007102054,0.000018445726],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988855,0.00022626073,0.0003052928,0.00008384525,0.00033637157,0.00016270779],"domain_scores_gemma":[0.99864817,0.000964503,0.00017318797,0.00014208417,0.000026821474,0.00004522985],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00065413315,0.00007594826,0.00014768053,0.000030721643,0.00019435778,0.00005076586,0.0005257169,0.00003722776,0.000024125202],"category_scores_gemma":[0.0003993948,0.000044305852,0.00021058375,0.00041223076,0.00016898934,0.00016270713,0.00019148065,0.00043252573,0.000004570071],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003734877,0.00022454417,0.0040630437,0.00008008118,0.00030511038,0.000013789366,0.007908842,0.35750377,0.18146318,0.000023048846,0.00035596892,0.44802126],"study_design_scores_gemma":[0.00010852261,0.00003374089,0.0013439105,0.00009516341,0.000044026303,0.000055541797,0.00091025064,0.99334776,0.0034640362,0.00022043387,0.00032304032,0.000053541913],"about_ca_topic_score_codex":0.000017200635,"about_ca_topic_score_gemma":0.0000015719933,"teacher_disagreement_score":0.8031975,"about_ca_system_score_codex":0.000089225876,"about_ca_system_score_gemma":0.000039304497,"threshold_uncertainty_score":0.18791331},"labels":[],"label_agreement":null},{"id":"W4400288586","doi":"10.1121/10.0027199","title":"Quantifying vowel category distinctness using Bayesian modelling","year":2024,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Bayesian probability; Vowel; Computer science; Bayesian inference; Artificial intelligence; Statistics; Natural language processing; Speech recognition; Mathematics","score_opus":0.05836696820019907,"score_gpt":0.2929317606397118,"score_spread":0.23456479243951275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400288586","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004203258,0.0005419863,0.9910932,0.0034886939,0.00049221364,0.0000515309,0.0000020891248,0.000026358712,0.00010067949],"genre_scores_gemma":[0.66716075,0.00015682126,0.33206707,0.00044620564,0.0001344917,2.6258616e-7,5.3354498e-8,0.000010056389,0.000024288302],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99859256,0.00016563937,0.00041174245,0.000115132134,0.00050021807,0.00021471905],"domain_scores_gemma":[0.9984011,0.0008383465,0.00024299433,0.0002993632,0.00014083437,0.00007738062],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00086542696,0.00011881013,0.00023868066,0.000029179724,0.00023772728,0.00010314205,0.0010764095,0.00004981133,0.000030186608],"category_scores_gemma":[0.0000906614,0.000060903327,0.00046017737,0.00047625162,0.00031262782,0.00022317417,0.00020900027,0.0004122996,0.000004939375],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008273955,0.00031556742,0.000079530626,0.00043962945,0.00083614915,0.0000357048,0.009859024,0.26811394,0.03888277,0.0008286487,0.011189475,0.66933686],"study_design_scores_gemma":[0.00005799154,0.000028885595,0.000030008334,0.00016388691,0.00012443517,0.00016154676,0.0006742823,0.9944584,0.0011206592,0.002736549,0.00036050647,0.00008285385],"about_ca_topic_score_codex":0.00006252328,"about_ca_topic_score_gemma":2.7170992e-7,"teacher_disagreement_score":0.72634447,"about_ca_system_score_codex":0.00006267431,"about_ca_system_score_gemma":0.00014909291,"threshold_uncertainty_score":0.24835657},"labels":[],"label_agreement":null},{"id":"W4400292625","doi":"10.31234/osf.io/vufw4","title":"Establishing the reliability of metrics extracted from long-form recordings using LENA and the ACLEW pipeline","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada; Grand Équipement National De Calcul Intensif; European Commission; China Scholarship Council; National Institutes of Health; National Science Foundation; James S. McDonnell Foundation; Agence Nationale de la Recherche","keywords":"Pipeline (software); Reliability (semiconductor); Computer science; Reliability engineering; Statistics; Mathematics; Engineering; Physics; Programming language","score_opus":0.04114783272527828,"score_gpt":0.27198729144373485,"score_spread":0.23083945871845657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400292625","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44425485,0.002322009,0.5320272,0.008016025,0.0026488202,0.0009191362,0.00007733167,0.00035076597,0.009383861],"genre_scores_gemma":[0.8164559,0.0010775321,0.18069242,0.0006979173,0.00035420747,0.000029553763,0.000015229795,0.00003706007,0.0006401853],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99749005,0.00028420016,0.0007017558,0.0007486742,0.00054013607,0.00023517536],"domain_scores_gemma":[0.99342847,0.0044645434,0.00037819246,0.0013101686,0.00034288966,0.00007575248],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0033292526,0.0002779027,0.00050162873,0.00022481724,0.00016037673,0.0011695927,0.0015755112,0.0002516117,0.00012841148],"category_scores_gemma":[0.0030554244,0.0001414553,0.00025844356,0.0008451719,0.00023730392,0.0003467317,0.0033766476,0.0010391426,0.000011277197],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000060694063,0.000096136086,0.0007045305,0.00029514518,0.0001634171,0.000014801978,0.0021936558,0.000078283854,0.0002191512,0.0033945413,0.0025815316,0.99019814],"study_design_scores_gemma":[0.00042834767,0.000011203605,0.0019658739,0.00047615197,0.00025751747,0.00002026334,0.0003035679,0.82502306,0.0051664812,0.16463006,0.0013147278,0.00040272874],"about_ca_topic_score_codex":0.004623527,"about_ca_topic_score_gemma":0.0001730675,"teacher_disagreement_score":0.9897954,"about_ca_system_score_codex":0.00008805573,"about_ca_system_score_gemma":0.00017805504,"threshold_uncertainty_score":0.99986726},"labels":[],"label_agreement":null},{"id":"W4400527917","doi":"10.1109/fg59268.2024.10582047","title":"Distilling Privileged Multimodal Information for Expression Recognition using Optimal Transport","year":2024,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; École de Technologie Supérieure","funders":"","keywords":"Computer science; Expression (computer science); Multimodal transport; Artificial intelligence; Human–computer interaction; Engineering; Transport engineering; Programming language","score_opus":0.040758615026911874,"score_gpt":0.2714358269321869,"score_spread":0.23067721190527501,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400527917","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.056775134,0.000015549964,0.9407302,0.000121263925,0.0004678541,0.00027518245,0.000027001364,0.0004351107,0.0011526918],"genre_scores_gemma":[0.40647614,0.0000047624885,0.59325546,0.00008170115,0.0000610334,0.0000345804,0.00005110767,0.0000058571695,0.00002938318],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99919546,0.000016747088,0.00025379378,0.00019550956,0.00016962188,0.00016884232],"domain_scores_gemma":[0.9995714,0.00011895934,0.000035985384,0.00012533624,0.00008734914,0.000060998107],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023792966,0.00010261932,0.00009372918,0.00016345747,0.00011700794,0.0002274843,0.00015959662,0.0000669156,0.00010154618],"category_scores_gemma":[0.000038137165,0.00008694864,0.00010039404,0.00018204836,0.000012168886,0.0022655996,0.000019003635,0.000065562315,0.00007524342],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021463598,0.00003143515,0.0000194044,0.00012799386,0.0000143443995,0.000004874587,0.000843259,0.0002779094,0.009279071,0.0010042534,0.00020663324,0.9881694],"study_design_scores_gemma":[0.00018858578,0.000022343485,0.00007844506,0.00014622806,0.000010966657,0.0000147817145,0.00006068365,0.91882277,0.07645309,0.0006098609,0.0034352862,0.00015694987],"about_ca_topic_score_codex":0.00000945505,"about_ca_topic_score_gemma":0.0000015949191,"teacher_disagreement_score":0.98801243,"about_ca_system_score_codex":0.0000369303,"about_ca_system_score_gemma":0.000047411435,"threshold_uncertainty_score":0.35456628},"labels":[],"label_agreement":null},{"id":"W4400910594","doi":"10.1109/ic3se62002.2024.10593399","title":"Exploring the Effectiveness of Advanced Machine Learning Models in Speech Emotion Recognition","year":2024,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Speech recognition; Emotion recognition; Natural language processing; Artificial intelligence","score_opus":0.10295351290849031,"score_gpt":0.2651108309336718,"score_spread":0.16215731802518152,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400910594","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.58190554,0.00011525847,0.40690756,0.00015108447,0.00034178517,0.00019846138,0.0000012279532,0.00021711734,0.010161957],"genre_scores_gemma":[0.98486775,0.00014672715,0.014828929,0.000015499423,0.000015386004,0.00004858355,0.0000036144672,0.0000075427865,0.00006597657],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989737,0.00034817483,0.00016460562,0.00022954424,0.00016417146,0.00011979309],"domain_scores_gemma":[0.9990082,0.0007609463,0.000023114406,0.00014049352,0.000046703473,0.000020552003],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012081466,0.00007944743,0.000110085784,0.00019012173,0.000040926367,0.000070204245,0.00018357471,0.00002132789,0.000029841221],"category_scores_gemma":[0.00010509558,0.00005574927,0.00005631993,0.00056946126,0.00001471754,0.0010677379,0.000057693665,0.00015749592,0.000047716305],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014539208,0.000020963182,0.000039241553,0.00006984083,0.000006999468,0.00000937277,0.00025602733,0.0012429487,0.0042247786,0.005243531,0.0000010235217,0.98887074],"study_design_scores_gemma":[0.00023392515,0.00006321104,0.0031034774,0.0005862114,0.0000057950047,0.000024723897,0.00016827327,0.7825208,0.17387205,0.03918377,0.00009340422,0.00014439819],"about_ca_topic_score_codex":0.000070550595,"about_ca_topic_score_gemma":0.000019862931,"teacher_disagreement_score":0.9887263,"about_ca_system_score_codex":0.000038177554,"about_ca_system_score_gemma":0.000017715169,"threshold_uncertainty_score":0.22733894},"labels":[],"label_agreement":null},{"id":"W4400926002","doi":"10.1007/s11042-024-19892-4","title":"Deep normalization for light SpineNet speaker anti-spoofing systems","year":2024,"lang":"en","type":"article","venue":"Multimedia Tools and Applications","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Normalization (sociology); Speaker verification; Speech recognition; Artificial intelligence; Spoofing attack; Computer security; Speaker recognition","score_opus":0.02683028761416486,"score_gpt":0.26277609325179724,"score_spread":0.23594580563763237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400926002","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00039975697,0.0010808536,0.99445236,0.00095875893,0.00024644486,0.0007231725,0.000033495216,0.00025264575,0.0018525082],"genre_scores_gemma":[0.5133971,0.00092899025,0.4764263,0.0006365326,0.0019839902,0.00426615,0.00039415574,0.00007508882,0.0018916785],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99922764,0.000013336072,0.00019104622,0.0003118395,0.00010193649,0.00015417872],"domain_scores_gemma":[0.9994186,0.00018430121,0.00003412482,0.00021440572,0.00006906737,0.000079495505],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014212783,0.000097888005,0.0001108386,0.000089946145,0.00013698089,0.00058534904,0.00018084327,0.000054438915,0.000016647467],"category_scores_gemma":[0.000026602653,0.00008627872,0.000044732296,0.00027014076,0.000018140949,0.00035146676,0.00003976829,0.000044536067,0.00012998446],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.725971e-7,0.000040732983,0.000106560576,0.00014325629,0.000026124602,0.0000020488114,0.000264278,0.000092581206,0.003228301,0.06790789,0.0017354131,0.92645186],"study_design_scores_gemma":[0.00010284588,0.000008182443,0.000676278,0.000033328964,0.000013324257,0.000012413996,0.000027723248,0.7065613,0.001730147,0.00043384405,0.29027575,0.00012481073],"about_ca_topic_score_codex":0.000006998429,"about_ca_topic_score_gemma":0.000003656804,"teacher_disagreement_score":0.92632705,"about_ca_system_score_codex":0.000015218689,"about_ca_system_score_gemma":0.000022247166,"threshold_uncertainty_score":0.5644534},"labels":[],"label_agreement":null},{"id":"W4401072402","doi":"10.1109/memea60663.2024.10596816","title":"Zero-Shot Multi-Task Cough Sound Analysis with Speech Foundation Model Embeddings","year":2024,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada; Carleton University","funders":"National Research Council Canada","keywords":"Zero (linguistics); Computer science; Task (project management); Speech recognition; Foundation (evidence); One shot; Shot (pellet); Acoustics; Physics; Engineering","score_opus":0.05202535987894881,"score_gpt":0.302398923194524,"score_spread":0.2503735633155752,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401072402","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022936111,0.000028930457,0.96468306,0.0004951195,0.000104534854,0.0001207008,0.000003818157,0.00054711057,0.011080592],"genre_scores_gemma":[0.6014682,0.000009819221,0.3930756,0.0003400171,0.000019575678,0.000015434247,0.000012555063,0.000010402675,0.0050484166],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99856395,0.000029525738,0.00021488137,0.000558625,0.000394756,0.00023827495],"domain_scores_gemma":[0.999214,0.000108167565,0.000041065607,0.0004068486,0.00012944524,0.00010046986],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027929162,0.00016722274,0.00020005796,0.00042354217,0.00009858546,0.00092493126,0.0003908086,0.0000620763,0.00037746786],"category_scores_gemma":[0.000021927375,0.00012559471,0.00014735335,0.0015837492,0.000040848223,0.00086270034,0.0000732777,0.00010870017,0.0006023989],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000856116,0.00065643294,0.0015215285,0.00015033444,0.0041059926,0.0003823872,0.0057719047,0.019655773,0.005755501,0.16057754,0.007174463,0.7941625],"study_design_scores_gemma":[0.00018459206,0.000022458746,0.00011668367,0.000013874659,0.00017665571,0.000022520104,0.000038381266,0.9913232,0.0022726746,0.0047716787,0.00084333395,0.00021397354],"about_ca_topic_score_codex":0.00006843601,"about_ca_topic_score_gemma":0.0001811949,"teacher_disagreement_score":0.9716674,"about_ca_system_score_codex":0.00006894677,"about_ca_system_score_gemma":0.00008038812,"threshold_uncertainty_score":0.89191335},"labels":[],"label_agreement":null},{"id":"W4401110548","doi":"10.1109/cai59869.2024.00186","title":"On the influence of metric learning loss functions for robust self-supervised speaker verification to label noise","year":2024,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Computer science; Metric (unit); Speech recognition; Noise (video); Speaker verification; Speaker recognition; Artificial intelligence; Robustness (evolution); Pattern recognition (psychology); Engineering","score_opus":0.035839557899245124,"score_gpt":0.2552282605859905,"score_spread":0.2193887026867454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401110548","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26057872,0.000023985242,0.7311752,0.0036210264,0.00017739196,0.00033944793,0.0000043628424,0.0003081934,0.0037716578],"genre_scores_gemma":[0.8945758,0.000010844367,0.10280917,0.00074954866,0.000026575843,0.00009873533,0.0000021430835,0.000009813115,0.0017173778],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99922055,0.000049501756,0.00015882262,0.00025701092,0.0001882482,0.00012587535],"domain_scores_gemma":[0.9986739,0.00081924995,0.00002539485,0.00027937966,0.00015220704,0.00004982377],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003828984,0.000078646524,0.000080575686,0.0002380235,0.00011906625,0.00014413675,0.00031065577,0.00003223472,0.00012390607],"category_scores_gemma":[0.0004083558,0.000052835338,0.00005770995,0.0012750434,0.000013257568,0.00020503876,0.000041868614,0.00008358131,0.0004608082],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005086868,0.0004941736,0.0005826977,0.00018598573,0.00020998875,0.0000060232665,0.0026304815,0.028761037,0.0149059165,0.2787858,0.016013138,0.6573739],"study_design_scores_gemma":[0.0002621131,0.0002671099,0.0052646324,0.00009064208,0.00003915755,0.0000081676535,0.00021882636,0.9616065,0.010695725,0.0011471874,0.020144975,0.00025493916],"about_ca_topic_score_codex":0.00001774709,"about_ca_topic_score_gemma":0.000004881026,"teacher_disagreement_score":0.9328455,"about_ca_system_score_codex":0.00003233694,"about_ca_system_score_gemma":0.00004318804,"threshold_uncertainty_score":0.59229106},"labels":[],"label_agreement":null},{"id":"W4401281176","doi":"10.1016/j.csl.2024.101695","title":"Speech self-supervised representations benchmarking: A case for larger probing heads","year":2024,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; Mila - Quebec Artificial Intelligence Institute","funders":"Agence de l'innovation de Défense","keywords":"Benchmarking; Computer science; Ranking (information retrieval); Inference; Task (project management); Downstream (manufacturing); Generalization; Feature (linguistics); Set (abstract data type); Artificial intelligence; Architecture; Machine learning; Benchmark (surveying); Data set; Natural language processing","score_opus":0.02313783000429004,"score_gpt":0.2944255563429296,"score_spread":0.27128772633863957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401281176","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054547563,0.0007905558,0.9337468,0.0018984771,0.0023063952,0.0010959331,0.000047560672,0.0020758822,0.0034907986],"genre_scores_gemma":[0.08816654,0.000016636815,0.9087351,0.0008780144,0.0013452783,0.00015011239,0.00004536579,0.000053869917,0.00060911104],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975308,0.0001280109,0.00044645183,0.0009713273,0.0003514787,0.00057190313],"domain_scores_gemma":[0.9982301,0.00046117321,0.00006875436,0.0008783738,0.00014932957,0.0002122978],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00063617167,0.0003151436,0.00031588515,0.00040009804,0.00028490054,0.0011650545,0.0007437792,0.00013240459,0.00031134833],"category_scores_gemma":[0.000044438813,0.00029254082,0.00031902784,0.00081882265,0.000032789456,0.00070197677,0.00034087835,0.00025168614,0.00023819733],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000048181428,0.00015498718,0.000029555476,0.00017738772,0.00012781637,0.010980012,0.0066681225,0.000008635706,0.0011597889,0.0040954202,0.012394567,0.9641989],"study_design_scores_gemma":[0.00072832906,0.0001313769,0.00008750348,0.0001798701,0.0000764618,0.010669451,0.00035677795,0.9455146,0.014840044,0.0010807979,0.025619278,0.0007154884],"about_ca_topic_score_codex":0.000066653694,"about_ca_topic_score_gemma":0.000050155202,"teacher_disagreement_score":0.9634834,"about_ca_system_score_codex":0.00010235074,"about_ca_system_score_gemma":0.00013291533,"threshold_uncertainty_score":0.9999527},"labels":[],"label_agreement":null},{"id":"W4401608508","doi":"10.1109/conit61985.2024.10626802","title":"Speaker Identification Using CNN-LSTM Model on RAVDESS Dataset: A Deep Learning Approach","year":2024,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Artificial intelligence; Identification (biology); Deep learning; Speaker identification; Speech recognition; Natural language processing; Pattern recognition (psychology); Speaker recognition","score_opus":0.07526706665184585,"score_gpt":0.3005111881364797,"score_spread":0.22524412148463385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401608508","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034956136,0.000058392703,0.9806889,0.00017098033,0.00018101052,0.00010165057,0.000011606991,0.00032322318,0.014968599],"genre_scores_gemma":[0.67244154,0.000021407252,0.32364342,0.00046290708,0.00010136636,0.000020141337,0.00020119065,0.00002588748,0.0030821424],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99879664,0.00006584589,0.00019278866,0.00048598796,0.000276478,0.0001822294],"domain_scores_gemma":[0.9994237,0.000064826825,0.000033894303,0.00037937568,0.00003304686,0.000065201966],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040758593,0.00011373726,0.00009683826,0.0001905467,0.000135113,0.0006661143,0.00038836402,0.000050798786,0.00011984594],"category_scores_gemma":[0.000038914353,0.00009813091,0.000052067327,0.00035733957,0.000019917725,0.0005909422,0.00009814837,0.000156961,0.0006534084],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010020126,0.00021953846,0.000016029957,0.00010650122,0.000071179384,0.000040055467,0.0012449942,0.0609577,0.011125901,0.103206076,0.0053273174,0.8176747],"study_design_scores_gemma":[0.00005033327,0.0000066137122,0.000020782853,0.000021306338,0.000009446902,0.000019176017,0.00005607612,0.9926119,0.0035912932,0.0011130349,0.0023618827,0.00013814718],"about_ca_topic_score_codex":0.000014753228,"about_ca_topic_score_gemma":0.0000019497413,"teacher_disagreement_score":0.9316542,"about_ca_system_score_codex":0.00004870025,"about_ca_system_score_gemma":0.00003303495,"threshold_uncertainty_score":0.83984613},"labels":[],"label_agreement":null},{"id":"W4401609584","doi":"10.1109/icasspw62465.2024.10626010","title":"Characterizing the Temporal Dynamics of Universal Speech Representations for Generalizable Deepfake Detection","year":2024,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Dynamics (music); Computer science; Speech recognition; Artificial intelligence; Natural language processing; Acoustics; Physics","score_opus":0.028143047117421098,"score_gpt":0.2683847684010593,"score_spread":0.2402417212836382,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401609584","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014528864,0.000018350353,0.978511,0.0022749682,0.000459553,0.00017846317,0.000010510956,0.00015660327,0.0038616837],"genre_scores_gemma":[0.8158793,0.00002299845,0.17882678,0.0002120146,0.00011003365,0.000031477648,0.000025683925,0.000013052799,0.0048786527],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994425,0.000034410896,0.00013730867,0.00017660808,0.000106063926,0.00010306873],"domain_scores_gemma":[0.99952364,0.00014840905,0.000034300985,0.00020310323,0.000066896726,0.000023633424],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022161145,0.00005675643,0.00006630891,0.000095586256,0.00010013024,0.00014033576,0.00022534262,0.000031283485,0.000057559115],"category_scores_gemma":[0.000026889642,0.0000410606,0.00008116628,0.00031213544,0.000023220296,0.00033459123,0.000045080706,0.000043111537,0.0000140738875],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012418828,0.000046717927,0.00016293232,0.00006339787,0.00007916945,0.0000115166995,0.0006706558,0.000035748228,0.028285127,0.15433067,0.001230935,0.8150707],"study_design_scores_gemma":[0.00008258065,0.000027064905,0.00017641395,0.000013395794,0.000012431706,0.00002471761,0.00025139443,0.8992134,0.08994376,0.003978827,0.006203071,0.000072999166],"about_ca_topic_score_codex":0.00013899892,"about_ca_topic_score_gemma":0.00036414884,"teacher_disagreement_score":0.8991776,"about_ca_system_score_codex":0.000041082247,"about_ca_system_score_gemma":0.000036241287,"threshold_uncertainty_score":0.16744027},"labels":[],"label_agreement":null},{"id":"W4401994215","doi":"10.3390/acoustics6030042","title":"Text-Independent Phone-to-Audio Alignment Leveraging SSL (TIPAA-SSL) Pre-Trained Model Latent Representation and Knowledge Transfer","year":2024,"lang":"en","type":"article","venue":"Acoustics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Phone; Speech recognition; Artificial intelligence; Classifier (UML); TIMIT; Transfer of learning; Hidden Markov model; Natural language processing; Frame (networking); Representation (politics)","score_opus":0.03828787458081839,"score_gpt":0.28654415752196705,"score_spread":0.24825628294114865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401994215","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.114272036,0.00024057613,0.8818075,0.0009618955,0.00060855347,0.000291374,0.000015079794,0.000288957,0.0015140044],"genre_scores_gemma":[0.96692157,0.00013831559,0.030348966,0.00036735614,0.00010434333,0.000049692895,0.0000058052483,0.000024715322,0.0020392227],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99833614,0.00005682633,0.00030447726,0.0006054826,0.0003757585,0.00032129392],"domain_scores_gemma":[0.99917275,0.00017155282,0.000018970604,0.00034946442,0.00008865283,0.00019863405],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032083108,0.00020220036,0.00019052504,0.00019460292,0.0001224238,0.00043590405,0.00032091304,0.000085503634,0.000045335008],"category_scores_gemma":[0.00004826547,0.00018868393,0.000084811,0.00033300466,0.000027976428,0.00029495568,0.00015140654,0.00015229096,0.00016135728],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056139976,0.00042866232,0.00015981079,0.00033050668,0.0002962502,0.0002931299,0.025892546,0.030804105,0.15921858,0.008812982,0.014019202,0.7596881],"study_design_scores_gemma":[0.00030081056,0.000040979132,0.00095345115,0.000108095504,0.00006123319,0.000052534037,0.00013692363,0.9795519,0.015534054,0.0024175902,0.00056679145,0.00027563874],"about_ca_topic_score_codex":0.000016435508,"about_ca_topic_score_gemma":0.000007898407,"teacher_disagreement_score":0.9487478,"about_ca_system_score_codex":0.000115149465,"about_ca_system_score_gemma":0.00010858953,"threshold_uncertainty_score":0.76943076},"labels":[],"label_agreement":null},{"id":"W4402112262","doi":"10.21437/interspeech.2024-552","title":"Quantifying the Role of Textual Predictability in Automatic Speech Recognition","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada; University of Toronto","keywords":"Predictability; Computer science; Leverage (statistics); Lexicon; Speech recognition; Language model; Syntax; Natural language processing; Acoustic model; Semantics (computer science); Context (archaeology); Artificial intelligence; Hidden Markov model; Speech processing","score_opus":0.056951169292264014,"score_gpt":0.28977791828759497,"score_spread":0.23282674899533096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402112262","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9025693,0.000777909,0.0110936975,0.001888395,0.0011934408,0.0013708182,0.00008059229,0.0008986922,0.08012714],"genre_scores_gemma":[0.92372084,0.000036161702,0.0759384,0.000073833486,0.00005477354,0.00008661072,0.000012297778,0.000012624439,0.000064463566],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99785864,0.00027003497,0.00064224994,0.0005879083,0.00042374062,0.00021743323],"domain_scores_gemma":[0.9983094,0.00052802823,0.00016412977,0.00083846203,0.00011268268,0.000047309728],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013943872,0.00021068161,0.00033669447,0.0002759772,0.000037381535,0.0002079717,0.0009986016,0.0002206788,0.00039750873],"category_scores_gemma":[0.00031953605,0.00014500445,0.0001967744,0.0004254267,0.00007662297,0.000117088006,0.0014788359,0.0006567318,0.0002785032],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020205412,0.00008759662,0.0006373043,0.0002447052,0.00002665152,0.0000067112355,0.0005296983,0.0000029428647,0.00018362669,0.0016218852,0.00010954455,0.99654734],"study_design_scores_gemma":[0.00014096007,0.00003462438,0.0064721815,0.0010028549,0.000044921784,0.00003391677,0.0010335144,0.61588854,0.04169385,0.3330947,0.00018892817,0.0003710055],"about_ca_topic_score_codex":0.00042732153,"about_ca_topic_score_gemma":0.00046545328,"teacher_disagreement_score":0.9961763,"about_ca_system_score_codex":0.00007779659,"about_ca_system_score_gemma":0.00021250732,"threshold_uncertainty_score":0.591311},"labels":[],"label_agreement":null},{"id":"W4402275989","doi":"10.1515/phon-2024-0015","title":"The Mason-Alberta Phonetic Segmenter: a forced alignment system based on deep neural networks and interpolation","year":2024,"lang":"en","type":"article","venue":"Phonetica","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"Social Sciences and Humanities Research Council of Canada; Nvidia","keywords":"Computer science; Interpolation (computer graphics); Speech recognition; Two-alternative forced choice; Artificial intelligence; Artificial neural network; Classifier (UML); Testbed; Task (project management); Similarity (geometry); Natural language processing; Mathematics","score_opus":0.007528713155730898,"score_gpt":0.21007607105451015,"score_spread":0.20254735789877926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402275989","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004966317,0.0007928999,0.9783143,0.0038885432,0.0018150784,0.00048341873,0.0000027280914,0.00030790584,0.0094288215],"genre_scores_gemma":[0.99659634,0.000023569484,0.0025465677,0.0004898189,0.00007775558,0.00006550327,0.0000028216884,0.000014196944,0.00018341196],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988155,0.00012191219,0.00021124254,0.00035657798,0.00023450688,0.0002602551],"domain_scores_gemma":[0.9987373,0.00075432175,0.000036781752,0.00035020104,0.000021340622,0.00010005361],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022485458,0.00015025627,0.00011484587,0.000071197406,0.00017515922,0.00060044235,0.00029411458,0.000045481564,0.000037922175],"category_scores_gemma":[0.0000272823,0.00010351967,0.000061391176,0.0002184326,0.0000457365,0.00008681246,0.000088619185,0.00011112323,0.00007430322],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012943667,0.00009585119,0.00015183787,0.00016891709,0.00011510286,0.00007568335,0.0013925065,0.0022906368,0.0010476117,0.02608441,0.003545162,0.9649028],"study_design_scores_gemma":[0.00017836985,0.00010027479,0.0002055138,0.00012209566,0.000015317948,0.000026233445,0.00007048823,0.9972501,0.00057742343,0.00011344447,0.0012191177,0.00012164204],"about_ca_topic_score_codex":0.000032306638,"about_ca_topic_score_gemma":0.000031845793,"teacher_disagreement_score":0.9949594,"about_ca_system_score_codex":0.000055460074,"about_ca_system_score_gemma":0.00001249542,"threshold_uncertainty_score":0.5790079},"labels":[],"label_agreement":null},{"id":"W4402625500","doi":"10.1007/s00034-024-02854-4","title":"Attentive Context-Aware Deep Speaker Representations for Voice Biometrics in Adverse Conditions","year":2024,"lang":"en","type":"article","venue":"Circuits Systems and Signal Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Biometrics; Speech recognition; Speaker recognition; Context (archaeology); Computer science; Voice analysis; Psychology; Artificial intelligence; History","score_opus":0.047731877708680696,"score_gpt":0.30188998190649563,"score_spread":0.2541581041978149,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402625500","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015193542,0.0042137625,0.9772144,0.00032639314,0.00042181925,0.00054989883,0.000052454736,0.00018329239,0.0018444249],"genre_scores_gemma":[0.9987756,0.000014577909,0.000483454,0.00012039271,0.00009545831,0.00012589278,0.000016036658,0.00001291273,0.0003556576],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99876463,0.000057817775,0.00032432217,0.0004405446,0.0001889338,0.00022375489],"domain_scores_gemma":[0.9991015,0.00042017916,0.00007535392,0.000114340975,0.00019666631,0.000091965936],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003521796,0.000124823,0.00018967806,0.0006192221,0.00023235088,0.00057336665,0.00016573066,0.000073188196,0.000013796505],"category_scores_gemma":[0.000069231406,0.000117161,0.0000626547,0.0012283063,0.000053388336,0.0008000616,0.00003235144,0.000096881864,0.000030990508],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000046784576,0.00012875232,0.0013872036,0.0016095495,0.000084084284,0.00021030473,0.005115718,0.00015239758,0.0033996042,0.01563982,0.0008103539,0.97145754],"study_design_scores_gemma":[0.0009849347,0.000081847094,0.004476328,0.001938294,0.00007002285,0.00033834076,0.008758465,0.9682887,0.0010029597,0.0046481853,0.008770452,0.0006414689],"about_ca_topic_score_codex":0.000036935697,"about_ca_topic_score_gemma":0.000021568689,"teacher_disagreement_score":0.9835821,"about_ca_system_score_codex":0.000056382127,"about_ca_system_score_gemma":0.000102053345,"threshold_uncertainty_score":0.5528988},"labels":[],"label_agreement":null},{"id":"W4402671182","doi":"10.18653/v1/2024.acl-srw.34","title":"Homophone2Vec: Embedding Space Analysis for Empirical Evaluation of Phonological and Semantic Similarity","year":2024,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"McGill University","keywords":"Computer science; Semantic similarity; Embedding; Similarity (geometry); Semantic space; Natural language processing; Space (punctuation); Artificial intelligence; Information retrieval","score_opus":0.11656631950415315,"score_gpt":0.38381896032013624,"score_spread":0.2672526408159831,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402671182","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24201527,0.00020907281,0.75451785,0.0018551014,0.00009594432,0.00014591243,0.0000034280151,0.00010311586,0.0010543187],"genre_scores_gemma":[0.90403384,0.000016704838,0.09572934,0.00008869728,0.000017561099,0.000018604249,0.0000023028126,0.0000026169853,0.000090328576],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990108,0.00009268363,0.00016892927,0.00032046242,0.00028798322,0.00011914531],"domain_scores_gemma":[0.9991208,0.00047692083,0.00002761341,0.00017842742,0.00014784547,0.00004839529],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010942112,0.00007502513,0.00018556345,0.0002528247,0.00004798481,0.00012817355,0.00013940339,0.000064681684,0.00019655595],"category_scores_gemma":[0.0002676105,0.00005692027,0.00013671943,0.0007860612,0.00003374349,0.00016508106,0.000067144894,0.000050766605,0.000009908565],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026795842,0.00032601142,0.015247415,0.00023360687,0.0016193175,0.000018175948,0.0020732833,0.00068364805,0.005041123,0.026381547,0.0043923287,0.94395673],"study_design_scores_gemma":[0.000115577386,0.000032301752,0.009915048,0.00000996177,0.00031605797,0.0000054350758,0.00006014495,0.97513676,0.0062397397,0.007862408,0.00022683592,0.000079749494],"about_ca_topic_score_codex":0.000012565604,"about_ca_topic_score_gemma":0.000023629465,"teacher_disagreement_score":0.9744531,"about_ca_system_score_codex":0.000025185496,"about_ca_system_score_gemma":0.000048573827,"threshold_uncertainty_score":0.23211414},"labels":[],"label_agreement":null},{"id":"W4402980134","doi":"10.1109/otcon60325.2024.10687796","title":"Merging Speech Recognition Capabilities with Large Language Models for Enhanced Communication and Interaction","year":2024,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Horizon College and Seminary","funders":"","keywords":"Computer science; Speech recognition; Natural language processing; Language model; Human–computer interaction; Artificial intelligence","score_opus":0.027778326045515507,"score_gpt":0.2801247445404287,"score_spread":0.2523464184949132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402980134","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.110448405,0.00022880024,0.87271714,0.0008205027,0.00009084825,0.00022728542,0.000010631904,0.00033705682,0.01511932],"genre_scores_gemma":[0.79347515,0.0000684674,0.20569082,0.00012385068,0.000016744558,0.00007554184,0.000020801823,0.000007945784,0.00052067783],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99940604,0.00004207457,0.00011732781,0.00022301676,0.00009028609,0.00012122797],"domain_scores_gemma":[0.9993466,0.00031638154,0.000024609279,0.00020518656,0.00007532303,0.000031908738],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026305672,0.000079436555,0.00008247961,0.00011163977,0.000095550946,0.00026593643,0.00011779805,0.000032377477,0.000074774085],"category_scores_gemma":[0.000028346802,0.00006329503,0.000029245452,0.00012928467,0.000019262807,0.0011874156,0.000041061445,0.00006774874,0.000019517796],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019118928,0.00003503994,0.0000015696435,0.0000953906,0.000030102558,0.0000022719194,0.004981036,0.0000058943547,0.005250083,0.024422133,0.00028703647,0.96487033],"study_design_scores_gemma":[0.00039002765,0.00009943294,0.000016951068,0.00032209026,0.000024815563,0.000058926013,0.0062444364,0.67073864,0.27749228,0.042720277,0.0016176642,0.00027447374],"about_ca_topic_score_codex":0.000050017366,"about_ca_topic_score_gemma":0.0001492404,"teacher_disagreement_score":0.96459585,"about_ca_system_score_codex":0.000030238203,"about_ca_system_score_gemma":0.000017697866,"threshold_uncertainty_score":0.25810966},"labels":[],"label_agreement":null},{"id":"W4403096752","doi":"10.1016/j.nlp.2024.100110","title":"Recent advancements in automatic disordered speech recognition: A survey paper","year":2024,"lang":"en","type":"article","venue":"Natural Language Processing Journal","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Speech recognition; Computer science","score_opus":0.024658999476806286,"score_gpt":0.301425732541467,"score_spread":0.2767667330646607,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403096752","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6130421,0.32420123,0.038124293,0.0089400895,0.006828734,0.0007230544,0.000039660317,0.0014854749,0.006615342],"genre_scores_gemma":[0.88240343,0.0012522984,0.11462845,0.00093253225,0.0002439077,0.000014858368,0.00002854163,0.000028765953,0.00046721712],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982824,0.00021009463,0.00039702817,0.00031454203,0.00045575586,0.0003401889],"domain_scores_gemma":[0.9993349,0.00015682649,0.00009874828,0.0001412547,0.00016785493,0.00010046043],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0009919,0.00017019249,0.00018730569,0.00032682173,0.00014898399,0.0010535192,0.0004268933,0.00007170017,0.0006661219],"category_scores_gemma":[0.00045959195,0.00013264484,0.000065405904,0.0010135297,0.000023183207,0.0016933995,0.000065626075,0.0006392855,0.00013975913],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000073916067,0.000044451866,0.00013323396,0.000049962477,0.000011468622,0.0004339245,0.0008501826,3.3965014e-7,0.00032459298,0.0000030229482,0.00035052415,0.99779093],"study_design_scores_gemma":[0.006093896,0.0004070984,0.06204421,0.012664181,0.00011959982,0.015556719,0.004036156,0.8196458,0.0146155935,0.017663067,0.043247703,0.0039059422],"about_ca_topic_score_codex":0.000013579957,"about_ca_topic_score_gemma":0.00013192242,"teacher_disagreement_score":0.993885,"about_ca_system_score_codex":0.00014494397,"about_ca_system_score_gemma":0.00019359516,"threshold_uncertainty_score":0.9999835},"labels":[],"label_agreement":null},{"id":"W4403863506","doi":"10.1109/taslp.2024.3487410","title":"CL-MASR: A Continual Learning Benchmark for Multilingual ASR","year":2024,"lang":"en","type":"article","venue":"IEEE/ACM Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada","keywords":"Benchmark (surveying); Computer science; Artificial intelligence; Geography","score_opus":0.017325009771891654,"score_gpt":0.2885879270057755,"score_spread":0.27126291723388385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403863506","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.057162434,0.002518234,0.93657833,0.000897426,0.0006019091,0.0003222629,0.000025641073,0.0008299385,0.001063792],"genre_scores_gemma":[0.81718975,0.00008619169,0.17949921,0.00034730052,0.0002073129,0.00007723238,0.0000071573077,0.000037358728,0.0025484518],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99834365,0.00006127085,0.0002901385,0.00063587446,0.0002643457,0.00040474723],"domain_scores_gemma":[0.9989816,0.0004327771,0.000062741994,0.00026696146,0.00009939404,0.00015651523],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041715676,0.00025048605,0.000249427,0.00031807096,0.00047357043,0.00074429746,0.00034516337,0.00013461977,0.00012967721],"category_scores_gemma":[0.00013356362,0.00022892791,0.00015766534,0.00043916944,0.000064032836,0.000550625,0.000009643331,0.00041803785,0.000042837393],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024886522,0.00005771801,0.0000044324534,0.00016765347,0.00003657906,0.00007927037,0.003599514,0.0000320732,0.007196973,0.00002331774,0.00007665654,0.9887009],"study_design_scores_gemma":[0.0021583317,0.00063011696,0.00008077669,0.0015681813,0.00022859423,0.0007812689,0.006571142,0.32276028,0.63014674,0.0014794623,0.032075558,0.0015195317],"about_ca_topic_score_codex":0.000020397556,"about_ca_topic_score_gemma":0.00004391715,"teacher_disagreement_score":0.98718137,"about_ca_system_score_codex":0.000046829253,"about_ca_system_score_gemma":0.00012882978,"threshold_uncertainty_score":0.93354094},"labels":[],"label_agreement":null},{"id":"W4404148262","doi":"10.37394/232025.2024.6.17","title":"Hubert-LSTM: A Hybrid Model for Artificial Intelligence and Human Speech","year":2024,"lang":"en","type":"article","venue":"Engineering World","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Speech recognition; Artificial intelligence","score_opus":0.0489171082153988,"score_gpt":0.26947782967047146,"score_spread":0.22056072145507266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404148262","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004115106,0.00014949117,0.9936144,0.0005111427,0.0003435597,0.000117437536,0.0000054552047,0.00046132633,0.00068208],"genre_scores_gemma":[0.7896663,0.0000045692154,0.20804301,0.00006744895,0.00013516766,0.0000374319,0.000002111038,0.000018152978,0.002025805],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99925923,0.0000044940093,0.00015646163,0.0002831881,0.00010172451,0.0001948887],"domain_scores_gemma":[0.9996155,0.000108889944,0.000010340804,0.00017370703,0.000020907237,0.000070665825],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017466323,0.000111584624,0.0001038351,0.00023629793,0.000055802815,0.00028442903,0.00021078438,0.000018330978,0.000022552937],"category_scores_gemma":[0.00003482117,0.000112103175,0.000055909997,0.00023719305,0.000011961988,0.0001929261,0.000060003276,0.000098821416,0.000039350743],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002303658,0.00002785014,0.0000030198328,0.0001234085,0.000031163094,0.000042611806,0.00031302703,0.007101423,0.0043009366,0.42523888,0.002069713,0.56074566],"study_design_scores_gemma":[0.000012941388,0.00001086557,0.000007535427,0.00006098732,0.000005434817,0.00001824091,0.0000022407041,0.9571078,0.022213291,0.016326306,0.0040929047,0.00014145485],"about_ca_topic_score_codex":0.0000032072644,"about_ca_topic_score_gemma":0.000010340521,"teacher_disagreement_score":0.95000637,"about_ca_system_score_codex":0.000023351706,"about_ca_system_score_gemma":0.00001608865,"threshold_uncertainty_score":0.45714346},"labels":[],"label_agreement":null},{"id":"W4404238744","doi":"10.1109/ijcb62174.2024.10744521","title":"On the influence of regularization techniques on label noise robustness: Self-supervised speaker verification as a use case","year":2024,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Robustness (evolution); Speaker verification; Computer science; Speech recognition; Regularization (linguistics); Speaker recognition; Artificial intelligence; Pattern recognition (psychology); Noise measurement; Noise reduction","score_opus":0.028424363915907774,"score_gpt":0.2556727641753869,"score_spread":0.22724840025947915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404238744","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8736559,0.00000885158,0.11826509,0.0022729358,0.000081881095,0.00042382206,0.0000047324725,0.00079871767,0.0044880407],"genre_scores_gemma":[0.9298693,0.000028122882,0.06830958,0.0010383758,0.000016477301,0.000055248456,0.0000030148947,0.0000125539245,0.0006673297],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989811,0.000115668445,0.00020801468,0.00031424008,0.00026913095,0.000111849185],"domain_scores_gemma":[0.9987346,0.00044297412,0.000046554607,0.0005811882,0.00015402466,0.00004064862],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003233375,0.0001170676,0.00009324399,0.00016497448,0.00008630255,0.00027192474,0.00029947667,0.00007034691,0.000089196175],"category_scores_gemma":[0.00023487445,0.00007700506,0.000045545232,0.0006035271,0.000033177384,0.00054225436,0.000044132794,0.000100380086,0.00012441874],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003667453,0.00051111996,0.000051168532,0.00009270987,0.00006749747,0.0003957728,0.0012952014,0.00056588737,0.024740256,0.7215092,0.0023524698,0.24838203],"study_design_scores_gemma":[0.00019949937,0.00028869833,0.0006056028,0.000403464,0.0000345107,0.00046699055,0.000097938675,0.66509974,0.3237585,0.0067349263,0.0019458169,0.00036427125],"about_ca_topic_score_codex":0.000072922805,"about_ca_topic_score_gemma":0.000007981025,"teacher_disagreement_score":0.7147743,"about_ca_system_score_codex":0.000040925566,"about_ca_system_score_gemma":0.000056427056,"threshold_uncertainty_score":0.31401753},"labels":[],"label_agreement":null},{"id":"W4404589970","doi":"10.1007/978-3-031-77961-9_5","title":"Advances in OpenASR21 Evaluation with Increased Temporal Resolution for Speech Self-supervised Learning Models","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Resolution (logic); Artificial intelligence; Speech recognition; Machine learning","score_opus":0.038711057289161604,"score_gpt":0.27545460294724594,"score_spread":0.23674354565808434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404589970","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00035905783,0.0011297801,0.9874508,0.00037357272,0.00056547986,0.0013112152,0.0000053510453,0.0002535281,0.0085512465],"genre_scores_gemma":[0.124968566,0.00016350445,0.87398463,0.00030600934,0.00024450803,0.0001223819,0.00002854539,0.000048904665,0.00013292019],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99590826,0.000095216266,0.00052396423,0.0016029072,0.0013137927,0.00055583025],"domain_scores_gemma":[0.99796003,0.0005774779,0.00021636681,0.0006436358,0.00047321964,0.00012927759],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0026048475,0.00046675946,0.00049596274,0.0012139315,0.00021873905,0.00065015885,0.0014617669,0.00026833598,0.000022562586],"category_scores_gemma":[0.00013588507,0.0003964854,0.00011245277,0.00088481646,0.00020460326,0.00166029,0.0003915863,0.0006709921,0.000025242975],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002982224,0.00003513954,0.000037520138,0.00009107607,0.000009298729,0.00004729668,0.0006163456,0.07836431,0.00003639692,0.006350562,0.0000040206637,0.9143782],"study_design_scores_gemma":[0.0005212908,0.00017290868,0.000013427258,0.0007184703,0.000018226585,0.00004586507,0.0000011880935,0.82007545,0.0004789697,0.1768142,0.00069650705,0.0004435214],"about_ca_topic_score_codex":0.00005417178,"about_ca_topic_score_gemma":0.00042352057,"teacher_disagreement_score":0.9139347,"about_ca_system_score_codex":0.00058047695,"about_ca_system_score_gemma":0.00087290537,"threshold_uncertainty_score":0.9998487},"labels":[],"label_agreement":null},{"id":"W4404591500","doi":"10.1007/978-3-031-78014-1_12","title":"On the Influence of CNN-Based Feature Learning Modules in Neural Speaker Verification Framework","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Speaker verification; Feature (linguistics); Speech recognition; Artificial intelligence; Artificial neural network; Speaker recognition; Pattern recognition (psychology)","score_opus":0.016975000110396377,"score_gpt":0.24203839625826967,"score_spread":0.2250633961478733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404591500","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013920985,0.00025349134,0.9786598,0.004231932,0.0007290024,0.00035535934,0.000003867147,0.00012498916,0.0017205515],"genre_scores_gemma":[0.8847897,0.00001863532,0.11311833,0.001739478,0.000094991345,0.000012860109,0.000002405519,0.000024651134,0.00019895718],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99713683,0.00007731966,0.0003897135,0.0010549302,0.0009589178,0.00038225873],"domain_scores_gemma":[0.99651545,0.0019751561,0.0002331127,0.0010153265,0.0001879244,0.00007304419],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009252069,0.00037343384,0.00035920122,0.0008968268,0.00013742445,0.0004119223,0.0022714066,0.00034100504,0.00003094181],"category_scores_gemma":[0.00060327497,0.00027032793,0.00013082217,0.001111141,0.0005026158,0.00025468634,0.00033603155,0.0016792007,0.00007007055],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013259164,0.000033366687,0.00013989604,0.00006157352,0.000008356716,0.00005641955,0.0007086839,0.43017483,0.00027151147,0.089990556,0.000017949185,0.47852358],"study_design_scores_gemma":[0.00007834794,0.00009960617,0.0019481493,0.0013610979,0.000005236721,0.000011352287,4.990696e-7,0.8013891,0.0019061927,0.19252618,0.0003371083,0.00033709855],"about_ca_topic_score_codex":0.000016793021,"about_ca_topic_score_gemma":0.000030202516,"teacher_disagreement_score":0.8708687,"about_ca_system_score_codex":0.00016286269,"about_ca_system_score_gemma":0.00017967724,"threshold_uncertainty_score":0.9999749},"labels":[],"label_agreement":null},{"id":"W4404782836","doi":"10.18653/v1/2024.emnlp-main.1231","title":"Is Child-Directed Speech Effective Training Data for Language Models?","year":2024,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Training (meteorology); Speech recognition; Training set; Language model; Natural language processing; Artificial intelligence","score_opus":0.07857330905148112,"score_gpt":0.31690856967814024,"score_spread":0.2383352606266591,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404782836","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013486197,0.0003935061,0.9211935,0.0017926232,0.00042692496,0.00043959587,0.00013930206,0.0015505854,0.07271539],"genre_scores_gemma":[0.34195936,0.000026252874,0.6517991,0.0022145405,0.00033911827,0.00010846913,0.00010894861,0.000036864745,0.0034073556],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99891037,0.000036334717,0.00012290767,0.00055738154,0.00015952098,0.0002134727],"domain_scores_gemma":[0.9988096,0.0004044198,0.000015765181,0.0006672831,0.00003666275,0.000066267734],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000365873,0.000114133276,0.00013581062,0.00012386045,0.00008067659,0.00031821642,0.0007952713,0.000051160216,0.00020306822],"category_scores_gemma":[0.00009418408,0.00009264739,0.00007109174,0.0003265959,0.000014684815,0.00076801376,0.00020222054,0.000089456415,0.00014266909],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000028080524,0.000016650547,5.7493605e-7,0.000029859866,0.000050655533,0.000023701466,0.0020865528,0.0000012757667,0.00019505231,0.007766537,0.009704616,0.98012173],"study_design_scores_gemma":[0.00015126467,0.000025489118,0.000021319172,0.000084418534,0.0000149941125,0.000053251853,0.00023773291,0.9742091,0.010307984,0.0053998507,0.009331608,0.00016302847],"about_ca_topic_score_codex":0.000032283882,"about_ca_topic_score_gemma":0.00002285519,"teacher_disagreement_score":0.9799587,"about_ca_system_score_codex":0.000019608346,"about_ca_system_score_gemma":0.000038734106,"threshold_uncertainty_score":0.37780508},"labels":[],"label_agreement":null},{"id":"W4404783544","doi":"10.18653/v1/2024.emnlp-main.302","title":"Improving Spoken Language Modeling with Phoneme Classification: A Simple Fine-tuning Approach","year":2024,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Agence de l'innovation de Défense; Grand Équipement National De Calcul Intensif; Agence Nationale de la Recherche; École des Hautes Etudes en Sciences Sociales; Canadian Institute for Advanced Research","keywords":"Computer science; Simple (philosophy); Spoken language; Speech recognition; Natural language processing; Language model; Artificial intelligence; Fine-tuning","score_opus":0.03837804051959954,"score_gpt":0.25130765712570646,"score_spread":0.21292961660610693,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404783544","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013288553,0.00013729383,0.94688445,0.00035426478,0.00006580498,0.000102885504,0.0000015259166,0.0007115169,0.038453724],"genre_scores_gemma":[0.68828475,0.0000021892474,0.31071526,0.00013267255,0.000071125716,0.00002387136,0.000007157409,0.0000120899085,0.0007508492],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99897856,0.000026399808,0.00015381548,0.00041334023,0.00022022081,0.0002076545],"domain_scores_gemma":[0.99944633,0.00006354808,0.000023299277,0.00034933875,0.000044243134,0.00007324018],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023596031,0.00011735893,0.00010682142,0.00013879908,0.000098895536,0.00046702832,0.00034939704,0.000041975687,0.00012263689],"category_scores_gemma":[0.000022192206,0.0000863665,0.00004743193,0.00044888826,0.000014656129,0.000470158,0.00008168943,0.0001238222,0.00011714374],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000071444156,0.000059841048,0.00003322972,0.0001109043,0.000046216028,0.000076451026,0.0025181698,0.0006205826,0.010903113,0.050333753,0.00063737936,0.9346532],"study_design_scores_gemma":[0.000085435255,0.00001446399,0.000012008668,0.000021894793,0.0000072193607,0.000046824516,0.00077362795,0.9967368,0.0015809984,0.00022640153,0.00034323471,0.00015108782],"about_ca_topic_score_codex":0.00010182452,"about_ca_topic_score_gemma":0.00002223048,"teacher_disagreement_score":0.9961162,"about_ca_system_score_codex":0.00003289855,"about_ca_system_score_gemma":0.00007556185,"threshold_uncertainty_score":0.45035648},"labels":[],"label_agreement":null},{"id":"W4404903811","doi":"10.61618/ssov3472","title":"Voice Calling Detection Distance in Land Search and Rescue","year":2024,"lang":"en","type":"article","venue":"The Journal of Search and Rescue","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Search and rescue; Computer science; Speech recognition; Artificial intelligence","score_opus":0.029450898186600908,"score_gpt":0.28431550182374954,"score_spread":0.25486460363714863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404903811","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93417394,0.0039061434,0.059461333,0.0021591247,0.00011806354,0.00006465438,0.0000013850853,0.000012738666,0.000102621154],"genre_scores_gemma":[0.9949859,0.0034644057,0.0012626717,0.00004415632,0.00011270342,6.259624e-7,7.150095e-8,0.000004926325,0.00012458344],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989711,0.00024365603,0.00018703837,0.00011147141,0.0003025999,0.00018412605],"domain_scores_gemma":[0.99943537,0.0002722766,0.00000851521,0.00010528054,0.000075217446,0.00010331781],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002136633,0.00006335388,0.00010855668,0.0001901702,0.00011861988,0.0002203566,0.00022176786,0.00003698171,0.000005581009],"category_scores_gemma":[0.000064559914,0.000036847137,0.00002761505,0.0002944551,0.0000761825,0.0002804264,0.000080010366,0.00044028743,0.0000066044313],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027784077,0.000053019285,0.0012767197,0.00021782189,0.00006762329,0.00045160978,0.0052508167,0.0006899582,0.029517105,0.00062117993,0.000055829107,0.9615205],"study_design_scores_gemma":[0.0016023257,0.0008154087,0.07696748,0.0018247862,0.000044102424,0.0039891982,0.002291088,0.80537146,0.0992777,0.0035656686,0.003790452,0.00046033753],"about_ca_topic_score_codex":0.00033678795,"about_ca_topic_score_gemma":0.0010710644,"teacher_disagreement_score":0.96106017,"about_ca_system_score_codex":0.000030429834,"about_ca_system_score_gemma":0.000062926316,"threshold_uncertainty_score":0.21249036},"labels":[],"label_agreement":null},{"id":"W4405013581","doi":"10.1007/978-3-031-78122-3_7","title":"CAB-KWS : Contrastive Augmentation: An Unsupervised Learning Approach for Keyword Spotting in Speech Technology","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Keyword spotting; Computer science; Spotting; Speech recognition; Artificial intelligence; Natural language processing","score_opus":0.024741399971856606,"score_gpt":0.26446691578312764,"score_spread":0.23972551581127105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405013581","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007556862,0.00027437718,0.9911785,0.00076663005,0.000810426,0.00083931675,0.0000070583746,0.00037073388,0.004997267],"genre_scores_gemma":[0.108124405,0.00002378378,0.8902602,0.00050616416,0.00032883036,0.000083069855,0.000023202098,0.00005212708,0.0005981731],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961514,0.00004851886,0.0006033243,0.001870947,0.0006176712,0.00070816407],"domain_scores_gemma":[0.9982336,0.00049695605,0.00020399883,0.0006457626,0.0002834167,0.00013624292],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011980797,0.00051017525,0.00060201547,0.0020830333,0.00025189464,0.0006761291,0.0020510645,0.00046657858,0.00002744153],"category_scores_gemma":[0.00015175164,0.0004942025,0.00013164831,0.0013077988,0.00044878153,0.0006197639,0.0005763428,0.0011059293,0.00002762169],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000114090835,0.00004188545,0.000089715635,0.00006641815,0.0000140875,0.00010393327,0.0010518123,0.0070070312,0.00027977955,0.01279348,0.000003811473,0.97853667],"study_design_scores_gemma":[0.00047184507,0.00022492184,0.000047993693,0.00038684416,0.0000130051085,0.00012089747,0.000009834035,0.89221686,0.0029409062,0.10250766,0.00045060946,0.0006086185],"about_ca_topic_score_codex":0.000018830939,"about_ca_topic_score_gemma":0.00007019066,"teacher_disagreement_score":0.97792804,"about_ca_system_score_codex":0.00037606002,"about_ca_system_score_gemma":0.00036361787,"threshold_uncertainty_score":0.999751},"labels":[],"label_agreement":null},{"id":"W4405365437","doi":"10.1016/j.specom.2024.103167","title":"Spoken language identification: An overview of past and present research trends","year":2024,"lang":"en","type":"article","venue":"Speech Communication","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Spoken language; Computer science; Identification (biology); Natural language processing; Language identification; Speech recognition; Linguistics; Artificial intelligence; Natural language","score_opus":0.19144291836526953,"score_gpt":0.4379504369399535,"score_spread":0.24650751857468398,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405365437","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6488012,0.14645746,0.022164207,0.05016714,0.0008082131,0.0012946988,0.00008781446,0.0016901932,0.12852909],"genre_scores_gemma":[0.9671032,0.002825239,0.028344827,0.00003398583,0.000061625055,0.000033227283,0.00004005709,0.000011220163,0.0015466404],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99851996,0.0004664478,0.00024457902,0.00025351657,0.00038225215,0.00013323544],"domain_scores_gemma":[0.99801993,0.00029048993,0.00004684694,0.0014105913,0.00016806582,0.00006408406],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017656967,0.00007097732,0.000105620784,0.00039043292,0.00012084414,0.00030690254,0.0009475507,0.00005124403,0.000103377584],"category_scores_gemma":[0.000051412324,0.00006675932,0.000037799466,0.00093832595,0.00010504351,0.0006021062,0.0003448849,0.00017914898,0.000068193636],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020776495,0.000059986214,0.00004552211,0.000052261294,0.000011592979,0.0000037943742,0.0017248981,3.3358396e-7,0.003191674,0.037721872,0.001329001,0.955857],"study_design_scores_gemma":[0.0010051787,0.0005045357,0.10027098,0.0017439759,0.00009660867,0.00033314843,0.005574261,0.19141872,0.35894305,0.08344856,0.2554072,0.00125377],"about_ca_topic_score_codex":0.00014703561,"about_ca_topic_score_gemma":0.00006302957,"teacher_disagreement_score":0.9546032,"about_ca_system_score_codex":0.00003343778,"about_ca_system_score_gemma":0.00003187745,"threshold_uncertainty_score":0.29594684},"labels":[],"label_agreement":null},{"id":"W4406080107","doi":"10.1016/j.rineng.2025.103943","title":"Automated speech therapy through personalized pronunciation correction using reinforcement learning and large language models","year":2025,"lang":"en","type":"article","venue":"Results in Engineering","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Pronunciation; Computer science; Reinforcement learning; Natural language processing; Reinforcement; Speech therapy; Speech recognition; Artificial intelligence; Linguistics; Psychology; Audiology; Medicine; Social psychology","score_opus":0.018812858151487085,"score_gpt":0.27529237021562325,"score_spread":0.25647951206413616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406080107","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.084398754,0.00029641358,0.9113637,0.000052675285,0.0003118242,0.0001984865,9.023625e-7,0.0005836612,0.0027935528],"genre_scores_gemma":[0.95743513,0.00013550076,0.04199276,0.000060021826,0.000020703337,0.000012080547,0.000005788477,0.000007808921,0.0003302031],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992457,0.000033288063,0.00020125856,0.00020684872,0.00013442944,0.00017849442],"domain_scores_gemma":[0.99971807,0.000080799735,0.00004755404,0.00010235349,0.0000340456,0.000017178367],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033789422,0.00009801624,0.000115807044,0.00016868334,0.0000621828,0.00007694454,0.00008797126,0.000057746118,0.000002930697],"category_scores_gemma":[0.00014187193,0.00009887595,0.00002403069,0.0003918605,0.0000051947413,0.00035592992,0.000043868764,0.00012327537,0.000001374547],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012145681,0.000092521,0.00025243644,0.000111139336,0.00006494515,0.000039362007,0.016223634,0.7638669,0.023020852,0.0054605175,0.00012023234,0.19062601],"study_design_scores_gemma":[0.00090916886,0.000012783661,0.000118092794,0.00014128555,0.000002050518,0.0000057654197,0.00020126064,0.987318,0.010430779,0.00003919889,0.00072212017,0.000099485726],"about_ca_topic_score_codex":0.0000621216,"about_ca_topic_score_gemma":0.0000050994113,"teacher_disagreement_score":0.8730364,"about_ca_system_score_codex":0.0001232192,"about_ca_system_score_gemma":0.000026255606,"threshold_uncertainty_score":0.4032044},"labels":[],"label_agreement":null},{"id":"W4406201495","doi":"10.1002/alz.089917","title":"Transformer‐based Deep Learning Architecture Improves Detection of Associations between Spontaneous Speech Language Markers and Cognition","year":2024,"lang":"en","type":"article","venue":"Alzheimer s & Dementia","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Cognition; Transformer; Natural language processing; Language model; Speech recognition; Artificial intelligence; Psychology","score_opus":0.012782707561069891,"score_gpt":0.24264903214625397,"score_spread":0.22986632458518408,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406201495","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27003562,0.019815113,0.70513225,0.00051981333,0.00040837715,0.00054361165,0.000067895984,0.00058832194,0.002888982],"genre_scores_gemma":[0.98405975,0.000028579781,0.015723923,0.00005662363,0.00005038559,0.000012952558,0.000047207133,0.000014768533,0.0000057902316],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998919,0.000117718024,0.0002394449,0.0002987548,0.00023160197,0.00019345917],"domain_scores_gemma":[0.99940765,0.0002855885,0.00007214672,0.00012214265,0.000048210928,0.00006423743],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033447295,0.00013348662,0.0001556033,0.00021612893,0.00012624881,0.00014072255,0.00013807,0.00008350641,0.000049415772],"category_scores_gemma":[0.000033132772,0.0001311712,0.000096842734,0.00030103102,0.00003677589,0.00021044485,0.000019996363,0.00018803112,0.000020059497],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006645658,0.000015197914,0.000054524233,0.000010920429,0.0013872643,0.000037655398,0.0005232467,0.0000047761814,0.051726174,0.000034276567,0.000004072414,0.94619524],"study_design_scores_gemma":[0.00073397375,0.00041644595,0.020218862,0.00012640945,0.009529373,0.00018020203,0.0004478953,0.024013238,0.93985665,0.0021678333,0.001646173,0.00066296273],"about_ca_topic_score_codex":0.0000822921,"about_ca_topic_score_gemma":0.0001428358,"teacher_disagreement_score":0.94553226,"about_ca_system_score_codex":0.000007372274,"about_ca_system_score_gemma":0.000028604129,"threshold_uncertainty_score":0.5349006},"labels":[],"label_agreement":null},{"id":"W4406344031","doi":"10.1121/10.0035261","title":"Three-dimensional finite element acoustic analysis of bent vocal tracts","year":2024,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Bent molecular geometry; Finite element method; Acoustics; Element (criminal law); Structural engineering; Geology; Computer science; Physics; Engineering; Political science","score_opus":0.01954315128730221,"score_gpt":0.26168890968996733,"score_spread":0.2421457584026651,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406344031","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00851342,0.00044441913,0.9843316,0.00622985,0.00030627448,0.00007741606,0.000017576604,0.000015384347,0.00006406125],"genre_scores_gemma":[0.854751,0.0001705979,0.1436855,0.0012517376,0.000095453695,0.0000010277402,5.675807e-7,0.000008854673,0.0000352554],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978579,0.00013357955,0.00066023844,0.0001372109,0.0009901918,0.00022083838],"domain_scores_gemma":[0.9966282,0.0022240866,0.00041066064,0.00038291924,0.0002522278,0.0001019066],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010239191,0.00013789308,0.000437711,0.000090311594,0.00010857611,0.00003949447,0.0010462437,0.00005681063,0.00021072192],"category_scores_gemma":[0.00024608892,0.000069814494,0.0010810681,0.0013047911,0.00037265234,0.00012329257,0.0002506051,0.00037225347,0.0000074192317],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018606201,0.0011562369,0.00022650308,0.00019926344,0.011263098,0.000026360907,0.002452648,0.370821,0.03982941,0.00029184655,0.06253626,0.5110113],"study_design_scores_gemma":[0.00011924448,0.00016756888,0.0019952566,0.00009634976,0.0019373902,0.000027486572,0.00019405068,0.99198735,0.0016722017,0.0011761897,0.0005430944,0.000083843755],"about_ca_topic_score_codex":0.000029480167,"about_ca_topic_score_gemma":0.0000029217663,"teacher_disagreement_score":0.8462376,"about_ca_system_score_codex":0.00006342183,"about_ca_system_score_gemma":0.00017248672,"threshold_uncertainty_score":0.28469524},"labels":[],"label_agreement":null},{"id":"W4406453155","doi":"10.1016/s0967-0653(98)82019-x","title":"10.1016/s0967-0653(98)82019-x","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Track (disk drive); Matching (statistics); Multipath propagation; Correlation; Computer science; Statistics; Telecommunications; Mathematics; Geometry","score_opus":0.010475086020867306,"score_gpt":0.1818329516253262,"score_spread":0.1713578656044589,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406453155","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000039266568,0.000020453232,0.00024097785,0.0008283611,0.0000032894686,0.000110132074,0.0000044175085,0.00030050328,0.9984526],"genre_scores_gemma":[0.00001801998,3.0095106e-7,0.007386772,0.0001874008,0.000081877275,0.000014946871,0.0000025740326,0.000011005657,0.9922971],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99900544,0.000051033745,0.00015547058,0.00030107825,0.0002245372,0.00026244842],"domain_scores_gemma":[0.9992342,0.00007024685,0.000022711254,0.00044884082,0.00004614099,0.00017785955],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0001627949,0.00012191273,0.00014279703,0.000092471666,0.000081496015,0.0001358436,0.0006347233,0.00005382009,0.9988949],"category_scores_gemma":[0.000032650183,0.000115388706,0.00007269225,0.00030481824,0.000019531639,0.00023437006,0.00006459436,0.00007569043,0.9997386],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000060513244,0.000026183214,5.604071e-9,0.0000011214457,0.000005364611,0.000006034813,0.000013065169,0.0000022662225,0.0000080139525,0.0000062434847,0.2362184,0.7637073],"study_design_scores_gemma":[0.00012423517,0.000056614655,0.00000737732,0.000010967199,0.000004381018,0.00001678652,4.3459136e-7,0.0016785497,0.00076538225,0.0000580483,0.997105,0.00017221336],"about_ca_topic_score_codex":0.000011236633,"about_ca_topic_score_gemma":1.7770499e-7,"teacher_disagreement_score":0.763535,"about_ca_system_score_codex":0.000024079804,"about_ca_system_score_gemma":0.000027331485,"threshold_uncertainty_score":0.47054148},"labels":[],"label_agreement":null},{"id":"W4406565803","doi":"10.1016/j.endend.2012.08.088","title":"10.1016/j.endend.2012.08.088","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"End-to-end principle; Test (biology); Computer science; Biology; Artificial intelligence","score_opus":0.010125527640857635,"score_gpt":0.17918364752398241,"score_spread":0.16905811988312477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406565803","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006902204,0.0000292499,0.00033836495,0.00078487035,0.0000039222123,0.00009970156,0.0000050873628,0.00030959066,0.9983602],"genre_scores_gemma":[0.00005285273,3.075622e-7,0.0073169908,0.00018741329,0.00009110087,0.000015827116,0.0000023294433,0.00001119209,0.99232197],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989695,0.000052596042,0.00015602307,0.00030584217,0.00023991529,0.00027611235],"domain_scores_gemma":[0.9992133,0.00007441324,0.000023759843,0.00045565743,0.000044527147,0.00018839263],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0001646722,0.00012332667,0.00013578628,0.000102915204,0.00008545838,0.00013340285,0.0006358008,0.00005383715,0.9976544],"category_scores_gemma":[0.000030306137,0.00011727645,0.00007299641,0.00029798123,0.000019374766,0.00032056862,0.00007466657,0.00007780089,0.99838495],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005883422,0.000028846103,1.8399957e-8,0.0000011063805,0.000005998911,0.000008200276,0.000011607578,0.0000022325503,0.000022436156,0.000008258007,0.20345621,0.7964492],"study_design_scores_gemma":[0.00012352127,0.000052465522,0.000023676532,0.000009815502,0.0000043448267,0.000026675547,4.65415e-7,0.0015861248,0.00078084675,0.00006437695,0.9971552,0.00017252371],"about_ca_topic_score_codex":0.0000070020365,"about_ca_topic_score_gemma":1.8371702e-7,"teacher_disagreement_score":0.7962767,"about_ca_system_score_codex":0.00002433118,"about_ca_system_score_gemma":0.00002826765,"threshold_uncertainty_score":0.4782395},"labels":[],"label_agreement":null},{"id":"W4407130456","doi":"10.1109/icit63607.2024.10860229","title":"Streamlining Attendance with Voice Recognition via Gaussian Mixture Model","year":2024,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Computer science; Speech recognition; Mixture model; Gaussian; Attendance; Gaussian process; Artificial intelligence; Pattern recognition (psychology); Physics","score_opus":0.025188535148869814,"score_gpt":0.24478488790510933,"score_spread":0.2195963527562395,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407130456","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034438912,0.000089046225,0.94989514,0.0025496904,0.00017048843,0.00008814705,0.0000068977906,0.00073503377,0.04302166],"genre_scores_gemma":[0.39795843,0.000017266428,0.59775394,0.0011200621,0.000100301346,0.000027234508,0.0000111710115,0.000019902418,0.0029916845],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989213,0.000029455588,0.00014744172,0.00044804558,0.00023276104,0.00022102449],"domain_scores_gemma":[0.9994464,0.000097692995,0.00002735489,0.0002638491,0.00006697674,0.00009775878],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00014608202,0.0001429941,0.0001136717,0.00012461035,0.00008638212,0.00031652575,0.00027530544,0.00006498402,0.00016322815],"category_scores_gemma":[0.0000139005615,0.000103022314,0.000054472654,0.00041228702,0.000025475483,0.0006918009,0.000045211975,0.00015915124,0.0008047274],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005668918,0.000027841486,0.000022946399,0.000028273489,0.00002684932,0.000067314344,0.00022796715,0.000040635303,0.0006772697,0.0023945442,0.0020170799,0.9944636],"study_design_scores_gemma":[0.00011795599,0.000049397655,0.00006907093,0.00017717581,0.000015022437,0.00012770256,0.000043888107,0.9797424,0.009065945,0.009043706,0.0012918197,0.0002559211],"about_ca_topic_score_codex":0.000020123185,"about_ca_topic_score_gemma":0.000076949145,"teacher_disagreement_score":0.9942077,"about_ca_system_score_codex":0.000028008744,"about_ca_system_score_gemma":0.000067134504,"threshold_uncertainty_score":0.99997324},"labels":[],"label_agreement":null},{"id":"W4407561023","doi":"10.3390/app15042002","title":"Speaker Diarization: A Review of Objectives and Methods","year":2025,"lang":"en","type":"review","venue":"Applied Sciences","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Speaker diarisation; Computer science; Speech recognition; Speaker recognition","score_opus":0.05587897824479983,"score_gpt":0.4048335960937901,"score_spread":0.3489546178489903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407561023","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[8.305959e-9,0.83968353,0.09242075,0.000064683816,0.00013170109,0.00043457915,0.0000032258824,0.00003771335,0.06722379],"genre_scores_gemma":[1.174552e-7,0.76929754,0.23023757,0.00024103465,0.000016079506,0.000074327545,0.0000014626148,0.0000028769723,0.00012897972],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981904,0.0003061462,0.00047455257,0.0005838399,0.00028108977,0.00016394973],"domain_scores_gemma":[0.9978654,0.001365389,0.0003094325,0.0003506689,0.000056413497,0.000052742882],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020339112,0.00020994102,0.0011374322,0.00028379037,0.0001336214,0.000101022146,0.0009841542,0.000088723566,0.00005295006],"category_scores_gemma":[0.0003619236,0.00014615792,0.00016881434,0.002027708,0.00031175776,0.00013923783,0.00031452577,0.00010440294,0.000013645809],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.882835e-8,0.000007764287,1.3560876e-7,0.025887592,0.000013009766,3.4246668e-7,0.000018250606,6.5222614e-9,3.903749e-7,0.035416238,0.0001591626,0.93849707],"study_design_scores_gemma":[0.000029815164,0.000014995109,0.000001669865,0.061536975,0.00015687082,0.000014660112,0.0000134205675,0.000028309607,0.00005071706,0.0036741658,0.9342306,0.00024780404],"about_ca_topic_score_codex":0.0000016625585,"about_ca_topic_score_gemma":4.9208404e-7,"teacher_disagreement_score":0.93824923,"about_ca_system_score_codex":0.00001380482,"about_ca_system_score_gemma":0.00044452192,"threshold_uncertainty_score":0.5960147},"labels":[],"label_agreement":null},{"id":"W4407735899","doi":"10.1109/twc.2025.3535714","title":"Latent Diffusion Model-Enabled Low-Latency Semantic Communication in the Presence of Semantic Ambiguities and Wireless Channel Noises","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Wireless Communications","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Wireless; Channel (broadcasting); Latency (audio); Computer network; Telecommunications","score_opus":0.030945437271525045,"score_gpt":0.26260520276381677,"score_spread":0.23165976549229172,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407735899","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31713524,0.00028255786,0.67482156,0.00607965,0.00009893284,0.0005849975,0.00001779707,0.00010679995,0.0008724785],"genre_scores_gemma":[0.98939455,0.0059572426,0.0038238713,0.0002838692,0.0000025889135,0.0002862282,0.000005909047,0.000011910905,0.0002338609],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997963,0.00062236347,0.0005673178,0.00030918946,0.00029174687,0.00024638476],"domain_scores_gemma":[0.995717,0.0011625456,0.0001474226,0.0027331128,0.00019175495,0.000048157577],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005883682,0.00021182589,0.00031661004,0.00046676325,0.0007024538,0.00014118834,0.00253658,0.00011661898,0.000005373162],"category_scores_gemma":[0.000019658539,0.00018013324,0.00010926485,0.0009960886,0.0003901561,0.0004367129,0.00006405025,0.00044593037,0.000006382028],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025885645,0.014588546,0.0008258167,0.0017393198,0.0006041069,0.000018029714,0.056240004,0.08137244,0.045084264,0.22965102,0.0005219827,0.5690956],"study_design_scores_gemma":[0.0005114096,0.00003318343,0.0016378429,0.000758873,0.000047009475,0.000009175505,0.0008767432,0.98276216,0.008410184,0.0047368226,0.0000137782135,0.00020281998],"about_ca_topic_score_codex":0.0005705766,"about_ca_topic_score_gemma":0.0013260755,"teacher_disagreement_score":0.9013897,"about_ca_system_score_codex":0.000049426846,"about_ca_system_score_gemma":0.000099510056,"threshold_uncertainty_score":0.73456204},"labels":[],"label_agreement":null},{"id":"W4407901436","doi":"10.1109/ictis62692.2024.10894357","title":"Transformer-Based Multi-Head Attention for Noisy Speech Recognition","year":2024,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Computer science; Speech recognition; Transformer; Artificial intelligence; Engineering; Electrical engineering; Voltage","score_opus":0.08409056606303837,"score_gpt":0.31579167348323833,"score_spread":0.23170110742019995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407901436","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009429437,0.000050816263,0.98112845,0.0024901489,0.0007042745,0.00041689991,0.00002800137,0.00073055964,0.00502142],"genre_scores_gemma":[0.14427488,0.000017316277,0.8521585,0.0008604226,0.00012252868,0.00017622042,0.000071443676,0.000022817976,0.0022958652],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989519,0.000031128075,0.00021805137,0.00039258017,0.00017862527,0.00022768916],"domain_scores_gemma":[0.99942905,0.00019291339,0.000019829708,0.00017854049,0.00010290502,0.00007673526],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00031915013,0.00012635518,0.00011443898,0.00021375685,0.00009168625,0.0002843113,0.00021372142,0.00008215991,0.0003346228],"category_scores_gemma":[0.000035662353,0.000109235494,0.00021039389,0.0003231405,0.000018499577,0.0005559568,0.000006972776,0.00007473925,0.00085555954],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000071009144,0.00007667484,0.000011834537,0.00006748838,0.0000139023505,0.000007397383,0.00002756805,4.1884456e-7,0.00820252,0.00082424446,0.0010655182,0.9896953],"study_design_scores_gemma":[0.0012030723,0.00019735744,0.00058109796,0.00022333243,0.000043754004,0.0000400163,0.000047234345,0.6365107,0.31819367,0.0055854493,0.03690025,0.00047401703],"about_ca_topic_score_codex":0.000017945898,"about_ca_topic_score_gemma":0.000074434574,"teacher_disagreement_score":0.98922133,"about_ca_system_score_codex":0.00004145281,"about_ca_system_score_gemma":0.00006214737,"threshold_uncertainty_score":0.9999224},"labels":[],"label_agreement":null},{"id":"W4408132766","doi":"10.1007/978-3-031-82156-1_12","title":"An RNN-LSTM Approach for Algerian Accent Identification","year":2025,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Stress (linguistics); Identification (biology); Computer science; Natural language processing; Artificial intelligence; Speech recognition; Botany; Biology","score_opus":0.05676930210946809,"score_gpt":0.31504300315739775,"score_spread":0.2582737010479297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408132766","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000005437626,0.00009115043,0.82625145,0.0005524912,0.00025470785,0.00061976333,0.000028392758,0.00010684646,0.17208974],"genre_scores_gemma":[0.009291877,0.001337587,0.98415023,0.0016206366,0.000054372107,0.00021740464,0.00038040525,0.000010273277,0.002937224],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981923,0.00003997755,0.0007683118,0.00040660953,0.00036783985,0.00022495934],"domain_scores_gemma":[0.99610984,0.00020475575,0.00035720613,0.002594831,0.0006164469,0.00011692015],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0014621245,0.00021444946,0.00024559803,0.0012517798,0.0006135345,0.0013318599,0.0042487774,0.0001495881,0.000007377265],"category_scores_gemma":[0.000069809816,0.00022346676,0.000066522734,0.00045356402,0.0004413423,0.007472365,0.0009776579,0.0002329778,0.000021481963],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000015233544,0.000024486575,0.0000034243712,0.00002565701,0.0000037109342,3.441914e-8,0.0003710719,0.000027572289,0.0000063036173,0.46457833,0.00031859477,0.5346393],"study_design_scores_gemma":[0.0002457681,0.00003564609,0.0004230183,0.000084495776,0.0000085408,0.000008525396,0.000028725153,0.8788283,0.000084982654,0.010379687,0.109568164,0.0003041335],"about_ca_topic_score_codex":0.000005626891,"about_ca_topic_score_gemma":0.0000036006081,"teacher_disagreement_score":0.87880075,"about_ca_system_score_codex":0.0001478424,"about_ca_system_score_gemma":0.00033648568,"threshold_uncertainty_score":0.99970484},"labels":[],"label_agreement":null},{"id":"W4408267680","doi":"10.20865/202510701","title":"A Study on Final Devoicing in Russian through Quantitative Analysis","year":2025,"lang":"en","type":"article","venue":"Language and Linguistics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Linguistics; History; Computer science; Philosophy","score_opus":0.0490464943126742,"score_gpt":0.3590970564083973,"score_spread":0.31005056209572307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408267680","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7218053,0.00032510646,0.14643638,0.00024738858,0.00037136461,0.00024409492,0.000007827062,0.00010728887,0.13045526],"genre_scores_gemma":[0.9681408,0.0000058202236,0.031142628,0.00042907282,0.000031432905,0.0000049925725,0.0000016512358,0.000002222882,0.0002414139],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9993478,0.00006768427,0.00014873041,0.00022210594,0.000097088465,0.00011660069],"domain_scores_gemma":[0.99944335,0.0002761108,0.000032511278,0.00019661838,0.000030333338,0.000021084343],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016435608,0.000079087375,0.00016929231,0.00025483442,0.00006220923,0.00007794657,0.00015023122,0.00002759731,0.000009756151],"category_scores_gemma":[0.00088094856,0.00006850397,0.000035840272,0.00083925156,0.000015305204,0.000018325898,0.000053680742,0.00009341425,0.0000076282317],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048212067,0.0009317773,0.069867745,0.00003485787,0.0005725143,0.001586662,0.09443669,0.000079573714,0.00003867837,0.7870521,0.00012785486,0.04522335],"study_design_scores_gemma":[0.0049289414,0.0014446847,0.70452887,0.0005870874,0.0013914836,0.000008942056,0.1251585,0.11332636,0.0040347027,0.036189508,0.006798864,0.0016020513],"about_ca_topic_score_codex":0.00029392462,"about_ca_topic_score_gemma":0.0006533245,"teacher_disagreement_score":0.7508626,"about_ca_system_score_codex":0.000015538073,"about_ca_system_score_gemma":0.00002143077,"threshold_uncertainty_score":0.2793511},"labels":[],"label_agreement":null},{"id":"W4408352315","doi":"10.1109/icassp49660.2025.10888434","title":"Large-Scale Recurrent Neural Networks with Fully Homomorphic Encryption for Privacy-Enhanced Speaker Identification","year":2025,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Homomorphic encryption; Computer science; Encryption; Identification (biology); Speaker identification; Artificial neural network; Scale (ratio); Speech recognition; Computer security; Computer network; Speaker recognition; Artificial intelligence","score_opus":0.014548531761685038,"score_gpt":0.2527619497386806,"score_spread":0.23821341797699558,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408352315","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022192305,0.000043272466,0.97245985,0.0016388319,0.00061874435,0.0005092133,0.0000029122384,0.00033605026,0.0021988156],"genre_scores_gemma":[0.9025742,0.000030148009,0.09329775,0.00071683625,0.00008833739,0.00023477497,0.00002420012,0.000013405602,0.003020379],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99880296,0.000052432504,0.00026644682,0.00043547072,0.00017172872,0.00027094284],"domain_scores_gemma":[0.9990675,0.000096096526,0.00009958456,0.00045723678,0.00022070814,0.00005886555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032489098,0.00013179943,0.00014547404,0.00012766136,0.000183649,0.0002497124,0.00044470702,0.00006395468,0.00009394178],"category_scores_gemma":[0.000048158836,0.00010719701,0.000076476244,0.0004867636,0.000024782656,0.0003894422,0.000082293045,0.00009326746,0.000052574258],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015664731,0.00051092915,0.00038812,0.00007745949,0.00007777212,0.0000035533785,0.000754956,0.00041630736,0.0041642278,0.024420727,0.014631057,0.9543982],"study_design_scores_gemma":[0.0009496192,0.00011012802,0.006627573,0.00006575672,0.00003128988,0.000006602511,0.00014085148,0.96405274,0.018724008,0.0026989544,0.00631306,0.00027940338],"about_ca_topic_score_codex":0.000002339929,"about_ca_topic_score_gemma":0.00005229868,"teacher_disagreement_score":0.96363646,"about_ca_system_score_codex":0.0000421913,"about_ca_system_score_gemma":0.000037626993,"threshold_uncertainty_score":0.4371367},"labels":[],"label_agreement":null},{"id":"W4408352429","doi":"10.1109/icassp49660.2025.10889032","title":"Phone-purity Guided Discrete Tokens for Dysarthric Speech Recognition","year":2025,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"Youth Innovation Promotion Association","keywords":"Speech recognition; Phone; Computer science; Linguistics","score_opus":0.04100966815545745,"score_gpt":0.29886033453776717,"score_spread":0.2578506663823097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408352429","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014390155,0.00004788526,0.85272473,0.00562022,0.00086524844,0.0005205188,0.000021772768,0.0005021626,0.1253073],"genre_scores_gemma":[0.10698355,0.0000889086,0.8695633,0.00564936,0.00015049707,0.00021274762,0.00004351702,0.000016607002,0.017291507],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99881524,0.00005507891,0.00028506017,0.0004048345,0.00016384885,0.0002759522],"domain_scores_gemma":[0.9990133,0.0002509455,0.00005618241,0.00040130588,0.00020313374,0.000075151205],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035903972,0.00013809039,0.00018021473,0.00019753417,0.00016450405,0.00018433285,0.0004354848,0.000081842874,0.0003476185],"category_scores_gemma":[0.00025032953,0.0001229931,0.00014769234,0.0004914005,0.000028393177,0.00040963615,0.00011175287,0.00007303801,0.00037704755],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000105180425,0.00005927612,0.000068945505,0.000022373435,0.00002601552,0.0000044829403,0.00004551212,2.4186835e-7,0.0010186741,0.006436432,0.05609517,0.93621236],"study_design_scores_gemma":[0.0023032955,0.00012053318,0.0018282208,0.00014052437,0.000055753946,0.000050259423,0.00014293396,0.03638394,0.61834466,0.21633065,0.123505406,0.0007938193],"about_ca_topic_score_codex":0.000033669767,"about_ca_topic_score_gemma":0.000050092953,"teacher_disagreement_score":0.93541855,"about_ca_system_score_codex":0.00004127282,"about_ca_system_score_gemma":0.000068749636,"threshold_uncertainty_score":0.5015513},"labels":[],"label_agreement":null},{"id":"W4408353132","doi":"10.1109/icassp49660.2025.10888478","title":"Text-dependent Speaker Verification Challenge 2024: Exploring Shared and User-defined Passphrases","year":2025,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Speaker verification; Human–computer interaction; Natural language processing; Speech recognition; Speaker recognition","score_opus":0.06496050737107423,"score_gpt":0.26082747468268785,"score_spread":0.19586696731161363,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408353132","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13410375,0.00094730785,0.55839056,0.022307884,0.002194127,0.0007515106,0.00001667164,0.0012859013,0.28000227],"genre_scores_gemma":[0.9329948,0.0008813181,0.051018246,0.0008302626,0.00005306506,0.00016441463,0.0000051539782,0.000011489502,0.01404126],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990934,0.000037756537,0.00017696214,0.00036923343,0.00015960811,0.00016302921],"domain_scores_gemma":[0.9993651,0.00012815413,0.000034344554,0.00035500163,0.000053931566,0.00006347115],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014754137,0.00010933508,0.000121178135,0.00014664356,0.00010292742,0.00021970012,0.00027285784,0.00004182195,0.00048343107],"category_scores_gemma":[0.000079732796,0.00009839376,0.00003633769,0.00022781579,0.000017049715,0.00054984604,0.00014693408,0.00006426603,0.00017986732],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013110826,0.00016451825,0.0014064498,0.000044431643,0.000052411637,0.000015081524,0.00037686346,0.0000019114827,0.0019950427,0.112459235,0.0067997575,0.8766712],"study_design_scores_gemma":[0.004882689,0.00036180616,0.25698736,0.0007055315,0.00014788486,0.00007743503,0.0038362585,0.06059521,0.17937183,0.026703125,0.46369454,0.0026363411],"about_ca_topic_score_codex":0.000045812976,"about_ca_topic_score_gemma":0.00006687677,"teacher_disagreement_score":0.8740348,"about_ca_system_score_codex":0.000028876286,"about_ca_system_score_gemma":0.00002867933,"threshold_uncertainty_score":0.5293231},"labels":[],"label_agreement":null},{"id":"W4408353590","doi":"10.1109/icassp49660.2025.10890553","title":"Stable-TTS: Stable Speaker-Adaptive Text-to-Speech Synthesis via Prosody Prompting","year":2025,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Prosody; Speech synthesis; Speech recognition; Computer science","score_opus":0.02149870901442346,"score_gpt":0.25179105564420484,"score_spread":0.23029234662978137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408353590","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005177617,0.000043381857,0.76787424,0.0027417706,0.00034929317,0.00085248705,0.000010812469,0.0007348488,0.22221555],"genre_scores_gemma":[0.29886672,0.000013811125,0.66337395,0.002817866,0.00010036932,0.0004041625,0.0000022411355,0.000036957816,0.0343839],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9971771,0.00016419581,0.0004978698,0.0009237514,0.00050676893,0.0007302787],"domain_scores_gemma":[0.99785733,0.00062502804,0.000111923335,0.00085693836,0.00031796933,0.00023083198],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008107121,0.00032574957,0.00042127012,0.000461774,0.00033971164,0.0004989689,0.0011726066,0.000121218014,0.00083656865],"category_scores_gemma":[0.00049137865,0.0002870011,0.00013037011,0.0016219121,0.000048181108,0.00075316016,0.0005335364,0.0002041756,0.001243299],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044076143,0.00033525808,0.0004485208,0.000060155813,0.00012443707,0.000048661936,0.00030993717,0.0000257393,0.0080019925,0.030605182,0.008500416,0.95149565],"study_design_scores_gemma":[0.00070161547,0.00020844676,0.0027637228,0.00061130564,0.000070395035,0.00005381651,0.0007832251,0.09103658,0.8257171,0.012801699,0.0638497,0.0014023806],"about_ca_topic_score_codex":0.00023054761,"about_ca_topic_score_gemma":0.00012038113,"teacher_disagreement_score":0.95009327,"about_ca_system_score_codex":0.00018292548,"about_ca_system_score_gemma":0.000224927,"threshold_uncertainty_score":0.9999582},"labels":[],"label_agreement":null},{"id":"W4408354505","doi":"10.1109/icassp49660.2025.10888920","title":"Effective and Efficient Mixed Precision Quantization of Speech Foundation Models","year":2025,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Computer science; Quantization (signal processing); Foundation (evidence); Speech recognition; Artificial intelligence; Algorithm","score_opus":0.014984164037450507,"score_gpt":0.2609719196665165,"score_spread":0.245987755629066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408354505","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1612198,0.000019204446,0.8259596,0.00017943923,0.00014885538,0.00023724367,3.401963e-7,0.000050024384,0.012185488],"genre_scores_gemma":[0.91863364,0.000013101181,0.0810738,0.00004759886,0.0000053518797,0.0000105887375,0.0000016223837,0.0000018311478,0.00021245943],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99936914,0.00007273832,0.00015086416,0.00019902554,0.00014067334,0.00006756081],"domain_scores_gemma":[0.99936825,0.00026017622,0.000047657708,0.00016447499,0.00013896904,0.000020463205],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029083903,0.000058115522,0.00009826488,0.00017819119,0.000049797884,0.00005552188,0.00012318231,0.00003696745,0.000014698721],"category_scores_gemma":[0.00010267684,0.000048951417,0.000025802983,0.00036058633,0.000021293688,0.00017909252,0.00007953506,0.000026102894,0.000010000561],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013232172,0.0000379069,0.00005627507,0.000014114966,0.000008064621,2.6938557e-7,0.00008018041,0.0003917611,0.002029918,0.113475166,0.000052055166,0.88384104],"study_design_scores_gemma":[0.00032269795,0.000028642227,0.0027954276,0.000043109692,0.0000060443467,0.000001488842,0.00002417686,0.84838104,0.12784828,0.020418555,0.00007676152,0.00005380063],"about_ca_topic_score_codex":0.000019270552,"about_ca_topic_score_gemma":0.000007484054,"teacher_disagreement_score":0.8837873,"about_ca_system_score_codex":0.000019128503,"about_ca_system_score_gemma":0.000020606278,"threshold_uncertainty_score":0.19961807},"labels":[],"label_agreement":null},{"id":"W4408355320","doi":"10.1109/icassp49660.2025.10888977","title":"LAVViT: Latent Audio-Visual Vision Transformers for Speaker Verification","year":2025,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Audio visual; Transformer; Speech recognition; Speaker verification; Computer vision; Artificial intelligence; Speaker recognition; Multimedia; Engineering; Electrical engineering","score_opus":0.014257599488651186,"score_gpt":0.30255972333916004,"score_spread":0.28830212385050885,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408355320","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0061338455,0.000015800779,0.96147776,0.0046825553,0.00031996606,0.00025403357,0.0000018194033,0.00015163013,0.026962616],"genre_scores_gemma":[0.882796,0.000053742686,0.10493519,0.0021058833,0.0000328483,0.00008313143,0.000012246158,0.000008082861,0.009972888],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993261,0.000019931638,0.00015606926,0.00023997857,0.00011230331,0.0001456178],"domain_scores_gemma":[0.999659,0.000082992345,0.000022462325,0.00012347577,0.00006983351,0.00004225467],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019960645,0.00007477209,0.00008905461,0.000110484165,0.000092367896,0.000091902184,0.00018027736,0.000049624974,0.00010811272],"category_scores_gemma":[0.000025076999,0.00006250135,0.00008699657,0.0002382899,0.000015658683,0.00024264563,0.00001729454,0.000034921042,0.000102154525],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014131547,0.0000744845,0.00008489001,0.000014678999,0.000015209586,4.0075292e-7,0.000055291213,0.0000014106473,0.0037015448,0.023219481,0.005571228,0.96724725],"study_design_scores_gemma":[0.0021851116,0.00031477757,0.023036674,0.00010532054,0.000048842376,0.000007692414,0.00017287687,0.3613547,0.32361534,0.010275302,0.27828762,0.0005957183],"about_ca_topic_score_codex":0.000008906709,"about_ca_topic_score_gemma":0.000012580359,"teacher_disagreement_score":0.96665156,"about_ca_system_score_codex":0.00003098527,"about_ca_system_score_gemma":0.000039749684,"threshold_uncertainty_score":0.25487313},"labels":[],"label_agreement":null},{"id":"W4408498124","doi":"10.1007/978-981-97-8695-4_40","title":"Artificial Neural Networks for Speaker Verification","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BP (Canada)","funders":"","keywords":"Speaker verification; Artificial neural network; Computer science; Speech recognition; Speaker recognition; Artificial intelligence","score_opus":0.027368379244865786,"score_gpt":0.24192020371765405,"score_spread":0.21455182447278826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408498124","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000098087385,0.005140516,0.9779771,0.0003481491,0.0029667676,0.00082677935,0.000011049477,0.00009862344,0.01262118],"genre_scores_gemma":[0.93427116,0.0021241456,0.013865826,0.0029725574,0.00881964,0.0005742189,0.00045078355,0.00021128093,0.0367104],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981865,0.00006073804,0.0005662354,0.00067004206,0.00017528365,0.00034118525],"domain_scores_gemma":[0.9982715,0.0008221371,0.00023295797,0.0004889515,0.000107009364,0.000077430814],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00040422837,0.0003563779,0.0005439605,0.00019514404,0.00013732212,0.00037935495,0.00037011143,0.00069767697,0.000013931166],"category_scores_gemma":[0.000067646106,0.00032109322,0.00015324265,0.00011338311,0.00004841813,0.000091219874,0.00007854337,0.00043237195,0.0000029839405],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035944504,0.00001336148,0.00004089006,0.00010111564,0.000056312452,0.00001276706,0.00004984374,0.07277082,0.000002423911,0.08326766,0.0014738344,0.842175],"study_design_scores_gemma":[0.000115400086,0.000037297188,0.000018932176,0.0003268788,0.000027190094,0.0000188709,0.0000011668493,0.966189,0.0000043536475,0.0077970885,0.02513701,0.00032676297],"about_ca_topic_score_codex":0.000024626146,"about_ca_topic_score_gemma":0.00013123208,"teacher_disagreement_score":0.9641113,"about_ca_system_score_codex":0.00005937037,"about_ca_system_score_gemma":0.000033707773,"threshold_uncertainty_score":0.9999241},"labels":[],"label_agreement":null},{"id":"W4408678082","doi":"10.1016/j.wocn.2025.101402","title":"Processing pronunciation variation with independently mappable allophones","year":2025,"lang":"en","type":"article","venue":"Journal of Phonetics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada","keywords":"Pronunciation; Variation (astronomy); Speech recognition; Computer science; Linguistics; Philosophy","score_opus":0.006363307138592676,"score_gpt":0.21844346278485252,"score_spread":0.21208015564625984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408678082","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041400563,0.00016779115,0.95416206,0.0010800202,0.00038235923,0.00008273039,3.5546466e-7,0.000024831832,0.002699262],"genre_scores_gemma":[0.77749044,0.000037143454,0.22161373,0.00026900813,0.000071903,0.0000020889793,3.3331003e-7,0.0000045122015,0.00051085226],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9991236,0.00004035118,0.00028363362,0.00009396928,0.0003534964,0.00010499969],"domain_scores_gemma":[0.9990107,0.00004714338,0.00033140162,0.000107132524,0.00046473916,0.00003892304],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037531205,0.000070524155,0.00012631102,0.00021189028,0.00007086918,0.00017818106,0.0002769574,0.00004802087,0.000017036977],"category_scores_gemma":[0.00007624566,0.000053857668,0.000033876393,0.00044338696,0.000012157728,0.00042060966,0.00002952489,0.0001232835,0.000007821247],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015093417,0.0005617522,0.0053470717,0.00016963301,0.0001711742,0.00008815861,0.0037419377,0.00092526275,0.020437542,0.0039543677,0.0031208226,0.96133137],"study_design_scores_gemma":[0.009142863,0.0023247674,0.34466588,0.0025564777,0.00044451575,0.0012439202,0.0015086364,0.21856426,0.311432,0.07493849,0.03176464,0.0014135503],"about_ca_topic_score_codex":0.0000034010914,"about_ca_topic_score_gemma":0.0000071337336,"teacher_disagreement_score":0.9599178,"about_ca_system_score_codex":0.00006424097,"about_ca_system_score_gemma":0.00030038826,"threshold_uncertainty_score":0.21962519},"labels":[],"label_agreement":null},{"id":"W4408691358","doi":"10.5753/eniac.2024.245057","title":"Phonetic segmentation for Brazilian Portuguese based on a self-supervised model and forced-alignment","year":2024,"lang":"pt","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Segmentation; Portuguese; Brazilian Portuguese; Artificial intelligence; Natural language processing; Image segmentation; Speech recognition; Computer vision; Pattern recognition (psychology); Linguistics","score_opus":0.030129838190083653,"score_gpt":0.27693819479266324,"score_spread":0.24680835660257958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408691358","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011367948,0.00037526616,0.97694147,0.0033659842,0.0006426335,0.0013486943,0.000079342295,0.00047661745,0.0054020663],"genre_scores_gemma":[0.6212672,0.00021031026,0.36131033,0.0067596454,0.00012664203,0.00039793688,0.0000544602,0.000067549176,0.009805896],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979013,0.00006959959,0.00037995906,0.0008171477,0.00044952563,0.00038247163],"domain_scores_gemma":[0.9989101,0.00035007848,0.000047317473,0.00036875214,0.000076866425,0.0002468525],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00043483672,0.00030315507,0.00023926364,0.0002858645,0.00014724051,0.0004790207,0.00023981796,0.00012204423,0.00026639918],"category_scores_gemma":[0.000024829227,0.00027180655,0.00017447922,0.00029807625,0.000030606894,0.00033691063,0.000060594888,0.00009737852,0.00012591862],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000098251134,0.00045915763,0.000016392332,0.0007488788,0.00013399556,0.000040055693,0.003111096,0.001895255,0.0057636173,0.005541972,0.013844893,0.9683464],"study_design_scores_gemma":[0.0009219236,0.00036932487,0.00007072882,0.00020854166,0.00008625106,0.000006730823,0.00025091364,0.98703945,0.0091467975,0.0011298916,0.00042521363,0.0003442214],"about_ca_topic_score_codex":0.000018518409,"about_ca_topic_score_gemma":0.000014945252,"teacher_disagreement_score":0.9851442,"about_ca_system_score_codex":0.0001277597,"about_ca_system_score_gemma":0.00020653216,"threshold_uncertainty_score":0.9999734},"labels":[],"label_agreement":null},{"id":"W4409036126","doi":"10.1075/jslp.24035.joh","title":"Exploring automatic speech recognition for corrective and confirmative pronunciation feedback","year":2025,"lang":"en","type":"article","venue":"Journal of Second Language Pronunciation","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université du Québec à Trois-Rivières; Concordia University; University of Calgary","funders":"","keywords":"Pronunciation; Speech recognition; Corrective feedback; Computer science; Natural language processing; Artificial intelligence; Psychology; Linguistics","score_opus":0.05225835841736854,"score_gpt":0.27115238157028987,"score_spread":0.21889402315292134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409036126","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8464326,0.0003838445,0.1489841,0.0006264511,0.0008617756,0.00075824664,0.000015823487,0.00007121595,0.001865904],"genre_scores_gemma":[0.7897879,0.00009261902,0.20829332,0.000805469,0.00029708332,0.00017241342,0.000023842287,0.00001897998,0.000508411],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988222,0.00010763723,0.00050382345,0.00017494503,0.00023621408,0.00015518825],"domain_scores_gemma":[0.99810135,0.00041243315,0.0006290685,0.00011013999,0.0006919895,0.00005503932],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009825706,0.00012603766,0.0002495099,0.00038263656,0.00011566198,0.00016750148,0.00016558885,0.00006455441,0.000069655456],"category_scores_gemma":[0.0009054775,0.00011415366,0.00008616472,0.00029359042,0.00001780509,0.0018169887,0.000031045918,0.00014663121,0.000008059084],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032992742,0.000056517398,0.00010521569,0.00013771064,0.00006837034,0.0000049570135,0.0051434296,8.8128365e-7,0.0027973664,0.00028111218,0.00034169713,0.99102974],"study_design_scores_gemma":[0.010494927,0.0017052944,0.12768203,0.003169497,0.00048997876,0.00057125813,0.030964794,0.12538579,0.64670295,0.04813302,0.0032870423,0.0014134365],"about_ca_topic_score_codex":0.000007014572,"about_ca_topic_score_gemma":0.000040700786,"teacher_disagreement_score":0.98961633,"about_ca_system_score_codex":0.00017101907,"about_ca_system_score_gemma":0.00015240407,"threshold_uncertainty_score":0.46550512},"labels":[],"label_agreement":null},{"id":"W4409450725","doi":"10.1016/j.specom.2025.103230","title":"Neural Chinese silent speech recognition with facial electromyography","year":2025,"lang":"en","type":"article","venue":"Speech Communication","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Natural Science Foundation of China","keywords":"Speech recognition; Electromyography; Facial electromyography; Computer science; Hidden Markov model; Artificial intelligence; Pattern recognition (psychology); Physical medicine and rehabilitation; Facial expression; Medicine","score_opus":0.012525358833797075,"score_gpt":0.2535649671924412,"score_spread":0.24103960835864413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409450725","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8164528,0.0006767344,0.065855645,0.010445645,0.00040791053,0.0010493161,0.000016077878,0.0011396854,0.103956185],"genre_scores_gemma":[0.8014934,0.00026540752,0.19661693,0.0010563222,0.000036386562,0.00009285045,0.00008781493,0.000014125386,0.00033677628],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984303,0.00027359504,0.00030658965,0.00037558938,0.00032459816,0.00028934368],"domain_scores_gemma":[0.9979506,0.00020828427,0.00013938092,0.001343247,0.00028630355,0.00007215618],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040387086,0.00021436036,0.00021487876,0.0004293406,0.00032969067,0.0002583475,0.0012705066,0.00010100626,0.00006791648],"category_scores_gemma":[0.00010123193,0.00018291689,0.0001139452,0.0015558123,0.00008704716,0.00066118554,0.00022909217,0.00031895022,0.000102825594],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036488436,0.00015520082,0.001649575,0.0000116866095,0.00004256879,0.000005667672,0.00011051062,0.0000014799658,0.0013891121,0.0012037155,0.0006909366,0.99470305],"study_design_scores_gemma":[0.008372426,0.0014243503,0.18293089,0.0010437886,0.0003223887,0.0006703866,0.0007178404,0.06370573,0.4033119,0.27750024,0.056106836,0.003893213],"about_ca_topic_score_codex":0.00010140238,"about_ca_topic_score_gemma":0.00022435552,"teacher_disagreement_score":0.99080986,"about_ca_system_score_codex":0.00007505637,"about_ca_system_score_gemma":0.000080196565,"threshold_uncertainty_score":0.74591345},"labels":[],"label_agreement":null},{"id":"W4409787672","doi":"10.61091/jcmcc127a-300","title":"Artificial Intelligence-driven Speech Signal Extraction and Generation Based on Wave RNN Models","year":2025,"lang":"en","type":"article","venue":"Journal of Combinatorial Mathematics and Combinatorial Computing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Recurrent neural network; Speech recognition; SIGNAL (programming language); Artificial intelligence; Extraction (chemistry); Natural language processing; Artificial neural network; Chemistry","score_opus":0.05272196945616726,"score_gpt":0.28455377712720986,"score_spread":0.2318318076710426,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409787672","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11915808,0.000063502186,0.8693231,0.00058914575,0.008976629,0.00023941508,0.0000010215731,0.00004980684,0.0015993237],"genre_scores_gemma":[0.9116317,0.000023007242,0.08745252,0.00009457171,0.00077838055,0.0000019799913,8.3843014e-7,0.000012294348,0.0000047224753],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99770623,0.00016182731,0.0009868252,0.00029400625,0.0006080584,0.00024305459],"domain_scores_gemma":[0.9975802,0.00090644555,0.0006337461,0.00023330843,0.0005025524,0.00014377541],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013418971,0.00024926785,0.000518399,0.00044156951,0.00033779818,0.00056913804,0.00032808125,0.00017483141,0.000007992937],"category_scores_gemma":[0.00027327798,0.0002279684,0.0001361691,0.00039650046,0.00006169875,0.0004176817,0.00013643566,0.00041198177,0.000001931692],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005290859,0.00045729088,0.000007197961,0.00005219452,0.000045753324,0.000029451225,0.00025487467,0.00069463544,0.0011171971,0.8808262,0.000108072956,0.11635424],"study_design_scores_gemma":[0.000354732,0.00027019277,0.000005751277,0.00016020647,0.000030151357,0.00003466865,0.000058182137,0.5459839,0.009296331,0.44363636,0.000044754972,0.00012474746],"about_ca_topic_score_codex":0.0000035674077,"about_ca_topic_score_gemma":4.845809e-7,"teacher_disagreement_score":0.7924736,"about_ca_system_score_codex":0.0000945759,"about_ca_system_score_gemma":0.00017845299,"threshold_uncertainty_score":0.92962813},"labels":[],"label_agreement":null},{"id":"W4410291915","doi":"10.1016/j.specom.2025.103253","title":"Human and automatic voice comparison with regionally variable speech samples","year":2025,"lang":"en","type":"article","venue":"Speech Communication","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Arts and Humanities Research Council; Arts and Humanities Research Board","keywords":"Speech recognition; Computer science; Variable (mathematics); Voice activity detection; Speech processing; Natural language processing; Artificial intelligence; Mathematics","score_opus":0.03229459497336561,"score_gpt":0.29117057046485045,"score_spread":0.25887597549148483,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410291915","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28768802,0.0013006582,0.47480646,0.016268592,0.00019785386,0.0012519734,0.000010104279,0.0015733499,0.21690299],"genre_scores_gemma":[0.3625307,0.00005356749,0.63570493,0.00059835496,0.000009904761,0.00003226825,0.00002073859,0.000008771533,0.0010407807],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99870867,0.0002290476,0.00031367538,0.00030061064,0.00025690655,0.00019108868],"domain_scores_gemma":[0.9978466,0.00037009074,0.00015608716,0.001369904,0.00019634566,0.000060972994],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005901216,0.00015143935,0.00023610084,0.0002006441,0.0004382304,0.00029999585,0.0011022271,0.00008017746,0.000032843873],"category_scores_gemma":[0.000100646066,0.00013814527,0.000029045796,0.00060625206,0.00011719564,0.00038843913,0.00035537424,0.00020549035,0.000038916707],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000143864245,0.00045105934,0.0068218205,0.00013693985,0.0001502942,0.0000064205387,0.0006583211,0.000015059581,0.003126193,0.43669176,0.008754456,0.5431733],"study_design_scores_gemma":[0.0046152337,0.0005304996,0.1986203,0.0027437932,0.00031306056,0.00038975905,0.0016133398,0.2029669,0.06005545,0.4316434,0.094304085,0.0022041933],"about_ca_topic_score_codex":0.00023776005,"about_ca_topic_score_gemma":0.00028998023,"teacher_disagreement_score":0.54096913,"about_ca_system_score_codex":0.00005819681,"about_ca_system_score_gemma":0.00009441666,"threshold_uncertainty_score":0.5633401},"labels":[],"label_agreement":null},{"id":"W4410431605","doi":"10.1016/j.csl.2025.101815","title":"BERSting at the screams: A benchmark for distanced, emotional and shouted speech recognition","year":2025,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Computer science; Benchmark (surveying); Speech recognition; Emotion recognition; Natural language processing","score_opus":0.01565752871258395,"score_gpt":0.2604487816432463,"score_spread":0.24479125293066237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410431605","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12772055,0.0006203275,0.85442287,0.0038126875,0.001003271,0.0008481196,0.00011274801,0.0003473195,0.011112104],"genre_scores_gemma":[0.074643746,0.000048238515,0.91446596,0.005409071,0.000693904,0.00013183187,0.00023954337,0.000033801836,0.004333893],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983684,0.00010305673,0.00031767177,0.00059679995,0.00025739067,0.00035670697],"domain_scores_gemma":[0.9985308,0.0006088314,0.000114477225,0.00049945194,0.00015520684,0.00009120351],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000510506,0.00022817997,0.00023826634,0.00016581718,0.0004537936,0.0003452665,0.0005801067,0.000096316464,0.00017824769],"category_scores_gemma":[0.00012994096,0.00018065776,0.00013869807,0.0004478738,0.00009888331,0.00030631296,0.00044108948,0.00015184397,0.00003746249],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020177256,0.000047646965,0.00013458196,0.00004149218,0.00004818597,0.00003242083,0.0004761997,0.0000015141319,0.0004442186,0.0015176345,0.009197186,0.9880387],"study_design_scores_gemma":[0.011344954,0.0007578636,0.039096452,0.0024373755,0.00046479874,0.0019651307,0.0025535596,0.5765508,0.16485497,0.05076406,0.14512052,0.0040895385],"about_ca_topic_score_codex":0.0000355907,"about_ca_topic_score_gemma":0.0001359585,"teacher_disagreement_score":0.9839492,"about_ca_system_score_codex":0.00008015053,"about_ca_system_score_gemma":0.00005270909,"threshold_uncertainty_score":0.736701},"labels":[],"label_agreement":null},{"id":"W4410617847","doi":"10.54254/2755-2721/2025.tj23214","title":"Study for Automatic Speech Recognition for Wav2Vec2.0","year":2025,"lang":"en","type":"article","venue":"Applied and Computational Engineering","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Speech recognition; Computer science; Natural language processing","score_opus":0.019156557871145046,"score_gpt":0.24763702891965278,"score_spread":0.22848047104850774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410617847","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.044452924,0.000015464628,0.9537508,0.00018691878,0.00014155559,0.00074182026,0.000006798509,0.00019390837,0.00050979987],"genre_scores_gemma":[0.463933,7.124393e-7,0.5354256,0.00015274339,0.000030547217,0.00040553196,0.00001611547,0.000005960684,0.000029817775],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999404,0.000004364957,0.0001648385,0.00022015124,0.00008483665,0.00012179259],"domain_scores_gemma":[0.99925846,0.0005392186,0.000026917432,0.000076177166,0.00006813094,0.000031094653],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016997648,0.00009341219,0.00012199278,0.00014147011,0.000095164636,0.000095773634,0.000116790674,0.000028622431,0.0000027047015],"category_scores_gemma":[0.000041099862,0.00009792342,0.00003583422,0.00016401711,0.0000056676927,0.00008723877,0.00003273365,0.000033343902,0.000004340849],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000063959205,0.000087737346,0.000013951317,0.0000837838,0.000057291298,7.7732824e-7,0.00012264724,0.0020536217,0.00013313645,0.053951073,0.00021134851,0.94327825],"study_design_scores_gemma":[0.00095822255,0.00004453482,0.0017883162,0.000025248204,0.000020241398,0.00000464352,0.0000850527,0.9382714,0.00090431975,0.057219196,0.0005311373,0.00014769599],"about_ca_topic_score_codex":7.4701484e-7,"about_ca_topic_score_gemma":4.0644716e-7,"teacher_disagreement_score":0.94313055,"about_ca_system_score_codex":0.000013841148,"about_ca_system_score_gemma":0.000025185453,"threshold_uncertainty_score":0.3993201},"labels":[],"label_agreement":null},{"id":"W4411272738","doi":"10.1007/978-981-96-1758-6_16","title":"An Efficient Voice Replay Antispoofing Method","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hamilton Health Sciences","funders":"","keywords":"Computer science; Speech recognition","score_opus":0.016423412517061097,"score_gpt":0.26617372554144547,"score_spread":0.24975031302438438,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411272738","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000018548468,0.0074800053,0.9446786,0.00011937755,0.0017076985,0.0003884944,0.000007696202,0.00014307823,0.045456495],"genre_scores_gemma":[0.5668101,0.003686827,0.3537894,0.0054268553,0.0060520405,0.00021827874,0.0001813675,0.0003636158,0.063471556],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99766874,0.00020706718,0.00054664677,0.0009237154,0.00029476112,0.00035906618],"domain_scores_gemma":[0.997543,0.0011821765,0.00024187025,0.00081602804,0.00009670706,0.00012023281],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010564801,0.00040754883,0.0007012601,0.00033567194,0.00014792415,0.0004377486,0.0005672072,0.0006689208,0.000016771119],"category_scores_gemma":[0.000083505336,0.000350964,0.00011961498,0.00016882447,0.000037076243,0.000078379424,0.00013989423,0.00061152957,0.000007778959],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013946135,0.00002621028,0.000049275175,0.00017338412,0.000075978016,0.0001588147,0.00021430827,0.1286103,0.000016160084,0.05402888,0.00036086905,0.8162719],"study_design_scores_gemma":[0.00016687976,0.000044903914,0.00003182181,0.0011808737,0.0000269458,0.000096143456,0.0000025633021,0.9752829,0.000023557708,0.001985124,0.020734083,0.00042417887],"about_ca_topic_score_codex":0.000118290285,"about_ca_topic_score_gemma":0.00009267867,"teacher_disagreement_score":0.84667265,"about_ca_system_score_codex":0.00006661877,"about_ca_system_score_gemma":0.000056686426,"threshold_uncertainty_score":0.99989426},"labels":[],"label_agreement":null},{"id":"W4411757453","doi":"10.1145/3746638","title":"Latency-Aware Pruning and Quantization of Self-Supervised Speech Transformers for Edge Devices","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Embedded Computing Systems","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Quantization (signal processing); Transformer; Speech recognition; Artificial intelligence; Algorithm; Engineering; Electrical engineering","score_opus":0.022925303094301124,"score_gpt":0.2754509292688123,"score_spread":0.2525256261745112,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411757453","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045255333,0.00012619885,0.9518867,0.0003065252,0.00074023096,0.0006710518,0.000010667055,0.00033273868,0.00067056157],"genre_scores_gemma":[0.89504665,0.000031482625,0.10466978,0.000093743416,0.000022325668,0.000030189258,0.0000043359514,0.000013315172,0.00008817502],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99844944,0.00012507905,0.0005236971,0.00043113442,0.00021305137,0.00025757105],"domain_scores_gemma":[0.9985145,0.0006735845,0.00013925832,0.00036678123,0.0002389265,0.00006697366],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004944508,0.00019637712,0.00034535094,0.0003972059,0.00034705977,0.00014758544,0.00046745385,0.00012970035,0.0000038379544],"category_scores_gemma":[0.000036066394,0.00019405968,0.00012701396,0.00067997,0.00003197166,0.00025521917,0.000010209491,0.00012556907,0.0000033436206],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005631519,0.00037394717,0.00035729827,0.0017485771,0.00043834385,0.0000038243065,0.005727357,0.0029883368,0.002224467,0.003947496,0.000106094274,0.98202795],"study_design_scores_gemma":[0.0010415427,0.00013119847,0.00021838772,0.0006905143,0.00008648813,0.000021637894,0.0020445983,0.98240817,0.012382009,0.0002746949,0.00043647626,0.00026429936],"about_ca_topic_score_codex":0.00004932297,"about_ca_topic_score_gemma":0.000012478993,"teacher_disagreement_score":0.98176366,"about_ca_system_score_codex":0.000048170565,"about_ca_system_score_gemma":0.00009355381,"threshold_uncertainty_score":0.79135245},"labels":[],"label_agreement":null},{"id":"W4411792967","doi":"10.18280/ts.420312","title":"Mel-Spectrograms Based LSTM Model for Speech Emotion Recognition","year":2025,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Spectrogram; Speech recognition; Computer science; Emotion recognition; Artificial intelligence","score_opus":0.03934978002030785,"score_gpt":0.26331803997867764,"score_spread":0.2239682599583698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411792967","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010803814,0.000018315151,0.9824733,0.0020742966,0.00019513512,0.0005982732,0.000025467174,0.0002905563,0.0035208066],"genre_scores_gemma":[0.57582116,0.000007867042,0.4208879,0.0023611523,0.00009727149,0.0002506642,0.0000880371,0.000013259325,0.00047269923],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99861884,0.00006066637,0.00031598468,0.00042153752,0.0002749193,0.0003080366],"domain_scores_gemma":[0.99928457,0.00014918287,0.00008190416,0.0002289514,0.00017955495,0.00007582259],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004906473,0.00016893685,0.0001742526,0.00024075988,0.00017444752,0.00019282971,0.0003670901,0.00007726881,0.00023993006],"category_scores_gemma":[0.000034095,0.00016796264,0.00018249347,0.00034284452,0.000026514406,0.0002953692,0.00003367759,0.00007941979,0.000054496686],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055070206,0.0003402286,0.000031709005,0.0000452552,0.000042266718,0.0000034938782,0.00010190725,0.0003067529,0.0037973921,0.007672972,0.0035984132,0.98400456],"study_design_scores_gemma":[0.001083647,0.00010186937,0.00015545577,0.000059219412,0.000032256667,0.0000023373123,0.000024290433,0.9301317,0.041807063,0.024968192,0.0014433871,0.00019058904],"about_ca_topic_score_codex":0.0000066709154,"about_ca_topic_score_gemma":0.000012938131,"teacher_disagreement_score":0.98381394,"about_ca_system_score_codex":0.00009275547,"about_ca_system_score_gemma":0.000098782846,"threshold_uncertainty_score":0.68493176},"labels":[],"label_agreement":null},{"id":"W4411859426","doi":"10.1007/978-981-96-6599-0_22","title":"Optimizing Learnable Frequency-Domain Filterbanks for Depression Detection via Speech Representation Disentanglement","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Representation (politics); Speech recognition; Frequency domain; Domain (mathematical analysis); Algorithm; Artificial intelligence; Mathematics; Computer vision","score_opus":0.021331876213969064,"score_gpt":0.26678365580849234,"score_spread":0.24545177959452327,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411859426","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000796561,0.00023842414,0.98957235,0.00049826043,0.002026857,0.00097120146,0.000010278471,0.00020350392,0.0063994955],"genre_scores_gemma":[0.016818939,0.00004010783,0.98116314,0.00074439513,0.00033873593,0.0000845126,0.000019218636,0.00002962976,0.00076128857],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962119,0.000062340536,0.0006212689,0.0016683348,0.00083337916,0.0006027827],"domain_scores_gemma":[0.99742293,0.0006645954,0.00034941122,0.001113069,0.00030796393,0.00014200526],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008377624,0.00046397015,0.00047036257,0.0009819551,0.00048426696,0.00059554883,0.0016972311,0.00031711825,0.000057487683],"category_scores_gemma":[0.00016419339,0.00044753743,0.00023219777,0.0006167176,0.00020143777,0.00072732224,0.0006803441,0.00047771074,0.00002123505],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013625593,0.000029217563,0.000035490917,0.000049161506,0.000015719645,0.000034420387,0.000247851,0.0011196677,0.002935893,0.0013446488,0.00003434602,0.99413997],"study_design_scores_gemma":[0.00070454285,0.00018642301,0.00006438825,0.0007662461,0.000028995406,0.000082635335,0.0000016212354,0.47246313,0.11818297,0.4052844,0.0013687819,0.00086584425],"about_ca_topic_score_codex":0.00005758865,"about_ca_topic_score_gemma":0.00017399069,"teacher_disagreement_score":0.9932741,"about_ca_system_score_codex":0.00052223844,"about_ca_system_score_gemma":0.00025880584,"threshold_uncertainty_score":0.99979764},"labels":[],"label_agreement":null},{"id":"W4411934141","doi":"10.1162/tacl_a_00759","title":"A Comparative Approach for Auditing Multilingual Phonetic Transcript Archives","year":2025,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Audit; Natural language processing; Linguistics; Speech recognition; Data science; Artificial intelligence; World Wide Web; Accounting; Business","score_opus":0.030497832723930175,"score_gpt":0.29480967779670436,"score_spread":0.26431184507277417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411934141","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00037938202,0.000027321803,0.9929854,0.0003037706,0.000813693,0.0006261557,0.00023193989,0.00006548437,0.0045668287],"genre_scores_gemma":[0.5785294,0.0000011904773,0.4203424,0.00008290379,0.000052747324,0.000077768185,0.000024702582,0.000004551825,0.00088432024],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99892837,0.00007520547,0.00039060626,0.00021797203,0.00022170751,0.00016611462],"domain_scores_gemma":[0.996176,0.002657177,0.00027607364,0.00014658995,0.0007164948,0.000027675625],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027995196,0.00011365312,0.00022947762,0.00014310879,0.00041080968,0.000057361292,0.00040064918,0.00006160774,0.000002206402],"category_scores_gemma":[0.00096948585,0.00010493297,0.00030262335,0.00031751758,0.000047488258,0.000037625283,0.000008974721,0.000101494035,7.271597e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018240498,0.0012649869,0.00040042572,0.00047170412,0.0011675416,1.4168447e-7,0.005709879,0.6580609,0.0009451272,0.2933827,0.0015345113,0.036879644],"study_design_scores_gemma":[0.0010148339,0.000038196245,0.0009533112,0.00003854898,0.00011963577,5.059355e-7,0.00017144077,0.9388521,0.006983152,0.0483165,0.0033875145,0.00012428874],"about_ca_topic_score_codex":0.000005179694,"about_ca_topic_score_gemma":0.0000043612868,"teacher_disagreement_score":0.57815003,"about_ca_system_score_codex":0.000083380255,"about_ca_system_score_gemma":0.00018828044,"threshold_uncertainty_score":0.42790425},"labels":[],"label_agreement":null},{"id":"W4411990369","doi":"10.1007/978-3-031-85747-8_10","title":"An Efficient Clustering Algorithm for Self-Supervised Speaker Recognition","year":2025,"lang":"en","type":"book-chapter","venue":"Machine translation","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Cluster analysis; Pattern recognition (psychology); Artificial intelligence; Speaker recognition; Speech recognition","score_opus":0.0329297984314789,"score_gpt":0.2570398133233841,"score_spread":0.2241100148919052,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411990369","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000007378346,0.00021332045,0.8848286,0.00028898095,0.0005219538,0.0008678206,0.00023660477,0.00052532955,0.112509996],"genre_scores_gemma":[0.00047125993,0.00007871529,0.98581403,0.00036930817,0.00027306046,0.000079225196,0.0010509439,0.00005932209,0.011804132],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982793,0.000046770918,0.00045224573,0.0006722837,0.00031448496,0.00023495003],"domain_scores_gemma":[0.9989585,0.000167719,0.00013739798,0.00046226467,0.00017306418,0.00010102652],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00035997224,0.0003585343,0.00033840552,0.00039114477,0.00017898898,0.00018691934,0.0004003852,0.0002869445,0.00023783612],"category_scores_gemma":[0.0000070217748,0.00037478303,0.00025854676,0.00008138893,0.000016678321,0.00023398332,0.000025903428,0.00021145114,0.00008080627],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012164531,0.000053585503,3.7267614e-7,0.00007040055,0.000047192232,0.0000037230209,0.00019376795,0.000055942535,0.000029122833,0.0010584632,0.000065821245,0.99840945],"study_design_scores_gemma":[0.0007631421,0.00009561092,0.00000925281,0.00015326675,0.00010480193,0.000009384074,0.0000025666732,0.974591,0.00020840403,0.0045079156,0.01912935,0.0004252665],"about_ca_topic_score_codex":0.000012330479,"about_ca_topic_score_gemma":0.000045460274,"teacher_disagreement_score":0.9979842,"about_ca_system_score_codex":0.00007515622,"about_ca_system_score_gemma":0.00006880721,"threshold_uncertainty_score":0.9998704},"labels":[],"label_agreement":null},{"id":"W4412020141","doi":"10.19139/soic-2310-5070-2521","title":"A Hybrid Approach of Long Short Term Memory and Transformer Models for Speech Emotion Recognition","year":2025,"lang":"en","type":"article","venue":"Statistics Optimization & Information Computing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Speech recognition; Term (time); Transformer; Long short term memory; Computer science; Short-term memory; Cognitive psychology; Natural language processing; Psychology; Artificial intelligence; Cognition; Engineering; Artificial neural network; Working memory; Electrical engineering; Recurrent neural network; Neuroscience","score_opus":0.02329019575944726,"score_gpt":0.2514189199685227,"score_spread":0.22812872420907546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412020141","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014811441,0.00001114817,0.9912814,0.000060245115,0.00019965303,0.00065794325,0.0001521647,0.000112971116,0.00604333],"genre_scores_gemma":[0.1304319,0.00003801594,0.86863244,0.00016707237,0.000016802429,0.000019196721,0.00066723785,0.0000063761254,0.000020943336],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986487,0.000046695695,0.0007009956,0.00019410801,0.00022539515,0.0001840738],"domain_scores_gemma":[0.99864185,0.00023671378,0.00022186081,0.00016590848,0.0006818539,0.000051808194],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004961538,0.00015019455,0.00022137657,0.00041013613,0.00021634808,0.00021361571,0.0001849029,0.00006535298,0.00000922121],"category_scores_gemma":[0.00013838036,0.00016423065,0.000049397942,0.00029623904,0.000044621418,0.0016529309,0.000040487637,0.000080538965,0.0000018699108],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014346483,0.000034947338,0.00001752419,0.00029087806,0.000026991072,2.854822e-7,0.00061116274,0.16053699,0.000008512582,0.008529663,0.00021877771,0.82970995],"study_design_scores_gemma":[0.0004971173,0.000031986627,0.00011266107,0.00008859535,0.000030240513,0.000016738373,0.00014264569,0.9919602,0.0022339346,0.004710632,0.000014352238,0.00016088226],"about_ca_topic_score_codex":0.000005455964,"about_ca_topic_score_gemma":6.192671e-7,"teacher_disagreement_score":0.8314232,"about_ca_system_score_codex":0.000045203542,"about_ca_system_score_gemma":0.000082757964,"threshold_uncertainty_score":0.66971314},"labels":[],"label_agreement":null},{"id":"W4412195314","doi":"10.3390/s25144288","title":"Phoneme-Aware Hierarchical Augmentation and Semantic-Aware SpecAugment for Low-Resource Cantonese Speech Recognition","year":2025,"lang":"en","type":"article","venue":"Sensors","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Natural Science Foundation of Shandong Province; National Natural Science Foundation of China","keywords":"Computer science; Speech recognition; Pronunciation; Word error rate; Context (archaeology); Masking (illustration); Artificial intelligence","score_opus":0.016940222352218908,"score_gpt":0.2642564729911856,"score_spread":0.2473162506389667,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412195314","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8395795,0.00005901172,0.14587936,0.00718422,0.00073181425,0.0012513355,0.00009876091,0.00038426524,0.004831728],"genre_scores_gemma":[0.9092383,0.0001319197,0.07931662,0.0038777166,0.00030983155,0.00019281391,0.00021363277,0.000048260405,0.0066709276],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985176,0.00010852619,0.0003000733,0.000516841,0.00024988403,0.0003070956],"domain_scores_gemma":[0.9990703,0.0003264622,0.00008182793,0.0002915545,0.0001284427,0.00010145295],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027645705,0.00018806968,0.00021770626,0.00025651613,0.00027768963,0.00023211568,0.00022087568,0.00009837547,0.00008792536],"category_scores_gemma":[0.00010086298,0.00018417179,0.00009139642,0.00034445082,0.000079567646,0.00017293176,0.0000986073,0.00011834119,0.00005652973],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009518095,0.00015619298,0.00020110345,0.00019349056,0.0000753391,0.000041345902,0.0006994904,0.000015997182,0.001841927,0.001036246,0.00525999,0.9903837],"study_design_scores_gemma":[0.006608356,0.00038711948,0.0060932795,0.0011228905,0.00022860209,0.00021231778,0.0027388649,0.3643446,0.53968644,0.03575457,0.041097555,0.0017253726],"about_ca_topic_score_codex":0.000055688186,"about_ca_topic_score_gemma":0.0000984666,"teacher_disagreement_score":0.9886583,"about_ca_system_score_codex":0.000080458776,"about_ca_system_score_gemma":0.00007160169,"threshold_uncertainty_score":0.7510308},"labels":[],"label_agreement":null},{"id":"W4412222534","doi":"","title":"D7.6 – Demo site report #6 N. Denmark","year":2023,"lang":"en","type":"report","venue":"VBN Forskningsportal (Aalborg Universitet)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Semtech (Canada)","funders":"","keywords":"Geography","score_opus":0.06467585731613737,"score_gpt":0.29003145903714206,"score_spread":0.2253556017210047,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412222534","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015143219,0.0004618834,0.012851273,0.00079525105,0.007788194,0.0009722169,0.00039578677,0.0032581396,0.958334],"genre_scores_gemma":[0.019011622,0.002480996,0.02809423,0.00064127997,0.0017328156,0.000045834302,0.0034546948,0.00042382,0.9441147],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99347204,0.000088572466,0.0010655854,0.001864813,0.0024350653,0.0010739376],"domain_scores_gemma":[0.99456424,0.00031646047,0.0014031545,0.0019216087,0.0011948241,0.00059973326],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001417151,0.0008640548,0.0011071927,0.001561435,0.0004993101,0.00034806842,0.0020128489,0.0009218718,0.0015617346],"category_scores_gemma":[0.0007161888,0.0009424459,0.00090197497,0.002194467,0.00016604377,0.0009846127,0.0010026346,0.000930593,0.0063472213],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028963621,0.00014541732,0.008466041,0.00024602888,0.0006587279,0.05741524,0.0005276987,0.000009355135,0.00008673852,0.0011571605,0.8823669,0.048891764],"study_design_scores_gemma":[0.0004237404,0.00008139361,0.0037118855,0.00039102952,0.00026172056,0.0030726031,0.00023782678,0.0003683324,0.00038305344,0.0003762444,0.9892859,0.0014062541],"about_ca_topic_score_codex":0.0009624982,"about_ca_topic_score_gemma":0.00029209213,"teacher_disagreement_score":0.10691905,"about_ca_system_score_codex":0.0007436909,"about_ca_system_score_gemma":0.0022362885,"threshold_uncertainty_score":0.99935097},"labels":[],"label_agreement":null},{"id":"W4412566360","doi":"10.36227/techrxiv.175321809.95815200/v1","title":"A Survey on Speech Large Language Models for Understanding","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Optech (Canada)","funders":"","keywords":"Linguistics; Computer science; Indirect speech; Natural language processing; Philosophy","score_opus":0.15512074020316538,"score_gpt":0.33272328338252016,"score_spread":0.17760254317935478,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412566360","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020363572,0.00003847106,0.9097978,0.0004539142,0.00068867166,0.0004805167,0.00047353574,0.0003095487,0.087553926],"genre_scores_gemma":[0.45543575,0.00008148358,0.4968867,0.0053282906,0.00022427118,0.00025831544,0.00047658567,0.000048677713,0.041259933],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983924,0.00013319912,0.00023670265,0.0006609431,0.0002587541,0.00031798275],"domain_scores_gemma":[0.9981032,0.0008784071,0.00008663826,0.00076450786,0.00009203524,0.00007522989],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010533672,0.00022640337,0.00031234944,0.0002883057,0.000107469066,0.0002986434,0.0009391077,0.00023323933,0.000095890515],"category_scores_gemma":[0.00018743261,0.00020543796,0.00019842919,0.00018600651,0.000010914025,0.00010134757,0.00070117234,0.00025057408,0.000035427987],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045710192,0.00030835564,0.000059411257,0.000246026,0.00019297843,0.000030355559,0.0009702647,0.00038782696,0.000011978062,0.86430883,0.043247044,0.090191185],"study_design_scores_gemma":[0.0004916233,0.000035232802,0.000113789465,0.0002413538,0.000015461716,0.0000013317923,0.00020207556,0.7554904,0.0017773868,0.24075039,0.00040934252,0.00047158296],"about_ca_topic_score_codex":0.00022877115,"about_ca_topic_score_gemma":0.0008010367,"teacher_disagreement_score":0.75510263,"about_ca_system_score_codex":0.00020102551,"about_ca_system_score_gemma":0.00017294472,"threshold_uncertainty_score":0.8377517},"labels":[],"label_agreement":null},{"id":"W4412672023","doi":"10.1101/2025.07.25.25332211","title":"Performance Analysis of Speech Recognition Models in Automated Scoring of the QuickSIN Test","year":2025,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"London Health Sciences Centre; Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Test (biology); Speech recognition; Computer science; Natural language processing; Artificial intelligence; Pattern recognition (psychology); Biology","score_opus":0.046860780830607664,"score_gpt":0.2710023107536934,"score_spread":0.22414152992308575,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412672023","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9885569,0.000044533244,0.0053865914,0.00016804226,0.00033747722,0.00024985237,0.000064457614,0.00014399261,0.0050481213],"genre_scores_gemma":[0.9802931,0.00013736878,0.019375458,0.000037119975,0.0000134856045,0.000028767456,0.000011356754,0.000005787558,0.000097585784],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99809855,0.00016706462,0.0006909963,0.0004538084,0.00040157637,0.00018802649],"domain_scores_gemma":[0.99796087,0.00032807756,0.0004578649,0.0009596716,0.00026080452,0.00003271218],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008150469,0.00018765578,0.00056331,0.001064846,0.000038625407,0.00003467319,0.0012624015,0.00017675804,0.000029765977],"category_scores_gemma":[0.00029196785,0.00015292662,0.00029385195,0.002762295,0.0000617098,0.00018324105,0.00076515274,0.00030393386,0.0000045087972],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020058513,0.0004607853,0.40713602,0.0010668263,0.0007846242,0.000010475121,0.0013980528,0.029868625,0.0029738059,0.00016743563,0.0000601289,0.55605316],"study_design_scores_gemma":[0.00009359447,0.000008924132,0.13809624,0.0006787574,0.00016601573,8.887141e-7,0.000013183938,0.80993474,0.050135624,0.0007414461,0.000003831428,0.000126769],"about_ca_topic_score_codex":0.00021388705,"about_ca_topic_score_gemma":0.00014857849,"teacher_disagreement_score":0.7800661,"about_ca_system_score_codex":0.00006648312,"about_ca_system_score_gemma":0.0001945723,"threshold_uncertainty_score":0.62361664},"labels":[],"label_agreement":null},{"id":"W4412754181","doi":"10.2139/ssrn.5372225","title":"Stacked One-vs-One (Sovo): A New Approach for Multi-Class Classification for Semg Recognition","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Class (philosophy); Pattern recognition (psychology); Artificial intelligence; Computer science; Speech recognition","score_opus":0.14259113620166353,"score_gpt":0.3227645324264219,"score_spread":0.18017339622475836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412754181","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004112005,0.00056645466,0.9913304,0.0033480148,0.000745995,0.0021144822,0.00012490869,0.00021493097,0.0011436496],"genre_scores_gemma":[0.009421719,0.00431475,0.96960723,0.00064530136,0.0013693701,0.0010676095,0.00066952634,0.00007613127,0.012828375],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9951516,0.00024697537,0.00086533534,0.0010887008,0.00048372435,0.0021636875],"domain_scores_gemma":[0.9971139,0.00033383528,0.0008295659,0.00071569165,0.00077629706,0.0002307555],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0031160386,0.00045940638,0.0006599648,0.0005837058,0.00043089257,0.00060353265,0.0015721013,0.00058508635,0.00002390528],"category_scores_gemma":[0.0005464602,0.00049484824,0.0006576443,0.0003412254,0.000041127718,0.00039641446,0.0002623436,0.0024689313,0.000032127027],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030921368,0.00072085287,0.000008741807,0.00028923686,0.00079207344,4.4237078e-7,0.00024487881,0.000053025444,0.0004866252,0.05704351,0.0020485008,0.9380029],"study_design_scores_gemma":[0.004208556,0.0003947609,0.00007047456,0.00038625492,0.00042754356,0.00008891214,0.00048450552,0.386152,0.0024293682,0.5985296,0.005853189,0.0009748653],"about_ca_topic_score_codex":0.000040419665,"about_ca_topic_score_gemma":0.00020413935,"teacher_disagreement_score":0.93702805,"about_ca_system_score_codex":0.0018443695,"about_ca_system_score_gemma":0.008166786,"threshold_uncertainty_score":0.9998324},"labels":[],"label_agreement":null},{"id":"W4412871783","doi":"10.1121/10.0037268","title":"Transforming child speech data into clinical-grade artificial intelligence pipelines for speech-language impairment detection","year":2025,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Language impairment; Speech recognition; Computer science; Psychology; Audiology; Natural language processing; Medicine; Developmental psychology","score_opus":0.04871944744811161,"score_gpt":0.3495868000122566,"score_spread":0.300867352564145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412871783","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00459487,0.0002547964,0.9796963,0.01438769,0.0006837522,0.0002933212,0.000008968953,0.000021426242,0.000058929232],"genre_scores_gemma":[0.37677065,0.0008463925,0.6190756,0.0028040123,0.00045027817,0.0000030103304,0.00000101283,0.000010933642,0.000038100978],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979732,0.00021646444,0.00094960927,0.0002032698,0.00043123844,0.00022623457],"domain_scores_gemma":[0.9969149,0.0015681977,0.0004848631,0.0007461823,0.00020874884,0.000077070734],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021835896,0.00014596371,0.00036049346,0.000043267282,0.0003218423,0.000056930057,0.002446762,0.00008753077,0.000013969553],"category_scores_gemma":[0.0009157988,0.00008156201,0.00055227743,0.0005431916,0.0004034209,0.00021888921,0.00037231235,0.00045073518,0.000003250101],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007776085,0.0002280266,0.0000056264616,0.000036329882,0.00012588876,8.0057333e-7,0.00057408446,0.00014194308,0.0063358415,0.00002563658,0.0018093105,0.99063873],"study_design_scores_gemma":[0.0002499112,0.00036755006,0.000093349285,0.00020911502,0.00035844557,0.00008312259,0.0051252763,0.8547199,0.121883735,0.013710017,0.0030349218,0.00016467247],"about_ca_topic_score_codex":0.0000466746,"about_ca_topic_score_gemma":0.000008525964,"teacher_disagreement_score":0.9904741,"about_ca_system_score_codex":0.000053852797,"about_ca_system_score_gemma":0.00012403815,"threshold_uncertainty_score":0.45467335},"labels":[],"label_agreement":null},{"id":"W4412944958","doi":"10.18653/v1/2025.acl-long.961","title":"ZIPA: A family of efficient models for multilingual phone recognition","year":2025,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Phone; Computer science; Speech recognition; Artificial intelligence; Pattern recognition (psychology); Linguistics","score_opus":0.05388308592547792,"score_gpt":0.2870036363835925,"score_spread":0.23312055045811458,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412944958","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0731851,0.00004344228,0.9011866,0.00018722277,0.0002667098,0.00024635653,0.000011086176,0.00010557541,0.024767919],"genre_scores_gemma":[0.64529777,0.000009258113,0.35329953,0.0005534667,0.000014662662,0.00005077281,0.000004177087,0.000003895142,0.0007664818],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99924815,0.000024274434,0.00022911906,0.00023462795,0.00012351757,0.00014032863],"domain_scores_gemma":[0.99922556,0.00025284724,0.000050469964,0.00020767456,0.00023118168,0.000032261527],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002449737,0.00007673421,0.00013972723,0.00016951819,0.000051125746,0.00003003506,0.00024402482,0.00004830006,0.000020372605],"category_scores_gemma":[0.00010025972,0.000068165005,0.000097796714,0.00028879897,0.000022477165,0.0000917286,0.000058713435,0.000033937158,0.000023613526],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026935217,0.00023223876,0.0000029230296,0.000038666865,0.000025485237,8.4190543e-7,0.00023174417,0.00038996068,0.007670942,0.0101548005,0.0010278957,0.98019755],"study_design_scores_gemma":[0.0005544195,0.00002718456,0.000052069336,0.00004431031,0.0000093273175,9.055042e-7,0.00012637723,0.77697325,0.2062119,0.015639016,0.00027381018,0.00008744963],"about_ca_topic_score_codex":0.000025736366,"about_ca_topic_score_gemma":0.0000055891587,"teacher_disagreement_score":0.9801101,"about_ca_system_score_codex":0.0000177178,"about_ca_system_score_gemma":0.00006848605,"threshold_uncertainty_score":0.27796882},"labels":[],"label_agreement":null},{"id":"W4412967876","doi":"10.1101/2025.07.14.25331543","title":"CharMark: A Markov Approach to Linguistic Biomarkers in Dementia","year":2025,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"National Science Foundation","keywords":"Dementia; Discriminative model; Character (mathematics); Cognition; Cognitive decline; Psychology; Computer science; Cognitive psychology; Artificial intelligence; Linguistics; Medicine; Disease; Mathematics; Psychiatry","score_opus":0.033594758036118215,"score_gpt":0.27707004961444714,"score_spread":0.24347529157832892,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412967876","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033187214,0.00075462094,0.6053695,0.0019793932,0.00447325,0.0016092125,0.00005283045,0.00054215465,0.35203183],"genre_scores_gemma":[0.47013378,0.00011908582,0.5257065,0.00190251,0.00021140373,0.00063066464,0.000032174754,0.0000282203,0.0012356051],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976476,0.00022258898,0.00044208815,0.00096099154,0.00033569703,0.00039106558],"domain_scores_gemma":[0.99853444,0.0001535873,0.00010622389,0.00093860994,0.000101812955,0.00016534682],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009883752,0.0002905118,0.00037435265,0.0007857261,0.000054183067,0.00020439894,0.0017582166,0.00018754667,0.00006595237],"category_scores_gemma":[0.0005571691,0.00029841985,0.00015404345,0.0007158534,0.000025881438,0.000044374716,0.0017026509,0.0003712167,0.000102640086],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000119933844,0.0016665471,0.06904505,0.0020301912,0.0017819759,0.0003776127,0.0047455765,0.00019148315,0.00056741794,0.010915383,0.01727143,0.8912874],"study_design_scores_gemma":[0.0029885855,0.000118592005,0.24146059,0.0038660932,0.000486451,0.000056054865,0.0002444242,0.5782983,0.010437933,0.022131283,0.1344485,0.0054632165],"about_ca_topic_score_codex":0.000085472304,"about_ca_topic_score_gemma":0.00001987149,"teacher_disagreement_score":0.8858242,"about_ca_system_score_codex":0.00008692691,"about_ca_system_score_gemma":0.00020338145,"threshold_uncertainty_score":0.9999468},"labels":[],"label_agreement":null},{"id":"W4412973321","doi":"10.1121/10.0038240","title":"Exploring the perception–production link in bilingual voices","year":2025,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Perception; Psychology; Production (economics); Quality (philosophy); Identification (biology); Identity (music); Cognitive psychology; Speech recognition; Acoustics; Computer science","score_opus":0.04558349218917922,"score_gpt":0.27866690866120813,"score_spread":0.2330834164720289,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412973321","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23938507,0.00021857166,0.62420434,0.13394123,0.0015861705,0.00017561179,9.823733e-7,0.000025182842,0.00046284572],"genre_scores_gemma":[0.9012277,0.0012859119,0.0937713,0.0030809732,0.00041149234,0.0000026944563,5.0707772e-8,0.000005685015,0.00021417029],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99880743,0.0002553282,0.0003529088,0.00009251132,0.0003471989,0.00014464196],"domain_scores_gemma":[0.9984637,0.0007799272,0.00023058914,0.00034194486,0.00015784547,0.000026026439],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012607408,0.00007939979,0.00016757216,0.00003362,0.00021057633,0.000035891007,0.0010955839,0.00002700379,0.000016168655],"category_scores_gemma":[0.0005789565,0.000035045086,0.0002556936,0.00066476164,0.00034108857,0.00021476585,0.00020325115,0.00040958848,0.000004581424],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003856196,0.00011371538,0.00017053251,0.000024281153,0.00009197437,6.000104e-7,0.004695511,0.0031935237,0.013506037,0.000058950536,0.0056124367,0.9724939],"study_design_scores_gemma":[0.0011477278,0.00045763867,0.08991466,0.001044651,0.0005569787,0.0002447768,0.054080244,0.7857336,0.025580324,0.021164248,0.019544415,0.000530761],"about_ca_topic_score_codex":0.000038904855,"about_ca_topic_score_gemma":0.0000018024286,"teacher_disagreement_score":0.9719631,"about_ca_system_score_codex":0.000058546946,"about_ca_system_score_gemma":0.000110731096,"threshold_uncertainty_score":0.20358856},"labels":[],"label_agreement":null},{"id":"W4412974457","doi":"10.1121/10.0037796","title":"Utilizing extended high frequencies for fricative identification","year":2025,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Intelligibility (philosophy); CLARITY; Identification (biology); Speech recognition; Random forest; Computer science; Acoustics; Artificial intelligence; Physics","score_opus":0.02347862433249369,"score_gpt":0.280669455454313,"score_spread":0.2571908311218193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412974457","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001648157,0.0002644677,0.98078334,0.01654656,0.0002889318,0.00013508268,0.0000050221133,0.0000131011675,0.00031530845],"genre_scores_gemma":[0.594293,0.00036490356,0.40297562,0.0020708407,0.000056192865,0.00000482147,1.801009e-7,0.000004572809,0.00022988072],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99893385,0.00013780563,0.00040049147,0.000091301976,0.0002943326,0.00014219208],"domain_scores_gemma":[0.997315,0.0014029093,0.0004957984,0.00034594128,0.0004068078,0.0000335368],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007833066,0.000080829406,0.00020263031,0.000026837095,0.00023930232,0.000039791266,0.0012447687,0.000040013747,0.000012288931],"category_scores_gemma":[0.00067377795,0.000042946787,0.0003458997,0.00043234465,0.00034195374,0.00014265788,0.00014088281,0.0001721974,0.0000022643396],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000073541705,0.00025624497,0.000025970317,0.00006333887,0.00043864324,3.355845e-7,0.0024809437,0.00030049507,0.10033269,0.0045137834,0.048270885,0.8432431],"study_design_scores_gemma":[0.0010065576,0.00031407858,0.010520042,0.00031056933,0.00069277606,0.00004595113,0.009588835,0.6331752,0.14517774,0.18793099,0.01093331,0.00030393468],"about_ca_topic_score_codex":0.000011886671,"about_ca_topic_score_gemma":1.6214217e-7,"teacher_disagreement_score":0.8429392,"about_ca_system_score_codex":0.000059396007,"about_ca_system_score_gemma":0.000115732175,"threshold_uncertainty_score":0.23131108},"labels":[],"label_agreement":null},{"id":"W4413051886","doi":"10.3233/shti250991","title":"A Proof-of-Concept Development on Speech Analysis for Concussion Detection","year":2025,"lang":"en","type":"article","venue":"Studies in health technology and informatics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Proof of concept; Computer science; Speech recognition; Natural language processing; Concussion; Medicine; Medical emergency; Injury prevention; Poison control; Operating system","score_opus":0.04934642542530765,"score_gpt":0.35157778503627135,"score_spread":0.3022313596109637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413051886","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06611292,0.0011866648,0.9273795,0.003344405,0.000334205,0.00077213946,0.0000027365468,0.00013067307,0.0007367704],"genre_scores_gemma":[0.8276442,0.00020447647,0.1712699,0.0006902527,0.0000030871065,0.00012793648,0.0000012324198,0.0000016026441,0.000057270197],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990748,0.000018490167,0.0005773741,0.00009854989,0.0000699508,0.00016083092],"domain_scores_gemma":[0.99935085,0.00018523465,0.0001916799,0.00016100986,0.000095726195,0.000015515761],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004623649,0.00007935576,0.00029842206,0.0012900073,0.00017843152,0.0000067834762,0.00015514136,0.00009336389,6.0196095e-7],"category_scores_gemma":[0.00031552973,0.00006296843,0.000027685674,0.0016072494,0.00012294066,0.00008979358,0.00011564729,0.000101872516,5.181021e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008394626,0.000024019639,0.0006234557,0.00027072465,0.00011264477,1.8091521e-7,0.001938821,0.000015393034,9.361633e-7,0.011784283,0.000052042782,0.9851691],"study_design_scores_gemma":[0.004378101,0.0025479542,0.009390264,0.0026377544,0.0001532771,0.000020952099,0.03746109,0.18763678,0.5939985,0.09333715,0.067484066,0.0009541347],"about_ca_topic_score_codex":0.0000017454427,"about_ca_topic_score_gemma":0.00003182656,"teacher_disagreement_score":0.98421496,"about_ca_system_score_codex":0.000082732215,"about_ca_system_score_gemma":0.00008071309,"threshold_uncertainty_score":0.2567778},"labels":[],"label_agreement":null},{"id":"W4413096419","doi":"10.1109/icc-robins64345.2025.11086131","title":"Optimized Efficientnet-B0 Framework for Speech Pathology Classification","year":2025,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Speech recognition; Artificial intelligence; Natural language processing","score_opus":0.037262661558918414,"score_gpt":0.3138960212722057,"score_spread":0.2766333597132873,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413096419","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012305073,0.000025238262,0.96251994,0.006540337,0.00063218817,0.000296471,0.000002128233,0.0002529127,0.02850025],"genre_scores_gemma":[0.020534568,0.000012458702,0.97341967,0.0025836788,0.00003077814,0.000087888955,0.0000042128577,0.000004415316,0.003322311],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99909157,0.00005635837,0.00020083992,0.0003535279,0.000099470555,0.00019823611],"domain_scores_gemma":[0.99869806,0.00064618007,0.000051613446,0.0004432682,0.00011906578,0.000041827396],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032742342,0.000090378475,0.00014485478,0.00016279731,0.00010826325,0.00010909453,0.0004892301,0.00012705909,0.0001408735],"category_scores_gemma":[0.0004060679,0.00007880893,0.000088821354,0.00039158794,0.000032866166,0.000091333124,0.00007236664,0.00007825164,0.00013015806],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011986994,0.000068143476,0.000022949282,0.000007042954,0.000009059613,0.0000023467844,0.00003573914,0.000007671376,0.00050930947,0.6394948,0.0034934103,0.35633758],"study_design_scores_gemma":[0.0016529241,0.00010770025,0.0028544436,0.00007430385,0.00003460848,0.000025890991,0.00019741575,0.56588703,0.07072788,0.31249148,0.045490474,0.00045587544],"about_ca_topic_score_codex":0.0000015204962,"about_ca_topic_score_gemma":7.7748376e-7,"teacher_disagreement_score":0.56587934,"about_ca_system_score_codex":0.000028325765,"about_ca_system_score_gemma":0.000051415016,"threshold_uncertainty_score":0.3213735},"labels":[],"label_agreement":null},{"id":"W4413205493","doi":"10.1109/eaic66483.2025.11101389","title":"DeepVoice: An End-to-End Speaker Recognition System Leveraging Convolutional and Recurrent Neural Networks for Robust Voice Identification","year":2025,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Speech recognition; Speaker recognition; End-to-end principle; Speaker identification; Convolutional neural network; Identification (biology); Speaker diarisation; Artificial intelligence","score_opus":0.04841114124058102,"score_gpt":0.27203916024032376,"score_spread":0.22362801899974274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413205493","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023077969,0.000083154795,0.9720949,0.0012100952,0.0012703426,0.0005421245,0.000017718836,0.0002624082,0.0014413078],"genre_scores_gemma":[0.90629643,0.000012103316,0.09182678,0.0008724927,0.0001979003,0.00017896813,0.000104827304,0.000011377688,0.0004991417],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99843913,0.0001314738,0.00037444395,0.0005852361,0.00019947102,0.0002702583],"domain_scores_gemma":[0.9988723,0.00029749758,0.00009869204,0.00028746075,0.00030591618,0.00013815962],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00066037744,0.00015596926,0.00016694603,0.00024005327,0.0003158043,0.0004308846,0.0002923637,0.00007737559,0.000041268086],"category_scores_gemma":[0.000090947186,0.00015598173,0.000063066036,0.00039257322,0.000033153807,0.0006591101,0.00009061849,0.00010012605,0.000033832097],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033003307,0.000076122014,0.00028191516,0.000080577905,0.000035248246,0.0000022261154,0.00014654083,0.000658371,0.0002606079,0.009290162,0.0019110717,0.98722416],"study_design_scores_gemma":[0.0003803131,0.000036948233,0.0085092,0.00009377249,0.000031376312,0.000026698528,0.00026074855,0.98790944,0.00093212206,0.0005689912,0.0010358768,0.00021453608],"about_ca_topic_score_codex":0.000033508586,"about_ca_topic_score_gemma":0.00007025764,"teacher_disagreement_score":0.98725104,"about_ca_system_score_codex":0.00011664011,"about_ca_system_score_gemma":0.00004309658,"threshold_uncertainty_score":0.636075},"labels":[],"label_agreement":null},{"id":"W4413441258","doi":"10.1613/jair.1.19171","title":"An MRP Formulation for Supervised Learning: Generalized Temporal Difference Learning Models","year":2025,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Royal Academy of Engineering; UK Research and Innovation","keywords":"Computer science; Artificial intelligence; Supervised learning; Temporal difference learning; Machine learning; Artificial neural network","score_opus":0.30398104370192736,"score_gpt":0.4386553844920129,"score_spread":0.13467434079008556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413441258","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16727781,0.000083197054,0.83074164,0.0010162375,0.00021826146,0.00022739657,7.210139e-7,0.00003851196,0.00039619213],"genre_scores_gemma":[0.9289361,0.00011138913,0.070235915,0.00004562367,0.00016858634,0.00001718525,0.0000038456415,0.000010616401,0.00047073426],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968988,0.00071483053,0.00078363245,0.00030508274,0.0008193708,0.00047831095],"domain_scores_gemma":[0.9964211,0.000980698,0.00020387645,0.00025978158,0.0019434534,0.00019107612],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004473045,0.00013670791,0.0002997281,0.00092640024,0.0005681672,0.0006026554,0.0010788,0.0001237518,0.00007302209],"category_scores_gemma":[0.0013040028,0.000117797856,0.00019073869,0.0009670589,0.0000682543,0.00097538513,0.00010849336,0.00075643224,0.00002546778],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024616937,0.00021324537,0.00042018335,0.000027805017,0.000032610613,0.000010763599,0.0009859696,0.010607947,0.02596856,0.1288812,0.0000752419,0.8325303],"study_design_scores_gemma":[0.00007628693,0.0004746286,0.0000720478,0.00006417239,0.0000057608704,0.0000070328483,0.00073358795,0.76525235,0.07037262,0.16230457,0.0005375627,0.000099387544],"about_ca_topic_score_codex":0.0000492011,"about_ca_topic_score_gemma":0.000022099148,"teacher_disagreement_score":0.8324309,"about_ca_system_score_codex":0.0001237488,"about_ca_system_score_gemma":0.00041334843,"threshold_uncertainty_score":0.581142},"labels":[],"label_agreement":null},{"id":"W4413458003","doi":"10.1109/iwbf63717.2025.11113424","title":"A Novel Hybrid Neural Embedding Extractor for Text Independent Speaker Verification","year":2025,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Extractor; Speaker verification; Speech recognition; Embedding; Speaker recognition; Artificial intelligence; Natural language processing; Pattern recognition (psychology); Engineering","score_opus":0.0323791740611883,"score_gpt":0.29495054214609395,"score_spread":0.26257136808490567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413458003","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020525219,0.000013838425,0.9658248,0.0011449133,0.0004930891,0.00024511645,0.0000051019056,0.00015807709,0.011589884],"genre_scores_gemma":[0.82553065,0.0000024755598,0.17092288,0.00083825475,0.00003036577,0.000054504228,0.0000044177928,0.000005030572,0.0026114346],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99920374,0.000017778602,0.00017678777,0.0003009059,0.00013329816,0.00016749857],"domain_scores_gemma":[0.9993223,0.00020972236,0.00004361232,0.00028986135,0.00008852721,0.00004596538],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022470883,0.00008781645,0.00009796161,0.00012319791,0.000088117034,0.0001915176,0.00036268623,0.00003202578,0.000112859976],"category_scores_gemma":[0.00011721618,0.000078615485,0.00007776639,0.00016304417,0.000011761997,0.00031419127,0.000060143364,0.000057201403,0.00006206213],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000293258,0.00024749152,0.00027111027,0.000038577364,0.000040085597,0.0000031245713,0.00009980633,0.000025973179,0.059964463,0.08397011,0.0059127137,0.84939724],"study_design_scores_gemma":[0.0010924294,0.000041170944,0.018347254,0.000046842197,0.000018535657,0.000042808533,0.000100144964,0.80125797,0.1437083,0.0034642285,0.03153765,0.00034264874],"about_ca_topic_score_codex":0.000014050756,"about_ca_topic_score_gemma":0.000007101721,"teacher_disagreement_score":0.8490546,"about_ca_system_score_codex":0.000039809544,"about_ca_system_score_gemma":0.000045807792,"threshold_uncertainty_score":0.32058463},"labels":[],"label_agreement":null},{"id":"W4413979917","doi":"10.1109/taslpro.2025.3606235","title":"Exploring Cross-Utterance Speech Contexts for Conformer-Transducer Speech Recognition Systems","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"National Natural Science Foundation of China","keywords":"Utterance; Speech recognition; Computer science; Speech processing; Natural language processing; Artificial intelligence","score_opus":0.05215438308880152,"score_gpt":0.2992675605736401,"score_spread":0.2471131774848386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413979917","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11980152,0.0010630642,0.87376904,0.000498502,0.0012337288,0.0007630979,0.00007121284,0.00045300872,0.0023468288],"genre_scores_gemma":[0.9333922,0.0002947299,0.062074233,0.0011151431,0.00015285269,0.00046740976,0.000011550449,0.000040497656,0.0024513567],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9977495,0.000078701174,0.0005482937,0.0007471764,0.00033322867,0.0005430872],"domain_scores_gemma":[0.9986805,0.00030699998,0.00015668436,0.00037293808,0.000321503,0.00016137595],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005942423,0.00036465478,0.00042636154,0.00048573685,0.000675553,0.0009454034,0.00038349567,0.00016094223,0.00006259516],"category_scores_gemma":[0.000044466546,0.0003555264,0.00017611818,0.0006418905,0.000106904365,0.001715027,0.0000045746287,0.00033663475,0.000050993356],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000940089,0.000107013686,0.000009680946,0.00042594393,0.000053383093,0.00003633463,0.00087123626,0.00002368356,0.006907953,0.000029759132,0.000054538843,0.9913865],"study_design_scores_gemma":[0.002664007,0.00016680705,0.00016473026,0.0015803495,0.000114182476,0.00030452953,0.0013378861,0.023442108,0.9660814,0.00042983622,0.0028496813,0.0008644996],"about_ca_topic_score_codex":0.000088741144,"about_ca_topic_score_gemma":0.00006912707,"teacher_disagreement_score":0.99052197,"about_ca_system_score_codex":0.000096890326,"about_ca_system_score_gemma":0.00013576262,"threshold_uncertainty_score":0.9998897},"labels":[],"label_agreement":null},{"id":"W4414039198","doi":"10.31234/osf.io/39fqa_v3","title":"A review of computational models of word recognition and pronunciation","year":2025,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Pronunciation; Computer science; Word (group theory); Natural language processing; Speech recognition; Artificial intelligence; Linguistics; Philosophy","score_opus":0.05549418121023892,"score_gpt":0.2737425653071686,"score_spread":0.2182483840969297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414039198","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033840165,0.0025353467,0.97208875,0.0010853122,0.000038517257,0.0002156133,0.000005643556,0.000032889428,0.020613898],"genre_scores_gemma":[0.21347003,0.006999024,0.77488375,0.00422511,0.000010031473,0.000040302744,0.000028327217,0.0000042884803,0.00033911422],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.999506,0.000036711393,0.00021320488,0.00010228304,0.000102700455,0.000039106424],"domain_scores_gemma":[0.9994711,0.000106262196,0.00008487863,0.00007969467,0.00024493854,0.000013092287],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022975686,0.000037082675,0.00011297156,0.00008802979,0.00001366091,0.0000074994678,0.0000799035,0.000018491986,0.00003747329],"category_scores_gemma":[0.00007324286,0.000032803044,0.000027881842,0.00025490476,0.00001661313,0.0001878305,0.00003221185,0.000019205829,0.0000034347438],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000025147413,0.000041189058,0.000022580894,0.0012643037,0.000012109628,9.7918786e-8,0.000039129154,0.000014387953,0.000057667792,0.017008744,0.0009641121,0.9805732],"study_design_scores_gemma":[0.00048065596,0.000049005983,0.0019465453,0.008977862,0.000036772526,0.0000059578747,0.000028012477,0.26560122,0.010626721,0.71155065,0.0005416585,0.00015491426],"about_ca_topic_score_codex":0.000008152669,"about_ca_topic_score_gemma":0.0000017262898,"teacher_disagreement_score":0.98041826,"about_ca_system_score_codex":0.000007728196,"about_ca_system_score_gemma":0.000048634185,"threshold_uncertainty_score":0.13376693},"labels":[],"label_agreement":null},{"id":"W4414069553","doi":"10.3390/sym17091478","title":"Phoneme-Aware Augmentation for Robust Cantonese ASR Under Low-Resource Conditions","year":2025,"lang":"en","type":"article","venue":"Symmetry","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"National Natural Science Foundation of China; Natural Science Foundation of Shandong Province; Texas Space Grant Consortium","keywords":"Dropout (neural networks); Connectionism; Formant; Lexicon; Word error rate; Field (mathematics); Speech processing; Conjunction (astronomy)","score_opus":0.02059244963797242,"score_gpt":0.28637632700530685,"score_spread":0.26578387736733444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414069553","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010186709,0.000056508215,0.97169477,0.0033255636,0.00060239766,0.00033240218,0.000057940273,0.00021448084,0.013529233],"genre_scores_gemma":[0.9188188,0.0000152543425,0.06289272,0.007959648,0.00014463371,0.0002717975,0.00016323559,0.000023287303,0.009710629],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99908733,0.000049349146,0.0001907307,0.00030158446,0.00015757693,0.00021345206],"domain_scores_gemma":[0.99916124,0.00030494726,0.000058155583,0.0003058065,0.0001031779,0.00006669308],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016386999,0.000112681715,0.00012995086,0.00024853402,0.0002343961,0.0001295116,0.00033681668,0.000072167626,0.00014934463],"category_scores_gemma":[0.000073997704,0.00011259076,0.000095776384,0.00057358126,0.00003621919,0.00021285523,0.00006870812,0.00007191278,0.000091439426],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005677731,0.00073802576,0.0012088193,0.0003504778,0.00039544853,0.00002219717,0.0006477591,0.0006337108,0.0062175523,0.31209874,0.30279407,0.37483644],"study_design_scores_gemma":[0.010234766,0.000308675,0.04271175,0.0010165172,0.00036610308,0.00007357859,0.008650389,0.3901144,0.3105689,0.13967338,0.093574345,0.0027071966],"about_ca_topic_score_codex":0.00004329624,"about_ca_topic_score_gemma":0.000051939103,"teacher_disagreement_score":0.90880203,"about_ca_system_score_codex":0.000088101784,"about_ca_system_score_gemma":0.00009922739,"threshold_uncertainty_score":0.45913178},"labels":[],"label_agreement":null},{"id":"W4414371545","doi":"10.1145/3769089","title":"A Systematic Literature Review on Bias Evaluation and Mitigation in Automatic Speech Recognition Models for Low-Resource African Languages","year":2025,"lang":"en","type":"article","venue":"ACM Computing Surveys","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Systematic review; Adversarial system; Diversity (politics); Languages of Africa; Linguistic diversity","score_opus":0.05212062967271452,"score_gpt":0.32011294596393874,"score_spread":0.2679923162912242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414371545","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42261726,0.039202567,0.512104,0.006912911,0.0007026805,0.011548921,0.000049752063,0.0010321548,0.005829776],"genre_scores_gemma":[0.87499875,0.0007517376,0.12090742,0.0025837498,0.00006653104,0.00034683204,0.00019274146,0.000026782682,0.00012545934],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99612814,0.0023379135,0.00055351073,0.00043481868,0.00033711473,0.00020848251],"domain_scores_gemma":[0.9957265,0.003172363,0.00024269303,0.0005173204,0.00029742665,0.000043662378],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009176481,0.00017857623,0.0004079393,0.00037502943,0.00011106477,0.00024172566,0.00039402457,0.00008356649,0.0000033917772],"category_scores_gemma":[0.0058942954,0.00015948631,0.00007829514,0.0009758464,0.000017501268,0.00025303126,0.00010700753,0.00012651879,0.000007962172],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000026663856,0.00007445347,0.00007676258,0.030142166,0.0000341316,0.000006468317,0.0006076605,0.0000766253,0.00002957773,0.00042094252,0.00039024235,0.9681383],"study_design_scores_gemma":[0.00046346232,0.000039720442,0.0016123663,0.124156274,0.00004981257,0.000015755515,0.000093224626,0.86433196,0.00054586254,0.008491462,0.000005677458,0.00019442607],"about_ca_topic_score_codex":0.000010961,"about_ca_topic_score_gemma":0.000027313825,"teacher_disagreement_score":0.9679439,"about_ca_system_score_codex":0.0000932312,"about_ca_system_score_gemma":0.00005512531,"threshold_uncertainty_score":0.7056448},"labels":[],"label_agreement":null},{"id":"W4414537366","doi":"10.47392/irjaeh.2025.0550","title":"Machine Learning Methods for Speech Emotion Recognition","year":2025,"lang":"en","type":"article","venue":"International Research Journal on Advanced Engineering Hub (IRJAEH)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Semtech (Canada)","funders":"","keywords":"Convolutional neural network; Support vector machine; Robustness (evolution); Feature extraction; Emotion classification; Mel-frequency cepstrum; Random forest; Generalization; Feature (linguistics); Benchmark (surveying)","score_opus":0.07098266512585713,"score_gpt":0.43011916330131245,"score_spread":0.35913649817545534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414537366","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002022898,0.00020432034,0.98529637,0.003414904,0.0020646348,0.00024273277,0.000008714398,0.00015996596,0.0065854657],"genre_scores_gemma":[0.036329985,0.00078829343,0.9577475,0.00027186205,0.00039765768,0.00009359445,0.000026045422,0.000033428114,0.004311604],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978539,0.00024663025,0.00040325418,0.0003606376,0.00068883225,0.00044676507],"domain_scores_gemma":[0.99663657,0.0017775572,0.00010380976,0.00020481204,0.00111023,0.00016702793],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032247787,0.00017168422,0.00019198284,0.001398335,0.0003052152,0.00045261704,0.000891952,0.00008493168,0.00014391073],"category_scores_gemma":[0.006476077,0.0001682059,0.00016638842,0.0006416403,0.000026402822,0.0006246408,0.0001376198,0.001032511,0.000069125796],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007304713,0.00006389247,0.000014763405,0.000018559998,0.0000738331,0.00002005822,0.0000314022,0.0049853316,0.009246807,0.010581255,0.00035363398,0.97453743],"study_design_scores_gemma":[0.0012816018,0.00029769394,0.00032455914,0.00055984396,0.0000073966494,0.00016402903,0.00005092597,0.5973336,0.05065658,0.032880902,0.31615883,0.00028401948],"about_ca_topic_score_codex":0.000005000834,"about_ca_topic_score_gemma":0.0000011931438,"teacher_disagreement_score":0.9742534,"about_ca_system_score_codex":0.0005203319,"about_ca_system_score_gemma":0.00011535025,"threshold_uncertainty_score":0.77529365},"labels":[],"label_agreement":null},{"id":"W4414774870","doi":"10.64701/ijrc/345/8907","title":"Speech Emotion Recognition with Hybrid CNN- LSTM and Transformers Models: Evaluating the Hybrid Model Using Grad-CAM","year":2024,"lang":"en","type":"article","venue":"International Journal of Research in Computing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Transformer; Convolutional neural network; Encoder; Feature extraction; Pattern recognition (psychology); Artificial neural network; Mel-frequency cepstrum; Hybrid neural network; Spectrogram","score_opus":0.2764907419420464,"score_gpt":0.43994649405967867,"score_spread":0.16345575211763225,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414774870","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5008224,0.00021906986,0.49605197,0.0020993506,0.00028709837,0.00010787453,0.000003103118,0.000020918886,0.00038819568],"genre_scores_gemma":[0.89219457,0.000154951,0.10727853,0.00008064772,0.00026130778,0.0000017880358,0.0000016475124,0.00001374188,0.000012820924],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966872,0.00038004015,0.0005244861,0.00029484858,0.0017954528,0.00031799648],"domain_scores_gemma":[0.9975729,0.0010072413,0.00014047991,0.00010879078,0.0010755664,0.0000950332],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0062512276,0.0001280943,0.00016322594,0.00096550846,0.00019115258,0.000850528,0.0006960512,0.00002954107,0.000007863702],"category_scores_gemma":[0.00019254065,0.000090822075,0.00008754446,0.0004707404,0.00010155832,0.0012389899,0.00014333993,0.0007721386,0.0000047789654],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006722728,0.000044012093,0.00005268604,0.00003088946,0.00007959018,0.00033151798,0.00067000487,0.037512384,0.0008208554,0.00053181616,0.000038801918,0.9598202],"study_design_scores_gemma":[0.00037190598,0.00014530531,0.0000402514,0.0012889887,0.000008894564,0.0028518962,0.0002571782,0.94372237,0.0021198324,0.049070686,0.000020629304,0.00010203583],"about_ca_topic_score_codex":0.000047768233,"about_ca_topic_score_gemma":0.0000054200855,"teacher_disagreement_score":0.95971817,"about_ca_system_score_codex":0.00028973402,"about_ca_system_score_gemma":0.00039055542,"threshold_uncertainty_score":0.8201662},"labels":[],"label_agreement":null},{"id":"W4414789198","doi":"10.48550/arxiv.2509.20786","title":"LiLAW: Lightweight Learnable Adaptive Weighting to Learn Sample Difficulty & Improve Noisy Training","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; University of Toronto","keywords":"Robustness (evolution); Weighting; Hyperparameter; Artificial neural network; Training set; Stochastic gradient descent; Gradient descent; Generalization; Noisy data","score_opus":0.09525507824844402,"score_gpt":0.2889259135805544,"score_spread":0.19367083533211038,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414789198","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38179246,0.0002588513,0.56650704,0.0047006416,0.0041205245,0.0013313575,0.00021165296,0.0014283794,0.03964908],"genre_scores_gemma":[0.514066,0.00013971954,0.44106123,0.003481394,0.0014480937,0.0005322859,0.00013245546,0.00011074378,0.039028082],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9955286,0.00026475056,0.00077139534,0.0018730046,0.00059109327,0.0009711519],"domain_scores_gemma":[0.9963182,0.0009081304,0.00039529824,0.0015569655,0.0004041796,0.00041722512],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006957324,0.00068396394,0.00087267056,0.00046339742,0.0005043987,0.00048415014,0.002177657,0.00051857997,0.00029516357],"category_scores_gemma":[0.0010752677,0.0006475705,0.0004660319,0.00070268975,0.0000689856,0.00035993636,0.0027091438,0.0013494793,0.0012482965],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018883059,0.0009685503,0.019408975,0.00061858393,0.0012836237,0.00020683002,0.030076306,0.0010708895,0.017044762,0.01630169,0.015924709,0.89690626],"study_design_scores_gemma":[0.0025486453,0.0006299721,0.04053039,0.003958978,0.00045678165,0.000060840324,0.002389534,0.03640204,0.09237946,0.017391069,0.79584676,0.0074055498],"about_ca_topic_score_codex":0.000621777,"about_ca_topic_score_gemma":0.00029449016,"teacher_disagreement_score":0.8895007,"about_ca_system_score_codex":0.00027555405,"about_ca_system_score_gemma":0.0004851776,"threshold_uncertainty_score":0.99959755},"labels":[],"label_agreement":null},{"id":"W4414870063","doi":"10.1101/2025.10.05.680511","title":"Mixture Models for Domain-Adaptive Brain Decoding","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Decoding methods; Mixture model; Weighting; Scalability; Selection (genetic algorithm); Generalization; Inference; Model selection","score_opus":0.027392009061669487,"score_gpt":0.23934329152199169,"score_spread":0.2119512824603222,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414870063","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007002473,0.0005418489,0.985461,0.002236605,0.0019345267,0.0012724956,0.00043008025,0.00089219457,0.00022877369],"genre_scores_gemma":[0.24909471,0.00008835316,0.7472952,0.0021803742,0.00042188485,0.00078897754,3.5393543e-7,0.00007457963,0.000055565837],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99649507,0.00019281323,0.0005881373,0.0015725511,0.00043222224,0.00071921287],"domain_scores_gemma":[0.9962681,0.00056817196,0.0003921653,0.0017219405,0.00075705885,0.0002925935],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009752784,0.00064568623,0.0007097488,0.0005310917,0.00032008922,0.0005955372,0.001957773,0.0007096385,0.000020421905],"category_scores_gemma":[0.0003346967,0.00070035004,0.00040551883,0.0006640483,0.0000750984,0.00044860863,0.0010455718,0.0006454499,0.000034920035],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020638705,0.0008171841,0.00023034656,0.001990911,0.0016058905,0.00024597772,0.00026258494,0.0011730832,0.16865687,0.7908058,0.032952186,0.0010527611],"study_design_scores_gemma":[0.0027991375,0.00020312169,0.0014010434,0.0030025747,0.00029764263,1.0682404e-7,0.000021818634,0.45600381,0.47213647,0.0076358295,0.05172053,0.0047779],"about_ca_topic_score_codex":0.000014933491,"about_ca_topic_score_gemma":0.0000031611453,"teacher_disagreement_score":0.78317,"about_ca_system_score_codex":0.00032999198,"about_ca_system_score_gemma":0.0009143908,"threshold_uncertainty_score":0.99954474},"labels":[],"label_agreement":null},{"id":"W4414995823","doi":"10.21203/rs.3.rs-7808032/v1","title":"Mixed Signal Design Using C++ and DSP Acceleration for Low Latency and Secure Speech Systems","year":2025,"lang":"en","type":"preprint","venue":"Research Square","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Latency (audio); Digital signal processing; Low latency (capital markets); Voice activity detection; Novelty; Speech processing; Signal processing; Digital signal processor","score_opus":0.24811628790915286,"score_gpt":0.39797848103519823,"score_spread":0.14986219312604537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414995823","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029674632,0.001812721,0.96372056,0.0005193195,0.00045822744,0.003093891,0.00012739155,0.00013445583,0.00045881758],"genre_scores_gemma":[0.6319133,0.0010939438,0.36407107,0.00006550741,0.0005681103,0.0008136845,0.0000848612,0.000049088965,0.0013404296],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968899,0.0007870488,0.00032473917,0.0008415637,0.00067918363,0.0004775603],"domain_scores_gemma":[0.99718773,0.0011921959,0.00009716285,0.00046347204,0.00088063156,0.00017878844],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0025488236,0.00023442646,0.00035916627,0.0005894568,0.000433736,0.0014447818,0.0005460598,0.00037480405,0.000017726385],"category_scores_gemma":[0.00035110765,0.00022163204,0.00007692503,0.00036438095,0.00008239445,0.00027066664,0.0009327797,0.0005845368,0.000005044236],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030154453,0.00046295146,0.0009973362,0.019414555,0.00045282158,0.00023238116,0.0029786655,0.0028835065,0.009448982,0.02607506,0.010043726,0.92670846],"study_design_scores_gemma":[0.00042499776,0.00013433718,0.0003256913,0.0019113806,0.000018264682,0.000030418318,0.00024196859,0.9777051,0.008902959,0.009475983,0.0004933198,0.00033553396],"about_ca_topic_score_codex":0.00015252031,"about_ca_topic_score_gemma":0.00001618405,"teacher_disagreement_score":0.9748216,"about_ca_system_score_codex":0.00014156262,"about_ca_system_score_gemma":0.0005570885,"threshold_uncertainty_score":0.9995918},"labels":[],"label_agreement":null},{"id":"W4415003378","doi":"10.1109/ciacon65473.2025.11189784","title":"VoiceIDE: Real-Time Code Editing Through Speech Recognition","year":2025,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Code (set theory); Java; Coding (social sciences); Speaker recognition; Speech technology; Speech processing; Acoustic model; Speech analytics","score_opus":0.03095695232509905,"score_gpt":0.2807548199204027,"score_spread":0.24979786759530365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415003378","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006765251,0.000013885104,0.2517375,0.004228693,0.00066238735,0.00016801505,0.000008213685,0.0008071129,0.73560894],"genre_scores_gemma":[0.0074440134,0.00011347936,0.96417147,0.0040993616,0.00030152517,0.0000365982,0.000023312903,0.000014478104,0.023795776],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99871856,0.000088071974,0.00028330288,0.00041081218,0.00022532803,0.00027393954],"domain_scores_gemma":[0.9989787,0.0003432066,0.00007170905,0.0003873289,0.00016641876,0.0000526648],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0003592343,0.0001360728,0.00017253374,0.00012709785,0.00016531559,0.00021119227,0.00046958454,0.00009033372,0.00109746],"category_scores_gemma":[0.00024962885,0.00012745836,0.000088661385,0.00059168617,0.000032117176,0.00074370165,0.00014662146,0.0001071755,0.002652478],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000036579095,0.00006094234,0.00005957433,0.000014485046,0.000024972427,0.000021283942,0.00008552722,2.871422e-7,0.0036068396,0.006782477,0.055789616,0.93355036],"study_design_scores_gemma":[0.0011913561,0.000085773296,0.0014190451,0.00036647375,0.000056504814,0.000096489275,0.0003263854,0.02641031,0.6539439,0.18984571,0.12540628,0.0008517739],"about_ca_topic_score_codex":0.0001250082,"about_ca_topic_score_gemma":0.000036896236,"teacher_disagreement_score":0.93269855,"about_ca_system_score_codex":0.0000483218,"about_ca_system_score_gemma":0.00006199225,"threshold_uncertainty_score":0.99981564},"labels":[],"label_agreement":null},{"id":"W4415540898","doi":"10.1145/3746027.3754745","title":"Pseudo-Autoregressive Neural Codec Language Models for Efficient Zero-Shot Text-to-Speech Synthesis","year":2025,"lang":"","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Microsoft (Canada)","funders":"National Natural Science Foundation of China","keywords":"Autoregressive model; Language model; Set (abstract data type); Inference; Codec; Face (sociological concept); Speech processing; Speech synthesis","score_opus":0.03375509139618933,"score_gpt":0.2939912735728801,"score_spread":0.26023618217669076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415540898","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033670712,0.0005371466,0.9050375,0.0076442487,0.002360189,0.0024073555,0.000240033,0.0005050578,0.04759775],"genre_scores_gemma":[0.8394675,0.00003788143,0.13449806,0.005554986,0.00016625064,0.0006902854,0.00000756563,0.00006465961,0.019512765],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.994107,0.00033565224,0.0011592202,0.0020156347,0.0009149436,0.0014675331],"domain_scores_gemma":[0.9938671,0.0027479853,0.0002978972,0.0017224721,0.00074144365,0.0006230983],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0010183532,0.00085586077,0.0010651489,0.0010462727,0.0007447934,0.0011155277,0.0024453013,0.0004060846,0.00090043206],"category_scores_gemma":[0.0012890773,0.0007726532,0.00077209476,0.0015045834,0.00020905271,0.00044822975,0.0008643898,0.00035087706,0.00052517094],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021081074,0.0006940097,0.000012816553,0.00018608147,0.00023174044,0.00009836427,0.002167668,0.006734187,0.0026784264,0.02597159,0.015917085,0.9450972],"study_design_scores_gemma":[0.00072318316,0.0001292943,0.00007774804,0.0004621225,0.00017507313,0.000036023925,0.00068177946,0.8764149,0.117309615,0.0017685337,0.0014141653,0.0008075829],"about_ca_topic_score_codex":0.00019067203,"about_ca_topic_score_gemma":0.000072008464,"teacher_disagreement_score":0.9442896,"about_ca_system_score_codex":0.0002986509,"about_ca_system_score_gemma":0.00048310639,"threshold_uncertainty_score":0.9999214},"labels":[],"label_agreement":null},{"id":"W4415898436","doi":"10.48550/arxiv.2503.06211","title":"Late Fusion and Multi-Level Fission Amplify Cross-Modal Transfer in Text-Speech LMs","year":2025,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Principle of compositionality; Feature (linguistics); Representation (politics); Process (computing); Hierarchy; Modality (human–computer interaction); Transfer (computing)","score_opus":0.1290470316641667,"score_gpt":0.23679426623934757,"score_spread":0.10774723457518087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415898436","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62082404,0.000063020816,0.37617522,0.00012558911,0.0003608759,0.00032310112,0.00007303851,0.00016762478,0.0018874662],"genre_scores_gemma":[0.98321223,0.00070337654,0.009752463,0.00023939427,0.000025996955,0.0000019496774,0.00002047176,0.0000129796135,0.0060311384],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978992,0.00016630847,0.00026474454,0.0012192972,0.00009956152,0.00035093207],"domain_scores_gemma":[0.99877834,0.00017315047,0.000071135175,0.00068773935,0.00011641184,0.00017321901],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003235913,0.0003357507,0.00037064467,0.0005465238,0.00017260626,0.00020531612,0.0010073022,0.00053256634,0.00009752309],"category_scores_gemma":[0.000047167006,0.00036462766,0.00015157399,0.0005693472,0.000110194276,0.00035112552,0.0011470049,0.00068574655,0.000052963973],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000784929,0.0024189744,0.083710365,0.0014305651,0.00046185922,0.003985883,0.0039327466,0.026285307,0.004619989,0.06927523,0.00093141396,0.80216277],"study_design_scores_gemma":[0.0029164646,0.000054569995,0.08140884,0.0007555294,0.0000624576,0.000014592176,0.00008174092,0.8956287,0.0036662384,0.012651073,0.0016311496,0.0011286511],"about_ca_topic_score_codex":0.00033882947,"about_ca_topic_score_gemma":0.00031466785,"teacher_disagreement_score":0.8693434,"about_ca_system_score_codex":0.00013588657,"about_ca_system_score_gemma":0.00015517863,"threshold_uncertainty_score":0.99988055},"labels":[],"label_agreement":null},{"id":"W4415987807","doi":"10.48550/arxiv.2508.21193","title":"Benchmarking Large Pretrained Multilingual Models on Québec French Speech Recognition","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Benchmarking; Pipeline (software); Benchmark (surveying); Variety (cybernetics); Language model; Word error rate","score_opus":0.08065248834183726,"score_gpt":0.2909048515514014,"score_spread":0.21025236320956414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415987807","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84507143,0.0002193808,0.110144205,0.0012053838,0.003108394,0.0009249897,0.0002560034,0.00094536773,0.03812485],"genre_scores_gemma":[0.92105126,0.00014943215,0.07358499,0.0018282436,0.0006179876,0.00017771998,0.00019535454,0.00003962713,0.0023553509],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99637926,0.00025677457,0.00067415746,0.0014852313,0.0005748775,0.00062969927],"domain_scores_gemma":[0.99728304,0.0005211695,0.00033788098,0.0013125014,0.0003594667,0.00018595744],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007767501,0.00055280956,0.0005692718,0.0005196338,0.00027596517,0.0002373415,0.0014309426,0.0005922866,0.00048037537],"category_scores_gemma":[0.0004526127,0.000571234,0.00039009817,0.00039934673,0.00005067833,0.00036047804,0.0011428862,0.0011311476,0.000442269],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002851012,0.0006086987,0.007187373,0.00024031858,0.00021679446,0.00014060065,0.002033976,0.0002059525,0.00016164397,0.00032427002,0.0024011987,0.9864507],"study_design_scores_gemma":[0.0033575615,0.00043795016,0.043333944,0.0054790736,0.00032658176,0.00006093875,0.00027833358,0.8235104,0.06939868,0.04023024,0.009251086,0.0043352162],"about_ca_topic_score_codex":0.0024139779,"about_ca_topic_score_gemma":0.0024603251,"teacher_disagreement_score":0.98211545,"about_ca_system_score_codex":0.00027913236,"about_ca_system_score_gemma":0.0007871603,"threshold_uncertainty_score":0.9996739},"labels":[],"label_agreement":null},{"id":"W4415991972","doi":"10.48550/arxiv.2508.21631","title":"Towards Improved Speech Recognition through Optimized Synthetic Data Generation","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Synthetic data; Training set; Voice activity detection; Speech synthesis; Acoustic model; Encoding (memory); Pattern recognition (psychology)","score_opus":0.19076982838371884,"score_gpt":0.3255550460538047,"score_spread":0.13478521767008586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415991972","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.059380956,0.00047040134,0.9000242,0.004978691,0.00618733,0.0014573985,0.0006972426,0.0010884245,0.025715383],"genre_scores_gemma":[0.052247085,0.0014902687,0.9378926,0.002457901,0.001062319,0.0002918455,0.0026393472,0.00005347183,0.0018651655],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99600726,0.00036354328,0.00074301875,0.001996439,0.0004365225,0.00045322513],"domain_scores_gemma":[0.99502516,0.00018972789,0.00039813356,0.0038361338,0.00043010397,0.00012072491],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00091467064,0.0005078237,0.0006237942,0.00023454257,0.00022678716,0.00053531973,0.0032045403,0.0005419724,0.00047455617],"category_scores_gemma":[0.0008928782,0.0005075318,0.00023529406,0.00039753268,0.000073965086,0.0011026254,0.0038395512,0.0007102528,0.0005277586],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032842985,0.00028072397,0.00014401523,0.00018443387,0.0002629079,0.00004723616,0.00029338693,0.000032211603,0.003124446,0.00014543236,0.008297286,0.9871551],"study_design_scores_gemma":[0.0017048041,0.000091644535,0.00097198837,0.0008479251,0.00043711005,0.00007052635,0.00007979333,0.7465713,0.22507136,0.010470469,0.011674445,0.0020086684],"about_ca_topic_score_codex":0.00034094663,"about_ca_topic_score_gemma":0.00005005637,"teacher_disagreement_score":0.9851464,"about_ca_system_score_codex":0.00015376577,"about_ca_system_score_gemma":0.00056556164,"threshold_uncertainty_score":0.9997376},"labels":[],"label_agreement":null},{"id":"W4416143831","doi":"10.65148/ecn/2025019","title":"Personalized Text to Speech Synthesis through Few Shot Speaker Adaptation with Contrastive Learning","year":2025,"lang":"en","type":"article","venue":"Elaris Computing Nexus","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trinity College","funders":"","keywords":"Naturalness; Similarity (geometry); Speaker recognition; Mean opinion score; Speech synthesis; Encoder; Feature learning; Word error rate; Speaker diarisation","score_opus":0.02728395361844038,"score_gpt":0.2702029549770197,"score_spread":0.2429190013585793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416143831","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022633806,0.00011620042,0.9205774,0.0020260226,0.0003398126,0.000352365,0.00000224597,0.00046418773,0.05348794],"genre_scores_gemma":[0.74504864,0.0000050386507,0.25201073,0.001451155,0.00008119529,0.00001764244,0.0000030885276,0.00001938585,0.0013631126],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976974,0.0002959959,0.00035305205,0.000729697,0.0004432402,0.00048062875],"domain_scores_gemma":[0.9978153,0.0012829246,0.00015585175,0.00035712877,0.0002664168,0.00012236746],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005286428,0.00029003483,0.00040808663,0.0002336105,0.00047686463,0.00041355664,0.0005804159,0.000107387576,0.000116131996],"category_scores_gemma":[0.0006886112,0.0002623815,0.00011497708,0.001111245,0.00007367441,0.00032300086,0.00020849341,0.0003552992,0.00025276266],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000120147146,0.00015660533,0.0008683947,0.000036330777,0.00024711198,0.00012503754,0.007817047,0.003234201,0.0005639483,0.023823483,0.0016981603,0.96130955],"study_design_scores_gemma":[0.00316012,0.0005983626,0.015329481,0.0020624914,0.00027781771,0.00026073743,0.008620107,0.85957605,0.03244366,0.004119351,0.07147193,0.0020798838],"about_ca_topic_score_codex":0.00017394256,"about_ca_topic_score_gemma":0.000038574013,"teacher_disagreement_score":0.95922965,"about_ca_system_score_codex":0.00012642863,"about_ca_system_score_gemma":0.00016403086,"threshold_uncertainty_score":0.99998283},"labels":[],"label_agreement":null},{"id":"W4416250889","doi":"10.1109/ijcnn64981.2025.11228198","title":"A Hybrid Neural Approach to Speaker Verification with an Improved Additive Angular Margin Loss","year":2025,"lang":"","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Softmax function; Pattern recognition (psychology); Artificial neural network; Feature extraction; Margin (machine learning); Feature (linguistics); Noise (video); Speaker recognition; Context (archaeology)","score_opus":0.015968510006563092,"score_gpt":0.23797865633334325,"score_spread":0.22201014632678015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416250889","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.073110536,0.000038025435,0.86124563,0.0019366734,0.0004268986,0.0013008359,0.00007084232,0.00023392777,0.06163664],"genre_scores_gemma":[0.7902816,0.000013163312,0.19906054,0.0033485664,0.00010509336,0.00018295413,0.000060899216,0.000026209336,0.0069210017],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99675137,0.0002869032,0.000463157,0.0014551926,0.0004178216,0.0006255733],"domain_scores_gemma":[0.99766177,0.00009354145,0.000134422,0.0012507895,0.00046305123,0.00039644603],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00040207116,0.0004328889,0.0004066786,0.00040618697,0.00029059456,0.0007752141,0.0010294159,0.000102291284,0.0005417687],"category_scores_gemma":[0.00009018367,0.00037347828,0.00012848202,0.0011961742,0.00015956763,0.0009654446,0.00022150668,0.0002502462,0.00021700317],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044537484,0.0014134976,0.00013716008,0.00005462516,0.00015731482,0.000041444182,0.00091261,0.00003818297,0.0010998973,0.0103490325,0.0028516415,0.98249924],"study_design_scores_gemma":[0.0012679169,0.0008047304,0.0078567825,0.000098575416,0.000098335266,0.00012027988,0.0008391844,0.9414969,0.03756112,0.0004924859,0.008492608,0.0008710895],"about_ca_topic_score_codex":0.00015361092,"about_ca_topic_score_gemma":0.00003786973,"teacher_disagreement_score":0.9816281,"about_ca_system_score_codex":0.00013028731,"about_ca_system_score_gemma":0.00028151157,"threshold_uncertainty_score":0.99987173},"labels":[],"label_agreement":null},{"id":"W4416336084","doi":"10.18280/isi.300921","title":"An Efficient Speaker Identification System with High-Level Feature Extraction and Database Dimensionality Reduction","year":2025,"lang":"","type":"article","venue":"Ingénierie des systèmes d information","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Dimensionality reduction; Pattern recognition (psychology); Speaker identification; Feature extraction; Feature (linguistics); Identification (biology)","score_opus":0.019282352263271244,"score_gpt":0.25361598978372674,"score_spread":0.2343336375204555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416336084","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31326944,0.00017551592,0.6816355,0.0003467378,0.0018631625,0.0008948509,0.00017488557,0.00029226235,0.0013476711],"genre_scores_gemma":[0.96955657,0.000054425094,0.029319683,0.000092283866,0.00011307086,0.00009544419,0.00052511797,0.000014506189,0.00022888454],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966397,0.00041135328,0.0011003134,0.0006469744,0.0007728652,0.00042877518],"domain_scores_gemma":[0.9962656,0.000108875036,0.00092448754,0.0009954202,0.0014881699,0.00021745848],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0016711404,0.00044002855,0.00040625958,0.0007930101,0.0012920585,0.001908985,0.00038391064,0.00030919965,0.000027222302],"category_scores_gemma":[0.0002128365,0.00040984532,0.000067660636,0.001636114,0.00030840933,0.008375558,0.0001293833,0.0003481911,0.000099850964],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007406323,0.0005042033,0.0003714543,0.0038067114,0.00030216962,0.00001885659,0.006716223,0.0050186617,0.011629406,0.107857354,0.0012099503,0.8618244],"study_design_scores_gemma":[0.0018371324,0.0002748708,0.1147661,0.0035800175,0.0003429075,0.0010157609,0.010090051,0.8250006,0.040278964,0.00069624913,0.001030717,0.0010866217],"about_ca_topic_score_codex":0.00038542465,"about_ca_topic_score_gemma":0.000026576818,"teacher_disagreement_score":0.86073774,"about_ca_system_score_codex":0.00088682846,"about_ca_system_score_gemma":0.00036357055,"threshold_uncertainty_score":0.9998353},"labels":[],"label_agreement":null},{"id":"W4416397568","doi":"10.1016/j.specom.2025.103330","title":"Towards unsupervised speech recognition without pronunciation models","year":2025,"lang":"en","type":"article","venue":"Speech Communication","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Institute for Information and Communications Technology Promotion","keywords":"Pronunciation; Word (group theory); Pipeline (software); Unsupervised learning; Segmentation; Vocabulary; Word error rate; Speech corpus; Joint (building)","score_opus":0.0460206974990346,"score_gpt":0.28150528242701406,"score_spread":0.23548458492797947,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416397568","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05130233,0.0005846073,0.6044388,0.014384633,0.00047139954,0.0013174142,0.000016360336,0.0012707794,0.3262137],"genre_scores_gemma":[0.40552497,0.00057324505,0.59069234,0.0017177255,0.0000380643,0.00016302658,0.00013441643,0.000019076293,0.0011371048],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980234,0.0003807285,0.00046065767,0.0004295295,0.00042829636,0.00027741355],"domain_scores_gemma":[0.9973208,0.00014743491,0.00017377603,0.0016985758,0.000582809,0.000076647266],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010106551,0.00020895469,0.000244247,0.00037599777,0.00032897238,0.00030878902,0.0014863776,0.00017435195,0.000070693204],"category_scores_gemma":[0.0002463282,0.00021694049,0.00011248846,0.0009634183,0.000058317877,0.0014478411,0.00037001714,0.00027466897,0.00027724964],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014237403,0.0001310929,0.0000864354,0.000020917543,0.00002793775,0.0000013442367,0.00023389532,0.000009280895,0.00076234643,0.012957174,0.0012472939,0.98450804],"study_design_scores_gemma":[0.0014870858,0.00007388677,0.0024061291,0.00040740866,0.000069927155,0.0000346124,0.00026056825,0.26027897,0.17633101,0.5465824,0.011361446,0.0007065627],"about_ca_topic_score_codex":0.00019708573,"about_ca_topic_score_gemma":0.00010967218,"teacher_disagreement_score":0.9838015,"about_ca_system_score_codex":0.00023311934,"about_ca_system_score_gemma":0.00022205182,"threshold_uncertainty_score":0.8846576},"labels":[],"label_agreement":null},{"id":"W4416581044","doi":"10.1016/j.csl.2025.101907","title":"A robust framework for noisy speech recognition using Frequency-Guided-Swin Transformer","year":2025,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Transformer; Robustness (evolution); Convolutional neural network; Word error rate; Pattern recognition (psychology); Deep neural networks; Artificial neural network; Deep learning","score_opus":0.06383290841893033,"score_gpt":0.3086372540781378,"score_spread":0.24480434565920747,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416581044","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03595994,0.00027758628,0.95451367,0.0011896698,0.0017652608,0.0008198338,0.00004748227,0.0005455591,0.004881018],"genre_scores_gemma":[0.010462695,0.000019841791,0.9854031,0.003113179,0.0005929616,0.00006098418,0.00004166626,0.000037248185,0.000268313],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973137,0.00012763396,0.0006156042,0.0008952772,0.00036992613,0.0006778833],"domain_scores_gemma":[0.998121,0.00041241344,0.00015511776,0.0008600366,0.00028143343,0.00016995969],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000583971,0.00040449135,0.0004832028,0.000513571,0.00028973486,0.00047554224,0.0011583676,0.0003171749,0.0002999068],"category_scores_gemma":[0.00014949041,0.00040260266,0.0003713951,0.0009890613,0.000066969995,0.00068427436,0.00013145432,0.0003567538,0.00014782046],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001292588,0.00014109524,0.000053868687,0.000098226796,0.00008833092,0.00012933364,0.0007119045,0.00001711316,0.002303372,0.004839781,0.0025756578,0.9890284],"study_design_scores_gemma":[0.0041743056,0.0004301316,0.0010922232,0.0020001112,0.00034890036,0.0009894788,0.0006421001,0.40609807,0.38958216,0.18242492,0.009201528,0.0030160735],"about_ca_topic_score_codex":0.00010760851,"about_ca_topic_score_gemma":0.000046015095,"teacher_disagreement_score":0.98601234,"about_ca_system_score_codex":0.00017014991,"about_ca_system_score_gemma":0.0001872152,"threshold_uncertainty_score":0.9998426},"labels":[],"label_agreement":null},{"id":"W4416610221","doi":"10.48550/arxiv.2505.23170","title":"ZIPA: A family of efficient models for multilingual phone recognition","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Phone; Leverage (statistics); Training set; Set (abstract data type); Noisy data; Data set","score_opus":0.12812033766292624,"score_gpt":0.3082748997877475,"score_spread":0.18015456212482128,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416610221","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5406844,0.00019191473,0.45416924,0.00015059489,0.0011932721,0.00064342975,0.00019673305,0.00017410539,0.0025962817],"genre_scores_gemma":[0.8624151,0.00011382172,0.13590422,0.0004644277,0.00014587946,0.00031927673,0.00008795213,0.000020982721,0.0005283811],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978344,0.00009553342,0.0006080913,0.00083048973,0.000308901,0.00032260997],"domain_scores_gemma":[0.99776435,0.00043308586,0.00033811695,0.0007953983,0.00057689805,0.000092169896],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00051498966,0.0003007852,0.00050897273,0.00033257037,0.000095480216,0.000058849077,0.0008969325,0.00031615415,0.000019503761],"category_scores_gemma":[0.00029320415,0.00030639963,0.00038261822,0.0002751111,0.000059153994,0.000099592675,0.0007095406,0.00030946764,0.00006534732],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018426846,0.0014437169,0.00081283384,0.0013503844,0.00042991323,0.000022463108,0.0031145674,0.0106723495,0.007122477,0.0008891832,0.0014829676,0.9724749],"study_design_scores_gemma":[0.0013362868,0.000087735956,0.0023611987,0.0011343983,0.00013323785,0.0000045315946,0.00019910285,0.8343546,0.1464073,0.0127405245,0.00048885215,0.00075224054],"about_ca_topic_score_codex":0.00008724482,"about_ca_topic_score_gemma":0.000009663052,"teacher_disagreement_score":0.97172266,"about_ca_system_score_codex":0.00007440661,"about_ca_system_score_gemma":0.00032363686,"threshold_uncertainty_score":0.9999388},"labels":[],"label_agreement":null},{"id":"W4416756303","doi":"10.1109/taslpro.2025.3633090","title":"Towards Effective and Efficient Non-Autoregressive Decoders for Conformer and LLM-Based ASR Using Block-Based Attention Mask","year":2025,"lang":"","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","keywords":"Decoding methods; Speedup; Inference; Autoregressive model; Connectionism; Language model; Speech processing; Speech coding","score_opus":0.01155468110483668,"score_gpt":0.27968695103775804,"score_spread":0.26813226993292133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416756303","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24487688,0.0015461968,0.7511192,0.00056328776,0.0004031619,0.0011673851,0.000067150024,0.000089073095,0.00016765592],"genre_scores_gemma":[0.9371591,0.00004818601,0.061480183,0.0009203591,0.000042621654,0.00013771132,0.000004333778,0.000033981716,0.00017352289],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973784,0.000149268,0.00050249475,0.0010186009,0.0003575674,0.00059363514],"domain_scores_gemma":[0.99838936,0.00047930164,0.00028432976,0.00027938516,0.00030343467,0.00026421525],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00065135665,0.00054092845,0.0005739778,0.0007673726,0.0012312281,0.00081286306,0.00018452898,0.0003018088,0.000029949793],"category_scores_gemma":[0.00006278708,0.00051911385,0.0001944677,0.0005827691,0.00039504663,0.00033286016,0.000007703806,0.00037254617,0.00000238132],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035013625,0.00033763394,0.00003457094,0.0011795042,0.00011761278,0.00002883731,0.0014565561,0.0017896806,0.01045686,0.000004643441,0.000008165743,0.9842358],"study_design_scores_gemma":[0.0031126414,0.00028262043,0.00038479813,0.0018719607,0.00040167337,0.00004248219,0.0009986004,0.76609844,0.22627586,0.000027536065,0.000033733653,0.00046965235],"about_ca_topic_score_codex":0.00009877957,"about_ca_topic_score_gemma":0.00006749757,"teacher_disagreement_score":0.98376614,"about_ca_system_score_codex":0.00016661394,"about_ca_system_score_gemma":0.0005312701,"threshold_uncertainty_score":0.99972606},"labels":[],"label_agreement":null},{"id":"W4417001668","doi":"10.48550/arxiv.2512.02201","title":"Swivuriso: The South African Next Voices Multilingual Speech Dataset","year":2025,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Pretoria; International Development Research Centre; Nvidia; Bill and Melinda Gates Foundation","keywords":"Benchmarking; Domain (mathematical analysis); Baseline (sea); Data collection; Speech technology; Computational linguistics","score_opus":0.12330761746984963,"score_gpt":0.2252155139685487,"score_spread":0.10190789649869907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417001668","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46635997,0.00075086684,0.39575943,0.0036144305,0.011840349,0.0052429247,0.024003007,0.001534227,0.090894796],"genre_scores_gemma":[0.9834367,0.0005357024,0.0040443735,0.00085353985,0.000340699,0.0000037071813,0.00058011117,0.000032030457,0.010173133],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9936346,0.00093726045,0.0007320972,0.0031921966,0.00039797058,0.0011058896],"domain_scores_gemma":[0.99269557,0.001196965,0.0008930751,0.004227741,0.0004957925,0.00049082946],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012363176,0.0010070566,0.0009044678,0.00070232624,0.0012132709,0.0011049041,0.0077582095,0.00064420054,0.0007862388],"category_scores_gemma":[0.00043071888,0.0009418603,0.0007108137,0.0023437503,0.0007580668,0.0009148462,0.005958196,0.001720649,0.0016073228],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015449175,0.0036958416,0.005697875,0.0014069646,0.0047789104,0.009484075,0.024258967,0.055104792,0.0001656352,0.07652946,0.031145347,0.78618723],"study_design_scores_gemma":[0.0019584415,0.00015989467,0.0012890317,0.00063450885,0.0011539543,0.00005354341,0.009644696,0.8400956,0.0025209298,0.010108512,0.12984662,0.002534269],"about_ca_topic_score_codex":0.00127427,"about_ca_topic_score_gemma":0.0005647614,"teacher_disagreement_score":0.7849908,"about_ca_system_score_codex":0.0003140852,"about_ca_system_score_gemma":0.0010702347,"threshold_uncertainty_score":0.99993205},"labels":[],"label_agreement":null},{"id":"W4417169656","doi":"10.1109/icecs66544.2025.11270693","title":"Low-Power Real-Time Keyword Spotting for Autonomous Edge Devices","year":2025,"lang":"","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Keyword spotting; Dynamic time warping; Feature extraction; Signal processing; Feature (linguistics); Latency (audio); Enhanced Data Rates for GSM Evolution; Key (lock); Power consumption; Window (computing)","score_opus":0.0165185287494423,"score_gpt":0.2672267519714799,"score_spread":0.25070822322203756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417169656","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021475209,0.00021475492,0.38870114,0.005048008,0.002804983,0.0011675342,0.000023390465,0.0006702787,0.5798947],"genre_scores_gemma":[0.37555587,0.00018102724,0.39525926,0.0070306887,0.00041590998,0.00022090049,0.00001247712,0.00006757799,0.22125626],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965967,0.00014324617,0.00090626645,0.0011548895,0.00030444542,0.00089445617],"domain_scores_gemma":[0.99683875,0.0013228701,0.00025875925,0.000900015,0.00044234443,0.00023723868],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0010521377,0.0004510053,0.0005991853,0.00043953746,0.00060472265,0.0009683123,0.001348614,0.00027409877,0.0042318893],"category_scores_gemma":[0.00036676606,0.00044003173,0.00044026368,0.0009705616,0.000118922544,0.00065651,0.00046030886,0.00018096535,0.001821176],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045986482,0.00034442518,0.00016202475,0.00019633169,0.00016090924,0.000016665897,0.0004715227,0.000004775264,0.0018847095,0.023767041,0.019084046,0.95386153],"study_design_scores_gemma":[0.0027646944,0.00046658664,0.0050686635,0.0016213261,0.0002843516,0.000034566994,0.00066829356,0.5814059,0.1509961,0.009039706,0.24543847,0.0022113805],"about_ca_topic_score_codex":0.00006114156,"about_ca_topic_score_gemma":0.000026141435,"teacher_disagreement_score":0.9516502,"about_ca_system_score_codex":0.00015768576,"about_ca_system_score_gemma":0.0006260107,"threshold_uncertainty_score":0.99980515},"labels":[],"label_agreement":null},{"id":"W4417275930","doi":"10.1162/tacl.a.54","title":"The Impact of Automatic Speech Transcription on Speaker Attribution","year":2025,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université TÉLUQ; Université du Québec à Montréal","funders":"","keywords":"Attribution; Transcription (linguistics); Task (project management); Speaker diarisation; Phonetic transcription; Speech processing","score_opus":0.018552587854670767,"score_gpt":0.296895449186917,"score_spread":0.2783428613322462,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417275930","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0054116473,0.000021251282,0.98953843,0.0008745218,0.0011654343,0.00041675684,0.00016597504,0.000056335808,0.0023496174],"genre_scores_gemma":[0.97541875,0.000007753943,0.023703618,0.00004155175,0.000042610336,0.000019150637,0.0000143091065,0.0000055394053,0.0007467186],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987789,0.00011231588,0.00045431362,0.00013605434,0.00037746987,0.00014094275],"domain_scores_gemma":[0.9963386,0.0017973464,0.00038157494,0.0002333609,0.0012272948,0.000021843352],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006140794,0.000102587095,0.00016490264,0.000119722376,0.00039116447,0.000054346885,0.00040185062,0.00007545382,0.000007717594],"category_scores_gemma":[0.0011820331,0.00007011711,0.00041200014,0.0005270405,0.000042857788,0.000045069293,0.000007165649,0.00010872378,0.0000037898487],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000120474004,0.0008686565,0.0018302446,0.00012882317,0.0010961723,2.320689e-7,0.00036413185,0.2176661,0.000566499,0.62670666,0.0039774603,0.14667456],"study_design_scores_gemma":[0.0010014249,0.00018134488,0.054863006,0.00013058796,0.00015453635,0.0000013424253,0.00003102253,0.79633564,0.0072742915,0.13648069,0.0033907294,0.00015537161],"about_ca_topic_score_codex":0.000028761102,"about_ca_topic_score_gemma":0.000010038573,"teacher_disagreement_score":0.9700071,"about_ca_system_score_codex":0.00034022925,"about_ca_system_score_gemma":0.00022095595,"threshold_uncertainty_score":0.30085605},"labels":[],"label_agreement":null},{"id":"W4417423602","doi":"10.48550/arxiv.2507.10827","title":"Supporting SENĆOTEN Language Documentation Efforts with Automatic Speech Recognition","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Pipeline (software); Documentation; Vocabulary; Word error rate; Language model; Constructed language; Set (abstract data type); Speech technology","score_opus":0.030550187482115333,"score_gpt":0.3052722171440733,"score_spread":0.27472202966195797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417423602","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9464171,0.0000543364,0.041729663,0.00076111924,0.00066118094,0.0006722279,0.00003104316,0.00080454844,0.008868773],"genre_scores_gemma":[0.70774096,0.00004798495,0.28662747,0.0014179262,0.00024040448,0.00024091001,0.00043888055,0.000039669965,0.003205805],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9976574,0.0001553571,0.00055031286,0.00079907925,0.0004328507,0.0004049619],"domain_scores_gemma":[0.9982419,0.00018646066,0.00049332,0.00078812893,0.00017634769,0.00011385107],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00055082026,0.00034511596,0.00039188896,0.0003299149,0.00014560763,0.00033057248,0.00063569035,0.00022978528,0.00046765408],"category_scores_gemma":[0.00015777188,0.0003130364,0.00014946905,0.0003740437,0.000038079845,0.0005311082,0.00051531487,0.00044159646,0.0005003284],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009984256,0.000099918245,0.020381853,0.0004180109,0.00015040154,0.0003054688,0.0014249559,0.000010784723,0.00043881242,0.000038698552,0.00071761734,0.97600347],"study_design_scores_gemma":[0.005340566,0.0006497207,0.27982032,0.012165475,0.0014048894,0.00095196354,0.004096291,0.1316854,0.53308105,0.020948716,0.0029132753,0.0069423425],"about_ca_topic_score_codex":0.00019808258,"about_ca_topic_score_gemma":0.00007206324,"teacher_disagreement_score":0.96906114,"about_ca_system_score_codex":0.00013527545,"about_ca_system_score_gemma":0.00022570496,"threshold_uncertainty_score":0.99993217},"labels":[],"label_agreement":null},{"id":"W4417530737","doi":"10.1145/3714394.3754429","title":"Poster: Recognizing Hidden-in-the-Ear Private Key for Reliable Silent Speech Interface Using Multi-Task Learning","year":2025,"lang":"","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Interface (matter); Decoding methods; Spelling; Key (lock); Authentication (law); Conjunction (astronomy); User interface; Identification (biology)","score_opus":0.05784036500355474,"score_gpt":0.3165426386370176,"score_spread":0.2587022736334629,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417530737","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19878621,0.0010537961,0.7824246,0.004112855,0.0025367802,0.0022721146,0.000010139325,0.00024916237,0.008554334],"genre_scores_gemma":[0.5085062,0.00031158488,0.48044178,0.002442695,0.00014318575,0.00008179055,0.000005865124,0.000059747716,0.008007196],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99470073,0.0006237995,0.0013568356,0.0014885819,0.0005566098,0.0012734396],"domain_scores_gemma":[0.9967091,0.0013123025,0.0004114442,0.0009901943,0.0004118257,0.00016511921],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0030394157,0.0006001923,0.00072973024,0.0007384979,0.00085175876,0.0014743599,0.0019378621,0.00034227024,0.00027224663],"category_scores_gemma":[0.00116243,0.0005514653,0.00041968073,0.0017138964,0.00012836828,0.0009235634,0.0008015928,0.0009051144,0.00030053058],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017690352,0.0007222948,0.0026478881,0.00041731718,0.00017478217,0.00007385943,0.0049007554,0.00029036813,0.014431968,0.0013753545,0.0007668067,0.9740217],"study_design_scores_gemma":[0.002949746,0.00036394107,0.0009580342,0.0025881778,0.0001704674,0.00011723124,0.0027685007,0.807954,0.14838748,0.0014379348,0.03116567,0.0011387852],"about_ca_topic_score_codex":0.00029465815,"about_ca_topic_score_gemma":0.00010960919,"teacher_disagreement_score":0.9728829,"about_ca_system_score_codex":0.00036701074,"about_ca_system_score_gemma":0.00031081145,"threshold_uncertainty_score":0.9996937},"labels":[],"label_agreement":null},{"id":"W6888789972","doi":"10.23641/asha.14167058","title":"Forced alignment of child speech (Mahr et al., 2021)","year":2021,"lang":"en","type":"article","venue":"figshare ASHA Publications","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Two-alternative forced choice; Segmentation; Sample (material); Speech processing; Phonetics; Speech segmentation; Interval (graph theory); Electroglottograph; Process (computing)","score_opus":0.04140962456034709,"score_gpt":0.2830461045837347,"score_spread":0.2416364800233876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6888789972","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00022171247,0.00039468895,0.031594336,0.35896564,0.00040631244,0.00065681984,0.015920622,0.0005221243,0.5913178],"genre_scores_gemma":[0.20862913,0.00052070164,0.47816557,0.17216305,0.0004587783,0.0027580927,0.08373205,0.00017900557,0.053393632],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986442,0.000084011204,0.00029750998,0.00040455416,0.0003572682,0.00021249002],"domain_scores_gemma":[0.99804,0.00019616306,0.00014577112,0.00094597647,0.0005409462,0.0001311069],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00015096412,0.00011756987,0.000155378,0.00015584698,0.00012084415,0.00023084665,0.00070818077,0.00005334939,0.042746823],"category_scores_gemma":[0.00092230184,0.00012233523,0.00013198936,0.00095755985,0.000010959431,0.00054490945,0.0002977252,0.00011376995,0.0011099979],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.3885638e-7,0.00016578901,0.000026327692,0.000009506708,0.000032845375,0.000004224372,0.00007188629,0.0000019191825,0.00042545592,0.023146471,0.91539955,0.06071558],"study_design_scores_gemma":[0.00017829443,0.0000145313015,0.0025962752,0.00011417833,0.000005447953,0.000051544943,0.000034868604,0.0015150274,0.03651131,0.00089545007,0.95791274,0.00017031792],"about_ca_topic_score_codex":0.000007230806,"about_ca_topic_score_gemma":0.000024695626,"teacher_disagreement_score":0.5379241,"about_ca_system_score_codex":0.00003488894,"about_ca_system_score_gemma":0.00021328116,"threshold_uncertainty_score":0.99966776},"labels":[],"label_agreement":null},{"id":"W6892655041","doi":"10.5281/zenodo.11726402","title":"driving test pdf book","year":2024,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Test (biology); Download; Government (linguistics); Agency (philosophy); Table (database); State (computer science)","score_opus":0.026210869389717464,"score_gpt":0.23542793802921627,"score_spread":0.2092170686394988,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6892655041","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[7.38505e-7,0.00051227765,0.02081714,0.00084635074,0.00030025185,0.00026647738,0.000082750164,0.0036340917,0.97353995],"genre_scores_gemma":[0.00013969859,0.00034612275,0.0036608854,0.00044050495,0.00040543164,5.5166208e-8,0.0002865764,0.0070539173,0.9876668],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99817806,0.00016523871,0.00020876422,0.0006651661,0.00042964492,0.0003530925],"domain_scores_gemma":[0.99875814,0.0000369924,0.00010910925,0.00074409525,0.00015962447,0.0001920465],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00037362642,0.00021733282,0.00019374657,0.00058754487,0.00053946674,0.0019798072,0.0020201383,0.00014541236,0.18746932],"category_scores_gemma":[0.0005496786,0.00022360231,0.00009177683,0.00057808764,0.00009327152,0.00019948544,0.0017432485,0.00034464427,0.39010766],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.431203e-7,0.000041363273,9.80097e-8,0.000059316706,0.000029599303,0.00004140997,0.00009517239,9.2863125e-8,0.00011230997,0.0021464361,0.866313,0.13116059],"study_design_scores_gemma":[0.00010669782,0.000059353188,0.000005789527,0.00021569841,0.000013079333,0.00013307706,0.000022128657,0.00037396053,0.0001255504,0.00028122996,0.99841034,0.0002530952],"about_ca_topic_score_codex":0.000008072126,"about_ca_topic_score_gemma":4.905788e-7,"teacher_disagreement_score":0.20263834,"about_ca_system_score_codex":0.00009991052,"about_ca_system_score_gemma":0.0000050824847,"threshold_uncertainty_score":0.9990562},"labels":[],"label_agreement":null},{"id":"W6892787335","doi":"10.5281/zenodo.12278899","title":"apprendre windows 10 pdf","year":2024,"lang":"fr","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Paraphernalia; TSG101; Dysgeusia; Filter (signal processing); Point (geometry)","score_opus":0.047591060985396144,"score_gpt":0.24449635005133402,"score_spread":0.19690528906593788,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6892787335","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00002214293,0.0007862911,0.022484517,0.0025195435,0.000964417,0.0005885467,0.00029315168,0.00155559,0.9707858],"genre_scores_gemma":[0.0008902632,0.00026271146,0.0031289442,0.00045165225,0.00089925854,1.01151805e-7,0.00076817675,0.005910705,0.9876882],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99616826,0.00069790205,0.0004630404,0.0012215481,0.0007321775,0.0007170629],"domain_scores_gemma":[0.9976051,0.00005248118,0.00019915172,0.0010880714,0.0006305566,0.00042464046],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00080162915,0.0004370564,0.0003843637,0.0006898365,0.0013069354,0.004275198,0.0029112517,0.0002816739,0.8131311],"category_scores_gemma":[0.0007870748,0.00047211917,0.00022925985,0.0012024395,0.00033794998,0.00036788333,0.0028493959,0.00070459326,0.85782135],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010362786,0.00010101714,6.486162e-8,0.00017565313,0.00009504731,0.0000962944,0.00055547094,0.0000023876842,0.00016124353,0.01593598,0.5829752,0.39989126],"study_design_scores_gemma":[0.00030742842,0.00018304645,0.000019577861,0.00038679823,0.00005779206,0.00051302265,0.00014579245,0.0023164449,0.00026137705,0.00094450824,0.9943631,0.0005010733],"about_ca_topic_score_codex":0.000017126209,"about_ca_topic_score_gemma":0.0000011258194,"teacher_disagreement_score":0.41138792,"about_ca_system_score_codex":0.0002483571,"about_ca_system_score_gemma":0.0000137858015,"threshold_uncertainty_score":0.9999932},"labels":[],"label_agreement":null},{"id":"W6921056807","doi":"10.60864/1s30-t715","title":"Less peaky and more accurate CTC forced alignment by label priors","year":2024,"lang":"en","type":"article","venue":"IEEE SIGPORT","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Offset (computer science); Security token; Pipeline (software); Hidden Markov model; Pattern recognition (psychology); Bayesian probability; Prior probability; Training set","score_opus":0.03190628355525705,"score_gpt":0.281614336227028,"score_spread":0.24970805267177093,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6921056807","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8200011,0.0011056104,0.15917777,0.0050593475,0.0021571931,0.00046230518,0.000042228883,0.0008354922,0.011158955],"genre_scores_gemma":[0.98722,0.0001514617,0.0060064117,0.0010086856,0.00009354307,0.00003997947,0.000007085172,0.000020426334,0.005452428],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989043,0.000023386481,0.00018737768,0.0003980007,0.00026411237,0.00022280638],"domain_scores_gemma":[0.99947846,0.00007337996,0.000035059413,0.00026061977,0.000031161788,0.000121297904],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021911185,0.0001365856,0.00013653601,0.00007406959,0.00007235015,0.00028074364,0.0002813793,0.000057478424,0.00004393894],"category_scores_gemma":[0.000013228073,0.00011713613,0.00004474432,0.0001947209,0.000040998675,0.00031696673,0.000066161556,0.00008743506,0.00009520296],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000668588,0.00008469633,0.00025901495,0.00008667497,0.00009881231,0.00034528147,0.0015860306,0.0000035729438,0.029676624,0.003480563,0.086446814,0.8779252],"study_design_scores_gemma":[0.0017025685,0.0003267333,0.0026042166,0.00049631955,0.00013223667,0.00056720927,0.001651372,0.18796076,0.5106731,0.0048213825,0.28699732,0.0020667622],"about_ca_topic_score_codex":0.000025372678,"about_ca_topic_score_gemma":0.0000047909107,"teacher_disagreement_score":0.8758585,"about_ca_system_score_codex":0.000031490465,"about_ca_system_score_gemma":0.00005664313,"threshold_uncertainty_score":0.47766727},"labels":[],"label_agreement":null},{"id":"W6930431502","doi":"10.5281/zenodo.11464895","title":")-(`! [[[[WhatsApp ((( (+27) 736616875))) *____**)) TOP QUALITY COUNTERFEIT MONEY FOR SALE South Korea Lushnjë Free State\\\\EUROPE USA 3","year":2024,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nucleofection; Hyporeflexia; Diafiltration; Fusible alloy; Pretext; Articular cartilage damage","score_opus":0.05270579122096652,"score_gpt":0.2747553673391952,"score_spread":0.22204957611822868,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930431502","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00011894023,0.00044094128,0.08791884,0.0010275443,0.0010374193,0.0013313864,0.0041409284,0.0035814394,0.90040255],"genre_scores_gemma":[0.0019944764,0.0005772664,0.013080625,0.00089805527,0.001025752,0.000001368854,0.0023637791,0.014158293,0.96590036],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99574643,0.00055501936,0.00062311656,0.0014024655,0.00090216275,0.0007707905],"domain_scores_gemma":[0.9965258,0.00008064587,0.00037860486,0.0019065349,0.0007199722,0.00038843966],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001321388,0.00050884584,0.00052580977,0.00075877726,0.0007716578,0.0030351332,0.0041260608,0.00025811858,0.02725432],"category_scores_gemma":[0.0010673623,0.00051338633,0.00023147184,0.0010020129,0.00023710988,0.00034545735,0.0028835547,0.00053372077,0.069963805],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003759041,0.00011496571,0.00000136635,0.00034581398,0.00014521736,0.000037124933,0.0008330761,0.0000024509666,0.00019088032,0.0049869646,0.93157655,0.06172799],"study_design_scores_gemma":[0.00062030164,0.00017635252,0.000031508665,0.00023259083,0.000041245625,0.00005986015,0.00012800771,0.00063871697,0.00033644523,0.00087141927,0.99626213,0.00060139847],"about_ca_topic_score_codex":0.000084265,"about_ca_topic_score_gemma":0.000009310756,"teacher_disagreement_score":0.07483821,"about_ca_system_score_codex":0.00018544795,"about_ca_system_score_gemma":0.00002728712,"threshold_uncertainty_score":0.9997318},"labels":[],"label_agreement":null},{"id":"W6939194750","doi":"10.60692/38hgp-2s302","title":"Synthetic Speech Dataset","year":2019,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Speech synthesis; Speech processing; Spoken language; Natural language; Speech corpus; Speech technology","score_opus":0.031170796375344853,"score_gpt":0.20937472157760784,"score_spread":0.17820392520226297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6939194750","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3721812,0.0000034467284,0.5128656,0.00042090236,0.0029131295,0.0012244335,0.0012470029,0.0015249565,0.107619315],"genre_scores_gemma":[0.9916496,4.923004e-8,0.0075568943,0.0004466674,0.00002732372,0.000019489315,0.00006562238,0.0000047779176,0.00022952253],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99881285,0.000055155368,0.00038776363,0.00018472297,0.00034431493,0.00021520403],"domain_scores_gemma":[0.9988049,0.000013156468,0.00016857832,0.00083732425,0.00008742597,0.00008861334],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003644127,0.00013248553,0.00016932438,0.00024001235,0.00006922014,0.000399121,0.00057176995,0.00006885886,0.00020748746],"category_scores_gemma":[0.000016443882,0.00010827991,0.000055731583,0.00024833553,0.00001090195,0.0015748395,0.00012543399,0.000065336506,0.03931185],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021234814,0.000053295098,0.22068232,0.0041616913,0.0005824093,0.0001902178,0.18497996,0.00022656191,0.00009264946,0.06654487,0.05258651,0.46968716],"study_design_scores_gemma":[0.009707636,0.00052471156,0.094036795,0.001929597,0.00014779993,0.00452127,0.037734896,0.5111521,0.053162854,0.00010704938,0.28185785,0.005117473],"about_ca_topic_score_codex":0.0000033578483,"about_ca_topic_score_gemma":4.1299966e-8,"teacher_disagreement_score":0.61946845,"about_ca_system_score_codex":0.000054947577,"about_ca_system_score_gemma":0.000026258756,"threshold_uncertainty_score":0.96143615},"labels":[],"label_agreement":null},{"id":"W6958761994","doi":"10.6084/m9.figshare.16828541.v1","title":"Influence of drinking water quality on the formation of corrosion scales in lead-bearing drinking water distribution systems","year":2021,"lang":"en","type":"article","venue":"Figshare","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Corrosion; Water quality; Lead (geology); Water supply; Water treatment; Soft water; Erosion corrosion of copper water tubes; Groundwater","score_opus":0.05980036939291211,"score_gpt":0.2688810242796449,"score_spread":0.20908065488673278,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958761994","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99616206,0.000021482967,0.0018350998,0.00016985947,0.000051691055,0.00016477906,0.0011950643,0.0000373369,0.00036264313],"genre_scores_gemma":[0.9963163,0.0000020534173,0.000072799514,0.00004255068,0.000012119684,0.000033573702,0.0035042488,0.0000036942465,0.000012663894],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988162,0.00017498288,0.00036863287,0.00016939803,0.00029938814,0.00017137622],"domain_scores_gemma":[0.9991639,0.00019537202,0.00010979261,0.000292412,0.00021915775,0.000019357625],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032236517,0.00008249497,0.0001489047,0.0000504412,0.00007911541,0.0000863809,0.0002891799,0.00005855715,0.0004563305],"category_scores_gemma":[0.00034311836,0.000048936417,0.000054277334,0.00014796003,0.0000078058765,0.00041873133,0.00020873747,0.00010302757,0.00014061008],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006197625,0.00044483208,0.007112701,0.002922833,0.000030584233,0.000062413594,0.010738096,0.019339481,0.9120781,0.008928283,0.0023349344,0.0359458],"study_design_scores_gemma":[0.00009618241,0.000011385612,0.009945889,0.0025030132,0.0000012885353,0.0000061115074,0.00011286963,0.014106233,0.9726098,0.00015861623,0.00036329223,0.00008530687],"about_ca_topic_score_codex":0.000021510195,"about_ca_topic_score_gemma":0.000042020823,"teacher_disagreement_score":0.060531747,"about_ca_system_score_codex":0.00005265219,"about_ca_system_score_gemma":0.000012885595,"threshold_uncertainty_score":0.4996499},"labels":[],"label_agreement":null},{"id":"W6964075530","doi":"10.25384/sage.21317302","title":"sj-docx-1-cjo-10.1177_00084174221129947 - Supplemental material for Review and Consultations of Canadian Financial Education Programs for Individuals with Disabilities","year":2022,"lang":"en","type":"article","venue":"Sage Journals Data","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Quarter (Canadian coin); Financial literacy; Formal education","score_opus":0.06687970547653425,"score_gpt":0.3224906653711449,"score_spread":0.25561095989461063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6964075530","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.062341593,0.053002737,0.050394595,0.09298549,0.0030954366,0.022632938,0.71392715,0.00021479074,0.0014052361],"genre_scores_gemma":[0.088475,0.013826186,0.8310113,0.006873509,0.0008231254,0.007417149,0.049270723,0.000105244806,0.0021977734],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988513,0.00008982108,0.00035584145,0.0002716846,0.0002066792,0.00022469457],"domain_scores_gemma":[0.9989368,0.0001740693,0.0002083479,0.00040683802,0.00014019995,0.00013376292],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00086737593,0.000104275896,0.00022333708,0.00020514442,0.0004048529,0.0001734073,0.00069636997,0.000020026771,0.005736205],"category_scores_gemma":[0.00031301574,0.000093547365,0.000035408684,0.00034679243,0.000064075335,0.00052450964,0.00019336713,0.00006251429,0.0000013771448],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028345032,0.0002909356,0.0024751362,0.0005249984,0.00008720347,0.0000012742357,0.0008423212,3.4002034e-7,0.000057342113,0.00075519906,0.27918053,0.71575636],"study_design_scores_gemma":[0.0012346399,0.00047208197,0.0013898137,0.00079380226,0.00026265264,0.00017531156,0.0025288614,0.00021157911,0.00047102338,0.0027265772,0.98938406,0.0003495723],"about_ca_topic_score_codex":0.0017217493,"about_ca_topic_score_gemma":0.0052453047,"teacher_disagreement_score":0.7806167,"about_ca_system_score_codex":0.00005183531,"about_ca_system_score_gemma":0.00090187526,"threshold_uncertainty_score":0.9951727},"labels":[],"label_agreement":null},{"id":"W6979728622","doi":"","title":"Acoustic/Phonetic Transcription Using a Polynomial Classifier and Hidden Markov Models","year":2022,"lang":"en","type":"article","venue":"Canadian acoustics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Hidden Markov model; Maximum-entropy Markov model; Classifier (UML); Pattern recognition (psychology); Hidden semi-Markov model; Transcription (linguistics); Markov model","score_opus":0.03649342766834752,"score_gpt":0.21748616550352848,"score_spread":0.18099273783518097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6979728622","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27082315,0.00025902307,0.72115284,0.0012311318,0.0015561433,0.00034401976,0.00024522826,0.00013141887,0.0042570145],"genre_scores_gemma":[0.94972926,0.000016934777,0.04827432,0.0014132501,0.00008910871,0.000016742573,0.00000661481,0.00001885927,0.00043492694],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987575,0.0000848076,0.00018350885,0.00032692193,0.00024328161,0.0004040051],"domain_scores_gemma":[0.99912786,0.00005405005,0.000045339926,0.00027147675,0.000048760463,0.00045253473],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018568542,0.00013898534,0.0001461304,0.0003185852,0.00049894635,0.0001995034,0.0003727807,0.000066509376,0.00027975283],"category_scores_gemma":[0.000026862062,0.0001672971,0.000047143512,0.00030413523,0.000054157423,0.00021325785,0.000074594696,0.00021392737,0.000008788225],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005028825,0.00012971077,0.00017473292,0.00008714827,0.000121874225,0.0009193343,0.003965628,0.020296771,0.2699583,0.0030955703,0.041481588,0.65971905],"study_design_scores_gemma":[0.0002675759,0.000037802736,0.0007070093,0.0000071266604,0.000040074316,0.00020562252,0.00039935083,0.9956062,0.00006720604,0.0009943147,0.0014128676,0.00025486527],"about_ca_topic_score_codex":0.0061537763,"about_ca_topic_score_gemma":0.0020918807,"teacher_disagreement_score":0.97530943,"about_ca_system_score_codex":0.00042546404,"about_ca_system_score_gemma":0.0006160752,"threshold_uncertainty_score":0.930271},"labels":[],"label_agreement":null},{"id":"W6997174494","doi":"","title":"Utilization of Multiple Units in Human And Machine Recognition of Continuous Speech---- Perceptual Evidence And A Proposal For An Asr System","year":2022,"lang":"en","type":"article","venue":"Canadian acoustics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Perception; Pattern recognition (psychology); Human–machine system; Human–machine interface","score_opus":0.09954456807472184,"score_gpt":0.27332700525050446,"score_spread":0.17378243717578262,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6997174494","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9728057,0.00011140964,0.02585107,0.00006743138,0.000092757735,0.0005488922,0.00039937807,0.000023251907,0.00010012213],"genre_scores_gemma":[0.9832704,0.000011097552,0.016566597,0.00004559315,0.0000124306125,0.000027186994,0.000039733328,0.000008353407,0.000018578396],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991689,0.00011463655,0.00023630587,0.00020208827,0.00013015622,0.00014791825],"domain_scores_gemma":[0.99925506,0.00016055569,0.0001028888,0.00013976352,0.00020246516,0.00013925172],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003972388,0.00007823699,0.0001664448,0.0002856167,0.0001297478,0.000032558328,0.00016146331,0.00004084973,0.000018354744],"category_scores_gemma":[0.00032039487,0.00008902004,0.000012808566,0.00029063335,0.000059766473,0.00016242627,0.000044145952,0.000071250404,2.4908584e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000111068235,0.00025546944,0.023920547,0.0014491287,0.00004690484,0.000102106475,0.010093542,0.0002692691,0.101284474,0.01025043,0.0006801898,0.85153687],"study_design_scores_gemma":[0.001878891,0.0015332547,0.042946998,0.0005055166,0.00008457814,0.00025873183,0.012610165,0.9315396,0.0062824385,0.0016713032,0.00014724734,0.0005412794],"about_ca_topic_score_codex":0.010783988,"about_ca_topic_score_gemma":0.0224778,"teacher_disagreement_score":0.9312703,"about_ca_system_score_codex":0.00010464381,"about_ca_system_score_gemma":0.0003109697,"threshold_uncertainty_score":0.9958033},"labels":[],"label_agreement":null},{"id":"W7000383101","doi":"","title":"Experiments on The Use of Demisyllables For Automatic Speech Recognition","year":2022,"lang":"en","type":"article","venue":"Canadian acoustics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Voice activity detection; Speech processing; Acoustic model; Speaker recognition; Pattern recognition (psychology); Automatic target recognition","score_opus":0.14526471405056032,"score_gpt":0.26103017194622447,"score_spread":0.11576545789566414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7000383101","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8404554,0.00007345685,0.14371662,0.005992505,0.0020505076,0.00198001,0.0015458806,0.00023002272,0.0039556157],"genre_scores_gemma":[0.7264815,0.0000101540645,0.2637643,0.008403572,0.0000728448,0.00033085863,0.00004674386,0.000029404335,0.0008606023],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992078,0.00007201886,0.0001606538,0.00015614314,0.00019260147,0.00021076003],"domain_scores_gemma":[0.9988583,0.00055131677,0.00007414949,0.00030251624,0.00008569138,0.00012803392],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021120839,0.00007817503,0.000094053255,0.0001487599,0.00030561053,0.00008274821,0.00039173552,0.000027513815,0.0005072068],"category_scores_gemma":[0.00039433717,0.000068858586,0.00005033685,0.00022959504,0.000026012503,0.00008641254,0.000041219755,0.0000777748,0.000024306908],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000080438285,0.00009296753,0.00004461675,0.000031855823,0.000054069427,0.00004161729,0.00051596214,0.00030847252,0.006468809,0.0036044826,0.15496974,0.8338594],"study_design_scores_gemma":[0.0006132138,0.0003842924,0.0007720484,0.00007730901,0.00006316491,0.00008335964,0.0010964299,0.8680019,0.029249148,0.008562243,0.09052149,0.00057539146],"about_ca_topic_score_codex":0.0014220804,"about_ca_topic_score_gemma":0.00030822342,"teacher_disagreement_score":0.8676934,"about_ca_system_score_codex":0.00018382404,"about_ca_system_score_gemma":0.00026937368,"threshold_uncertainty_score":0.5553559},"labels":[],"label_agreement":null},{"id":"W7001204461","doi":"","title":"Issues of bilingualism in likelihood ratio-based forensic voice comparison","year":2021,"lang":"en","type":"dissertation","venue":"White Rose eTheses Online (University of Leeds, The University of Sheffield, University of York)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Formant; Linear discriminant analysis; Matching (statistics); Situated; Neuroscience of multilingualism; Speaker recognition; Software","score_opus":0.0240817240188065,"score_gpt":0.24365453749311639,"score_spread":0.21957281347430987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7001204461","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9657652,0.0010674087,0.022412807,0.0032390777,0.000412114,0.00070625584,0.00049958105,0.00011826512,0.0057793297],"genre_scores_gemma":[0.9326178,0.001333812,0.058082722,0.00004786758,0.000036718597,2.053167e-8,0.0006378834,0.000028314525,0.0072148866],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9972937,0.00048659375,0.0004120529,0.0006688321,0.0007705182,0.00036828962],"domain_scores_gemma":[0.9957611,0.00076202775,0.0013105625,0.0009878756,0.0010328235,0.0001456384],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00054077525,0.00039758385,0.0013060512,0.00098135,0.0003499276,0.000018633209,0.0027122395,0.0006654356,0.0005248087],"category_scores_gemma":[0.0001176748,0.0005141793,0.000705814,0.0013136558,0.00068425684,0.0004554923,0.00042858967,0.000721606,0.000010407185],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008405589,0.012491876,0.021850485,0.008941601,0.004050701,0.0014209263,0.5744044,0.008172296,0.017010782,0.00671905,0.014336317,0.32219598],"study_design_scores_gemma":[0.0069705686,0.0010637469,0.033129502,0.0048805457,0.001487232,0.000011255586,0.8825143,0.044180617,0.012554096,0.0006628049,0.010802654,0.0017426978],"about_ca_topic_score_codex":0.012377796,"about_ca_topic_score_gemma":0.049570486,"teacher_disagreement_score":0.3204533,"about_ca_system_score_codex":0.00012731137,"about_ca_system_score_gemma":0.0007458771,"threshold_uncertainty_score":0.999731},"labels":[],"label_agreement":null},{"id":"W7002446300","doi":"","title":"Nivelrikko-oppaan harjoitteluohjeiden kääntäminen arabian kielelle. Kommentoitu käännös.","year":2019,"lang":"fi","type":"other","venue":"Theseus (Ammattikorkeakoulujen)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quarter (Canadian coin); Government (linguistics); Mercantilism","score_opus":0.030569287495678853,"score_gpt":0.25262348639020915,"score_spread":0.2220541988945303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7002446300","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011866855,0.001738644,0.009708936,0.008675596,0.0045240102,0.002812227,0.00031541608,0.0013183831,0.9697201],"genre_scores_gemma":[0.006649864,0.0014249476,0.012238149,0.0036244518,0.0023554775,0.00023507487,0.00015702914,0.0011512995,0.97216374],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9869094,0.0013189053,0.0022522963,0.0038039314,0.0025385756,0.003176891],"domain_scores_gemma":[0.98958635,0.0012775585,0.0019460034,0.0052701524,0.00054964033,0.0013702845],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","insufficient_payload"],"category_scores_codex":[0.0019434126,0.002771873,0.0030126863,0.0018751314,0.00068257964,0.0018087034,0.007427665,0.002092652,0.03180562],"category_scores_gemma":[0.0005370888,0.0027107385,0.0016509871,0.0017905139,0.00068233046,0.0013146058,0.0020523146,0.0020693946,0.13925017],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013862285,0.00066551013,0.00022451904,0.0004590151,0.00085874053,0.00047411027,0.0013977882,0.000013615955,0.0005570347,0.00527065,0.015243986,0.9746964],"study_design_scores_gemma":[0.002005747,0.00035277414,0.0012496823,0.0016216971,0.00037650604,0.00030390368,0.0005263681,0.0036551286,0.0016552415,0.0019815497,0.9829953,0.0032761255],"about_ca_topic_score_codex":0.0013839229,"about_ca_topic_score_gemma":0.00040807977,"teacher_disagreement_score":0.9714203,"about_ca_system_score_codex":0.0007780282,"about_ca_system_score_gemma":0.0008448818,"threshold_uncertainty_score":0.9992275},"labels":[],"label_agreement":null},{"id":"W7006028432","doi":"","title":"Speech Recognition Based Upon a Segment Classification and Labelling Technique and Hidden Markov Model","year":2022,"lang":"en","type":"article","venue":"Canadian acoustics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Hidden Markov model; Pattern recognition (psychology); Labelling; Markov model; Acoustic model; Maximum-entropy Markov model","score_opus":0.03500273309650751,"score_gpt":0.22743946707279994,"score_spread":0.19243673397629243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7006028432","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09985021,0.00008696794,0.89442766,0.0024921189,0.0001591693,0.0005742136,0.00021612272,0.00013945397,0.0020540815],"genre_scores_gemma":[0.5847798,0.00003433709,0.41362342,0.0012857204,0.00001978677,0.00010658538,0.000028843157,0.000012127174,0.000109364686],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999098,0.00006848071,0.00014466656,0.00029754685,0.00017284468,0.00021843919],"domain_scores_gemma":[0.9993305,0.00007300733,0.00005491403,0.0002074871,0.00006699464,0.0002670607],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035890695,0.000102059435,0.00009435369,0.00028272846,0.00034193174,0.00013499662,0.00017864452,0.00005676322,0.00007383799],"category_scores_gemma":[0.000050606523,0.00012323163,0.0000177486,0.00022482117,0.00002562874,0.00011462583,0.00005543424,0.00016085003,0.000005466605],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000063255657,0.000029181929,0.0001001905,0.000033157452,0.000009161281,0.000058787133,0.00014854979,0.00016067666,0.028760564,0.00039638596,0.0017244968,0.9685725],"study_design_scores_gemma":[0.00015282963,0.000034457244,0.0005653219,0.000015373203,0.000016332317,0.00006069367,0.000120197765,0.99465567,0.0011882294,0.0025534274,0.00044922106,0.00018826262],"about_ca_topic_score_codex":0.00087426376,"about_ca_topic_score_gemma":0.00069503434,"teacher_disagreement_score":0.994495,"about_ca_system_score_codex":0.00026893438,"about_ca_system_score_gemma":0.00033161478,"threshold_uncertainty_score":0.502524},"labels":[],"label_agreement":null},{"id":"W7009343680","doi":"","title":"The Effect of LPC Order on The Performance of Vector Quantization in Isolated-Word Recognition","year":2022,"lang":"en","type":"article","venue":"Canadian acoustics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Vector quantization; Quantization (signal processing); Pattern recognition (psychology); Order (exchange); Control theory (sociology)","score_opus":0.012971245003816393,"score_gpt":0.20651318531538204,"score_spread":0.19354194031156566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7009343680","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.994707,0.000032734297,0.0031677263,0.00075592607,0.00036762908,0.00024662097,0.000032672768,0.000012937837,0.0006767558],"genre_scores_gemma":[0.9993799,0.00002754727,0.0002733841,0.00021464216,0.000013434418,0.000027519985,0.000005876668,0.0000062496947,0.00005148754],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99916685,0.00020066518,0.00017829989,0.00011009602,0.00018162762,0.00016246882],"domain_scores_gemma":[0.9989275,0.0006144159,0.00009206405,0.00024230035,0.00007525022,0.000048511392],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005657164,0.00006753995,0.000091979186,0.00014239541,0.00023208749,0.00002793713,0.00038515273,0.000027804674,0.000090856534],"category_scores_gemma":[0.0003079846,0.00004601002,0.000027241167,0.00067058177,0.000040955012,0.000048783717,0.000031578384,0.00014971962,0.000012658123],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019897503,0.00008724974,0.011740321,0.00014203132,0.00007603484,0.000032278927,0.0012550977,0.013617916,0.011387278,0.0035484387,0.0063106935,0.9516037],"study_design_scores_gemma":[0.00042968369,0.0009558297,0.025772758,0.000083348605,0.000024360505,0.0000147996825,0.00018064455,0.9617126,0.008466383,0.0002885408,0.0018537107,0.00021735043],"about_ca_topic_score_codex":0.0013208803,"about_ca_topic_score_gemma":0.0023051882,"teacher_disagreement_score":0.95138633,"about_ca_system_score_codex":0.00009047187,"about_ca_system_score_gemma":0.00018250958,"threshold_uncertainty_score":0.19967847},"labels":[],"label_agreement":null},{"id":"W7019613109","doi":"","title":"Hierarchical Recognition of French Vowels by Expert System Iroise-Serac","year":2022,"lang":"en","type":"article","venue":"Canadian acoustics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Expert system; Hierarchical control system; Legal expert system; Pattern recognition (psychology); Knowledge base","score_opus":0.019236881012785003,"score_gpt":0.21382764349238406,"score_spread":0.19459076247959906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7019613109","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31422338,0.0012684366,0.6043452,0.006819412,0.0064291814,0.0013455588,0.0048792535,0.0007691988,0.059920404],"genre_scores_gemma":[0.97786653,0.000013352573,0.020009452,0.0013641543,0.00008092704,0.000046075682,0.000072831725,0.000016882817,0.0005298082],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99868983,0.00012816278,0.00025948408,0.0002755219,0.00032651334,0.00032051056],"domain_scores_gemma":[0.9989397,0.00012924508,0.00008211981,0.0003463067,0.0000978328,0.0004047915],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002289746,0.00011410677,0.00017048474,0.00025115896,0.00024239827,0.00006473392,0.0005903634,0.000059664348,0.0005598381],"category_scores_gemma":[0.00008605705,0.00013127466,0.000065164015,0.00038176947,0.000041473937,0.0000995978,0.00008275892,0.00020060973,0.0000718786],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009307883,0.00016993757,0.00015138436,0.000105729734,0.00007501946,0.0004070776,0.0018799651,0.00012928392,0.032297578,0.0032049199,0.50345373,0.45811608],"study_design_scores_gemma":[0.0032304712,0.0011677004,0.0063218973,0.00038606118,0.00018042208,0.0014866901,0.0069715586,0.6313037,0.023029417,0.0068401406,0.31527904,0.0038028662],"about_ca_topic_score_codex":0.010603396,"about_ca_topic_score_gemma":0.00068597985,"teacher_disagreement_score":0.6636431,"about_ca_system_score_codex":0.00040257623,"about_ca_system_score_gemma":0.00042795468,"threshold_uncertainty_score":0.9959851},"labels":[],"label_agreement":null},{"id":"W7022136763","doi":"","title":"Introduction","year":2020,"lang":"en","type":"article","venue":"eYLS (Yale Law School)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"The arctic; Arctic; Multidisciplinary approach; Corporate governance; Indigenous; Work (physics); Fishing","score_opus":0.02161385027929595,"score_gpt":0.23265043975838118,"score_spread":0.2110365894790852,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7022136763","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.042464476,0.00040059604,0.51395726,0.2876554,0.003386391,0.0005370387,0.000011854118,0.0026785363,0.1489084],"genre_scores_gemma":[0.7648202,0.00004430611,0.1897999,0.037007414,0.0055800974,0.000041422456,0.0000115805215,0.000033107717,0.0026619362],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99905014,0.00005750207,0.00015050593,0.00035795456,0.00020637787,0.00017751128],"domain_scores_gemma":[0.9993199,0.00003164864,0.000041683572,0.0003135717,0.00005525391,0.00023792463],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00012225188,0.00009334765,0.000114385584,0.000026049494,0.000104836894,0.00018590034,0.00044138115,0.000045429224,0.0014405759],"category_scores_gemma":[0.00016008031,0.00008970992,0.000063780746,0.00028928564,0.000028328872,0.0005143435,0.000097806536,0.0001415237,0.0057765837],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022004064,0.00009255944,0.00022228963,0.00002874402,0.000043083553,0.00005266682,0.00037446013,0.000019139246,0.013267349,0.551239,0.22715387,0.20748486],"study_design_scores_gemma":[0.00025909563,0.000064340056,0.00040266116,0.000005873794,0.000005984242,0.000020899943,0.00003051423,0.0033516143,0.044086173,0.0034631155,0.94809145,0.00021830443],"about_ca_topic_score_codex":0.000028628936,"about_ca_topic_score_gemma":0.000013258273,"teacher_disagreement_score":0.7223558,"about_ca_system_score_codex":0.000021263953,"about_ca_system_score_gemma":0.000025911826,"threshold_uncertainty_score":0.99947226},"labels":[],"label_agreement":null},{"id":"W7024091935","doi":"","title":"Promoting Inclusive Systems for Migrants in Education","year":2024,"lang":"en","type":"other","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Promotion (chess); Inclusion (mineral); Quality (philosophy); Capability approach; Youth studies; Higher education","score_opus":0.01791785218485285,"score_gpt":0.29081109361695856,"score_spread":0.2728932414321057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7024091935","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00000478353,0.0028959187,0.02211654,0.000592248,0.0025191575,0.0009824255,0.000011370767,0.00037658887,0.97050095],"genre_scores_gemma":[0.00033689497,0.000062388346,0.023021445,0.00017210907,0.00032272958,0.00035650522,0.000008266436,0.00012866425,0.975591],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992648,0.000027228387,0.00015196016,0.0003193542,0.000110446155,0.00012624453],"domain_scores_gemma":[0.9996274,0.00004107054,0.000069207694,0.00020036472,0.000028876855,0.00003308197],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016646161,0.0001127555,0.00015690642,0.000408685,0.000012606522,0.00014604989,0.0002954511,0.00012351884,0.00012470428],"category_scores_gemma":[0.00004355365,0.00009532839,0.000047844973,0.00019875726,0.0000060307334,0.000049878305,0.00007366721,0.000061032748,0.00055709766],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.6709798e-7,0.00004775966,0.0000033651731,0.00044802696,0.0000144066325,0.000002631307,0.00040815305,3.0330394e-8,0.0000076018446,0.008077745,0.75165486,0.23933505],"study_design_scores_gemma":[0.00007979582,0.000012823783,0.0000026312223,0.0017506145,0.000006965164,0.000010661689,0.00014630085,0.01044817,0.00009515474,0.0023680753,0.98488635,0.0001924661],"about_ca_topic_score_codex":0.0005119637,"about_ca_topic_score_gemma":0.00029810282,"teacher_disagreement_score":0.23914258,"about_ca_system_score_codex":0.00005433544,"about_ca_system_score_gemma":0.00014607194,"threshold_uncertainty_score":0.716055},"labels":[],"label_agreement":null},{"id":"W7024242503","doi":"","title":"Proceso de internacionalización de las medianas empresas: caso de estudio del sector alimenticio del casco central de la provincia de Heredia en el período 2005-2010","year":2016,"lang":"es","type":"other","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Private sector; Primary sector of the economy; Economic sector; Quarter (Canadian coin)","score_opus":0.012075088849600606,"score_gpt":0.27611303714122293,"score_spread":0.2640379482916223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7024242503","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30391493,0.003318089,0.5534432,0.002703019,0.002383573,0.0026428448,0.00049964624,0.0014301889,0.12966453],"genre_scores_gemma":[0.27154195,0.003790806,0.21559155,0.0067873076,0.007962982,0.00085974456,0.000056668658,0.001206688,0.4922023],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99267006,0.0012884786,0.0008408025,0.0014153363,0.0009158663,0.002869443],"domain_scores_gemma":[0.9955585,0.0012396063,0.0005159602,0.00089851924,0.00024130159,0.0015461011],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0017753554,0.0011176077,0.00094438525,0.0005805784,0.0002864555,0.00060542143,0.0023949326,0.0013235264,0.008965929],"category_scores_gemma":[0.0008215155,0.0009564763,0.00054256135,0.00027662603,0.0004484213,0.00040065168,0.00053427287,0.00085126486,0.0010647719],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003280042,0.0020557067,0.4639188,0.0012391431,0.0032937964,0.0068204887,0.01998607,0.000036348112,0.0064976644,0.008450305,0.37707758,0.1102961],"study_design_scores_gemma":[0.00849467,0.0007184256,0.26206687,0.0068347296,0.0023361617,0.017738286,0.0026727053,0.053677347,0.07906285,0.0069603273,0.55083233,0.008605319],"about_ca_topic_score_codex":0.0058643688,"about_ca_topic_score_gemma":0.007924896,"teacher_disagreement_score":0.36253777,"about_ca_system_score_codex":0.0026362494,"about_ca_system_score_gemma":0.0056527606,"threshold_uncertainty_score":0.99998426},"labels":[],"label_agreement":null},{"id":"W7024469088","doi":"","title":"Sequential decision modeling in uncertain conditions","year":2023,"lang":"fr","type":"dissertation","venue":"Papyrus : Institutional Repository (Université de Montréal)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Compute Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Canadian Institute for Advanced Research","keywords":"Decision process; Context (archaeology); Decision theory","score_opus":0.030841804608981224,"score_gpt":0.22930683564816084,"score_spread":0.19846503103917962,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7024469088","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91743374,0.005078317,0.04376054,0.00083013705,0.0063367747,0.0007462748,0.00017372661,0.00045227748,0.025188219],"genre_scores_gemma":[0.90860295,0.0013692987,0.019834308,0.00022046635,0.00034226518,0.00010530512,0.0011008669,0.00008176944,0.06834277],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99629086,0.00027086327,0.0007292607,0.0010372613,0.0009997829,0.00067198055],"domain_scores_gemma":[0.99788153,0.00041600742,0.0003165574,0.00053194055,0.0004602927,0.0003936445],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.00042731498,0.0005157428,0.00051623804,0.001043739,0.005859294,0.00023491264,0.00088525726,0.00065488234,0.00016025754],"category_scores_gemma":[0.00023078431,0.0006489063,0.0004483827,0.0012214006,0.00017873343,0.00089103665,0.0003008079,0.00062381924,0.0007569231],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001529235,0.0013375025,0.005426557,0.0005406922,0.0008662187,0.04041711,0.13202526,0.38976467,0.02277764,0.1736744,0.002234016,0.22940671],"study_design_scores_gemma":[0.0013191547,0.00006798607,0.0056919814,0.0012517431,0.00016667166,0.00088519417,0.025148684,0.9516103,0.0031550257,0.0063510034,0.0034756514,0.00087657745],"about_ca_topic_score_codex":0.074431404,"about_ca_topic_score_gemma":0.04101949,"teacher_disagreement_score":0.56184566,"about_ca_system_score_codex":0.0064758128,"about_ca_system_score_gemma":0.0027825497,"threshold_uncertainty_score":0.99959624},"labels":[],"label_agreement":null},{"id":"W7025064530","doi":"","title":"Une continuité essentielle toujours engagée dans la réussite collégiale : mémoire présenté à la Commission parlementaire de l'éducation sur l'enseignement collégial québécois /","year":2015,"lang":"fr","type":"other","venue":"Bibliothèque et Archives nationales du Québec (Québec government)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Commission; Context (archaeology); Government (linguistics); Legislation","score_opus":0.017892423987609707,"score_gpt":0.24635385212684802,"score_spread":0.2284614281392383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7025064530","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034833744,0.0028701995,0.013519888,0.04134748,0.0009109789,0.0015550862,0.00070384046,0.00036628547,0.9038925],"genre_scores_gemma":[0.20848517,0.00085435325,0.0075552585,0.0014356576,0.0008413071,0.00052378466,0.00015171264,0.00035226322,0.7798005],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9915042,0.002479685,0.0013106163,0.0013628611,0.0024346316,0.00090801064],"domain_scores_gemma":[0.98479235,0.011809042,0.0013356815,0.00092990766,0.00032869814,0.0008043289],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0017828414,0.0010952448,0.000983465,0.0012186005,0.00077831786,0.0013665245,0.0018473844,0.00041651633,0.008026068],"category_scores_gemma":[0.0041015195,0.0011240173,0.0005496343,0.0017264244,0.00079604366,0.0008871559,0.000907995,0.0008244016,0.0004250947],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00028139065,0.0026899574,0.0120407725,0.00034787832,0.000735043,0.00022709851,0.050098713,0.00012677374,0.0019258843,0.024750585,0.8876058,0.01917011],"study_design_scores_gemma":[0.0026467836,0.00028364253,0.04357765,0.0010227533,0.00028717355,0.00027831487,0.004298084,0.0055541336,0.0012022993,0.00068919663,0.93892473,0.0012352129],"about_ca_topic_score_codex":0.38731596,"about_ca_topic_score_gemma":0.97853017,"teacher_disagreement_score":0.59121424,"about_ca_system_score_codex":0.02733972,"about_ca_system_score_gemma":0.1635227,"threshold_uncertainty_score":0.99967015},"labels":[],"label_agreement":null},{"id":"W7025243928","doi":"","title":"TonB-protein interactions in nutrient uptake systems of «Escherichia coli»","year":2010,"lang":"en","type":"other","venue":"Library and Archives Canada (Government of Canada)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Nutrient; Bacteria; Mechanism (biology); Essential nutrient","score_opus":0.0059942614857877025,"score_gpt":0.16116464028990743,"score_spread":0.1551703788041197,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7025243928","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022405572,0.0002753618,0.0016478953,0.0011712619,0.00080927555,0.0003752785,0.0002819044,0.000024741568,0.9931737],"genre_scores_gemma":[0.23598133,0.00016001253,0.018706601,0.00046349154,0.00014656784,0.00006578418,0.000012597154,0.00012824534,0.74433535],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977567,0.00007151582,0.0003704478,0.00028635297,0.0012986808,0.00021626987],"domain_scores_gemma":[0.9990066,0.0001279897,0.00034076237,0.00034937164,0.0000010455966,0.00017421538],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000017087064,0.00020388942,0.00037086505,0.0000928654,0.000039618433,0.000033491877,0.0004909335,0.00005402563,0.0001898777],"category_scores_gemma":[0.000007035519,0.00019963346,0.000036500966,0.00014204574,0.000052676576,0.00017822001,0.00016006439,0.00024612455,1.1475517e-8],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026156736,0.0003913547,0.0033196183,0.0016525591,0.00040290112,0.000377253,0.00024047324,0.000015868542,0.058372203,0.7327273,0.11578294,0.08645595],"study_design_scores_gemma":[0.00034163435,0.00003721885,0.0023216314,0.0008611227,0.00001147818,0.000009054445,0.00053670607,0.0021564995,0.043651443,0.00043449845,0.9492794,0.00035926956],"about_ca_topic_score_codex":0.016660303,"about_ca_topic_score_gemma":0.13660371,"teacher_disagreement_score":0.8334965,"about_ca_system_score_codex":0.0000078799085,"about_ca_system_score_gemma":0.0011965544,"threshold_uncertainty_score":0.98988783},"labels":[],"label_agreement":null},{"id":"W7025320981","doi":"","title":"An Ultrasound Investigation of Possible Covert Contrasts in First Language Acquisition: The Case of /sp ~ sw ~ sm/ > [f] Mergers","year":2010,"lang":"en","type":"article","venue":"Canadian acoustics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Covert; Ultrasound; Language understanding; Perspective (graphical)","score_opus":0.00856648009175951,"score_gpt":0.22449331340096626,"score_spread":0.21592683330920676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7025320981","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9938826,0.000029608475,0.0043244,0.0004282026,0.00030759218,0.00013775921,0.00012111657,0.000016980763,0.0007517243],"genre_scores_gemma":[0.9928234,0.000007384299,0.0065142657,0.00055604044,0.0000497063,0.0000054405787,0.000012729219,0.0000074964355,0.00002349208],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99921966,0.000053836084,0.00023447827,0.00016610893,0.000118757445,0.00020716051],"domain_scores_gemma":[0.998777,0.0002962664,0.0000995517,0.00043128265,0.00013134544,0.0002645914],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000317791,0.000092683076,0.00013608411,0.00019046834,0.00009713083,0.00006434967,0.0003711803,0.00009554446,0.00016376993],"category_scores_gemma":[0.00024304165,0.00008196825,0.000034786586,0.0003925188,0.00015488279,0.00019941988,0.00001144899,0.00013965686,0.000007850383],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018569031,0.00013174073,0.01790766,0.00014724227,0.00007189617,0.0023829034,0.014110741,0.0013211885,0.89801604,0.023723766,0.007360758,0.034807492],"study_design_scores_gemma":[0.0025400154,0.00042711958,0.42225596,0.00030501766,0.00017836822,0.0029697507,0.009262182,0.3672526,0.18606237,0.0064519183,0.0007670132,0.0015277079],"about_ca_topic_score_codex":0.028822884,"about_ca_topic_score_gemma":0.18669116,"teacher_disagreement_score":0.7119537,"about_ca_system_score_codex":0.00005603295,"about_ca_system_score_gemma":0.00039221812,"threshold_uncertainty_score":0.97764426},"labels":[],"label_agreement":null},{"id":"W7025401875","doi":"","title":"Where are the voices coming from? Canadian culture and the legacies of history","year":2004,"lang":"en","type":"book","venue":"CentAUR (University of Reading)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Narrative; Agency (philosophy); Colonialism","score_opus":0.011807440498167204,"score_gpt":0.16576960607504762,"score_spread":0.15396216557688042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7025401875","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024410586,0.015118382,0.0022125142,0.007690164,0.0009655446,0.0006136927,0.00028671054,0.000089477784,0.9705825],"genre_scores_gemma":[0.016656334,0.0033476434,0.0045422195,0.0006244658,0.00011727914,4.587855e-7,0.000043978107,0.000023105142,0.97464454],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992533,0.00006663342,0.00009598387,0.00023351931,0.00020674367,0.00014386256],"domain_scores_gemma":[0.99894804,0.00016013594,0.00032696212,0.00036439384,0.00010351874,0.000096966716],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015136244,0.00014457693,0.00031590962,0.000120793564,0.00026451284,0.00003101531,0.0009780101,0.00016434919,0.00017013316],"category_scores_gemma":[0.000015980339,0.00010958637,0.00014550272,0.00006237274,0.0006932779,0.00020290863,0.00015269412,0.0002326789,0.000011172962],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010933431,0.00006531873,0.00087191147,0.0006180316,0.0010525403,0.00024740407,0.13003659,0.0000062103472,0.00010095006,0.19360998,0.613748,0.05953373],"study_design_scores_gemma":[0.00057361653,0.0000128513675,0.00052342424,0.00061942765,0.00012201645,0.000009031432,0.0075921,0.00012132705,0.00003204249,0.0024124961,0.9877931,0.0001885708],"about_ca_topic_score_codex":0.05831102,"about_ca_topic_score_gemma":0.15499862,"teacher_disagreement_score":0.3740451,"about_ca_system_score_codex":0.00073306257,"about_ca_system_score_gemma":0.000749147,"threshold_uncertainty_score":0.9479598},"labels":[],"label_agreement":null},{"id":"W7027868473","doi":"","title":"Deep neural networks for voice control","year":2023,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; McGill University","keywords":"","score_opus":0.0219650226790906,"score_gpt":0.25048067043630934,"score_spread":0.22851564775721875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7027868473","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4853058,0.003644934,0.027773937,0.0014892364,0.115213975,0.026024785,0.0073054037,0.025035309,0.30820662],"genre_scores_gemma":[0.9614963,0.00020293193,0.014299116,0.002660271,0.00045962344,0.0017386087,0.0015206713,0.0005259177,0.017096573],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9951284,0.0003744932,0.0009811294,0.0015733623,0.0008057468,0.0011368932],"domain_scores_gemma":[0.99549437,0.001595632,0.0006340687,0.0011173757,0.00069843704,0.00046012338],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0011239289,0.0008369443,0.0009337942,0.0005380504,0.0013052444,0.00040867442,0.0020777914,0.00095312303,0.00009761061],"category_scores_gemma":[0.0013605596,0.00088607945,0.00079351495,0.000966928,0.000038444654,0.0010092648,0.00014442347,0.0011742099,0.0007678515],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001489544,0.000106175365,0.000004890603,0.00014858393,0.00024195576,0.00007964627,0.0000068545146,0.00038421244,0.0007289081,0.031665374,0.00004700783,0.96643746],"study_design_scores_gemma":[0.0072735394,0.0007852362,0.0024890387,0.0007413924,0.00095524546,0.00014518843,0.00048148943,0.77375376,0.021693943,0.083139345,0.102651276,0.005890527],"about_ca_topic_score_codex":0.00008122592,"about_ca_topic_score_gemma":0.0012205223,"teacher_disagreement_score":0.9605469,"about_ca_system_score_codex":0.00030950556,"about_ca_system_score_gemma":0.000040085673,"threshold_uncertainty_score":0.99999493},"labels":[],"label_agreement":null},{"id":"W7028486788","doi":"","title":"Fine-tuning an Automatic Speech Recognition model for a Canadian Indigenous counselling program","year":2025,"lang":"en","type":"dissertation","venue":"Mspace (University of Manitoba)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"Acoustic model; Adaptability; Outlier; Speech corpus; Software; Speech technology; Hidden Markov model; Language model","score_opus":0.037547961906066595,"score_gpt":0.24052708833876238,"score_spread":0.20297912643269578,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7028486788","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7499873,0.00010917515,0.2395708,0.0003894006,0.00069621217,0.0026190456,0.0002639552,0.00068289,0.005681253],"genre_scores_gemma":[0.043965694,0.00019867712,0.9477273,0.000105757346,0.00008197825,0.00002659864,0.0028509588,0.000057736586,0.0049852678],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99856573,0.000064023116,0.00016549739,0.00050732226,0.00029586785,0.00040158248],"domain_scores_gemma":[0.9985003,0.00009490023,0.00027822613,0.0003997873,0.0005126835,0.00021413877],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00029148217,0.00024930193,0.00037028137,0.0008483924,0.00060290314,0.00014015108,0.00087696494,0.00035527436,0.000010247675],"category_scores_gemma":[0.000028487906,0.00035632603,0.00018371896,0.00043493844,0.00002413567,0.0005436585,0.000019551098,0.00022254334,0.00002759019],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025633988,0.00012567511,0.000049695354,0.00045305106,0.00008662916,0.000039958097,0.0029712445,0.000065119115,0.000056609155,0.00013537517,0.0006966017,0.9952944],"study_design_scores_gemma":[0.00042627822,0.00015758183,0.0007467285,0.00055290817,0.00017650223,0.0000067997025,0.0066338903,0.9859156,0.00044164518,0.0034401217,0.0010079832,0.000493969],"about_ca_topic_score_codex":0.03167831,"about_ca_topic_score_gemma":0.9805257,"teacher_disagreement_score":0.99480045,"about_ca_system_score_codex":0.00025840857,"about_ca_system_score_gemma":0.0010216521,"threshold_uncertainty_score":0.9998889},"labels":[],"label_agreement":null},{"id":"W7028694018","doi":"","title":"Gastroenteric, Zoonotic and Vectorborne Diseases in Ireland: Quarterly report: Quarter 1, 2024","year":2024,"lang":"en","type":"report","venue":"Lenus, The Irish Health Repository (Dr Steevens Hospital Library)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quarter (Canadian coin); Hand washing; Shower; Sanitation; Clean water; Contaminated food; Food preparation; Washing hands; Laundry","score_opus":0.01341536060511671,"score_gpt":0.25482735189314404,"score_spread":0.24141199128802732,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7028694018","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19155724,0.22927722,0.0078959055,0.25319782,0.1315031,0.01466148,0.0019198201,0.0073738876,0.16261351],"genre_scores_gemma":[0.80455947,0.008946771,0.009585162,0.0064025065,0.008383677,0.0016184923,0.0006779594,0.0009838254,0.15884216],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9931597,0.0006093211,0.0019523063,0.0018555581,0.0013248533,0.001098265],"domain_scores_gemma":[0.9958263,0.0004146545,0.0010885368,0.0019201293,0.00011968986,0.00063071353],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006828001,0.0008501569,0.001256127,0.00057185505,0.00033396613,0.0013780892,0.0013042979,0.00039793443,0.00006837046],"category_scores_gemma":[0.00009352514,0.00066889304,0.00048604506,0.00073900155,0.00021154151,0.0012817166,0.00044974458,0.0013711334,0.00008704635],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003670466,0.00042852716,0.012745378,0.001881003,0.00026464427,0.011870945,0.0016611555,0.0000017050253,0.0000027965455,0.00009745614,0.9299973,0.041012365],"study_design_scores_gemma":[0.0014082589,0.004661309,0.32485572,0.008628927,0.00044422556,0.00935342,0.0012337114,0.0017762895,0.00007853404,0.0028852976,0.64146453,0.0032097916],"about_ca_topic_score_codex":0.00068992336,"about_ca_topic_score_gemma":0.000037580292,"teacher_disagreement_score":0.6130022,"about_ca_system_score_codex":0.00037786143,"about_ca_system_score_gemma":0.0020836052,"threshold_uncertainty_score":0.9996586},"labels":[],"label_agreement":null},{"id":"W7030535816","doi":"","title":"Newsletters - Potters Guild of British Columbia 2006 July 1","year":2006,"lang":"en","type":"other","venue":"Arca (British Columbia Electronic Library Network)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Guild; Assemblage (archaeology); Government (linguistics); Period (music)","score_opus":0.00371546682897417,"score_gpt":0.1612861864951602,"score_spread":0.15757071966618602,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7030535816","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012687077,0.007968555,0.00041842094,0.00044861145,0.0013893684,0.0012405558,0.000762142,0.0020004208,0.98564506],"genre_scores_gemma":[0.006763291,0.003060303,0.017893588,0.0056700334,0.002173365,0.00021150269,0.00066712033,0.0010343733,0.96252644],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99351233,0.00042149716,0.0011316533,0.0017298901,0.000900991,0.0023036532],"domain_scores_gemma":[0.9970518,0.0002088664,0.00087153853,0.0014539052,0.000060349274,0.00035355036],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00028792906,0.0004617693,0.001299765,0.00015479655,0.00026693146,0.0047600893,0.00299449,0.00076577335,0.091982245],"category_scores_gemma":[0.000021413794,0.0012135953,0.0006414825,0.0015303522,0.00033364943,0.00109706,0.0006414585,0.0009959949,0.00015617188],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000028772163,0.00018782752,0.0009245804,0.00008144911,0.0002113584,0.00036581035,0.0000033693548,0.0000054986167,5.763794e-7,0.00037200135,0.8767991,0.121045545],"study_design_scores_gemma":[0.0009557236,0.00019804925,0.00053713744,0.0014010111,0.00008383228,0.00055352814,0.0000026837808,0.00027965748,0.0000031784562,0.04333256,0.9513901,0.0012625215],"about_ca_topic_score_codex":0.23102738,"about_ca_topic_score_gemma":0.65615404,"teacher_disagreement_score":0.42512664,"about_ca_system_score_codex":0.00013683985,"about_ca_system_score_gemma":0.00071082124,"threshold_uncertainty_score":0.99903136},"labels":[],"label_agreement":null},{"id":"W7033575953","doi":"","title":"Renowned Alberta Marketer & Creative Genius @Eric Cheng from 12 Creative chops it up with us on The Business Growth School","year":2019,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Genius; Social media; Value (mathematics); Creativity; Business opportunity; Key (lock)","score_opus":0.010590378243418415,"score_gpt":0.18064254734760848,"score_spread":0.17005216910419008,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7033575953","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00018355394,0.000064332155,0.000052527597,0.0012624307,0.00036300428,0.0008957634,0.00013915819,0.000158701,0.99688053],"genre_scores_gemma":[0.000288759,0.00025031532,0.0066933543,0.0016719617,0.0001702196,0.00007175488,0.00014826973,0.00011905603,0.9905863],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974066,0.00028891984,0.0006156937,0.00051646656,0.0007674799,0.0004048658],"domain_scores_gemma":[0.99654615,0.00091326976,0.00088394264,0.0010255553,0.000458472,0.00017258177],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00027454406,0.0006066281,0.0006380575,0.00015745452,0.000140584,0.0002757416,0.0011510245,0.0003994644,0.34729642],"category_scores_gemma":[0.000658615,0.00041160663,0.00018298118,0.000048075904,0.00017256985,0.0000021725352,0.00019286519,0.00042407395,0.035838217],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024197911,0.00005224652,0.0000073441847,0.00010311524,0.00024309546,0.000009244478,0.0004449365,0.000015811096,4.2198172e-7,0.000039932565,0.99666685,0.0021750529],"study_design_scores_gemma":[0.0007799351,0.00011448756,0.00036176556,0.000790414,0.00008064887,0.00004101206,0.00014190757,0.00007385228,0.000040169987,0.000017968638,0.9970018,0.00055599085],"about_ca_topic_score_codex":0.022885712,"about_ca_topic_score_gemma":0.004817311,"teacher_disagreement_score":0.3114582,"about_ca_system_score_codex":0.00010684418,"about_ca_system_score_gemma":0.00009792143,"threshold_uncertainty_score":0.9998336},"labels":[],"label_agreement":null},{"id":"W7034498190","doi":"","title":"Toward detecting and classification non-verbal events and biosignals in hearables","year":2022,"lang":"en","type":"article","venue":"Canadian acoustics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Pattern recognition (psychology); Artificial neural network; Noise (video); Signal processing; Feature extraction","score_opus":0.03950968081213772,"score_gpt":0.23418033928138896,"score_spread":0.19467065846925125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7034498190","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9625747,0.00015621248,0.034013215,0.0017591993,0.00025591577,0.0001795453,0.000033533765,0.00003167231,0.0009959871],"genre_scores_gemma":[0.993626,0.000023466895,0.005690202,0.00057536294,0.000014311658,0.000014395235,0.0000015375434,0.0000047670337,0.00004995997],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99937946,0.000044369997,0.00010725747,0.00018658579,0.00009954541,0.00018276575],"domain_scores_gemma":[0.9995988,0.00006956092,0.000030188421,0.00010361752,0.000019905705,0.00017789766],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002269286,0.000058589983,0.00007433171,0.00021243017,0.00018147772,0.00007199728,0.00013877933,0.000027946146,0.000029805502],"category_scores_gemma":[0.00007086042,0.00006941283,0.000009593838,0.00023567962,0.000017174498,0.00008675529,0.000056748395,0.00010312025,0.000003997313],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008983926,0.0000543333,0.022094991,0.00007412031,0.000025405305,0.00026971166,0.0037313015,0.0002821146,0.046767477,0.0017223007,0.0027503062,0.922219],"study_design_scores_gemma":[0.0005945763,0.0001054221,0.33924016,0.000047431127,0.000015439246,0.0002530341,0.002537788,0.64968306,0.00070212805,0.0038487308,0.0024998402,0.0004723817],"about_ca_topic_score_codex":0.0034636362,"about_ca_topic_score_gemma":0.0022025923,"teacher_disagreement_score":0.92174655,"about_ca_system_score_codex":0.0001501728,"about_ca_system_score_gemma":0.00018222969,"threshold_uncertainty_score":0.5236005},"labels":[],"label_agreement":null},{"id":"W7037599012","doi":"","title":"Environmental Impacts of Tunnels in fractured crystalline rocks of the Central Alps","year":2007,"lang":"en","type":"book-chapter","venue":"Research Portal (Queen's University Belfast)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Nucleofection; Gestational period; TSG101; Liquation; Dysgeusia; Diafiltration; Emperipolesis; Triacetin; Durvalumab","score_opus":0.027095911277219904,"score_gpt":0.2566447456166851,"score_spread":0.22954883433946519,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7037599012","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11717832,0.0003226336,0.013537709,0.0033362105,0.0005648618,0.0037336892,0.0018876638,0.00018622068,0.8592527],"genre_scores_gemma":[0.92382187,0.0004958133,0.0008712504,0.000037169448,0.000055167253,3.6435574e-7,0.00003421707,0.00002812154,0.07465601],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9966531,0.00016361027,0.00042517358,0.0005163795,0.0015725932,0.00066914933],"domain_scores_gemma":[0.99814504,0.00030448122,0.0003443811,0.0007662703,0.00014155541,0.00029826773],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00071710243,0.00028736945,0.0004780285,0.0008488679,0.00014405379,0.000025065005,0.0015817567,0.00041650128,0.001391093],"category_scores_gemma":[0.00007314111,0.00025833564,0.00035443902,0.0002763976,0.0004895414,0.00030385083,0.00092290074,0.0009919952,0.00002375581],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0037123554,0.008088377,0.06898274,0.00253985,0.004439992,0.027854534,0.015583505,0.00076104375,0.019011201,0.4898311,0.044359013,0.3148363],"study_design_scores_gemma":[0.009880847,0.0022530903,0.36533245,0.004751066,0.0003318805,0.00019494872,0.004137742,0.0016749463,0.083379604,0.024389252,0.4991423,0.0045318906],"about_ca_topic_score_codex":0.0009076891,"about_ca_topic_score_gemma":0.00018697632,"teacher_disagreement_score":0.80664355,"about_ca_system_score_codex":0.0003258898,"about_ca_system_score_gemma":0.00039042244,"threshold_uncertainty_score":0.9999869},"labels":[],"label_agreement":null},{"id":"W7043108712","doi":"","title":"A Spectral-Temporal Suppression Hodel for Speech Recognition","year":2022,"lang":"en","type":"article","venue":"Canadian acoustics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Voice activity detection; Speech processing; Speaker recognition; Speech enhancement; Signal processing; Noise (video)","score_opus":0.0376745272477753,"score_gpt":0.24264028282403846,"score_spread":0.20496575557626318,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7043108712","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13130167,0.00010737536,0.8384318,0.008387458,0.0042683547,0.0014251906,0.002079114,0.00046329031,0.013535765],"genre_scores_gemma":[0.65725845,0.000011816576,0.3370642,0.0033259015,0.00025360516,0.00018139087,0.00023722247,0.00003344135,0.0016339449],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987988,0.0000591694,0.00018753002,0.00031632354,0.00022494064,0.00041322535],"domain_scores_gemma":[0.99905336,0.00010792918,0.000064792905,0.0003059229,0.000098360164,0.00036962127],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002890341,0.00011917757,0.00012712012,0.00028722445,0.0005014188,0.00015216932,0.0005150089,0.000052699594,0.0008108849],"category_scores_gemma":[0.00012441484,0.00013757538,0.000082893035,0.0003109636,0.000020663456,0.00017081956,0.000071176146,0.00016399939,0.000073798285],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022543483,0.0000891189,0.0001388068,0.000035968653,0.000028425793,0.0002944645,0.00035529188,0.00016837005,0.008896139,0.0018757957,0.2522884,0.7358067],"study_design_scores_gemma":[0.002024892,0.00058258633,0.0022608677,0.000054369528,0.00009843437,0.0007247228,0.0010568254,0.6545016,0.011602491,0.08956763,0.23586608,0.0016594649],"about_ca_topic_score_codex":0.0030675028,"about_ca_topic_score_gemma":0.0019495838,"teacher_disagreement_score":0.7341472,"about_ca_system_score_codex":0.00034075786,"about_ca_system_score_gemma":0.00055637566,"threshold_uncertainty_score":0.88786215},"labels":[],"label_agreement":null},{"id":"W7067814757","doi":"","title":"Northland Power Inc. Announces Results for the First Quarter of 2011 (MRW)","year":2011,"lang":"en","type":"other","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quarter (Canadian coin); Power (physics)","score_opus":0.025164371520317162,"score_gpt":0.22900613540276882,"score_spread":0.20384176388245165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7067814757","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000018250327,0.0002814528,0.035376277,0.0008764925,0.0006667735,0.00036974598,0.00019091126,0.00012784885,0.9621087],"genre_scores_gemma":[0.0012635447,0.00024371177,0.042604737,0.0010226335,0.0002865215,0.000103722254,0.000028603028,0.000110894005,0.95433563],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99901325,0.00002125783,0.00025848948,0.0003288821,0.0001976805,0.00018042479],"domain_scores_gemma":[0.9986613,0.00028045205,0.00024344792,0.0006846278,0.00008935484,0.000040825507],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00024694297,0.00017840747,0.00023501959,0.0001346918,0.000060836584,0.000048824717,0.00093979994,0.00016084767,0.0037913807],"category_scores_gemma":[0.000030594307,0.00010012862,0.000118720105,0.00007548929,0.00007348012,0.00006832571,0.00007663823,0.000066713204,0.00061157666],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015942038,0.000038454986,0.000027536069,0.000015621641,0.000054859112,0.0000010220334,0.00017172628,2.1686054e-8,3.6833262e-7,0.0022781934,0.98993164,0.007464615],"study_design_scores_gemma":[0.00031402998,0.00009112994,0.00027948822,0.000043275664,0.000014754999,0.0000029677756,0.00003647227,0.0001490598,0.00008371348,0.00043293316,0.9983803,0.00017187052],"about_ca_topic_score_codex":0.0005995125,"about_ca_topic_score_gemma":0.0026944971,"teacher_disagreement_score":0.008448665,"about_ca_system_score_codex":0.0000055213645,"about_ca_system_score_gemma":0.00003888299,"threshold_uncertainty_score":0.9971193},"labels":[],"label_agreement":null},{"id":"W7071542273","doi":"","title":"Text Input Using Speaker-Adaptive Connected Syllable Recognition","year":2022,"lang":"en","type":"article","venue":"Canadian acoustics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Syllable; Pattern recognition (psychology); Speech processing; Signal processing; Speaker recognition","score_opus":0.05008207425272345,"score_gpt":0.22521278818215595,"score_spread":0.1751307139294325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071542273","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36708105,0.00020070675,0.5771371,0.0017877873,0.0036707018,0.00086040475,0.0010532899,0.0005574461,0.047651503],"genre_scores_gemma":[0.9168235,0.0000070887295,0.0791798,0.0032167407,0.000123118,0.000023767321,0.000040694522,0.00002542396,0.00055983616],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986602,0.00012247264,0.00019235953,0.00032956255,0.00025659087,0.0004388223],"domain_scores_gemma":[0.99890727,0.00012198123,0.00008017293,0.00031736336,0.00017031968,0.00040288045],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00022680186,0.00013560125,0.000147222,0.00037428085,0.0006066014,0.00016545253,0.00047090332,0.000055295306,0.0017097867],"category_scores_gemma":[0.00016145899,0.00016849981,0.00005133935,0.0007603345,0.000038116897,0.00018961623,0.000111380774,0.00023106101,0.00022667355],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048944064,0.00027687082,0.00035621008,0.000054613098,0.0002558514,0.0027100537,0.0025910267,0.008302729,0.045065515,0.013372118,0.09264043,0.8343256],"study_design_scores_gemma":[0.0005951818,0.00018020935,0.0011178289,0.00003413006,0.00006561398,0.000514861,0.0014585627,0.9600146,0.0013162068,0.0066102245,0.027241979,0.00085062877],"about_ca_topic_score_codex":0.012487976,"about_ca_topic_score_gemma":0.0030642143,"teacher_disagreement_score":0.95171183,"about_ca_system_score_codex":0.0007655273,"about_ca_system_score_gemma":0.00094555423,"threshold_uncertainty_score":0.9992028},"labels":[],"label_agreement":null},{"id":"W7071593548","doi":"","title":"Some Considerations on The Definition of Sub-Word Units For a Template- Matching Speech Recognition System","year":2022,"lang":"en","type":"article","venue":"Canadian acoustics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Matching (statistics); Voice activity detection; Pattern recognition (psychology); Speech processing; Speaker recognition; Acoustic model","score_opus":0.0821286735079449,"score_gpt":0.2311703834526719,"score_spread":0.149041709944727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071593548","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8975435,0.0000949126,0.0770818,0.008240742,0.0028293822,0.0021520867,0.0042543737,0.00032823524,0.0074749533],"genre_scores_gemma":[0.9779872,0.0000052745913,0.019757705,0.0019066773,0.00008369538,0.00015167975,0.00006747576,0.000014835548,0.00002546665],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99896294,0.00013842616,0.00024869622,0.0001964149,0.00021409734,0.00023941937],"domain_scores_gemma":[0.99826723,0.0009557688,0.000121102465,0.00027859,0.00023783538,0.00013946768],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004643243,0.00010286628,0.00012949714,0.0002693989,0.0008102718,0.000118768796,0.00024838158,0.00004477107,0.00008319946],"category_scores_gemma":[0.00034404817,0.00009848867,0.000050887505,0.0003605851,0.000030190791,0.0001257501,0.00003390581,0.00015992028,0.00003275574],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028161334,0.00010000883,0.000017208677,0.00020084082,0.00011851331,0.00020811037,0.0014689153,0.0010918665,0.018700399,0.86264825,0.05155099,0.063866735],"study_design_scores_gemma":[0.0021947701,0.00086523657,0.001520357,0.00063217635,0.00034460783,0.0015441463,0.01630383,0.11876973,0.044168577,0.8063247,0.0054411306,0.0018907528],"about_ca_topic_score_codex":0.0017473764,"about_ca_topic_score_gemma":0.0014575314,"teacher_disagreement_score":0.11767786,"about_ca_system_score_codex":0.0003095928,"about_ca_system_score_gemma":0.0006271852,"threshold_uncertainty_score":0.62320375},"labels":[],"label_agreement":null},{"id":"W7083818636","doi":"10.17870/bathspa.30138790","title":"word-process-object_2","year":2025,"lang":"en","type":"dataset","venue":"Bath Spa University","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Thursday; Attendance; Ridiculous; Period (music)","score_opus":0.010233795827676707,"score_gpt":0.2245457471190524,"score_spread":0.2143119512913757,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7083818636","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000019335948,0.00003465235,0.0060799336,0.00037101528,0.0007191291,0.00013468463,0.9804866,0.00019368756,0.011961001],"genre_scores_gemma":[0.000030397716,0.00046668324,0.006147835,0.0008881671,0.00012618041,0.000001074487,0.9791985,0.000005117923,0.013136035],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99875396,0.0000764645,0.00010759505,0.00052323355,0.00029373792,0.00024501202],"domain_scores_gemma":[0.9987099,0.0001206952,0.000110942485,0.0008287926,0.00011648846,0.00011318901],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001280947,0.00021128189,0.00026488057,0.0004175236,0.00020532709,0.00009911161,0.002191606,0.00024376187,0.00045858312],"category_scores_gemma":[0.0000705394,0.00023713733,0.00013628606,0.0006884226,0.00004524906,0.00025623437,0.00054969115,0.00030030403,0.00019814353],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000055017717,0.000047547433,0.0000032984592,0.000044437194,0.000026525051,0.00018915962,0.000013062174,3.7920603e-7,2.8050843e-7,0.00022780056,0.987865,0.01157704],"study_design_scores_gemma":[0.00018407636,0.00001247182,0.000056345823,0.00007523506,0.000041936775,0.000006568625,0.000047114787,0.00008020269,0.0000427011,0.0001477918,0.99905366,0.00025188626],"about_ca_topic_score_codex":0.00020410804,"about_ca_topic_score_gemma":0.00015048932,"teacher_disagreement_score":0.0113251535,"about_ca_system_score_codex":0.00010915314,"about_ca_system_score_gemma":0.00036594443,"threshold_uncertainty_score":0.96701795},"labels":[],"label_agreement":null},{"id":"W7089305642","doi":"10.1017/psj.2025.10102","title":"Survey Insights: Perspectives on the Current Policy Climate","year":2025,"lang":"en","type":"article","venue":"Political Science Today","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kimberly-Clark (Canada)","funders":"","keywords":"Current (fluid); Government (linguistics); Climate change; Public policy","score_opus":0.04186002555645232,"score_gpt":0.340529924898125,"score_spread":0.2986698993416727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7089305642","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0798438,0.00034654542,0.027560143,0.14682746,0.0016084227,0.0003991847,0.000033167864,0.00045996218,0.7429213],"genre_scores_gemma":[0.9961619,0.000035392666,0.00048709923,0.0030529615,0.00007151961,0.000016851189,3.5101803e-7,0.0000026604282,0.00017131054],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99761593,0.00024334098,0.00018024138,0.0005111405,0.0005221607,0.0009271699],"domain_scores_gemma":[0.99770737,0.00116857,0.000029963903,0.0005928633,0.00021354614,0.00028767303],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015580575,0.00012712239,0.00012494648,0.0003428397,0.00060441974,0.0004544677,0.0015935438,0.000025743882,0.000051239866],"category_scores_gemma":[0.0041619544,0.000074475196,0.00006411536,0.00223157,0.00090294605,0.0003195037,0.0003986205,0.00020501508,0.00037226532],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014699795,0.00006987417,0.00020970234,0.0000018310683,0.0000017203115,7.0631256e-7,0.00020616317,1.7146336e-7,0.00004555758,0.92633003,0.00020183311,0.07293096],"study_design_scores_gemma":[0.00036771537,0.00014712014,0.5176102,0.00018569082,0.000010227619,0.000006095302,0.001267618,0.020473626,0.016233047,0.42154276,0.021491883,0.0006640389],"about_ca_topic_score_codex":0.00016435543,"about_ca_topic_score_gemma":0.000022817174,"teacher_disagreement_score":0.91631806,"about_ca_system_score_codex":0.00030859138,"about_ca_system_score_gemma":0.0006478532,"threshold_uncertainty_score":0.4982549},"labels":[],"label_agreement":null},{"id":"W7095177847","doi":"","title":"Mixed-mode Multilinguality in TTS: The Case of Canadian French","year":2006,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Pronunciation; Intelligibility (philosophy); French; Context (archaeology); British English","score_opus":0.03380943487620321,"score_gpt":0.2670775767187989,"score_spread":0.2332681418425957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7095177847","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9138495,0.00002629953,0.00703141,0.0015386484,0.00014252572,0.000113128066,0.000016492895,0.000037017086,0.07724502],"genre_scores_gemma":[0.97911155,0.000001461282,0.02040762,0.00021799841,0.000015413352,0.0000041994513,8.5031616e-7,0.000001879772,0.00023902307],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99939364,0.000069954775,0.0001739741,0.00013925793,0.00006739148,0.00015578231],"domain_scores_gemma":[0.99943894,0.00014179166,0.000028760487,0.0002895807,0.000047121503,0.00005380716],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002820094,0.00005343567,0.00007652042,0.00022306228,0.00004991107,0.00003163772,0.00027962553,0.000033563065,0.00009842179],"category_scores_gemma":[0.00005600016,0.00003656067,0.000033648488,0.0004962984,0.000030402602,0.00007970651,0.000027739972,0.00005395673,0.00005460322],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000023420257,0.00029466295,0.019824939,0.000022866374,0.000017167806,0.0030684087,0.0021351802,0.00012702172,0.0007072173,0.1365147,0.017113874,0.82017165],"study_design_scores_gemma":[0.0016819304,0.000071784336,0.23546107,0.00007488102,0.000019551348,0.0021480997,0.002783992,0.47621816,0.18172711,0.06040009,0.038344223,0.0010690902],"about_ca_topic_score_codex":0.8939651,"about_ca_topic_score_gemma":0.9801287,"teacher_disagreement_score":0.8191025,"about_ca_system_score_codex":0.000031692674,"about_ca_system_score_gemma":0.0001013547,"threshold_uncertainty_score":0.14909008},"labels":[],"label_agreement":null},{"id":"W7095779796","doi":"","title":"Mixedmode multilinguality in TTS: The case of Canadian French","year":2006,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Pronunciation; Intelligibility (philosophy); French; Context (archaeology); British English","score_opus":0.026460925611151837,"score_gpt":0.25120654448978397,"score_spread":0.22474561887863212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7095779796","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8923491,0.000034250923,0.008800219,0.0018665767,0.00011490328,0.00012021936,0.000012162204,0.000036907586,0.096665636],"genre_scores_gemma":[0.9801807,0.0000013676762,0.01933816,0.00023125566,0.000012999486,0.000003741014,5.788748e-7,0.0000016265739,0.00022961479],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99944973,0.000062651576,0.00015959785,0.00012639776,0.00005957647,0.00014206636],"domain_scores_gemma":[0.99948925,0.00012750064,0.000025646967,0.00026771758,0.000042177373,0.000047712732],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029573267,0.00004776749,0.000068972346,0.00021434794,0.000045129298,0.000028463448,0.0002591819,0.00002982243,0.00010793874],"category_scores_gemma":[0.000047803813,0.00003238002,0.00002989209,0.00047987132,0.000027507622,0.000074125135,0.000024147465,0.00004853727,0.000050224266],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000028457391,0.0003586855,0.029914161,0.000027186077,0.00001971163,0.004054596,0.002998352,0.00013979866,0.00082706293,0.14439966,0.015548397,0.80170953],"study_design_scores_gemma":[0.0016816793,0.00006682048,0.28665334,0.00007127499,0.00001774265,0.0022728622,0.0023515653,0.4714067,0.13018367,0.070107855,0.034160517,0.0010259922],"about_ca_topic_score_codex":0.8929517,"about_ca_topic_score_gemma":0.97197247,"teacher_disagreement_score":0.80068356,"about_ca_system_score_codex":0.000028262604,"about_ca_system_score_gemma":0.00009329062,"threshold_uncertainty_score":0.13204189},"labels":[],"label_agreement":null},{"id":"W7099266526","doi":"","title":"Located in the Oil Sands Region","year":2014,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Oil sands; Land reclamation; Public opinion; Environmental policy; Public policy; Work (physics); Energy policy; Petroleum industry","score_opus":0.026060234295216356,"score_gpt":0.22614019660103996,"score_spread":0.2000799623058236,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7099266526","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031554766,0.000009480859,0.5504519,0.008828129,0.00012254414,0.000026834094,5.12416e-8,0.00013460818,0.4088717],"genre_scores_gemma":[0.9915384,0.000009327029,0.0046622357,0.0027070688,0.00002164684,0.000005039763,3.0560676e-7,0.0000014039922,0.0010545766],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99957323,0.00008261943,0.00006612975,0.00010184911,0.00009334902,0.00008284362],"domain_scores_gemma":[0.99960876,0.00011301267,0.000012939286,0.000233546,0.000015626863,0.000016107633],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027546522,0.0000349235,0.000040641884,0.00004397025,0.000028397906,0.000062158484,0.0003756321,0.000020302943,0.000036383866],"category_scores_gemma":[0.000048149086,0.000020073532,0.000017934193,0.00020981395,0.000009015243,0.00008905917,0.000022847244,0.000038419665,0.00013778027],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.9810186e-7,0.000023987042,0.00045008864,0.0000018361249,9.136072e-7,0.0000044828353,0.00020316495,7.6760693e-7,0.000029657844,0.047481958,0.002853392,0.94894886],"study_design_scores_gemma":[0.0020770177,0.00023416929,0.08123933,0.00011946405,0.000010047398,0.00034986908,0.00086906843,0.5425521,0.025754401,0.040439636,0.30546188,0.000893007],"about_ca_topic_score_codex":0.000034219614,"about_ca_topic_score_gemma":0.000044340453,"teacher_disagreement_score":0.95998365,"about_ca_system_score_codex":0.000004971483,"about_ca_system_score_gemma":0.000006119099,"threshold_uncertainty_score":0.17709327},"labels":[],"label_agreement":null},{"id":"W7110691195","doi":"","title":"Comparing language-specific and cross-language acoustic models for low-resource phonetic forced alignment","year":2025,"lang":"en","type":"article","venue":"ScholarSpace (University of Hawaii at Manoa)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Phone; Acoustic model; Homogeneous; Hidden Markov model; Stress (linguistics)","score_opus":0.0166982691697692,"score_gpt":0.2336168389856255,"score_spread":0.21691856981585628,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7110691195","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6426304,0.00056540634,0.34840855,0.00072663795,0.00009202908,0.00031379025,0.000014055166,0.00011037283,0.0071387463],"genre_scores_gemma":[0.9633616,0.000055744666,0.027119778,0.00012513109,0.000011717871,0.0000016586029,0.000008096826,0.000009679602,0.009306573],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99880564,0.000062566054,0.00011504027,0.00047638596,0.00024207507,0.00029827794],"domain_scores_gemma":[0.99903834,0.00017112117,0.000106839434,0.0004848141,0.000084151485,0.000114763105],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030463375,0.00016280683,0.00028425962,0.0002494443,0.00044854076,0.00014891695,0.0006395107,0.00009554916,0.00005597237],"category_scores_gemma":[0.000022980574,0.00020142412,0.00012319311,0.000277828,0.00013218838,0.0005424288,0.0005523279,0.00012758515,0.000022028522],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017354998,0.0011545337,0.007263174,0.0025892556,0.0011877571,0.00068746216,0.06936905,0.020953914,0.49858534,0.108771764,0.039271083,0.24843118],"study_design_scores_gemma":[0.014426267,0.0003560673,0.024594236,0.0011825784,0.00033087743,0.00007601367,0.07715526,0.77210414,0.08318463,0.0032517703,0.021261541,0.0020766058],"about_ca_topic_score_codex":0.00004179542,"about_ca_topic_score_gemma":0.00013131062,"teacher_disagreement_score":0.75115025,"about_ca_system_score_codex":0.00012739997,"about_ca_system_score_gemma":0.000031324416,"threshold_uncertainty_score":0.8213837},"labels":[],"label_agreement":null},{"id":"W7116439662","doi":"10.18280/ijsse.150907","title":"Hybrid CNN-BiLSTM for Deepfake Voice Detection: A Comparative Study","year":2025,"lang":"","type":"article","venue":"International Journal of Safety and Security Engineering","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Poison control; Human factors and ergonomics; Vulnerability (computing); Occupational safety and health","score_opus":0.016897535934624185,"score_gpt":0.2777137796706393,"score_spread":0.26081624373601514,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7116439662","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13900457,0.001063163,0.85264444,0.0013021904,0.0051395106,0.00038641324,0.000036303198,0.000027537395,0.00039583395],"genre_scores_gemma":[0.9944469,0.0003710351,0.004489504,0.00013944456,0.0004664437,0.000008752453,0.0000014680013,0.000008308436,0.000068171714],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99791884,0.00008275709,0.0009677576,0.00029545787,0.0005076213,0.00022754859],"domain_scores_gemma":[0.99740493,0.0007327527,0.0003676519,0.00014367547,0.0012120303,0.0001389486],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009697599,0.00025140945,0.0004875821,0.00057838106,0.00016514721,0.00037033667,0.00071857433,0.0000730546,0.00002963676],"category_scores_gemma":[0.00033888646,0.00025834702,0.00024836784,0.00022885553,0.000043497614,0.0007013251,0.00017620935,0.00042191223,0.0000034698844],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005006244,0.0036566884,0.0011655972,0.00046316016,0.009153409,0.0007639616,0.029718995,0.01039817,0.0028811558,0.016187154,0.0005679824,0.9200375],"study_design_scores_gemma":[0.0048456048,0.0008036587,0.004320084,0.0007823229,0.00023196539,0.0006732867,0.0017747554,0.940148,0.010628207,0.0028713846,0.032445665,0.00047509596],"about_ca_topic_score_codex":0.000010975674,"about_ca_topic_score_gemma":0.000022781149,"teacher_disagreement_score":0.9297498,"about_ca_system_score_codex":0.00019289892,"about_ca_system_score_gemma":0.00012907927,"threshold_uncertainty_score":0.9999869},"labels":[],"label_agreement":null},{"id":"W7117561788","doi":"10.1109/jiot.2025.3649544","title":"Branch-MFA-TDNN: A Parallel Branch Speaker Verification Model for Voice IoT","year":2025,"lang":"","type":"article","venue":"IEEE Internet of Things Journal","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Carleton University","funders":"China University of Mining and Technology; National Natural Science Foundation of China","keywords":"Focus (optics); Construct (python library); Noise (video); Authentication (law); Identity (music); Voice activity detection; Baseline (sea); Internet of Things","score_opus":0.03953475174061769,"score_gpt":0.29180733490534266,"score_spread":0.25227258316472495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117561788","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0396354,0.0007096199,0.94545287,0.004892423,0.004941654,0.00048350767,0.000016254498,0.000058510876,0.0038097498],"genre_scores_gemma":[0.8580601,0.00033921006,0.12262175,0.0032274078,0.00032993095,0.000029024675,0.000002258629,0.000037365957,0.015352949],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959193,0.00021561916,0.0016928288,0.0007407119,0.00075261644,0.0006789284],"domain_scores_gemma":[0.9962453,0.00045073518,0.0012288037,0.0006495108,0.0011470951,0.00027850707],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0018841209,0.00046818433,0.00074908487,0.0006390202,0.00027824595,0.0009091948,0.002220252,0.00035736855,0.00022627792],"category_scores_gemma":[0.00053523964,0.00046669913,0.00080019305,0.00048341524,0.00020274542,0.001176589,0.00016506697,0.0009130233,0.00010853227],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013358883,0.0011754754,0.00030165268,0.0007188719,0.0011259271,0.00002126237,0.015689135,0.0046268287,0.027274124,0.008371468,0.08228641,0.85707295],"study_design_scores_gemma":[0.0018220939,0.00019067591,0.0002110558,0.0014765629,0.00016285345,0.00024145203,0.000061245,0.92542136,0.032640234,0.03116047,0.0061857733,0.00042622432],"about_ca_topic_score_codex":0.00006557455,"about_ca_topic_score_gemma":0.000017243288,"teacher_disagreement_score":0.92079455,"about_ca_system_score_codex":0.00024091352,"about_ca_system_score_gemma":0.0005567885,"threshold_uncertainty_score":0.99977845},"labels":[],"label_agreement":null},{"id":"W7117562559","doi":"10.18280/ts.420611","title":"Multi-Model Telugu Speech Recognition: Improving ASR with Dialect Classification and Optimization Techniques","year":2025,"lang":"","type":"article","venue":"Traitement du signal","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Telugu; Speech processing; Speech synthesis; Hidden Markov model","score_opus":0.04243502867289677,"score_gpt":0.26085636779599214,"score_spread":0.21842133912309536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117562559","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0066293483,0.0001709024,0.98675483,0.001558713,0.00015628999,0.0013475335,0.00003988353,0.00035570996,0.0029867631],"genre_scores_gemma":[0.27517855,0.00031993783,0.72291946,0.00075868535,0.00011026937,0.00022209655,0.00004623734,0.000028447033,0.00041632104],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968564,0.00024297592,0.00077733863,0.0011051096,0.000525871,0.0004923169],"domain_scores_gemma":[0.99829423,0.00018795903,0.00037324565,0.00041528398,0.0005477052,0.00018154786],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000889688,0.00047430382,0.0004120761,0.00058789167,0.0005655973,0.000824226,0.00045413346,0.00024584346,0.00038650478],"category_scores_gemma":[0.00008201687,0.0004566563,0.00010926369,0.0008965262,0.00022307978,0.0011524233,0.00014901027,0.00030331188,0.000019850724],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013111506,0.00048373005,0.00021970944,0.00015644931,0.00009463545,0.000013677548,0.0003146703,0.0006699004,0.010725461,0.00024935673,0.00023849074,0.9867028],"study_design_scores_gemma":[0.0012720552,0.0003066656,0.00093072164,0.0004828266,0.00018503123,0.00003209527,0.0001398302,0.9467168,0.048915666,0.0002996495,0.00017720158,0.0005414634],"about_ca_topic_score_codex":0.00003641813,"about_ca_topic_score_gemma":0.000034905985,"teacher_disagreement_score":0.98616135,"about_ca_system_score_codex":0.00020678017,"about_ca_system_score_gemma":0.00039744095,"threshold_uncertainty_score":0.9997885},"labels":[],"label_agreement":null},{"id":"W7125949704","doi":"10.1109/smc58881.2025.11343334","title":"Phonetic Analysis of Real and Synthetic Speech Using HuBERT Embeddings: Perspectives for Deepfake Detection","year":2025,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique; Cégep de l'Outaouais","funders":"","keywords":"Speech synthesis; Synthetic data; Sophistication; Speech processing; Rank (graph theory); Divergence (linguistics); Noise (video)","score_opus":0.01738696341447149,"score_gpt":0.2900737172972532,"score_spread":0.2726867538827817,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7125949704","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35627475,0.000065836626,0.6398426,0.00008642569,0.00006071242,0.00012108648,0.0000019768145,0.00005414692,0.0034924136],"genre_scores_gemma":[0.8766727,0.00004728112,0.1229964,0.000037326798,0.000007804215,0.000008529008,4.3858796e-7,0.0000035038952,0.00022602688],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991947,0.0000406875,0.00019570436,0.00032563583,0.0001096947,0.00013356953],"domain_scores_gemma":[0.9992581,0.0002636999,0.00006768203,0.00022194156,0.00015375606,0.00003479521],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023679549,0.00009145964,0.00023514846,0.00065455126,0.000105811516,0.000071667106,0.00015478743,0.000052826068,0.000036910245],"category_scores_gemma":[0.00012537067,0.00008408112,0.00013564606,0.0012255119,0.000050269486,0.00013842504,0.000056868274,0.00003394444,9.376281e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049116625,0.00017764962,0.0011776746,0.00007594396,0.0012455231,0.0000024920414,0.0021831864,0.000116267605,0.084381774,0.0155384,0.00002821378,0.89502376],"study_design_scores_gemma":[0.00022414824,0.00004571121,0.005465728,0.000029916038,0.00057814963,0.000006760073,0.0014324192,0.8155866,0.17404486,0.0023991268,0.000047340156,0.00013923687],"about_ca_topic_score_codex":0.00020248866,"about_ca_topic_score_gemma":0.00019892871,"teacher_disagreement_score":0.8948845,"about_ca_system_score_codex":0.00004750668,"about_ca_system_score_gemma":0.000025614407,"threshold_uncertainty_score":0.34287286},"labels":[],"label_agreement":null},{"id":"W7127860883","doi":"","title":"Robustness of neural models for automatic speech processing","year":2025,"lang":"en","type":"article","venue":"theses.fr (ABES)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Robustness (evolution); Speech processing; Error analysis","score_opus":0.04123261635679393,"score_gpt":0.2872287094734819,"score_spread":0.24599609311668796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7127860883","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.051127084,0.00011973329,0.92049897,0.00063947117,0.0002833482,0.0003880105,0.0000057121356,0.0002777526,0.02665993],"genre_scores_gemma":[0.82448155,0.000005376496,0.17508315,0.00018093131,0.000033512475,0.000051342293,0.0000014202334,0.000010438975,0.00015230673],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998792,0.0000589718,0.00033183463,0.00030658563,0.0002328877,0.00027774193],"domain_scores_gemma":[0.9988891,0.00031623832,0.00012411513,0.00042282138,0.00019327998,0.000054457083],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036612805,0.00015227692,0.0002938751,0.0002001524,0.00011207279,0.00012517805,0.0007829,0.000072072784,0.00003379914],"category_scores_gemma":[0.00014425062,0.00013152206,0.0001188598,0.00048866175,0.00005826327,0.0005124313,0.00013344422,0.00007835083,0.0000068440195],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007430449,0.00010715341,0.000024618836,0.0002787172,0.000024149353,0.0000027238525,0.00047168962,0.0018974578,0.00041989016,0.029363733,0.00013420302,0.9672682],"study_design_scores_gemma":[0.0002940116,0.00002218416,0.0000908331,0.00018978569,0.00002272465,0.000009399383,0.00023954926,0.9691917,0.017353123,0.012225599,0.00022133089,0.0001397683],"about_ca_topic_score_codex":0.000034196877,"about_ca_topic_score_gemma":0.000009680532,"teacher_disagreement_score":0.9672942,"about_ca_system_score_codex":0.000031303516,"about_ca_system_score_gemma":0.00010598459,"threshold_uncertainty_score":0.5363314},"labels":[],"label_agreement":null},{"id":"W7130678234","doi":"10.1109/swc65939.2025.00066","title":"Augmenting Japanese Language Acquisition via LLMs and ASR","year":2025,"lang":"","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Athabasca University","funders":"Alberta Innovates; Natural Sciences and Engineering Research Council of Canada; Athabasca University","keywords":"Active listening; Japanese language; Language acquisition; Kanji","score_opus":0.009253066351147973,"score_gpt":0.25425679137887,"score_spread":0.245003725027722,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7130678234","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34807584,0.0017697923,0.3946008,0.00468781,0.0014910364,0.00044973195,0.0000060566313,0.00033412097,0.2485848],"genre_scores_gemma":[0.96164364,0.00008521104,0.016306765,0.0027831213,0.00008089414,0.0000115144685,0.0000030914014,0.000007452359,0.019078303],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99839044,0.00013160484,0.0003386616,0.0005565141,0.00023410829,0.00034869587],"domain_scores_gemma":[0.9991115,0.00020113622,0.00008439134,0.00039550802,0.00008925555,0.0001182219],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00047836718,0.00020374062,0.00022642678,0.00025464583,0.00028674433,0.00057269266,0.00032739365,0.0001227719,0.0021136736],"category_scores_gemma":[0.00006598836,0.00019579033,0.000088812354,0.0005641902,0.00007878795,0.00048663784,0.0003583862,0.00012589872,0.00030888914],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009100319,0.000096248004,0.00026498755,0.000074503594,0.000052023068,0.000034574397,0.0024470259,4.6483729e-7,0.009392512,0.0025610891,0.0008053954,0.98426205],"study_design_scores_gemma":[0.0031509467,0.00025500086,0.026199594,0.0011841992,0.00029732453,0.00023003135,0.012191021,0.7186928,0.22530094,0.006407023,0.004332989,0.0017581637],"about_ca_topic_score_codex":0.00019033671,"about_ca_topic_score_gemma":0.000031658616,"teacher_disagreement_score":0.9825039,"about_ca_system_score_codex":0.00004128783,"about_ca_system_score_gemma":0.000045957233,"threshold_uncertainty_score":0.99879855},"labels":[],"label_agreement":null},{"id":"W7132590463","doi":"","title":"Supporting SENĆOŦEN language documentation efforts with Automatic Speech Recognition","year":2025,"lang":"en","type":"article","venue":"NPARC","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Pipeline (software); Documentation; Vocabulary; Word error rate; Speech technology; Language model; Set (abstract data type); Variation (astronomy)","score_opus":0.010882510643594174,"score_gpt":0.2816661806138079,"score_spread":0.2707836699702137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7132590463","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.665457,0.000011938634,0.16370277,0.0013909631,0.0002380062,0.00037374318,0.000003976586,0.0005922283,0.16822937],"genre_scores_gemma":[0.60064214,0.000003251238,0.39685225,0.00080492464,0.00002863993,0.00004090103,0.000019999301,0.000007446463,0.0016004286],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990608,0.000056423345,0.00020866652,0.00024856074,0.00021491722,0.00021061343],"domain_scores_gemma":[0.9994456,0.000105753286,0.000095924115,0.00024147908,0.00006332224,0.000047906888],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00029334295,0.00009947863,0.0001189971,0.00016460776,0.00009644271,0.00018992405,0.00019983848,0.00003931245,0.0009168769],"category_scores_gemma":[0.00006806835,0.000085103224,0.000037882368,0.00040012685,0.000019396937,0.00049964635,0.00004836417,0.0000727282,0.00022197345],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000033508186,0.000028275015,0.00019413946,0.000030142975,0.000017682372,0.000046597943,0.00033263644,3.277475e-7,0.0064992374,0.00055746146,0.0012035191,0.9910866],"study_design_scores_gemma":[0.0018320677,0.00019090709,0.004561748,0.000649671,0.000105348496,0.00024509773,0.0014487776,0.08871977,0.8217565,0.07695023,0.002783568,0.0007563543],"about_ca_topic_score_codex":0.00001921653,"about_ca_topic_score_gemma":0.00001561462,"teacher_disagreement_score":0.9903303,"about_ca_system_score_codex":0.00004514548,"about_ca_system_score_gemma":0.00005750517,"threshold_uncertainty_score":0.9999964},"labels":[],"label_agreement":null},{"id":"W7132892771","doi":"","title":"Robustesse des modèles neuronaux pour le traitement automatique de la parole","year":2025,"lang":"en","type":"dissertation","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Robustness (evolution); Training set; Focus (optics); Variation (astronomy); Speech processing; Speech technology; Stress (linguistics)","score_opus":0.015796261104006698,"score_gpt":0.23986411379419034,"score_spread":0.22406785269018364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7132892771","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12943314,0.0010031387,0.60140246,0.003308813,0.0002553687,0.0005081869,0.000036471276,0.0008025028,0.2632499],"genre_scores_gemma":[0.37816486,0.0008656967,0.5331639,0.0003677444,0.000031263327,0.00027683712,0.00061922084,0.00008230958,0.08642818],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99188197,0.005860436,0.00057499093,0.0007963195,0.00043501396,0.00045127203],"domain_scores_gemma":[0.99396265,0.002624337,0.00041793293,0.001442298,0.0013429525,0.00020984255],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0037777682,0.0004020819,0.00040664457,0.00037888723,0.0005625858,0.0008622086,0.0019808589,0.00035973065,0.00011666054],"category_scores_gemma":[0.0016839906,0.00044338495,0.00027163408,0.00065139757,0.000121869234,0.00036896867,0.00025198658,0.0004721258,0.000047785696],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001676231,0.0012981967,0.00019096432,0.00047093476,0.00014594728,0.000027550865,0.019161604,0.00013857968,0.009341884,0.24530987,0.0033352782,0.7205624],"study_design_scores_gemma":[0.0016805803,0.0000020787586,0.024878507,0.0054483064,0.00014552117,0.00006421918,0.0026334187,0.38701135,0.51519465,0.042166874,0.019186044,0.0015884605],"about_ca_topic_score_codex":0.0011038358,"about_ca_topic_score_gemma":0.0028906914,"teacher_disagreement_score":0.718974,"about_ca_system_score_codex":0.00015529421,"about_ca_system_score_gemma":0.0012758281,"threshold_uncertainty_score":0.9998018},"labels":[],"label_agreement":null},{"id":"W7133044638","doi":"","title":"Scale in Acoustic Modelling","year":2023,"lang":"","type":"dissertation","venue":"TSpace","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Hidden Markov model; Representation (politics); Pipeline (software); Feature (linguistics); Computation; Event (particle physics); ENCODE; Scale (ratio); Acoustic model; Phone","score_opus":0.06277386535438166,"score_gpt":0.3385953024865143,"score_spread":0.27582143713213264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7133044638","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48293385,0.00035731206,0.48407218,0.0009980943,0.0053504347,0.0008688953,0.000007807073,0.0006007684,0.024810646],"genre_scores_gemma":[0.69191355,0.0020630425,0.053782016,0.00029483918,0.00045720162,0.00022429237,0.00018347565,0.00022685714,0.25085476],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99694514,0.00015437597,0.0005755074,0.0010022806,0.00064784114,0.0006748307],"domain_scores_gemma":[0.99835145,0.00037847905,0.0002530093,0.00063374575,0.00018851686,0.00019477391],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00057837693,0.00044083,0.0005602379,0.0007806074,0.00018643458,0.00033791648,0.00088540884,0.00045788952,0.00049580826],"category_scores_gemma":[0.00012663392,0.0004387422,0.0002120046,0.0016525559,0.000038967708,0.0002451284,0.00010274114,0.0006049103,0.004048813],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011754052,0.00047662086,0.00024192799,0.0007770637,0.00009769463,0.0003824627,0.14170115,0.09216992,0.0032651823,0.00025471943,0.001445555,0.75907016],"study_design_scores_gemma":[0.00030871242,0.000037761773,0.0008080169,0.00091686286,0.00004007686,0.000007739219,0.011674197,0.97993845,0.004242023,0.0011198452,0.0002751034,0.00063119293],"about_ca_topic_score_codex":0.00093811855,"about_ca_topic_score_gemma":0.0017867968,"teacher_disagreement_score":0.88776857,"about_ca_system_score_codex":0.00014246054,"about_ca_system_score_gemma":0.00029777712,"threshold_uncertainty_score":0.99980646},"labels":[],"label_agreement":null},{"id":"W7133331044","doi":"10.1109/ijcb65343.2025.11410671","title":"Text-Independent Speaker Verification Employing A Novel Hybrid Neural Embedding Extractor","year":2025,"lang":"","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Discriminative model; Robustness (evolution); Pattern recognition (psychology); Convolutional neural network; Embedding; Artificial neural network; Feature extraction; Feature (linguistics); Softmax function; Pooling","score_opus":0.03752871438985219,"score_gpt":0.29739213717069957,"score_spread":0.2598634227808474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7133331044","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09931035,0.00018922969,0.86142373,0.002228094,0.0032708412,0.000572679,0.000016932681,0.000354659,0.032633487],"genre_scores_gemma":[0.94013363,0.00006035971,0.051535413,0.0014810886,0.00013674822,0.00003984465,0.000007355672,0.000027612876,0.006577963],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959661,0.00020296554,0.0009613808,0.0013504634,0.00072926417,0.00078987307],"domain_scores_gemma":[0.99747914,0.0005275548,0.00027226008,0.0011192127,0.00033191298,0.00026990403],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00096112245,0.0004868127,0.0004723451,0.00057008455,0.00052653503,0.0014679352,0.0012439541,0.00017201719,0.0020606958],"category_scores_gemma":[0.00039481162,0.0004948141,0.00034842448,0.00093931804,0.0000995389,0.0012787757,0.00043691715,0.00048055203,0.0008162013],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000069152964,0.00078761653,0.0011655099,0.00012636343,0.00016627707,0.00005260791,0.0003581037,0.00014412182,0.03988843,0.016257802,0.0019439885,0.93904],"study_design_scores_gemma":[0.0011074453,0.00005635264,0.020964576,0.00035121225,0.00009100202,0.00014061315,0.0002909053,0.9088409,0.05757743,0.0006110435,0.009220326,0.00074819697],"about_ca_topic_score_codex":0.00011256498,"about_ca_topic_score_gemma":0.00002512808,"teacher_disagreement_score":0.93829185,"about_ca_system_score_codex":0.00027058576,"about_ca_system_score_gemma":0.0003255655,"threshold_uncertainty_score":0.9999618},"labels":[],"label_agreement":null},{"id":"W7148307382","doi":"10.1109/asru65441.2025.11434672","title":"Maestro-EVC: Controllable Emotional Voice Conversion Guided by References and Explicit Prosody","year":2025,"lang":"","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Research Foundation","keywords":"Prosody; Representation (politics); Identity (music); Emotional prosody; Style (visual arts); Dynamics (music)","score_opus":0.02420264739188317,"score_gpt":0.26149773320609704,"score_spread":0.23729508581421388,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7148307382","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20747639,0.003934597,0.3131786,0.05976866,0.003981939,0.0025614297,0.00018141721,0.0006478281,0.40826914],"genre_scores_gemma":[0.8442907,0.001059488,0.021549875,0.0065511013,0.00010902807,0.000068109686,0.000026816444,0.00001613586,0.12632877],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969595,0.00025660463,0.0006609926,0.0010454037,0.000539444,0.0005380653],"domain_scores_gemma":[0.99810934,0.00047609827,0.00019561022,0.0005001984,0.0004681261,0.00025063977],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006276478,0.00037337551,0.0005041001,0.0002537305,0.00052935275,0.00080214674,0.00068541884,0.00023975217,0.0023643735],"category_scores_gemma":[0.00024470806,0.00033715361,0.000117097516,0.00068609713,0.00018013238,0.000768859,0.00039378193,0.00022103246,0.00047181264],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020627974,0.0007535628,0.007805071,0.00030646325,0.00035958315,0.00002371091,0.00034374758,0.000002947846,0.016558088,0.06783557,0.557828,0.34797695],"study_design_scores_gemma":[0.012768253,0.00095147645,0.011686219,0.0014243998,0.00035580565,0.00011510246,0.0018331584,0.36556274,0.20180403,0.016597996,0.38448578,0.0024150463],"about_ca_topic_score_codex":0.00022045054,"about_ca_topic_score_gemma":0.000016587806,"teacher_disagreement_score":0.6368143,"about_ca_system_score_codex":0.00008236766,"about_ca_system_score_gemma":0.00032980443,"threshold_uncertainty_score":0.99990803},"labels":[],"label_agreement":null},{"id":"W7148418289","doi":"10.1109/asru65441.2025.11434627","title":"Low-Resource Domain Adaptation for Speech LLMs via Text-Only Fine-Tuning","year":2025,"lang":"","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Optech (Canada)","funders":"","keywords":"Adaptation (eye); Domain (mathematical analysis); Generalization; Domain adaptation; Encoder; Mechanism (biology); Degradation (telecommunications)","score_opus":0.02317349662740988,"score_gpt":0.2601340969287989,"score_spread":0.23696060030138902,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7148418289","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00601823,0.00017147059,0.916426,0.005966059,0.001043303,0.0009793171,0.00001644695,0.0002667022,0.06911248],"genre_scores_gemma":[0.2452197,0.000031859185,0.6949939,0.0052048275,0.0003690841,0.00012530632,0.000032035405,0.000049796734,0.053973492],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99639684,0.0002484,0.00090265315,0.0011189023,0.00052996725,0.0008032151],"domain_scores_gemma":[0.99701136,0.0012537728,0.00026363818,0.0008437685,0.0003916482,0.00023579386],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011868487,0.00046679695,0.0005149624,0.0006010969,0.0006652804,0.0007477919,0.001151126,0.00030189357,0.000998765],"category_scores_gemma":[0.00040201124,0.00047180097,0.0004121588,0.0013966041,0.00013418592,0.00058657845,0.0003206559,0.0002720952,0.0004400703],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007109751,0.00022280074,0.000057489146,0.00011103017,0.0000876017,0.000015280917,0.0006480032,0.00006737757,0.0024012597,0.021374138,0.0053512864,0.96959263],"study_design_scores_gemma":[0.0019412978,0.00023191865,0.0004919983,0.0005104976,0.00009213994,0.000051650706,0.0011661357,0.8318667,0.05017357,0.022620795,0.09004719,0.0008061393],"about_ca_topic_score_codex":0.00006684341,"about_ca_topic_score_gemma":0.00028143259,"teacher_disagreement_score":0.9687865,"about_ca_system_score_codex":0.00015829707,"about_ca_system_score_gemma":0.00048010648,"threshold_uncertainty_score":0.99991447},"labels":[],"label_agreement":null},{"id":"W7148467367","doi":"10.1109/asru65441.2025.11434705","title":"Multi-Target Backdoor Attacks Against Speaker Recognition","year":2025,"lang":"","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Backdoor; Speaker recognition; Speaker identification; Task (project management); Speaker diarisation; Speaker verification; Identification (biology)","score_opus":0.04730060825118691,"score_gpt":0.2875064403786451,"score_spread":0.24020583212745816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7148467367","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006570468,0.0005148614,0.6752441,0.0053075,0.004284791,0.00075709756,0.00005825313,0.00045643534,0.3068065],"genre_scores_gemma":[0.11691674,0.0010574596,0.7741937,0.021063242,0.00035727967,0.00009161216,0.00007905642,0.000052178944,0.086188704],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99572843,0.00040616453,0.0010340653,0.0014131475,0.0005113984,0.0009068191],"domain_scores_gemma":[0.99732566,0.00038702475,0.00023239965,0.0010877708,0.0006205786,0.0003465851],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00086794794,0.00058213115,0.00059686124,0.0006493709,0.00048275775,0.00089576305,0.0011468992,0.00041632424,0.009448995],"category_scores_gemma":[0.0004861538,0.0005790405,0.0004739625,0.0016510409,0.00019631747,0.0009925686,0.00050538953,0.00047727354,0.012769672],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028465072,0.00067767774,0.000428169,0.00008160765,0.00015583393,0.00005631871,0.00021003559,0.0000051171655,0.0012209847,0.00031197176,0.024916766,0.9719071],"study_design_scores_gemma":[0.0043482613,0.00016053402,0.008535031,0.0011673493,0.00016656128,0.000033074968,0.00067914743,0.6432481,0.132348,0.0040890737,0.20313686,0.002088046],"about_ca_topic_score_codex":0.000042038428,"about_ca_topic_score_gemma":0.00006989483,"teacher_disagreement_score":0.969819,"about_ca_system_score_codex":0.000185441,"about_ca_system_score_gemma":0.0004096963,"threshold_uncertainty_score":0.9996661},"labels":[],"label_agreement":null},{"id":"W7150799232","doi":"10.70675/0f82ff96z8b2cz4523z9426zd8215c37a473","title":"Reconnaissance automatique de la parole à large vocabulaire : des approches hybrides aux approches End-to-End","year":2021,"lang":"","type":"dissertation","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"History of sociology; Lexicography; Digital humanities","score_opus":0.024617067766640684,"score_gpt":0.2906459060132357,"score_spread":0.266028838246595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7150799232","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3587041,0.0030945744,0.5171666,0.0010228342,0.0011765504,0.0014723676,0.00010724533,0.0012878296,0.11596787],"genre_scores_gemma":[0.688921,0.00085175957,0.28222662,0.0015566205,0.00034378126,0.00090805715,0.0003672785,0.0001639204,0.024660984],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99143994,0.0014086945,0.0015880227,0.0026424325,0.001112656,0.0018082529],"domain_scores_gemma":[0.9937061,0.0020207723,0.000693698,0.0014933513,0.0010855938,0.001000499],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.0028812415,0.001403926,0.001532566,0.00074507686,0.0014669225,0.0023758535,0.0023378164,0.0010850974,0.004237987],"category_scores_gemma":[0.0027460607,0.0014670169,0.00082165236,0.0017900303,0.00056889956,0.0011782824,0.00043359865,0.0010841328,0.0006143297],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000101214,0.0012361197,0.0011262615,0.0017729073,0.000524704,0.00037396787,0.03408624,0.000025880134,0.005044569,0.018527815,0.004234143,0.9329462],"study_design_scores_gemma":[0.0016128697,0.00040077238,0.044632237,0.005904099,0.00045157346,0.001027246,0.042664003,0.10455266,0.72749597,0.026655696,0.039280932,0.0053219623],"about_ca_topic_score_codex":0.0003452854,"about_ca_topic_score_gemma":0.001472774,"teacher_disagreement_score":0.9276242,"about_ca_system_score_codex":0.00035504543,"about_ca_system_score_gemma":0.0028419225,"threshold_uncertainty_score":0.9998711},"labels":[],"label_agreement":null},{"id":"W7152567113","doi":"10.70675/cd07449cz121az45b9zaa1bz82f77086939d","title":"Robustness of neural models for automatic speech processing","year":2025,"lang":"","type":"dissertation","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Robustness (evolution); Speech processing; Deep neural networks","score_opus":0.05468512467044811,"score_gpt":0.30275509348258994,"score_spread":0.24806996881214183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7152567113","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013988014,0.0002829869,0.9666922,0.00030355665,0.0017424633,0.0015274475,0.00002757508,0.00020905085,0.015226672],"genre_scores_gemma":[0.15029874,0.00005194283,0.8244355,0.00023507595,0.00014385648,0.0003625962,0.00019986375,0.000054462413,0.02421799],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99634165,0.00010827475,0.0013773221,0.0009770134,0.0006604212,0.0005352949],"domain_scores_gemma":[0.9962779,0.00054366235,0.00084509776,0.0006144213,0.001584973,0.00013388817],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005197222,0.0005647553,0.0010138882,0.00071889436,0.0003206898,0.00043453983,0.0013803964,0.000468389,0.0002881517],"category_scores_gemma":[0.0002489281,0.00054369407,0.00052425254,0.0010815533,0.00005291887,0.0010244364,0.00009986399,0.00023545488,0.0000046650357],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003463836,0.00020361411,0.0000012246388,0.004367579,0.00006128722,0.0000022924396,0.00050796533,0.0067777713,0.000100576166,0.0020283223,0.00021730993,0.98569745],"study_design_scores_gemma":[0.00050716527,0.00008264579,0.00003591049,0.0016855712,0.00019534517,0.000010933349,0.0008723062,0.9758976,0.016814003,0.0033622081,0.000018193268,0.0005181279],"about_ca_topic_score_codex":0.000034642984,"about_ca_topic_score_gemma":0.00007673718,"teacher_disagreement_score":0.9851793,"about_ca_system_score_codex":0.00006512326,"about_ca_system_score_gemma":0.001050929,"threshold_uncertainty_score":0.99970144},"labels":[],"label_agreement":null},{"id":"W7154460112","doi":"10.1109/smartagrisusy68475.2025.11466843","title":"Toward Lightweight IoC Extraction in IoT: The Role of Small Language Models","year":2025,"lang":"","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique; Université du Québec en Outaouais","funders":"","keywords":"Information extraction; Extraction (chemistry); Matching (statistics); Key (lock)","score_opus":0.028787555935481192,"score_gpt":0.2586371234694949,"score_spread":0.22984956753401373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7154460112","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.066535264,0.004807923,0.45195127,0.0064168926,0.00089683005,0.0005866803,0.000007642068,0.00009737887,0.46870014],"genre_scores_gemma":[0.97636676,0.00033419533,0.016607167,0.00063838,0.000048286445,0.000023761784,8.2862834e-7,0.0000075779203,0.005973044],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99819255,0.00022625888,0.0005619517,0.00044095804,0.00026589268,0.0003123993],"domain_scores_gemma":[0.99867094,0.00038199703,0.00014372161,0.0006230503,0.00012132013,0.00005898381],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006073262,0.00019810308,0.00028796043,0.00035017682,0.00008996793,0.00015372835,0.0008726149,0.00016437775,0.00064257736],"category_scores_gemma":[0.000074531185,0.00014136208,0.0001733714,0.00096995913,0.00007506318,0.0002632525,0.00022539978,0.00026363408,0.000079188605],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023025355,0.0002627731,0.00011054101,0.00003250823,0.000035943052,0.00001214356,0.003913454,0.00013726474,0.003947475,0.07747892,0.00013404392,0.9139119],"study_design_scores_gemma":[0.00031847841,0.00003306739,0.0007602467,0.00020603107,0.000026774216,0.0000085587535,0.002737322,0.697682,0.26490337,0.030403163,0.002731331,0.00018961202],"about_ca_topic_score_codex":0.00071685197,"about_ca_topic_score_gemma":0.00046436643,"teacher_disagreement_score":0.9137223,"about_ca_system_score_codex":0.000067382774,"about_ca_system_score_gemma":0.00018128815,"threshold_uncertainty_score":0.7035771},"labels":[],"label_agreement":null},{"id":"W7160921222","doi":"10.1121/10.0041466","title":"A Praat script for unsupervised phoneme segmentation based on spectro-temporal representation","year":2025,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"TIMIT; Segmentation; Representation (politics); Spectrogram; Set (abstract data type); Measure (data warehouse); Software; Boundary (topology); Data set","score_opus":0.022547207252939523,"score_gpt":0.2854492572117903,"score_spread":0.2629020499588508,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7160921222","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028322556,0.000031490104,0.97365475,0.022653444,0.00030054018,0.00024356855,0.0000043300306,0.000013870123,0.000265759],"genre_scores_gemma":[0.34444603,0.00006188092,0.64608365,0.009124116,0.00009927084,0.0000073051633,0.0000011669729,0.0000075834437,0.00016900642],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987657,0.00019857418,0.0003642511,0.00010638975,0.00041941012,0.00014567711],"domain_scores_gemma":[0.9981047,0.0009672332,0.00035022144,0.00031172915,0.00022510052,0.000040998],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006249677,0.00009359535,0.00020162064,0.00003824935,0.00018084407,0.000042478798,0.00070276717,0.000037960785,0.00002956501],"category_scores_gemma":[0.00032883103,0.000052037707,0.00038913853,0.0004586172,0.00016107869,0.00012629524,0.00006626738,0.00016628826,0.0000022253112],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013437129,0.0012116511,0.0006833595,0.00020497583,0.0006229713,0.0000022565798,0.0026057453,0.014452369,0.20359279,0.00039939454,0.28483242,0.49004835],"study_design_scores_gemma":[0.0009715883,0.00029061182,0.0008676637,0.000099175144,0.000133942,0.0000061323753,0.0010796788,0.9416779,0.05007964,0.00371898,0.0009975919,0.000077065735],"about_ca_topic_score_codex":0.000021181988,"about_ca_topic_score_gemma":4.176833e-7,"teacher_disagreement_score":0.9272256,"about_ca_system_score_codex":0.000082084225,"about_ca_system_score_gemma":0.00013819363,"threshold_uncertainty_score":0.2122036},"labels":[],"label_agreement":null}]}