{"meta":{"query_hash":"0c76d1bcefc8","filters":{"venue":"Computer Speech & Language"},"cohort_total":21,"direct_labels_cover":0,"predictions_cover":21,"exported":21,"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/0c76d1bcefc8","api":"https://metacan.xera.ac/api/v1/cohort?venue=Computer+Speech+%26+Language"},"results":[{"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":"W1995193848","doi":"10.1016/j.csl.2012.11.001","title":"Adjusting dysarthric speech signals to be more intelligible","year":2012,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Phonetics and Phonology Research","field":"Psychology","cited_by":54,"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; Speech recognition; Artificial intelligence","score_opus":0.053916686106043304,"score_gpt":0.3787507243040557,"score_spread":0.3248340381980124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1995193848","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":[0.96971023,0.00237452,0.008033556,0.0013061877,0.0018892355,0.00041540805,0.000024562407,0.00020161297,0.016044691],"genre_scores_gemma":[0.967781,0.000011116324,0.019188369,0.0048590214,0.0020744489,0.00003606514,0.000034475197,0.00006557187,0.005949917],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977192,0.00016252552,0.00031072408,0.00044108002,0.00028624604,0.0010802058],"domain_scores_gemma":[0.9984766,0.00019733363,0.000067680005,0.00075579836,0.00007855374,0.00042403073],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0006265371,0.00025373444,0.00032921557,0.00029836255,0.00010357245,0.00006640716,0.0006279722,0.00019132574,0.0046152202],"category_scores_gemma":[0.000043372092,0.00023801296,0.00010410424,0.00052769046,0.00007747146,0.00009516943,0.0004752721,0.00047985598,0.00366124],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009468981,0.00061266293,0.0072291386,0.000045197026,0.0002080998,0.0008269085,0.098835535,0.000033355664,0.019150162,0.000614101,0.15866163,0.7136885],"study_design_scores_gemma":[0.005139169,0.002746394,0.32444564,0.00029986302,0.00022653046,0.0037279236,0.016464135,0.0032998894,0.25999048,0.0007596874,0.37850127,0.004399025],"about_ca_topic_score_codex":0.00032577876,"about_ca_topic_score_gemma":0.00003831826,"teacher_disagreement_score":0.7092895,"about_ca_system_score_codex":0.000044311844,"about_ca_system_score_gemma":0.000025677524,"threshold_uncertainty_score":0.99711454},"labels":[],"label_agreement":null},{"id":"W2036126214","doi":"10.1016/j.csl.2014.10.007","title":"Hybrid Arabic–French machine translation using syntactic re-ordering and morphological pre-processing","year":2014,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Machine translation; Natural language processing; Artificial intelligence; Example-based machine translation; Arabic; BLEU; Translation (biology); Verb; Linguistics","score_opus":0.016871099164201,"score_gpt":0.2750535633622381,"score_spread":0.2581824641980371,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2036126214","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18061498,0.0060551134,0.81174743,0.00024377761,0.00016524928,0.00016575768,0.0000017398265,0.0008455167,0.00016043353],"genre_scores_gemma":[0.5090957,0.000005068855,0.49045914,0.00026440067,0.00014042936,0.0000030605015,0.0000047141584,0.0000148818635,0.000012571504],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980354,0.00014303927,0.0003391952,0.0007255944,0.00033209857,0.00042472882],"domain_scores_gemma":[0.9989392,0.000112544185,0.00017629878,0.00056963955,0.00007018753,0.0001321147],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005147009,0.00030794396,0.00033373805,0.00019887791,0.00022481667,0.0005311564,0.0008239946,0.000112728034,0.00001770964],"category_scores_gemma":[0.00005503136,0.00026561876,0.00006712072,0.00029848822,0.000061706654,0.00090168713,0.00041251798,0.00040467625,0.0000044667704],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000052727987,0.000036549245,0.00017093666,0.000094736184,0.0000085916045,0.00022737998,0.0012177755,0.00004919031,0.009283161,0.0003678826,0.00003232297,0.9885062],"study_design_scores_gemma":[0.00032560472,0.000109519824,0.0005721144,0.00014917088,0.000019133679,0.0010535169,0.000009047619,0.9682175,0.025745442,0.00314574,0.00021595396,0.00043724434],"about_ca_topic_score_codex":0.00016950167,"about_ca_topic_score_gemma":0.000015461419,"teacher_disagreement_score":0.98806894,"about_ca_system_score_codex":0.00005536317,"about_ca_system_score_gemma":0.000029594366,"threshold_uncertainty_score":0.9999796},"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":"W2059790057","doi":"10.1016/j.csl.2014.11.003","title":"Native and non-native class discrimination using speech rhythm- and auditory-based cues","year":2014,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":9,"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 du Québec à Trois-Rivières; University of New Brunswick; Université de Moncton","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Speech recognition; Support vector machine; Metric (unit); Mixture model; Rhythm; Context (archaeology); Artificial intelligence; Pattern recognition (psychology)","score_opus":0.011635727441856787,"score_gpt":0.261708059154234,"score_spread":0.2500723317123772,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2059790057","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39059535,0.00018561298,0.60740787,0.00043880765,0.00043731477,0.00014769791,0.0000031319873,0.00013504813,0.00064915966],"genre_scores_gemma":[0.6436732,0.0000048066745,0.3549331,0.000651226,0.00063966203,0.0000042235047,0.0000060915227,0.000018655783,0.00006906807],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981607,0.0001252689,0.00025593647,0.00069398264,0.00037292493,0.00039114806],"domain_scores_gemma":[0.99888724,0.00018413384,0.00020154881,0.0004000122,0.00015989564,0.00016717172],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00041417408,0.00030169004,0.00032760517,0.00024632405,0.00027462665,0.0005184963,0.00041941652,0.000089716195,0.0000074721515],"category_scores_gemma":[0.000062596846,0.00027350636,0.00005336162,0.0003358606,0.00015619023,0.0008038821,0.00039620418,0.0002352196,0.000007823315],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013678801,0.000091375055,0.00088896556,0.00016443849,0.00003984396,0.00020990058,0.0076029976,0.00013848224,0.011344762,0.0008091671,0.0006942608,0.97800213],"study_design_scores_gemma":[0.001418752,0.0002466187,0.00990494,0.00029366463,0.00003289021,0.00022540132,0.00031513907,0.76126784,0.22270228,0.0017149327,0.0011269993,0.00075057324],"about_ca_topic_score_codex":0.000042483047,"about_ca_topic_score_gemma":0.000042701857,"teacher_disagreement_score":0.9772515,"about_ca_system_score_codex":0.000075603,"about_ca_system_score_gemma":0.000069601716,"threshold_uncertainty_score":0.9999717},"labels":[],"label_agreement":null},{"id":"W2083400649","doi":"10.1016/j.csl.2013.04.009","title":"Prior and contextual emotion of words in sentential context","year":2013,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Sentence; Context (archaeology); Natural language processing; Set (abstract data type); Word (group theory); Feature (linguistics); Focus (optics); Task (project management); Similarity (geometry); Artificial intelligence; Contrast (vision); Affect (linguistics); Function (biology); Linguistics; Image (mathematics)","score_opus":0.009483769740171108,"score_gpt":0.23875473576759712,"score_spread":0.22927096602742603,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2083400649","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":[0.8059755,0.0003142653,0.1927957,0.00025268336,0.00025090776,0.00014741959,6.5012586e-7,0.000035979432,0.00022687238],"genre_scores_gemma":[0.9664608,0.000008008082,0.033035077,0.00021782464,0.00010503688,0.0000034753587,0.0000046481478,0.0000054361903,0.00015968393],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989655,0.000062353465,0.00030205102,0.00029031525,0.00019011338,0.00018969446],"domain_scores_gemma":[0.9994333,0.00004577509,0.000113394286,0.0002896129,0.00005595769,0.00006197512],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017945466,0.000116026655,0.00023779257,0.00018660219,0.000030794763,0.00013704288,0.00033745164,0.000045377074,0.00012708668],"category_scores_gemma":[0.000009128166,0.00010403918,0.00006530175,0.0002504925,0.000040170486,0.00037026496,0.0002753769,0.00008794886,0.00003907894],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000031116952,0.00007702397,0.0066916356,0.000014612061,0.000029347115,0.000027239214,0.006885943,0.000013873983,0.0022696408,0.0018446825,0.00072440546,0.9814185],"study_design_scores_gemma":[0.0028744098,0.00024766166,0.18476659,0.00018790152,0.000020672056,0.000059487345,0.003288285,0.79594463,0.011161333,0.00028534044,0.00063758926,0.00052611635],"about_ca_topic_score_codex":0.0003349809,"about_ca_topic_score_gemma":0.000047167792,"teacher_disagreement_score":0.98089236,"about_ca_system_score_codex":0.000014608617,"about_ca_system_score_gemma":0.000013395286,"threshold_uncertainty_score":0.42425948},"labels":[],"label_agreement":null},{"id":"W2114705006","doi":"10.1016/j.csl.2009.02.004","title":"Syllabification rules versus data-driven methods in a language with low syllabic complexity: The case of Italian","year":2009,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Phonetics and Phonology Research","field":"Psychology","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University; National Research Council Canada; National Research Council Institute for Biodiagnostics","funders":"Natural Sciences and Engineering Research Council of Canada; Killam Trusts","keywords":"Syllabification; Syllabic verse; Computer science; Syllable; Natural language processing; Artificial intelligence; Lexicon; Parsing; Machine translation; Speech recognition","score_opus":0.08642458988048203,"score_gpt":0.441595487778507,"score_spread":0.355170897898025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2114705006","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":[0.98733085,0.0010385313,0.0071433634,0.00084786204,0.00037100504,0.0004246289,0.000112724134,0.000057028385,0.0026740055],"genre_scores_gemma":[0.9257321,0.0000072470198,0.07345168,0.0002003632,0.00018470662,0.000010989915,0.00019677138,0.000020419979,0.00019574948],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9981539,0.000579706,0.00029232478,0.00046411686,0.00013697021,0.00037297633],"domain_scores_gemma":[0.99773157,0.00032613985,0.00012450005,0.001684714,0.00005721438,0.00007583893],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007122052,0.00017977972,0.00030677405,0.00017271827,0.000067459514,0.000045915906,0.0009433132,0.00011135239,0.00035114874],"category_scores_gemma":[0.0000322059,0.00012791238,0.000041346524,0.00040740133,0.00024530254,0.000069869995,0.00022070478,0.0003663325,0.00007666605],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007625508,0.0007642974,0.00057562353,0.000060188457,0.00027972512,0.011043752,0.069748975,0.00005360325,0.006581152,0.0044936775,0.0038597917,0.9017767],"study_design_scores_gemma":[0.0355254,0.009805937,0.69465977,0.00065680896,0.00057890784,0.020069877,0.06976508,0.13152471,0.02069816,0.0053952103,0.007219787,0.0041003423],"about_ca_topic_score_codex":0.0015690308,"about_ca_topic_score_gemma":0.001997575,"teacher_disagreement_score":0.89767635,"about_ca_system_score_codex":0.00003406567,"about_ca_system_score_gemma":0.00004175731,"threshold_uncertainty_score":0.5216116},"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":"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":"W2597891111","doi":"10.1016/j.csl.2017.01.014","title":"On integrating a language model into neural machine translation","year":2017,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":113,"is_retracted":false,"has_abstract":false,"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":"Machine translation; Computer science; Artificial intelligence; Phrase; Natural language processing; Translation (biology); BLEU; Language model; Baseline (sea); Example-based machine translation; Turkish; Machine learning; Linguistics","score_opus":0.016226769020705842,"score_gpt":0.3056925943937503,"score_spread":0.28946582537304444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2597891111","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032977667,0.0025114024,0.9596383,0.0013677314,0.00037234774,0.00026574545,0.0000067734873,0.001197676,0.0016623598],"genre_scores_gemma":[0.5062477,0.00000200406,0.49281457,0.0006334964,0.00014815023,0.000007986948,0.000010765479,0.000019896941,0.000115435236],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99811584,0.00007171216,0.00030774274,0.000672801,0.00042547545,0.00040642032],"domain_scores_gemma":[0.9976716,0.00007851947,0.00026507294,0.0017847047,0.0000710696,0.0001290162],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003467765,0.00034383216,0.0003028657,0.0002001906,0.0005193943,0.0010879252,0.0028666551,0.00013803742,0.000017316723],"category_scores_gemma":[0.000095826916,0.00028445953,0.00014081792,0.00014364877,0.000075863216,0.0011177397,0.00060953747,0.0005497884,0.00003158267],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011720256,0.000049939572,0.00002480923,0.000029263394,0.000013511451,0.00031240666,0.008423117,0.00013857256,0.0054584723,0.009693504,0.00034257848,0.97550213],"study_design_scores_gemma":[0.00038014958,0.000108789405,0.000054690205,0.00009052255,0.000008830203,0.00005263875,0.00003255042,0.9754,0.01612655,0.007355284,0.000030776246,0.00035926758],"about_ca_topic_score_codex":0.00034202417,"about_ca_topic_score_gemma":0.00017824148,"teacher_disagreement_score":0.9752614,"about_ca_system_score_codex":0.00007442103,"about_ca_system_score_gemma":0.000041949712,"threshold_uncertainty_score":0.9999608},"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":"W3136363192","doi":"10.1016/j.csl.2022.101429","title":"On the effect of dropping layers of pre-trained transformer models","year":2022,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Topic Modeling","field":"Computer Science","cited_by":91,"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":"Transformer; Computer science; Limiting; Sentence; Artificial intelligence; Paraphrase; Machine learning; Natural language processing; Engineering","score_opus":0.010209370206985395,"score_gpt":0.2361752071494904,"score_spread":0.225965836942505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3136363192","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42879853,0.00007406495,0.5692059,0.0002471228,0.00020380429,0.00023935776,0.0000042692827,0.000053768486,0.0011731818],"genre_scores_gemma":[0.9818287,0.0000011898904,0.017753035,0.00026198916,0.000049969905,0.000020644131,0.0000020000098,0.000011297852,0.00007116513],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99851763,0.00022454385,0.00028113165,0.00029727124,0.00045595676,0.00022347205],"domain_scores_gemma":[0.99879956,0.00028983163,0.000114122115,0.00073576276,0.00002209999,0.000038632446],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006593522,0.00014460292,0.00025421823,0.00010896195,0.000101320315,0.000025451342,0.001276457,0.000028053122,0.00006145281],"category_scores_gemma":[0.000010290098,0.000103225175,0.00015012847,0.00028851474,0.000032596065,0.00013656904,0.0002630788,0.00022411646,0.0000019232464],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000108122906,0.00013955282,0.00008455669,0.00019573845,0.00014852815,0.00010179802,0.032346968,0.28377074,0.015957132,0.0798124,0.0006810533,0.5866534],"study_design_scores_gemma":[0.0005144819,0.0005873109,0.000082517035,0.000032127067,0.000010280424,0.000020777581,0.00006993425,0.9647587,0.03249719,0.0012204541,0.00006964427,0.00013656798],"about_ca_topic_score_codex":0.00006363192,"about_ca_topic_score_gemma":0.0000027710187,"teacher_disagreement_score":0.680988,"about_ca_system_score_codex":0.000037009533,"about_ca_system_score_gemma":0.000029788693,"threshold_uncertainty_score":0.42094007},"labels":[],"label_agreement":null},{"id":"W3214734602","doi":"10.1016/j.csl.2021.101322","title":"Empirical Mode Decomposition articulation feature extraction on Parkinson’s Diadochokinesia","year":2021,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Voice and Speech Disorders","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"H2020 Marie Skłodowska-Curie Actions; Horizon 2020; Natural Sciences and Engineering Research Council of Canada; Horizon 2020 Framework Programme; Universidad de Antioquia","keywords":"Segmentation; Computer science; Artificial intelligence; Pattern recognition (psychology); Hilbert–Huang transform; Frame (networking); Feature (linguistics); Filter (signal processing); Speech recognition; Computer vision; Telecommunications","score_opus":0.015105509905435072,"score_gpt":0.377200725557779,"score_spread":0.3620952156523439,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3214734602","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":[0.9646677,0.00039001112,0.024115486,0.0070756134,0.00043701145,0.00023708213,0.0000054312077,0.00019657926,0.0028750885],"genre_scores_gemma":[0.9659618,0.000028781864,0.026997825,0.0047927937,0.0009864763,0.000010768158,0.00034502518,0.000030801075,0.00084574375],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9986937,0.00007064169,0.00018450056,0.00038915407,0.0004177187,0.00024427258],"domain_scores_gemma":[0.9992197,0.00004725634,0.000060407612,0.0003896415,0.00014687947,0.00013608132],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009216573,0.00018242265,0.0002422189,0.000104616476,0.000079710044,0.000064831285,0.000059118454,0.00015943336,0.00021443823],"category_scores_gemma":[0.000037508144,0.00016528304,0.00015009628,0.00025316392,0.000017810458,0.00013580063,0.00003259975,0.00031190307,0.0001629722],"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":[0.0005677975,0.0021667085,0.032874934,0.00022268978,0.00024817314,0.0075107105,0.003602291,0.0012892287,0.12317788,0.00024162784,0.106859036,0.7212389],"study_design_scores_gemma":[0.004118263,0.0006313955,0.7471077,0.0003471997,0.0002894778,0.0022513943,0.00045538426,0.05790489,0.12117819,0.000309017,0.064688504,0.0007186143],"about_ca_topic_score_codex":0.000014353325,"about_ca_topic_score_gemma":0.00005499524,"teacher_disagreement_score":0.7205203,"about_ca_system_score_codex":0.00013717792,"about_ca_system_score_gemma":0.000070310656,"threshold_uncertainty_score":0.6740047},"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":"W4391421598","doi":"10.1016/j.csl.2024.101685","title":"Objective and subjective evaluation of speech enhancement methods in the UDASE task of the 7th CHiME challenge","year":2024,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Speech and Audio Processing","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":"Google (Canada)","funders":"Agence Nationale de la Recherche; University of Sheffield","keywords":"Computer science; Speech recognition; Speech enhancement; Leverage (statistics); Task (project management); Noise (video); Distortion (music); Artificial intelligence; Domain adaptation; Noise reduction","score_opus":0.023781224384059923,"score_gpt":0.3505703286582682,"score_spread":0.32678910427420826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391421598","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44924617,0.009737152,0.5358797,0.0009846133,0.00066769397,0.00078393385,0.000005238911,0.00005598168,0.002639566],"genre_scores_gemma":[0.8776155,0.000034079596,0.12202057,0.00013271926,0.00014177697,0.000020607855,0.0000014552431,0.000009298561,0.00002395668],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99771285,0.0006705476,0.00031731505,0.00043865794,0.0006351894,0.00022545291],"domain_scores_gemma":[0.9987978,0.00029455105,0.0001441882,0.00058368075,0.00014880815,0.000030979238],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002925975,0.00017445575,0.00024575292,0.00016074486,0.000065064516,0.00012017857,0.0008336949,0.00005908322,0.000015570253],"category_scores_gemma":[0.00007531764,0.00010479222,0.00009061973,0.00079760904,0.000071713795,0.00028996175,0.0003944202,0.0002541829,0.0000034837035],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004736234,0.00007511106,0.000070599395,0.000084620544,0.000040889874,0.000024485264,0.029507691,0.000033376327,0.016151661,0.00065675424,0.000037866666,0.9533122],"study_design_scores_gemma":[0.0006639838,0.0002576156,0.008803505,0.00042484244,0.00007490985,0.000097854696,0.0014491801,0.14324796,0.83760613,0.0069384184,0.0001762389,0.00025933533],"about_ca_topic_score_codex":0.000066175955,"about_ca_topic_score_gemma":0.000038667393,"teacher_disagreement_score":0.9530529,"about_ca_system_score_codex":0.0000767781,"about_ca_system_score_gemma":0.0001684763,"threshold_uncertainty_score":0.42733026},"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":"W4402127086","doi":"10.1016/j.csl.2024.101715","title":"Enhancing analysis of diadochokinetic speech using deep neural networks","year":2024,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Voice and Speech Disorders","field":"Medicine","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":"Western University","funders":"Government of Ontario; National Institutes of Health; National Science Foundation; Ministry of Science and Technology, Israel; Ontario Brain Institute; United States-Israel Binational Science Foundation","keywords":"Computer science; Speech recognition; Deep learning; Artificial intelligence; Convolutional neural network; Artificial neural network; Pattern recognition (psychology)","score_opus":0.011068829136460576,"score_gpt":0.2895941880896504,"score_spread":0.2785253589531898,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402127086","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":[0.791741,0.005743152,0.20094988,0.00013368837,0.00051898183,0.00021114183,0.000005110661,0.00017547862,0.00052157586],"genre_scores_gemma":[0.97525805,0.000037174363,0.023157604,0.0005460875,0.00069290004,0.0000025390884,0.00007794213,0.000044680684,0.0001830012],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99831855,0.00005021186,0.00044252357,0.00044319508,0.00034175243,0.00040378814],"domain_scores_gemma":[0.99909174,0.00009728958,0.00007405053,0.00051621685,0.00007483017,0.0001458913],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021578299,0.00024476097,0.0006275459,0.0006728971,0.000043067623,0.00007871462,0.000183139,0.00012536599,0.00048253575],"category_scores_gemma":[0.000022979359,0.00021448355,0.00045061964,0.0018210714,0.00005872408,0.00011449838,0.00011621833,0.00033103835,0.000017116372],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008541244,0.00030143742,0.011438473,0.0007429291,0.004484912,0.0060082395,0.006035703,0.03486923,0.03298453,0.00013070433,0.00047636044,0.9024421],"study_design_scores_gemma":[0.0003413587,0.0001195756,0.0074526533,0.00014106986,0.0022994932,0.0001651798,0.00029078595,0.9840211,0.0047581657,0.0000090332815,0.00018132874,0.00022019929],"about_ca_topic_score_codex":0.00024816734,"about_ca_topic_score_gemma":0.00030130302,"teacher_disagreement_score":0.94915193,"about_ca_system_score_codex":0.000063718224,"about_ca_system_score_gemma":0.000036485257,"threshold_uncertainty_score":0.8746385},"labels":[],"label_agreement":null},{"id":"W4402910001","doi":"10.1016/j.csl.2024.101723","title":"Speech Generation for Indigenous Language Education","year":2024,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Multilingual Education and Policy","field":"Social Sciences","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":"University nuhelot'ine thaiyots'i nistameyimâkanak Blue Quills; National Research Council Canada","funders":"UK Research and Innovation","keywords":"Computer science; Indigenous; Natural language processing; Linguistics; Artificial intelligence; Speech recognition; Ecology","score_opus":0.04128638080843477,"score_gpt":0.4452927727766668,"score_spread":0.404006391968232,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402910001","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":[0.9454288,0.004112849,0.009598664,0.0024494352,0.008070417,0.0011130099,0.00003927576,0.00058138545,0.028606178],"genre_scores_gemma":[0.8776673,0.000079218626,0.04429961,0.003421417,0.02600224,0.00010877088,0.0003522832,0.000058213012,0.048010945],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99891424,0.00008932453,0.00018560493,0.00029687356,0.0002119641,0.0003019633],"domain_scores_gemma":[0.9994191,0.00008381881,0.000042308922,0.00022593055,0.0000920362,0.00013682581],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046210267,0.00012339359,0.00011941141,0.00018170824,0.00028790324,0.00039332805,0.00023698546,0.000107683,0.0004985866],"category_scores_gemma":[0.00007958284,0.00012297335,0.00009223609,0.00029431994,0.00004835996,0.0001810469,0.00002631343,0.000119718316,0.0002535256],"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":[0.0000016302578,0.000059748563,0.00002022049,0.000035761772,0.000011473655,0.0000086363725,0.20172656,0.0000025417546,0.0012987416,0.004048528,0.014343761,0.7784424],"study_design_scores_gemma":[0.00023867679,0.00007299041,0.00030688036,0.00007254747,0.000040924933,0.000025952768,0.020861713,0.005542043,0.0077292477,0.00033598542,0.96430945,0.00046358278],"about_ca_topic_score_codex":0.0037589066,"about_ca_topic_score_gemma":0.0019004939,"teacher_disagreement_score":0.9499657,"about_ca_system_score_codex":0.00016217238,"about_ca_system_score_gemma":0.00096099364,"threshold_uncertainty_score":0.56823677},"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":"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":"W4417072973","doi":"10.1016/j.csl.2025.101923","title":"Enhanced audio-visual speech enhancement with posterior sampling methods in recurrent variational autoencoders","year":2025,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Speech and Audio Processing","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":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Speech enhancement; Inference; Intelligibility (philosophy); Sampling (signal processing); Autoencoder; Pattern recognition (psychology); Noise reduction; Posterior probability","score_opus":0.015556743825154234,"score_gpt":0.35044631308874546,"score_spread":0.33488956926359126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417072973","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06439032,0.00052604853,0.9309851,0.0007837521,0.001024128,0.00036211414,0.0000019494062,0.00024458065,0.0016820391],"genre_scores_gemma":[0.047593433,0.000009897601,0.9504756,0.0012797224,0.00019652273,0.00003729799,0.00001546919,0.000018359346,0.00037370634],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9971666,0.00019758636,0.00056370196,0.00094887655,0.00046358848,0.00065966684],"domain_scores_gemma":[0.9987049,0.00020117016,0.00021307071,0.0006101768,0.00014710493,0.00012355912],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000799565,0.00037190213,0.00046174022,0.00048100538,0.0001661228,0.00045981005,0.0010779839,0.000111297144,0.0000758449],"category_scores_gemma":[0.000048820915,0.0003336559,0.00009472396,0.0012633478,0.000056040346,0.0005540515,0.0006009833,0.00037954835,0.000030418514],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004009322,0.00019469096,0.00013638962,0.00007184671,0.00005141617,0.000112584865,0.0020222568,0.00033976603,0.031577975,0.00043784134,0.00012558133,0.9648896],"study_design_scores_gemma":[0.0024999497,0.0005374305,0.0072377184,0.0009358193,0.000034353026,0.00011778004,0.000239569,0.12592244,0.8586945,0.0014647149,0.001301152,0.00101456],"about_ca_topic_score_codex":0.000036431673,"about_ca_topic_score_gemma":0.0000645201,"teacher_disagreement_score":0.963875,"about_ca_system_score_codex":0.00026839212,"about_ca_system_score_gemma":0.00037076388,"threshold_uncertainty_score":0.99991155},"labels":[],"label_agreement":null}]}