{"meta":{"query_hash":"a8a6aac901d9","filters":{"venue":"IEEE Transactions on Speech and Audio Processing"},"cohort_total":16,"direct_labels_cover":0,"predictions_cover":16,"exported":16,"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/a8a6aac901d9","api":"https://metacan.xera.ac/api/v1/cohort?venue=IEEE+Transactions+on+Speech+and+Audio+Processing"},"results":[{"id":"W2000916836","doi":"10.1109/89.902276","title":"An adaptive KLT approach for speech enhancement","year":2001,"lang":"en","type":"article","venue":"IEEE Transactions on Speech and Audio Processing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":235,"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 enhancement; Speech recognition; Noise (video); Computer science; Speech processing; White noise; Additive white Gaussian noise; Residual; Background noise; Colors of noise; Distortion (music); Mathematics; Artificial intelligence; Noise reduction; Algorithm; Telecommunications","score_opus":0.027864317274008104,"score_gpt":0.2735090793971463,"score_spread":0.2456447621231382,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2000916836","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013035799,0.00036396412,0.98337597,0.00031931864,0.00021374975,0.00045669713,0.0000069141397,0.0003315542,0.001896022],"genre_scores_gemma":[0.56704164,0.00008143657,0.43170232,0.00043302425,0.0001100211,0.000089477835,0.000002854469,0.000024245894,0.0005149988],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9975947,0.00004278183,0.0003680629,0.0009449812,0.0003884467,0.0006610174],"domain_scores_gemma":[0.9988582,0.000051731586,0.00016438989,0.00043258083,0.00021025534,0.00028284692],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003793208,0.0003627032,0.000335007,0.0002605565,0.0009351995,0.0006181193,0.00056155154,0.0001427727,0.000018577557],"category_scores_gemma":[0.0000055086466,0.00033780606,0.000107152846,0.00066369254,0.00010442148,0.0016335458,0.00000481275,0.00029949434,0.000011423728],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000118211196,0.00042000625,0.000011360367,0.0000742198,0.000024530122,0.000015244188,0.00039725594,0.0005694503,0.025191016,0.00002886638,0.000054880045,0.97309494],"study_design_scores_gemma":[0.0011396509,0.00086133997,0.000019753008,0.00013080999,0.000043526674,0.00025306098,0.00031228803,0.07282626,0.92128074,0.0015203708,0.000997048,0.00061512383],"about_ca_topic_score_codex":0.000011246488,"about_ca_topic_score_gemma":0.000009814531,"teacher_disagreement_score":0.9724798,"about_ca_system_score_codex":0.000082981656,"about_ca_system_score_gemma":0.00017309863,"threshold_uncertainty_score":0.9999074},"labels":[],"label_agreement":null},{"id":"W2096441936","doi":"10.1109/tsa.2005.851925","title":"A frequency domain method for blind source separation of convolutive audio mixtures","year":2005,"lang":"en","type":"article","venue":"IEEE Transactions on Speech and Audio Processing","topic":"Blind Source Separation Techniques","field":"Computer Science","cited_by":132,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Blind signal separation; Algorithm; Initialization; Frequency domain; Computer science; Mixing (physics); Joint (building); Bin; Speech recognition; Permutation (music); Spectral density; Mathematics; Acoustics","score_opus":0.019362324051516985,"score_gpt":0.32183531275924726,"score_spread":0.30247298870773026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096441936","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010483241,0.00023105252,0.9865996,0.0014049849,0.0000585444,0.00043926234,0.000011219231,0.0002306026,0.00054146355],"genre_scores_gemma":[0.4218474,0.00001803404,0.57747203,0.00033888794,0.000036496458,0.000056296576,0.000001226824,0.000010921795,0.00021867281],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986584,0.00010060011,0.00036309237,0.00041060455,0.00023695224,0.00023032895],"domain_scores_gemma":[0.9990964,0.00015335497,0.00022151558,0.0002306604,0.0002170922,0.000080999824],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00057111017,0.00018794643,0.00025334416,0.0002571519,0.00030811172,0.00015201523,0.00024584166,0.00013718978,0.000007340957],"category_scores_gemma":[0.000010430559,0.0001791599,0.000097092015,0.00038396526,0.00007629388,0.0007974389,0.0000027643994,0.0002035166,0.000003071596],"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":[0.00010451888,0.00026654822,0.000008043401,0.000119029944,0.00005443492,0.0000011964221,0.007389618,0.002340697,0.12435538,0.0023137543,0.00025746648,0.86278933],"study_design_scores_gemma":[0.00107204,0.0002582259,0.00001823148,0.00010333187,0.00003337944,0.000039739967,0.00014487382,0.044289995,0.9402277,0.011639448,0.0018828255,0.00029022072],"about_ca_topic_score_codex":0.000016846941,"about_ca_topic_score_gemma":0.000043535612,"teacher_disagreement_score":0.86249906,"about_ca_system_score_codex":0.00004925719,"about_ca_system_score_gemma":0.00015125936,"threshold_uncertainty_score":0.7305929},"labels":[],"label_agreement":null},{"id":"W2100555417","doi":"10.1109/tsa.2003.815518","title":"A soft voice activity detector based on a laplacian-gaussian model","year":2003,"lang":"en","type":"article","venue":"IEEE Transactions on Speech and Audio Processing","topic":"Speech and Audio Processing","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":"Queen's University","funders":"","keywords":"Speech recognition; Hidden Markov model; Computer science; Noise (video); Discrete cosine transform; Gaussian; Posterior probability; Detector; Probability distribution; Bayesian probability; Pattern recognition (psychology); Mathematics; Artificial intelligence; Statistics","score_opus":0.01821155687566045,"score_gpt":0.24881046777282215,"score_spread":0.2305989108971617,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2100555417","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03208615,0.00009934748,0.96363354,0.00068421476,0.00020406324,0.00020584867,0.0000080554555,0.00041416127,0.0026646247],"genre_scores_gemma":[0.89116454,0.000012123778,0.10710539,0.001164386,0.000033472286,0.000038801474,3.377499e-7,0.000034984765,0.00044597633],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99758685,0.0000905393,0.00027654445,0.00088593474,0.00050158834,0.000658521],"domain_scores_gemma":[0.99881953,0.00011667895,0.00016415247,0.00048370028,0.000103762664,0.00031217505],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003562593,0.0004161449,0.00034109433,0.00036040263,0.0009684105,0.000606284,0.00039441808,0.00018116218,0.000017000411],"category_scores_gemma":[0.00003084129,0.00038464103,0.00012850015,0.00082489336,0.000102388454,0.001065649,0.000003197423,0.0005776856,0.00004160837],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010521113,0.00044268105,0.000022507702,0.00015654732,0.000019289275,0.000040439812,0.0003032471,0.02477002,0.036727495,0.000025972238,0.000043300657,0.9373433],"study_design_scores_gemma":[0.0008085436,0.00017650636,0.000024711286,0.00021257489,0.000022546172,0.000050163762,0.00002105662,0.32540134,0.67198384,0.0005836834,0.0002773643,0.00043766326],"about_ca_topic_score_codex":0.0000064306796,"about_ca_topic_score_gemma":0.000027923857,"teacher_disagreement_score":0.9369056,"about_ca_system_score_codex":0.00010866231,"about_ca_system_score_gemma":0.0004745297,"threshold_uncertainty_score":0.9998605},"labels":[],"label_agreement":null},{"id":"W2101999036","doi":"10.1109/tsa.2005.851943","title":"Speech enhancement employing Laplacian-Gaussian mixture","year":2005,"lang":"en","type":"article","venue":"IEEE Transactions on Speech and Audio Processing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":68,"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":"Speech recognition; Wiener filter; Computer science; Estimator; Minimum mean square error; Speech enhancement; Gaussian; Computational complexity theory; Filter (signal processing); Noise (video); Algorithm; Mathematics; Artificial intelligence; Statistics; Physics","score_opus":0.013688057152124792,"score_gpt":0.25468810587074936,"score_spread":0.24100004871862457,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2101999036","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039856452,0.0009972062,0.9511487,0.0036536832,0.00036335003,0.00022997326,0.0000043333594,0.00047822733,0.0032680843],"genre_scores_gemma":[0.7702487,0.00016347154,0.22574508,0.0016902382,0.00024391881,0.000029736619,0.0000012027625,0.0000348381,0.0018427937],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9972766,0.000048081303,0.00047037326,0.0008942778,0.0005477085,0.00076296227],"domain_scores_gemma":[0.9988637,0.000051232164,0.00019307864,0.00045580434,0.00012614325,0.00031005873],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003347647,0.000433119,0.0003662027,0.00033449283,0.0010383145,0.0008286713,0.00058556924,0.00018420204,0.00008282156],"category_scores_gemma":[0.000008431119,0.0004003401,0.00011988027,0.0007840631,0.00010600565,0.0017356734,0.000010472449,0.0005728477,0.00013341813],"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":[0.000020793077,0.00016614379,0.000019487374,0.0000799839,0.000022675335,0.000035110003,0.00061813765,0.00017899572,0.032230627,0.000015233608,0.00017938735,0.9664334],"study_design_scores_gemma":[0.0007225972,0.00014350592,0.00004500718,0.00035574893,0.000031825428,0.00026234932,0.000093886265,0.0037735263,0.9851051,0.00039693163,0.008484589,0.00058492104],"about_ca_topic_score_codex":0.00000876071,"about_ca_topic_score_gemma":0.00004928158,"teacher_disagreement_score":0.9658485,"about_ca_system_score_codex":0.0001298371,"about_ca_system_score_gemma":0.00019395066,"threshold_uncertainty_score":0.99984485},"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":"W2127390035","doi":"10.1109/89.902283","title":"Synthetic stereo acoustic echo cancellation structure for multiple participant VoIP conferences","year":2001,"lang":"en","type":"article","venue":"IEEE Transactions on Speech and Audio Processing","topic":"Speech and Audio Processing","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":"Carleton University","funders":"","keywords":"Monaural; Spatialization; Echo (communications protocol); Computer science; Stereophonic sound; Teleconference; Loudspeaker; Voice over IP; Reverberation; Speech recognition; Channel (broadcasting); Artificial intelligence; Acoustics; Telecommunications; The Internet","score_opus":0.0403782802899136,"score_gpt":0.2751404288449312,"score_spread":0.23476214855501756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2127390035","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12120304,0.00037757005,0.8767616,0.0005885961,0.00033425578,0.0003054403,0.000016936043,0.00031493016,0.00009758688],"genre_scores_gemma":[0.95323557,0.000098860604,0.04601177,0.00026670488,0.00009616846,0.000046435056,0.0000020096304,0.000028559225,0.00021392952],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99816453,0.000034834244,0.00034937987,0.00063886144,0.00027188775,0.00054049323],"domain_scores_gemma":[0.99902743,0.00016952169,0.0001767462,0.00027162296,0.00017188276,0.00018280782],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001812223,0.00028458785,0.0003008761,0.00017888853,0.00064169284,0.0005604528,0.0003155326,0.0001276083,0.000018052748],"category_scores_gemma":[0.000025001083,0.0002487557,0.00007326442,0.00041187173,0.000098294535,0.00074727257,0.0000039832057,0.00023549951,0.000004362447],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007915039,0.00008667655,0.00024776603,0.00018794031,0.000024991046,0.000012928346,0.000818462,0.005544006,0.05608052,0.0000073714723,0.000036204394,0.936874],"study_design_scores_gemma":[0.0012822746,0.00027258502,0.00020630982,0.00045840937,0.00011210733,0.00017220803,0.0003819682,0.17338409,0.8196943,0.0021381166,0.0012823744,0.00061529625],"about_ca_topic_score_codex":0.000024580517,"about_ca_topic_score_gemma":0.00028823153,"teacher_disagreement_score":0.9362587,"about_ca_system_score_codex":0.000049845406,"about_ca_system_score_gemma":0.00024396589,"threshold_uncertainty_score":0.9999965},"labels":[],"label_agreement":null},{"id":"W2128604088","doi":"10.1109/tsa.2003.818031","title":"Incorporating the human hearing properties in the signal subspace approach for speech enhancement","year":2003,"lang":"en","type":"article","venue":"IEEE Transactions on Speech and Audio Processing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":171,"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 recognition; Speech enhancement; Computer science; Signal subspace; Noise (video); Spectrogram; Noise reduction; Residual; Colors of noise; Subspace topology; Filter (signal processing); Artificial intelligence; Algorithm; Computer vision","score_opus":0.04549423966659918,"score_gpt":0.264615521974624,"score_spread":0.21912128230802483,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128604088","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07527658,0.0005098885,0.9207963,0.00077577314,0.00008050226,0.00062211684,9.4164795e-7,0.00006916092,0.0018687759],"genre_scores_gemma":[0.89156765,0.000013894289,0.10735693,0.0005280014,0.000054835047,0.0001273876,6.187314e-7,0.000018634715,0.0003320435],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99803156,0.00013667015,0.00037197064,0.0005565064,0.00039999757,0.00050327595],"domain_scores_gemma":[0.9992371,0.0000924771,0.00017127048,0.00033308033,0.00009898572,0.000067060246],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0012663704,0.0002782925,0.0002364242,0.0001475058,0.0014599639,0.00087630155,0.00058380637,0.00008160181,0.0000048117686],"category_scores_gemma":[0.000014314582,0.00016999226,0.00007973565,0.00068945845,0.00015050496,0.00070634903,0.0000056669355,0.00045674926,0.0000032407559],"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":[0.0000497525,0.0008618046,0.0002763733,0.0006223466,0.000049313367,0.000021919874,0.008717634,0.0042705922,0.1882878,0.0006155778,0.00009974187,0.79612714],"study_design_scores_gemma":[0.00067630736,0.00016556385,0.000036156613,0.00021650708,0.00002214748,0.00013267482,0.0016262813,0.011698854,0.98325753,0.0015757186,0.0002471553,0.00034509224],"about_ca_topic_score_codex":0.00001816165,"about_ca_topic_score_gemma":0.000032656084,"teacher_disagreement_score":0.8162911,"about_ca_system_score_codex":0.00006094757,"about_ca_system_score_gemma":0.00016025339,"threshold_uncertainty_score":0.99984},"labels":[],"label_agreement":null},{"id":"W2132572274","doi":"10.1109/tsa.2005.851917","title":"LSP quantization by a union of locally trained codebooks","year":2005,"lang":"en","type":"article","venue":"IEEE Transactions on Speech and Audio Processing","topic":"Advanced Data Compression Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Codebook; Vector quantization; Algorithm; Mathematics; Encoder; Speech coding; Computational complexity theory; Code-excited linear prediction; Speech recognition; Pattern recognition (psychology); Linear predictive coding; Computer science; Artificial intelligence; Statistics","score_opus":0.012466712998972692,"score_gpt":0.2608341671625037,"score_spread":0.24836745416353098,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2132572274","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035301924,0.00017907622,0.995056,0.00046237872,0.00004334666,0.00014166777,0.000015220955,0.00029912876,0.00027304067],"genre_scores_gemma":[0.79445374,0.000080292186,0.2050274,0.00018108546,0.000013102626,0.000012138771,0.0000026351331,0.0000108230515,0.00021877621],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989506,0.00004276546,0.00027614963,0.00032327216,0.00023157122,0.00017562804],"domain_scores_gemma":[0.99939656,0.000038402228,0.00013570761,0.00025621467,0.000097635915,0.00007547303],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016186235,0.00014270903,0.0001693907,0.0001446834,0.00018923046,0.00007582781,0.000284575,0.000074074196,0.000008217612],"category_scores_gemma":[0.000004326397,0.0001323738,0.00003382523,0.0002776842,0.00007497799,0.0008660803,0.0000040435107,0.00015468577,0.000002711848],"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":[0.0000132079,0.00008704603,0.0000013875336,0.00003125912,0.000004042806,9.029303e-7,0.00022971144,0.00038220853,0.08717419,0.00008367645,0.00018470283,0.91180766],"study_design_scores_gemma":[0.00036615084,0.000112237074,0.000008187501,0.00018211547,0.000007666743,0.000019522902,0.000020602149,0.067920275,0.9278379,0.000521991,0.002833585,0.00016975249],"about_ca_topic_score_codex":0.0000075148405,"about_ca_topic_score_gemma":0.000009597868,"teacher_disagreement_score":0.9116379,"about_ca_system_score_codex":0.000030985957,"about_ca_system_score_gemma":0.000057550114,"threshold_uncertainty_score":0.5398047},"labels":[],"label_agreement":null},{"id":"W2133278758","doi":"10.1109/tsa.2004.825668","title":"Speaker Adaptation Using an Eigenphone Basis","year":2004,"lang":"en","type":"article","venue":"IEEE Transactions on Speech and Audio Processing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Speech recognition; Adaptation (eye); Computer science; Basis (linear algebra); Mathematics; Psychology","score_opus":0.037026132462567876,"score_gpt":0.2671019762390837,"score_spread":0.23007584377651585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133278758","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20359099,0.00028203608,0.79487425,0.000403017,0.00023922787,0.000117706775,0.000003317396,0.0002841964,0.0002052639],"genre_scores_gemma":[0.7032628,0.000043002743,0.29602847,0.00048705176,0.000081139464,0.0000071432364,9.712837e-7,0.000023227301,0.00006619966],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9980936,0.00003755062,0.00032875943,0.00067968515,0.00038426855,0.00047611288],"domain_scores_gemma":[0.9990931,0.000021558368,0.00014873857,0.00033873672,0.00014334157,0.00025448683],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002360723,0.00029172006,0.0002469669,0.00030086964,0.00088953075,0.00062808,0.00033925212,0.00012300866,0.000016764312],"category_scores_gemma":[0.0000057159455,0.00028446896,0.00007379105,0.0008196273,0.000095147676,0.0024679536,0.000004353822,0.00029867288,0.000023715325],"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":[0.000023121913,0.00025069702,0.000013324406,0.000056649398,0.000016499303,0.00003930386,0.0017058791,0.028097203,0.0530131,0.000021985537,0.0000026270982,0.9167596],"study_design_scores_gemma":[0.0010192211,0.00018696161,0.00009674869,0.00025802205,0.000037356116,0.00030973897,0.00040503396,0.031849068,0.9625526,0.002698663,0.00008872369,0.00049786613],"about_ca_topic_score_codex":0.00006972043,"about_ca_topic_score_gemma":0.000067663736,"teacher_disagreement_score":0.91626173,"about_ca_system_score_codex":0.00012395256,"about_ca_system_score_gemma":0.00031522114,"threshold_uncertainty_score":0.9999607},"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":"W2135817141","doi":"10.1109/tsa.2004.833008","title":"Time-Delay Estimation via Linear Interpolation and Cross Correlation","year":2004,"lang":"en","type":"article","venue":"IEEE Transactions on Speech and Audio Processing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":243,"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":"Reverberation; Multilateration; Cross-correlation; Computer science; Microphone; Multipath propagation; Algorithm; Noise (video); Interpolation (computer graphics); SIGNAL (programming language); Linear interpolation; Speech recognition; Acoustics; Mathematics; Artificial intelligence; Telecommunications; Pattern recognition (psychology)","score_opus":0.00977493263216831,"score_gpt":0.25927492469456587,"score_spread":0.24949999206239756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135817141","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.121597596,0.00019006837,0.8770434,0.0004178616,0.00016269041,0.0001377892,0.0000020621137,0.00025860977,0.00018987205],"genre_scores_gemma":[0.792267,0.000024231269,0.20728998,0.00019226957,0.0000420605,0.000008916162,0.0000024659705,0.000015572245,0.00015744985],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986864,0.000023467072,0.00030267914,0.00047406784,0.0002437461,0.0002696589],"domain_scores_gemma":[0.9993818,0.000040596133,0.00015416143,0.0001766187,0.00011564174,0.00013118565],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022225498,0.00021510248,0.0001799293,0.00021678738,0.0006763643,0.0004825004,0.00015493201,0.00012788025,0.000010436865],"category_scores_gemma":[0.00001103621,0.00020857736,0.000041202184,0.000421548,0.00012784102,0.0019927374,0.0000050653166,0.00026815274,0.000046329595],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030907446,0.0000756051,0.000044587105,0.00006836484,0.000011150803,0.000009505977,0.00088181783,0.032816436,0.015265611,0.000014187315,0.0000044093763,0.9507774],"study_design_scores_gemma":[0.0010836335,0.0001796964,0.00025741235,0.0003266187,0.000026131513,0.00032217504,0.000031470034,0.69554013,0.2984495,0.003368035,0.000046553738,0.0003686412],"about_ca_topic_score_codex":0.000011556422,"about_ca_topic_score_gemma":0.00000617812,"teacher_disagreement_score":0.95040876,"about_ca_system_score_codex":0.000063584004,"about_ca_system_score_gemma":0.00009562495,"threshold_uncertainty_score":0.8505538},"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":"W2137996830","doi":"10.1109/tsa.2005.851941","title":"A blind channel identification-based two-stage approach to separation and dereverberation of speech signals in a reverberant environment","year":2005,"lang":"en","type":"article","venue":"IEEE Transactions on Speech and Audio Processing","topic":"Blind Source Separation Techniques","field":"Computer Science","cited_by":103,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec","funders":"","keywords":"Reverberation; Blind signal separation; MIMO; Robustness (evolution); Computer science; Speech recognition; Source separation; Interference (communication); Channel (broadcasting); Signal processing; Acoustics; Algorithm; Telecommunications; Physics","score_opus":0.025129042935960907,"score_gpt":0.28828980738897314,"score_spread":0.26316076445301223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2137996830","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08473204,0.0000797886,0.9134051,0.0009650953,0.00001774718,0.000533304,0.00000696039,0.00007016841,0.00018979247],"genre_scores_gemma":[0.82665336,0.00003129181,0.1726519,0.00034174506,0.000018308674,0.00008449358,0.0000033956578,0.0000101982405,0.00020531965],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99850833,0.00009188668,0.0004478434,0.00047478706,0.00029956194,0.00017757458],"domain_scores_gemma":[0.9993989,0.00004681026,0.0001644547,0.00023810002,0.00006390897,0.000087852786],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061450066,0.00017123956,0.00020595788,0.00040265662,0.00016637951,0.00021137724,0.00015643307,0.000080370715,0.0000035397177],"category_scores_gemma":[0.0000053784456,0.00017693272,0.00003450446,0.00042416307,0.000045109155,0.0007705496,0.0000036845058,0.00016545912,0.000008398028],"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":[0.00013512869,0.00069770234,0.00002930424,0.00019694622,0.000019124347,0.0000030523177,0.0057415036,0.28922683,0.15027887,0.00018924734,0.00003706545,0.5534452],"study_design_scores_gemma":[0.00076821796,0.00008370834,0.0001580366,0.00008474734,0.0000101886435,0.000010543382,0.00006542321,0.33410844,0.6641907,0.00020812284,0.00011450229,0.00019734145],"about_ca_topic_score_codex":0.000035967372,"about_ca_topic_score_gemma":0.0000561991,"teacher_disagreement_score":0.7419213,"about_ca_system_score_codex":0.000073008756,"about_ca_system_score_gemma":0.00008390567,"threshold_uncertainty_score":0.72151065},"labels":[],"label_agreement":null},{"id":"W2145103350","doi":"10.1109/89.966081","title":"Linear prediction based packet loss concealment algorithm for PCM coded speech","year":2001,"lang":"en","type":"article","venue":"IEEE Transactions on Speech and Audio Processing","topic":"Advanced Data Compression Techniques","field":"Computer Science","cited_by":83,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Nortel (Canada)","funders":"","keywords":"Linear prediction; Computer science; Speech coding; Algorithm; Packet loss; Speech recognition; Network packet; Voice activity detection; Linear predictive coding; Frame (networking); Pulse-code modulation; Speech processing; SIGNAL (programming language); Speech enhancement; Residual; Artificial intelligence; Noise reduction; Telecommunications; Computer network","score_opus":0.023244735467878783,"score_gpt":0.29098343852523606,"score_spread":0.26773870305735725,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145103350","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014855348,0.00008503934,0.9960489,0.0005828593,0.00028145214,0.000533775,0.00014228417,0.0007412551,0.00009884552],"genre_scores_gemma":[0.13054295,0.0001551804,0.8680745,0.0005018722,0.00010840565,0.00015878511,0.000018786472,0.00002945411,0.00041011712],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99821365,0.00004256661,0.0003558811,0.0006471085,0.00035562323,0.00038519857],"domain_scores_gemma":[0.9989297,0.00010761767,0.00015283762,0.0004466603,0.00019415836,0.00016906037],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002576732,0.00025988743,0.00025635865,0.00019790666,0.00054407964,0.00017454223,0.0003905,0.00012669548,0.000021595462],"category_scores_gemma":[0.000007742429,0.00024247232,0.000079886806,0.00042734333,0.00010035508,0.0009711388,0.0000065428167,0.00025965,0.00000638478],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040314328,0.00015900777,0.000012866282,0.000041528343,0.000010181748,0.000020588679,0.000058754827,0.0005157751,0.003808295,0.000010277595,0.00028900485,0.9950334],"study_design_scores_gemma":[0.0010634933,0.00029623247,0.000019348272,0.00021620888,0.00002136122,0.0001077646,0.000022953946,0.4680769,0.51889795,0.00082046137,0.010176477,0.00028081174],"about_ca_topic_score_codex":0.000008288732,"about_ca_topic_score_gemma":0.000004725112,"teacher_disagreement_score":0.9947526,"about_ca_system_score_codex":0.00008354881,"about_ca_system_score_gemma":0.0001184316,"threshold_uncertainty_score":0.9887734},"labels":[],"label_agreement":null},{"id":"W2146814186","doi":"10.1109/tsa.2005.851945","title":"A variable step-size pre-filter-bank adaptive algorithm","year":2005,"lang":"en","type":"article","venue":"IEEE Transactions on Speech and Audio Processing","topic":"Advanced Adaptive Filtering Techniques","field":"Engineering","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":"Queen's University","funders":"","keywords":"Algorithm; Adaptive filter; Mathematics; Filter (signal processing); Computational complexity theory; Convergence (economics); Autocorrelation; Filter bank; Noise (video); Adaptive algorithm; A priori and a posteriori; Computer science; Statistics; Artificial intelligence","score_opus":0.01163436432685181,"score_gpt":0.23488334796582935,"score_spread":0.22324898363897755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2146814186","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030434958,0.00035599354,0.99296623,0.000044371172,0.00013816229,0.0002362016,0.000049271068,0.0013034814,0.0018627676],"genre_scores_gemma":[0.42176595,0.000088671266,0.5771672,0.000064895656,0.00010772321,0.00006266686,8.9308315e-7,0.000056043293,0.00068592076],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988089,0.000017062812,0.0002574189,0.00033855674,0.00018783775,0.0003901926],"domain_scores_gemma":[0.9994998,0.00006517281,0.000046408386,0.00020124871,0.00006459456,0.00012280435],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00010018342,0.0002993998,0.00025593655,0.00012567238,0.00022794674,0.00008873727,0.0001320869,0.00012530928,0.000078135134],"category_scores_gemma":[0.000004117219,0.0003099857,0.00005319305,0.0002766668,0.00007125769,0.0006213658,0.0000022626507,0.00041310844,0.00001720458],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030980376,0.00006729118,8.405084e-7,0.000057917227,0.000038203263,0.0000076335,0.00018077745,0.026458256,0.019843938,0.000017149,0.00013490305,0.95316213],"study_design_scores_gemma":[0.00082285993,0.0002766286,0.000048475205,0.00055804616,0.00007265857,0.00014445659,0.00009922334,0.29528388,0.685192,0.0009693057,0.015692534,0.0008399336],"about_ca_topic_score_codex":0.000008898473,"about_ca_topic_score_gemma":0.000009254688,"teacher_disagreement_score":0.9523222,"about_ca_system_score_codex":0.00014031999,"about_ca_system_score_gemma":0.00003244075,"threshold_uncertainty_score":0.9999352},"labels":[],"label_agreement":null},{"id":"W2170959418","doi":"10.1109/tsa.2003.814411","title":"Quantization of lsf parameters using a trellis modeling","year":2003,"lang":"en","type":"article","venue":"IEEE Transactions on Speech and Audio Processing","topic":"Advanced Data Compression Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Trellis quantization; Vector quantization; Algorithm; Quantization (signal processing); Speech recognition; Mathematics; Computer science; Trellis (graph); Speech coding; Decoding methods; Artificial intelligence; Image processing","score_opus":0.04364163151637969,"score_gpt":0.2915569645516571,"score_spread":0.2479153330352774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170959418","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030284112,0.00016574809,0.9690792,0.000022323213,0.00008233948,0.00011079378,0.0000038087728,0.00016249713,0.000089162495],"genre_scores_gemma":[0.5489863,0.00005524678,0.4509004,0.000032317654,0.000002855202,0.00000383116,2.914852e-7,0.000007668524,0.000011027096],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989584,0.000050413506,0.00027135253,0.00033316715,0.00020303359,0.00018364498],"domain_scores_gemma":[0.999413,0.000037599337,0.00012350062,0.00027165917,0.0000902078,0.00006403659],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015778928,0.0001394904,0.00017777339,0.0001629016,0.00022860606,0.00008764274,0.00018909789,0.00006427856,0.000003195985],"category_scores_gemma":[0.000010438708,0.00013271354,0.00004283964,0.00045654082,0.00004525788,0.00089970615,0.0000025123047,0.00014436276,9.2482935e-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":[0.000017291273,0.00013727778,0.000014833977,0.00010128893,0.000012931535,0.0000048425813,0.0003789826,0.3195939,0.046025272,0.00041613512,0.0000052052087,0.633292],"study_design_scores_gemma":[0.00012691521,0.00003102176,4.041711e-7,0.00014258496,0.000008735575,0.00002205151,0.000027623082,0.5297688,0.46732205,0.00241502,0.000024970597,0.00010980626],"about_ca_topic_score_codex":0.00001453084,"about_ca_topic_score_gemma":0.0000018188855,"teacher_disagreement_score":0.6331822,"about_ca_system_score_codex":0.000026559654,"about_ca_system_score_gemma":0.00006494584,"threshold_uncertainty_score":0.54119015},"labels":[],"label_agreement":null}]}