{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":1031,"total_is_capped":false,"direct_labels_cover":2,"predictions_cover":1031,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"7a36b2ebf8e4","filters":{"topic":"Music and Audio Processing"}},"results":[{"id":"W2099866409","doi":"10.1145/1273496.1273596","title":"Restricted Boltzmann machines for collaborative filtering","year":2007,"lang":"en","type":"article","venue":"","topic":"Music and Audio Processing","field":"Computer Science","cited_by":1882,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Restricted Boltzmann machine; Boltzmann machine; Computer science; Collaborative filtering; Graphical model; Inference; Set (abstract data type); Class (philosophy); Artificial intelligence; Data set; Machine learning; Layer (electronics); Recommender system; Data mining; Deep learning","retraction":null,"screen_n_in":null,"score":{"opus":0.02414147631483186,"gpt":0.2826722957050696,"spread":0.2585308193902377,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000174586,0.00007198254,0.00007936583,0.00006368032,0.0001397965,0.0001258273,0.0002908417,0.00002774023,0.00001216596],"category_scores_gemma":[0.00004832669,0.00005770833,0.00002159294,0.0004413127,0.00001481462,0.0003123878,0.0000803506,0.00003667903,0.000006920802],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001347602,"about_ca_system_score_gemma":0.00004433035,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007468465,"about_ca_topic_score_gemma":0.00001456118,"domain_scores_codex":[0.9993678,0.000006562534,0.0001329959,0.0001930371,0.00009495597,0.0002046415],"domain_scores_gemma":[0.9995252,0.0001043054,0.00004987041,0.0001565949,0.0001135393,0.00005050792],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00004860261,0.00008019037,0.0006096509,0.00007914232,0.00003103992,0.00002974859,0.002533248,0.00006096398,0.06319806,0.2456621,0.05054922,0.637118],"study_design_scores_gemma":[0.002746814,0.0004744571,0.0188521,0.0001369028,0.00001829482,0.00003945955,0.0004732046,0.1543368,0.4015082,0.04475555,0.3753139,0.001344322],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007937011,0.00006921041,0.9626484,0.0008780779,0.0002068262,0.0001159158,0.000001283271,0.0001651094,0.02797815],"genre_scores_gemma":[0.3817595,0.000002676221,0.613583,0.001696145,0.0001818046,0.00001126133,0.00000257134,0.000007596836,0.00275537],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6357737,"threshold_uncertainty_score":0.2353277,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2053101950","doi":"10.1007/s00530-010-0182-0","title":"Multimodal fusion for multimedia analysis: a survey","year":2010,"lang":"en","type":"article","venue":"Multimedia Systems","topic":"Music and Audio Processing","field":"Computer Science","cited_by":1226,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa; University of Winnipeg","funders":"","keywords":"Computer science; Modalities; Modality (human–computer interaction); Perspective (graphical); Process (computing); Multimedia; Sensor fusion; Artificial intelligence; Human–computer interaction","retraction":null,"screen_n_in":null,"score":{"opus":0.02559643849957117,"gpt":0.2733577503753194,"spread":0.2477613118757482,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001822072,0.0003019681,0.0005705198,0.0003900543,0.0002907941,0.0004252385,0.001160091,0.000249356,0.00002752072],"category_scores_gemma":[0.0006509113,0.000255738,0.0002410423,0.001127923,0.00008472941,0.0004833189,0.0001983403,0.0003105871,0.0001091427],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003128645,"about_ca_system_score_gemma":0.0001373509,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001400143,"about_ca_topic_score_gemma":0.0008942927,"domain_scores_codex":[0.9973605,0.0001606829,0.0005814083,0.0008032027,0.0004967456,0.0005974786],"domain_scores_gemma":[0.9971282,0.0009000603,0.0003206219,0.0009374849,0.0004048026,0.0003088536],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001310499,0.0008488621,0.1690707,0.0005067939,0.001402206,0.00004668071,0.01114435,0.001727483,0.1008782,0.0005669733,0.01740657,0.69627],"study_design_scores_gemma":[0.0008941935,0.0000280417,0.03927981,0.00002108665,0.00006702232,0.000005440727,0.00003290087,0.9540404,0.0009315988,0.00001665088,0.004348719,0.0003341342],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06532233,0.0001903997,0.9271192,0.000214824,0.005484801,0.0009057673,0.00007702074,0.0003987245,0.0002869575],"genre_scores_gemma":[0.7771832,0.000002677768,0.221349,0.0001171623,0.0005627805,0.0001851643,0.0000985474,0.00002333531,0.0004780808],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9523129,"threshold_uncertainty_score":0.9999895,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1718516643","doi":"10.1073/pnas.1414495112","title":"Statistical universals reveal the structures and functions of human music","year":2015,"lang":"en","type":"article","venue":"Proceedings of the National Academy of Sciences","topic":"Music and Audio Processing","field":"Computer Science","cited_by":650,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"","keywords":"Problem of universals; Linguistics; Psychology; Mathematics; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.08503047264000195,"gpt":0.3169157324849309,"spread":0.2318852598449289,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009988459,0.00005426547,0.00009678206,0.00007672066,0.0002405584,0.00003987101,0.0008745176,0.00003200959,0.000004413304],"category_scores_gemma":[0.0002974118,0.00002931704,0.00002127678,0.0005235511,0.001164031,0.0004687598,0.0002488925,0.0000973417,1.916662e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001210723,"about_ca_system_score_gemma":0.00005746309,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008430573,"about_ca_topic_score_gemma":8.293711e-8,"domain_scores_codex":[0.9987685,0.000008094309,0.0001910856,0.0001591088,0.0007838864,0.00008932863],"domain_scores_gemma":[0.9992826,0.0001139715,0.0002943832,0.00001005513,0.0002652331,0.00003373296],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000003228872,0.00001456362,0.002428467,0.00003808514,0.000008286917,5.004468e-9,0.00107213,0.00004751002,0.03836745,0.9481829,0.007580277,0.002257119],"study_design_scores_gemma":[0.0002388132,0.00009568707,0.1003016,0.00007058364,0.00001605224,0.00001503246,0.0009292565,0.002598753,0.0432732,0.8518972,0.0004662692,0.00009751815],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9785179,0.0001672333,0.000760563,0.007378758,0.00004576875,0.0001324184,0.00001295809,0.00001536603,0.01296907],"genre_scores_gemma":[0.9934276,0.00000174862,0.006159254,0.0002584153,0.00003866582,0.000001015695,3.781197e-8,0.00000112473,0.0001121229],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09787314,"threshold_uncertainty_score":0.4288921,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2964335273","doi":"","title":"How to Construct Deep Recurrent Neural Networks","year":2014,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Music and Audio Processing","field":"Computer Science","cited_by":582,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Recurrent neural network; Computer science; Deep learning; Artificial intelligence; Construct (python library); Feedforward neural network; Feed forward; Function (biology); Artificial neural network; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.03925941227028947,"gpt":0.3147329136198822,"spread":0.2754735013495928,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001688021,0.0001275578,0.0001147352,0.0001617805,0.0002290671,0.0009746208,0.0007609122,0.0000389148,0.0001003284],"category_scores_gemma":[0.0004743663,0.0001240069,0.00005428129,0.0002346618,0.0000493279,0.0004448814,0.0001905393,0.0003010761,0.00005004302],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003503931,"about_ca_system_score_gemma":0.00003137244,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001355466,"about_ca_topic_score_gemma":0.000009008383,"domain_scores_codex":[0.9986789,0.0001178089,0.0001776128,0.0004373162,0.0003776379,0.0002107125],"domain_scores_gemma":[0.9989928,0.0001843177,0.0001342791,0.0002650293,0.0002979397,0.0001256333],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001041338,0.00003604565,0.003878257,0.000003513728,0.00002503041,0.000004841221,0.001274356,0.0520456,0.0003521519,0.3646266,0.001162574,0.5765806],"study_design_scores_gemma":[0.0001795376,0.00007159698,0.002611556,0.00003488198,0.000002858238,0.00001267232,0.0001590925,0.9867647,0.0001104311,0.002118067,0.007780647,0.0001539776],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01079298,0.000007066521,0.9349864,0.02375981,0.00112517,0.00009404848,7.856831e-7,0.0001613146,0.02907249],"genre_scores_gemma":[0.9875556,0.000004961417,0.009368742,0.001065621,0.000263156,0.000027507,0.00001441607,0.000007856293,0.001692192],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9767626,"threshold_uncertainty_score":0.9398291,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1819710477","doi":"10.48550/arxiv.1206.6392","title":"Modeling Temporal Dependencies in High-Dimensional Sequences: Application to Polyphonic Music Generation and Transcription","year":2012,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Music and Audio Processing","field":"Computer Science","cited_by":490,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Polyphony; Computer science; Estimator; Probabilistic logic; Speech recognition; Representation (politics); Transcription (linguistics); Artificial intelligence; Statistical model; Natural language processing; Mathematics; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.09894440991759594,"gpt":0.1934819880977269,"spread":0.09453757818013096,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003006547,0.000205552,0.0002015567,0.0002703933,0.0001482875,0.0001133897,0.0004534315,0.0001893115,0.000007474763],"category_scores_gemma":[0.000005901936,0.000234512,0.00004648377,0.0003889809,0.00003488902,0.0007254009,0.0003796332,0.0002780877,0.00001316334],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001954275,"about_ca_system_score_gemma":0.0001757525,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001227867,"about_ca_topic_score_gemma":0.0006514537,"domain_scores_codex":[0.9985701,0.00006846648,0.0001979893,0.0007911942,0.0001118256,0.0002603885],"domain_scores_gemma":[0.9993016,0.00001151314,0.0001013686,0.0003786112,0.00008181856,0.0001251004],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000009732915,0.00003665263,0.0009477141,0.00005145048,0.000009321316,0.0000120413,0.0008508238,0.9657184,0.007965651,0.02097182,0.00001447102,0.003411927],"study_design_scores_gemma":[0.0001952312,0.00001207524,0.0004893031,0.00006529073,0.00001487652,0.000003850565,0.00003625491,0.98891,0.0004266211,0.009568363,0.00001307037,0.0002650417],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4929819,0.0001035753,0.5064341,0.0001024923,0.0001588254,0.000144464,0.00000193432,0.0000457459,0.00002701135],"genre_scores_gemma":[0.9910121,0.00002820319,0.008477429,0.0002613439,0.0001208548,0.000003787226,0.00002698641,0.000009310986,0.00005996415],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4980303,"threshold_uncertainty_score":0.9563123,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2976594877","doi":"10.1016/j.apacoust.2019.107020","title":"Trends in audio signal feature extraction methods","year":2019,"lang":"en","type":"article","venue":"Applied Acoustics","topic":"Music and Audio Processing","field":"Computer Science","cited_by":467,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada; Ryerson University","keywords":"Computer science; Feature extraction; SIGNAL (programming language); Audio signal; Speech recognition; Signal processing; Audio signal processing; Frequency domain; Wavelet; Mel-frequency cepstrum; Time domain; Feature (linguistics); Pattern recognition (psychology); Artificial intelligence; Domain (mathematical analysis); Cepstrum; Speech processing; Audio signal flow; Digital signal processing; Speech coding; Computer vision; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01591782837905122,"gpt":0.3086868783877196,"spread":0.2927690500086684,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003295117,0.0001262582,0.000163996,0.0001649469,0.00005309463,0.0001063802,0.0003645725,0.0001196679,0.00009251322],"category_scores_gemma":[0.00000643448,0.000116511,0.00003372699,0.000603421,0.00001732094,0.0001919772,0.000104102,0.0002963532,0.00006942716],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004768755,"about_ca_system_score_gemma":0.00004073763,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002547702,"about_ca_topic_score_gemma":7.948317e-7,"domain_scores_codex":[0.9990594,0.00002621136,0.0001451807,0.0003302742,0.0001846672,0.0002542102],"domain_scores_gemma":[0.9994407,0.0001027066,0.00008951618,0.0002932575,0.00002420337,0.00004957971],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006069589,0.0000382812,0.0001009992,0.00002172465,0.000005764371,0.000006435833,0.0003262133,0.003515391,0.1727066,0.008189461,0.0050599,0.8100232],"study_design_scores_gemma":[0.002439076,0.0001453702,0.03189875,0.0001197298,0.00005903209,0.00007913091,0.0003688238,0.8111495,0.06198499,0.02718617,0.06296988,0.001599515],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005785337,0.00006142554,0.9638512,0.0003833492,0.0003490521,0.00006581475,6.340434e-7,0.0001021593,0.02940101],"genre_scores_gemma":[0.6232979,0.000003514883,0.3745505,0.0005985815,0.00009970498,0.000006089047,0.000002898814,0.000008112584,0.001432702],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8084236,"threshold_uncertainty_score":0.4751181,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1964812476","doi":"10.1109/taslp.2014.2303296","title":"Application of Deep Belief Networks for Natural Language Understanding","year":2014,"lang":"en","type":"article","venue":"IEEE/ACM Transactions on Audio Speech and Language Processing","topic":"Music and Audio Processing","field":"Computer Science","cited_by":460,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Deep belief network; Artificial intelligence; Computer science; Support vector machine; Boosting (machine learning); Artificial neural network; Machine learning; Deep learning; Principle of maximum entropy; Backpropagation; Pattern recognition (psychology)","retraction":null,"screen_n_in":null,"score":{"opus":0.01281846356590224,"gpt":0.2571697326409619,"spread":0.2443512690750596,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003312266,0.0001967862,0.0002448529,0.00016376,0.0004087475,0.0001734108,0.0003883158,0.0001011881,0.000006226889],"category_scores_gemma":[0.0000378137,0.000179705,0.0000802561,0.0004014425,0.00007831167,0.0004256805,0.00001114393,0.0002257252,0.000001588339],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005241065,"about_ca_system_score_gemma":0.00003409975,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002148545,"about_ca_topic_score_gemma":0.0000527072,"domain_scores_codex":[0.9987231,0.00003405166,0.0002742607,0.0004355256,0.000209415,0.0003235799],"domain_scores_gemma":[0.9991093,0.0001931465,0.0001936787,0.0003458905,0.00006694461,0.00009100488],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002573893,0.00004920567,0.00002115573,0.0002154994,0.0000149069,0.000001679046,0.002793928,0.0009877875,0.005823479,0.0002195491,0.00001128729,0.9898358],"study_design_scores_gemma":[0.001064341,0.0001319688,0.00008262472,0.0002831789,0.00005813342,0.00004304103,0.001775335,0.9517795,0.04296726,0.001282358,0.0001315341,0.0004006962],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008386606,0.002279979,0.9881622,0.000329905,0.0001857396,0.0002430367,0.000003049397,0.0001731572,0.0002363561],"genre_scores_gemma":[0.9180419,0.00001505095,0.08118219,0.0004780634,0.0001340466,0.00003205657,0.000005416641,0.00002052698,0.00009078223],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9894351,"threshold_uncertainty_score":0.7328158,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4372260310","doi":"10.1109/icassp49357.2023.10095969","title":"Large-Scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation","year":2023,"lang":"en","type":"article","venue":"","topic":"Music and Audio Processing","field":"Computer Science","cited_by":385,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Computer science; Audio mining; Natural language processing; Pipeline (software); Speech recognition; Artificial intelligence; Encoder; Construct (python library); Feature (linguistics); Natural language; Language model; Speech processing; Acoustic model; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.00899152659473625,"gpt":0.2488691384566329,"spread":0.2398776118618966,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002128643,0.00009570768,0.00009704208,0.00009937483,0.0001796262,0.0001600126,0.0001195498,0.00004147024,0.00002065961],"category_scores_gemma":[0.00001457221,0.00007188765,0.00001303106,0.0005636938,0.00001697599,0.0003849753,0.0001024597,0.00008545841,0.00003218816],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001790899,"about_ca_system_score_gemma":0.00002472211,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007512777,"about_ca_topic_score_gemma":0.00005019678,"domain_scores_codex":[0.9991775,0.00002332112,0.00007727752,0.0003047683,0.0001990515,0.0002180747],"domain_scores_gemma":[0.9996723,0.0000378047,0.0000450384,0.0001219782,0.00004410498,0.00007878541],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001145215,0.00008736847,0.009606932,0.0001560318,0.00006616784,0.000108142,0.2051406,0.0008068438,0.0810886,0.006107971,0.02789843,0.6688184],"study_design_scores_gemma":[0.00530858,0.0007514471,0.2856543,0.0008579382,0.000061183,0.0001023615,0.03470401,0.6352397,0.02938636,0.001401277,0.005160846,0.001372013],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3496008,0.00003837464,0.6457483,0.002010686,0.00007281828,0.0001329394,0.000001903033,0.0002616458,0.002132552],"genre_scores_gemma":[0.943721,0.000007769921,0.05212638,0.001479199,0.00007328064,0.00001523879,0.00001112398,0.000008722618,0.002557296],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6674464,"threshold_uncertainty_score":0.2931494,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2008066450","doi":"10.1121/1.3642604","title":"The Timbre Toolbox: Extracting audio descriptors from musical signals","year":2011,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Music and Audio Processing","field":"Computer Science","cited_by":379,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; Centre for Interdisciplinary Research in Music Media and Technology","funders":"","keywords":"Timbre; Computer science; Music information retrieval; Speech recognition; Audio signal; Toolbox; Audio analyzer; Pattern recognition (psychology); Set (abstract data type); Audio signal processing; Artificial intelligence; Speech coding; Musical","retraction":null,"screen_n_in":null,"score":{"opus":0.03284561586498905,"gpt":0.2422844526021924,"spread":0.2094388367372033,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001184718,0.0001523856,0.0002862159,0.000009380905,0.0006661999,0.00009551962,0.002494629,0.00006593159,0.00006365452],"category_scores_gemma":[0.0004037816,0.00006456326,0.0004358848,0.0003157526,0.0007647228,0.0003024855,0.0004171072,0.0006786234,0.00000740519],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000448158,"about_ca_system_score_gemma":0.0001712883,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007354658,"about_ca_topic_score_gemma":3.899439e-7,"domain_scores_codex":[0.9980885,0.0002471981,0.000539744,0.0001349852,0.0006596001,0.0003299967],"domain_scores_gemma":[0.9968274,0.001470821,0.000876774,0.0005105459,0.0002071723,0.0001073188],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002251496,0.0004732216,0.0003104162,0.00004311224,0.0007756625,0.00001150049,0.03273303,0.002147618,0.09262025,0.0002622628,0.2682725,0.6021252],"study_design_scores_gemma":[0.001653452,0.001104348,0.01467093,0.0009055586,0.001229873,0.0004358944,0.02062275,0.8204962,0.02656548,0.04788607,0.06333013,0.001099315],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01631046,0.0005481103,0.9736293,0.008186058,0.000517116,0.00007246354,0.000001924773,0.00001868561,0.0007158572],"genre_scores_gemma":[0.818741,0.0001464418,0.1760552,0.004516048,0.0004137477,7.780812e-7,6.551832e-8,0.00001203871,0.0001146116],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8183486,"threshold_uncertainty_score":0.5123938,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2126203737","doi":"10.1109/asru.2009.5372931","title":"Unsupervised spoken keyword spotting via segmental DTW on Gaussian posteriorgrams","year":2009,"lang":"en","type":"article","venue":"","topic":"Music and Audio Processing","field":"Computer Science","cited_by":338,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Keyword spotting; Computer science; Dynamic time warping; Speech recognition; Artificial intelligence; TIMIT; Ranking (information retrieval); Gaussian; Spotting; Viterbi algorithm; Gaussian process; Natural language processing; Pattern recognition (psychology); Hidden Markov model","retraction":null,"screen_n_in":null,"score":{"opus":0.01218157054232683,"gpt":0.2340915820983202,"spread":0.2219100115559933,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001670065,0.000184802,0.0001651667,0.00008169989,0.00021441,0.0003258905,0.000638171,0.00005628914,0.0001305653],"category_scores_gemma":[0.000006820252,0.0001498042,0.00006796893,0.0003141466,0.0000225932,0.0004964336,0.0001102308,0.0001350557,0.0002016247],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004450377,"about_ca_system_score_gemma":0.00003393682,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001618556,"about_ca_topic_score_gemma":0.000001807296,"domain_scores_codex":[0.9986269,0.000028489,0.0002266182,0.0004338815,0.0002942743,0.0003898292],"domain_scores_gemma":[0.9993519,0.00002099375,0.00006794822,0.0003992222,0.00002394937,0.0001360146],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001278925,0.0001069385,0.0004038832,0.000009978906,0.000006526937,0.00005350443,0.0008430248,0.00001508661,0.0173653,0.004660528,0.001039146,0.9754833],"study_design_scores_gemma":[0.009610311,0.005020835,0.1884599,0.001783066,0.00007341475,0.0008897599,0.001122259,0.3188379,0.387555,0.03551821,0.0446414,0.006487994],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3724309,0.00007353419,0.4707178,0.01434033,0.0005382737,0.0002702502,9.033558e-7,0.0008140575,0.1408139],"genre_scores_gemma":[0.945388,0.000002239316,0.04043755,0.01289868,0.0001329272,0.000001685776,0.000002698987,0.000008038758,0.001128185],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9689953,"threshold_uncertainty_score":0.6108839,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2126410803","doi":"10.1109/icme.2001.1237829","title":"A music similarity function based on signal analysis","year":2001,"lang":"en","type":"article","venue":"","topic":"Music and Audio Processing","field":"Computer Science","cited_by":313,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"PQ Corporation (Canada)","funders":"","keywords":"Similarity (geometry); Computer science; Function (biology); Speech recognition; SIGNAL (programming language); Pattern recognition (psychology); Artificial intelligence; Image (mathematics)","retraction":null,"screen_n_in":null,"score":{"opus":0.0274103455880917,"gpt":0.2320162935495742,"spread":0.2046059479614825,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000184744,0.00007841664,0.0001040768,0.0001857098,0.0001289921,0.0001364409,0.0002347359,0.00003423072,0.001049086],"category_scores_gemma":[0.000007676326,0.00006285327,0.00009285557,0.001379675,0.00001355605,0.000228248,0.00003574169,0.00007301906,0.00005420392],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001931062,"about_ca_system_score_gemma":0.00003814466,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002192688,"about_ca_topic_score_gemma":0.00003059865,"domain_scores_codex":[0.9991975,0.00002963995,0.0001039321,0.0002808277,0.000231923,0.0001561564],"domain_scores_gemma":[0.9995306,0.00004322144,0.00004080455,0.0002849161,0.00004243722,0.00005801116],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009717607,0.0006971667,0.04384089,0.00002848298,0.0003147347,0.00009078539,0.0003731275,0.09822538,0.001306866,0.02124252,0.02485319,0.8089297],"study_design_scores_gemma":[0.0001536894,0.0000564831,0.0144617,0.000004009288,0.0000488527,7.438767e-7,0.000004682471,0.979086,0.0003148947,0.0009579178,0.004805652,0.0001054125],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009675589,0.000006477968,0.9526582,0.001277484,0.0000705756,0.00002901159,1.701366e-7,0.0001534328,0.03612906],"genre_scores_gemma":[0.9777236,4.022384e-7,0.01082506,0.01075661,0.00005774873,0.000002763513,0.000002034038,0.000002335036,0.0006294267],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.968048,"threshold_uncertainty_score":0.9998641,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2295991281","doi":"10.5281/zenodo.1414969","title":"Learning Features From Music Audio With Deep Belief Networks.","year":2010,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Music and Audio Processing","field":"Computer Science","cited_by":259,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Feature extraction; Artificial intelligence; Support vector machine; Classifier (UML); Deep belief network; Mel-frequency cepstrum; Task (project management); Speech recognition; Pattern recognition (psychology); Audio signal processing; Frame (networking); Deep learning; Audio signal; Speech coding","retraction":null,"screen_n_in":null,"score":{"opus":0.01368831642541261,"gpt":0.2031335805673518,"spread":0.1894452641419392,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0003946626,0.0001532746,0.0001356912,0.0001190728,0.00249371,0.001806825,0.001614556,0.00007525062,0.003314088],"category_scores_gemma":[0.0002144634,0.0001368313,0.00003399522,0.0006156759,0.0001401291,0.0005499851,0.001200031,0.0007343047,0.001126762],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003218088,"about_ca_system_score_gemma":0.000005826032,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002246832,"about_ca_topic_score_gemma":0.00000342201,"domain_scores_codex":[0.998417,0.0001522655,0.0001562295,0.0005183807,0.0003630621,0.0003930868],"domain_scores_gemma":[0.9988255,0.00003437584,0.0001207111,0.0005174699,0.0003228679,0.000179063],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003557821,0.00009647737,0.00003483363,0.00002218435,0.0000497896,0.00004700385,0.003927227,0.002028492,0.006887815,0.008481061,0.07758646,0.9008031],"study_design_scores_gemma":[0.0005267927,0.0002173773,0.002771506,0.00004179241,0.0000115775,0.0001399657,0.0001428066,0.02352887,0.0006477369,0.0004275259,0.9712183,0.0003257419],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04578152,0.0001744386,0.8571298,0.00166074,0.0003707626,0.0002862224,0.00000978926,0.002260761,0.09232595],"genre_scores_gemma":[0.9864736,0.00002091976,0.01072753,0.0006263815,0.0004448052,3.66657e-8,0.0002371603,0.0006415525,0.0008280207],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9406921,"threshold_uncertainty_score":0.999651,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2037202300","doi":"10.1353/lan.2011.0016","title":"The Surfeit of the Stimulus: Analytic Biases Filter Lexical Statistics in Turkish Laryngeal Alternations","year":2011,"lang":"en","type":"article","venue":"Language","topic":"Music and Audio Processing","field":"Computer Science","cited_by":224,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Phonotactics; Lexicon; Turkish; Linguistics; Vowel harmony; Alternation (linguistics); Psychology; Phrase; Phonology; Computer science; Natural language processing","retraction":null,"screen_n_in":null,"score":{"opus":0.036742338371428,"gpt":0.2724039918726861,"spread":0.2356616535012581,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001719498,0.00005594958,0.00007460446,0.00002668831,0.00008297973,0.00004789557,0.0006195189,0.00001915021,0.00004706677],"category_scores_gemma":[0.0001450821,0.00003075756,0.00002851937,0.0002122857,0.00007702377,0.0001027097,0.0001568052,0.00009331354,0.000005462743],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000105529,"about_ca_system_score_gemma":0.00004330902,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003596086,"about_ca_topic_score_gemma":0.0006248003,"domain_scores_codex":[0.9993799,0.00005363337,0.0001505689,0.0001151791,0.0001603269,0.000140401],"domain_scores_gemma":[0.9993507,0.0002057235,0.00006919847,0.0003227671,0.00002827643,0.00002334927],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00006456085,0.001063159,0.1151946,0.0002207283,0.000200241,0.0006035739,0.1499164,0.00129251,0.004846499,0.2767287,0.03984748,0.4100216],"study_design_scores_gemma":[0.001751971,0.0002065574,0.5570686,0.0004984152,0.00007856215,0.00005382477,0.002489197,0.3548251,0.04937948,0.02839094,0.004422707,0.0008347079],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6848574,0.0007098683,0.3015816,0.001186406,0.0005383092,0.0002090863,0.0000592455,0.00005611228,0.010802],"genre_scores_gemma":[0.9929959,0.00000447032,0.005969419,0.0004180616,0.00003174565,0.000002705197,0.000001447837,0.000003590266,0.0005726827],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.441874,"threshold_uncertainty_score":0.1254257,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2162124943","doi":"","title":"Automatic Generation of Social Tags for Music Recommendation","year":2007,"lang":"en","type":"article","venue":"neural information processing systems","topic":"Music and Audio Processing","field":"Computer Science","cited_by":184,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; CMC Microsystems (Canada)","funders":"","keywords":"Recommender system; Computer science; Information retrieval; Set (abstract data type); Baseline (sea); World Wide Web; Resource (disambiguation); Space (punctuation); Social web; Component (thermodynamics); Social media","retraction":null,"screen_n_in":null,"score":{"opus":0.06320323338863898,"gpt":0.294099101272341,"spread":0.230895867883702,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008937056,0.0001118661,0.0001685806,0.0001946566,0.0003506072,0.0004276312,0.000233123,0.00007871951,0.000006745347],"category_scores_gemma":[0.00005605614,0.000102881,0.00004540184,0.0003854236,0.0000229113,0.00445299,0.00003292842,0.00006461768,0.000005912831],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005741855,"about_ca_system_score_gemma":0.00007033005,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006955217,"about_ca_topic_score_gemma":0.000001663368,"domain_scores_codex":[0.998639,0.00002407027,0.0007668139,0.0001201699,0.0002412377,0.0002086494],"domain_scores_gemma":[0.9986271,0.00004129551,0.0007965032,0.0001000889,0.0003980815,0.00003690423],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000441552,0.00001380187,0.00001955559,0.0008027273,0.000004614978,8.116378e-8,0.005054919,0.0002532348,0.002103581,0.004461475,0.003582013,0.9836996],"study_design_scores_gemma":[0.0003432028,0.00003758072,0.000268636,0.00005249053,0.000006043378,0.00001063856,0.0003016938,0.9861856,0.003630516,0.00008066795,0.00895167,0.0001312938],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05010068,0.00003010116,0.946924,0.0004890517,0.0007533237,0.0003284406,0.000003336189,0.0001730332,0.001198004],"genre_scores_gemma":[0.9887086,3.151767e-7,0.01032235,0.0005552922,0.0002702517,0.00003058556,0.00006606636,0.000005655536,0.00004091623],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9859324,"threshold_uncertainty_score":0.4195366,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2106339924","doi":"10.1109/icassp.2000.859336","title":"Speech/music discrimination for multimedia applications","year":2002,"lang":"en","type":"article","venue":"","topic":"Music and Audio Processing","field":"Computer Science","cited_by":181,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Multimedia; Speech recognition","retraction":null,"screen_n_in":null,"score":{"opus":0.05160292578650467,"gpt":0.2628288248486828,"spread":0.2112258990621781,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006145924,0.00005106188,0.00004898889,0.00003809997,0.0001168309,0.00008743791,0.0002759786,0.00002172488,0.0001182248],"category_scores_gemma":[0.00001387278,0.00004288919,0.00002692062,0.0001536929,0.00001625648,0.0003051609,0.00004117129,0.00002579777,0.0001164132],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000111709,"about_ca_system_score_gemma":0.00000599956,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002508357,"about_ca_topic_score_gemma":0.000004351224,"domain_scores_codex":[0.9995171,0.000004261858,0.00008967368,0.000182467,0.00008820387,0.000118315],"domain_scores_gemma":[0.9996358,0.00004641227,0.00003484383,0.0001968201,0.00004879801,0.00003735412],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[1.32417e-7,0.0000340708,0.000008915155,0.00001261465,0.0000014592,1.696522e-7,0.0003476788,0.000003151053,0.0005629144,0.03019019,0.01543389,0.9534048],"study_design_scores_gemma":[0.0003142622,0.00002119786,0.0002614703,0.000009450681,0.000006238805,0.000005423009,0.00003733832,0.8239626,0.006751985,0.01360883,0.154839,0.0001822524],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001606043,0.00005794158,0.9748019,0.002456163,0.0000788137,0.0002129338,7.579707e-7,0.0001358529,0.02209504],"genre_scores_gemma":[0.2376165,0.000005650815,0.7530274,0.001841134,0.0001916752,0.0001835529,0.00000348349,0.000006038712,0.007124595],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9532226,"threshold_uncertainty_score":0.174897,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1801907668","doi":"10.5281/zenodo.1416157","title":"Automatic Genre Classification Using Large High-Level Musical Feature Sets.","year":2004,"lang":"en","type":"article","venue":"","topic":"Music and Audio Processing","field":"Computer Science","cited_by":153,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Computer science; MIDI; Artificial intelligence; Hierarchy; Pattern recognition (psychology); Feature (linguistics); Classifier (UML); Music information retrieval; Feature extraction; Embedding; Rhythm; Speech recognition; Musical; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.0597030218101955,"gpt":0.2884801686068033,"spread":0.2287771467966078,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001772901,0.0001347295,0.000140356,0.00007075867,0.0002487116,0.0002353373,0.0004712081,0.0001041284,0.00006138062],"category_scores_gemma":[0.00002381362,0.0001093748,0.00004724797,0.0004026454,0.00002731682,0.0005881595,0.0001508344,0.0001550246,0.00008204743],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009796811,"about_ca_system_score_gemma":0.0001740221,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001830096,"about_ca_topic_score_gemma":0.000008698731,"domain_scores_codex":[0.9988567,0.00002453463,0.0001642308,0.0003653213,0.000281091,0.000308089],"domain_scores_gemma":[0.9993323,0.0000189402,0.00008880104,0.0004055284,0.00006230099,0.0000921107],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003526055,0.0004430599,0.0002865212,0.0001865179,0.00004489323,0.00006897764,0.003888448,0.0007256489,0.0325001,0.6653128,0.008984203,0.2875552],"study_design_scores_gemma":[0.001348979,0.00004104066,0.03911358,0.0001612597,0.00002356527,0.0001187654,0.0001823913,0.9300309,0.005820808,0.01976623,0.002788254,0.000604252],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.197482,0.00003251564,0.7964339,0.004416352,0.0002386669,0.00008014563,0.000002103005,0.0002910586,0.001023288],"genre_scores_gemma":[0.657509,7.364493e-7,0.3402886,0.001909112,0.00006651963,0.000002639508,0.00000370764,0.000006856632,0.0002128894],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9293053,"threshold_uncertainty_score":0.4460174,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2395935897","doi":"10.5281/zenodo.1418318","title":"Audio Chord Recognition With Recurrent Neural Networks.","year":2013,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Music and Audio Processing","field":"Computer Science","cited_by":145,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Chord (peer-to-peer); Artificial neural network; Recurrent neural network; Speech recognition; Artificial intelligence; Time delay neural network; Pattern recognition (psychology); Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.03494166430596236,"gpt":0.2214052918098112,"spread":0.1864636275038488,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0002829692,0.0001251446,0.0001055699,0.0001165765,0.001400902,0.001747638,0.001032813,0.00003830735,0.003672218],"category_scores_gemma":[0.0000923316,0.0001097111,0.0000282944,0.0006151746,0.00008633136,0.0009381854,0.0007381739,0.0002335261,0.003348702],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006083059,"about_ca_system_score_gemma":0.000002987449,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009786702,"about_ca_topic_score_gemma":1.449338e-7,"domain_scores_codex":[0.9986097,0.000163824,0.0001729923,0.0004071279,0.0002893364,0.0003569801],"domain_scores_gemma":[0.9988467,0.00001437579,0.0001056395,0.0003725524,0.0004988284,0.0001619526],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000008718527,0.00004848244,0.000002687321,0.00001894355,0.00001079323,0.000005234871,0.0003625277,0.0001354317,0.0002570704,0.000546532,0.1016907,0.8969129],"study_design_scores_gemma":[0.0008896794,0.0006145696,0.001820706,0.0001268546,0.00001398035,0.0003103832,0.0001267914,0.1809085,0.0003592088,0.000907667,0.813369,0.0005526852],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04020123,0.0001535417,0.8699269,0.005015795,0.0003317482,0.0007778039,0.00001448054,0.002198899,0.0813796],"genre_scores_gemma":[0.9904073,0.00005297239,0.006780494,0.0009901932,0.0003021125,1.768651e-7,0.0003559387,0.0006504651,0.0004602843],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9502062,"threshold_uncertainty_score":0.9998991,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1981219830","doi":"10.1145/2601097.2601110","title":"Exploratory font selection using crowdsourced attributes","year":2014,"lang":"en","type":"article","venue":"ACM Transactions on Graphics","topic":"Music and Audio Processing","field":"Computer Science","cited_by":144,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research; Adobe Systems","keywords":"Font; Computer science; Selection (genetic algorithm); Similarity (geometry); Crowdsourcing; Information retrieval; Artificial intelligence; Metric (unit); Human–computer interaction; Natural language processing; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.04275869709030147,"gpt":0.2576552930373095,"spread":0.214896595947008,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003079686,0.0001554812,0.0001431467,0.0002579167,0.0006307342,0.0001630662,0.0005393179,0.0001003378,0.00001516308],"category_scores_gemma":[0.0000368196,0.0001543439,0.0001047214,0.0009532892,0.00005618131,0.00058206,0.00001131736,0.0002783361,0.00001548564],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003831651,"about_ca_system_score_gemma":0.00006129398,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001418485,"about_ca_topic_score_gemma":0.00002267696,"domain_scores_codex":[0.9988387,0.000087564,0.0001950987,0.0003542373,0.0002571233,0.0002673273],"domain_scores_gemma":[0.9990454,0.000133423,0.00008102339,0.0005305646,0.0001151745,0.00009444026],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007973972,0.001193658,0.002397233,0.0002714111,0.0003304001,0.00001220671,0.005854078,0.06320436,0.06486349,0.05626344,0.002311752,0.8032182],"study_design_scores_gemma":[0.001745706,0.0005750378,0.002250794,0.0002783295,0.0001311921,0.00009624332,0.0001703903,0.7681551,0.1306838,0.05968716,0.03474307,0.001483119],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03904437,0.00003404117,0.9589297,0.001180217,0.000337231,0.00007086735,0.000001381844,0.0003047502,0.00009742511],"genre_scores_gemma":[0.9446362,0.00001629961,0.05354569,0.001662799,0.00007269058,0.00001267641,9.373757e-7,0.00001534779,0.00003739031],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9055918,"threshold_uncertainty_score":0.6293963,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3109961563","doi":"10.3390/math8122133","title":"CLSTM: Deep Feature-Based Speech Emotion Recognition Using the Hierarchical ConvLSTM Network","year":2020,"lang":"en","type":"article","venue":"Mathematics","topic":"Music and Audio Processing","field":"Computer Science","cited_by":142,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Computer science; Artificial intelligence; Deep learning; Feature (linguistics); Block (permutation group theory); Machine learning; State (computer science); Pattern recognition (psychology)","retraction":null,"screen_n_in":null,"score":{"opus":0.06164806315143793,"gpt":0.2596169155525182,"spread":0.1979688524010803,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003164405,0.0001268636,0.0001588723,0.00001955491,0.0002591203,0.0002453981,0.0004369494,0.00007027368,0.00003356866],"category_scores_gemma":[0.0001108475,0.00008965792,0.00006485729,0.0004172901,0.0000547287,0.0001629765,0.000107992,0.0002413868,0.00004510652],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002194672,"about_ca_system_score_gemma":0.00005893479,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000112381,"about_ca_topic_score_gemma":8.293096e-7,"domain_scores_codex":[0.9990176,0.00006896313,0.0002041828,0.0001919045,0.0002799627,0.0002374133],"domain_scores_gemma":[0.9992786,0.0001634967,0.0001484344,0.0002618077,0.00006581564,0.00008183312],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005668711,0.0005858663,0.0004188622,0.002163943,0.0001570305,0.0001450804,0.03619998,0.0214342,0.004283445,0.03948618,0.04959319,0.8454756],"study_design_scores_gemma":[0.0001709218,0.00002682577,0.00002056784,0.0001065937,0.0000179121,0.00002125291,0.00006161749,0.9640893,0.001166016,0.03324246,0.0009419264,0.0001345718],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01291196,0.00005609314,0.9773026,0.008402321,0.0001675796,0.0001612695,8.80754e-7,0.0001452281,0.0008520624],"genre_scores_gemma":[0.1650751,0.00000289095,0.8253241,0.008965629,0.0005820883,0.000004778953,0.000006493106,0.00001773002,0.00002125585],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9426551,"threshold_uncertainty_score":0.3656144,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2090879738","doi":"10.1007/s00530-006-0032-2","title":"Support vector machine active learning for music retrieval","year":2006,"lang":"en","type":"article","venue":"Multimedia Systems","topic":"Music and Audio Processing","field":"Computer Science","cited_by":133,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"National Science Foundation","keywords":"Computer science; Similarity (geometry); Music information retrieval; Artificial intelligence; Digital audio; Support vector machine; Scheme (mathematics); Active learning (machine learning); Machine learning; Style (visual arts); Information retrieval; Speech recognition; Pattern recognition (psychology); Audio signal; Musical; Mathematics; Speech coding","retraction":null,"screen_n_in":null,"score":{"opus":0.01953620587089179,"gpt":0.2414020996941554,"spread":0.2218658938232636,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003838712,0.0001764731,0.0002676998,0.000095319,0.0002353907,0.0002164017,0.0004297278,0.0000931054,0.00002361475],"category_scores_gemma":[0.0001110379,0.000156078,0.00008506284,0.000269193,0.00003662274,0.0003679062,0.00008819599,0.000171739,0.00007835664],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007635043,"about_ca_system_score_gemma":0.00008358205,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000208563,"about_ca_topic_score_gemma":0.00001092917,"domain_scores_codex":[0.9984849,0.00006519132,0.0003143394,0.0004285136,0.0003119043,0.0003951607],"domain_scores_gemma":[0.999079,0.0002260528,0.0002188329,0.000261419,0.0001281546,0.0000865288],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000383957,0.0006977546,0.009134579,0.001777167,0.0002630361,0.000226042,0.01668682,0.006702133,0.1192067,0.005629761,0.1004647,0.7388272],"study_design_scores_gemma":[0.001024727,0.0001104812,0.002079518,0.00006173521,0.00001209459,0.00002694421,0.00007177843,0.9326163,0.006404314,0.00008060555,0.05720702,0.0003045161],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0155992,0.0004161561,0.9752964,0.0003865201,0.003192015,0.0007481106,0.00001581119,0.0005015367,0.003844277],"genre_scores_gemma":[0.974735,0.000001262521,0.02018662,0.000092202,0.001060098,0.00004545664,0.00004342385,0.00002434751,0.003811606],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9591358,"threshold_uncertainty_score":0.6364677,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2119662931","doi":"10.1109/tasl.2011.2118753","title":"Time–Frequency Matrix Feature Extraction and Classification of Environmental Audio Signals","year":2011,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Music and Audio Processing","field":"Computer Science","cited_by":125,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Mel-frequency cepstrum; Computer science; Feature extraction; Audio signal; Speech recognition; Pattern recognition (psychology); Artificial intelligence; Audio signal processing; Support vector machine; Feature (linguistics); Time–frequency analysis; Speech coding; Computer vision","retraction":null,"screen_n_in":null,"score":{"opus":0.01521591215504704,"gpt":0.247987920621622,"spread":0.232772008466575,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002314945,0.0001910333,0.0002061027,0.0001705914,0.0002676777,0.00009469553,0.0001749949,0.0001256577,0.0001292029],"category_scores_gemma":[0.000004654387,0.0001749397,0.00004787759,0.0002247905,0.0001425961,0.0008461994,0.000004200806,0.0002431045,0.00001615907],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003400343,"about_ca_system_score_gemma":0.00004895637,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001271832,"about_ca_topic_score_gemma":0.000005016136,"domain_scores_codex":[0.9988614,0.0000506785,0.0002343023,0.0004101442,0.0002266861,0.0002168125],"domain_scores_gemma":[0.9994111,0.00003703169,0.0002091829,0.0002122147,0.00002716508,0.0001032868],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000189584,0.0001121679,0.00004210311,0.00009535964,0.00001406238,0.00001354234,0.003892273,0.000006751567,0.405346,0.00001427125,0.00003119474,0.5904133],"study_design_scores_gemma":[0.001117524,0.0003457776,0.007774055,0.0004997864,0.0001489393,0.0005562633,0.001948194,0.03076323,0.9551808,0.0006656835,0.0001685036,0.0008312115],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2207639,0.002497328,0.7748271,0.0001906782,0.00009058243,0.0001636305,0.00001293885,0.0001291584,0.001324737],"genre_scores_gemma":[0.947206,0.0001076818,0.05171456,0.0001134879,0.00003292619,0.00001030559,0.0000018406,0.00001529799,0.0007978511],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7264422,"threshold_uncertainty_score":0.7133833,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W56995320","doi":"10.5281/zenodo.1417417","title":"Musical Genre Classification: Is It Worth Pursuing And How Can It Be Improved?","year":2006,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Music and Audio Processing","field":"Computer Science","cited_by":121,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Subjectivity; Similarity (geometry); Musical; Genre analysis; Discipline; Data science; Music information retrieval; Musicology; Linguistics; Artificial intelligence; Natural language processing; Epistemology; Sociology; Social science; Pedagogy; Literature","retraction":null,"screen_n_in":null,"score":{"opus":0.05322688878533093,"gpt":0.2470623955776686,"spread":0.1938355067923377,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004086031,0.000138254,0.0001218656,0.0001331993,0.001766473,0.002426343,0.001037444,0.00005967205,0.001085431],"category_scores_gemma":[0.0001271659,0.0001400588,0.00003353111,0.0005509707,0.0001463883,0.0005104726,0.001048903,0.0002152749,0.0002735144],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007445826,"about_ca_system_score_gemma":0.000009002633,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001816904,"about_ca_topic_score_gemma":0.000001790395,"domain_scores_codex":[0.9984637,0.0001147218,0.0001686806,0.0005562776,0.000344452,0.0003520993],"domain_scores_gemma":[0.9989159,0.00001843697,0.0001150089,0.0004716863,0.0003297855,0.0001492284],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000008211302,0.00007430978,0.00001240414,0.00006125976,0.00001630504,0.0000154308,0.002435555,0.000006812354,0.01630828,0.01379326,0.6839852,0.283283],"study_design_scores_gemma":[0.0002700382,0.00006510213,0.001176408,0.00002414423,0.000006440314,0.00008200764,0.000308728,0.009338679,0.0006955807,0.0002131192,0.9876258,0.0001939509],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.06332816,0.0003170253,0.3366413,0.3531201,0.000402172,0.0009888033,0.0001492636,0.002342023,0.2427111],"genre_scores_gemma":[0.9864661,0.00003526158,0.004126602,0.003453135,0.0003076157,6.992215e-8,0.0001799766,0.000422003,0.005009282],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9231379,"threshold_uncertainty_score":0.9998277,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4213366994","doi":"10.1109/lsp.2022.3150258","title":"CNN-RNN and Data Augmentation Using Deep Convolutional Generative Adversarial Network for Environmental Sound Classification","year":2022,"lang":"en","type":"article","venue":"IEEE Signal Processing Letters","topic":"Music and Audio Processing","field":"Computer Science","cited_by":118,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Kids Brain Health Network","keywords":"Computer science; Artificial intelligence; Deep learning; Convolutional neural network; Recurrent neural network; Normalization (sociology); Transfer of learning; Feature extraction; Pattern recognition (psychology); Generative adversarial network; Feature (linguistics); Feature learning; Machine learning; Spectrogram; Generative grammar; Artificial neural network","retraction":null,"screen_n_in":null,"score":{"opus":0.07475645323796545,"gpt":0.2863002993979042,"spread":0.2115438461599388,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.000492412,0.0001627205,0.0001398406,0.00006240523,0.00162839,0.0003180867,0.0005701435,0.00003353046,0.00002333344],"category_scores_gemma":[0.00000567551,0.0001820519,0.00002987746,0.0001797277,0.0001403621,0.001200603,0.0002717354,0.0001318653,0.000001296712],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002133641,"about_ca_system_score_gemma":0.0001290599,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005295794,"about_ca_topic_score_gemma":0.000001232818,"domain_scores_codex":[0.9982762,0.0001038821,0.0002654631,0.0006699229,0.0003784431,0.0003060705],"domain_scores_gemma":[0.9993305,0.00007865141,0.0002807637,0.0002286026,0.00001934093,0.00006219777],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001791481,0.0001423604,0.001343477,0.0001128913,0.00009693112,0.00001231265,0.002930125,0.3739235,0.4460857,0.000813145,0.009769082,0.1645914],"study_design_scores_gemma":[0.0006585901,0.00003820235,0.000322695,0.00001423605,0.00003354566,0.00002541715,0.0001703009,0.9958134,0.0004506659,0.001237974,0.0009981397,0.0002367942],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06995725,0.0003278333,0.9275495,0.001378899,0.0004416506,0.0002419965,0.00003754456,0.00004877119,0.00001649804],"genre_scores_gemma":[0.8919743,0.000001698028,0.1025597,0.004400355,0.0007718157,0.00004536475,0.0002123086,0.00001638541,0.00001804458],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8249898,"threshold_uncertainty_score":0.9996713,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2296557957","doi":"10.5281/zenodo.1417546","title":"An Expert Ground Truth Set For Audio Chord Recognition And Music Analysis.","year":2011,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Music and Audio Processing","field":"Computer Science","cited_by":114,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Chord (peer-to-peer); Computer science; Speech recognition; Music information retrieval; Phrase; USable; Ground truth; Melody; Natural language processing; Scope (computer science); Chart; Artificial intelligence; Information retrieval; Musical; Multimedia; Database; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.1466874330866852,"gpt":0.2704199464206599,"spread":0.1237325133339746,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005961742,0.0001200649,0.0001470518,0.0002717122,0.00139204,0.0009242023,0.000851377,0.00004913844,0.001387194],"category_scores_gemma":[0.000152667,0.0001209746,0.00005084654,0.0007178246,0.00009178231,0.0009078007,0.000439499,0.0001032602,0.0003232906],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000423791,"about_ca_system_score_gemma":0.000004384148,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001472221,"about_ca_topic_score_gemma":6.345621e-7,"domain_scores_codex":[0.9986754,0.0001386779,0.0001910944,0.0005117642,0.000199893,0.0002831547],"domain_scores_gemma":[0.998952,0.00001895132,0.0001061491,0.0004123733,0.0003404695,0.0001700483],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000777697,0.0002247478,0.000007105296,0.00007602528,0.000178901,0.000008863708,0.02099297,0.00002259407,0.004835469,0.008880833,0.03727517,0.9274195],"study_design_scores_gemma":[0.002794201,0.001749767,0.005768767,0.0001019541,0.000301962,0.0001925587,0.001848736,0.1411418,0.0064212,0.02657746,0.8115438,0.001557895],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06282715,0.0000758088,0.9125164,0.0002603577,0.0001035461,0.000345146,0.00008884193,0.0008257676,0.02295705],"genre_scores_gemma":[0.9706468,0.00004428123,0.02719583,0.0006950488,0.0001437983,1.790694e-7,0.0007552426,0.0003617585,0.0001570567],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9258617,"threshold_uncertainty_score":0.999908,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2064082346","doi":"10.1109/icassp.2010.5495651","title":"Phone recognition using Restricted Boltzmann Machines","year":2010,"lang":"en","type":"article","venue":"","topic":"Music and Audio Processing","field":"Computer Science","cited_by":108,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"TIMIT; Hidden Markov model; Computer science; Phone; Conditional independence; Boltzmann machine; Independence (probability theory); Set (abstract data type); Speech recognition; Generative model; Artificial intelligence; Restricted Boltzmann machine; Markov model; Generative grammar; Machine learning; Pattern recognition (psychology); Markov chain; Artificial neural network; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.0326160043459392,"gpt":0.2635966483133135,"spread":0.2309806439673743,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009072199,0.00007353049,0.00006988824,0.00007202879,0.0001433825,0.0001683779,0.0002746337,0.00004752217,0.0001538496],"category_scores_gemma":[0.00004276345,0.00006047876,0.00002355931,0.0003393973,0.00002216795,0.0005147915,0.00009268303,0.0001472269,0.00009021538],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005554281,"about_ca_system_score_gemma":0.00004400952,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008337165,"about_ca_topic_score_gemma":0.00002115843,"domain_scores_codex":[0.9993867,0.00001362649,0.0001177128,0.0002052417,0.0001240344,0.0001527394],"domain_scores_gemma":[0.999584,0.00002413024,0.0000544807,0.0002166521,0.00006690974,0.00005380743],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002904769,0.00004866575,0.0004448002,0.00001337916,0.000005611818,0.00001178472,0.0002160486,0.000007834833,0.2761,0.001605725,0.003576546,0.7179667],"study_design_scores_gemma":[0.0009051968,0.00004351475,0.008438568,0.0000655102,0.00001719698,0.0002185857,0.00002398074,0.8227779,0.1178112,0.03710332,0.01181411,0.0007809811],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4544834,0.00001496354,0.5321239,0.0006160265,0.0006091491,0.0000396005,5.12375e-7,0.0002201725,0.01189232],"genre_scores_gemma":[0.6130918,0.000002232125,0.3852795,0.0010404,0.0002197278,0.0000017827,0.000002767977,0.000005942432,0.0003558118],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8227701,"threshold_uncertainty_score":0.2466252,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W179394430","doi":"","title":"Disambiguating Music Emotion Using Software Agents.","year":2004,"lang":"en","type":"article","venue":"","topic":"Music and Audio Processing","field":"Computer Science","cited_by":105,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Lyrics; Computer science; Heuristics; Active listening; Ambiguity; Metadata; Focus (optics); Software; Annotation; Artificial intelligence; Natural language processing; Cognitive psychology; Human–computer interaction; Psychology; World Wide Web; Communication","retraction":null,"screen_n_in":null,"score":{"opus":0.0664556378404012,"gpt":0.2801708730104419,"spread":0.2137152351700407,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001182235,0.00008716064,0.00008001197,0.00004770701,0.0002315125,0.0001871503,0.0002975363,0.00003160723,0.00005677979],"category_scores_gemma":[0.00003842974,0.00007685625,0.00003759126,0.0002919445,0.00002014504,0.0006831235,0.0001508122,0.00006509041,0.00004060784],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006390983,"about_ca_system_score_gemma":0.00007275689,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007677493,"about_ca_topic_score_gemma":0.000005560085,"domain_scores_codex":[0.9992002,0.00001201871,0.0001401532,0.0002511932,0.0001883728,0.0002080964],"domain_scores_gemma":[0.9996136,0.00001138861,0.00006416821,0.0002207719,0.00003609249,0.00005393795],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001743579,0.0001558026,0.001904475,0.0001005589,0.00002054289,0.00004700169,0.006302053,0.02824114,0.007742913,0.03671317,0.0008702074,0.9179004],"study_design_scores_gemma":[0.004306387,0.000220202,0.02415047,0.001293677,0.00005865951,0.000347817,0.0009615476,0.6961192,0.06298808,0.2032002,0.003687199,0.002666604],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1930173,0.00002089256,0.804733,0.0003190871,0.0002206404,0.00003903454,1.218398e-7,0.0002183244,0.001431588],"genre_scores_gemma":[0.6298001,4.872896e-7,0.3686477,0.001386584,0.00006848481,7.995954e-7,6.547504e-7,0.000004950667,0.00009030043],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9152338,"threshold_uncertainty_score":0.3134107,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W123034841","doi":"10.1016/b978-0-12-381460-9.00002-x","title":"Musical Timbre Perception","year":2012,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Music and Audio Processing","field":"Computer Science","cited_by":101,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"Core Research for Evolutional Science and Technology","keywords":"Timbre; Musical; Perception; Art; Psychology; Communication; Speech recognition; Visual arts; Computer science; Neuroscience","retraction":null,"screen_n_in":null,"score":{"opus":0.02194690475241409,"gpt":0.2378707900940175,"spread":0.2159238853416034,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00022982,0.0003591962,0.0003641743,0.0001130282,0.0001698358,0.0001720408,0.0007640632,0.0003385683,0.0005584389],"category_scores_gemma":[0.000005736432,0.0003222576,0.0002040401,0.00001381737,0.0001035321,0.0002085926,0.0003998784,0.000494901,0.001632332],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008035506,"about_ca_system_score_gemma":0.0001178239,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":1.39634e-7,"about_ca_topic_score_gemma":0.000001253748,"domain_scores_codex":[0.9983407,0.00001912448,0.0003096461,0.0005458957,0.0004126135,0.0003720064],"domain_scores_gemma":[0.9987636,0.00002719135,0.000201289,0.000745772,0.00007703652,0.0001850899],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000001005155,0.000004712339,6.082105e-7,0.00004298607,0.00001397816,0.00001024247,0.0004768026,1.418649e-7,0.0000489302,0.02254055,0.001054269,0.9758058],"study_design_scores_gemma":[0.00009133403,0.00002022773,0.00003686862,0.0002299985,0.00003087386,0.00004137874,0.000001861883,0.0001294425,0.000008222099,0.01372682,0.9852837,0.0003993141],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.00001197326,0.0006970482,0.005593074,0.0002985848,0.0005762012,0.000175796,0.000002672806,0.0002110853,0.9924335],"genre_scores_gemma":[0.001651594,0.00003417563,0.009628354,0.002264617,0.001346382,0.00001098611,0.000007808888,0.00004792328,0.9850082],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.9842294,"threshold_uncertainty_score":0.9999229,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2109573991","doi":"10.1155/2010/451695","title":"Audio Signal Processing Using Time-Frequency Approaches: Coding, Classification, Fingerprinting, and Watermarking","year":2010,"lang":"en","type":"article","venue":"EURASIP Journal on Advances in Signal Processing","topic":"Music and Audio Processing","field":"Computer Science","cited_by":97,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Digital watermarking; Audio signal; Digital audio; Speech coding; Audio signal processing; Speech recognition; Coding (social sciences); Psychoacoustics; Signal processing; Artificial intelligence; Digital signal processing; Perception; Computer hardware","retraction":null,"screen_n_in":null,"score":{"opus":0.04103532990992343,"gpt":0.2835590867445217,"spread":0.2425237568345983,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002063661,0.0005370358,0.0005416464,0.0006017625,0.001468735,0.002079873,0.001197823,0.000201047,0.00005015608],"category_scores_gemma":[0.000117822,0.0004703215,0.0001008916,0.0009618988,0.0003373781,0.005701493,0.0002354397,0.001980068,0.00001209654],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001564096,"about_ca_system_score_gemma":0.0005088295,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001876026,"about_ca_topic_score_gemma":0.00000323933,"domain_scores_codex":[0.9959267,0.0001875695,0.001108016,0.0009881657,0.000863634,0.0009258663],"domain_scores_gemma":[0.9976598,0.0001717766,0.001259096,0.0002993045,0.000292824,0.0003171699],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003034831,0.0001328592,0.008338081,0.0002963196,0.000008407763,0.00009868998,0.001963017,0.001285067,0.0707846,0.0009833563,0.00001822496,0.916061],"study_design_scores_gemma":[0.001359898,0.0001701367,0.003272435,0.003379853,0.00003735083,0.002126731,0.00038978,0.9596078,0.01032306,0.01434452,0.003578365,0.001410062],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1947964,0.004761357,0.7919168,0.0007755221,0.0003843059,0.0002710289,0.000001075858,0.0002339369,0.006859537],"genre_scores_gemma":[0.8784916,0.0000928693,0.1201861,0.0004824537,0.0006194161,0.000009417333,0.000001437308,0.00005217245,0.00006454857],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9583228,"threshold_uncertainty_score":0.9998312,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2162911105","doi":"10.1109/icassp.2013.6638244","title":"High-dimensional sequence transduction","year":2013,"lang":"en","type":"article","venue":"","topic":"Music and Audio Processing","field":"Computer Science","cited_by":96,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Polyphony; Sequence (biology); Computer science; Probabilistic logic; Speech recognition; Notation; Noise (video); Mode (computer interface); Artificial neural network; Recurrent neural network; Transduction (biophysics); Algorithm; Artificial intelligence; Mathematics; Arithmetic","retraction":null,"screen_n_in":null,"score":{"opus":0.02160387256074852,"gpt":0.2278007704775471,"spread":0.2061968979167986,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00005056365,0.00004812115,0.00004652421,0.0000236702,0.00007253871,0.0000974095,0.0001982004,0.00001976393,0.0007451645],"category_scores_gemma":[0.0000030945,0.00003654251,0.00001637239,0.0001231424,0.00002072993,0.001081765,0.00002835181,0.00004229637,0.0004595084],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009340646,"about_ca_system_score_gemma":0.00002744763,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000123365,"about_ca_topic_score_gemma":0.000001202081,"domain_scores_codex":[0.9995108,0.000009313252,0.00007652146,0.0001642244,0.0001254592,0.0001137214],"domain_scores_gemma":[0.9997447,0.000009674087,0.00001859934,0.0001388873,0.00004590423,0.00004220458],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[7.23532e-7,0.00003877402,0.00004647568,0.00001280971,0.000006656536,0.000004404515,0.0002961014,0.0004223285,0.1213442,0.2088755,0.0274822,0.6414698],"study_design_scores_gemma":[0.0009154559,0.0001420596,0.008201638,0.00007664476,0.000008428468,0.0002057477,0.00004082948,0.3993574,0.2805849,0.2972128,0.01227086,0.0009832227],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09291411,0.00001858645,0.8949196,0.008649815,0.0003136873,0.00005044364,9.406453e-8,0.000170588,0.002963054],"genre_scores_gemma":[0.8452595,7.453874e-7,0.151122,0.002200393,0.0000529262,0.000005782117,4.992978e-7,0.000001854153,0.001356288],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7523454,"threshold_uncertainty_score":0.8159028,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2108672713","doi":"10.1145/1631272.1631393","title":"Improving automatic music tag annotation using stacked generalization of probabilistic SVM outputs","year":2009,"lang":"en","type":"article","venue":"","topic":"Music and Audio Processing","field":"Computer Science","cited_by":96,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria","funders":"","keywords":"Annotation; Computer science; Probabilistic logic; Generalization; Support vector machine; Music information retrieval; Information retrieval; Recommender system; Artificial intelligence; Scheme (mathematics); Natural language processing; Machine learning; Speech recognition; Musical","retraction":null,"screen_n_in":null,"score":{"opus":0.02967875432838947,"gpt":0.2574788825945556,"spread":0.2278001282661661,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002197454,0.0001130711,0.0001554747,0.0001162047,0.0001080229,0.0001311943,0.0002658467,0.00004324051,0.00001933074],"category_scores_gemma":[0.00008067609,0.0001000196,0.00003507282,0.0004901774,0.00002457235,0.0007328013,0.00004824345,0.00004458245,0.000003214985],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005143388,"about_ca_system_score_gemma":0.0001275143,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002961086,"about_ca_topic_score_gemma":0.000003802785,"domain_scores_codex":[0.9989077,0.00004245137,0.0003440857,0.0002649986,0.0002495114,0.0001912312],"domain_scores_gemma":[0.9992416,0.00002307985,0.000258061,0.0002676331,0.0001644905,0.00004514793],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003046012,0.0001414469,0.0001852468,0.000301218,0.000009732374,0.000004549299,0.002837556,0.01057295,0.1928505,0.05953065,0.0003091025,0.733254],"study_design_scores_gemma":[0.0001853158,0.00004947075,0.001209152,0.00005567606,0.000009153592,0.000004779901,0.00001863516,0.982686,0.010245,0.005391363,0.00001531368,0.000130143],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2610667,0.00003416226,0.7380179,0.0001545,0.0001030782,0.000132031,3.104227e-7,0.0001354476,0.0003559043],"genre_scores_gemma":[0.7435014,4.829798e-7,0.2558993,0.0004915954,0.00003887502,0.000001479006,0.000002724437,0.000004400266,0.00005969236],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.972113,"threshold_uncertainty_score":0.407868,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2406196141","doi":"10.5281/zenodo.1418237","title":"Temporal Pooling And Multiscale Learning For Automatic Annotation And Ranking Of Music Audio.","year":2011,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Music and Audio Processing","field":"Computer Science","cited_by":95,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Pooling; Automatic summarization; Computer science; Ranking (information retrieval); Annotation; Artificial intelligence; Principal component analysis; Machine learning; Selection (genetic algorithm)","retraction":null,"screen_n_in":null,"score":{"opus":0.05333081680777514,"gpt":0.237022333243612,"spread":0.1836915164358369,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005749881,0.00008133498,0.0001141298,0.0001384874,0.001053392,0.0003058179,0.0003371992,0.00003178589,0.0001849323],"category_scores_gemma":[0.0002900052,0.00008323718,0.0000194622,0.0002333156,0.00009512799,0.0004596158,0.0004904037,0.00009954156,0.00002803822],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001642832,"about_ca_system_score_gemma":0.000003109111,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001063745,"about_ca_topic_score_gemma":1.707526e-7,"domain_scores_codex":[0.9991083,0.0001048797,0.0001924919,0.0002660815,0.0001464275,0.0001818665],"domain_scores_gemma":[0.9993867,0.00003136993,0.0001455679,0.0001435005,0.0002248383,0.00006800248],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002312799,0.00005476472,0.0001607878,0.0003746628,0.00002506883,0.000003677655,0.01936485,0.0000475838,0.007976728,0.005072273,0.001722286,0.9651742],"study_design_scores_gemma":[0.004275109,0.001286071,0.03117659,0.0007114001,0.00007400473,0.0003494408,0.002536168,0.778443,0.01111605,0.006704522,0.1623461,0.0009814822],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2944924,0.0001567097,0.6985126,0.0001647255,0.00005688532,0.0003234503,0.000005765695,0.0004505211,0.005836951],"genre_scores_gemma":[0.9746417,0.00001330852,0.02498475,0.00005155763,0.00002964418,4.802675e-8,0.00003114958,0.0001719046,0.00007588314],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9641927,"threshold_uncertainty_score":0.8101946,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2166706387","doi":"10.1109/tasl.2006.885921","title":"Audio Signal Feature Extraction and Classification Using Local Discriminant Bases","year":2007,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Music and Audio Processing","field":"Computer Science","cited_by":93,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Metropolitan University; Western University","funders":"","keywords":"Audio signal; Linear discriminant analysis; Flute; Feature extraction; Computer science; Speech recognition; Pattern recognition (psychology); Artificial intelligence; Natural sounds; Classifier (UML); Audio signal processing; Search engine indexing; Linear subspace; Mel-frequency cepstrum; Mathematics; Speech coding; Acoustics","retraction":null,"screen_n_in":null,"score":{"opus":0.0230565890800868,"gpt":0.2885249737227967,"spread":0.2654683846427099,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005122676,0.0002544004,0.0002133298,0.0002514124,0.0007194853,0.0003825639,0.0001672832,0.0001520004,0.00001916483],"category_scores_gemma":[0.000007901261,0.0002237007,0.00005237365,0.0004420502,0.0001567194,0.001092263,0.000005584742,0.0003999426,0.000004081363],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008820673,"about_ca_system_score_gemma":0.0001045741,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004617266,"about_ca_topic_score_gemma":0.00007838215,"domain_scores_codex":[0.9984037,0.00004688472,0.0002622833,0.0005665837,0.0003177789,0.0004027626],"domain_scores_gemma":[0.9992628,0.00009383608,0.0001698346,0.0002083577,0.00008054483,0.0001846421],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003576579,0.00007231529,0.00002760417,0.0001180222,0.000008787285,0.00005839942,0.001589333,0.0001235316,0.08836492,0.00002565204,0.00003476783,0.9095409],"study_design_scores_gemma":[0.001100308,0.0001936354,0.002575612,0.0008171739,0.0001475179,0.001497368,0.005005747,0.3410287,0.6455111,0.0002135956,0.0009417229,0.0009675423],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07366958,0.001433683,0.923594,0.0004489798,0.0001768482,0.0001316702,0.000003350841,0.0001753777,0.0003664819],"genre_scores_gemma":[0.9279364,0.00004886177,0.07109388,0.0004718218,0.0001126565,0.000005097331,0.00000178312,0.00002036445,0.0003091819],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9085733,"threshold_uncertainty_score":0.9122249,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2796517058","doi":"10.3390/app8040606","title":"End-to-End Neural Optical Music Recognition of Monophonic Scores","year":2018,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Music and Audio Processing","field":"Computer Science","cited_by":90,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"Social Sciences and Humanities Research Council of Canada; Ministerio de Economía y Competitividad","keywords":"Connectionism; Computer science; Artificial neural network; Convolutional neural network; Musical notation; Scalability; Notation; Artificial intelligence; Speech recognition; Pattern recognition (psychology); End-to-end principle; Musical; Arithmetic; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.05113765583816901,"gpt":0.2677386336652907,"spread":0.2166009778271217,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005086664,0.0001027141,0.0001374213,0.0001397411,0.0003105103,0.0001826808,0.000918093,0.00003442608,0.0001078448],"category_scores_gemma":[0.0000356254,0.00008215135,0.00002988255,0.001042861,0.0007357144,0.0003613322,0.000254285,0.00006885172,0.0001587589],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001130973,"about_ca_system_score_gemma":0.0001204429,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001754253,"about_ca_topic_score_gemma":0.00001692148,"domain_scores_codex":[0.998576,0.00001553403,0.0002073646,0.0004582154,0.0004245437,0.0003182826],"domain_scores_gemma":[0.9994248,0.00008816963,0.0000916924,0.0002260372,0.00006862998,0.000100693],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000111608,0.00005557251,0.0001949943,0.00001824606,0.000005100143,0.000002426266,0.002064912,0.00006036906,0.1159841,0.03602264,0.001235809,0.8443447],"study_design_scores_gemma":[0.000582359,0.0008968453,0.01005019,0.0001222277,0.00001877884,0.00003227974,0.000457882,0.04471839,0.8713661,0.06948113,0.001499028,0.0007747473],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8614849,0.0000330726,0.1066558,0.0007859429,0.0004102741,0.0001283693,0.000001061611,0.00007899576,0.0304215],"genre_scores_gemma":[0.9349501,0.000001204003,0.06362375,0.001230845,0.0001574732,0.00001047004,4.513761e-7,0.000003143258,0.00002252678],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8435699,"threshold_uncertainty_score":0.3350035,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2097705935","doi":"10.1109/tsmcb.2005.862491","title":"Modeling emotional content of music using system identification","year":2006,"lang":"en","type":"article","venue":"IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics)","topic":"Music and Audio Processing","field":"Computer Science","cited_by":90,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Arousal; Valence (chemistry); Statistic; Ambiguity; Content (measure theory); Identification (biology); Computer science; Emotional valence; Emotion detection; Musical; Speech recognition; Psychology; Artificial intelligence; Pattern recognition (psychology); Cognitive psychology; Mathematics; Emotion recognition; Social psychology; Statistics; Cognition; Art","retraction":null,"screen_n_in":null,"score":{"opus":0.05631744724370018,"gpt":0.2370317147277042,"spread":0.180714267484004,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004049246,0.000299119,0.0004066952,0.000246344,0.0003044118,0.0003129153,0.0003820007,0.0001570392,0.00000822221],"category_scores_gemma":[0.000002553954,0.0003019005,0.0001292079,0.0003337991,0.0001143699,0.0002657596,0.000009483986,0.0001995332,0.00002156332],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001166715,"about_ca_system_score_gemma":0.00007491544,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000722193,"about_ca_topic_score_gemma":0.00004432808,"domain_scores_codex":[0.9973099,0.0001285567,0.0009866176,0.0006017468,0.0006119648,0.0003612748],"domain_scores_gemma":[0.9986186,0.00005806166,0.0003388249,0.0005515976,0.0003053472,0.0001275805],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002324537,0.0003972851,0.00009802034,0.0008260817,0.0001119675,0.00001325159,0.0009138834,0.9228507,0.02138831,0.04665467,0.0002410521,0.006481523],"study_design_scores_gemma":[0.0005220126,0.00005995737,0.0001827862,0.0006478644,0.00007375458,0.00009515218,0.0003200653,0.990439,0.006925139,0.0002032654,0.0001968099,0.0003342033],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2424206,0.0004082477,0.7548362,0.0000461675,0.001134106,0.0002853611,0.00001867668,0.0001164852,0.0007341492],"genre_scores_gemma":[0.9960127,0.00003053815,0.002408324,0.00003910777,0.0001776275,0.00002681476,0.000004548057,0.0000306853,0.001269692],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.753592,"threshold_uncertainty_score":0.9999433,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1964850609","doi":"10.1109/tifs.2006.885036","title":"Gaussian Mixture Modeling of Short-Time Fourier Transform Features for Audio Fingerprinting","year":2006,"lang":"en","type":"article","venue":"IEEE Transactions on Information Forensics and Security","topic":"Music and Audio Processing","field":"Computer Science","cited_by":87,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Pattern recognition (psychology); Mixture model; Centroid; Artificial intelligence; Fingerprint (computing); Speech recognition; Cepstrum; Audio signal; Robustness (evolution); Entropy (arrow of time); Word error rate; Speech coding","retraction":null,"screen_n_in":null,"score":{"opus":0.007905369170801714,"gpt":0.2148253334217568,"spread":0.2069199642509551,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002130661,0.0001464971,0.0001837559,0.0001417382,0.0003298616,0.0001584045,0.0001520644,0.0001487218,0.000004525579],"category_scores_gemma":[0.00000320402,0.0001332419,0.0001133685,0.0001863774,0.00004293328,0.001334368,0.000002279703,0.0002212634,0.000001476097],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002011947,"about_ca_system_score_gemma":0.00004508985,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003427496,"about_ca_topic_score_gemma":0.00002323021,"domain_scores_codex":[0.9990422,0.00000894697,0.0003884886,0.0001439414,0.0002138962,0.0002025194],"domain_scores_gemma":[0.9994826,0.00004227748,0.00009583643,0.0001715967,0.0001568504,0.0000507935],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008175605,0.00009570728,0.000007475123,0.000499308,0.00006148347,7.004745e-7,0.008324766,0.1152126,0.0004221111,0.02953615,0.00153701,0.8442209],"study_design_scores_gemma":[0.0003215016,0.00005103367,0.00001244446,0.00006102236,0.00001878049,0.000009150303,0.00005938083,0.9694785,0.009521623,0.01906539,0.001227201,0.000173978],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009068251,0.00002900958,0.9873634,0.0006762375,0.0001834573,0.0002250599,0.00003695883,0.00007558282,0.002342044],"genre_scores_gemma":[0.9531209,0.00001207362,0.04651445,0.0002443613,0.00003623083,0.00001687398,0.00001162668,0.000006001632,0.00003742012],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9440527,"threshold_uncertainty_score":0.5433446,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1688667826","doi":"10.1073/pnas.1510724112","title":"Cross-cultural convergence of musical features","year":2015,"lang":"en","type":"letter","venue":"Proceedings of the National Academy of Sciences","topic":"Music and Audio Processing","field":"Computer Science","cited_by":87,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Musical; Convergence (economics); Computer science; Computational biology; Speech recognition; Biological system; Biology; Art; Economics; Literature","retraction":null,"screen_n_in":null,"score":{"opus":0.06741783976302491,"gpt":0.3420739352726175,"spread":0.2746560955095926,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001458885,0.0002056107,0.0003715433,0.0001946201,0.0002008734,0.0001589331,0.004526985,0.0003914348,0.00001634144],"category_scores_gemma":[0.0008211693,0.0001245365,0.0001703353,0.00114744,0.002697119,0.001487559,0.0007103556,0.0008456777,0.000001944627],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004333817,"about_ca_system_score_gemma":0.0001957105,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008598104,"about_ca_topic_score_gemma":1.609056e-8,"domain_scores_codex":[0.9955888,0.00001103307,0.000549112,0.0005116402,0.003066782,0.0002725829],"domain_scores_gemma":[0.9968334,0.0001421006,0.001346865,0.00002331646,0.001612401,0.00004188025],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000004425719,0.0000227668,0.0005906822,0.0003948561,0.00002288048,6.442652e-8,0.0005231816,0.0000336073,0.01746434,0.02746265,0.9526107,0.0008698863],"study_design_scores_gemma":[0.0007890591,0.0002375692,0.03266944,0.00185863,0.00007404278,0.0001836517,0.0001506251,0.004593262,0.4013292,0.3186994,0.2382389,0.001176222],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.0994404,0.00101969,0.00006709201,0.8601898,0.0005287394,0.0004645395,0.00007214137,0.00007861712,0.038139],"genre_scores_gemma":[0.8366461,0.00002739439,0.01172735,0.1479069,0.001454554,0.00001160871,7.567036e-7,0.00001058846,0.002214713],"genre_candidate":"commentary","genre_consensus":null,"teacher_disagreement_score":0.7372057,"threshold_uncertainty_score":0.9937647,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3049459827","doi":"10.1109/cjece.2020.2970144","title":"Neural Network Music Genre Classification","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Electrical and Computer Engineering","topic":"Music and Audio Processing","field":"Computer Science","cited_by":84,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"University of Regina","funders":"","keywords":"Spectrogram; Computer science; Artificial neural network; Musical; Artificial intelligence; Speech recognition; Machine learning; Art; Visual arts","retraction":null,"screen_n_in":null,"score":{"opus":0.02022962826200411,"gpt":0.1746245635508428,"spread":0.1543949352888387,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007371619,0.00008485631,0.0001374496,0.00007594056,0.00007391075,0.0001732469,0.0003032309,0.00003438922,0.000003626618],"category_scores_gemma":[0.00002172383,0.00007667301,0.00004074122,0.0004180713,0.000009567852,0.0002337625,0.00002116591,0.0002256605,0.000001330766],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000260882,"about_ca_system_score_gemma":0.0001637836,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001487222,"about_ca_topic_score_gemma":0.000009281644,"domain_scores_codex":[0.9993336,0.00001231013,0.0001917062,0.0001219539,0.00008579102,0.0002546252],"domain_scores_gemma":[0.9992021,0.00003837458,0.00006762131,0.00006007954,0.00005472776,0.0005771316],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005388432,0.000008165199,0.002524891,0.00005104956,0.00005392547,0.000387506,0.001113186,0.1059418,0.0006563316,0.02481187,0.01800932,0.8464366],"study_design_scores_gemma":[0.0001065967,0.00009480655,0.007723667,0.00001783269,0.000004444215,0.0001458123,0.000001007902,0.9836078,0.00002444761,0.0001074238,0.008070461,0.00009564751],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03359908,0.001366092,0.9618592,0.002799779,0.0002877655,0.00002422241,1.439909e-7,0.00002066555,0.00004303905],"genre_scores_gemma":[0.9742264,0.000006600379,0.02234397,0.00243024,0.0009834408,3.433234e-7,2.079605e-7,0.000005759959,0.000003084213],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9406273,"threshold_uncertainty_score":0.3126634,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3109392859","doi":"10.3989/loquens.2019.065","title":"Sets, rules and natural classes: [ ] vs. { }","year":2019,"lang":"en","type":"article","venue":"Loquens","topic":"Music and Audio Processing","field":"Computer Science","cited_by":83,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Unification; Computer science; Feature (linguistics); Set (abstract data type); Subtraction; Theoretical computer science; Natural (archaeology); Singleton; Artificial intelligence; Mathematics; Algorithm; Arithmetic; Programming language; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.007942647612564515,"gpt":0.2297369402026419,"spread":0.2217942925900774,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006076839,0.00006605779,0.00008339984,0.00002677056,0.00005228639,0.0001486459,0.0002224335,0.00002919608,0.00002348901],"category_scores_gemma":[0.00000807449,0.00005332256,0.00001734905,0.00006539155,0.0000234631,0.0003206065,0.0001294567,0.00008830713,0.0001799329],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009022601,"about_ca_system_score_gemma":0.00002805734,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009446383,"about_ca_topic_score_gemma":0.000002685144,"domain_scores_codex":[0.999468,0.00001185151,0.00006847916,0.0002028779,0.0000975803,0.0001512084],"domain_scores_gemma":[0.9996853,0.00002818454,0.00003088671,0.0001969796,0.00002063645,0.00003803091],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001976339,0.00008622569,0.0533773,0.0003973223,0.00006212355,0.0001046054,0.00557689,0.00002741044,0.0189403,0.330793,0.03374482,0.5568703],"study_design_scores_gemma":[0.002168815,0.0002654119,0.3303798,0.0004535545,0.00002488159,0.0003953388,0.0002427127,0.1345779,0.01009383,0.06473918,0.4549551,0.001703347],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9654611,0.000821038,0.01497433,0.003504701,0.0006690008,0.00008977486,0.000001322558,0.0001671018,0.01431166],"genre_scores_gemma":[0.9791314,0.00001334283,0.01678207,0.00259584,0.00003935583,0.00000106691,0.000001144271,0.000004125532,0.001431651],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.555167,"threshold_uncertainty_score":0.2312733,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2753868141","doi":"10.48550/arxiv.1903.07227","title":"Counterpoint By Convolution.","year":2017,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Music and Audio Processing","field":"Computer Science","cited_by":80,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Gibbs sampling; Computer science; Sampling (signal processing); Convolution (computer science); Convolutional neural network; Artificial intelligence; Counterpoint; Set (abstract data type); Algorithm; Artificial neural network; Filter (signal processing); Computer vision; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.05705792341172985,"gpt":0.1739792359229458,"spread":0.116921312511216,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000103256,0.00008448151,0.0000881458,0.00003117902,0.0006093425,0.0002386398,0.001225303,0.00004134581,0.00005758178],"category_scores_gemma":[0.00002069621,0.00009039825,0.00004342479,0.00007919603,0.0001301604,0.001051084,0.0003194275,0.00007952945,0.0001535592],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004881428,"about_ca_system_score_gemma":0.00004743466,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005227974,"about_ca_topic_score_gemma":0.000004428395,"domain_scores_codex":[0.9993442,0.00001672705,0.0000611974,0.0003461088,0.00004416293,0.0001876132],"domain_scores_gemma":[0.9990088,0.00001641439,0.0001258953,0.0007090798,0.00005667641,0.00008307563],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002007147,0.0001245891,0.01491151,0.00003146648,0.00004915055,0.0002824634,0.0003144866,0.000895004,0.001741632,0.8930752,0.08306087,0.005493502],"study_design_scores_gemma":[0.001928637,0.0001008456,0.01021967,0.000101223,0.00003000112,0.0000225272,0.0001366374,0.8504385,0.003449434,0.05588854,0.07681954,0.0008644093],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09849081,0.00004010094,0.8750635,0.0005393433,0.000245965,0.00004129274,0.000002279367,0.000102938,0.02547379],"genre_scores_gemma":[0.9955962,0.00001972588,0.0005154407,0.0004108374,0.0000295349,9.630709e-8,7.630762e-7,0.000003627787,0.003423735],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8971055,"threshold_uncertainty_score":0.4686631,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2152156982","doi":"10.1109/ism.2009.123","title":"Music Emotion Identification from Lyrics","year":2009,"lang":"en","type":"article","venue":"","topic":"Music and Audio Processing","field":"Computer Science","cited_by":79,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Lyrics; Computer science; Music information retrieval; Identification (biology); Emotion classification; Musical; Emotion detection; Natural language processing; Classifier (UML); Emotion recognition; Artificial intelligence; Art; Literature","retraction":null,"screen_n_in":null,"score":{"opus":0.02320938488149102,"gpt":0.2355040165623796,"spread":0.2122946316808886,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008298529,0.00004365214,0.00004292866,0.00003188063,0.00007376429,0.0001947002,0.0002689487,0.00002391972,0.00005640063],"category_scores_gemma":[0.00001122206,0.00003833279,0.00001767902,0.0001974723,0.000005904694,0.0005186897,0.00002332516,0.00003380165,0.0001473253],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001248291,"about_ca_system_score_gemma":0.00001506521,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001123705,"about_ca_topic_score_gemma":0.000001411595,"domain_scores_codex":[0.9994932,0.00001070675,0.0001061709,0.0001833046,0.0001235114,0.00008309757],"domain_scores_gemma":[0.9996495,0.0000106748,0.00004763635,0.0002317364,0.0000330603,0.0000273581],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[4.254398e-7,0.00003262044,0.00007284413,0.000001458343,0.000001500636,0.000001442585,0.0006057721,0.00002524962,0.01672645,0.03308923,0.01015347,0.9392895],"study_design_scores_gemma":[0.0004763843,0.00006341777,0.251646,0.00004635217,0.00001179545,0.000007122833,0.00009154899,0.2978069,0.07347488,0.3637492,0.01211585,0.0005105566],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05285116,0.00003532404,0.9355751,0.002564582,0.0002113007,0.0000270949,1.808878e-7,0.0001590584,0.00857624],"genre_scores_gemma":[0.9613576,0.000002652307,0.03502085,0.002846718,0.00009152127,5.213374e-7,0.00000333711,0.000001272179,0.0006755408],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.938779,"threshold_uncertainty_score":0.1893618,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W192383697","doi":"10.5281/zenodo.7432188","title":"ENST-Drums: an extensive audio-visual database for drum signals processing","year":2006,"lang":"en","type":"dataset","venue":"","topic":"Music and Audio Processing","field":"Computer Science","cited_by":77,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Drum; Audio visual; Computer science; Database; Computer graphics (images); Speech recognition; Multimedia; Geography; Archaeology","retraction":null,"screen_n_in":null,"score":{"opus":0.02936108337964647,"gpt":0.3172990123547395,"spread":0.287937928975093,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006414349,0.0006906094,0.0007506859,0.0003415416,0.0006337359,0.001257244,0.00217916,0.0003508487,0.0001070956],"category_scores_gemma":[0.0001137996,0.0005999273,0.0001740947,0.000428966,0.0001432911,0.002011975,0.0006903912,0.000444921,0.00009637566],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007546027,"about_ca_system_score_gemma":0.0008542364,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002490704,"about_ca_topic_score_gemma":0.0001472633,"domain_scores_codex":[0.9958647,0.00009505495,0.0007220306,0.001658505,0.0007066722,0.0009530492],"domain_scores_gemma":[0.9971149,0.0001809196,0.000648455,0.001284225,0.000493015,0.0002785007],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001024094,0.0001754244,8.089504e-7,0.0005394401,0.00001594981,0.00005132583,0.00003807429,0.00002794299,0.0002179262,0.0000834193,0.9724309,0.02640854],"study_design_scores_gemma":[0.0004703758,0.0001813111,0.000004345944,0.000419995,0.00007404113,0.00004476612,0.00004308884,0.01436171,0.001487863,0.0005692206,0.9813636,0.0009796749],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.00001229711,0.0004023498,0.4331175,0.0003048845,0.0004214254,0.0004529473,0.5649137,0.0002200746,0.000154838],"genre_scores_gemma":[0.00007033265,0.00002113623,0.05770442,0.005804896,0.001200645,0.0001112942,0.9342578,0.00004303282,0.0007864401],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.3754131,"threshold_uncertainty_score":0.9997795,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2186385212","doi":"10.31234/osf.io/s9ryg","title":"CantoCore: A new cross-cultural song classification scheme","year":2020,"lang":"en","type":"article","venue":"","topic":"Music and Audio Processing","field":"Computer Science","cited_by":77,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"","keywords":"Classification scheme; Scheme (mathematics); Musical; Problem of universals; Computer science; Natural language processing; Reliability (semiconductor); Cross-cultural; Artificial intelligence; Linguistics; Machine learning; Literature; Mathematics; Art; Sociology; Anthropology; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.1010133824232493,"gpt":0.3313369098939356,"spread":0.2303235274706864,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00004325655,0.00007307969,0.000068007,0.00001079856,0.0001073348,0.0005324998,0.0004493459,0.0000316868,0.000107331],"category_scores_gemma":[0.00004455942,0.00005548437,0.0000298082,0.0002553295,0.00003103718,0.0009647314,0.0001086798,0.00007559657,0.0001573305],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001573063,"about_ca_system_score_gemma":0.0001271217,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004185836,"about_ca_topic_score_gemma":0.000003432421,"domain_scores_codex":[0.9992972,0.000007201128,0.0001225488,0.0002695089,0.0001492029,0.000154331],"domain_scores_gemma":[0.9995685,0.000009158403,0.00005097181,0.000151783,0.00006447907,0.0001551089],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001572867,0.0000307283,0.0142763,0.00008675837,0.00001902376,0.00001406254,0.005797322,0.00005053962,0.07619368,0.3191675,0.1813487,0.4029997],"study_design_scores_gemma":[0.0009965254,0.0001047931,0.04213096,0.00003423535,0.000005976037,0.00001822941,0.0001790812,0.7517322,0.02850477,0.003127078,0.1725483,0.0006178005],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02067513,0.00004965713,0.9293289,0.0310575,0.00009862407,0.00007893336,2.543232e-7,0.0003044813,0.01840651],"genre_scores_gemma":[0.8771172,0.000002224569,0.1126029,0.008008719,0.0002665033,0.000004200868,0.000001292179,0.000004038066,0.001993035],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.856442,"threshold_uncertainty_score":0.5134908,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2591984255","doi":"10.17863/cam.21343","title":"Sequence Tutor: Conservative Fine-Tuning of Sequence Generation Models with KL-control","year":2017,"lang":"en","type":"article","venue":"Apollo (University of Cambridge)","topic":"Music and Audio Processing","field":"Computer Science","cited_by":76,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; Google (Canada)","funders":"Engineering and Physical Sciences Research Council; Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Recurrent neural network; Sequence (biology); Reinforcement learning; Security token; Artificial intelligence; Machine learning; Artificial neural network","retraction":null,"screen_n_in":null,"score":{"opus":0.06863170625603472,"gpt":0.239950264465594,"spread":0.1713185582095593,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002102837,0.0001220316,0.0002548066,0.00007368223,0.0005437833,0.0000741439,0.001027415,0.00005347835,0.000004792544],"category_scores_gemma":[0.00002426589,0.000129548,0.00005674234,0.0001239834,0.0004183806,0.002131694,0.0001698773,0.0000995393,0.000003027541],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004330735,"about_ca_system_score_gemma":0.0003132991,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001345165,"about_ca_topic_score_gemma":0.0001391256,"domain_scores_codex":[0.9990616,0.00004456397,0.0001205239,0.0003074982,0.0002787305,0.0001871286],"domain_scores_gemma":[0.9984679,0.00004040796,0.0005117774,0.0006179665,0.0002917667,0.00007018715],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002495395,0.0001701534,0.01224372,0.0003326342,0.0003689359,0.0003429257,0.01245692,0.01445024,0.4562185,0.4341877,0.004728445,0.06425025],"study_design_scores_gemma":[0.001638073,0.0001573245,0.004664051,0.0002247989,0.00004905336,0.00002474241,0.0002955532,0.9799593,0.01173487,0.0005575735,0.0003660462,0.0003285797],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3188851,0.00003031918,0.6765987,0.00143993,0.00005207488,0.00008719364,0.00001482328,0.00002826102,0.002863652],"genre_scores_gemma":[0.9552149,0.00001007513,0.04385437,0.0001522504,0.00002382091,2.529616e-7,0.000002897919,0.000004765018,0.0007367057],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9655091,"threshold_uncertainty_score":0.5282816,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2138960858","doi":"","title":"Modeling Deep Temporal Dependencies with Recurrent Grammar Cells","year":2014,"lang":"en","type":"article","venue":"","topic":"Music and Audio Processing","field":"Computer Science","cited_by":76,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Recurrent neural network; Frame (networking); Autoencoder; Variety (cybernetics); Artificial intelligence; Transformation (genetics); Syntax; Grammar; Pyramid (geometry); Artificial neural network; Pattern recognition (psychology); Algorithm; Natural language processing; Mathematics; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.01618343484872841,"gpt":0.212876189027172,"spread":0.1966927541784436,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002163002,0.0001076059,0.0001083644,0.00004216917,0.0001313093,0.0002070438,0.0004497712,0.00002890544,0.00001610744],"category_scores_gemma":[0.000007551195,0.00007286638,0.00002253559,0.0001716824,0.00002097091,0.0003981997,0.000119628,0.0000882903,0.00003395196],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000012402,"about_ca_system_score_gemma":0.000047069,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005617838,"about_ca_topic_score_gemma":0.00009803687,"domain_scores_codex":[0.9990804,0.00002420351,0.0001304951,0.0002868623,0.0002453651,0.0002326613],"domain_scores_gemma":[0.9995152,0.00001832482,0.00003844904,0.0002807802,0.00006711597,0.0000800817],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000188012,0.0001254073,0.0008318769,0.0001096219,0.00002457159,0.00001585057,0.002394552,0.05351877,0.001884422,0.07261318,0.001601005,0.8668619],"study_design_scores_gemma":[0.0001313397,0.00005546027,0.000008609088,0.00002249146,0.000002563121,0.000006468916,0.00003605118,0.9933782,0.002212516,0.002451097,0.001546347,0.0001488542],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01742231,0.0000550127,0.9741559,0.0003599529,0.000155934,0.00004607574,7.682635e-8,0.0001673253,0.007637418],"genre_scores_gemma":[0.7876492,0.000002568037,0.2115165,0.0005182142,0.00005352651,0.000003079666,5.077158e-7,0.000005030665,0.0002513524],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9398594,"threshold_uncertainty_score":0.2971405,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2328848613","doi":"10.1080/09298215.2015.1132737","title":"A Comparison of Approaches to Timbre Descriptors in Music Information Retrieval and Music Psychology","year":2016,"lang":"en","type":"article","venue":"Journal of New Music Research","topic":"Music and Audio Processing","field":"Computer Science","cited_by":75,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Timbre; Music information retrieval; Information retrieval; Computer science; Speech recognition; Psychology; Musical; Visual arts; Art","retraction":null,"screen_n_in":null,"score":{"opus":0.5352193071220087,"gpt":0.435350893729382,"spread":0.0998684133926267,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002765322,0.0001111055,0.0003581434,0.001072817,0.00007994416,0.0001351849,0.0008003117,0.0000994272,0.00004623708],"category_scores_gemma":[0.0005008536,0.00007434776,0.00005322956,0.001299982,0.0001354013,0.001376045,0.0003014211,0.0004200037,0.0000161737],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009092159,"about_ca_system_score_gemma":0.0004254961,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002679262,"about_ca_topic_score_gemma":0.00004187836,"domain_scores_codex":[0.9975826,0.0001882391,0.0007733469,0.0001935239,0.0008794408,0.0003828075],"domain_scores_gemma":[0.9985545,0.0002312905,0.0003515634,0.000299082,0.0003137647,0.0002498248],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0004686344,0.000173782,0.01075875,0.0001223569,0.00002697417,0.00001962223,0.01758241,0.00004962683,0.0181189,0.001833117,0.07228965,0.8785562],"study_design_scores_gemma":[0.02071168,0.0105401,0.6555397,0.006261334,0.00005718194,0.00112233,0.00507642,0.02812884,0.03431527,0.08994354,0.1464725,0.001831149],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8592293,0.0002765471,0.1314939,0.0073561,0.0002744958,0.0001771883,5.90833e-7,0.000008069787,0.001183818],"genre_scores_gemma":[0.988656,0.00001485174,0.01065669,0.0003942952,0.000191732,0.000001345609,1.668389e-7,0.000006005727,0.00007884646],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.876725,"threshold_uncertainty_score":0.3031814,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2078120539","doi":"10.1145/2009916.2010011","title":"Enhancing multi-label music genre classification through ensemble techniques","year":2011,"lang":"en","type":"article","venue":"","topic":"Music and Audio Processing","field":"Computer Science","cited_by":75,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Lethbridge","funders":"","keywords":"Computer science; Multi-label classification; Ensemble learning; Set (abstract data type); Artificial intelligence; Music information retrieval; Task (project management); Machine learning; Field (mathematics); Statistical classification; Empirical research; Natural language processing; Information retrieval; Musical; Mathematics; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.1637955893780131,"gpt":0.3016030120560653,"spread":0.1378074226780522,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001907429,0.000119193,0.000111853,0.00004757297,0.0001666175,0.00009105507,0.0005231607,0.00007209353,0.00007831425],"category_scores_gemma":[0.0000181856,0.00009977142,0.00003008461,0.0002635588,0.00003434066,0.0009453453,0.0001501989,0.00009763771,0.0001055606],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002689462,"about_ca_system_score_gemma":0.00005621502,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007313195,"about_ca_topic_score_gemma":0.00003683862,"domain_scores_codex":[0.9990165,0.00002591222,0.0002100628,0.0003658502,0.0001449617,0.0002367472],"domain_scores_gemma":[0.9993195,0.00001787955,0.0001016904,0.0004285148,0.00008759538,0.00004482171],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000001961452,0.0001529739,0.00009466933,0.00003216519,0.000007835728,0.000006012875,0.006704338,6.174082e-8,0.4387482,0.06386655,0.001848939,0.4885363],"study_design_scores_gemma":[0.0001463035,0.00003538966,0.000568832,0.00004201104,0.000004350688,0.00001078909,0.0001695035,0.01255252,0.9794782,0.004899615,0.001869334,0.0002231795],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003620575,0.00006874602,0.9329277,0.0001823048,0.0001360695,0.000106597,1.389778e-7,0.00058987,0.06236797],"genre_scores_gemma":[0.2729194,0.000009680588,0.7243418,0.001482676,0.00004315525,0.00001708851,5.798817e-7,0.000007390144,0.001178163],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.54073,"threshold_uncertainty_score":0.4068561,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2107495852","doi":"10.1109/icme.2006.262954","title":"Mixed Type Audio Classification with Support Vector Machine","year":2006,"lang":"en","type":"article","venue":"","topic":"Music and Audio Processing","field":"Computer Science","cited_by":75,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Audio mining; Support vector machine; Speech recognition; Naive Bayes classifier; Feature extraction; Classifier (UML); Artificial intelligence; Mel-frequency cepstrum; Audio signal processing; Audio signal; Pattern recognition (psychology); Speech coding; Acoustic model; Speech processing","retraction":null,"screen_n_in":null,"score":{"opus":0.02580508025301679,"gpt":0.2253374570773634,"spread":0.1995323768243466,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008376561,0.00007288966,0.00007147489,0.00003469355,0.00007617734,0.0001039259,0.0002469799,0.00002450288,0.000117369],"category_scores_gemma":[0.000003984247,0.00005037201,0.00001317042,0.00028244,0.00002252745,0.0002549716,0.00003650248,0.00004892438,0.0001281098],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001723353,"about_ca_system_score_gemma":0.00007707397,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004922197,"about_ca_topic_score_gemma":0.00004905788,"domain_scores_codex":[0.9993808,0.00001134036,0.000103235,0.00021223,0.0001523251,0.0001400792],"domain_scores_gemma":[0.9995977,0.00001227348,0.0000534563,0.0002417274,0.00006285742,0.00003202553],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00003780609,0.0002872978,0.021014,0.0000631534,0.00002733923,0.00004736541,0.0002917611,0.0001434819,0.02963934,0.5834005,0.2059559,0.1590921],"study_design_scores_gemma":[0.001805826,0.0006255594,0.4697998,0.00006286259,0.00003359621,0.0001634573,0.00004639922,0.1760712,0.06037134,0.007409913,0.2823767,0.001233302],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01778779,0.00003776132,0.8988467,0.002951603,0.0001863622,0.00006132616,4.41837e-7,0.0002453122,0.07988268],"genre_scores_gemma":[0.9361476,9.688796e-7,0.05616404,0.0005296046,0.0000734485,0.000002740038,0.000007824894,0.000005257538,0.007068504],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9183598,"threshold_uncertainty_score":0.2054111,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3139654456","doi":"10.1109/infvis.2004.60","title":"Steerable, Progressive Multidimensional Scaling","year":2005,"lang":"en","type":"article","venue":"IEEE Symposium on Information Visualization","topic":"Music and Audio Processing","field":"Computer Science","cited_by":71,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Scaling; Computer science; Multidimensional scaling; Mathematics; Machine learning; Geometry","retraction":null,"screen_n_in":null,"score":{"opus":0.01085608954989996,"gpt":0.2703813822750954,"spread":0.2595252927251955,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002757015,0.0001521524,0.0001202239,0.0002383969,0.0003083386,0.0003413629,0.0002507205,0.00008316742,0.00003233526],"category_scores_gemma":[0.00002757949,0.0001397744,0.00004115857,0.0004311115,0.00002418618,0.00481001,0.00004387156,0.00008981686,0.0004109035],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009259253,"about_ca_system_score_gemma":0.00008601435,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001769597,"about_ca_topic_score_gemma":3.366901e-7,"domain_scores_codex":[0.9985617,0.00004425466,0.0004462725,0.0001807461,0.0005403419,0.0002266921],"domain_scores_gemma":[0.9990237,0.00003920295,0.0003099382,0.0002373979,0.0003076664,0.00008211639],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006045808,0.0003331716,0.000247838,0.0002014477,0.00004567597,0.000003383076,0.0161728,0.2987199,0.008237708,0.4325465,0.0255111,0.2179201],"study_design_scores_gemma":[0.0006170812,0.00006592232,0.0001508694,0.0001163822,0.000004847813,0.000012766,0.00003867062,0.8929762,0.05513583,0.0001276465,0.050492,0.0002617989],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01577763,0.00002158866,0.9734189,0.00156126,0.0006235446,0.0002577044,0.000002618117,0.0003669445,0.007969845],"genre_scores_gemma":[0.9623998,0.00001185585,0.02790112,0.008966076,0.0003348807,0.00004753247,0.00007192512,0.00001262611,0.0002541517],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9466222,"threshold_uncertainty_score":0.5699833,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2538750502","doi":"10.1109/iembs.2004.1403077","title":"Respiratory sounds classification using cepstral analysis and Gaussian mixture models","year":2005,"lang":"en","type":"article","venue":"","topic":"Music and Audio Processing","field":"Computer Science","cited_by":66,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Rimouski","funders":"","keywords":"Mel-frequency cepstrum; Pattern recognition (psychology); Speech recognition; Vector quantization; Mixture model; Computer science; Artificial intelligence; Multilayer perceptron; Feature vector; Perceptron; Feature extraction; Cepstrum; Hidden Markov model; Artificial neural network; Support vector machine; Gaussian","retraction":null,"screen_n_in":null,"score":{"opus":0.06297010440452305,"gpt":0.2887242472730468,"spread":0.2257541428685237,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001799902,0.00009074312,0.0001182598,0.0001772586,0.0001697892,0.0002623885,0.0002255468,0.00006091583,0.00002190469],"category_scores_gemma":[0.00000389907,0.00007600407,0.000047981,0.0006540692,0.00003877859,0.0009876055,0.00006316778,0.00007852626,0.000003399421],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003234047,"about_ca_system_score_gemma":0.00005117648,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001759495,"about_ca_topic_score_gemma":0.00003939402,"domain_scores_codex":[0.9991583,0.00002800653,0.0001621192,0.0003221686,0.0001586084,0.000170787],"domain_scores_gemma":[0.9995108,0.00001274565,0.00007313808,0.000284939,0.00003909077,0.00007924895],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001098903,0.0001675414,0.01663998,0.00006410993,0.0003976871,0.00001031876,0.005431938,0.03797472,0.04746578,0.3106214,0.002449868,0.5787656],"study_design_scores_gemma":[0.00008445913,0.000006171516,0.005157669,0.000005014382,0.00004564012,0.000002891753,0.00003330517,0.9898628,0.0009845846,0.00269055,0.0009991438,0.0001277972],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09190713,0.0001397758,0.9000948,0.001177948,0.0000243969,0.00002935536,3.883791e-7,0.00007770259,0.006548502],"genre_scores_gemma":[0.8539089,0.000002731615,0.1443163,0.001423716,0.00008615918,0.00000117274,7.090447e-7,0.000003408793,0.0002568734],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9518881,"threshold_uncertainty_score":0.3099356,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2132189140","doi":"10.18061/1811/48548","title":"Using Automated Rhyme Detection to Characterize Rhyming Style in Rap Music","year":2010,"lang":"en","type":"article","venue":"Empirical Musicology Review","topic":"Music and Audio Processing","field":"Computer Science","cited_by":65,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Rhyme; Style (visual arts); Psychology; Speech recognition; Communication; Art; Linguistics; Computer science; Literature; Philosophy; Poetry","retraction":null,"screen_n_in":null,"score":{"opus":0.1135838939556501,"gpt":0.3659130687035156,"spread":0.2523291747478655,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008446387,0.0002391971,0.0005777025,0.0002118542,0.0001732885,0.0001043903,0.0006419488,0.0001882576,0.0002338329],"category_scores_gemma":[0.0004040286,0.000214692,0.0001003343,0.001506003,0.0000652107,0.0004344925,0.0003687807,0.0005445775,0.0001833297],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007362728,"about_ca_system_score_gemma":0.0001524759,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002040083,"about_ca_topic_score_gemma":0.00007861597,"domain_scores_codex":[0.9978178,0.0002174308,0.0005810078,0.0006559221,0.0001996593,0.0005281608],"domain_scores_gemma":[0.9988355,0.0001317179,0.0002069159,0.0005359561,0.00009305796,0.0001968627],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001469119,0.0003048799,0.001872207,0.001296726,0.00002505315,0.0001588106,0.00130264,0.00001656619,0.2709888,0.0003779966,0.02692994,0.6967117],"study_design_scores_gemma":[0.001167336,0.000290519,0.07916092,0.00337599,0.00007769597,0.0006574297,0.000007845699,0.08389281,0.0033535,0.0004573748,0.8261767,0.001381874],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8857554,0.002384174,0.06969567,0.0372835,0.002364733,0.0009727717,0.000001301219,0.0008349544,0.000707478],"genre_scores_gemma":[0.6942794,0.0002433405,0.04020268,0.2646151,0.0004324632,0.0001246376,0.000003471941,0.00003516176,0.00006374119],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7992468,"threshold_uncertainty_score":0.8754886,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}