{"meta":{"query_hash":"50a8d0646b88","filters":{"venue":"Interspeech 2022"},"cohort_total":3,"direct_labels_cover":0,"predictions_cover":3,"exported":3,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/50a8d0646b88","api":"https://metacan.xera.ac/api/v1/cohort?venue=Interspeech+2022"},"results":[{"id":"W4297841482","doi":"10.21437/interspeech.2022-760","title":"Low-bit Shift Network for End-to-End Spoken Language Understanding","year":2022,"lang":"en","type":"article","venue":"Interspeech 2022","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Huawei Technologies (Canada)","funders":"","keywords":"Computer science; End-to-end principle; Computer network","score_opus":0.02692692012041936,"score_gpt":0.27559052982646537,"score_spread":0.248663609706046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297841482","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02339223,0.0001889222,0.9625043,0.009541193,0.0011428354,0.00070903613,0.000074114134,0.00025636528,0.002190975],"genre_scores_gemma":[0.98644555,0.0000031853267,0.008683696,0.002598348,0.0003551195,0.00035245827,0.000029274019,0.000021699696,0.0015106729],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986075,0.000049909686,0.00019858715,0.00045572815,0.00027282626,0.0004154593],"domain_scores_gemma":[0.99909335,0.00024803856,0.00007144469,0.00045788323,0.000015980351,0.00011329031],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003609229,0.00013112141,0.00014360792,0.00008585459,0.00048361887,0.0001463637,0.0010786712,0.00002270446,0.00058397115],"category_scores_gemma":[0.000014034902,0.0001386958,0.00011374037,0.00067191396,0.000021351714,0.00013352581,0.0008775043,0.00023525438,0.000034074892],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000082678314,0.00019734447,0.00019386454,0.000023736611,0.00008599097,0.000096876814,0.006110519,0.012032622,0.0024498615,0.5857924,0.34380928,0.04912483],"study_design_scores_gemma":[0.0028239272,0.0018671373,0.0006461161,0.00019908941,0.000090998925,0.00018044579,0.013627503,0.17296934,0.006685094,0.15329593,0.64513063,0.002483759],"about_ca_topic_score_codex":0.000036938225,"about_ca_topic_score_gemma":0.00005463499,"teacher_disagreement_score":0.9630533,"about_ca_system_score_codex":0.00025298132,"about_ca_system_score_gemma":0.000038321414,"threshold_uncertainty_score":0.63940746},"labels":[],"label_agreement":null},{"id":"W4297841830","doi":"10.21437/interspeech.2022-11066","title":"SoundChoice: Grapheme-to-Phoneme Models with Semantic Disambiguation","year":2022,"lang":"en","type":"article","venue":"Interspeech 2022","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; Université de Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Grapheme; Computer science; Natural language processing; Artificial intelligence","score_opus":0.01880117531733043,"score_gpt":0.23215500689416602,"score_spread":0.21335383157683557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297841830","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11086264,0.00006651214,0.8707237,0.0070368936,0.0007619806,0.00050139375,0.00001942812,0.00048213446,0.0095452955],"genre_scores_gemma":[0.9490138,0.0000062160325,0.04511077,0.0033745156,0.000052196985,0.0003047211,0.000014131215,0.000029002878,0.0020946008],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980057,0.00013853256,0.00022865683,0.0005497168,0.00075391855,0.00032346757],"domain_scores_gemma":[0.9989725,0.00009459046,0.000088397705,0.0006099125,0.0000988285,0.00013578261],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00038444652,0.00017263593,0.0001769186,0.00035677213,0.00036015036,0.00018011783,0.0010381632,0.000024230776,0.001244545],"category_scores_gemma":[0.00003214419,0.00016521798,0.00009836292,0.0011190748,0.000030123183,0.00042592382,0.00050166703,0.00024287103,0.00018963843],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004918166,0.0019700646,0.0011091107,0.00008226929,0.00056980114,0.00075670646,0.026122602,0.009879524,0.022862148,0.13122024,0.12586449,0.67907125],"study_design_scores_gemma":[0.004395087,0.0032189195,0.0019257849,0.0001894835,0.00015237159,0.0014457603,0.013964999,0.67451304,0.03725662,0.15017377,0.10910386,0.003660271],"about_ca_topic_score_codex":0.00011049683,"about_ca_topic_score_gemma":0.00007115402,"teacher_disagreement_score":0.8381512,"about_ca_system_score_codex":0.00017509022,"about_ca_system_score_gemma":0.00006554546,"threshold_uncertainty_score":0.9996685},"labels":[],"label_agreement":null},{"id":"W4297841867","doi":"10.21437/interspeech.2022-10761","title":"Daft-Exprt: Cross-Speaker Prosody Transfer on Any Text for Expressive Speech Synthesis","year":2022,"lang":"en","type":"article","venue":"Interspeech 2022","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ubisoft (Canada)","funders":"","keywords":"Prosody; Computer science; Speech synthesis; Speech recognition; Transfer (computing); Natural language processing","score_opus":0.02503636111819494,"score_gpt":0.28065545976882816,"score_spread":0.2556190986506332,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297841867","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.59537286,0.0004750758,0.2971759,0.015318927,0.007928592,0.00591102,0.001752002,0.0022934373,0.073772155],"genre_scores_gemma":[0.95982546,0.000019872545,0.024098989,0.0034367284,0.00029581424,0.0031958038,0.000032489887,0.00010612616,0.008988721],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9963897,0.0002781676,0.00052930263,0.001169008,0.0009239573,0.0007099057],"domain_scores_gemma":[0.9974507,0.0009381259,0.00011586435,0.0010824369,0.00020646882,0.00020642062],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008573191,0.0003929927,0.0004294277,0.00042462107,0.00068592286,0.00041872406,0.0020495828,0.000104227656,0.005776633],"category_scores_gemma":[0.00034103214,0.00039059806,0.00047149078,0.00062800344,0.000108084016,0.0004684788,0.0004892619,0.0004905102,0.0003491863],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012658646,0.0026469175,0.0003986921,0.00014325064,0.00050716696,0.0008311617,0.007060428,0.00017577203,0.06669888,0.02606915,0.11626756,0.77793515],"study_design_scores_gemma":[0.0018263167,0.0010906863,0.00054106495,0.00010857885,0.000057522862,0.00033112327,0.0024077585,0.0068698316,0.7281638,0.0038558508,0.25342673,0.0013207768],"about_ca_topic_score_codex":0.00002306814,"about_ca_topic_score_gemma":0.0000074496174,"teacher_disagreement_score":0.77661437,"about_ca_system_score_codex":0.00034286958,"about_ca_system_score_gemma":0.00012545768,"threshold_uncertainty_score":0.99985456},"labels":[],"label_agreement":null}]}