{"id":"W4307783259","doi":"10.48550/arxiv.2210.15775","title":"Evaluating context-invariance in unsupervised speech representations","year":2022,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Connaught Fund; Agence Nationale de la Recherche; Natural Sciences and Engineering Research Council of Canada; Morgan Family Foundation","keywords":"Computer science; Context (archaeology); Benchmark (surveying); Word (group theory); Independence (probability theory); Artificial intelligence; Speech recognition; Natural language processing; Linguistics; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000749003,0.000254255,0.0003371516,0.0004751599,0.0002200497,0.0001495632,0.001879207,0.0001623561,0.001164995],"category_scores_gemma":[0.0002512892,0.0003351028,0.0002034817,0.001149533,0.00006210238,0.000383172,0.001979849,0.0007209481,0.0001388997],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003624489,"about_ca_system_score_gemma":0.0003441775,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006538223,"about_ca_topic_score_gemma":0.0002995169,"domain_scores_codex":[0.9972728,0.0005888933,0.0003122787,0.001287708,0.0002009865,0.0003373516],"domain_scores_gemma":[0.9977781,0.0004143998,0.0002325382,0.00130411,0.0001456004,0.0001252915],"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":[0.0001889667,0.001254523,0.0356845,0.0002706978,0.0003885925,0.006263089,0.004720371,0.3123739,0.0006214482,0.415152,0.001785598,0.2212963],"study_design_scores_gemma":[0.001144684,0.00004908994,0.005724957,0.00009953677,0.00004270533,0.00001272088,0.0009284165,0.9328069,0.000381421,0.05769861,0.0005230621,0.0005878747],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7393575,0.0001005145,0.2344604,0.0007241067,0.001277815,0.0008654009,0.00004730264,0.0004583572,0.0227086],"genre_scores_gemma":[0.9821956,0.00009460294,0.01467832,0.0003315611,0.0000419976,0.000009085494,0.00002810831,0.00001798884,0.002602702],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.620433,"threshold_uncertainty_score":0.9999101,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2375631459508236,"score_gpt":0.2724413548986045,"score_spread":0.03487820894778088,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}