{"id":"W4381193492","doi":"10.36227/techrxiv.14852652.v3","title":"Deep Clustering with Self-supervision using Pairwise Data Similarities","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Hypersphere; Cluster analysis; Autoencoder; Pairwise comparison; Embedding; Cluster (spacecraft); Computer science; Artificial intelligence; Benchmark (surveying); Set (abstract data type); Pattern recognition (psychology); Mathematics; Data mining; Deep learning; Geography","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001396961,0.0009914543,0.001264945,0.001254997,0.0006918283,0.001212891,0.002220281,0.001244936,0.001662622],"category_scores_gemma":[0.003696258,0.0007151578,0.001077985,0.001267018,0.001514998,0.002907487,0.00291947,0.001729682,0.0008131795],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001363708,"about_ca_system_score_gemma":0.00158952,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004394241,"about_ca_topic_score_gemma":0.006713081,"domain_scores_codex":[0.9986125,0.0003222844,0.00007983924,0.0004866604,0.0003904873,0.0001081175],"domain_scores_gemma":[0.9980484,0.0004256347,0.0003108622,0.0006122772,0.0004851338,0.0001176078],"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":[0.0001828594,0.0001968405,0.00324187,0.0001849001,0.0001824509,0.00008246137,0.0003117567,0.582773,0.01693334,0.02969147,0.003519013,0.3627],"study_design_scores_gemma":[0.000005759545,0.00003511858,0.0002950746,0.000006985978,0.000006324277,0.00003045913,0.00002171721,0.9860124,0.003380395,0.009663216,0.0005321587,0.00001043912],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01478438,0.00008457417,0.9837348,0.00007339346,0.00001078454,0.00003357964,0.00005202713,0.0006054014,0.0006209066],"genre_scores_gemma":[0.5196005,0.0001648747,0.4761573,0.0001306726,0.0000432978,0.0001527179,0.0006514773,0.0002292005,0.002869985],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004394241,"threshold_uncertainty_score":0.009894431,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1368079784655158,"score_gpt":0.3048059021646434,"score_spread":0.1679979236991277,"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."}}