{"id":"W4388900178","doi":"10.36227/techrxiv.14852652.v4","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":"Cluster analysis; Hypersphere; Autoencoder; Pairwise comparison; Embedding; Computer science; Cluster (spacecraft); Benchmark (surveying); Artificial intelligence; Set (abstract data type); Pattern recognition (psychology); Data set; Code (set theory); 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":[0.001332412,0.001127708,0.00140789,0.001421859,0.0007666324,0.001321748,0.002500292,0.001329056,0.001991378],"category_scores_gemma":[0.003590316,0.0007774904,0.001237501,0.001384075,0.001546208,0.002925579,0.003068461,0.001865381,0.001067347],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001504732,"about_ca_system_score_gemma":0.001701094,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005599693,"about_ca_topic_score_gemma":0.008504658,"domain_scores_codex":[0.9985873,0.0002876851,0.00007960139,0.0005399595,0.000384555,0.0001210207],"domain_scores_gemma":[0.9981116,0.0003648265,0.0002777595,0.0006343163,0.0004931249,0.0001184265],"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":[0.0001975675,0.0001947183,0.00324039,0.0001874648,0.0001937792,0.00008339019,0.0003161843,0.5591148,0.01701752,0.02881349,0.005045937,0.3855948],"study_design_scores_gemma":[0.00000634361,0.00003005853,0.0002974756,0.000007586233,0.000006562515,0.00003143204,0.00002279738,0.9850269,0.003350979,0.01057199,0.0006368501,0.00001107848],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01428201,0.00009434172,0.9838621,0.00008292797,0.00001361224,0.00003643338,0.00007472274,0.0008398024,0.0007140948],"genre_scores_gemma":[0.4861901,0.0001787218,0.5081757,0.0001685976,0.00005076936,0.0001729727,0.001009773,0.0003258998,0.003727482],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005599693,"threshold_uncertainty_score":0.01113421,"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."}}