{"id":"W4220945643","doi":"10.36227/techrxiv.19357979","title":"Deep Multi-Representation Learning for Data Clustering","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"Compute Canada; Natural Sciences and Engineering Research Council of Canada; McGill University","keywords":"Cluster analysis; Autoencoder; Computer science; Artificial intelligence; Clustering high-dimensional data; Pattern recognition (psychology); Representation (politics); Embedding; Benchmark (surveying); Correlation clustering; Cluster (spacecraft); AKA; Subspace topology; Data mining; Deep learning; Geography","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0003485669,0.0001421264,0.0001596649,0.0001099501,0.0002504069,0.0003091955,0.001946607,0.00009362899,0.0002214281],"category_scores_gemma":[0.0001367588,0.0001430509,0.00006689513,0.00009519776,0.000008563364,0.0004700031,0.01067458,0.0004085185,0.00002924698],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003597569,"about_ca_system_score_gemma":0.00005052331,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001571445,"about_ca_topic_score_gemma":0.00005496361,"domain_scores_codex":[0.9984114,0.00009854267,0.0002332493,0.0008354782,0.0002288621,0.0001924424],"domain_scores_gemma":[0.9984131,0.0001439117,0.0001573333,0.001176181,0.00005957555,0.00004991759],"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":[0.00002641974,0.0001410488,0.0007204749,0.0003225112,0.00007970969,0.000009654623,0.001842096,0.5045418,0.000938828,0.0003416197,0.009976599,0.4810593],"study_design_scores_gemma":[0.0002706987,0.00001704465,0.0001151589,0.00002903991,0.000008597836,0.000001820244,0.0001913328,0.9897557,0.0002468952,0.0005313888,0.008645567,0.0001867172],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004282159,0.00007237762,0.9960807,0.0004509512,0.001210601,0.0004800271,0.000009253973,0.0003136685,0.0009541831],"genre_scores_gemma":[0.02962517,0.00008881401,0.963506,0.0003188409,0.0001440738,0.000415456,0.002466086,0.00002664492,0.003408924],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.485214,"threshold_uncertainty_score":0.9973269,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1619162002673303,"score_gpt":0.3748241467168809,"score_spread":0.2129079464495506,"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."}}