{"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":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0003680801,0.0002839159,0.0002750704,0.0001861314,0.0001873281,0.0006474163,0.002327182,0.0002238279,0.00004039285],"category_scores_gemma":[0.00002306493,0.0002224309,0.0000495143,0.0002030074,0.00002387573,0.0008926426,0.01203742,0.0004120957,0.00008718934],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004839355,"about_ca_system_score_gemma":0.0001428313,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003784001,"about_ca_topic_score_gemma":0.0002552313,"domain_scores_codex":[0.9977987,0.00008245494,0.0002839852,0.001052887,0.0004587956,0.0003231941],"domain_scores_gemma":[0.9972762,0.00009264742,0.0001090504,0.002309249,0.0001093299,0.0001035468],"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":[0.0001742801,0.0009425386,0.003694697,0.00713496,0.001056415,0.001368452,0.01556562,0.6534746,0.001856195,0.001238645,0.05656925,0.2569244],"study_design_scores_gemma":[0.0001729606,0.00002460648,0.00008963788,0.0006425824,0.00002384323,0.00001527673,0.0002049535,0.9966636,0.0001785931,0.001010362,0.0006181921,0.000355423],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005476071,0.00009810294,0.9905704,0.0006646246,0.0008361624,0.0002906974,0.00002288516,0.001383695,0.0006574186],"genre_scores_gemma":[0.02537275,0.0002784476,0.9728726,0.0004917154,0.0002043226,0.00002530759,0.0003430524,0.00005506764,0.0003567988],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.343189,"threshold_uncertainty_score":0.995953,"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."}}