{"id":"W4388235576","doi":"10.1109/sampta59647.2023.10301400","title":"Sampling Informative Positives Pairs in Contrastive Learning","year":2023,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Similarity (geometry); Sampling (signal processing); Artificial intelligence; Representation (politics); Computer science; Class (philosophy); Space (punctuation); False positive paradox; Machine learning; Mathematics; Pattern recognition (psychology)","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":[0.01107105,0.001404234,0.001763215,0.001645206,0.001270348,0.002434351,0.00328079,0.002623329,0.002582147],"category_scores_gemma":[0.04748532,0.0009285454,0.001025423,0.001017964,0.004903365,0.004797327,0.004144539,0.003543352,0.0006292819],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001499381,"about_ca_system_score_gemma":0.00101054,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009011728,"about_ca_topic_score_gemma":0.001127155,"domain_scores_codex":[0.9934727,0.004017615,0.0001736861,0.001151147,0.0009725188,0.0002122201],"domain_scores_gemma":[0.9778364,0.0174032,0.001136679,0.002243629,0.0008435405,0.0005365507],"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":[0.0008621902,0.000728743,0.008240446,0.0003558343,0.0001980033,0.0006088319,0.0008052961,0.2034761,0.007536789,0.5924615,0.004306803,0.1804196],"study_design_scores_gemma":[0.0001047966,0.000278651,0.0005051414,0.00005985179,0.00004081168,0.0002097943,0.00007960176,0.6877892,0.003518336,0.3051343,0.002244761,0.00003479401],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03557168,0.000360425,0.9605787,0.0006201195,0.0000358649,0.0001587597,0.00007713931,0.0002172438,0.002379921],"genre_scores_gemma":[0.681834,0.0003519482,0.3118648,0.0008899298,0.000177935,0.000624204,0.0004344416,0.0001723972,0.003650294],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01107105,"threshold_uncertainty_score":0.05854994,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01514522349937,"score_gpt":0.2783324649142953,"score_spread":0.2631872414149253,"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."}}