{"id":"W4396758629","doi":"10.1145/3589334.3645668","title":"DualCL: Principled Supervised Contrastive Learning as Mutual Information Maximization for Text Classification","year":2024,"lang":"en","type":"article","venue":"","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Mutual information; Artificial intelligence; Maximization; Natural language processing; Machine learning; Pattern recognition (psychology); Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.0003540937,0.00009645381,0.000104618,0.0002269601,0.0001509416,0.0006925672,0.0001914174,0.00005170944,0.0001172817],"category_scores_gemma":[0.0001272134,0.00008364017,0.0000829405,0.0004364414,0.00001251716,0.001780561,0.00005139182,0.00007396383,0.0003373114],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004747473,"about_ca_system_score_gemma":0.0000720597,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006655846,"about_ca_topic_score_gemma":0.000001505574,"domain_scores_codex":[0.9990765,0.00003756997,0.0002971972,0.0002159541,0.000217026,0.0001557617],"domain_scores_gemma":[0.9994156,0.0001691203,0.00007064432,0.0001359041,0.0001623947,0.00004631641],"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":[0.00002222962,0.00002748815,0.0006602909,0.00004790364,0.0001029656,7.933514e-7,0.004544199,0.002961178,0.001480316,0.7753075,0.002384336,0.2124608],"study_design_scores_gemma":[0.0002831835,0.00006461512,0.001030015,0.00002086934,0.00001560605,0.000001212385,0.0005163967,0.9712005,0.0009447971,0.0005746752,0.02523504,0.0001131242],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008208943,0.00003869557,0.9837194,0.001127175,0.0002949265,0.000259408,0.000001129773,0.0003285319,0.006021769],"genre_scores_gemma":[0.970134,0.0000193479,0.02662029,0.0002740861,0.0000892512,0.00006036309,0.0001982765,0.000007899286,0.002596549],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9682393,"threshold_uncertainty_score":0.6678441,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02243108802316635,"score_gpt":0.2795962578342131,"score_spread":0.2571651698110468,"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."}}