{"id":"W4392678259","doi":"10.1609/aaai.v38i16.29789","title":"Cross-Modal and Uni-Modal Soft-Label Alignment for Image-Text Retrieval","year":2024,"lang":"en","type":"preprint","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Modal; Computer science; Artificial intelligence; Image (mathematics); Computer vision; Information retrieval; Materials science","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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001135656,0.0005534402,0.0005682816,0.0002390047,0.0002974444,0.001838608,0.003172439,0.0004107036,0.00004189403],"category_scores_gemma":[0.0006250326,0.00043053,0.0002733739,0.0005572588,0.0008077384,0.0003642429,0.003489091,0.0009768978,0.00005545514],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001576297,"about_ca_system_score_gemma":0.0004017445,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003114249,"about_ca_topic_score_gemma":0.00000145765,"domain_scores_codex":[0.9962267,0.00002414616,0.001013639,0.001376209,0.0008238708,0.0005353874],"domain_scores_gemma":[0.9966813,0.0001743288,0.0007111288,0.0006526503,0.001619643,0.0001609099],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001701129,0.0001772919,0.00001521431,0.0006730813,0.00005259823,8.843393e-7,0.000799074,0.000003155284,0.07892071,0.8014686,0.0003112771,0.117408],"study_design_scores_gemma":[0.00002878882,0.0001703309,0.00002924019,0.0003356265,0.00003118932,0.000005210607,0.00007838849,0.07959083,0.4951804,0.4240792,0.0001732804,0.0002974869],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08619178,0.0008318443,0.8575628,0.0298548,0.004132107,0.005872273,0.0003418625,0.001414557,0.01379798],"genre_scores_gemma":[0.9775878,0.0002341854,0.01978002,0.0002099154,0.0002222068,0.0001628227,0.000004463351,0.00004697627,0.001751647],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.891396,"threshold_uncertainty_score":0.9998146,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07936549470850399,"score_gpt":0.3473004146126378,"score_spread":0.2679349199041339,"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."}}