{"id":"W4393147811","doi":"10.1609/aaai.v38i10.29037","title":"Make Prompts Adaptable: Bayesian Modeling for Vision-Language Prompt Learning with Data-Dependent Prior","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea","keywords":"Computer science; Bayesian probability; Artificial intelligence; Machine learning; Bayesian statistics; Natural language processing; Bayesian inference; Psychology; Cognitive 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009833882,0.0002964724,0.0002811798,0.0001780564,0.0004061316,0.0008955396,0.003255559,0.00009055988,0.00002649962],"category_scores_gemma":[0.0004286354,0.0002065518,0.00007377079,0.000739344,0.0001250209,0.0006621016,0.000808603,0.0006359485,0.00004488758],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005786073,"about_ca_system_score_gemma":0.000288213,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001721956,"about_ca_topic_score_gemma":0.00003807832,"domain_scores_codex":[0.9972622,0.00002450498,0.0005396551,0.001102774,0.0006255058,0.0004453324],"domain_scores_gemma":[0.9982677,0.000192052,0.0002438739,0.0007039875,0.0004831091,0.0001092548],"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":[0.0001019874,0.00019247,0.00006556595,0.000322932,0.00005477062,0.000001873971,0.00351801,0.01553611,0.02934261,0.5541974,0.0000723679,0.396594],"study_design_scores_gemma":[0.00003526417,0.0002651373,0.00002148985,0.0005929664,0.00002784395,0.00001164319,0.0004764124,0.961006,0.02271389,0.01436162,0.0002301645,0.0002575179],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05095797,0.0000906986,0.9382318,0.005353368,0.0002294563,0.001646799,0.0000227092,0.0004986961,0.002968509],"genre_scores_gemma":[0.9497629,0.000009684145,0.04920538,0.00005264312,0.00009633319,0.0001931614,0.00000667273,0.0000373476,0.0006358573],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9454699,"threshold_uncertainty_score":0.8635709,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07165001741030415,"score_gpt":0.3458690247856473,"score_spread":0.2742190073753432,"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."}}