{"id":"W7160037063","doi":"10.1109/iccv51701.2025.00027","title":"Bootstrapping Grounded Chain-of-Thought in Multimodal Llms for Data-Efficient Model Adaptation","year":2025,"lang":"","type":"article","venue":"","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Bootstrapping (finance); Adaptation (eye); Process (computing); Key (lock)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002038807,0.0003728606,0.0005422525,0.0007419582,0.0002995058,0.0003113941,0.001770542,0.0002113455,0.00002473464],"category_scores_gemma":[0.0004131214,0.0004052024,0.000159749,0.00153081,0.0001431331,0.000769234,0.0007113614,0.0003452287,0.000009178973],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001741466,"about_ca_system_score_gemma":0.0008644718,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002963968,"about_ca_topic_score_gemma":0.000241482,"domain_scores_codex":[0.9959452,0.000200721,0.001316935,0.001292949,0.0005354357,0.0007087847],"domain_scores_gemma":[0.9972264,0.0005998483,0.0004177908,0.001317986,0.0003097267,0.0001282523],"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":[0.00008084013,0.0002738727,0.00002559786,0.0001301617,0.00003341192,0.000001497561,0.002972882,0.6620557,0.0003947305,0.2124381,0.00009171827,0.1215015],"study_design_scores_gemma":[0.00269154,0.00007917192,0.0004388021,0.0002623337,0.00003072193,0.000001112764,0.001734788,0.9904531,0.0002567631,0.002399107,0.001282254,0.0003703091],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004432261,0.0003588948,0.9834442,0.001187062,0.0009004623,0.001347072,0.00002382428,0.00009892174,0.00820729],"genre_scores_gemma":[0.7398178,0.00002868003,0.256638,0.0003901776,0.00003287669,0.00005111963,0.00005098738,0.00001641237,0.002973967],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7353855,"threshold_uncertainty_score":0.99984,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0995441739132138,"score_gpt":0.3358859772925355,"score_spread":0.2363418033793217,"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."}}