{"id":"W4409367667","doi":"10.1609/aaai.v39i6.32683","title":"VHM: Versatile and Honest Vision Language Model for Remote Sensing Image Analysis","year":2025,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Image (mathematics); Computer vision; Natural language processing; Remote sensing; Geology","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":[0.002665371,0.001395851,0.000834409,0.001751362,0.000641887,0.002334894,0.004301752,0.001765719,0.006515412],"category_scores_gemma":[0.009211672,0.0006935677,0.002570984,0.0008445578,0.0009937249,0.005410419,0.002574497,0.003485954,0.005430682],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001974823,"about_ca_system_score_gemma":0.002184974,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008603046,"about_ca_topic_score_gemma":0.01190915,"domain_scores_codex":[0.9977663,0.0006570758,0.0001769587,0.0006514895,0.0005816691,0.0001665285],"domain_scores_gemma":[0.9965815,0.001676283,0.0002419648,0.0006843351,0.0006679481,0.0001480225],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009806544,0.0009029026,0.005591009,0.001202026,0.0002751542,0.0006375661,0.001248352,0.1179424,0.02766601,0.09309001,0.1443816,0.6060823],"study_design_scores_gemma":[0.00003344707,0.0001070965,0.0005909538,0.00004939377,0.00002920891,0.0001459016,0.0001300449,0.929361,0.006655272,0.04303086,0.01980961,0.00005719929],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01256266,0.000723647,0.9428741,0.001259987,0.0002192105,0.0006428447,0.007856265,0.02962564,0.004235565],"genre_scores_gemma":[0.2115661,0.0004465454,0.7527769,0.001819406,0.0002157985,0.001518931,0.02371293,0.001315315,0.006628085],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008603046,"threshold_uncertainty_score":0.02179623,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04229463515084809,"score_gpt":0.3309535695221735,"score_spread":0.2886589343713254,"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."}}