{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000420377,0.0001426875,0.0002258235,0.0002391303,0.0001872832,0.000278659,0.0007342274,0.00006889757,0.00000404244],"category_scores_gemma":[0.0003034831,0.0001096074,0.0001241061,0.001085564,0.0001839777,0.0003065111,0.0002476859,0.0001270552,0.000003793854],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003243656,"about_ca_system_score_gemma":0.00006312655,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004158007,"about_ca_topic_score_gemma":0.000009188728,"domain_scores_codex":[0.9988428,0.00001008369,0.0003378238,0.0004035479,0.0002162461,0.0001895173],"domain_scores_gemma":[0.9988083,0.00009247326,0.0002131155,0.0002669881,0.000578517,0.00004057212],"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":[0.00005118971,0.00003792491,0.00001293779,0.00006700141,0.00004379973,1.712561e-7,0.00151687,0.00002058241,0.2595242,0.3555461,0.0001195268,0.3830598],"study_design_scores_gemma":[0.00001101363,0.00002588738,0.00002623952,0.00005459024,0.00003413294,2.925905e-7,0.0001755064,0.5446332,0.3892959,0.06566866,0.00001082508,0.00006377521],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01429802,0.00002164781,0.9795203,0.003386743,0.00006272776,0.0003103738,0.000005186457,0.0001005522,0.002294499],"genre_scores_gemma":[0.917088,0.00003121791,0.08206923,0.000171976,0.00001132598,0.000002774597,7.124336e-7,0.000004971431,0.0006198209],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.90279,"threshold_uncertainty_score":0.4469659,"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."}}