{"id":"W4404914975","doi":"10.1109/ismar-adjunct64951.2024.00050","title":"Function-Adaptive Affordance Extraction from 3D Objects Using LLM for Interaction Authoring with Augmented Artifacts","year":2024,"lang":"en","type":"article","venue":"","topic":"Image Processing and 3D Reconstruction","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Affordance; Computer science; Human–computer interaction; Function (biology); Augmented reality; Extraction (chemistry); Multimedia; Computer vision; Artificial intelligence; Chromatography; Chemistry","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":[0.0001387569,0.0001565524,0.0001188897,0.0001721758,0.0002662062,0.0006150653,0.000111021,0.00006056007,0.00002839219],"category_scores_gemma":[0.00001652361,0.0001283701,0.00004947775,0.0003693697,0.00002745219,0.002733595,0.00003007024,0.0001762076,0.00003172607],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001600165,"about_ca_system_score_gemma":0.0001595304,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001170351,"about_ca_topic_score_gemma":0.00005162309,"domain_scores_codex":[0.998884,0.00002613693,0.0001917656,0.0005044548,0.0001717023,0.0002219339],"domain_scores_gemma":[0.9994289,0.0001239061,0.00009262313,0.0001741734,0.0001252874,0.00005512048],"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":[0.0002565721,0.00008338115,0.00008876772,0.0001009861,0.0001698362,0.00001469215,0.001071999,0.004005479,0.05035796,0.00368015,0.0003053976,0.9398648],"study_design_scores_gemma":[0.0002182522,0.0001838383,0.0001027913,0.0003322738,0.00004372025,0.00008961217,0.0002984273,0.9436515,0.05171305,0.002037834,0.001128692,0.0002000271],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03852035,0.0001553252,0.9557303,0.0001095984,0.003253983,0.0001810962,0.000002103382,0.0005642903,0.001482968],"genre_scores_gemma":[0.7033677,0.000003177032,0.2956239,0.00003830431,0.0002453082,0.00002512285,0.00000544411,0.00001411401,0.0006769473],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9396647,"threshold_uncertainty_score":0.5931089,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03298517318615567,"score_gpt":0.289957959431307,"score_spread":0.2569727862451513,"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."}}