{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004574454,0.001383654,0.001216661,0.001694534,0.00043753,0.001040032,0.001258126,0.0007758792,0.002363773],"category_scores_gemma":[0.001443553,0.0006440381,0.001576359,0.001122148,0.0006291937,0.001084488,0.001964155,0.0006956347,0.001365172],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005337142,"about_ca_system_score_gemma":0.000664359,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002313079,"about_ca_topic_score_gemma":0.005092993,"domain_scores_codex":[0.9995186,0.00007335781,0.00003462647,0.0001695591,0.0001588323,0.00004498695],"domain_scores_gemma":[0.9996762,0.00009014523,0.00004668643,0.00009578629,0.00005747932,0.00003365938],"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":[0.0002851607,0.0001438423,0.002244046,0.0003352662,0.00008530812,0.000452851,0.0005736705,0.05723005,0.1897453,0.004751188,0.004514199,0.7396392],"study_design_scores_gemma":[0.00003081932,0.0001293063,0.001466332,0.00002396956,0.00004027471,0.0003728791,0.0001453513,0.9296491,0.05582399,0.005080736,0.007184894,0.00005225611],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007981132,0.00009583232,0.9869464,0.00002745802,0.000009400748,0.00002995857,0.00006743179,0.004540029,0.0003024165],"genre_scores_gemma":[0.1287951,0.0001338809,0.8688182,0.00005839959,0.00001460019,0.0001504224,0.0004323048,0.0005793929,0.00101769],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002363773,"threshold_uncertainty_score":0.007907629,"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."}}