{"id":"W4396234746","doi":"10.1109/aihcir61661.2023.00056","title":"Structural Segmentation and Large Language Model Make Behavior Tree More Explainable","year":2023,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Artificial intelligence; Modular design; Tree (set theory); Robot; Machine learning; Robotics; Task (project management); Natural language; Segmentation; Field (mathematics); Reuse; Human–computer interaction; Engineering; Systems engineering; Programming language","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":[0.0009012333,0.001035245,0.0003372287,0.001306402,0.0006247054,0.001328858,0.001244358,0.0008742565,0.003984743],"category_scores_gemma":[0.004461877,0.0005504857,0.00182237,0.0006904319,0.001450301,0.003352118,0.001392018,0.001967888,0.0009631422],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001078487,"about_ca_system_score_gemma":0.001867154,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00631117,"about_ca_topic_score_gemma":0.009858789,"domain_scores_codex":[0.9992138,0.0002519501,0.00006151316,0.0002413546,0.0001797376,0.00005165907],"domain_scores_gemma":[0.9975568,0.00131551,0.0002650649,0.0005055231,0.0002965773,0.00006048779],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000216763,0.0003052362,0.006077909,0.0006938599,0.0001450774,0.001224376,0.008039921,0.1619777,0.04286633,0.4963003,0.009439861,0.2727127],"study_design_scores_gemma":[0.00002634769,0.00006834187,0.001425604,0.0001044229,0.00009750517,0.0003036699,0.0005085719,0.7006472,0.01156833,0.2523933,0.03279626,0.00006049917],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006887331,0.00005463804,0.9888947,0.000232144,0.00001703449,0.00007717207,0.0002882466,0.001667241,0.001881555],"genre_scores_gemma":[0.1592789,0.0001612361,0.8358024,0.0001509012,0.00002747211,0.000272884,0.001515817,0.0007022244,0.002088208],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00631117,"threshold_uncertainty_score":0.01333034,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03308277149821073,"score_gpt":0.3156483097816421,"score_spread":0.2825655382834314,"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."}}