{"id":"W4387394661","doi":"10.1609/aiide.v19i1.27520","title":"Tree-Based Reconstructive Partitioning: A Novel Low-Data Level Generation Approach","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Tree (set theory); Artificial intelligence; Machine learning; Quality (philosophy); Theoretical computer science; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004264899,0.000335979,0.0003186373,0.0002664928,0.0002621045,0.0009839517,0.001932834,0.00009270869,0.00002464575],"category_scores_gemma":[0.0006042992,0.0002634972,0.00012886,0.0007279161,0.0004437896,0.002222523,0.0009714849,0.0003030897,0.00008618116],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009356581,"about_ca_system_score_gemma":0.0001136215,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000299445,"about_ca_topic_score_gemma":0.0000128615,"domain_scores_codex":[0.9972696,0.00002127421,0.0007228793,0.0009611382,0.0005899939,0.0004350715],"domain_scores_gemma":[0.998122,0.0001906788,0.0004709696,0.0005418942,0.000548536,0.0001259506],"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":[0.0002413467,0.00109085,0.001144887,0.00007485496,0.0001331761,0.000001824891,0.00444768,0.0005890088,0.05002153,0.5135295,0.0006746283,0.4280507],"study_design_scores_gemma":[0.00004619038,0.000239366,0.0002276386,0.0002211324,0.00001165864,0.000005515428,0.003430523,0.6657569,0.3153313,0.01438074,0.00007958847,0.0002694377],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.472787,0.00001462551,0.5000393,0.004416767,0.001051289,0.001327058,0.0002521703,0.0002817918,0.01983005],"genre_scores_gemma":[0.9968106,0.00001750977,0.002467315,0.0002374134,0.00009296517,0.00007968303,0.00003413895,0.00001855254,0.0002418074],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6651679,"threshold_uncertainty_score":0.9999817,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2060435326138589,"score_gpt":0.3205882956809046,"score_spread":0.1145447630670457,"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."}}