{"id":"W4387074701","doi":"10.48550/arxiv.2309.13071","title":"Tree-Based Reconstructive Partitioning: A Novel Low-Data Level Generation Approach","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","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); Development (topology); Training set; Theoretical computer science; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005074955,0.0003507894,0.0003361484,0.000366323,0.0002698773,0.0003161655,0.003556974,0.0003400882,0.00002106143],"category_scores_gemma":[0.0001728916,0.0004292446,0.0001583575,0.0008621297,0.0002567373,0.0007855357,0.002823087,0.0005767982,0.0002173928],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002276542,"about_ca_system_score_gemma":0.0006007096,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004129077,"about_ca_topic_score_gemma":0.0004158136,"domain_scores_codex":[0.996919,0.0001512749,0.0003401536,0.00201095,0.0001674861,0.0004110819],"domain_scores_gemma":[0.9963332,0.0001768808,0.0003664122,0.002687413,0.0002784336,0.0001575938],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002247951,0.0002594479,0.001644069,0.00006781238,0.0001269891,0.00008459261,0.0003810439,0.8231552,0.0003582895,0.1684489,0.001145587,0.004305577],"study_design_scores_gemma":[0.0001495582,0.00002387978,0.0004166804,0.00006872673,0.00004264353,0.000002554592,0.0001595308,0.9813315,0.001834431,0.01546108,0.0000596123,0.0004498419],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05085565,0.00001115761,0.9455024,0.0001575438,0.001107068,0.0003787035,0.0001832014,0.0004753935,0.001328869],"genre_scores_gemma":[0.9392632,0.00002025939,0.05902757,0.00008702888,0.0002409335,0.000004754976,0.0003715583,0.0000303052,0.0009543557],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8884076,"threshold_uncertainty_score":0.9998159,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4882467954376616,"score_gpt":0.2540606662038178,"score_spread":0.2341861292338438,"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."}}