{"id":"W7132919007","doi":"","title":"Generalization in Planning","year":2022,"lang":"","type":"dissertation","venue":"TSpace","topic":"AI-based Problem Solving and Planning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Generalization; Leverage (statistics); Automated planning and scheduling; Action (physics); Automation; State (computer science)","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009690776,0.0004856647,0.0004761996,0.0006831483,0.0006325687,0.0003549948,0.001121636,0.000318123,0.001229937],"category_scores_gemma":[0.00009140195,0.0006137125,0.0001190828,0.001593237,0.00002124998,0.0003508875,0.0002190219,0.001124946,0.00006825891],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002871169,"about_ca_system_score_gemma":0.0005765635,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001562686,"about_ca_topic_score_gemma":0.0001072614,"domain_scores_codex":[0.9964638,0.0004597433,0.0006225635,0.001031405,0.0007223296,0.0007002085],"domain_scores_gemma":[0.9983296,0.0002334067,0.0005551984,0.0006534614,0.00009208445,0.0001362174],"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":[0.0001315846,0.0001519629,0.01823995,0.0004665448,0.00005547326,0.0004488003,0.3393466,0.6121224,0.001081506,0.006866864,0.006260611,0.01482772],"study_design_scores_gemma":[0.001135139,0.0003963651,0.01049737,0.001528342,0.00005688293,0.00003320325,0.01647282,0.9219911,0.001042274,0.0008578082,0.04414208,0.001846577],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6828454,0.02093344,0.2271155,0.002060929,0.01077726,0.001583464,0.00001972019,0.0006846044,0.05397966],"genre_scores_gemma":[0.9054573,0.000244646,0.01762885,0.0008450457,0.0004369588,0.0002284749,0.002817783,0.0001571695,0.07218373],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3228738,"threshold_uncertainty_score":0.9996831,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03239516550572556,"score_gpt":0.3563130111429674,"score_spread":0.3239178456372419,"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."}}