{"id":"W2904811519","doi":"10.1609/aaai.v33i01.33017610","title":"Generalized Planning via Abstraction: Arbitrary Numbers of Objects","year":2019,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"AI-based Problem Solving and Planning","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Microsoft Research","keywords":"Nondeterministic algorithm; Abstraction; Class (philosophy); Computer science; Set (abstract data type); Task (project management); Action (physics); Observable; Theoretical computer science; Mathematical optimization; Artificial intelligence; Mathematics; Programming language","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":[],"consensus_categories":[],"category_scores_codex":[0.0005219006,0.0002172152,0.0003183426,0.0001762337,0.0001370607,0.0001238101,0.00148748,0.00009704944,0.0001255594],"category_scores_gemma":[0.00009176783,0.0001744875,0.0001371077,0.0006820423,0.0001253332,0.0004842481,0.0002035083,0.0003803087,0.0001070633],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003184197,"about_ca_system_score_gemma":0.0001291501,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001175372,"about_ca_topic_score_gemma":0.000004405782,"domain_scores_codex":[0.9981242,0.00002075585,0.0005908057,0.0004420185,0.0004961604,0.0003260084],"domain_scores_gemma":[0.9984529,0.0001588244,0.0006074326,0.000327246,0.0003744133,0.00007915622],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001950927,0.0001860243,0.008726689,0.0002463606,0.00006205821,0.000002189306,0.005706582,0.002854747,0.1951284,0.763301,0.0004088765,0.02318199],"study_design_scores_gemma":[0.00005948777,0.0002200671,0.0007373125,0.0006567584,0.00001389441,0.0000106248,0.0004815426,0.08641644,0.8164232,0.09454636,0.0001299402,0.0003043372],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9048232,0.0000871575,0.02059448,0.001439161,0.001253969,0.0005578072,0.000005323089,0.0001788135,0.07106005],"genre_scores_gemma":[0.9905836,0.000006658773,0.008611096,0.0001846199,0.00005260752,0.000008693952,8.017374e-7,0.00001198325,0.0005399657],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6687546,"threshold_uncertainty_score":0.7115392,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05131861020903025,"score_gpt":0.2826157438696489,"score_spread":0.2312971336606187,"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."}}