{"id":"W3022326288","doi":"10.1609/aaai.v26i1.8195","title":"Generalizing and Executing Plans","year":2021,"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":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Plan (archaeology); Generalization; Computer science; Task (project management); Representation (politics); Key (lock); Process (computing); Order (exchange); Artificial intelligence; Management science; Operations research; Computer security; Systems engineering; Engineering; Programming language; Political science; Business; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.0004494214,0.0001625299,0.0001908862,0.00006527988,0.0002895102,0.0003439164,0.0008550909,0.00007132769,0.0000224932],"category_scores_gemma":[0.0003273276,0.0001304291,0.00006109645,0.0004451968,0.0001155244,0.000284574,0.0004182283,0.000265942,0.00001722406],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000179145,"about_ca_system_score_gemma":0.0001018824,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003205195,"about_ca_topic_score_gemma":0.000008287654,"domain_scores_codex":[0.9985808,0.00002063515,0.0003552062,0.0004443401,0.000298321,0.0003007348],"domain_scores_gemma":[0.9989849,0.0001229502,0.0002163509,0.0002229024,0.0003732253,0.00007970838],"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":[0.000009834254,0.00003527733,0.001411431,0.00004473805,0.00001172838,0.00000297042,0.002051866,0.00009768039,0.07269946,0.8716061,0.0001848714,0.05184403],"study_design_scores_gemma":[0.00002477671,0.00007551574,0.0002712816,0.0004440979,0.00001082479,0.00003365993,0.0007169875,0.100325,0.7861642,0.1113581,0.0003244358,0.0002511025],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7988324,0.0004643653,0.1356309,0.01781976,0.001140945,0.0004200779,0.00001537993,0.0003530763,0.04532308],"genre_scores_gemma":[0.9852023,0.00004042027,0.01402689,0.0003705485,0.00005683706,0.00000596743,5.218966e-7,0.000008108947,0.0002884096],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7602481,"threshold_uncertainty_score":0.5318743,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07715901879387925,"score_gpt":0.2800754265498518,"score_spread":0.2029164077559725,"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."}}