{"id":"W1574220574","doi":"10.5591/978-1-57735-516-8/ijcai11-439","title":"A correctness result for reasoning about one-dimensional planning problems","year":2010,"lang":"en","type":"article","venue":"","topic":"Logic, Reasoning, and Knowledge","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Correctness; Computer science; Plan (archaeology); Domain (mathematical analysis); Semantics (computer science); Representation (politics); Class (philosophy); Planner; Theoretical computer science; Algorithm; Artificial intelligence; Mathematics; Programming language","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":[0.0008472849,0.0001835,0.0002187237,0.00008653195,0.000348024,0.0002418996,0.000768679,0.0001368183,0.00004038842],"category_scores_gemma":[0.0005246394,0.0001488882,0.0000942972,0.0002465894,0.00005758554,0.0003817206,0.0002484382,0.0002948917,0.00006766967],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002728588,"about_ca_system_score_gemma":0.0001805207,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005301858,"about_ca_topic_score_gemma":0.0001234819,"domain_scores_codex":[0.9983369,0.0000296149,0.0002604706,0.0005555661,0.0003302205,0.0004872544],"domain_scores_gemma":[0.9985206,0.0003258123,0.000120474,0.0005000457,0.0003669719,0.0001660547],"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":[0.00005746975,0.0002881992,0.002901291,0.00007100072,0.00005426086,0.0000172455,0.004292978,0.0006492877,0.01624171,0.9204771,0.02843055,0.0265189],"study_design_scores_gemma":[0.003429712,0.0005319844,0.01487965,0.0004435903,0.00003510248,0.0002384233,0.0001171785,0.8204523,0.01752527,0.02910231,0.1117574,0.001487147],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07331135,0.0002528686,0.8076087,0.0007462908,0.004034924,0.0007882794,0.000005230399,0.0009501289,0.1123022],"genre_scores_gemma":[0.799059,0.00000143584,0.1941684,0.0003195773,0.0003767632,0.0001018062,0.000008874989,0.00001995564,0.005944186],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8913748,"threshold_uncertainty_score":0.6071483,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0264066088234619,"score_gpt":0.2718747890836058,"score_spread":0.2454681802601439,"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."}}