{"id":"W4393988223","doi":"10.1002/aaai.12169","title":"The 2023 International Planning Competition","year":2024,"lang":"en","type":"article","venue":"AI Magazine","topic":"AI-based Problem Solving and Planning","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Engineering and Physical Sciences Research Council; European Research Council; Natural Sciences and Engineering Research Council of Canada; Vetenskapsrådet; University of Edinburgh","keywords":"Competition (biology); Business; Biology; Ecology","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003255419,0.00006748229,0.00004484343,0.00005516857,0.000167581,0.0005623933,0.0004773322,0.0000247633,0.00004279362],"category_scores_gemma":[0.00002536757,0.00004809053,0.00003182146,0.0001912074,0.00002199427,0.0002853956,0.0001143797,0.0001750125,0.0008747465],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002251208,"about_ca_system_score_gemma":0.00003657863,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005367625,"about_ca_topic_score_gemma":0.000002595556,"domain_scores_codex":[0.9993525,0.00002714659,0.0001134167,0.0001803915,0.0001767501,0.0001498508],"domain_scores_gemma":[0.9994869,0.0002444953,0.00001955075,0.0001822798,0.00003567222,0.00003114274],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000007830597,0.00001350811,0.001246337,0.00002518496,0.00005867537,0.0001954678,0.0007158253,0.00258944,0.0009478563,0.5317281,0.3755443,0.0869275],"study_design_scores_gemma":[0.00006130783,0.00002515227,0.001468681,0.0001231965,0.000002560851,0.00003428248,0.000006043193,0.2723988,0.00007570555,0.006877787,0.7188427,0.00008374228],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001131958,0.002498971,0.8980573,0.04589178,0.003887356,0.00007437711,0.000007865477,0.0005602849,0.04789012],"genre_scores_gemma":[0.9731548,0.00005730288,0.00930899,0.002000171,0.0006756233,0.00001811736,0.00004891052,0.00001533021,0.01472078],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9720228,"threshold_uncertainty_score":0.9999032,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01289369188400001,"score_gpt":0.2739984527139299,"score_spread":0.2611047608299298,"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."}}