{"id":"W3174309074","doi":"10.1613/jair.1.13768","title":"Classical Planning in Deep Latent Space","year":2022,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"AI-based Problem Solving and Planning","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Bottleneck; Artificial intelligence; Domain (mathematical analysis); Representation (politics); Plan (archaeology); Automated planning and scheduling; Set (abstract data type); Space (punctuation); Rotation formalisms in three dimensions; Action (physics); Machine learning; Theoretical computer science; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008235336,0.0008544319,0.0007524069,0.0005865708,0.0004530831,0.001176096,0.001256482,0.001056002,0.004546737],"category_scores_gemma":[0.002932748,0.0005205376,0.0007418416,0.0007492372,0.001727835,0.002500034,0.001705991,0.002098554,0.0005729618],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002240232,"about_ca_system_score_gemma":0.002164581,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01807612,"about_ca_topic_score_gemma":0.02736291,"domain_scores_codex":[0.9995203,0.0001589282,0.00002169329,0.0001340537,0.0001000818,0.00006496078],"domain_scores_gemma":[0.9987329,0.0008669683,0.00007946213,0.0001618932,0.00009458003,0.00006432886],"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":[0.0001395897,0.00005933486,0.0006735415,0.0001643527,0.00004105512,0.00006981807,0.00009225253,0.8667201,0.001022308,0.05744185,0.002777603,0.07079807],"study_design_scores_gemma":[0.00001396718,0.000014619,0.00006294809,0.000009197568,0.000004074019,0.000007450165,0.000008845401,0.9496291,0.0005416574,0.04900867,0.0006955105,0.000003898197],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04483442,0.000896975,0.9403488,0.0008892372,0.0000503718,0.00008798261,0.0006705819,0.005151138,0.00707059],"genre_scores_gemma":[0.7041638,0.0006280914,0.2872654,0.0003554156,0.00004252662,0.0002252679,0.001630412,0.0003426579,0.005346522],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01807612,"threshold_uncertainty_score":0.03594184,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1989048434107749,"score_gpt":0.4151454853527687,"score_spread":0.2162406419419938,"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."}}