{"id":"W4416363507","doi":"10.54254/2753-8818/2025.dl29641","title":"Learning to Slide: Cross-Size Graph Neural Heuristics for Optimal Puzzle Solving","year":2025,"lang":"","type":"article","venue":"Theoretical and Natural Science","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Heuristics; Artificial neural network; Heuristic; Graph; Inference; Ranging; Scalability; Embedding; DPLL algorithm","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":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.001282664,0.0003351298,0.0004206904,0.0002610254,0.001476206,0.0007849265,0.0006104247,0.0001320332,0.00006395572],"category_scores_gemma":[0.003448143,0.0002823185,0.0001893612,0.001664791,0.002101453,0.0002557962,0.0003914853,0.0006781626,0.000008716956],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007213615,"about_ca_system_score_gemma":0.00007770183,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001077201,"about_ca_topic_score_gemma":0.000001610328,"domain_scores_codex":[0.997301,0.00004328271,0.0004506722,0.0007545605,0.0004109121,0.001039504],"domain_scores_gemma":[0.9981367,0.0008951473,0.00004179389,0.0002432577,0.0002935329,0.0003895578],"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":[0.0002887389,0.00005778861,0.001425407,0.0003431466,0.00008870824,0.00001205315,0.0009854103,0.4403358,0.01510717,0.4557872,0.00008061314,0.08548791],"study_design_scores_gemma":[0.0003133894,0.0001529225,0.000751895,0.0001405073,0.0001036797,0.000004747919,0.0001430159,0.9745192,0.002382196,0.02093885,0.0001736437,0.0003759584],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.881576,0.001876096,0.1123745,0.001258007,0.001103998,0.0003479903,0.00001533197,0.0001617963,0.00128623],"genre_scores_gemma":[0.9913367,0.00009919868,0.007377969,0.000247447,0.0001332913,0.0000187012,0.000001881025,0.00001880742,0.0007660004],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5341833,"threshold_uncertainty_score":0.9999629,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004787438996856412,"score_gpt":0.270022258130102,"score_spread":0.2652348191332456,"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."}}