{"id":"W2624303218","doi":"10.1103/physreve.96.023312","title":"Patch-planting spin-glass solution for benchmarking","year":2017,"lang":"en","type":"article","venue":"Physical review. E","topic":"Theoretical and Computational Physics","field":"Physics and Astronomy","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"QLT (Canada)","funders":"Lincoln Laboratory, Massachusetts Institute of Technology; Office of the Director of National Intelligence; Texas A and M University; Intelligence Advanced Research Projects Activity; National Science Foundation","keywords":"Spin glass; Computational complexity theory; Scaling; Simulated annealing; Computer science; Heuristic; Monte Carlo method; Benchmarking; Algorithm; Set (abstract data type); Frustration; Mathematical optimization; Statistical physics; Mathematics; Theoretical computer science; Physics; Statistics; Geometry; Quantum mechanics","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":[0.001363136,0.0009322132,0.001005564,0.0006963026,0.0005811997,0.0008791944,0.002486253,0.001796521,0.01188362],"category_scores_gemma":[0.007307941,0.000384933,0.0006536268,0.001011742,0.0005592214,0.001186232,0.0008844307,0.00160724,0.001304002],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009088299,"about_ca_system_score_gemma":0.001386255,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003614811,"about_ca_topic_score_gemma":0.006139209,"domain_scores_codex":[0.9994223,0.0001952803,0.00003132793,0.0001110041,0.000149132,0.00009096856],"domain_scores_gemma":[0.9977534,0.001326916,0.00009522607,0.0004246084,0.0002806693,0.0001190509],"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":[0.0002407675,0.0003754355,0.001661288,0.0003847648,0.00008984871,0.0001184821,0.00007880107,0.9028938,0.002157231,0.02912652,0.01687848,0.04599452],"study_design_scores_gemma":[0.00004516074,0.00004557092,0.00009326029,0.00001200534,0.000005037494,0.00001218867,0.00001778336,0.9886504,0.0007607112,0.008754638,0.001597944,0.000005264106],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2606547,0.001299834,0.6694406,0.001565184,0.0007864283,0.0008191888,0.003367028,0.01278461,0.04928239],"genre_scores_gemma":[0.4648514,0.000204934,0.5258341,0.0004112108,0.00005681047,0.0007857018,0.003194203,0.001334508,0.003327144],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01188362,"threshold_uncertainty_score":0.03975463,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01920299787829322,"score_gpt":0.353450276209467,"score_spread":0.3342472783311738,"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."}}