{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001256488,0.0001375517,0.0002700416,0.00000673772,0.0004346254,0.00008364569,0.0002571027,0.00001068756,0.00003968563],"category_scores_gemma":[0.00003213525,0.0001152593,0.0002473956,0.0000293619,0.0000725112,0.0001593665,0.00009603776,0.0001030769,0.00008553803],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008995873,"about_ca_system_score_gemma":0.00002196624,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003464967,"about_ca_topic_score_gemma":3.977181e-7,"domain_scores_codex":[0.9991985,0.00002172219,0.0001692141,0.0002279779,0.0001434219,0.0002391402],"domain_scores_gemma":[0.9992369,0.0001409576,0.0001962474,0.0002783957,0.00007631404,0.00007114532],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000005493206,0.00009647423,0.001193569,0.0001541797,0.00002641148,1.816933e-7,0.0000173632,0.000008268152,0.0005974904,0.7883695,0.0008372891,0.2086938],"study_design_scores_gemma":[0.0003113698,0.00005724802,0.003367451,0.0007570363,0.0001004491,2.314771e-7,0.000005059278,0.03532675,0.001213439,0.9483494,0.01023505,0.0002764812],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4410231,0.000886199,0.4810362,0.0048825,0.0009227335,0.001674938,0.0002016548,0.0001140108,0.06925859],"genre_scores_gemma":[0.9966871,0.00002301068,0.0008583549,0.0001656496,0.002083602,0.0000542444,0.00006843499,0.00001368244,0.00004588113],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.555664,"threshold_uncertainty_score":0.4700137,"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."}}