{"id":"W4388685739","doi":"10.48550/arxiv.2311.07540","title":"Finding planted cliques using gradient descent","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; National Science Foundation","keywords":"Combinatorics; Clique; Markov chain Monte Carlo; Mathematics; Omega; Markov chain; Vertex (graph theory); Time complexity; Vertex cover; Discrete mathematics; Gradient descent; Graph; Monte Carlo method; Computer science; Statistics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003071066,0.0003706364,0.0003584476,0.0007411611,0.0002214999,0.0001838135,0.001870365,0.0002959087,0.000009757729],"category_scores_gemma":[0.00007926897,0.000450262,0.0002051752,0.0009553424,0.00009482726,0.0002990178,0.002681237,0.0005023371,0.00004493226],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005739997,"about_ca_system_score_gemma":0.000184524,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002008314,"about_ca_topic_score_gemma":0.00001673148,"domain_scores_codex":[0.9976935,0.000127243,0.0002960417,0.001250971,0.0001469013,0.0004853251],"domain_scores_gemma":[0.9979789,0.0001343635,0.0003576,0.001159148,0.0001829684,0.0001870772],"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":[0.00001844217,0.00009655715,0.002711612,0.00009954286,0.0001142346,0.0005434942,0.0004778992,0.6444979,0.00006587161,0.3506164,0.000561157,0.0001968557],"study_design_scores_gemma":[0.0001900874,0.00004139934,0.0004092323,0.0003314518,0.00004801003,0.00001048467,0.00003521808,0.947439,0.0004634355,0.05052639,0.00004119833,0.0004641302],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06895766,0.00002198579,0.9273639,0.0000567004,0.001080493,0.0004255469,0.00002027891,0.001832799,0.0002406683],"genre_scores_gemma":[0.94956,0.0001344007,0.04967761,0.00005877484,0.0000593199,0.000002172909,0.00003193021,0.00004074697,0.0004350454],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8806024,"threshold_uncertainty_score":0.9997949,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2234772960350749,"score_gpt":0.2309315381908273,"score_spread":0.007454242155752383,"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."}}