{"id":"W4287236889","doi":"10.48550/arxiv.2104.03546","title":"Graph Partitioning and Sparse Matrix Ordering using Reinforcement\\n Learning and Graph Neural Networks","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"VLSI and FPGA Design Techniques","field":"Engineering","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Graph partition; Computer science; Dense graph; Reinforcement learning; Sparse matrix; Adjacency matrix; Graph; Algorithm; Theoretical computer science; Combinatorics; Artificial intelligence; Mathematics; Line graph; Pathwidth","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.0001407995,0.0003310819,0.0003344627,0.0002746645,0.0002237223,0.0001870055,0.0001345911,0.0002884628,0.00002422326],"category_scores_gemma":[0.00001125258,0.0004414499,0.0001034329,0.0003480249,0.00009128948,0.0002756298,0.0004385163,0.0007973812,4.919988e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006524439,"about_ca_system_score_gemma":0.00001409338,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001232835,"about_ca_topic_score_gemma":0.00002651814,"domain_scores_codex":[0.9988246,0.00006130142,0.000204828,0.000500591,0.00004998697,0.0003587045],"domain_scores_gemma":[0.9994486,0.00004196712,0.00009439176,0.00023669,0.00005226683,0.0001260712],"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":[0.000007315199,0.000004260106,0.01035493,0.0001690981,0.00008932604,0.0001647575,0.0001052011,0.9878379,0.0003101281,0.0006139749,0.000009416632,0.0003337221],"study_design_scores_gemma":[0.0002176295,0.00002252511,0.0002956138,0.0002408044,0.0001353026,0.00002176937,0.0002443824,0.9973782,0.0001795287,0.0007734585,0.00004100037,0.0004497429],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.527597,0.0008913524,0.4705711,0.000001620438,0.0001332327,0.0001293095,0.000001005295,0.0004056593,0.0002697628],"genre_scores_gemma":[0.9958624,0.002867996,0.001047809,0.00001163976,0.0000616504,0.000001348535,0.00002563084,0.00005040376,0.00007117901],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4695233,"threshold_uncertainty_score":0.9998037,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04123634730311696,"score_gpt":0.186060707543579,"score_spread":0.144824360240462,"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."}}