{"id":"W4392781204","doi":"10.48550/arxiv.2403.07688","title":"Maxwell's Demon at Work: Efficient Pruning by Leveraging Saturation of Neurons","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Alliance de recherche numérique du Canada; Nvidia","keywords":"Maxwell's demon; Demon; Pruning; Saturation (graph theory); Work (physics); Computer science; Artificial intelligence; Physics; Mathematics; Biology; Quantum mechanics; Combinatorics; Botany","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001187895,0.0006560442,0.0007284324,0.0005280778,0.0004962608,0.0008045064,0.001916333,0.000919629,0.002337363],"category_scores_gemma":[0.006430975,0.0004291224,0.0003722805,0.0004743883,0.000931893,0.001777664,0.001799,0.001280828,0.0004532555],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006025867,"about_ca_system_score_gemma":0.0008452768,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001344598,"about_ca_topic_score_gemma":0.003662081,"domain_scores_codex":[0.9995933,0.0001195646,0.00003078222,0.0000693741,0.0001229131,0.00006420591],"domain_scores_gemma":[0.9982139,0.000923645,0.0001561377,0.0003552579,0.0002276178,0.0001234563],"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":[0.0006120558,0.0001929828,0.005063245,0.0002993497,0.0001507749,0.000571617,0.0005048469,0.5627937,0.03459162,0.03762064,0.008985933,0.3486131],"study_design_scores_gemma":[0.00003907942,0.0001382407,0.0004012322,0.00004063303,0.00003132307,0.0001523357,0.00005209796,0.9663612,0.01199077,0.01819114,0.002586814,0.00001504921],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2196351,0.001579317,0.7677493,0.0009830826,0.0001877135,0.00009596453,0.0001417388,0.002096713,0.007531032],"genre_scores_gemma":[0.8541212,0.0004784968,0.1402827,0.000585694,0.00006893492,0.0001395092,0.000165074,0.000276336,0.003881931],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002337363,"threshold_uncertainty_score":0.007819295,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05092135791348678,"score_gpt":0.1798401205163763,"score_spread":0.1289187626028895,"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."}}