{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/code/muon-update","entry":"muon_update","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":7,"n_papers_ran":5,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":6,"n_samples_ran":4,"n_samples_fingerprinted":2,"n_places":7,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":0,"ran":2,"unverified":2},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2608.22994","paper":"/paper/arxiv-2608-22994","title":"A Physical Response-and-Memory Model for Muon Optimization","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"orange4664/bimaxwell-track3-reproduction","path":"record_2635_submission/train_gpt_bimaxwell_2635.py","file_url":"https://github.com/orange4664/bimaxwell-track3-reproduction/blob/HEAD/record_2635_submission/train_gpt_bimaxwell_2635.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c6b79e26c521b25a","mcp_get_code":{"code_sha256":"c6b79e26c521b25a"}},{"arxiv_id":"2605.22297","paper":"/paper/arxiv-2605-22297","title":"One LR Doesn't Fit All: Heavy-Tail Guided Layerwise Learning Rates for LLMs","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"hed-ucas/Layer-wise-Learning-Rate","path":"galore_utils/muon.py","file_url":"https://github.com/hed-ucas/Layer-wise-Learning-Rate/blob/HEAD/galore_utils/muon.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a21a1aeb7c4ef8ed","mcp_get_code":{"code_sha256":"a21a1aeb7c4ef8ed"}},{"arxiv_id":"2605.09991","paper":"/paper/arxiv-2605-09991","title":"Optimizer-Induced Mode Connectivity: From AdamW to Muon","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"KellerJordan/Muon","path":"muon.py","file_url":"https://github.com/KellerJordan/Muon/blob/HEAD/muon.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f61c0f406f9700a1","mcp_get_code":{"code_sha256":"f61c0f406f9700a1"}},{"arxiv_id":"2604.01472","paper":"/paper/arxiv-2604-01472","title":"The Newton-Muon Optimizer","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"KellerJordan/modded-nanogpt","path":"records/track_3_optimization/train_gpt_simple.py","file_url":"https://github.com/KellerJordan/modded-nanogpt/blob/HEAD/records/track_3_optimization/train_gpt_simple.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e2d7543a51c8ea15","mcp_get_code":{"code_sha256":"e2d7543a51c8ea15"}},{"arxiv_id":"2602.04669","paper":"/paper/arxiv-2602-04669","title":"Delving into Muon and Beyond: Deep Analysis and Extensions","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"Ocram7/BeyondMuon","path":"optimizers/spectral_ns.py","file_url":"https://github.com/Ocram7/BeyondMuon/blob/HEAD/optimizers/spectral_ns.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7e5bfd49da2b921d","mcp_get_code":{"code_sha256":"7e5bfd49da2b921d"}},{"arxiv_id":"2508.20577","paper":"/paper/arxiv-2508-20577","title":"MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training","date":null,"month_inferred_from_arxiv_id":"2025-08","title_source":"syntology","repo":"kyleliang919/C-Optim","path":"c_muon.py","file_url":"https://github.com/kyleliang919/C-Optim/blob/HEAD/c_muon.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cb1f2229e6a594f7","mcp_get_code":{"code_sha256":"cb1f2229e6a594f7"}},{"arxiv_id":"2411.16085","paper":"/paper/cautious-optimizers-improving-training-with","title":"Cautious Optimizers: Improving Training with One Line of Code","date":"2024-11-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kyleliang919/c-optim","path":"c_muon.py","file_url":"https://github.com/kyleliang919/c-optim/blob/HEAD/c_muon.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cb1f2229e6a594f7","mcp_get_code":{"code_sha256":"cb1f2229e6a594f7"}}]}