{"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/set-weight-decay-and-lr","entry":"set_weight_decay_and_lr","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":5,"n_papers_ran":0,"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":1,"n_samples_ran":0,"n_samples_fingerprinted":0,"n_places":5,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"unverified":1},"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":"2506.08297","paper":"/paper/sema-a-scalable-and-efficient-mamba-like","title":"SEMA: a Scalable and Efficient Mamba like Attention via Token Localization and Averaging","date":"2025-06-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nhatthanhtran/SEMA","path":"optimizer.py","file_url":"https://github.com/nhatthanhtran/SEMA/blob/HEAD/optimizer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"104af48a94364f24","mcp_get_code":{"code_sha256":"104af48a94364f24"}},{"arxiv_id":"2412.06590","paper":"/paper/bridging-the-divide-reconsidering-softmax-and","title":"Bridging the Divide: Reconsidering Softmax and Linear Attention","date":"2024-12-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"leaplabthu/inline","path":"optimizer.py","file_url":"https://github.com/leaplabthu/inline/blob/HEAD/optimizer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"104af48a94364f24","mcp_get_code":{"code_sha256":"104af48a94364f24"}},{"arxiv_id":"2312.08874","paper":"/paper/agent-attention-on-the-integration-of-softmax","title":"Agent Attention: On the Integration of Softmax and Linear Attention","date":"2023-12-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"leaplabthu/agent-attention","path":"agent_transformer/optimizer.py","file_url":"https://github.com/leaplabthu/agent-attention/blob/HEAD/agent_transformer/optimizer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"104af48a94364f24","mcp_get_code":{"code_sha256":"104af48a94364f24"}},{"arxiv_id":"2309.01430","paper":"/paper/dat-spatially-dynamic-vision-transformer-with","title":"DAT++: Spatially Dynamic Vision Transformer with Deformable Attention","date":"2023-09-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"leaplabthu/dat","path":"optimizer.py","file_url":"https://github.com/leaplabthu/dat/blob/HEAD/optimizer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"104af48a94364f24","mcp_get_code":{"code_sha256":"104af48a94364f24"}},{"arxiv_id":"00666","paper":null,"title":"arXiv:00666","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"lliai/AttnZero","path":"imagenet/optimizer.py","file_url":"https://github.com/lliai/AttnZero/blob/HEAD/imagenet/optimizer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"104af48a94364f24","mcp_get_code":{"code_sha256":"104af48a94364f24"}}]}