{"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/linear-attention","entry":"linear_attention","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":7,"n_samples_ran":4,"n_samples_fingerprinted":3,"n_places":8,"n_places_pointer_only":5,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":2,"ran":0,"unverified":3},"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":"2603.06248","paper":"/paper/arxiv-2603-06248","title":"Gradient Flow Polarizes Softmax Outputs towards Low-Entropy Solutions","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"tml-epfl/softmax","path":"src/attention.py","file_url":"https://github.com/tml-epfl/softmax/blob/HEAD/src/attention.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a91bbe5c96744514","mcp_get_code":{"code_sha256":"a91bbe5c96744514"}},{"arxiv_id":"2506.18335","paper":"/paper/rethinking-decoder-design-improving-biomarker-1","title":"Rethinking Decoder Design: Improving Biomarker Segmentation Using Depth-to-Space Restoration and Residual Linear Attention","date":"2025-06-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"saadwazir/MCADS-Decoder","path":"mcadsDecoder.py","file_url":"https://github.com/saadwazir/MCADS-Decoder/blob/HEAD/mcadsDecoder.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"b6cacb94dcf9491c","mcp_get_code":{"code_sha256":"b6cacb94dcf9491c"}},{"arxiv_id":"2410.10254","paper":"/paper/lolcats-on-low-rank-linearizing-of-large","title":"LoLCATs: On Low-Rank Linearizing of Large Language Models","date":"2024-10-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"HazyResearch/lolcats","path":"src/model/linear_attention/linear_attention.py","file_url":"https://github.com/HazyResearch/lolcats/blob/HEAD/src/model/linear_attention/linear_attention.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":"d8595b54ec29491c","mcp_get_code":{"code_sha256":"d8595b54ec29491c"}},{"arxiv_id":"2410.10254","paper":"/paper/lolcats-on-low-rank-linearizing-of-large","title":"LoLCATs: On Low-Rank Linearizing of Large Language Models","date":"2024-10-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hazyresearch/lolcats","path":"src/model/linear_attention/linear_window_attention_sw_linear.py","file_url":"https://github.com/hazyresearch/lolcats/blob/HEAD/src/model/linear_attention/linear_window_attention_sw_linear.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":"61e674e010a5aa26","mcp_get_code":{"code_sha256":"61e674e010a5aa26"}},{"arxiv_id":"2308.06383","paper":"/paper/u-red-unsupervised-3d-shape-retrieval-and","title":"U-RED: Unsupervised 3D Shape Retrieval and Deformation for Partial Point Clouds","date":"2023-08-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhangcyg/u-red","path":"network/deformation_net.py","file_url":"https://github.com/zhangcyg/u-red/blob/HEAD/network/deformation_net.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e44c028c4b4ffc80","mcp_get_code":{"code_sha256":"e44c028c4b4ffc80"}},{"arxiv_id":"2201.03794","paper":"/paper/efficient-non-local-contrastive-attention-for","title":"Efficient Non-Local Contrastive Attention for Image Super-Resolution","date":"2022-01-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"285e3997b7d7c24b","mcp_get_code":{"code_sha256":"285e3997b7d7c24b"}},{"arxiv_id":"2111.00035","paper":"/paper/skyformer-remodel-self-attention-with","title":"Skyformer: Remodel Self-Attention with Gaussian Kernel and Nyström Method","date":"2021-10-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pkuzengqi/Skyformer","path":"src/models/attention_skyformer.py","file_url":"https://github.com/pkuzengqi/Skyformer/blob/HEAD/src/models/attention_skyformer.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"285e3997b7d7c24b","mcp_get_code":{"code_sha256":"285e3997b7d7c24b"}},{"arxiv_id":"2110.15343","paper":"/paper/scatterbrain-unifying-sparse-and-low-rank","title":"Scatterbrain: Unifying Sparse and Low-rank Attention Approximation","date":"2021-10-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hazyresearch/scatterbrain","path":"src/models/attention/scatterbrain_utils.py","file_url":"https://github.com/hazyresearch/scatterbrain/blob/HEAD/src/models/attention/scatterbrain_utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"98b8406f67dac23d","mcp_get_code":{"code_sha256":"98b8406f67dac23d"}}]}