{"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/sum-norm","entry":"sum_norm","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":12,"n_papers_ran":11,"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":5,"n_samples_ran":4,"n_samples_fingerprinted":3,"n_places":12,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":1,"ran":1,"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":"2606.08804","paper":"/paper/arxiv-2606-08804","title":"Q-Delta: Beyond Key-Value Associative State Evolution","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"psmiz/Q-Delta","path":"qdelta/qdelta.py","file_url":"https://github.com/psmiz/Q-Delta/blob/HEAD/qdelta/qdelta.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"126a3c02771cd7bd","mcp_get_code":{"code_sha256":"126a3c02771cd7bd"}},{"arxiv_id":"2603.28743","paper":"/paper/arxiv-2603-28743","title":"Rethinking Language Model Scaling under Transferable Hypersphere Optimization","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"microsoft/ArchScale","path":"lit_gpt/delta_net.py","file_url":"https://github.com/microsoft/ArchScale/blob/HEAD/lit_gpt/delta_net.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e544fdb6373b9f42","mcp_get_code":{"code_sha256":"e544fdb6373b9f42"}},{"arxiv_id":"2503.02130","paper":"/paper/forgetting-transformer-softmax-attention-with","title":"Forgetting Transformer: Softmax Attention with a Forget Gate","date":"2025-03-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhixuan-lin/forgetting-transformer","path":"src/forgetting_transformer/model/delta_net/delta_net_layer.py","file_url":"https://github.com/zhixuan-lin/forgetting-transformer/blob/HEAD/src/forgetting_transformer/model/delta_net/delta_net_layer.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e544fdb6373b9f42","mcp_get_code":{"code_sha256":"e544fdb6373b9f42"}},{"arxiv_id":"2502.10297","paper":"/paper/deltaproduct-increasing-the-expressivity-of","title":"DeltaProduct: Improving State-Tracking in Linear RNNs via Householder Products","date":"2025-02-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"automl/deltaproduct","path":"flash-linear-attention/fla/layers/gated_deltaproduct.py","file_url":"https://github.com/automl/deltaproduct/blob/HEAD/flash-linear-attention/fla/layers/gated_deltaproduct.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e544fdb6373b9f42","mcp_get_code":{"code_sha256":"e544fdb6373b9f42"}},{"arxiv_id":"2410.00983","paper":"/paper/robust-guided-diffusion-for-offline-black-box","title":"Robust Guided Diffusion for Offline Black-Box Optimization","date":"2024-10-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ggchen1997/rgd","path":"likelihood.py","file_url":"https://github.com/ggchen1997/rgd/blob/HEAD/likelihood.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4c2d6f936b53a0cb","mcp_get_code":{"code_sha256":"4c2d6f936b53a0cb"}},{"arxiv_id":"2406.06976","paper":"/paper/discrete-dictionary-based-decomposition-layer","title":"Discrete Dictionary-based Decomposition Layer for Structured Representation Learning","date":"2024-06-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"taewonpark/D3","path":"WikiText103/src/utils/D3.py","file_url":"https://github.com/taewonpark/D3/blob/HEAD/WikiText103/src/utils/D3.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"379d7685e2a746e5","mcp_get_code":{"code_sha256":"379d7685e2a746e5"}},{"arxiv_id":"2406.06484","paper":"/paper/parallelizing-linear-transformers-with-the","title":"Parallelizing Linear Transformers with the Delta Rule over Sequence Length","date":"2024-06-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fla-org/flash-linear-attention","path":"fla/layers/delta_net.py","file_url":"https://github.com/fla-org/flash-linear-attention/blob/HEAD/fla/layers/delta_net.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1837bde376a0260d","mcp_get_code":{"code_sha256":"1837bde376a0260d"}},{"arxiv_id":"2406.01012","paper":"/paper/attention-based-iterative-decomposition-for","title":"Attention-based Iterative Decomposition for Tensor Product Representation","date":"2024-06-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"taewonpark/aid","path":"WikiText103/src/utils/AID.py","file_url":"https://github.com/taewonpark/aid/blob/HEAD/WikiText103/src/utils/AID.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"379d7685e2a746e5","mcp_get_code":{"code_sha256":"379d7685e2a746e5"}},{"arxiv_id":"2402.18668","paper":"/paper/simple-linear-attention-language-models","title":"Simple linear attention language models balance the recall-throughput tradeoff","date":"2024-02-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hazyresearch/zoology","path":"zoology/mixers/delta_net.py","file_url":"https://github.com/hazyresearch/zoology/blob/HEAD/zoology/mixers/delta_net.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"e544fdb6373b9f42","mcp_get_code":{"code_sha256":"e544fdb6373b9f42"}},{"arxiv_id":"2312.00276","paper":"/paper/automating-continual-learning","title":"Automating Continual Learning","date":"2023-12-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"idsia/automated-cl","path":"layer.py","file_url":"https://github.com/idsia/automated-cl/blob/HEAD/layer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"379d7685e2a746e5","mcp_get_code":{"code_sha256":"379d7685e2a746e5"}},{"arxiv_id":"2310.16076","paper":"/paper/practical-computational-power-of-linear","title":"Practical Computational Power of Linear Transformers and Their Recurrent and Self-Referential Extensions","date":"2023-10-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"IDSIA/fwp-formal-lang","path":"layers.py","file_url":"https://github.com/IDSIA/fwp-formal-lang/blob/HEAD/layers.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"379d7685e2a746e5","mcp_get_code":{"code_sha256":"379d7685e2a746e5"}},{"arxiv_id":"2106.06295","paper":"/paper/going-beyond-linear-transformers-with","title":"Going Beyond Linear Transformers with Recurrent Fast Weight Programmers","date":"2021-06-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"IDSIA/lmtool-fwms","path":"src/utils/cuda_fast_weight_layer.py","file_url":"https://github.com/IDSIA/lmtool-fwms/blob/HEAD/src/utils/cuda_fast_weight_layer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"379d7685e2a746e5","mcp_get_code":{"code_sha256":"379d7685e2a746e5"}}]}