{"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/get-docs","entry":"get_docs","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":6,"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":2,"n_samples_ran":0,"n_samples_fingerprinted":0,"n_places":6,"n_places_pointer_only":4,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"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":"2504.12463","paper":"/paper/dense-backpropagation-improves-training-for","title":"Dense Backpropagation Improves Training for Sparse Mixture-of-Experts","date":"2025-04-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vatsal0/default-moe","path":"configs/gen_docs.py","file_url":"https://github.com/vatsal0/default-moe/blob/HEAD/configs/gen_docs.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"d5081f28e2befd2c","mcp_get_code":{"code_sha256":"d5081f28e2befd2c"}},{"arxiv_id":"2411.12992","paper":"/paper/memoryformer-minimize-transformer-computation","title":"MemoryFormer: Minimize Transformer Computation by Removing Fully-Connected Layers","date":"2024-11-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ningding-o/MemoryFormer","path":"configs/gen_docs.py","file_url":"https://github.com/ningding-o/MemoryFormer/blob/HEAD/configs/gen_docs.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d5081f28e2befd2c","mcp_get_code":{"code_sha256":"d5081f28e2befd2c"}},{"arxiv_id":"2410.04798","paper":"/paper/dape-v2-process-attention-score-as-feature","title":"DAPE V2: Process Attention Score as Feature Map for Length Extrapolation","date":"2024-10-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chuanyang-zheng/cape","path":"configs/gen_docs.py","file_url":"https://github.com/chuanyang-zheng/cape/blob/HEAD/configs/gen_docs.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":"d5081f28e2befd2c","mcp_get_code":{"code_sha256":"d5081f28e2befd2c"}},{"arxiv_id":"2406.12428","paper":"/paper/pslm-parallel-generation-of-text-and-speech","title":"PSLM: Parallel Generation of Text and Speech with LLMs for Low-Latency Spoken Dialogue Systems","date":"2024-06-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"eleutherai/gpt-neox","path":"configs/gen_docs.py","file_url":"https://github.com/eleutherai/gpt-neox/blob/HEAD/configs/gen_docs.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":"d5081f28e2befd2c","mcp_get_code":{"code_sha256":"d5081f28e2befd2c"}},{"arxiv_id":"2312.02406","paper":"/paper/efficient-online-data-mixing-for-language","title":"Efficient Online Data Mixing For Language Model Pre-Training","date":"2023-12-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alon-albalak/online-data-mixing","path":"configs/gen_docs.py","file_url":"https://github.com/alon-albalak/online-data-mixing/blob/HEAD/configs/gen_docs.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"750d7ac5c014981c","mcp_get_code":{"code_sha256":"750d7ac5c014981c"}},{"arxiv_id":"2205.09921","paper":"/paper/kerple-kernelized-relative-positional","title":"KERPLE: Kernelized Relative Positional Embedding for Length Extrapolation","date":"2022-05-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chijames/KERPLE","path":"configs/gen_docs.py","file_url":"https://github.com/chijames/KERPLE/blob/HEAD/configs/gen_docs.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"750d7ac5c014981c","mcp_get_code":{"code_sha256":"750d7ac5c014981c"}}]}