{"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-device-mesh","entry":"get_device_mesh","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":4,"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":4},"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":"2510.06195","paper":"/paper/arxiv-2510-06195","title":"Latent Speech-Text Transformer","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"facebookresearch/lst","path":"lst/distributed.py","file_url":"https://github.com/facebookresearch/lst/blob/HEAD/lst/distributed.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"ebf689175ca08206","mcp_get_code":{"code_sha256":"ebf689175ca08206"}},{"arxiv_id":"2506.14761","paper":"/paper/from-bytes-to-ideas-language-modeling-with","title":"From Bytes to Ideas: Language Modeling with Autoregressive U-Nets","date":"2025-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/lingua","path":"lingua/distributed.py","file_url":"https://github.com/facebookresearch/lingua/blob/HEAD/lingua/distributed.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"d9d11e6287ad4384","mcp_get_code":{"code_sha256":"d9d11e6287ad4384"}},{"arxiv_id":"2503.18866","paper":"/paper/reasoning-to-learn-from-latent-thoughts","title":"Reasoning to Learn from Latent Thoughts","date":"2025-03-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ryoungj/BoLT","path":"lingua/distributed.py","file_url":"https://github.com/ryoungj/BoLT/blob/HEAD/lingua/distributed.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":"d9d11e6287ad4384","mcp_get_code":{"code_sha256":"d9d11e6287ad4384"}},{"arxiv_id":"2412.09871","paper":"/paper/byte-latent-transformer-patches-scale-better","title":"Byte Latent Transformer: Patches Scale Better Than Tokens","date":"2024-12-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/blt","path":"bytelatent/distributed.py","file_url":"https://github.com/facebookresearch/blt/blob/HEAD/bytelatent/distributed.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ebf689175ca08206","mcp_get_code":{"code_sha256":"ebf689175ca08206"}},{"arxiv_id":"2412.09764","paper":"/paper/memory-layers-at-scale","title":"Memory Layers at Scale","date":"2024-12-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/memory","path":"lingua/distributed.py","file_url":"https://github.com/facebookresearch/memory/blob/HEAD/lingua/distributed.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"eae71867f83f5695","mcp_get_code":{"code_sha256":"eae71867f83f5695"}},{"arxiv_id":"2309.06497","paper":"/paper/a-distributed-data-parallel-pytorch","title":"A Distributed Data-Parallel PyTorch Implementation of the Distributed Shampoo Optimizer for Training Neural Networks At-Scale","date":"2023-09-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/optimizers","path":"distributed_shampoo/distributor/shampoo_dist_utils.py","file_url":"https://github.com/facebookresearch/optimizers/blob/HEAD/distributed_shampoo/distributor/shampoo_dist_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"3e3c14dedb9c5a3b","mcp_get_code":{"code_sha256":"3e3c14dedb9c5a3b"}}]}