{"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/forward-step-func","entry":"forward_step_func","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":2,"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":2,"n_samples_fingerprinted":0,"n_places":5,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":1,"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":"2510.16415","paper":"/paper/arxiv-2510-16415","title":"MeCeFO: Enhancing LLM Training Robustness via Fault-Tolerant Optimization","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"pkumelon/MeCeFO","path":"llama_train.py","file_url":"https://github.com/pkumelon/MeCeFO/blob/HEAD/llama_train.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":"2ec0850397547476","mcp_get_code":{"code_sha256":"2ec0850397547476"}},{"arxiv_id":"2409.01143","paper":"/paper/flashflex-accommodating-large-language-model","title":"HexiScale: Accommodating Large Language Model Training over Heterogeneous Environment","date":null,"month_inferred_from_arxiv_id":"2024-09","title_source":"archive","repo":"relaxed-system-lab/flashflex","path":"llama_train.py","file_url":"https://github.com/relaxed-system-lab/flashflex/blob/HEAD/llama_train.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"401ab1df19f0bb57","mcp_get_code":{"code_sha256":"401ab1df19f0bb57"}},{"arxiv_id":"2311.11514","paper":"/paper/hexgen-generative-inference-of-foundation","title":"HexGen: Generative Inference of Large Language Model over Heterogeneous Environment","date":null,"month_inferred_from_arxiv_id":"2023-11","title_source":"archive","repo":"Relaxed-System-Lab/HexGen","path":"hexgen/llama/llama_inference.py","file_url":"https://github.com/Relaxed-System-Lab/HexGen/blob/HEAD/hexgen/llama/llama_inference.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"be32a1cb7f68aa17","mcp_get_code":{"code_sha256":"be32a1cb7f68aa17"}},{"arxiv_id":"2205.05198","paper":"/paper/reducing-activation-recomputation-in-large","title":"Reducing Activation Recomputation in Large Transformer Models","date":"2022-05-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"49589b188f2c635f","mcp_get_code":{"code_sha256":"49589b188f2c635f"}},{"arxiv_id":"2104.04473","paper":"/paper/efficient-large-scale-language-model-training","title":"Efficient Large-Scale Language Model Training on GPU Clusters Using Megatron-LM","date":"2021-04-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"NVIDIA/Megatron-LM","path":"examples/run_simple_mcore_train_loop.py","file_url":"https://github.com/NVIDIA/Megatron-LM/blob/HEAD/examples/run_simple_mcore_train_loop.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"49589b188f2c635f","mcp_get_code":{"code_sha256":"49589b188f2c635f"}}]}