{"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-train-ds-config","entry":"get_train_ds_config","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-25T09:33:49+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":9,"n_papers_ran":9,"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":7,"n_samples_fingerprinted":0,"n_places":9,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":7,"unverified":0},"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":"2410.07471","paper":"/paper/seal-safety-enhanced-aligned-llm-fine-tuning","title":"SEAL: Safety-enhanced Aligned LLM Fine-tuning via Bilevel Data Selection","date":"2024-10-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hanshen95/seal","path":"seal/utils/deepspeed_utils.py","file_url":"https://github.com/hanshen95/seal/blob/HEAD/seal/utils/deepspeed_utils.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":"05904ae9639815b8","mcp_get_code":{"code_sha256":"05904ae9639815b8"}},{"arxiv_id":"2408.12109","paper":"/paper/rovrm-a-robust-visual-reward-model-optimized","title":"RoVRM: A Robust Visual Reward Model Optimized via Auxiliary Textual Preference Data","date":"2024-08-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wangclnlp/vision-llm-alignment","path":"training/utils/ds_utils.py","file_url":"https://github.com/wangclnlp/vision-llm-alignment/blob/HEAD/training/utils/ds_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9d10b3b5c4e7a742","mcp_get_code":{"code_sha256":"9d10b3b5c4e7a742"}},{"arxiv_id":"2406.08434","paper":"/paper/taste-teaching-large-language-models-to","title":"TasTe: Teaching Large Language Models to Translate through Self-Reflection","date":"2024-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yutongwang1216/reflectionllmmt","path":"train/trainer/utils/ds_utils.py","file_url":"https://github.com/yutongwang1216/reflectionllmmt/blob/HEAD/train/trainer/utils/ds_utils.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":"bc9a14cb2f220424","mcp_get_code":{"code_sha256":"bc9a14cb2f220424"}},{"arxiv_id":"2405.07667","paper":"/paper/backdoor-removal-for-generative-large","title":"Simulate and Eliminate: Revoke Backdoors for Generative Large Language Models","date":"2024-05-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"HKUST-KnowComp/SANDE","path":"deepspeed_utils.py","file_url":"https://github.com/HKUST-KnowComp/SANDE/blob/HEAD/deepspeed_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"05904ae9639815b8","mcp_get_code":{"code_sha256":"05904ae9639815b8"}},{"arxiv_id":"2402.18150","paper":"/paper/unsupervised-information-refinement-training","title":"Unsupervised Information Refinement Training of Large Language Models for Retrieval-Augmented Generation","date":"2024-02-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xsc1234/info-rag","path":"utils/ds_utils.py","file_url":"https://github.com/xsc1234/info-rag/blob/HEAD/utils/ds_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0b7ef7574493a1eb","mcp_get_code":{"code_sha256":"0b7ef7574493a1eb"}},{"arxiv_id":"2402.14700","paper":"/paper/unveiling-linguistic-regions-in-large","title":"Unveiling Linguistic Regions in Large Language Models","date":"2024-02-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zzhang0179/Unveiling-Linguistic-Regions-in-LLMs","path":"training/utils/ds_utils.py","file_url":"https://github.com/zzhang0179/Unveiling-Linguistic-Regions-in-LLMs/blob/HEAD/training/utils/ds_utils.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":"86613110e9a3611b","mcp_get_code":{"code_sha256":"86613110e9a3611b"}},{"arxiv_id":"2310.20246","paper":"/paper/breaking-language-barriers-in-multilingual","title":"Breaking Language Barriers in Multilingual Mathematical Reasoning: Insights and Observations","date":"2023-10-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/MathOctopus","path":"utils/ds_utils.py","file_url":"https://github.com/microsoft/MathOctopus/blob/HEAD/utils/ds_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"311aba0a9b717df8","mcp_get_code":{"code_sha256":"311aba0a9b717df8"}},{"arxiv_id":"2308.02223","paper":"/paper/esrl-efficient-sampling-based-reinforcement","title":"ESRL: Efficient Sampling-based Reinforcement Learning for Sequence Generation","date":"2023-08-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wangclnlp/DeepSpeed-Chat-Extension","path":"rlhf_llama/deepspeed_chat/training/utils/ds_utils.py","file_url":"https://github.com/wangclnlp/DeepSpeed-Chat-Extension/blob/HEAD/rlhf_llama/deepspeed_chat/training/utils/ds_utils.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":"0d4552e23174dc98","mcp_get_code":{"code_sha256":"0d4552e23174dc98"}},{"arxiv_id":"2024.naacl-long.326","paper":null,"title":"arXiv:2024.naacl-long.326","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"LanXiu0523/RLHF_instructGPT","path":"applications/utils/ds_utils.py","file_url":"https://github.com/LanXiu0523/RLHF_instructGPT/blob/HEAD/applications/utils/ds_utils.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":"0b7ef7574493a1eb","mcp_get_code":{"code_sha256":"0b7ef7574493a1eb"}}]}