{"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/strip-sequence","entry":"strip_sequence","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":8,"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":9,"n_places_pointer_only":2,"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":"2601.17671","paper":"/paper/arxiv-2601-17671","title":"Align to the Pivot: Dual Alignment with Self-Feedback for Multilingual Math Reasoning","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"Rover912/PASMR","path":"openrlhf/cli/serve_rm.py","file_url":"https://github.com/Rover912/PASMR/blob/HEAD/openrlhf/cli/serve_rm.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":"ca3514c46a1261d7","mcp_get_code":{"code_sha256":"ca3514c46a1261d7"}},{"arxiv_id":"2510.20369","paper":"/paper/arxiv-2510-20369","title":"Ask a Strong LLM Judge when Your Reward Model is Uncertain","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"zhenghaoxu-gatech/uncertainty-router","path":"ppo/openrlhf/cli/serve_pm_router.py","file_url":"https://github.com/zhenghaoxu-gatech/uncertainty-router/blob/HEAD/ppo/openrlhf/cli/serve_pm_router.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4081a5e23d9bc90f","mcp_get_code":{"code_sha256":"4081a5e23d9bc90f"}},{"arxiv_id":"2505.15456","paper":"/paper/teaching-language-models-to-evolve-with-users","title":"Teaching Language Models to Evolve with Users: Dynamic Profile Modeling for Personalized Alignment","date":"2025-05-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"XingYuSSS/RLPA","path":"openrlhf/cli/serve_rm.py","file_url":"https://github.com/XingYuSSS/RLPA/blob/HEAD/openrlhf/cli/serve_rm.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":"ca3514c46a1261d7","mcp_get_code":{"code_sha256":"ca3514c46a1261d7"}},{"arxiv_id":"2504.07912","paper":"/paper/echo-chamber-rl-post-training-amplifies","title":"Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining","date":"2025-04-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rosieyzh/openrlhf-pretrain","path":"openrlhf/cli/serve_rm.py","file_url":"https://github.com/rosieyzh/openrlhf-pretrain/blob/HEAD/openrlhf/cli/serve_rm.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":"ca3514c46a1261d7","mcp_get_code":{"code_sha256":"ca3514c46a1261d7"}},{"arxiv_id":"2502.18968","paper":"/paper/know-you-first-and-be-you-better-modeling","title":"Know You First and Be You Better: Modeling Human-Like User Simulators via Implicit Profiles","date":"2025-02-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wangkevin02/USP","path":"src/rlcc/OpenRLHF/openrlhf/cli/serve_rm.py","file_url":"https://github.com/wangkevin02/USP/blob/HEAD/src/rlcc/OpenRLHF/openrlhf/cli/serve_rm.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ca3514c46a1261d7","mcp_get_code":{"code_sha256":"ca3514c46a1261d7"}},{"arxiv_id":"2502.18968","paper":"/paper/know-you-first-and-be-you-better-modeling","title":"Know You First and Be You Better: Modeling Human-Like User Simulators via Implicit Profiles","date":"2025-02-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wangkevin02/USP","path":"src/rlcc/OpenRLHF/remote_rm.py","file_url":"https://github.com/wangkevin02/USP/blob/HEAD/src/rlcc/OpenRLHF/remote_rm.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4081a5e23d9bc90f","mcp_get_code":{"code_sha256":"4081a5e23d9bc90f"}},{"arxiv_id":"2502.03373","paper":"/paper/demystifying-long-chain-of-thought-reasoning","title":"Demystifying Long Chain-of-Thought Reasoning in LLMs","date":"2025-02-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"eddycmu/demystify-long-cot","path":"openrlhf/openrlhf/cli/serve_rm.py","file_url":"https://github.com/eddycmu/demystify-long-cot/blob/HEAD/openrlhf/openrlhf/cli/serve_rm.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ca3514c46a1261d7","mcp_get_code":{"code_sha256":"ca3514c46a1261d7"}},{"arxiv_id":"2404.18922","paper":"/paper/dpo-meets-ppo-reinforced-token-optimization","title":"DPO Meets PPO: Reinforced Token Optimization for RLHF","date":"2024-04-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zkshan2002/RTO","path":"openrlhf/cli/serve_rm.py","file_url":"https://github.com/zkshan2002/RTO/blob/HEAD/openrlhf/cli/serve_rm.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":"4081a5e23d9bc90f","mcp_get_code":{"code_sha256":"4081a5e23d9bc90f"}},{"arxiv_id":"2402.09345","paper":"/paper/mitigating-reward-hacking-via-information","title":"InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling","date":"2024-02-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"miaoyuchun/InfoRM","path":"openrlhf/cli/serve_rm.py","file_url":"https://github.com/miaoyuchun/InfoRM/blob/HEAD/openrlhf/cli/serve_rm.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ca3514c46a1261d7","mcp_get_code":{"code_sha256":"ca3514c46a1261d7"}}]}