{"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/masked-var","entry":"masked_var","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":12,"n_papers_ran":12,"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":5,"n_samples_ran":5,"n_samples_fingerprinted":5,"n_places":12,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":2,"ran":2,"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":"2605.11974","paper":"/paper/arxiv-2605-11974","title":"Towards Order Fairness: Mitigating LLMs Order Sensitivity through Dual Group Advantage Optimization","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"Hyalinesky/DGAO","path":"trl/core.py","file_url":"https://github.com/Hyalinesky/DGAO/blob/HEAD/trl/core.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"67607956afbb2a83","mcp_get_code":{"code_sha256":"67607956afbb2a83"}},{"arxiv_id":"2509.13760","paper":"/paper/arxiv-2509-13760","title":"Iterative Prompt Refinement for Safer Text-to-Image Generation","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"ku-dmlab/IPR","path":"trl/core.py","file_url":"https://github.com/ku-dmlab/IPR/blob/HEAD/trl/core.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"67607956afbb2a83","mcp_get_code":{"code_sha256":"67607956afbb2a83"}},{"arxiv_id":"2506.13752","paper":"/paper/steering-llm-thinking-with-budget-guidance","title":"Steering LLM Thinking with Budget Guidance","date":"2025-06-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"umass-embodied-agi/budgetguidance","path":"3rdparty/trl/trl/core.py","file_url":"https://github.com/umass-embodied-agi/budgetguidance/blob/HEAD/3rdparty/trl/trl/core.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"67607956afbb2a83","mcp_get_code":{"code_sha256":"67607956afbb2a83"}},{"arxiv_id":"2505.20280","paper":"/paper/lorentz-local-canonicalization-how-to-make","title":"Lorentz Local Canonicalization: How to Make Any Network Lorentz-Equivariant","date":"2025-05-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"heidelberg-hepml/lloca-experiments","path":"experiments/baselines/pelican/perm_equiv_layers.py","file_url":"https://github.com/heidelberg-hepml/lloca-experiments/blob/HEAD/experiments/baselines/pelican/perm_equiv_layers.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e78c5ecf916dd19c","mcp_get_code":{"code_sha256":"e78c5ecf916dd19c"}},{"arxiv_id":"2505.15656","paper":"/paper/be-careful-when-fine-tuning-on-open-source","title":"Be Careful When Fine-tuning On Open-Source LLMs: Your Fine-tuning Data Could Be Secretly Stolen!","date":"2025-05-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thu-coai/backdoor-data-extraction","path":"train/trl/core.py","file_url":"https://github.com/thu-coai/backdoor-data-extraction/blob/HEAD/train/trl/core.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"67607956afbb2a83","mcp_get_code":{"code_sha256":"67607956afbb2a83"}},{"arxiv_id":"2505.15404","paper":"/paper/how-should-we-enhance-the-safety-of-large","title":"How Should We Enhance the Safety of Large Reasoning Models: An Empirical Study","date":"2025-05-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thu-coai/lrm-safety-study","path":"trl/trl/core.py","file_url":"https://github.com/thu-coai/lrm-safety-study/blob/HEAD/trl/trl/core.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"67607956afbb2a83","mcp_get_code":{"code_sha256":"67607956afbb2a83"}},{"arxiv_id":"2505.09655","paper":"/paper/dra-grpo-exploring-diversity-aware-reward","title":"DRA-GRPO: Exploring Diversity-Aware Reward Adjustment for R1-Zero-Like Training of Large Language Models","date":"2025-05-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xiwenc1/dra-grpo","path":"src/open_r1/trl/core.py","file_url":"https://github.com/xiwenc1/dra-grpo/blob/HEAD/src/open_r1/trl/core.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"67607956afbb2a83","mcp_get_code":{"code_sha256":"67607956afbb2a83"}},{"arxiv_id":"2504.20157","paper":"/paper/toward-evaluative-thinking-meta-policy","title":"Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models","date":"2025-04-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"minnesotanlp/mpo","path":"trl/core.py","file_url":"https://github.com/minnesotanlp/mpo/blob/HEAD/trl/core.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"67607956afbb2a83","mcp_get_code":{"code_sha256":"67607956afbb2a83"}},{"arxiv_id":"2503.19470","paper":"/paper/research-learning-to-reason-with-search-for","title":"ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning","date":"2025-03-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"agent-rl/research","path":"src/verl/trainer/ppo/core_algos.py","file_url":"https://github.com/agent-rl/research/blob/HEAD/src/verl/trainer/ppo/core_algos.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"252438cc046bfb61","mcp_get_code":{"code_sha256":"252438cc046bfb61"}},{"arxiv_id":"2503.13538","paper":"/paper/from-demonstrations-to-rewards-alignment","title":"From Demonstrations to Rewards: Alignment Without Explicit Human Preferences","date":"2025-03-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Hong-Lab-UMN-ECE/IRLAlignment","path":"summarize_from_feedback_details/data_pairing.py","file_url":"https://github.com/Hong-Lab-UMN-ECE/IRLAlignment/blob/HEAD/summarize_from_feedback_details/data_pairing.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3a136e5f5a8047ac","mcp_get_code":{"code_sha256":"3a136e5f5a8047ac"}},{"arxiv_id":"2406.09279","paper":"/paper/unpacking-dpo-and-ppo-disentangling-best","title":"Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback","date":"2024-06-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hamishivi/EasyLM","path":"EasyLM/models/llama/llama_train_ppo.py","file_url":"https://github.com/hamishivi/EasyLM/blob/HEAD/EasyLM/models/llama/llama_train_ppo.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"c39dac404ff3f2b3","mcp_get_code":{"code_sha256":"c39dac404ff3f2b3"}},{"arxiv_id":"2403.17031","paper":"/paper/the-n-implementation-details-of-rlhf-with-ppo","title":"The N+ Implementation Details of RLHF with PPO: A Case Study on TL;DR Summarization","date":"2024-03-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vwxyzjn/summarize_from_feedback_details","path":"summarize_from_feedback_details/ppo.py","file_url":"https://github.com/vwxyzjn/summarize_from_feedback_details/blob/HEAD/summarize_from_feedback_details/ppo.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3a136e5f5a8047ac","mcp_get_code":{"code_sha256":"3a136e5f5a8047ac"}}]}