{"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/dataproto","entry":"DataProto","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":3,"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":3,"n_samples_fingerprinted":0,"n_places":5,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":3,"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":"2605.24331","paper":"/paper/arxiv-2605-24331","title":"CurveRL: Principled Distribution-Aware Context Reweighting for LLM Reasoning","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"zhyzmath/CurveRL","path":"recipe/sppo/sppo_ray_trainer.py","file_url":"https://github.com/zhyzmath/CurveRL/blob/HEAD/recipe/sppo/sppo_ray_trainer.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":"ef325088d033e27f","mcp_get_code":{"code_sha256":"ef325088d033e27f"}},{"arxiv_id":"2603.02146","paper":"/paper/arxiv-2603-02146","title":"LongRLVR: Long-Context Reinforcement Learning Requires Verifiable Context Rewards","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"real-absolute-AI/LongRLVR","path":"recipe/dapo/longrl_reward_manager.py","file_url":"https://github.com/real-absolute-AI/LongRLVR/blob/HEAD/recipe/dapo/longrl_reward_manager.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"be6ff037330b7987","mcp_get_code":{"code_sha256":"be6ff037330b7987"}},{"arxiv_id":"2506.05316","paper":"/paper/improving-data-efficiency-for-llm","title":"Improving Data Efficiency for LLM Reinforcement Fine-tuning Through Difficulty-targeted Online Data Selection and Rollout Replay","date":"2025-06-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"astral-group/data-efficient-llm-rl","path":"rl_training/verl/verl/trainer/ppo/ray_trainer_teacher_replay.py","file_url":"https://github.com/astral-group/data-efficient-llm-rl/blob/HEAD/rl_training/verl/verl/trainer/ppo/ray_trainer_teacher_replay.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"20ba9212ecfbbbbc","mcp_get_code":{"code_sha256":"20ba9212ecfbbbbc"}},{"arxiv_id":"2505.17447","paper":null,"title":"arXiv:2505.17447","date":null,"month_inferred_from_arxiv_id":"2025-05","title_source":null,"repo":"Cheungki/LeTS","path":"src/verl/workers/reward_manager/lets.py","file_url":"https://github.com/Cheungki/LeTS/blob/HEAD/src/verl/workers/reward_manager/lets.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ed505af43bfe067d","mcp_get_code":{"code_sha256":"ed505af43bfe067d"}},{"arxiv_id":"2505.14146","paper":"/paper/s3-you-don-t-need-that-much-data-to-train-a","title":"s3: You Don't Need That Much Data to Train a Search Agent via RL","date":"2025-05-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pat-jj/s3","path":"s3/llm_agent/generation_s3.py","file_url":"https://github.com/pat-jj/s3/blob/HEAD/s3/llm_agent/generation_s3.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"3ddd2f19ce79889e","mcp_get_code":{"code_sha256":"3ddd2f19ce79889e"}}]}