{"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/tag-count-reward","entry":"tag_count_reward","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":5,"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":1,"n_samples_fingerprinted":0,"n_places":8,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":1,"unverified":1},"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":"2606.12900","paper":"/paper/arxiv-2606-12900","title":"Zero-source LLM Hallucination Detection with Human-like Criteria Probing","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"TRISKEL10N/HCPD","path":"src/open_r1/rewards.py","file_url":"https://github.com/TRISKEL10N/HCPD/blob/HEAD/src/open_r1/rewards.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":"0a5673b11c91e69d","mcp_get_code":{"code_sha256":"0a5673b11c91e69d"}},{"arxiv_id":"2602.03876","paper":"/paper/arxiv-2602-03876","title":"GOPO: Policy Optimization using Ranked Rewards","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"friendshipkim/gopo","path":"src/open_r1/rewards.py","file_url":"https://github.com/friendshipkim/gopo/blob/HEAD/src/open_r1/rewards.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":"0a5673b11c91e69d","mcp_get_code":{"code_sha256":"0a5673b11c91e69d"}},{"arxiv_id":"2602.02258","paper":"/paper/arxiv-2602-02258","title":"Alignment-Aware Model Adaptation via Feedback-Guided Optimization","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"facebookresearch/TruthRL","path":"training/open-r1/src/open_r1/rewards.py","file_url":"https://github.com/facebookresearch/TruthRL/blob/HEAD/training/open-r1/src/open_r1/rewards.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0a5673b11c91e69d","mcp_get_code":{"code_sha256":"0a5673b11c91e69d"}},{"arxiv_id":"2507.02834","paper":null,"title":"arXiv:2507.02834","date":null,"month_inferred_from_arxiv_id":"2025-07","title_source":null,"repo":"huggingface/open-r1","path":"src/open_r1/rewards.py","file_url":"https://github.com/huggingface/open-r1/blob/HEAD/src/open_r1/rewards.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":"0a5673b11c91e69d","mcp_get_code":{"code_sha256":"0a5673b11c91e69d"}},{"arxiv_id":"2506.20639","paper":"/paper/diffucoder-understanding-and-improving-masked","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","date":"2025-06-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"apple/ml-diffucoder","path":"src/open_r1/rewards.py","file_url":"https://github.com/apple/ml-diffucoder/blob/HEAD/src/open_r1/rewards.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0a5673b11c91e69d","mcp_get_code":{"code_sha256":"0a5673b11c91e69d"}},{"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/rewards.py","file_url":"https://github.com/xiwenc1/dra-grpo/blob/HEAD/src/open_r1/rewards.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0a9f60618bd16d86","mcp_get_code":{"code_sha256":"0a9f60618bd16d86"}},{"arxiv_id":"2504.15777","paper":"/paper/tina-tiny-reasoning-models-via-lora","title":"Tina: Tiny Reasoning Models via LoRA","date":"2025-04-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shangshang-wang/tina","path":"tina/post_train_hf/rewards.py","file_url":"https://github.com/shangshang-wang/tina/blob/HEAD/tina/post_train_hf/rewards.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":"0a9f60618bd16d86","mcp_get_code":{"code_sha256":"0a9f60618bd16d86"}},{"arxiv_id":"2503.16219","paper":"/paper/reinforcement-learning-for-reasoning-in-small","title":"Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn't","date":"2025-03-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"knoveleng/open-rs","path":"src/open_r1/rewards.py","file_url":"https://github.com/knoveleng/open-rs/blob/HEAD/src/open_r1/rewards.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0a9f60618bd16d86","mcp_get_code":{"code_sha256":"0a9f60618bd16d86"}}]}