{"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/extract-xml-answer","entry":"extract_xml_answer","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":6,"n_samples_ran":3,"n_samples_fingerprinted":3,"n_places":8,"n_places_pointer_only":3,"by_status":{"ran_honours":1,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":2,"unverified":3},"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":"2606.18195","paper":"/paper/arxiv-2606-18195","title":"Learning from the Self-future: On-policy Self-distillation for dLLMs","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"xingzhejun/d-OPSD","path":"d-opsd/reward_func.py","file_url":"https://github.com/xingzhejun/d-OPSD/blob/HEAD/d-opsd/reward_func.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"08fcee8ccfd3d4a9","mcp_get_code":{"code_sha256":"08fcee8ccfd3d4a9"}},{"arxiv_id":"2606.16517","paper":"/paper/arxiv-2606-16517","title":"How Post-Training Shapes Biological Reasoning Models","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"mims-harvard/bio-posttrain","path":"BioReason/reason.py","file_url":"https://github.com/mims-harvard/bio-posttrain/blob/HEAD/BioReason/reason.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"3fca4c3b8039e70a","mcp_get_code":{"code_sha256":"3fca4c3b8039e70a"}},{"arxiv_id":"2603.02215","paper":"/paper/arxiv-2603-02215","title":"RxnNano:Training Compact LLMs for Chemical Reaction and Retrosynthesis Prediction via Hierarchical Curriculum Learning","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"rlisml/RxnNano","path":"src/evaluation/metrics.py","file_url":"https://github.com/rlisml/RxnNano/blob/HEAD/src/evaluation/metrics.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"697299f1698779c5","mcp_get_code":{"code_sha256":"697299f1698779c5"}},{"arxiv_id":"2602.19049","paper":"/paper/arxiv-2602-19049","title":"IAPO: Information-Aware Policy Optimization for Token-Efficient Reasoning","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"YinhanHe123/IAPO","path":"compute_reward.py","file_url":"https://github.com/YinhanHe123/IAPO/blob/HEAD/compute_reward.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ebf9846a096d47ae","mcp_get_code":{"code_sha256":"ebf9846a096d47ae"}},{"arxiv_id":"2602.06462","paper":"/paper/arxiv-2602-06462","title":"Diffusion-State Policy Optimization for Masked Diffusion Language Models","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"dllm-reasoning/d1","path":"diffu-grpo/reward_func.py","file_url":"https://github.com/dllm-reasoning/d1/blob/HEAD/diffu-grpo/reward_func.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":"08fcee8ccfd3d4a9","mcp_get_code":{"code_sha256":"08fcee8ccfd3d4a9"}},{"arxiv_id":"2510.07312","paper":"/paper/arxiv-2510-07312","title":"BOOTSTRAPPING LLMS TO REASON OVER LONGER HORIZONS VIA REINFORCEMENT LEARNING","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"AlesyaIvanova/h1","path":"grpo.py","file_url":"https://github.com/AlesyaIvanova/h1/blob/HEAD/grpo.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"08fcee8ccfd3d4a9","mcp_get_code":{"code_sha256":"08fcee8ccfd3d4a9"}},{"arxiv_id":"2505.17018","paper":"/paper/sophiavl-r1-reinforcing-mllms-reasoning-with","title":"SophiaVL-R1: Reinforcing MLLMs Reasoning with Thinking Reward","date":"2025-05-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kxfan2002/sophiavl-r1","path":"verl/workers/reward/custom.py","file_url":"https://github.com/kxfan2002/sophiavl-r1/blob/HEAD/verl/workers/reward/custom.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"816215511a181080","mcp_get_code":{"code_sha256":"816215511a181080"}},{"arxiv_id":"2504.01698","paper":"/paper/tom-rl-reinforcement-learning-unlocks-theory","title":"Do Theory of Mind Benchmarks Need Explicit Human-like Reasoning in Language Models?","date":"2025-04-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bigai-ai/ToM-RL","path":"verl/utils/reward_score/explore_tom_2.py","file_url":"https://github.com/bigai-ai/ToM-RL/blob/HEAD/verl/utils/reward_score/explore_tom_2.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"55d752fd12d893c2","mcp_get_code":{"code_sha256":"55d752fd12d893c2"}}]}