{"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/split-tensor-dict","entry":"split_tensor_dict","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":10,"n_papers_ran":9,"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":4,"n_samples_fingerprinted":0,"n_places":10,"n_places_pointer_only":4,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":0,"ran":2,"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":"2605.29398","paper":"/paper/arxiv-2605-29398","title":"GDSD: Reinforcement Learning as Guided Denoiser Self-Distillation for Diffusion Language Models","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"GaryBall/GDSD","path":"gdsd/trainers/espo_trainer.py","file_url":"https://github.com/GaryBall/GDSD/blob/HEAD/gdsd/trainers/espo_trainer.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":"23e33cf487ecdf91","mcp_get_code":{"code_sha256":"23e33cf487ecdf91"}},{"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/trainer/dgao_trainer.py","file_url":"https://github.com/Hyalinesky/DGAO/blob/HEAD/trl/trainer/dgao_trainer.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":"ba58cd6dfd66f89c","mcp_get_code":{"code_sha256":"ba58cd6dfd66f89c"}},{"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":"package_code/trainer/dapo_trainer.py","file_url":"https://github.com/YinhanHe123/IAPO/blob/HEAD/package_code/trainer/dapo_trainer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ba58cd6dfd66f89c","mcp_get_code":{"code_sha256":"ba58cd6dfd66f89c"}},{"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/grpo_trainer.py","file_url":"https://github.com/friendshipkim/gopo/blob/HEAD/src/open_r1/grpo_trainer.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"efd67e2adf6b1ba5","mcp_get_code":{"code_sha256":"efd67e2adf6b1ba5"}},{"arxiv_id":"2601.04700","paper":"/paper/arxiv-2601-04700","title":"PRISM: A Unified Framework for Post-Training LLMs Without Verifiable Rewards","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"ghimiremukesh/PRISM","path":"open-r1-intuitor/src/open_r1/critque_intuitor_trainer.py","file_url":"https://github.com/ghimiremukesh/PRISM/blob/HEAD/open-r1-intuitor/src/open_r1/critque_intuitor_trainer.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"efd67e2adf6b1ba5","mcp_get_code":{"code_sha256":"efd67e2adf6b1ba5"}},{"arxiv_id":"2511.04902","paper":"/paper/arxiv-2511-04902","title":"You Need Reasoning to Learn Reasoning: The Limitations of Label-Free RL in Weak Base Models","date":null,"month_inferred_from_arxiv_id":"2025-11","title_source":"syntology","repo":"BorealisAI/CuMa","path":"src/open_r1/intuitor_trainer.py","file_url":"https://github.com/BorealisAI/CuMa/blob/HEAD/src/open_r1/intuitor_trainer.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"efd67e2adf6b1ba5","mcp_get_code":{"code_sha256":"efd67e2adf6b1ba5"}},{"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/coupled_grpo.py","file_url":"https://github.com/apple/ml-diffucoder/blob/HEAD/src/open_r1/coupled_grpo.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"0fa983fc585a3b51","mcp_get_code":{"code_sha256":"0fa983fc585a3b51"}},{"arxiv_id":"2506.14755","paper":"/paper/optimizing-length-compression-in-large","title":"Optimizing Length Compression in Large Reasoning Models","date":"2025-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"efd67e2adf6b1ba5","mcp_get_code":{"code_sha256":"efd67e2adf6b1ba5"}},{"arxiv_id":"2505.17534","paper":"/paper/co-reinforcement-learning-for-unified","title":"Co-Reinforcement Learning for Unified Multimodal Understanding and Generation","date":"2025-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mm-vl/ulm-r1","path":"ttrl/trainer/grpo_trainer_mm2t.py","file_url":"https://github.com/mm-vl/ulm-r1/blob/HEAD/ttrl/trainer/grpo_trainer_mm2t.py","status":"ran_draft_wrong","verification_level":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"e919a9d676d7aefe","mcp_get_code":{"code_sha256":"e919a9d676d7aefe"}},{"arxiv_id":"2402.16302","paper":"/paper/graph-diffusion-policy-optimization","title":"Graph Diffusion Policy Optimization","date":"2024-02-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"NVlabs/GDPO","path":"trl-GDPO/trl-0.18.0-gdpo/trl/trainer/grpo_trainer.py","file_url":"https://github.com/NVlabs/GDPO/blob/HEAD/trl-GDPO/trl-0.18.0-gdpo/trl/trainer/grpo_trainer.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"efd67e2adf6b1ba5","mcp_get_code":{"code_sha256":"efd67e2adf6b1ba5"}}]}