{"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/is-valid-ipv6-address","entry":"is_valid_ipv6_address","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":16,"n_papers_ran":0,"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":1,"n_samples_ran":0,"n_samples_fingerprinted":0,"n_places":16,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"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":"2609.02548","paper":"/paper/arxiv-2609-02548","title":"Learn from Whoever Is Right: Answer-Verified Multi-Teacher Distillation for Multi-Domain LLMs","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"hexixiang/MT-SDPO","path":"training/verl/utils/net_utils.py","file_url":"https://github.com/hexixiang/MT-SDPO/blob/HEAD/training/verl/utils/net_utils.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":"72b5e8089e8c68a6","mcp_get_code":{"code_sha256":"72b5e8089e8c68a6"}},{"arxiv_id":"2609.01245","paper":"/paper/arxiv-2609-01245","title":"Explore More, Drift Less: Outcome-Only Reinforcement Learning Can Suffice for Long-Horizon Interactive Agents","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"AlibabaResearch/SignalCoverageRL","path":"verl/utils/net_utils.py","file_url":"https://github.com/AlibabaResearch/SignalCoverageRL/blob/HEAD/verl/utils/net_utils.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":"72b5e8089e8c68a6","mcp_get_code":{"code_sha256":"72b5e8089e8c68a6"}},{"arxiv_id":"2608.24350","paper":"/paper/arxiv-2608-24350","title":"FARCA: Fact-Aligned Reliability-Aware Credit Assignment for Reinforcement Learning with Factual Supervision","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"verl-project/verl","path":"verl/utils/net_utils.py","file_url":"https://github.com/verl-project/verl/blob/HEAD/verl/utils/net_utils.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":"72b5e8089e8c68a6","mcp_get_code":{"code_sha256":"72b5e8089e8c68a6"}},{"arxiv_id":"2608.23566","paper":"/paper/arxiv-2608-23566","title":"Best Practice Critic Optimization BEST PRACTICE CRITIC OPTIMIZATION","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"QPHutu/golden_critic","path":"verl/utils/net_utils.py","file_url":"https://github.com/QPHutu/golden_critic/blob/HEAD/verl/utils/net_utils.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":"72b5e8089e8c68a6","mcp_get_code":{"code_sha256":"72b5e8089e8c68a6"}},{"arxiv_id":"2608.02139","paper":"/paper/arxiv-2608-02139","title":"Self-Improving Large Language Models via Progressive Experience Evolution","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"rrrsj/SPEE","path":"verl/utils/net_utils.py","file_url":"https://github.com/rrrsj/SPEE/blob/HEAD/verl/utils/net_utils.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":"72b5e8089e8c68a6","mcp_get_code":{"code_sha256":"72b5e8089e8c68a6"}},{"arxiv_id":"2607.07976","paper":"/paper/arxiv-2607-07976","title":"When Implausible Tokens Get Reinforced: Tail-Aware Credit Calibration for LLM Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"xiuyilou/TACO","path":"verl/utils/net_utils.py","file_url":"https://github.com/xiuyilou/TACO/blob/HEAD/verl/utils/net_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"72b5e8089e8c68a6","mcp_get_code":{"code_sha256":"72b5e8089e8c68a6"}},{"arxiv_id":"2607.01763","paper":"/paper/arxiv-2607-01763","title":"DENSER ̸ = BETTER: LIMITS OF ON-POLICY SELF-DISTILLATION FOR CONTINUAL POST-TRAINING","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"Moenupa/SDPO-CL","path":"verl/utils/net_utils.py","file_url":"https://github.com/Moenupa/SDPO-CL/blob/HEAD/verl/utils/net_utils.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":"72b5e8089e8c68a6","mcp_get_code":{"code_sha256":"72b5e8089e8c68a6"}},{"arxiv_id":"2606.04036","paper":"/paper/arxiv-2606-04036","title":"Self-Distilled Policy Gradient","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"lauyikfung/SDPG","path":"verl/utils/net_utils.py","file_url":"https://github.com/lauyikfung/SDPG/blob/HEAD/verl/utils/net_utils.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":"72b5e8089e8c68a6","mcp_get_code":{"code_sha256":"72b5e8089e8c68a6"}},{"arxiv_id":"2605.28014","paper":"/paper/arxiv-2605-28014","title":"ROSD: Reflective On-Policy Self-Distillation for Language Model Reasoning across Domains","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"ZiqiZhao1/ROSD","path":"verl/utils/net_utils.py","file_url":"https://github.com/ZiqiZhao1/ROSD/blob/HEAD/verl/utils/net_utils.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":"72b5e8089e8c68a6","mcp_get_code":{"code_sha256":"72b5e8089e8c68a6"}},{"arxiv_id":"2605.27865","paper":"/paper/arxiv-2605-27865","title":"MERIT: Matching Expertise via Rubric-Informed Training for Reviewer Assignment","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"Luli3220/MERIT","path":"MERIT-Assessor/verl/utils/net_utils.py","file_url":"https://github.com/Luli3220/MERIT/blob/HEAD/MERIT-Assessor/verl/utils/net_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"72b5e8089e8c68a6","mcp_get_code":{"code_sha256":"72b5e8089e8c68a6"}},{"arxiv_id":"2605.16999","paper":"/paper/arxiv-2605-16999","title":"Ranking-Aware Calibration for Reliable Multimodal Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"Stellaris167/RAC","path":"verl/utils/net_utils.py","file_url":"https://github.com/Stellaris167/RAC/blob/HEAD/verl/utils/net_utils.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":"72b5e8089e8c68a6","mcp_get_code":{"code_sha256":"72b5e8089e8c68a6"}},{"arxiv_id":"2605.07331","paper":"/paper/arxiv-2605-07331","title":"Rethinking Importance Sampling in LLM Policy Optimization: A Cumulative Token Perspective","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"horizon-llm/CTPO","path":"verl/utils/net_utils.py","file_url":"https://github.com/horizon-llm/CTPO/blob/HEAD/verl/utils/net_utils.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":"72b5e8089e8c68a6","mcp_get_code":{"code_sha256":"72b5e8089e8c68a6"}},{"arxiv_id":"2603.24472","paper":"/paper/arxiv-2603-24472","title":"Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"lasgroup/SDPO","path":"verl/utils/net_utils.py","file_url":"https://github.com/lasgroup/SDPO/blob/HEAD/verl/utils/net_utils.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":"72b5e8089e8c68a6","mcp_get_code":{"code_sha256":"72b5e8089e8c68a6"}},{"arxiv_id":"2602.10609","paper":"/paper/arxiv-2602-10609","title":"Online Causal Kalman Filtering for Stable and Effective Policy Optimization","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"shuohe1995/verl-kpo","path":"verl/utils/net_utils.py","file_url":"https://github.com/shuohe1995/verl-kpo/blob/HEAD/verl/utils/net_utils.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":"72b5e8089e8c68a6","mcp_get_code":{"code_sha256":"72b5e8089e8c68a6"}},{"arxiv_id":"2602.04879","paper":"/paper/arxiv-2602-04879","title":"Rethinking the Trust Region in LLM Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"sail-sg/Stable-RL","path":"verl/utils/net_utils.py","file_url":"https://github.com/sail-sg/Stable-RL/blob/HEAD/verl/utils/net_utils.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":"72b5e8089e8c68a6","mcp_get_code":{"code_sha256":"72b5e8089e8c68a6"}},{"arxiv_id":"2506.03887","paper":"/paper/pre-3-enabling-deterministic-pushdown","title":"Pre$^3$: Enabling Deterministic Pushdown Automata for Faster Structured LLM Generation","date":"2025-06-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ModelTC/lightllm","path":"lightllm/utils/net_utils.py","file_url":"https://github.com/ModelTC/lightllm/blob/HEAD/lightllm/utils/net_utils.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":"72b5e8089e8c68a6","mcp_get_code":{"code_sha256":"72b5e8089e8c68a6"}}]}