{"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/load-state-dict-to-megatron-gptmodel","entry":"load_state_dict_to_megatron_gptmodel","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-25T09:33:49+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":7,"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":3,"n_samples_ran":0,"n_samples_fingerprinted":0,"n_places":7,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"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":"2606.03608","paper":"/paper/arxiv-2606-03608","title":"Exploiting Verification-Generation Gap: Test-Time Reinforcement Learning with Confidence-Conditioned Verification","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"shanjf666/CoCoV","path":"verl/verl/models/mcore/loader.py","file_url":"https://github.com/shanjf666/CoCoV/blob/HEAD/verl/verl/models/mcore/loader.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0d364d43436cf1dd","mcp_get_code":{"code_sha256":"0d364d43436cf1dd"}},{"arxiv_id":"2603.10624","paper":"/paper/arxiv-2603-10624","title":"Reinforcement Learning with Conditional Expectation Reward","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"changyi7231/CER","path":"verl/models/mcore/loader.py","file_url":"https://github.com/changyi7231/CER/blob/HEAD/verl/models/mcore/loader.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":"1853101234cf952e","mcp_get_code":{"code_sha256":"1853101234cf952e"}},{"arxiv_id":"2603.05308","paper":"/paper/arxiv-2603-05308","title":"Med-V1: Small Language Models for Zero-shot and Scalable Biomedical Evidence Attribution","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"ncbi-nlp/Med-V1","path":"training/grpo/verl/models/mcore/loader.py","file_url":"https://github.com/ncbi-nlp/Med-V1/blob/HEAD/training/grpo/verl/models/mcore/loader.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0d364d43436cf1dd","mcp_get_code":{"code_sha256":"0d364d43436cf1dd"}},{"arxiv_id":"2602.12113","paper":"/paper/arxiv-2602-12113","title":"Adaptive Reflection and Length Coordinated Penalty (ARLCP) STOP UNNECESSARY REFLECTION: TRAINING LRMS FOR EFFICIENT REASONING WITH ADAPTIVE REFLEC-TION AND LENGTH COORDINATED PENALTY","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"ZeweiYu1/ARLCP","path":"verl/models/mcore/loader.py","file_url":"https://github.com/ZeweiYu1/ARLCP/blob/HEAD/verl/models/mcore/loader.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1853101234cf952e","mcp_get_code":{"code_sha256":"1853101234cf952e"}},{"arxiv_id":"2512.16848","paper":"/paper/arxiv-2512-16848","title":"Meta-RL Induces Exploration in Language Agents","date":null,"month_inferred_from_arxiv_id":"2025-12","title_source":"syntology","repo":"mlbio-epfl/LaMer","path":"verl/models/mcore/loader.py","file_url":"https://github.com/mlbio-epfl/LaMer/blob/HEAD/verl/models/mcore/loader.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1853101234cf952e","mcp_get_code":{"code_sha256":"1853101234cf952e"}},{"arxiv_id":"2504.05520","paper":"/paper/efficient-reinforcement-finetuning-via","title":"Efficient Reinforcement Finetuning via Adaptive Curriculum Learning","date":"2025-04-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"uscnlp-lime/verl","path":"verl/models/mcore/loader.py","file_url":"https://github.com/uscnlp-lime/verl/blob/HEAD/verl/models/mcore/loader.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":"1901b047ab8e1654","mcp_get_code":{"code_sha256":"1901b047ab8e1654"}},{"arxiv_id":"2503.22342","paper":"/paper/cppo-accelerating-the-training-of-group","title":"CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models","date":"2025-03-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lzhxmu/cppo","path":"cppo_verl/verl/models/mcore/loader.py","file_url":"https://github.com/lzhxmu/cppo/blob/HEAD/cppo_verl/verl/models/mcore/loader.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":"1901b047ab8e1654","mcp_get_code":{"code_sha256":"1901b047ab8e1654"}}]}