{"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/masked-sum","entry":"masked_sum","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":7,"n_samples_ran":6,"n_samples_fingerprinted":4,"n_places":10,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":4,"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":"2607.21653","paper":"/paper/arxiv-2607-21653","title":"Molt: A Scalable PyTorch-Native Training Framework for Agentic Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"NVIDIA-NeMo/labs-molt","path":"molt/models/loss.py","file_url":"https://github.com/NVIDIA-NeMo/labs-molt/blob/HEAD/molt/models/loss.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":"d4a9d22201f6f141","mcp_get_code":{"code_sha256":"d4a9d22201f6f141"}},{"arxiv_id":"2606.26917","paper":"/paper/arxiv-2606-26917","title":"GEOALIGN: Geometric Rollout Curation for Robust LLM Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"SYSUzhouting/Trinity-RFT","path":"trinity/algorithm/utils.py","file_url":"https://github.com/SYSUzhouting/Trinity-RFT/blob/HEAD/trinity/algorithm/utils.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":"21d59eaacff05781","mcp_get_code":{"code_sha256":"21d59eaacff05781"}},{"arxiv_id":"2606.20002","paper":"/paper/arxiv-2606-20002","title":"Connect the Dots: Training LLMs for Long-Lifecycle Agents with Cross-Domain Generalization Via Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"agentscope-ai/Trinity-RFT","path":"trinity/algorithm/utils.py","file_url":"https://github.com/agentscope-ai/Trinity-RFT/blob/HEAD/trinity/algorithm/utils.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":"21d59eaacff05781","mcp_get_code":{"code_sha256":"21d59eaacff05781"}},{"arxiv_id":"2601.03715","paper":"/paper/arxiv-2601-03715","title":"AgentScope, Tongyi Lab R 3 L: Reflect-then-Retry Reinforcement Learning with Language-Guided Exploration, Pivotal Credit, and Positive Amplification","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"shiweijiezero/R3L","path":"trinity/algorithm/utils.py","file_url":"https://github.com/shiweijiezero/R3L/blob/HEAD/trinity/algorithm/utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"a6fdd35c17b3e086","mcp_get_code":{"code_sha256":"a6fdd35c17b3e086"}},{"arxiv_id":"2510.25441","paper":"/paper/arxiv-2510-25441","title":"Grounded in Reality: Learning and Deploying Proactive LLM from Offline Logs","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"modelscope/Trinity-RFT","path":"trinity/algorithm/utils.py","file_url":"https://github.com/modelscope/Trinity-RFT/blob/HEAD/trinity/algorithm/utils.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":"21d59eaacff05781","mcp_get_code":{"code_sha256":"21d59eaacff05781"}},{"arxiv_id":"2505.20280","paper":"/paper/lorentz-local-canonicalization-how-to-make","title":"Lorentz Local Canonicalization: How to Make Any Network Lorentz-Equivariant","date":"2025-05-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"heidelberg-hepml/lloca-experiments","path":"experiments/baselines/pelican/perm_equiv_layers.py","file_url":"https://github.com/heidelberg-hepml/lloca-experiments/blob/HEAD/experiments/baselines/pelican/perm_equiv_layers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b6fc95bee01e3fa3","mcp_get_code":{"code_sha256":"b6fc95bee01e3fa3"}},{"arxiv_id":"2505.15311","paper":"/paper/trajectory-bellman-residual-minimization-a","title":"Trajectory Bellman Residual Minimization: A Simple Value-Based Method for LLM Reasoning","date":"2025-05-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rlx-lab/TBRM","path":"verl/tbrm/core_algos.py","file_url":"https://github.com/rlx-lab/TBRM/blob/HEAD/verl/tbrm/core_algos.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"a6fdd35c17b3e086","mcp_get_code":{"code_sha256":"a6fdd35c17b3e086"}},{"arxiv_id":"2406.09279","paper":"/paper/unpacking-dpo-and-ppo-disentangling-best","title":"Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback","date":"2024-06-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hamishivi/EasyLM","path":"EasyLM/models/llama/llama_train_ppo.py","file_url":"https://github.com/hamishivi/EasyLM/blob/HEAD/EasyLM/models/llama/llama_train_ppo.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"7cbbe7f38c74cab8","mcp_get_code":{"code_sha256":"7cbbe7f38c74cab8"}},{"arxiv_id":"2202.13196","paper":"/paper/toward-interpretable-semantic-textual","title":"Toward Interpretable Semantic Textual Similarity via Optimal Transport-based Contrastive Sentence Learning","date":"2022-02-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sh0416/clrcmd","path":"src/clrcmd/models.py","file_url":"https://github.com/sh0416/clrcmd/blob/HEAD/src/clrcmd/models.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"09bf1daaa67faf33","mcp_get_code":{"code_sha256":"09bf1daaa67faf33"}},{"arxiv_id":"2108.13643","paper":"/paper/learning-to-synthesize-programs-as","title":"Learning to Synthesize Programs as Interpretable and Generalizable Policies","date":"2021-08-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"clvrai/leaps","path":"pretrain/models.py","file_url":"https://github.com/clvrai/leaps/blob/HEAD/pretrain/models.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"656bc963190be4b0","mcp_get_code":{"code_sha256":"656bc963190be4b0"}}]}