{"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/aggregate-loss","entry":"aggregate_loss","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":5,"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":2,"n_samples_ran":2,"n_samples_fingerprinted":0,"n_places":5,"n_places_pointer_only":0,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":2,"unverified":0},"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":"2606.26917","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":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"29290736aa877212","mcp_get_code":{"code_sha256":"29290736aa877212"}},{"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":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"29290736aa877212","mcp_get_code":{"code_sha256":"29290736aa877212"}},{"arxiv_id":"2606.09124","paper":"/paper/arxiv-2606-09124","title":"A Regret Minimization Framework on Preference Learning in Large Language Models","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"OpenRLHF/OpenRLHF","path":"openrlhf/models/loss.py","file_url":"https://github.com/OpenRLHF/OpenRLHF/blob/HEAD/openrlhf/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":"0edeb138e07fbecc","mcp_get_code":{"code_sha256":"0edeb138e07fbecc"}},{"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":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"29290736aa877212","mcp_get_code":{"code_sha256":"29290736aa877212"}},{"arxiv_id":"2502.14768","paper":"/paper/logic-rl-unleashing-llm-reasoning-with-rule","title":"Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning","date":"2025-02-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"OpenLLMAI/OpenLLaMA2","path":"openrlhf/models/loss.py","file_url":"https://github.com/OpenLLMAI/OpenLLaMA2/blob/HEAD/openrlhf/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":"0edeb138e07fbecc","mcp_get_code":{"code_sha256":"0edeb138e07fbecc"}}]}