{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YYXR2WAL6MK5EWBYF2QDMLUFPS","short_pith_number":"pith:YYXR2WAL","schema_version":"1.0","canonical_sha256":"c62f1d580bf315d258382ea0362e857c8d43d67375d111aa7ff0b1884177f5cb","source":{"kind":"arxiv","id":"2405.11143","version":6},"attestation_state":"computed","paper":{"title":"OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"OpenRLHF delivers a streamlined open-source framework for RLHF that trains models 1.22x to 1.68x faster while requiring far fewer lines of code.","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Bin Chen, Hao Chen, Haoran Wang, Haotian Xu, Jason Klein Liu, Jian Hu, Songlin Jiang, Weikai Fang, Wei Shen, Weixun Wang, Xianyu, Xibin Wu, Yiming Liu, Yu Cao, Zilin Zhu","submitted_at":"2024-05-20T01:04:40Z","abstract_excerpt":"Large Language Models (LLMs) fine-tuned via Reinforcement Learning from Human Feedback (RLHF) and Reinforcement Learning with Verifiable Rewards (RLVR) significantly improve the alignment of human-AI values, further raising the upper bound of AI capabilities, particularly in reasoning-intensive, long-context Chain-of-Thought (CoT) tasks. However, existing frameworks commonly face challenges such as inference bottlenecks and complexity barriers, which restrict their accessibility to newcomers. To bridge this gap, we introduce \\textbf{OpenRLHF}, a user-friendly, scalable, and easy-to-learn open-"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2405.11143","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-05-20T01:04:40Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"cac5c1897e3139b2e2616615e0260b990c1809c83d38220b3a69c988b2521d15","abstract_canon_sha256":"97f3ea108185fc25741dae86d92f03fa0ec171db8c855fab78d2fd4659774e7a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:53.680532Z","signature_b64":"KqYSQGxBRekqEfjP2TJkgyzVdX1WcNPQ+Fmnkp2QYOiVKtOOg7GSZbBYdg7szU8+6ro08xvRpNEjixvoAcoPBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c62f1d580bf315d258382ea0362e857c8d43d67375d111aa7ff0b1884177f5cb","last_reissued_at":"2026-05-17T23:38:53.680048Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:53.680048Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"OpenRLHF delivers a streamlined open-source framework for RLHF that trains models 1.22x to 1.68x faster while requiring far fewer lines of code.","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Bin Chen, Hao Chen, Haoran Wang, Haotian Xu, Jason Klein Liu, Jian Hu, Songlin Jiang, Weikai Fang, Wei Shen, Weixun Wang, Xianyu, Xibin Wu, Yiming Liu, Yu Cao, Zilin Zhu","submitted_at":"2024-05-20T01:04:40Z","abstract_excerpt":"Large Language Models (LLMs) fine-tuned via Reinforcement Learning from Human Feedback (RLHF) and Reinforcement Learning with Verifiable Rewards (RLVR) significantly improve the alignment of human-AI values, further raising the upper bound of AI capabilities, particularly in reasoning-intensive, long-context Chain-of-Thought (CoT) tasks. However, existing frameworks commonly face challenges such as inference bottlenecks and complexity barriers, which restrict their accessibility to newcomers. To bridge this gap, we introduce \\textbf{OpenRLHF}, a user-friendly, scalable, and easy-to-learn open-"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experimental results show that OpenRLHF achieves superior training efficiency, with speedups ranging from 1.22x to 1.68x across different model sizes, compared to state-of-the-art frameworks. Additionally, it requires significantly fewer lines of code for implementation.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The reported speedups and code reductions are measured under fair, comparable conditions against the true state-of-the-art baselines, and the ease-of-use metric (lines of code) accurately reflects real-world implementation effort for typical users.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"OpenRLHF is a new open-source RLHF framework reporting 1.22x to 1.68x speedups and fewer lines of code than prior systems.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"OpenRLHF delivers a streamlined open-source framework for RLHF that trains models 1.22x to 1.68x faster while requiring far fewer lines of code.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"ae0be8a697a3fc02167f98e44202e47dbd919e6c41b6a9fd0a9ea4d481e2e6df"},"source":{"id":"2405.11143","kind":"arxiv","version":6},"verdict":{"id":"edd6e13c-8c67-4d5f-93cf-1a2be2b4b07b","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T03:24:18.968024Z","strongest_claim":"Experimental results show that OpenRLHF achieves superior training efficiency, with speedups ranging from 1.22x to 1.68x across different model sizes, compared to state-of-the-art frameworks. Additionally, it requires significantly fewer lines of code for implementation.","one_line_summary":"OpenRLHF is a new open-source RLHF framework reporting 1.22x to 1.68x speedups and fewer lines of code than prior systems.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The reported speedups and code reductions are measured under fair, comparable conditions against the true state-of-the-art baselines, and the ease-of-use metric (lines of code) accurately reflects real-world implementation effort for typical users.","pith_extraction_headline":"OpenRLHF delivers a streamlined open-source framework for RLHF that trains models 1.22x to 1.68x faster while requiring far fewer lines of code."},"references":{"count":30,"sample":[{"doi":"","year":2017,"title":"Deep reinforcement learning from human preferences.Advances in neural information processing systems, 30","work_id":"a63ca98b-8916-47bd-bd9b-d0c693024f4c","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"Learning to summarize with human feedback","work_id":"4098eb4f-6e58-402f-9bde-2a625fa0675c","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","work_id":"e6b75ad5-2877-4168-97c8-710407094d20","ref_index":3,"cited_arxiv_id":"2501.12948","is_internal_anchor":true},{"doi":"","year":2025,"title":"Exploring data scaling trends and effects in reinforcement learning from human feedback","work_id":"b7419524-b2c2-49b3-9745-04133e8060b2","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","ref_index":5,"cited_arxiv_id":"2303.08774","is_internal_anchor":true}],"resolved_work":30,"snapshot_sha256":"ccd33241ac43c41a3506861d99c53b6a062aee36fbf96c8829ac817e291594f2","internal_anchors":10},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2405.11143","created_at":"2026-05-17T23:38:53.680124+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.11143v6","created_at":"2026-05-17T23:38:53.680124+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.11143","created_at":"2026-05-17T23:38:53.680124+00:00"},{"alias_kind":"pith_short_12","alias_value":"YYXR2WAL6MK5","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"YYXR2WAL6MK5EWBY","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"YYXR2WAL","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":50,"internal_anchor_count":50,"sample":[{"citing_arxiv_id":"2605.20201","citing_title":"Long-Context Reasoning Through Proxy-Based Chain-of-Thought Tuning","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2502.12272","citing_title":"Learning to Reason at the Frontier of Learnability","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2502.13957","citing_title":"Supervising the search process produces reliable and generalizable information-seeking agents","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2504.12501","citing_title":"Reinforcement Learning from Human Feedback","ref_index":156,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22781","citing_title":"DeltaBox: Scaling Stateful AI Agents with Millisecond-Level Sandbox Checkpoint/Rollback","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2508.04149","citing_title":"Difficulty-Based Preference Data Selection by DPO Implicit Reward Gap","ref_index":49,"is_internal_anchor":true},{"citing_arxiv_id":"2601.21350","citing_title":"Factored Causal Representation Learning for Robust Reward Modeling in RLHF","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2602.03839","citing_title":"Understanding and Exploiting Weight Update Sparsity for Communication-Efficient Distributed RL","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20201","citing_title":"Long-Context Reasoning Through Proxy-Based Chain-of-Thought Tuning","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06534","citing_title":"ROSE: Rollout On Serving GPUs via Cooperative Elasticity for Agentic RL","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20863","citing_title":"PlexRL: Cluster-Level Orchestration of Serviceized LLM Execution for RLVR","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15565","citing_title":"AstraFlow: Dataflow-Oriented Reinforcement Learning for Agentic LLMs","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19358","citing_title":"Taming the Thinker: Conditional Entropy Shaping for Adaptive LLM Reasoning","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15422","citing_title":"DualKV: Shared-Prompt Flash Attention for Efficient RL Training with Large Rollouts and Long Contexts","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2507.15640","citing_title":"Data Mixing Agent: Learning to Re-weight Domains for Continual Pre-training","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2510.19225","citing_title":"RLBoost: Harvesting Preemptible Resources for Cost-Efficient Reinforcement Learning on LLMs","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2509.08827","citing_title":"A Survey of Reinforcement Learning for Large Reasoning Models","ref_index":201,"is_internal_anchor":true},{"citing_arxiv_id":"2511.14617","citing_title":"Seer: Online Context Learning for Fast Synchronous LLM Reinforcement Learning","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2511.18871","citing_title":"Periodic Asynchrony: An On-Policy Approach for Accelerating LLM Reinforcement Learning","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2512.12476","citing_title":"HetRL: Efficient Reinforcement Learning for LLMs in Heterogeneous Environments","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2503.07536","citing_title":"LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2505.18719","citing_title":"VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learning","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2503.15558","citing_title":"Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2602.13218","citing_title":"Scaling the Scaling Logic: Agentic Meta-Synthesis of Logic Reasoning","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2601.18150","citing_title":"FP8-RL: A Practical and Stable Low-Precision Stack for LLM Reinforcement Learning","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YYXR2WAL6MK5EWBYF2QDMLUFPS","json":"https://pith.science/pith/YYXR2WAL6MK5EWBYF2QDMLUFPS.json","graph_json":"https://pith.science/api/pith-number/YYXR2WAL6MK5EWBYF2QDMLUFPS/graph.json","events_json":"https://pith.science/api/pith-number/YYXR2WAL6MK5EWBYF2QDMLUFPS/events.json","paper":"https://pith.science/paper/YYXR2WAL"},"agent_actions":{"view_html":"https://pith.science/pith/YYXR2WAL6MK5EWBYF2QDMLUFPS","download_json":"https://pith.science/pith/YYXR2WAL6MK5EWBYF2QDMLUFPS.json","view_paper":"https://pith.science/paper/YYXR2WAL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.11143&json=true","fetch_graph":"https://pith.science/api/pith-number/YYXR2WAL6MK5EWBYF2QDMLUFPS/graph.json","fetch_events":"https://pith.science/api/pith-number/YYXR2WAL6MK5EWBYF2QDMLUFPS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YYXR2WAL6MK5EWBYF2QDMLUFPS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YYXR2WAL6MK5EWBYF2QDMLUFPS/action/storage_attestation","attest_author":"https://pith.science/pith/YYXR2WAL6MK5EWBYF2QDMLUFPS/action/author_attestation","sign_citation":"https://pith.science/pith/YYXR2WAL6MK5EWBYF2QDMLUFPS/action/citation_signature","submit_replication":"https://pith.science/pith/YYXR2WAL6MK5EWBYF2QDMLUFPS/action/replication_record"}},"created_at":"2026-05-17T23:38:53.680124+00:00","updated_at":"2026-05-17T23:38:53.680124+00:00"}