{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4RVOZWSSGWRNUOXU72EDWKVPD2","short_pith_number":"pith:4RVOZWSS","schema_version":"1.0","canonical_sha256":"e46aecda5235a2da3af4fe883b2aaf1e9e14235c44b99b203b04f342cb48cc4d","source":{"kind":"arxiv","id":"2507.13833","version":4},"attestation_state":"computed","paper":{"title":"DistFlow: A Fully Distributed RL Framework for Scalable and Efficient LLM Post-Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Dian Yang, Jiaming Xu, Jiarui Hu, Jinlong Hou, Liming Liu, Mingjun Zhang, Ping Zhang, Siyuan Feng, Tianyi Zhou, Tongyu Wang, Yuan Cheng, Yuan Qi, Zhixin Wang","submitted_at":"2025-07-18T11:41:49Z","abstract_excerpt":"Effectively scaling Reinforcement Learning (RL) is crucial for enhancing the reasoning and alignment of Large Language Models. The massive data and complex execution flows inherent in these tasks require a distributed architecture capable of efficient scaling. However, to simplify programming and dependency management, mainstream frameworks often rely on a centralized architecture where a single node dispatches both control and data. This inherent coupling creates significant communication bottlenecks, severely limiting system scalability and efficiency. We present DISTFLOW, a novel, fully dis"},"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":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2507.13833","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-07-18T11:41:49Z","cross_cats_sorted":[],"title_canon_sha256":"9f8afc9fb72c08ab8d95d1444cec348a56d9bee1a2af85a60e082ca3985e33c0","abstract_canon_sha256":"946ad5bc895d34e97fb7577d1d3c5b2cd9c2bef5ec8c395dd7dc613b15a74dda"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:03:32.756865Z","signature_b64":"iVrh7UVDNVQtLCTLziv6ySfShzLjx+LB5v7LIlmhBtXMh+xDLsKkQzxAGC7sToocKL8xkkJBSpTC3JfPsnZyBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e46aecda5235a2da3af4fe883b2aaf1e9e14235c44b99b203b04f342cb48cc4d","last_reissued_at":"2026-06-02T01:03:32.756271Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:03:32.756271Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DistFlow: A Fully Distributed RL Framework for Scalable and Efficient LLM Post-Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Dian Yang, Jiaming Xu, Jiarui Hu, Jinlong Hou, Liming Liu, Mingjun Zhang, Ping Zhang, Siyuan Feng, Tianyi Zhou, Tongyu Wang, Yuan Cheng, Yuan Qi, Zhixin Wang","submitted_at":"2025-07-18T11:41:49Z","abstract_excerpt":"Effectively scaling Reinforcement Learning (RL) is crucial for enhancing the reasoning and alignment of Large Language Models. The massive data and complex execution flows inherent in these tasks require a distributed architecture capable of efficient scaling. However, to simplify programming and dependency management, mainstream frameworks often rely on a centralized architecture where a single node dispatches both control and data. This inherent coupling creates significant communication bottlenecks, severely limiting system scalability and efficiency. We present DISTFLOW, a novel, fully dis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.13833","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2507.13833/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"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":"2507.13833","created_at":"2026-06-02T01:03:32.756349+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.13833v4","created_at":"2026-06-02T01:03:32.756349+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.13833","created_at":"2026-06-02T01:03:32.756349+00:00"},{"alias_kind":"pith_short_12","alias_value":"4RVOZWSSGWRN","created_at":"2026-06-02T01:03:32.756349+00:00"},{"alias_kind":"pith_short_16","alias_value":"4RVOZWSSGWRNUOXU","created_at":"2026-06-02T01:03:32.756349+00:00"},{"alias_kind":"pith_short_8","alias_value":"4RVOZWSS","created_at":"2026-06-02T01:03:32.756349+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4RVOZWSSGWRNUOXU72EDWKVPD2","json":"https://pith.science/pith/4RVOZWSSGWRNUOXU72EDWKVPD2.json","graph_json":"https://pith.science/api/pith-number/4RVOZWSSGWRNUOXU72EDWKVPD2/graph.json","events_json":"https://pith.science/api/pith-number/4RVOZWSSGWRNUOXU72EDWKVPD2/events.json","paper":"https://pith.science/paper/4RVOZWSS"},"agent_actions":{"view_html":"https://pith.science/pith/4RVOZWSSGWRNUOXU72EDWKVPD2","download_json":"https://pith.science/pith/4RVOZWSSGWRNUOXU72EDWKVPD2.json","view_paper":"https://pith.science/paper/4RVOZWSS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.13833&json=true","fetch_graph":"https://pith.science/api/pith-number/4RVOZWSSGWRNUOXU72EDWKVPD2/graph.json","fetch_events":"https://pith.science/api/pith-number/4RVOZWSSGWRNUOXU72EDWKVPD2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4RVOZWSSGWRNUOXU72EDWKVPD2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4RVOZWSSGWRNUOXU72EDWKVPD2/action/storage_attestation","attest_author":"https://pith.science/pith/4RVOZWSSGWRNUOXU72EDWKVPD2/action/author_attestation","sign_citation":"https://pith.science/pith/4RVOZWSSGWRNUOXU72EDWKVPD2/action/citation_signature","submit_replication":"https://pith.science/pith/4RVOZWSSGWRNUOXU72EDWKVPD2/action/replication_record"}},"created_at":"2026-06-02T01:03:32.756349+00:00","updated_at":"2026-06-02T01:03:32.756349+00:00"}