{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:T653KA5JSXDPBLAGXZPI5NXOR4","short_pith_number":"pith:T653KA5J","schema_version":"1.0","canonical_sha256":"9fbbb503a995c6f0ac06be5e8eb6ee8f2f7f37d5418f0d587e24ee79070254db","source":{"kind":"arxiv","id":"2508.07970","version":3},"attestation_state":"computed","paper":{"title":"WeChat-YATT: A Scalable, Simple, Efficient, and Production Ready Training Library","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Boqi Chen, Feng Lin, Guanyou He, Haoqiang Hong, Hongtao Tian, Jiatao Xu, Junyu Wu, Tao Yang, Tingfeng Xian, Ting Yao, Weiming Chang, Xiaotao Liu, Yunsheng Shi","submitted_at":"2025-08-11T13:31:53Z","abstract_excerpt":"Reinforcement Learning from Human Feedback (RLHF) has emerged as a prominent paradigm for training large language models and multimodal systems. Despite the notable advances enabled by existing RLHF training frameworks, significant challenges remain to scale to complex multimodal workflows and adapt to dynamic workloads. In particular, current systems often encounter limitations related to controller scalability when managing large models, as well as inefficiencies in orchestrating intricate RLHF pipelines, especially in scenarios that require dynamic sampling and resource allocation. In this "},"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":"2508.07970","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-11T13:31:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c718d3cfbaef6eaee9e4065711815a2e34733b70f3d8e246c8d320aed3a3e9e4","abstract_canon_sha256":"952a9d9b5f785d09bc380c82a3370db1d6b620f7b942694ec15c89c46b9d27e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:55:21.372645Z","signature_b64":"nsqwB9oCAjF/Ff1m13fLVNmkPdcbkZv23bKPhUMxdPQHLEjUroyMF2gq0PyD2xna2yX37RAsyB7Wg3zheI6sCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9fbbb503a995c6f0ac06be5e8eb6ee8f2f7f37d5418f0d587e24ee79070254db","last_reissued_at":"2026-07-05T11:55:21.372162Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:55:21.372162Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WeChat-YATT: A Scalable, Simple, Efficient, and Production Ready Training Library","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Boqi Chen, Feng Lin, Guanyou He, Haoqiang Hong, Hongtao Tian, Jiatao Xu, Junyu Wu, Tao Yang, Tingfeng Xian, Ting Yao, Weiming Chang, Xiaotao Liu, Yunsheng Shi","submitted_at":"2025-08-11T13:31:53Z","abstract_excerpt":"Reinforcement Learning from Human Feedback (RLHF) has emerged as a prominent paradigm for training large language models and multimodal systems. Despite the notable advances enabled by existing RLHF training frameworks, significant challenges remain to scale to complex multimodal workflows and adapt to dynamic workloads. In particular, current systems often encounter limitations related to controller scalability when managing large models, as well as inefficiencies in orchestrating intricate RLHF pipelines, especially in scenarios that require dynamic sampling and resource allocation. In this "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.07970","kind":"arxiv","version":3},"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/2508.07970/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":"2508.07970","created_at":"2026-07-05T11:55:21.372220+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.07970v3","created_at":"2026-07-05T11:55:21.372220+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.07970","created_at":"2026-07-05T11:55:21.372220+00:00"},{"alias_kind":"pith_short_12","alias_value":"T653KA5JSXDP","created_at":"2026-07-05T11:55:21.372220+00:00"},{"alias_kind":"pith_short_16","alias_value":"T653KA5JSXDPBLAG","created_at":"2026-07-05T11:55:21.372220+00:00"},{"alias_kind":"pith_short_8","alias_value":"T653KA5J","created_at":"2026-07-05T11:55:21.372220+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/T653KA5JSXDPBLAGXZPI5NXOR4","json":"https://pith.science/pith/T653KA5JSXDPBLAGXZPI5NXOR4.json","graph_json":"https://pith.science/api/pith-number/T653KA5JSXDPBLAGXZPI5NXOR4/graph.json","events_json":"https://pith.science/api/pith-number/T653KA5JSXDPBLAGXZPI5NXOR4/events.json","paper":"https://pith.science/paper/T653KA5J"},"agent_actions":{"view_html":"https://pith.science/pith/T653KA5JSXDPBLAGXZPI5NXOR4","download_json":"https://pith.science/pith/T653KA5JSXDPBLAGXZPI5NXOR4.json","view_paper":"https://pith.science/paper/T653KA5J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.07970&json=true","fetch_graph":"https://pith.science/api/pith-number/T653KA5JSXDPBLAGXZPI5NXOR4/graph.json","fetch_events":"https://pith.science/api/pith-number/T653KA5JSXDPBLAGXZPI5NXOR4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T653KA5JSXDPBLAGXZPI5NXOR4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T653KA5JSXDPBLAGXZPI5NXOR4/action/storage_attestation","attest_author":"https://pith.science/pith/T653KA5JSXDPBLAGXZPI5NXOR4/action/author_attestation","sign_citation":"https://pith.science/pith/T653KA5JSXDPBLAGXZPI5NXOR4/action/citation_signature","submit_replication":"https://pith.science/pith/T653KA5JSXDPBLAGXZPI5NXOR4/action/replication_record"}},"created_at":"2026-07-05T11:55:21.372220+00:00","updated_at":"2026-07-05T11:55:21.372220+00:00"}