{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:AU6H4OFLJPWUY2Y7HGVFZHHYF4","short_pith_number":"pith:AU6H4OFL","canonical_record":{"source":{"id":"2507.22789","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-30T15:55:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f23b8ce98b537c0be9c91b8009f640ecb83c31490b2f810a5b46943100a9ff9e","abstract_canon_sha256":"e43f956be3da2960f2b9905428faf8cb31b47d6c9be4e1ed2289093c61e7325b"},"schema_version":"1.0"},"canonical_sha256":"053c7e38ab4bed4c6b1f39aa5c9cf82f0d0bdc268068d629660c747e956ac7ac","source":{"kind":"arxiv","id":"2507.22789","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.22789","created_at":"2026-07-05T11:46:00Z"},{"alias_kind":"arxiv_version","alias_value":"2507.22789v2","created_at":"2026-07-05T11:46:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.22789","created_at":"2026-07-05T11:46:00Z"},{"alias_kind":"pith_short_12","alias_value":"AU6H4OFLJPWU","created_at":"2026-07-05T11:46:00Z"},{"alias_kind":"pith_short_16","alias_value":"AU6H4OFLJPWUY2Y7","created_at":"2026-07-05T11:46:00Z"},{"alias_kind":"pith_short_8","alias_value":"AU6H4OFL","created_at":"2026-07-05T11:46:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:AU6H4OFLJPWUY2Y7HGVFZHHYF4","target":"record","payload":{"canonical_record":{"source":{"id":"2507.22789","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-30T15:55:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f23b8ce98b537c0be9c91b8009f640ecb83c31490b2f810a5b46943100a9ff9e","abstract_canon_sha256":"e43f956be3da2960f2b9905428faf8cb31b47d6c9be4e1ed2289093c61e7325b"},"schema_version":"1.0"},"canonical_sha256":"053c7e38ab4bed4c6b1f39aa5c9cf82f0d0bdc268068d629660c747e956ac7ac","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:46:00.740624Z","signature_b64":"2SWK5HuXtZYRHq973eGhZVURwNFzpYfVypekrLz+wmRx38Fz+zb/fGWTrzBuI9t5UllEDGkK1Tvi5r7vpbM9Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"053c7e38ab4bed4c6b1f39aa5c9cf82f0d0bdc268068d629660c747e956ac7ac","last_reissued_at":"2026-07-05T11:46:00.740068Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:46:00.740068Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.22789","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:46:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DZR3hJVBhcpblA3odGxRWRgwLxfvH37SiNKaabFpqX5+0gzksf9EoTw/DoVIKSs1n33Iynkg+5nxTQsQBaciBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T14:35:50.433276Z"},"content_sha256":"c786a4d0cd39bcc49e4cd5c5186ff805b14ec642473d0fc03dd09e7e7ee6510f","schema_version":"1.0","event_id":"sha256:c786a4d0cd39bcc49e4cd5c5186ff805b14ec642473d0fc03dd09e7e7ee6510f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:AU6H4OFLJPWUY2Y7HGVFZHHYF4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"G-Core: A Simple, Scalable and Balanced RLHF Trainer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Boqi Liu, Feng Lin, Guanyou He, Haoqiang Hong, Hongtao Tian, Junyu Wu, Tao Yang, Ting Yao, Weiming Chang, Xiaotao Liu, Yunsheng Shi","submitted_at":"2025-07-30T15:55:08Z","abstract_excerpt":"Reinforcement Learning from Human Feedback (RLHF) has become an increasingly popular paradigm for training large language models (LLMs) and diffusion models. While existing RLHF training systems have enabled significant progress, they often face challenges in scaling to multi-modal and diffusion workflows and adapting to dynamic workloads. In particular, current approaches may encounter limitations in controller scalability, flexible resource placement, and efficient orchestration when handling complex RLHF pipelines, especially in scenarios involving dynamic sampling or generative reward mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.22789","kind":"arxiv","version":2},"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/2507.22789/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:46:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bGbpI3/6RVdCPwPmZQolQfg7h0xFmDJeTYfubimYW5BIBC5Ee4ur5QRKhs4HMxtMDPpgcc7CYRJDHHMQrqEvDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T14:35:50.433660Z"},"content_sha256":"0e6f22462af2ccaa6a4a02a52d199a5547d3fecb7ee62c76928f1e7c11a10306","schema_version":"1.0","event_id":"sha256:0e6f22462af2ccaa6a4a02a52d199a5547d3fecb7ee62c76928f1e7c11a10306"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AU6H4OFLJPWUY2Y7HGVFZHHYF4/bundle.json","state_url":"https://pith.science/pith/AU6H4OFLJPWUY2Y7HGVFZHHYF4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AU6H4OFLJPWUY2Y7HGVFZHHYF4/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-22T14:35:50Z","links":{"resolver":"https://pith.science/pith/AU6H4OFLJPWUY2Y7HGVFZHHYF4","bundle":"https://pith.science/pith/AU6H4OFLJPWUY2Y7HGVFZHHYF4/bundle.json","state":"https://pith.science/pith/AU6H4OFLJPWUY2Y7HGVFZHHYF4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AU6H4OFLJPWUY2Y7HGVFZHHYF4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AU6H4OFLJPWUY2Y7HGVFZHHYF4","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e43f956be3da2960f2b9905428faf8cb31b47d6c9be4e1ed2289093c61e7325b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-30T15:55:08Z","title_canon_sha256":"f23b8ce98b537c0be9c91b8009f640ecb83c31490b2f810a5b46943100a9ff9e"},"schema_version":"1.0","source":{"id":"2507.22789","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.22789","created_at":"2026-07-05T11:46:00Z"},{"alias_kind":"arxiv_version","alias_value":"2507.22789v2","created_at":"2026-07-05T11:46:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.22789","created_at":"2026-07-05T11:46:00Z"},{"alias_kind":"pith_short_12","alias_value":"AU6H4OFLJPWU","created_at":"2026-07-05T11:46:00Z"},{"alias_kind":"pith_short_16","alias_value":"AU6H4OFLJPWUY2Y7","created_at":"2026-07-05T11:46:00Z"},{"alias_kind":"pith_short_8","alias_value":"AU6H4OFL","created_at":"2026-07-05T11:46:00Z"}],"graph_snapshots":[{"event_id":"sha256:0e6f22462af2ccaa6a4a02a52d199a5547d3fecb7ee62c76928f1e7c11a10306","target":"graph","created_at":"2026-07-05T11:46:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2507.22789/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning from Human Feedback (RLHF) has become an increasingly popular paradigm for training large language models (LLMs) and diffusion models. While existing RLHF training systems have enabled significant progress, they often face challenges in scaling to multi-modal and diffusion workflows and adapting to dynamic workloads. In particular, current approaches may encounter limitations in controller scalability, flexible resource placement, and efficient orchestration when handling complex RLHF pipelines, especially in scenarios involving dynamic sampling or generative reward mode","authors_text":"Boqi Liu, Feng Lin, Guanyou He, Haoqiang Hong, Hongtao Tian, Junyu Wu, Tao Yang, Ting Yao, Weiming Chang, Xiaotao Liu, Yunsheng Shi","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-30T15:55:08Z","title":"G-Core: A Simple, Scalable and Balanced RLHF Trainer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.22789","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c786a4d0cd39bcc49e4cd5c5186ff805b14ec642473d0fc03dd09e7e7ee6510f","target":"record","created_at":"2026-07-05T11:46:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e43f956be3da2960f2b9905428faf8cb31b47d6c9be4e1ed2289093c61e7325b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-30T15:55:08Z","title_canon_sha256":"f23b8ce98b537c0be9c91b8009f640ecb83c31490b2f810a5b46943100a9ff9e"},"schema_version":"1.0","source":{"id":"2507.22789","kind":"arxiv","version":2}},"canonical_sha256":"053c7e38ab4bed4c6b1f39aa5c9cf82f0d0bdc268068d629660c747e956ac7ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"053c7e38ab4bed4c6b1f39aa5c9cf82f0d0bdc268068d629660c747e956ac7ac","first_computed_at":"2026-07-05T11:46:00.740068Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:46:00.740068Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2SWK5HuXtZYRHq973eGhZVURwNFzpYfVypekrLz+wmRx38Fz+zb/fGWTrzBuI9t5UllEDGkK1Tvi5r7vpbM9Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:46:00.740624Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.22789","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c786a4d0cd39bcc49e4cd5c5186ff805b14ec642473d0fc03dd09e7e7ee6510f","sha256:0e6f22462af2ccaa6a4a02a52d199a5547d3fecb7ee62c76928f1e7c11a10306"],"state_sha256":"cd855ada75b8cb1ccf3b202c447a6e3bc0219b15744791a26a344e0c3400ab7f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aVosSei6cmRMFdKPBgFRWizIYSkxXYGqq5zqwPUhivl3zabN19Sl6DXK8A99VwfapYRoqLWIlTn/76RWcvocDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T14:35:50.436207Z","bundle_sha256":"905b8795cf8a83cc7c96d84608a2ff9f2ab77d03e1c06359e84ed612bfb2c8cb"}}