{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:JU63OZBXWSEDUQ2JADGJKVQBWK","short_pith_number":"pith:JU63OZBX","canonical_record":{"source":{"id":"2312.11819","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-19T03:24:55Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"7e9f34dcba670b33e3020ec593561fbf7feb903972b36dea6ef74d6363796130","abstract_canon_sha256":"9ce7102ca5decfd9d0edaa69284330701db3170a7507a0ce4a05edcdc7eac9fb"},"schema_version":"1.0"},"canonical_sha256":"4d3db76437b4883a434900cc955601b29c1ffc665f94b817e184af7c4902b2a5","source":{"kind":"arxiv","id":"2312.11819","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.11819","created_at":"2026-07-05T09:19:53Z"},{"alias_kind":"arxiv_version","alias_value":"2312.11819v3","created_at":"2026-07-05T09:19:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.11819","created_at":"2026-07-05T09:19:53Z"},{"alias_kind":"pith_short_12","alias_value":"JU63OZBXWSED","created_at":"2026-07-05T09:19:53Z"},{"alias_kind":"pith_short_16","alias_value":"JU63OZBXWSEDUQ2J","created_at":"2026-07-05T09:19:53Z"},{"alias_kind":"pith_short_8","alias_value":"JU63OZBX","created_at":"2026-07-05T09:19:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:JU63OZBXWSEDUQ2JADGJKVQBWK","target":"record","payload":{"canonical_record":{"source":{"id":"2312.11819","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-19T03:24:55Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"7e9f34dcba670b33e3020ec593561fbf7feb903972b36dea6ef74d6363796130","abstract_canon_sha256":"9ce7102ca5decfd9d0edaa69284330701db3170a7507a0ce4a05edcdc7eac9fb"},"schema_version":"1.0"},"canonical_sha256":"4d3db76437b4883a434900cc955601b29c1ffc665f94b817e184af7c4902b2a5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:53.371717Z","signature_b64":"/YBXFfDX7sdjlkJiLe3mwt6IJVVHTjvS6ZaSrq7oF2bwwJ4IxGNHA8zvC5z2dHb/sYlma5JXXo+HMDIDBYA4Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d3db76437b4883a434900cc955601b29c1ffc665f94b817e184af7c4902b2a5","last_reissued_at":"2026-07-05T09:19:53.371302Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:53.371302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.11819","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:19:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DEOl7aktm4WTAHGGekdu8BVcG/YmMoZndnBpDQ69F++9fM3b3TP1t0CaNb1WFvE67KHeGfZahjjKvn839xWaAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T18:36:39.647589Z"},"content_sha256":"333824ca538c4d6e1409be89455863ce198ea826508dd448ad636f5b505db63b","schema_version":"1.0","event_id":"sha256:333824ca538c4d6e1409be89455863ce198ea826508dd448ad636f5b505db63b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:JU63OZBXWSEDUQ2JADGJKVQBWK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Adaptive Placement and Parallelism Framework for Accelerating RLHF Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Fagui Mao, Jun Zhou, Lei Liang, Lin Ju, Shangchun Zhao, Weichang Wu, Xiaolu Zhang, Youshao Xiao, Zhenglei Zhou","submitted_at":"2023-12-19T03:24:55Z","abstract_excerpt":"Recently, ChatGPT or InstructGPT like large language models (LLM) has made a significant impact in the AI world. Many works have attempted to reproduce the complex InstructGPT's training pipeline, namely Reinforcement Learning with Human Feedback (RLHF). However, the mainstream distributed RLHF training methods typically adopt a fixed model placement strategy, referred to as the Co-located strategy. This strategy treats all four interdependent models involved in RLHF as a single entity, distributing them across all devices and applying parallelism techniques designed for a single model, regard"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.11819","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/2312.11819/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":"2026-07-05T09:19:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7CVtojHeMHenRNWCNx4u53dogLiMHr6AvDmV9m77dQPeuqjERi0dZ2uXmRyFkDAjCZEc/7wFxU07499SGQdJCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T18:36:39.648104Z"},"content_sha256":"1fff575134324f3408bb384c68cb73f232642baca2b203a6af69f486247812af","schema_version":"1.0","event_id":"sha256:1fff575134324f3408bb384c68cb73f232642baca2b203a6af69f486247812af"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JU63OZBXWSEDUQ2JADGJKVQBWK/bundle.json","state_url":"https://pith.science/pith/JU63OZBXWSEDUQ2JADGJKVQBWK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JU63OZBXWSEDUQ2JADGJKVQBWK/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":"2026-08-06T18:36:39Z","links":{"resolver":"https://pith.science/pith/JU63OZBXWSEDUQ2JADGJKVQBWK","bundle":"https://pith.science/pith/JU63OZBXWSEDUQ2JADGJKVQBWK/bundle.json","state":"https://pith.science/pith/JU63OZBXWSEDUQ2JADGJKVQBWK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JU63OZBXWSEDUQ2JADGJKVQBWK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:JU63OZBXWSEDUQ2JADGJKVQBWK","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":"9ce7102ca5decfd9d0edaa69284330701db3170a7507a0ce4a05edcdc7eac9fb","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-19T03:24:55Z","title_canon_sha256":"7e9f34dcba670b33e3020ec593561fbf7feb903972b36dea6ef74d6363796130"},"schema_version":"1.0","source":{"id":"2312.11819","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.11819","created_at":"2026-07-05T09:19:53Z"},{"alias_kind":"arxiv_version","alias_value":"2312.11819v3","created_at":"2026-07-05T09:19:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.11819","created_at":"2026-07-05T09:19:53Z"},{"alias_kind":"pith_short_12","alias_value":"JU63OZBXWSED","created_at":"2026-07-05T09:19:53Z"},{"alias_kind":"pith_short_16","alias_value":"JU63OZBXWSEDUQ2J","created_at":"2026-07-05T09:19:53Z"},{"alias_kind":"pith_short_8","alias_value":"JU63OZBX","created_at":"2026-07-05T09:19:53Z"}],"graph_snapshots":[{"event_id":"sha256:1fff575134324f3408bb384c68cb73f232642baca2b203a6af69f486247812af","target":"graph","created_at":"2026-07-05T09:19:53Z","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/2312.11819/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, ChatGPT or InstructGPT like large language models (LLM) has made a significant impact in the AI world. Many works have attempted to reproduce the complex InstructGPT's training pipeline, namely Reinforcement Learning with Human Feedback (RLHF). However, the mainstream distributed RLHF training methods typically adopt a fixed model placement strategy, referred to as the Co-located strategy. This strategy treats all four interdependent models involved in RLHF as a single entity, distributing them across all devices and applying parallelism techniques designed for a single model, regard","authors_text":"Fagui Mao, Jun Zhou, Lei Liang, Lin Ju, Shangchun Zhao, Weichang Wu, Xiaolu Zhang, Youshao Xiao, Zhenglei Zhou","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-19T03:24:55Z","title":"An Adaptive Placement and Parallelism Framework for Accelerating RLHF Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.11819","kind":"arxiv","version":3},"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":"sha256:333824ca538c4d6e1409be89455863ce198ea826508dd448ad636f5b505db63b","target":"record","created_at":"2026-07-05T09:19:53Z","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":"9ce7102ca5decfd9d0edaa69284330701db3170a7507a0ce4a05edcdc7eac9fb","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-19T03:24:55Z","title_canon_sha256":"7e9f34dcba670b33e3020ec593561fbf7feb903972b36dea6ef74d6363796130"},"schema_version":"1.0","source":{"id":"2312.11819","kind":"arxiv","version":3}},"canonical_sha256":"4d3db76437b4883a434900cc955601b29c1ffc665f94b817e184af7c4902b2a5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4d3db76437b4883a434900cc955601b29c1ffc665f94b817e184af7c4902b2a5","first_computed_at":"2026-07-05T09:19:53.371302Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:19:53.371302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/YBXFfDX7sdjlkJiLe3mwt6IJVVHTjvS6ZaSrq7oF2bwwJ4IxGNHA8zvC5z2dHb/sYlma5JXXo+HMDIDBYA4Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:19:53.371717Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.11819","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:333824ca538c4d6e1409be89455863ce198ea826508dd448ad636f5b505db63b","sha256:1fff575134324f3408bb384c68cb73f232642baca2b203a6af69f486247812af"],"state_sha256":"8f5ef1fe7e9b713fb83022a5031f6bec6b06369c27b6d303d5adcae818018300"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h112pPqWlo47sIA/Bc31oCMalQ0QCCRD+G5x2VcIdN3BUK8qv0mkVSctVs0Fv+LrYkKUh4rk7QgqOo6vQAh8CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T18:36:39.652565Z","bundle_sha256":"1ddda9ae817e4b0a05e3642d6fbf0caef60af213806ffb8ef946b8c4e71fe8cb"}}