{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:FHIBFT2FCAH6TNYKWKJEBOYM4L","short_pith_number":"pith:FHIBFT2F","canonical_record":{"source":{"id":"2502.21231","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-02-28T17:01:03Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"2e6a45ba58ae11bf412d31c8074d2163d792aa1908613db288ddd2b69bf975c7","abstract_canon_sha256":"f3dc7f4a96c544f4991bcbb28fd7751712d541c30c7db47dc874fb443251a96e"},"schema_version":"1.0"},"canonical_sha256":"29d012cf45100fe9b70ab29240bb0ce2faaef089f12e26f51d99bb3f725d3bbb","source":{"kind":"arxiv","id":"2502.21231","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.21231","created_at":"2026-07-05T12:01:21Z"},{"alias_kind":"arxiv_version","alias_value":"2502.21231v1","created_at":"2026-07-05T12:01:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.21231","created_at":"2026-07-05T12:01:21Z"},{"alias_kind":"pith_short_12","alias_value":"FHIBFT2FCAH6","created_at":"2026-07-05T12:01:21Z"},{"alias_kind":"pith_short_16","alias_value":"FHIBFT2FCAH6TNYK","created_at":"2026-07-05T12:01:21Z"},{"alias_kind":"pith_short_8","alias_value":"FHIBFT2F","created_at":"2026-07-05T12:01:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:FHIBFT2FCAH6TNYKWKJEBOYM4L","target":"record","payload":{"canonical_record":{"source":{"id":"2502.21231","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-02-28T17:01:03Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"2e6a45ba58ae11bf412d31c8074d2163d792aa1908613db288ddd2b69bf975c7","abstract_canon_sha256":"f3dc7f4a96c544f4991bcbb28fd7751712d541c30c7db47dc874fb443251a96e"},"schema_version":"1.0"},"canonical_sha256":"29d012cf45100fe9b70ab29240bb0ce2faaef089f12e26f51d99bb3f725d3bbb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:01:21.108283Z","signature_b64":"6P5+kD62as8iHIoO6G0cpo6KAtxsXu6zvLI0FRZNR3pY7PweHvEZV/rwEbqDFHjFCNqAgIiIGjFRNJQDmM1xAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29d012cf45100fe9b70ab29240bb0ce2faaef089f12e26f51d99bb3f725d3bbb","last_reissued_at":"2026-07-05T12:01:21.107866Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:01:21.107866Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.21231","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:01:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sg2wvpi3HflAMMC4bl8L68dP1R59ZSK/LytlF+ZGNWd/TkEisXoOW776PsH4dyYKwepH7NzkztBy+AKNGgxUAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T13:01:42.915557Z"},"content_sha256":"3bae44c757deb7bf4d9bf821bf9028eee679104826f93005463d04736ec63004","schema_version":"1.0","event_id":"sha256:3bae44c757deb7bf4d9bf821bf9028eee679104826f93005463d04736ec63004"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:FHIBFT2FCAH6TNYKWKJEBOYM4L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ByteScale: Efficient Scaling of LLM Training with a 2048K Context Length on More Than 12,000 GPUs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.DC","authors_text":"Bin Cui, Fangcheng Fu, Haibin Lin, Hao Ge, Junda Feng, Lei Zuo, Qi Huang, Xiaonan Nie, Xin Liu","submitted_at":"2025-02-28T17:01:03Z","abstract_excerpt":"Scaling long-context ability is essential for Large Language Models (LLMs). To amortize the memory consumption across multiple devices in long-context training, inter-data partitioning (a.k.a. Data Parallelism) and intra-data partitioning (a.k.a. Context Parallelism) are commonly used. Current training frameworks predominantly treat the two techniques as orthogonal, and establish static communication groups to organize the devices as a static mesh (e.g., a 2D mesh). However, the sequences for LLM training typically vary in lengths, no matter for texts, multi-modalities or reinforcement learnin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.21231","kind":"arxiv","version":1},"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/2502.21231/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":"2026-07-05T12:01:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a0R4tZEATADD55UrpqGQH+4O9yzb/WAm05nCr/hOo/l9rs3ADbksgbbM2PuyNuWli851V2PnkMe/35tI39xLDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T13:01:42.916172Z"},"content_sha256":"1af7c38be7c8f78ca2836300f198718d0aca5b3303409a512b6a51a4b6398862","schema_version":"1.0","event_id":"sha256:1af7c38be7c8f78ca2836300f198718d0aca5b3303409a512b6a51a4b6398862"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FHIBFT2FCAH6TNYKWKJEBOYM4L/bundle.json","state_url":"https://pith.science/pith/FHIBFT2FCAH6TNYKWKJEBOYM4L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FHIBFT2FCAH6TNYKWKJEBOYM4L/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":"2026-08-06T13:01:42Z","links":{"resolver":"https://pith.science/pith/FHIBFT2FCAH6TNYKWKJEBOYM4L","bundle":"https://pith.science/pith/FHIBFT2FCAH6TNYKWKJEBOYM4L/bundle.json","state":"https://pith.science/pith/FHIBFT2FCAH6TNYKWKJEBOYM4L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FHIBFT2FCAH6TNYKWKJEBOYM4L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FHIBFT2FCAH6TNYKWKJEBOYM4L","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":"f3dc7f4a96c544f4991bcbb28fd7751712d541c30c7db47dc874fb443251a96e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-02-28T17:01:03Z","title_canon_sha256":"2e6a45ba58ae11bf412d31c8074d2163d792aa1908613db288ddd2b69bf975c7"},"schema_version":"1.0","source":{"id":"2502.21231","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.21231","created_at":"2026-07-05T12:01:21Z"},{"alias_kind":"arxiv_version","alias_value":"2502.21231v1","created_at":"2026-07-05T12:01:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.21231","created_at":"2026-07-05T12:01:21Z"},{"alias_kind":"pith_short_12","alias_value":"FHIBFT2FCAH6","created_at":"2026-07-05T12:01:21Z"},{"alias_kind":"pith_short_16","alias_value":"FHIBFT2FCAH6TNYK","created_at":"2026-07-05T12:01:21Z"},{"alias_kind":"pith_short_8","alias_value":"FHIBFT2F","created_at":"2026-07-05T12:01:21Z"}],"graph_snapshots":[{"event_id":"sha256:1af7c38be7c8f78ca2836300f198718d0aca5b3303409a512b6a51a4b6398862","target":"graph","created_at":"2026-07-05T12:01:21Z","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/2502.21231/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Scaling long-context ability is essential for Large Language Models (LLMs). To amortize the memory consumption across multiple devices in long-context training, inter-data partitioning (a.k.a. Data Parallelism) and intra-data partitioning (a.k.a. Context Parallelism) are commonly used. Current training frameworks predominantly treat the two techniques as orthogonal, and establish static communication groups to organize the devices as a static mesh (e.g., a 2D mesh). However, the sequences for LLM training typically vary in lengths, no matter for texts, multi-modalities or reinforcement learnin","authors_text":"Bin Cui, Fangcheng Fu, Haibin Lin, Hao Ge, Junda Feng, Lei Zuo, Qi Huang, Xiaonan Nie, Xin Liu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-02-28T17:01:03Z","title":"ByteScale: Efficient Scaling of LLM Training with a 2048K Context Length on More Than 12,000 GPUs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.21231","kind":"arxiv","version":1},"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":"sha256:3bae44c757deb7bf4d9bf821bf9028eee679104826f93005463d04736ec63004","target":"record","created_at":"2026-07-05T12:01:21Z","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":"f3dc7f4a96c544f4991bcbb28fd7751712d541c30c7db47dc874fb443251a96e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-02-28T17:01:03Z","title_canon_sha256":"2e6a45ba58ae11bf412d31c8074d2163d792aa1908613db288ddd2b69bf975c7"},"schema_version":"1.0","source":{"id":"2502.21231","kind":"arxiv","version":1}},"canonical_sha256":"29d012cf45100fe9b70ab29240bb0ce2faaef089f12e26f51d99bb3f725d3bbb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"29d012cf45100fe9b70ab29240bb0ce2faaef089f12e26f51d99bb3f725d3bbb","first_computed_at":"2026-07-05T12:01:21.107866Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:01:21.107866Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6P5+kD62as8iHIoO6G0cpo6KAtxsXu6zvLI0FRZNR3pY7PweHvEZV/rwEbqDFHjFCNqAgIiIGjFRNJQDmM1xAA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:01:21.108283Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.21231","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3bae44c757deb7bf4d9bf821bf9028eee679104826f93005463d04736ec63004","sha256:1af7c38be7c8f78ca2836300f198718d0aca5b3303409a512b6a51a4b6398862"],"state_sha256":"df428d630e6cc8b22486faf447c7d2882bd63e9df0d6676e05803441f151a5c1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q4hXGth1dlK4hIXhhg9YVKND60/rGy48ZmHG0yn5+hWr/p137zlp4tLtQohkwwPWv4xtDls6Zgi6hrt4iAfHAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T13:01:42.923013Z","bundle_sha256":"f8abca59dd45d11d5013d79d255f2a7618eeb5bbe359375e43b48472aac2918b"}}