{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UEAXDXOCJAZACYPNZDD6XEPAXZ","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":"af53762249a6050e030e50b037ffab5f10250ffd8fa34f1f6699c10fc5365d81","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-31T18:29:39Z","title_canon_sha256":"5b8277ad8892b63026a65847f024a9c993f4d49e5e5f8aedc8797a873f1bbfa3"},"schema_version":"1.0","source":{"id":"2401.18058","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.18058","created_at":"2026-07-05T07:39:46Z"},{"alias_kind":"arxiv_version","alias_value":"2401.18058v1","created_at":"2026-07-05T07:39:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.18058","created_at":"2026-07-05T07:39:46Z"},{"alias_kind":"pith_short_12","alias_value":"UEAXDXOCJAZA","created_at":"2026-07-05T07:39:46Z"},{"alias_kind":"pith_short_16","alias_value":"UEAXDXOCJAZACYPN","created_at":"2026-07-05T07:39:46Z"},{"alias_kind":"pith_short_8","alias_value":"UEAXDXOC","created_at":"2026-07-05T07:39:46Z"}],"graph_snapshots":[{"event_id":"sha256:4f4d8a42872c4b7bd31c6038bc80e46ad59788634e542dbd973445e1e83507cd","target":"graph","created_at":"2026-07-05T07:39:46Z","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/2401.18058/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Extending large language models to effectively handle long contexts requires instruction fine-tuning on input sequences of similar length. To address this, we present LongAlign -- a recipe of the instruction data, training, and evaluation for long context alignment. First, we construct a long instruction-following dataset using Self-Instruct. To ensure the data diversity, it covers a broad range of tasks from various long context sources. Second, we adopt the packing and sorted batching strategies to speed up supervised fine-tuning on data with varied length distributions. Additionally, we dev","authors_text":"Jiajie Zhang, Jie Tang, Ji Qi, Juanzi Li, Lei Hou, Xin Lv, Yushi Bai, Yuxiao Dong, Yuze He","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-31T18:29:39Z","title":"LongAlign: A Recipe for Long Context Alignment of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.18058","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":"sha256:4fd583f10c516ca962766ecfedd4568a99417ca985722e63e4df7f23404baf5f","target":"record","created_at":"2026-07-05T07:39:46Z","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":"af53762249a6050e030e50b037ffab5f10250ffd8fa34f1f6699c10fc5365d81","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-31T18:29:39Z","title_canon_sha256":"5b8277ad8892b63026a65847f024a9c993f4d49e5e5f8aedc8797a873f1bbfa3"},"schema_version":"1.0","source":{"id":"2401.18058","kind":"arxiv","version":1}},"canonical_sha256":"a10171ddc248320161edc8c7eb91e0be541bb3c8d22057836b2d0ef32cdf480f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a10171ddc248320161edc8c7eb91e0be541bb3c8d22057836b2d0ef32cdf480f","first_computed_at":"2026-07-05T07:39:46.304933Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:39:46.304933Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5tgL/4dEcotjXY/qjCSFPV428EHHOcfdIoVp/eNTtRKfczxN5c+icaMIaQtBu0bXSu5UJVvgmFu2WcuAHaNJBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:39:46.305357Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.18058","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4fd583f10c516ca962766ecfedd4568a99417ca985722e63e4df7f23404baf5f","sha256:4f4d8a42872c4b7bd31c6038bc80e46ad59788634e542dbd973445e1e83507cd"],"state_sha256":"137645c325138fa6cbebb6f8c1cb9244bbbb8a9e6454c785fac3339b3ed9bdd6"}