{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LBFNAMMSCDMSIDD5J6HB3OHT2K","short_pith_number":"pith:LBFNAMMS","schema_version":"1.0","canonical_sha256":"584ad0319210d9240c7d4f8e1db8f3d2a0b795c54e787109fd6a6f36c577f3fd","source":{"kind":"arxiv","id":"2409.00509","version":2},"attestation_state":"computed","paper":{"title":"LongRecipe: Recipe for Efficient Long Context Generalization in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anh Tuan Luu, Bryan Hooi, Jinman Zhao, Qing Gu, See-kiong Ng, Suyuchen Wang, Wei Shen, Yan Wang, Yuliang Liu, Zhiwei Jiang, Zhiyuan Hu","submitted_at":"2024-08-31T17:19:30Z","abstract_excerpt":"Large language models (LLMs) face significant challenges in handling long-context tasks because of their limited effective context window size during pretraining, which restricts their ability to generalize over extended sequences. Meanwhile, extending the context window in LLMs through post-pretraining is highly resource-intensive. To address this, we introduce LongRecipe, an efficient training strategy for extending the context window of LLMs, including impactful token analysis, position index transformation, and training optimization strategies. It simulates long-sequence inputs while maint"},"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":"2409.00509","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-31T17:19:30Z","cross_cats_sorted":[],"title_canon_sha256":"4970ce5bddd2e2750588c2d1798a13de1d63d2da609e84bb4ba0308f00325cf9","abstract_canon_sha256":"4fbb8d1e09543c99712ae30282d12666383c87796a1e6ea8655b11c9122e84d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:03:03.269379Z","signature_b64":"aYo8cBhMOgXJRmZgqRw1PQilg2FPNqG6D9YXFDvubNqpmXF7hnJbbUHE1Zu8KHHpQ7Gus6rcv64zeGCM8LWQDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"584ad0319210d9240c7d4f8e1db8f3d2a0b795c54e787109fd6a6f36c577f3fd","last_reissued_at":"2026-07-05T09:03:03.268883Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:03:03.268883Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LongRecipe: Recipe for Efficient Long Context Generalization in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anh Tuan Luu, Bryan Hooi, Jinman Zhao, Qing Gu, See-kiong Ng, Suyuchen Wang, Wei Shen, Yan Wang, Yuliang Liu, Zhiwei Jiang, Zhiyuan Hu","submitted_at":"2024-08-31T17:19:30Z","abstract_excerpt":"Large language models (LLMs) face significant challenges in handling long-context tasks because of their limited effective context window size during pretraining, which restricts their ability to generalize over extended sequences. Meanwhile, extending the context window in LLMs through post-pretraining is highly resource-intensive. To address this, we introduce LongRecipe, an efficient training strategy for extending the context window of LLMs, including impactful token analysis, position index transformation, and training optimization strategies. It simulates long-sequence inputs while maint"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.00509","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/2409.00509/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":"2409.00509","created_at":"2026-07-05T09:03:03.268949+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.00509v2","created_at":"2026-07-05T09:03:03.268949+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.00509","created_at":"2026-07-05T09:03:03.268949+00:00"},{"alias_kind":"pith_short_12","alias_value":"LBFNAMMSCDMS","created_at":"2026-07-05T09:03:03.268949+00:00"},{"alias_kind":"pith_short_16","alias_value":"LBFNAMMSCDMSIDD5","created_at":"2026-07-05T09:03:03.268949+00:00"},{"alias_kind":"pith_short_8","alias_value":"LBFNAMMS","created_at":"2026-07-05T09:03:03.268949+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/LBFNAMMSCDMSIDD5J6HB3OHT2K","json":"https://pith.science/pith/LBFNAMMSCDMSIDD5J6HB3OHT2K.json","graph_json":"https://pith.science/api/pith-number/LBFNAMMSCDMSIDD5J6HB3OHT2K/graph.json","events_json":"https://pith.science/api/pith-number/LBFNAMMSCDMSIDD5J6HB3OHT2K/events.json","paper":"https://pith.science/paper/LBFNAMMS"},"agent_actions":{"view_html":"https://pith.science/pith/LBFNAMMSCDMSIDD5J6HB3OHT2K","download_json":"https://pith.science/pith/LBFNAMMSCDMSIDD5J6HB3OHT2K.json","view_paper":"https://pith.science/paper/LBFNAMMS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.00509&json=true","fetch_graph":"https://pith.science/api/pith-number/LBFNAMMSCDMSIDD5J6HB3OHT2K/graph.json","fetch_events":"https://pith.science/api/pith-number/LBFNAMMSCDMSIDD5J6HB3OHT2K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LBFNAMMSCDMSIDD5J6HB3OHT2K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LBFNAMMSCDMSIDD5J6HB3OHT2K/action/storage_attestation","attest_author":"https://pith.science/pith/LBFNAMMSCDMSIDD5J6HB3OHT2K/action/author_attestation","sign_citation":"https://pith.science/pith/LBFNAMMSCDMSIDD5J6HB3OHT2K/action/citation_signature","submit_replication":"https://pith.science/pith/LBFNAMMSCDMSIDD5J6HB3OHT2K/action/replication_record"}},"created_at":"2026-07-05T09:03:03.268949+00:00","updated_at":"2026-07-05T09:03:03.268949+00:00"}