{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:AKQW2IBSZYK2D6ZFKR5ONXESHN","short_pith_number":"pith:AKQW2IBS","canonical_record":{"source":{"id":"2309.16039","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-27T21:41:49Z","cross_cats_sorted":[],"title_canon_sha256":"8eb7dc28f1d7f8c2ff7f6d475e8bb51ccfc3030a6d2ba0a3c9e4605f0d343f6f","abstract_canon_sha256":"7d41460099cf26210a5f486dd5c6ed5605d52f709dcf2720bccf46121f818862"},"schema_version":"1.0"},"canonical_sha256":"02a16d2032ce15a1fb25547ae6dc923b478ba0980eaa21ab4c6eb334d6913c0f","source":{"kind":"arxiv","id":"2309.16039","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.16039","created_at":"2026-07-05T07:12:18Z"},{"alias_kind":"arxiv_version","alias_value":"2309.16039v3","created_at":"2026-07-05T07:12:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.16039","created_at":"2026-07-05T07:12:18Z"},{"alias_kind":"pith_short_12","alias_value":"AKQW2IBSZYK2","created_at":"2026-07-05T07:12:18Z"},{"alias_kind":"pith_short_16","alias_value":"AKQW2IBSZYK2D6ZF","created_at":"2026-07-05T07:12:18Z"},{"alias_kind":"pith_short_8","alias_value":"AKQW2IBS","created_at":"2026-07-05T07:12:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:AKQW2IBSZYK2D6ZFKR5ONXESHN","target":"record","payload":{"canonical_record":{"source":{"id":"2309.16039","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-27T21:41:49Z","cross_cats_sorted":[],"title_canon_sha256":"8eb7dc28f1d7f8c2ff7f6d475e8bb51ccfc3030a6d2ba0a3c9e4605f0d343f6f","abstract_canon_sha256":"7d41460099cf26210a5f486dd5c6ed5605d52f709dcf2720bccf46121f818862"},"schema_version":"1.0"},"canonical_sha256":"02a16d2032ce15a1fb25547ae6dc923b478ba0980eaa21ab4c6eb334d6913c0f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:12:18.720714Z","signature_b64":"LudLmAolsEUtkLoA80F189Fs33ZymTxaiQGPMp5gP6Ypq3Xt5MNCsFeh7rFvwrT0gKEuMATLKnXTkBEfgrYdCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"02a16d2032ce15a1fb25547ae6dc923b478ba0980eaa21ab4c6eb334d6913c0f","last_reissued_at":"2026-07-05T07:12:18.719956Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:12:18.719956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.16039","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":"2026-07-05T07:12:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qIqs6rZkei3VtM4NB6wYXKmArN2Ni1VOuSBdR0zsOQ8cIsAzR2Ukof0uO21AKzWHTmt6jWLfGTCd//qoqPMKCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T18:08:54.476790Z"},"content_sha256":"37f29572b9c1d75336d84365e383965a15164033b8ab44cdcfbd7b57c8c8397c","schema_version":"1.0","event_id":"sha256:37f29572b9c1d75336d84365e383965a15164033b8ab44cdcfbd7b57c8c8397c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:AKQW2IBSZYK2D6ZFKR5ONXESHN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Effective Long-Context Scaling of Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Angela Fan, Barlas Oguz, Han Fang, Hao Ma, Hejia Zhang, Igor Molybog, Jingyu Liu, Karthik Abinav Sankararaman, Kshitiz Malik, Louis Martin, Madian Khabsa, Mike Lewis, Prajjwal Bhargava, Rashi Rungta, Rui Hou, Sergey Edunov, Sharan Narang, Shruti Bhosale, Sinong Wang, Wenhan Xiong, Yashar Mehdad","submitted_at":"2023-09-27T21:41:49Z","abstract_excerpt":"We present a series of long-context LLMs that support effective context windows of up to 32,768 tokens. Our model series are built through continual pretraining from Llama 2 with longer training sequences and on a dataset where long texts are upsampled. We perform extensive evaluation on language modeling, synthetic context probing tasks, and a wide range of research benchmarks. On research benchmarks, our models achieve consistent improvements on most regular tasks and significant improvements on long-context tasks over Llama 2. Notably, with a cost-effective instruction tuning procedure that"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.16039","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/2309.16039/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":"2026-07-05T07:12:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YbeNr7i9WKkcYmvh6lLJOro7hiBd7CegauMEykl7caoRu/OnDWf1yKX0HxSJdwAet9m1hQVZGD0U8+4EobSeAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T18:08:54.477388Z"},"content_sha256":"dc4667b9f60401e1032141b6e2c67031c39a303e8e29881a49ee763e711cd6e1","schema_version":"1.0","event_id":"sha256:dc4667b9f60401e1032141b6e2c67031c39a303e8e29881a49ee763e711cd6e1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AKQW2IBSZYK2D6ZFKR5ONXESHN/bundle.json","state_url":"https://pith.science/pith/AKQW2IBSZYK2D6ZFKR5ONXESHN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AKQW2IBSZYK2D6ZFKR5ONXESHN/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":"2026-08-14T18:08:54Z","links":{"resolver":"https://pith.science/pith/AKQW2IBSZYK2D6ZFKR5ONXESHN","bundle":"https://pith.science/pith/AKQW2IBSZYK2D6ZFKR5ONXESHN/bundle.json","state":"https://pith.science/pith/AKQW2IBSZYK2D6ZFKR5ONXESHN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AKQW2IBSZYK2D6ZFKR5ONXESHN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:AKQW2IBSZYK2D6ZFKR5ONXESHN","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":"7d41460099cf26210a5f486dd5c6ed5605d52f709dcf2720bccf46121f818862","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-27T21:41:49Z","title_canon_sha256":"8eb7dc28f1d7f8c2ff7f6d475e8bb51ccfc3030a6d2ba0a3c9e4605f0d343f6f"},"schema_version":"1.0","source":{"id":"2309.16039","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.16039","created_at":"2026-07-05T07:12:18Z"},{"alias_kind":"arxiv_version","alias_value":"2309.16039v3","created_at":"2026-07-05T07:12:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.16039","created_at":"2026-07-05T07:12:18Z"},{"alias_kind":"pith_short_12","alias_value":"AKQW2IBSZYK2","created_at":"2026-07-05T07:12:18Z"},{"alias_kind":"pith_short_16","alias_value":"AKQW2IBSZYK2D6ZF","created_at":"2026-07-05T07:12:18Z"},{"alias_kind":"pith_short_8","alias_value":"AKQW2IBS","created_at":"2026-07-05T07:12:18Z"}],"graph_snapshots":[{"event_id":"sha256:dc4667b9f60401e1032141b6e2c67031c39a303e8e29881a49ee763e711cd6e1","target":"graph","created_at":"2026-07-05T07:12:18Z","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/2309.16039/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a series of long-context LLMs that support effective context windows of up to 32,768 tokens. Our model series are built through continual pretraining from Llama 2 with longer training sequences and on a dataset where long texts are upsampled. We perform extensive evaluation on language modeling, synthetic context probing tasks, and a wide range of research benchmarks. On research benchmarks, our models achieve consistent improvements on most regular tasks and significant improvements on long-context tasks over Llama 2. Notably, with a cost-effective instruction tuning procedure that","authors_text":"Angela Fan, Barlas Oguz, Han Fang, Hao Ma, Hejia Zhang, Igor Molybog, Jingyu Liu, Karthik Abinav Sankararaman, Kshitiz Malik, Louis Martin, Madian Khabsa, Mike Lewis, Prajjwal Bhargava, Rashi Rungta, Rui Hou, Sergey Edunov, Sharan Narang, Shruti Bhosale, Sinong Wang, Wenhan Xiong, Yashar Mehdad","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-27T21:41:49Z","title":"Effective Long-Context Scaling of Foundation Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.16039","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":"sha256:37f29572b9c1d75336d84365e383965a15164033b8ab44cdcfbd7b57c8c8397c","target":"record","created_at":"2026-07-05T07:12:18Z","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":"7d41460099cf26210a5f486dd5c6ed5605d52f709dcf2720bccf46121f818862","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-27T21:41:49Z","title_canon_sha256":"8eb7dc28f1d7f8c2ff7f6d475e8bb51ccfc3030a6d2ba0a3c9e4605f0d343f6f"},"schema_version":"1.0","source":{"id":"2309.16039","kind":"arxiv","version":3}},"canonical_sha256":"02a16d2032ce15a1fb25547ae6dc923b478ba0980eaa21ab4c6eb334d6913c0f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"02a16d2032ce15a1fb25547ae6dc923b478ba0980eaa21ab4c6eb334d6913c0f","first_computed_at":"2026-07-05T07:12:18.719956Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:12:18.719956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LudLmAolsEUtkLoA80F189Fs33ZymTxaiQGPMp5gP6Ypq3Xt5MNCsFeh7rFvwrT0gKEuMATLKnXTkBEfgrYdCw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:12:18.720714Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.16039","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:37f29572b9c1d75336d84365e383965a15164033b8ab44cdcfbd7b57c8c8397c","sha256:dc4667b9f60401e1032141b6e2c67031c39a303e8e29881a49ee763e711cd6e1"],"state_sha256":"4a2afde301cf179a11a61419fc0bfdb1245f42fd0453d97fc40417c4034d14b1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z2bzSTYyf+oAX29r7oi3Z6iAw74SMJ1/c4iOMiUG8kcFYIAU1Kf9YqbRbEijcfCp6eU42561OnYbfmI4QR/SBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T18:08:54.491327Z","bundle_sha256":"0c3878c50edc0e8f1430182bb06749ea5e930924a488f44c9dcabe3e1e1b6e27"}}