{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:5R3MAAJGRQLA4A3HZG36AB2ACV","short_pith_number":"pith:5R3MAAJG","canonical_record":{"source":{"id":"2402.10171","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-15T18:19:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"97f206c93851126b95c769100447045af28605db2dbc7faa3df5cf52cf13c6dd","abstract_canon_sha256":"a8916aa01eb192359a7a40c367e1f07ac0a6d9549829bc917ef744d4940d68b0"},"schema_version":"1.0"},"canonical_sha256":"ec76c001268c160e0367c9b7e00740154e0db77ff4cd3702e2d4cf0186c8bdb8","source":{"kind":"arxiv","id":"2402.10171","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.10171","created_at":"2026-07-05T07:45:42Z"},{"alias_kind":"arxiv_version","alias_value":"2402.10171v1","created_at":"2026-07-05T07:45:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.10171","created_at":"2026-07-05T07:45:42Z"},{"alias_kind":"pith_short_12","alias_value":"5R3MAAJGRQLA","created_at":"2026-07-05T07:45:42Z"},{"alias_kind":"pith_short_16","alias_value":"5R3MAAJGRQLA4A3H","created_at":"2026-07-05T07:45:42Z"},{"alias_kind":"pith_short_8","alias_value":"5R3MAAJG","created_at":"2026-07-05T07:45:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:5R3MAAJGRQLA4A3HZG36AB2ACV","target":"record","payload":{"canonical_record":{"source":{"id":"2402.10171","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-15T18:19:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"97f206c93851126b95c769100447045af28605db2dbc7faa3df5cf52cf13c6dd","abstract_canon_sha256":"a8916aa01eb192359a7a40c367e1f07ac0a6d9549829bc917ef744d4940d68b0"},"schema_version":"1.0"},"canonical_sha256":"ec76c001268c160e0367c9b7e00740154e0db77ff4cd3702e2d4cf0186c8bdb8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:45:42.322149Z","signature_b64":"bZabs9qqG2aeuor6WwzUdPIjcRQKuP6cUnd+b4YtLXFsmwQbHywj5AcKsG3YiPExhUdpB9oLGgip94O1rxA/BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec76c001268c160e0367c9b7e00740154e0db77ff4cd3702e2d4cf0186c8bdb8","last_reissued_at":"2026-07-05T07:45:42.321603Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:45:42.321603Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.10171","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":"2026-07-05T07:45:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G03SK7wbNu5ksZSwMe7N8AY8OzhS2j7jax0mLAk1IdaE9XrcSz1N9e19/0goiuZIdtlkBFzgepSrzw9C00lnDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-25T06:35:35.032049Z"},"content_sha256":"2242e439b7f30fe8798e46be63a8a995c8dbbed146bb4aa4cb4742b3be87873e","schema_version":"1.0","event_id":"sha256:2242e439b7f30fe8798e46be63a8a995c8dbbed146bb4aa4cb4742b3be87873e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:5R3MAAJGRQLA4A3HZG36AB2ACV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data Engineering for Scaling Language Models to 128K Context","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hannaneh Hajishirzi, Hao Peng, Rameswar Panda, Xiang Yue, Xinyao Niu, Yao Fu, Yoon Kim","submitted_at":"2024-02-15T18:19:16Z","abstract_excerpt":"We study the continual pretraining recipe for scaling language models' context lengths to 128K, with a focus on data engineering. We hypothesize that long context modeling, in particular \\textit{the ability to utilize information at arbitrary input locations}, is a capability that is mostly already acquired through large-scale pretraining, and that this capability can be readily extended to contexts substantially longer than seen during training~(e.g., 4K to 128K) through lightweight continual pretraining on appropriate data mixture. We investigate the \\textit{quantity} and \\textit{quality} of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.10171","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/2402.10171/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":"2026-07-05T07:45:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZIsjk5TAzAlnG3FaagvkpmRL0DD8ydD1+tVdomhQithHajg9d9v2Ih3sUheHZc+NRGrKE/sZSI24oz58R1MRCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-25T06:35:35.032454Z"},"content_sha256":"722557831cac931be124e2d628874de0803cf05a03223d270a8654764e79003a","schema_version":"1.0","event_id":"sha256:722557831cac931be124e2d628874de0803cf05a03223d270a8654764e79003a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5R3MAAJGRQLA4A3HZG36AB2ACV/bundle.json","state_url":"https://pith.science/pith/5R3MAAJGRQLA4A3HZG36AB2ACV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5R3MAAJGRQLA4A3HZG36AB2ACV/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":"2026-07-25T06:35:35Z","links":{"resolver":"https://pith.science/pith/5R3MAAJGRQLA4A3HZG36AB2ACV","bundle":"https://pith.science/pith/5R3MAAJGRQLA4A3HZG36AB2ACV/bundle.json","state":"https://pith.science/pith/5R3MAAJGRQLA4A3HZG36AB2ACV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5R3MAAJGRQLA4A3HZG36AB2ACV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5R3MAAJGRQLA4A3HZG36AB2ACV","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":"a8916aa01eb192359a7a40c367e1f07ac0a6d9549829bc917ef744d4940d68b0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-15T18:19:16Z","title_canon_sha256":"97f206c93851126b95c769100447045af28605db2dbc7faa3df5cf52cf13c6dd"},"schema_version":"1.0","source":{"id":"2402.10171","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.10171","created_at":"2026-07-05T07:45:42Z"},{"alias_kind":"arxiv_version","alias_value":"2402.10171v1","created_at":"2026-07-05T07:45:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.10171","created_at":"2026-07-05T07:45:42Z"},{"alias_kind":"pith_short_12","alias_value":"5R3MAAJGRQLA","created_at":"2026-07-05T07:45:42Z"},{"alias_kind":"pith_short_16","alias_value":"5R3MAAJGRQLA4A3H","created_at":"2026-07-05T07:45:42Z"},{"alias_kind":"pith_short_8","alias_value":"5R3MAAJG","created_at":"2026-07-05T07:45:42Z"}],"graph_snapshots":[{"event_id":"sha256:722557831cac931be124e2d628874de0803cf05a03223d270a8654764e79003a","target":"graph","created_at":"2026-07-05T07:45:42Z","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/2402.10171/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the continual pretraining recipe for scaling language models' context lengths to 128K, with a focus on data engineering. We hypothesize that long context modeling, in particular \\textit{the ability to utilize information at arbitrary input locations}, is a capability that is mostly already acquired through large-scale pretraining, and that this capability can be readily extended to contexts substantially longer than seen during training~(e.g., 4K to 128K) through lightweight continual pretraining on appropriate data mixture. We investigate the \\textit{quantity} and \\textit{quality} of","authors_text":"Hannaneh Hajishirzi, Hao Peng, Rameswar Panda, Xiang Yue, Xinyao Niu, Yao Fu, Yoon Kim","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-15T18:19:16Z","title":"Data Engineering for Scaling Language Models to 128K Context"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.10171","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":"sha256:2242e439b7f30fe8798e46be63a8a995c8dbbed146bb4aa4cb4742b3be87873e","target":"record","created_at":"2026-07-05T07:45:42Z","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":"a8916aa01eb192359a7a40c367e1f07ac0a6d9549829bc917ef744d4940d68b0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-15T18:19:16Z","title_canon_sha256":"97f206c93851126b95c769100447045af28605db2dbc7faa3df5cf52cf13c6dd"},"schema_version":"1.0","source":{"id":"2402.10171","kind":"arxiv","version":1}},"canonical_sha256":"ec76c001268c160e0367c9b7e00740154e0db77ff4cd3702e2d4cf0186c8bdb8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ec76c001268c160e0367c9b7e00740154e0db77ff4cd3702e2d4cf0186c8bdb8","first_computed_at":"2026-07-05T07:45:42.321603Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:45:42.321603Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bZabs9qqG2aeuor6WwzUdPIjcRQKuP6cUnd+b4YtLXFsmwQbHywj5AcKsG3YiPExhUdpB9oLGgip94O1rxA/BA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:45:42.322149Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.10171","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2242e439b7f30fe8798e46be63a8a995c8dbbed146bb4aa4cb4742b3be87873e","sha256:722557831cac931be124e2d628874de0803cf05a03223d270a8654764e79003a"],"state_sha256":"555062965b9bfdc49a60ee34e94bc696d833ad67b01e05f26f67affd7eac9d82"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"neY2KlqQ0k168nvWKiXGFahiIYLbwQcU/1nrI94FLV0pHqacU8GG3bDJBTSkPkOESbyhuflko/TpdBML2TWVCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-25T06:35:35.034820Z","bundle_sha256":"a16ae3b2166686827bcabb4b833d073f3afa7a52f347a2a517807e12838aaa66"}}