{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:TB7PEXAMGEDP4KVD5JSPD5YDDU","short_pith_number":"pith:TB7PEXAM","canonical_record":{"source":{"id":"2412.18860","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-25T10:08:54Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"1ff325a7b7c35312350175a2f362f632f128e8ebbe258220602c5a23a018ac96","abstract_canon_sha256":"7409105876b05d2c841c36afc1fba2a524424e8b3d25a3466afd3685aebb19b3"},"schema_version":"1.0"},"canonical_sha256":"987ef25c0c3106fe2aa3ea64f1f7031d005d23488461a4b87eaeb2aaee0da5b5","source":{"kind":"arxiv","id":"2412.18860","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.18860","created_at":"2026-07-05T10:34:14Z"},{"alias_kind":"arxiv_version","alias_value":"2412.18860v2","created_at":"2026-07-05T10:34:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18860","created_at":"2026-07-05T10:34:14Z"},{"alias_kind":"pith_short_12","alias_value":"TB7PEXAMGEDP","created_at":"2026-07-05T10:34:14Z"},{"alias_kind":"pith_short_16","alias_value":"TB7PEXAMGEDP4KVD","created_at":"2026-07-05T10:34:14Z"},{"alias_kind":"pith_short_8","alias_value":"TB7PEXAM","created_at":"2026-07-05T10:34:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:TB7PEXAMGEDP4KVD5JSPD5YDDU","target":"record","payload":{"canonical_record":{"source":{"id":"2412.18860","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-25T10:08:54Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"1ff325a7b7c35312350175a2f362f632f128e8ebbe258220602c5a23a018ac96","abstract_canon_sha256":"7409105876b05d2c841c36afc1fba2a524424e8b3d25a3466afd3685aebb19b3"},"schema_version":"1.0"},"canonical_sha256":"987ef25c0c3106fe2aa3ea64f1f7031d005d23488461a4b87eaeb2aaee0da5b5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:34:14.097929Z","signature_b64":"GNHQGfIYVbUihboNFmgstjqQx/xlsQYkAh6ZQs80x7KZ++mXFN0LmqWIBwMAlERJ6nwNvCJBQO6xYHZCqzMzAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"987ef25c0c3106fe2aa3ea64f1f7031d005d23488461a4b87eaeb2aaee0da5b5","last_reissued_at":"2026-07-05T10:34:14.097302Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:34:14.097302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.18860","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:34:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FIQYfUUUNoEsG9P26njr2SqAoBdZSEVBuSGrtbCSLVWrZCZ5Q/FXi4ofQWSVvA0yOOcGK6gH2R4Q22BcUvEiBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T00:48:28.565498Z"},"content_sha256":"3d9fe073ed6906d4864b465ea9e7844d597cbd5ee09fddb24ad9f8f6f0a70b73","schema_version":"1.0","event_id":"sha256:3d9fe073ed6906d4864b465ea9e7844d597cbd5ee09fddb24ad9f8f6f0a70b73"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:TB7PEXAMGEDP4KVD5JSPD5YDDU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bootstrap Your Own Context Length","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Furu Wei, Liang Wang, Nan Yang, Xiaolong Huang, Xingxing Zhang","submitted_at":"2024-12-25T10:08:54Z","abstract_excerpt":"We introduce a bootstrapping approach to train long-context language models by exploiting their short-context capabilities only. Our method utilizes a simple agent workflow to synthesize diverse long-context instruction tuning data, thereby eliminating the necessity for manual data collection and annotation. The proposed data synthesis workflow requires only a short-context language model, a text retriever, and a document collection, all of which are readily accessible within the open-source ecosystem. Subsequently, language models are fine-tuned using the synthesized data to extend their cont"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18860","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/2412.18860/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":"2026-07-05T10:34:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CdIOqqjUSlnrTTwCGDicdtpRCtGlndk9uDmQlcbujSuDa3McAinIJdltMEMH24ovPgvccNXkTPnWnogsCadzBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T00:48:28.566003Z"},"content_sha256":"84059645dddd95c3dd0219712aed26714acc648b2a81dc91c9bbe32a3f2f0758","schema_version":"1.0","event_id":"sha256:84059645dddd95c3dd0219712aed26714acc648b2a81dc91c9bbe32a3f2f0758"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TB7PEXAMGEDP4KVD5JSPD5YDDU/bundle.json","state_url":"https://pith.science/pith/TB7PEXAMGEDP4KVD5JSPD5YDDU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TB7PEXAMGEDP4KVD5JSPD5YDDU/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":"2026-08-10T00:48:28Z","links":{"resolver":"https://pith.science/pith/TB7PEXAMGEDP4KVD5JSPD5YDDU","bundle":"https://pith.science/pith/TB7PEXAMGEDP4KVD5JSPD5YDDU/bundle.json","state":"https://pith.science/pith/TB7PEXAMGEDP4KVD5JSPD5YDDU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TB7PEXAMGEDP4KVD5JSPD5YDDU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TB7PEXAMGEDP4KVD5JSPD5YDDU","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":"7409105876b05d2c841c36afc1fba2a524424e8b3d25a3466afd3685aebb19b3","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-25T10:08:54Z","title_canon_sha256":"1ff325a7b7c35312350175a2f362f632f128e8ebbe258220602c5a23a018ac96"},"schema_version":"1.0","source":{"id":"2412.18860","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.18860","created_at":"2026-07-05T10:34:14Z"},{"alias_kind":"arxiv_version","alias_value":"2412.18860v2","created_at":"2026-07-05T10:34:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18860","created_at":"2026-07-05T10:34:14Z"},{"alias_kind":"pith_short_12","alias_value":"TB7PEXAMGEDP","created_at":"2026-07-05T10:34:14Z"},{"alias_kind":"pith_short_16","alias_value":"TB7PEXAMGEDP4KVD","created_at":"2026-07-05T10:34:14Z"},{"alias_kind":"pith_short_8","alias_value":"TB7PEXAM","created_at":"2026-07-05T10:34:14Z"}],"graph_snapshots":[{"event_id":"sha256:84059645dddd95c3dd0219712aed26714acc648b2a81dc91c9bbe32a3f2f0758","target":"graph","created_at":"2026-07-05T10:34:14Z","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/2412.18860/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce a bootstrapping approach to train long-context language models by exploiting their short-context capabilities only. Our method utilizes a simple agent workflow to synthesize diverse long-context instruction tuning data, thereby eliminating the necessity for manual data collection and annotation. The proposed data synthesis workflow requires only a short-context language model, a text retriever, and a document collection, all of which are readily accessible within the open-source ecosystem. Subsequently, language models are fine-tuned using the synthesized data to extend their cont","authors_text":"Furu Wei, Liang Wang, Nan Yang, Xiaolong Huang, Xingxing Zhang","cross_cats":["cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-25T10:08:54Z","title":"Bootstrap Your Own Context Length"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18860","kind":"arxiv","version":2},"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":"sha256:3d9fe073ed6906d4864b465ea9e7844d597cbd5ee09fddb24ad9f8f6f0a70b73","target":"record","created_at":"2026-07-05T10:34:14Z","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":"7409105876b05d2c841c36afc1fba2a524424e8b3d25a3466afd3685aebb19b3","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-25T10:08:54Z","title_canon_sha256":"1ff325a7b7c35312350175a2f362f632f128e8ebbe258220602c5a23a018ac96"},"schema_version":"1.0","source":{"id":"2412.18860","kind":"arxiv","version":2}},"canonical_sha256":"987ef25c0c3106fe2aa3ea64f1f7031d005d23488461a4b87eaeb2aaee0da5b5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"987ef25c0c3106fe2aa3ea64f1f7031d005d23488461a4b87eaeb2aaee0da5b5","first_computed_at":"2026-07-05T10:34:14.097302Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:34:14.097302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GNHQGfIYVbUihboNFmgstjqQx/xlsQYkAh6ZQs80x7KZ++mXFN0LmqWIBwMAlERJ6nwNvCJBQO6xYHZCqzMzAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:34:14.097929Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.18860","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3d9fe073ed6906d4864b465ea9e7844d597cbd5ee09fddb24ad9f8f6f0a70b73","sha256:84059645dddd95c3dd0219712aed26714acc648b2a81dc91c9bbe32a3f2f0758"],"state_sha256":"174ee14ea5d8b3f1ac2860b6db6a1159c0aafcb1547ea90d42d681354c9cc1f0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NbRjW52c9JzbQzOsVX/cG7eEYUVX4K8QI6mlKz94WzYMOICUKxbsugHHb9LxjnUekesNJ4HqLGmmCFl+S/ZbAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T00:48:28.571162Z","bundle_sha256":"486ba2c64e18dc468be8e24e5140613e310225ec328d0bad2a696bf44b2e5b9e"}}