{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:VOAAFGPV2AR5FWC76PXSPY3YY4","short_pith_number":"pith:VOAAFGPV","canonical_record":{"source":{"id":"2504.12637","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-17T04:46:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1b99cceb520d3b249f23fc9eff900c68844c57e0b44316a3de6b97a62777157c","abstract_canon_sha256":"de179f81b55dfea093520650e0068a725f840f9fb1a26a1b6fb525d45ba574b8"},"schema_version":"1.0"},"canonical_sha256":"ab800299f5d023d2d85ff3ef27e378c7280853a627a619a1559985ef0e6e846b","source":{"kind":"arxiv","id":"2504.12637","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.12637","created_at":"2026-07-05T10:50:19Z"},{"alias_kind":"arxiv_version","alias_value":"2504.12637v1","created_at":"2026-07-05T10:50:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.12637","created_at":"2026-07-05T10:50:19Z"},{"alias_kind":"pith_short_12","alias_value":"VOAAFGPV2AR5","created_at":"2026-07-05T10:50:19Z"},{"alias_kind":"pith_short_16","alias_value":"VOAAFGPV2AR5FWC7","created_at":"2026-07-05T10:50:19Z"},{"alias_kind":"pith_short_8","alias_value":"VOAAFGPV","created_at":"2026-07-05T10:50:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:VOAAFGPV2AR5FWC76PXSPY3YY4","target":"record","payload":{"canonical_record":{"source":{"id":"2504.12637","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-17T04:46:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1b99cceb520d3b249f23fc9eff900c68844c57e0b44316a3de6b97a62777157c","abstract_canon_sha256":"de179f81b55dfea093520650e0068a725f840f9fb1a26a1b6fb525d45ba574b8"},"schema_version":"1.0"},"canonical_sha256":"ab800299f5d023d2d85ff3ef27e378c7280853a627a619a1559985ef0e6e846b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:50:19.990918Z","signature_b64":"izvmuE7KQODpfQm1zt07REWY8xb80fTmTTmOonpv1ItDxLgGmXXYJNmR2toBW/BEjduF71Dn6EnqQUiYQ1UqAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab800299f5d023d2d85ff3ef27e378c7280853a627a619a1559985ef0e6e846b","last_reissued_at":"2026-07-05T10:50:19.990405Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:50:19.990405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.12637","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":"2026-07-05T10:50:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hAdxNSZ9VhqvBja8kqDFOHrWQCwBqtbcivCcaeMcejdqq6VPo9pCVuoyGCfutzagjUNgDMJObP7fCpVXYlskDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T11:51:39.203473Z"},"content_sha256":"cde2ffc4b404f86349e0cead2a6905e2924e8ea4476991501d68c4bcd391858c","schema_version":"1.0","event_id":"sha256:cde2ffc4b404f86349e0cead2a6905e2924e8ea4476991501d68c4bcd391858c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:VOAAFGPV2AR5FWC76PXSPY3YY4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scaling Instruction-Tuned LLMs to Million-Token Contexts via Hierarchical Synthetic Data Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ben Athiwaratkun, Ce Zhang, Jue Wang, Linda He, Maurice Weber, Shang Zhu","submitted_at":"2025-04-17T04:46:57Z","abstract_excerpt":"Large Language Models (LLMs) struggle with long-context reasoning, not only due to the quadratic scaling of computational complexity with sequence length but also because of the scarcity and expense of annotating long-context data. There has been barely any open-source work that systematically ablates long-context data, nor is there any openly available instruction tuning dataset with contexts surpassing 100K tokens. To bridge this gap, we introduce a novel post-training synthetic data generation strategy designed to efficiently extend the context window of LLMs while preserving their general "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.12637","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/2504.12637/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":"2026-07-05T10:50:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yHxuQeNeYqTxM6lftP4XO0mbcNdADYAJMcWSQsS8gZIAMscfJvhyFSgkqRzc8XIovTByOFElelWxuYIJ7onqCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T11:51:39.204425Z"},"content_sha256":"17c2e3e1b8e2c3ea8a9b0114e978eec62d700ffda5e4fa0f9eaf4c7ce1bc2b9d","schema_version":"1.0","event_id":"sha256:17c2e3e1b8e2c3ea8a9b0114e978eec62d700ffda5e4fa0f9eaf4c7ce1bc2b9d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VOAAFGPV2AR5FWC76PXSPY3YY4/bundle.json","state_url":"https://pith.science/pith/VOAAFGPV2AR5FWC76PXSPY3YY4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VOAAFGPV2AR5FWC76PXSPY3YY4/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":"2026-08-18T11:51:39Z","links":{"resolver":"https://pith.science/pith/VOAAFGPV2AR5FWC76PXSPY3YY4","bundle":"https://pith.science/pith/VOAAFGPV2AR5FWC76PXSPY3YY4/bundle.json","state":"https://pith.science/pith/VOAAFGPV2AR5FWC76PXSPY3YY4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VOAAFGPV2AR5FWC76PXSPY3YY4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VOAAFGPV2AR5FWC76PXSPY3YY4","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":"de179f81b55dfea093520650e0068a725f840f9fb1a26a1b6fb525d45ba574b8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-17T04:46:57Z","title_canon_sha256":"1b99cceb520d3b249f23fc9eff900c68844c57e0b44316a3de6b97a62777157c"},"schema_version":"1.0","source":{"id":"2504.12637","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.12637","created_at":"2026-07-05T10:50:19Z"},{"alias_kind":"arxiv_version","alias_value":"2504.12637v1","created_at":"2026-07-05T10:50:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.12637","created_at":"2026-07-05T10:50:19Z"},{"alias_kind":"pith_short_12","alias_value":"VOAAFGPV2AR5","created_at":"2026-07-05T10:50:19Z"},{"alias_kind":"pith_short_16","alias_value":"VOAAFGPV2AR5FWC7","created_at":"2026-07-05T10:50:19Z"},{"alias_kind":"pith_short_8","alias_value":"VOAAFGPV","created_at":"2026-07-05T10:50:19Z"}],"graph_snapshots":[{"event_id":"sha256:17c2e3e1b8e2c3ea8a9b0114e978eec62d700ffda5e4fa0f9eaf4c7ce1bc2b9d","target":"graph","created_at":"2026-07-05T10:50:19Z","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/2504.12637/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) struggle with long-context reasoning, not only due to the quadratic scaling of computational complexity with sequence length but also because of the scarcity and expense of annotating long-context data. There has been barely any open-source work that systematically ablates long-context data, nor is there any openly available instruction tuning dataset with contexts surpassing 100K tokens. To bridge this gap, we introduce a novel post-training synthetic data generation strategy designed to efficiently extend the context window of LLMs while preserving their general ","authors_text":"Ben Athiwaratkun, Ce Zhang, Jue Wang, Linda He, Maurice Weber, Shang Zhu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-17T04:46:57Z","title":"Scaling Instruction-Tuned LLMs to Million-Token Contexts via Hierarchical Synthetic Data Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.12637","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:cde2ffc4b404f86349e0cead2a6905e2924e8ea4476991501d68c4bcd391858c","target":"record","created_at":"2026-07-05T10:50:19Z","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":"de179f81b55dfea093520650e0068a725f840f9fb1a26a1b6fb525d45ba574b8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-17T04:46:57Z","title_canon_sha256":"1b99cceb520d3b249f23fc9eff900c68844c57e0b44316a3de6b97a62777157c"},"schema_version":"1.0","source":{"id":"2504.12637","kind":"arxiv","version":1}},"canonical_sha256":"ab800299f5d023d2d85ff3ef27e378c7280853a627a619a1559985ef0e6e846b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ab800299f5d023d2d85ff3ef27e378c7280853a627a619a1559985ef0e6e846b","first_computed_at":"2026-07-05T10:50:19.990405Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:50:19.990405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"izvmuE7KQODpfQm1zt07REWY8xb80fTmTTmOonpv1ItDxLgGmXXYJNmR2toBW/BEjduF71Dn6EnqQUiYQ1UqAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:50:19.990918Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.12637","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cde2ffc4b404f86349e0cead2a6905e2924e8ea4476991501d68c4bcd391858c","sha256:17c2e3e1b8e2c3ea8a9b0114e978eec62d700ffda5e4fa0f9eaf4c7ce1bc2b9d"],"state_sha256":"4417454d4b8d18c8787417406261d70c2b63672d2276d1c6d1774dc78ca89ad8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"77Ajm1CZ9JO7WGdXK3b7MixFN8zVNs4Ar9vHyNK9l3QIyZmrm2nDFPtP6bFZVC9taWnnl1SHuRJQZ9z5WtF1DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T11:51:39.210365Z","bundle_sha256":"5c8745df28aebaa1aad2deacc550d834dad543b332087508bf6562acfff3f704"}}