{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:W2FIJG6KR5UQSGNWGFVH5H2UWM","short_pith_number":"pith:W2FIJG6K","canonical_record":{"source":{"id":"2409.01893","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-03T13:30:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"670076622bc24816a26b2f0d1173681bea24c78869abfb811cc7274ff72c256a","abstract_canon_sha256":"75ac7c650f5112fce2069d329faed82b30b7124f418c9369b26acefffcd73ee2"},"schema_version":"1.0"},"canonical_sha256":"b68a849bca8f690919b6316a7e9f54b33b80acbb447961a5cee2b8639e928e6f","source":{"kind":"arxiv","id":"2409.01893","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.01893","created_at":"2026-07-05T11:05:21Z"},{"alias_kind":"arxiv_version","alias_value":"2409.01893v2","created_at":"2026-07-05T11:05:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.01893","created_at":"2026-07-05T11:05:21Z"},{"alias_kind":"pith_short_12","alias_value":"W2FIJG6KR5UQ","created_at":"2026-07-05T11:05:21Z"},{"alias_kind":"pith_short_16","alias_value":"W2FIJG6KR5UQSGNW","created_at":"2026-07-05T11:05:21Z"},{"alias_kind":"pith_short_8","alias_value":"W2FIJG6K","created_at":"2026-07-05T11:05:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:W2FIJG6KR5UQSGNWGFVH5H2UWM","target":"record","payload":{"canonical_record":{"source":{"id":"2409.01893","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-03T13:30:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"670076622bc24816a26b2f0d1173681bea24c78869abfb811cc7274ff72c256a","abstract_canon_sha256":"75ac7c650f5112fce2069d329faed82b30b7124f418c9369b26acefffcd73ee2"},"schema_version":"1.0"},"canonical_sha256":"b68a849bca8f690919b6316a7e9f54b33b80acbb447961a5cee2b8639e928e6f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:21.499527Z","signature_b64":"1RNosxYmnXPSKNcCKAXEnLX2m4GB1ezNnZglyS0prl/DdYj8ZEiBKQVaXYAWdCxT2Y1nivNqK/j8jjXBVPI9Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b68a849bca8f690919b6316a7e9f54b33b80acbb447961a5cee2b8639e928e6f","last_reissued_at":"2026-07-05T11:05:21.499085Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:21.499085Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.01893","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":"2026-07-05T11:05:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GsnX/Aji378xb4Lk0NE1YTw/PYFvwuq0rnMm0ACQ8NpWlhy9PzwsgIkRgv5ZEn3zOEdOqq2id0Gv/Mhzv/4NAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T03:09:24.181383Z"},"content_sha256":"0ced1785f079a1e82a9a2b5a29d7edf5f0f0bdc00a1355f72fad386224c1b165","schema_version":"1.0","event_id":"sha256:0ced1785f079a1e82a9a2b5a29d7edf5f0f0bdc00a1355f72fad386224c1b165"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:W2FIJG6KR5UQSGNWGFVH5H2UWM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"What are the Essential Factors in Crafting Effective Long Context Multi-Hop Instruction Datasets? Insights and Best Practices","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dahua Lin, Haijun Lv, Hang Yan, Kai Chen, Libo Qin, Qiguang Chen, Qipeng Guo, Wanxiang Che, Yicheng Zou, Zhi Chen","submitted_at":"2024-09-03T13:30:00Z","abstract_excerpt":"Recent advancements in large language models (LLMs) with extended context windows have significantly improved tasks such as information extraction, question answering, and complex planning scenarios. In order to achieve success in long context tasks, a large amount of work has been done to enhance the long context capabilities of the model through synthetic data. Existing methods typically utilize the Self-Instruct framework to generate instruction tuning data for better long context capability improvement. However, our preliminary experiments indicate that less than 35% of generated samples a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.01893","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/2409.01893/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":"2026-07-05T11:05:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dnlXbio6lIZgzPF3I0W+8LIH8uWijgDJuff6sqHjD7ObpoFkcmDC+5APd7cCZVTvk/umDtFWoon4aghDEybAAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T03:09:24.181909Z"},"content_sha256":"1a73a840ec60451387e4645498a92be32c615dcd23ff3e01da61c6400f9f3ab0","schema_version":"1.0","event_id":"sha256:1a73a840ec60451387e4645498a92be32c615dcd23ff3e01da61c6400f9f3ab0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W2FIJG6KR5UQSGNWGFVH5H2UWM/bundle.json","state_url":"https://pith.science/pith/W2FIJG6KR5UQSGNWGFVH5H2UWM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W2FIJG6KR5UQSGNWGFVH5H2UWM/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":"2026-08-19T03:09:24Z","links":{"resolver":"https://pith.science/pith/W2FIJG6KR5UQSGNWGFVH5H2UWM","bundle":"https://pith.science/pith/W2FIJG6KR5UQSGNWGFVH5H2UWM/bundle.json","state":"https://pith.science/pith/W2FIJG6KR5UQSGNWGFVH5H2UWM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W2FIJG6KR5UQSGNWGFVH5H2UWM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:W2FIJG6KR5UQSGNWGFVH5H2UWM","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":"75ac7c650f5112fce2069d329faed82b30b7124f418c9369b26acefffcd73ee2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-03T13:30:00Z","title_canon_sha256":"670076622bc24816a26b2f0d1173681bea24c78869abfb811cc7274ff72c256a"},"schema_version":"1.0","source":{"id":"2409.01893","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.01893","created_at":"2026-07-05T11:05:21Z"},{"alias_kind":"arxiv_version","alias_value":"2409.01893v2","created_at":"2026-07-05T11:05:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.01893","created_at":"2026-07-05T11:05:21Z"},{"alias_kind":"pith_short_12","alias_value":"W2FIJG6KR5UQ","created_at":"2026-07-05T11:05:21Z"},{"alias_kind":"pith_short_16","alias_value":"W2FIJG6KR5UQSGNW","created_at":"2026-07-05T11:05:21Z"},{"alias_kind":"pith_short_8","alias_value":"W2FIJG6K","created_at":"2026-07-05T11:05:21Z"}],"graph_snapshots":[{"event_id":"sha256:1a73a840ec60451387e4645498a92be32c615dcd23ff3e01da61c6400f9f3ab0","target":"graph","created_at":"2026-07-05T11:05:21Z","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/2409.01893/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in large language models (LLMs) with extended context windows have significantly improved tasks such as information extraction, question answering, and complex planning scenarios. In order to achieve success in long context tasks, a large amount of work has been done to enhance the long context capabilities of the model through synthetic data. Existing methods typically utilize the Self-Instruct framework to generate instruction tuning data for better long context capability improvement. However, our preliminary experiments indicate that less than 35% of generated samples a","authors_text":"Dahua Lin, Haijun Lv, Hang Yan, Kai Chen, Libo Qin, Qiguang Chen, Qipeng Guo, Wanxiang Che, Yicheng Zou, Zhi Chen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-03T13:30:00Z","title":"What are the Essential Factors in Crafting Effective Long Context Multi-Hop Instruction Datasets? Insights and Best Practices"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.01893","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":"sha256:0ced1785f079a1e82a9a2b5a29d7edf5f0f0bdc00a1355f72fad386224c1b165","target":"record","created_at":"2026-07-05T11:05:21Z","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":"75ac7c650f5112fce2069d329faed82b30b7124f418c9369b26acefffcd73ee2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-03T13:30:00Z","title_canon_sha256":"670076622bc24816a26b2f0d1173681bea24c78869abfb811cc7274ff72c256a"},"schema_version":"1.0","source":{"id":"2409.01893","kind":"arxiv","version":2}},"canonical_sha256":"b68a849bca8f690919b6316a7e9f54b33b80acbb447961a5cee2b8639e928e6f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b68a849bca8f690919b6316a7e9f54b33b80acbb447961a5cee2b8639e928e6f","first_computed_at":"2026-07-05T11:05:21.499085Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:05:21.499085Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1RNosxYmnXPSKNcCKAXEnLX2m4GB1ezNnZglyS0prl/DdYj8ZEiBKQVaXYAWdCxT2Y1nivNqK/j8jjXBVPI9Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:05:21.499527Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.01893","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0ced1785f079a1e82a9a2b5a29d7edf5f0f0bdc00a1355f72fad386224c1b165","sha256:1a73a840ec60451387e4645498a92be32c615dcd23ff3e01da61c6400f9f3ab0"],"state_sha256":"cd57830f949ef40f1e283fade5c603737a749b0d2b510f60b240760dce835f6d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BV8eCDUvlIMuTht0YcRhNchjTCAGRW6prd9fYSJcgk5iqdAnAgIpCZNq+eHi6HXjDK167zvJBtVNBBlLT2ZzDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T03:09:24.186533Z","bundle_sha256":"e5202069e9440ebfac3cd6b715c5181ca3aa2371636b20f231b27813446be560"}}