{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2FKXDTJN4QH2CUMPFTPRLZONGA","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":"b22e61c82a88efd193681aeff09698f1ab8b5df5655f49c7f37e7ccd8511335d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-22T10:01:54Z","title_canon_sha256":"3010e1a95c4eaa9aceb23a0d89ab00b1e940bdf3531a545b2f9a12734358cc5b"},"schema_version":"1.0","source":{"id":"2501.12766","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.12766","created_at":"2026-07-05T11:09:06Z"},{"alias_kind":"arxiv_version","alias_value":"2501.12766v2","created_at":"2026-07-05T11:09:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.12766","created_at":"2026-07-05T11:09:06Z"},{"alias_kind":"pith_short_12","alias_value":"2FKXDTJN4QH2","created_at":"2026-07-05T11:09:06Z"},{"alias_kind":"pith_short_16","alias_value":"2FKXDTJN4QH2CUMP","created_at":"2026-07-05T11:09:06Z"},{"alias_kind":"pith_short_8","alias_value":"2FKXDTJN","created_at":"2026-07-05T11:09:06Z"}],"graph_snapshots":[{"event_id":"sha256:8a74582e15114c9a9a3f5e739cc3ad25011e5f49376579d0c50f5f26e193f16d","target":"graph","created_at":"2026-07-05T11:09:06Z","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/2501.12766/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) with extended context windows have made significant strides yet remain a challenge due to the scarcity of long documents. Existing methods tend to synthesize long-context data but lack a clear mechanism to reinforce the long-range dependency modeling. To address this limitation, we propose NExtLong, a novel framework for synthesizing long-context data through Negative document Extension. NExtLong decomposes a document into multiple meta-chunks and extends the context by interleaving hard negative distractors retrieved from pretraining corpora. This approach compels","authors_text":"Chaochen Gao, Debing Zhang, Songlin Hu, Xing Wu, Zijia Lin","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-22T10:01:54Z","title":"NExtLong: Toward Effective Long-Context Training without Long Documents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.12766","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":"sha256:82d9325c9b7cd705db25fe956c22d009b4faaf956ba0d41415f047c543493689","target":"record","created_at":"2026-07-05T11:09:06Z","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":"b22e61c82a88efd193681aeff09698f1ab8b5df5655f49c7f37e7ccd8511335d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-22T10:01:54Z","title_canon_sha256":"3010e1a95c4eaa9aceb23a0d89ab00b1e940bdf3531a545b2f9a12734358cc5b"},"schema_version":"1.0","source":{"id":"2501.12766","kind":"arxiv","version":2}},"canonical_sha256":"d15571cd2de40fa1518f2cdf15e5cd3000603d54614e952f8db25e6af80893f6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d15571cd2de40fa1518f2cdf15e5cd3000603d54614e952f8db25e6af80893f6","first_computed_at":"2026-07-05T11:09:06.911762Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:06.911762Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iyXSAX/tXkyViKW42O+tC2kKvs1Gz+60qdZunF+ligeXfNq7fdKws9O6+lWfy6eEUZGOv7QLtKMaDxWEg112BA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:06.912240Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.12766","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:82d9325c9b7cd705db25fe956c22d009b4faaf956ba0d41415f047c543493689","sha256:8a74582e15114c9a9a3f5e739cc3ad25011e5f49376579d0c50f5f26e193f16d"],"state_sha256":"e43d52039c2f337f8dd0de5e605cf758580552ff21e4f12a55099c02e9bb13c5"}