{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JFU4VDSQZBMZKA36SWIHCT27IW","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":"677088529abaf44954619f8959da48a9f928dcf12284d8ed712906cf45b759e6","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-22T04:05:02Z","title_canon_sha256":"5bb3b4494685ad0993d9d26cfe465ae9f417fc00a6894dc8bb2f6893dba970de"},"schema_version":"1.0","source":{"id":"2505.17134","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.17134","created_at":"2026-07-05T11:14:29Z"},{"alias_kind":"arxiv_version","alias_value":"2505.17134v2","created_at":"2026-07-05T11:14:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17134","created_at":"2026-07-05T11:14:29Z"},{"alias_kind":"pith_short_12","alias_value":"JFU4VDSQZBMZ","created_at":"2026-07-05T11:14:29Z"},{"alias_kind":"pith_short_16","alias_value":"JFU4VDSQZBMZKA36","created_at":"2026-07-05T11:14:29Z"},{"alias_kind":"pith_short_8","alias_value":"JFU4VDSQ","created_at":"2026-07-05T11:14:29Z"}],"graph_snapshots":[{"event_id":"sha256:1c6bbe9c9125fbbf09373de1830e13bf5e44b743f9f08c70e742768800278926","target":"graph","created_at":"2026-07-05T11:14:29Z","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/2505.17134/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"High-quality long-context instruction data is essential for aligning long-context large language models (LLMs). Despite the public release of models like Qwen and Llama, their long-context instruction data remains proprietary. Human annotation is costly and challenging, while template-based synthesis methods limit scale, diversity, and quality. We introduce LongMagpie, a self-synthesis framework that automatically generates large-scale long-context instruction data. Our key insight is that aligned long-context LLMs, when presented with a document followed by special tokens preceding a user tur","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":"2025-05-22T04:05:02Z","title":"LongMagpie: A Self-synthesis Method for Generating Large-scale Long-context Instructions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17134","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":"sha256:29fe1aae86038506d02498a2f2afa881da1fb893f66efcce149f9319e047a12e","target":"record","created_at":"2026-07-05T11:14:29Z","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":"677088529abaf44954619f8959da48a9f928dcf12284d8ed712906cf45b759e6","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-22T04:05:02Z","title_canon_sha256":"5bb3b4494685ad0993d9d26cfe465ae9f417fc00a6894dc8bb2f6893dba970de"},"schema_version":"1.0","source":{"id":"2505.17134","kind":"arxiv","version":2}},"canonical_sha256":"4969ca8e50c85995037e9590714f5f4590c689e93781e4e15feb066a66ccbac4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4969ca8e50c85995037e9590714f5f4590c689e93781e4e15feb066a66ccbac4","first_computed_at":"2026-07-05T11:14:29.258882Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:14:29.258882Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jeklnLk8n5eULVpg4/g66O4LwYENZn+W+tJXTR2LdU0EPc7sqYX5vRVo1T8OuPEBU98aQvrR4fAGe7vgcXMNAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:14:29.259388Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.17134","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:29fe1aae86038506d02498a2f2afa881da1fb893f66efcce149f9319e047a12e","sha256:1c6bbe9c9125fbbf09373de1830e13bf5e44b743f9f08c70e742768800278926"],"state_sha256":"e88d9ea52c3c26088bffac91b32ab046e2b352f0d6943026c93d5a7791e65702"}