{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EAKTCZXMWLFYSH33PTPGZDPTHP","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":"f7e5cf583710d76d7396cb0438278c98a40b6e76a6ddf283c0568b73a63f8509","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T12:22:18Z","title_canon_sha256":"8f74c2901ee9a4f53502553cb87edd9de2e029fa58693bf5a7e5836aa07ae925"},"schema_version":"1.0","source":{"id":"2502.14494","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.14494","created_at":"2026-07-05T11:12:27Z"},{"alias_kind":"arxiv_version","alias_value":"2502.14494v2","created_at":"2026-07-05T11:12:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14494","created_at":"2026-07-05T11:12:27Z"},{"alias_kind":"pith_short_12","alias_value":"EAKTCZXMWLFY","created_at":"2026-07-05T11:12:27Z"},{"alias_kind":"pith_short_16","alias_value":"EAKTCZXMWLFYSH33","created_at":"2026-07-05T11:12:27Z"},{"alias_kind":"pith_short_8","alias_value":"EAKTCZXM","created_at":"2026-07-05T11:12:27Z"}],"graph_snapshots":[{"event_id":"sha256:83b3f53697fffcb00eb6c55e558641fb6825b172356946995f225d13137e517f","target":"graph","created_at":"2026-07-05T11:12:27Z","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/2502.14494/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-turn instruction following capability constitutes a core competency of large language models (LLMs) in real-world applications. Existing evaluation benchmarks predominantly focus on fine-grained constraint satisfaction and domain-specific capability assessment, yet overlook the crucial structural dependencies between dialogue turns that distinguish multi-turn from single-turn interactions. These structural dependencies not only reflect user intent but also establish an essential second dimension for the instruction following evaluation beyond constraint satisfaction. To address this gap,","authors_text":"Jinnan Li, Jinzhe Li, Yi Chang, Yuan Wu, Yue Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T12:22:18Z","title":"StructFlowBench: A Structured Flow Benchmark for Multi-turn Instruction Following"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14494","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:ad51bccfe5e5af2fb2366294fab89c5a82f184b63cb623f41ee73be9534162c7","target":"record","created_at":"2026-07-05T11:12:27Z","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":"f7e5cf583710d76d7396cb0438278c98a40b6e76a6ddf283c0568b73a63f8509","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T12:22:18Z","title_canon_sha256":"8f74c2901ee9a4f53502553cb87edd9de2e029fa58693bf5a7e5836aa07ae925"},"schema_version":"1.0","source":{"id":"2502.14494","kind":"arxiv","version":2}},"canonical_sha256":"20153166ecb2cb891f7b7cde6c8df33bce69e0f1e7e830764210f2b6c50cb192","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"20153166ecb2cb891f7b7cde6c8df33bce69e0f1e7e830764210f2b6c50cb192","first_computed_at":"2026-07-05T11:12:27.861187Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:27.861187Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"obpp7mK4pu+NbhkzWG/T95H/AZgD/LMcc7UzsJDctadh49MFqk33mgKic1MY3NJFK9Zgx7MvpZDQURjIaMMNDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:27.861772Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.14494","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ad51bccfe5e5af2fb2366294fab89c5a82f184b63cb623f41ee73be9534162c7","sha256:83b3f53697fffcb00eb6c55e558641fb6825b172356946995f225d13137e517f"],"state_sha256":"92acf69fb6fb5f5f5154a2808f1e3d16ed5ec08ee59db3bbcfe24d5d39e82a07"}