{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EAKTCZXMWLFYSH33PTPGZDPTHP","short_pith_number":"pith:EAKTCZXM","schema_version":"1.0","canonical_sha256":"20153166ecb2cb891f7b7cde6c8df33bce69e0f1e7e830764210f2b6c50cb192","source":{"kind":"arxiv","id":"2502.14494","version":2},"attestation_state":"computed","paper":{"title":"StructFlowBench: A Structured Flow Benchmark for Multi-turn Instruction Following","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jinnan Li, Jinzhe Li, Yi Chang, Yuan Wu, Yue Wang","submitted_at":"2025-02-20T12:22:18Z","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,"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2502.14494","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T12:22:18Z","cross_cats_sorted":[],"title_canon_sha256":"8f74c2901ee9a4f53502553cb87edd9de2e029fa58693bf5a7e5836aa07ae925","abstract_canon_sha256":"f7e5cf583710d76d7396cb0438278c98a40b6e76a6ddf283c0568b73a63f8509"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:27.861772Z","signature_b64":"obpp7mK4pu+NbhkzWG/T95H/AZgD/LMcc7UzsJDctadh49MFqk33mgKic1MY3NJFK9Zgx7MvpZDQURjIaMMNDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20153166ecb2cb891f7b7cde6c8df33bce69e0f1e7e830764210f2b6c50cb192","last_reissued_at":"2026-07-05T11:12:27.861187Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:27.861187Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"StructFlowBench: A Structured Flow Benchmark for Multi-turn Instruction Following","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jinnan Li, Jinzhe Li, Yi Chang, Yuan Wu, Yue Wang","submitted_at":"2025-02-20T12:22:18Z","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,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14494","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/2502.14494/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2502.14494","created_at":"2026-07-05T11:12:27.861254+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.14494v2","created_at":"2026-07-05T11:12:27.861254+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14494","created_at":"2026-07-05T11:12:27.861254+00:00"},{"alias_kind":"pith_short_12","alias_value":"EAKTCZXMWLFY","created_at":"2026-07-05T11:12:27.861254+00:00"},{"alias_kind":"pith_short_16","alias_value":"EAKTCZXMWLFYSH33","created_at":"2026-07-05T11:12:27.861254+00:00"},{"alias_kind":"pith_short_8","alias_value":"EAKTCZXM","created_at":"2026-07-05T11:12:27.861254+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.27209","citing_title":"Learning to Act under Noise: Enhancing Agent Robustness via Noisy Environments","ref_index":69,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EAKTCZXMWLFYSH33PTPGZDPTHP","json":"https://pith.science/pith/EAKTCZXMWLFYSH33PTPGZDPTHP.json","graph_json":"https://pith.science/api/pith-number/EAKTCZXMWLFYSH33PTPGZDPTHP/graph.json","events_json":"https://pith.science/api/pith-number/EAKTCZXMWLFYSH33PTPGZDPTHP/events.json","paper":"https://pith.science/paper/EAKTCZXM"},"agent_actions":{"view_html":"https://pith.science/pith/EAKTCZXMWLFYSH33PTPGZDPTHP","download_json":"https://pith.science/pith/EAKTCZXMWLFYSH33PTPGZDPTHP.json","view_paper":"https://pith.science/paper/EAKTCZXM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.14494&json=true","fetch_graph":"https://pith.science/api/pith-number/EAKTCZXMWLFYSH33PTPGZDPTHP/graph.json","fetch_events":"https://pith.science/api/pith-number/EAKTCZXMWLFYSH33PTPGZDPTHP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EAKTCZXMWLFYSH33PTPGZDPTHP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EAKTCZXMWLFYSH33PTPGZDPTHP/action/storage_attestation","attest_author":"https://pith.science/pith/EAKTCZXMWLFYSH33PTPGZDPTHP/action/author_attestation","sign_citation":"https://pith.science/pith/EAKTCZXMWLFYSH33PTPGZDPTHP/action/citation_signature","submit_replication":"https://pith.science/pith/EAKTCZXMWLFYSH33PTPGZDPTHP/action/replication_record"}},"created_at":"2026-07-05T11:12:27.861254+00:00","updated_at":"2026-07-05T11:12:27.861254+00:00"}