{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VDYXBPT24AG3KZVQQTOPEDD326","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":"a3cb67f0e1e66b5ec4e618d5d532e0c9d782b09fd40fa8be46a9441dcdfd03b2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-02T16:20:55Z","title_canon_sha256":"160e63ad112696b1738bb72712dc7d3aef61b77e4abbe8dc8d3c9837c94acb18"},"schema_version":"1.0","source":{"id":"2608.01358","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.01358","created_at":"2026-08-04T02:04:52Z"},{"alias_kind":"arxiv_version","alias_value":"2608.01358v1","created_at":"2026-08-04T02:04:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01358","created_at":"2026-08-04T02:04:52Z"},{"alias_kind":"pith_short_12","alias_value":"VDYXBPT24AG3","created_at":"2026-08-04T02:04:52Z"},{"alias_kind":"pith_short_16","alias_value":"VDYXBPT24AG3KZVQ","created_at":"2026-08-04T02:04:52Z"},{"alias_kind":"pith_short_8","alias_value":"VDYXBPT2","created_at":"2026-08-04T02:04:52Z"}],"graph_snapshots":[{"event_id":"sha256:ec9adb7f3bd8fd58bffb55baf4847016ca36bef8df24db353b3d52530745a157","target":"graph","created_at":"2026-08-04T02:04:52Z","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/2608.01358/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Search-augmented large language model agents are increasingly capable of solving knowledge-intensive tasks, but their behavior when a multi-hop question is fundamentally unanswerable remains poorly understood. Existing abstention benchmarks largely expose defects at the surface of single-hop queries and therefore cannot reveal failures that emerge only after valid intermediate reasoning and retrieval. We introduce HopRefusalBench, the first controlled benchmark of refusal within multi-hop search, comprising 889 unanswerable questions constructed from KILT-grounded entity paths. It crosses thre","authors_text":"Bowen Song, Jianan Xie, Qiang Liu, Xing Zheng, Xin Sun, Zhongqi Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-02T16:20:55Z","title":"HopRefusalBench: Diagnosing Refusal Failures in Search-Augmented Agents for Multi-Hop Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01358","kind":"arxiv","version":1},"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:ac7d1d5497534563276fac858f5dfe4fcdda31cf8ecae0a1b7d7bed5a7552fc1","target":"record","created_at":"2026-08-04T02:04:52Z","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":"a3cb67f0e1e66b5ec4e618d5d532e0c9d782b09fd40fa8be46a9441dcdfd03b2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-02T16:20:55Z","title_canon_sha256":"160e63ad112696b1738bb72712dc7d3aef61b77e4abbe8dc8d3c9837c94acb18"},"schema_version":"1.0","source":{"id":"2608.01358","kind":"arxiv","version":1}},"canonical_sha256":"a8f170be7ae00db566b084dcf20c7bd7a2f6c2a8ffec79696e9612edcbfe36ea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a8f170be7ae00db566b084dcf20c7bd7a2f6c2a8ffec79696e9612edcbfe36ea","first_computed_at":"2026-08-04T02:04:52.491100Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T02:04:52.491100Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kwdqyJnQXbfxnVks+hJ9eO4Z2qlJ6V6ve+r/xkcwEwhHSVT2YdaqrLcqr4gGRuAOYKjQpY05gfAX78XssRGrBQ==","signature_status":"signed_v1","signed_at":"2026-08-04T02:04:52.492746Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.01358","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ac7d1d5497534563276fac858f5dfe4fcdda31cf8ecae0a1b7d7bed5a7552fc1","sha256:ec9adb7f3bd8fd58bffb55baf4847016ca36bef8df24db353b3d52530745a157"],"state_sha256":"9fb1d539c414919469d951e322bde462b69b7f3c347256979f5a3611215dd7da"}