{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VDYXBPT24AG3KZVQQTOPEDD326","short_pith_number":"pith:VDYXBPT2","schema_version":"1.0","canonical_sha256":"a8f170be7ae00db566b084dcf20c7bd7a2f6c2a8ffec79696e9612edcbfe36ea","source":{"kind":"arxiv","id":"2608.01358","version":1},"attestation_state":"computed","paper":{"title":"HopRefusalBench: Diagnosing Refusal Failures in Search-Augmented Agents for Multi-Hop Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bowen Song, Jianan Xie, Qiang Liu, Xing Zheng, Xin Sun, Zhongqi Chen","submitted_at":"2026-08-02T16:20:55Z","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"},"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":"2608.01358","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-02T16:20:55Z","cross_cats_sorted":[],"title_canon_sha256":"160e63ad112696b1738bb72712dc7d3aef61b77e4abbe8dc8d3c9837c94acb18","abstract_canon_sha256":"a3cb67f0e1e66b5ec4e618d5d532e0c9d782b09fd40fa8be46a9441dcdfd03b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:04:52.492746Z","signature_b64":"kwdqyJnQXbfxnVks+hJ9eO4Z2qlJ6V6ve+r/xkcwEwhHSVT2YdaqrLcqr4gGRuAOYKjQpY05gfAX78XssRGrBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8f170be7ae00db566b084dcf20c7bd7a2f6c2a8ffec79696e9612edcbfe36ea","last_reissued_at":"2026-08-04T02:04:52.491100Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:04:52.491100Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HopRefusalBench: Diagnosing Refusal Failures in Search-Augmented Agents for Multi-Hop Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bowen Song, Jianan Xie, Qiang Liu, Xing Zheng, Xin Sun, Zhongqi Chen","submitted_at":"2026-08-02T16:20:55Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01358","kind":"arxiv","version":1},"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/2608.01358/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":"2608.01358","created_at":"2026-08-04T02:04:52.492699+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.01358v1","created_at":"2026-08-04T02:04:52.492699+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01358","created_at":"2026-08-04T02:04:52.492699+00:00"},{"alias_kind":"pith_short_12","alias_value":"VDYXBPT24AG3","created_at":"2026-08-04T02:04:52.492699+00:00"},{"alias_kind":"pith_short_16","alias_value":"VDYXBPT24AG3KZVQ","created_at":"2026-08-04T02:04:52.492699+00:00"},{"alias_kind":"pith_short_8","alias_value":"VDYXBPT2","created_at":"2026-08-04T02:04:52.492699+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VDYXBPT24AG3KZVQQTOPEDD326","json":"https://pith.science/pith/VDYXBPT24AG3KZVQQTOPEDD326.json","graph_json":"https://pith.science/api/pith-number/VDYXBPT24AG3KZVQQTOPEDD326/graph.json","events_json":"https://pith.science/api/pith-number/VDYXBPT24AG3KZVQQTOPEDD326/events.json","paper":"https://pith.science/paper/VDYXBPT2"},"agent_actions":{"view_html":"https://pith.science/pith/VDYXBPT24AG3KZVQQTOPEDD326","download_json":"https://pith.science/pith/VDYXBPT24AG3KZVQQTOPEDD326.json","view_paper":"https://pith.science/paper/VDYXBPT2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.01358&json=true","fetch_graph":"https://pith.science/api/pith-number/VDYXBPT24AG3KZVQQTOPEDD326/graph.json","fetch_events":"https://pith.science/api/pith-number/VDYXBPT24AG3KZVQQTOPEDD326/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VDYXBPT24AG3KZVQQTOPEDD326/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VDYXBPT24AG3KZVQQTOPEDD326/action/storage_attestation","attest_author":"https://pith.science/pith/VDYXBPT24AG3KZVQQTOPEDD326/action/author_attestation","sign_citation":"https://pith.science/pith/VDYXBPT24AG3KZVQQTOPEDD326/action/citation_signature","submit_replication":"https://pith.science/pith/VDYXBPT24AG3KZVQQTOPEDD326/action/replication_record"}},"created_at":"2026-08-04T02:04:52.492699+00:00","updated_at":"2026-08-04T02:04:52.492699+00:00"}