{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JULDF2DXXQIZRDM2EA2DOC7J5S","short_pith_number":"pith:JULDF2DX","schema_version":"1.0","canonical_sha256":"4d1632e877bc11988d9a2034370be9ec8c61fe4738af73b0270e2b5863e47e42","source":{"kind":"arxiv","id":"2608.01913","version":1},"attestation_state":"computed","paper":{"title":"Diagnosing Search Behavior and Failure Modes in Long-Horizon Search Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.AI","authors_text":"Fengbin Zhu, Jiaxin Mao, Qi Liu, Tat-Seng Chua","submitted_at":"2026-08-03T08:46:48Z","abstract_excerpt":"Deep search agents answer difficult information-seeking questions by iteratively issuing search queries to gather supporting evidence, but it remains unclear whether and how greater search effort leads to better answers. We study these questions through a trajectory-level diagnosis of long-horizon search agents. Using human-annotated document-level relevance judgments, we evaluate the evidence retrieved at each search step and separate two stages of agent behavior: what evidence an agent retrieves and how effectively it uses that evidence. This distinction further allows us to decompose failur"},"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":"2608.01913","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-03T08:46:48Z","cross_cats_sorted":["cs.CL","cs.IR"],"title_canon_sha256":"ea8dd1ba4ac66e38e6218c8fb82fb47f10d7a2d87227d4c553f29f4fe02de6c5","abstract_canon_sha256":"066bc8361b25fc1f7b0d71c5ba4b4a57198e3f7f5a778db5796cc4e82612b8b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:07:37.428267Z","signature_b64":"tMzGEs6JE0ab9NvfioMplOxgQFJb7CENbk/Fr2yY2JFqboyMLlFtUKM3sttZ1ckrNVk97lX7EEYks5Rt/SlPAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d1632e877bc11988d9a2034370be9ec8c61fe4738af73b0270e2b5863e47e42","last_reissued_at":"2026-08-04T02:07:37.426700Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:07:37.426700Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diagnosing Search Behavior and Failure Modes in Long-Horizon Search Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.AI","authors_text":"Fengbin Zhu, Jiaxin Mao, Qi Liu, Tat-Seng Chua","submitted_at":"2026-08-03T08:46:48Z","abstract_excerpt":"Deep search agents answer difficult information-seeking questions by iteratively issuing search queries to gather supporting evidence, but it remains unclear whether and how greater search effort leads to better answers. We study these questions through a trajectory-level diagnosis of long-horizon search agents. Using human-annotated document-level relevance judgments, we evaluate the evidence retrieved at each search step and separate two stages of agent behavior: what evidence an agent retrieves and how effectively it uses that evidence. This distinction further allows us to decompose failur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01913","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/2608.01913/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":"2608.01913","created_at":"2026-08-04T02:07:37.428218+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.01913v1","created_at":"2026-08-04T02:07:37.428218+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01913","created_at":"2026-08-04T02:07:37.428218+00:00"},{"alias_kind":"pith_short_12","alias_value":"JULDF2DXXQIZ","created_at":"2026-08-04T02:07:37.428218+00:00"},{"alias_kind":"pith_short_16","alias_value":"JULDF2DXXQIZRDM2","created_at":"2026-08-04T02:07:37.428218+00:00"},{"alias_kind":"pith_short_8","alias_value":"JULDF2DX","created_at":"2026-08-04T02:07:37.428218+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/JULDF2DXXQIZRDM2EA2DOC7J5S","json":"https://pith.science/pith/JULDF2DXXQIZRDM2EA2DOC7J5S.json","graph_json":"https://pith.science/api/pith-number/JULDF2DXXQIZRDM2EA2DOC7J5S/graph.json","events_json":"https://pith.science/api/pith-number/JULDF2DXXQIZRDM2EA2DOC7J5S/events.json","paper":"https://pith.science/paper/JULDF2DX"},"agent_actions":{"view_html":"https://pith.science/pith/JULDF2DXXQIZRDM2EA2DOC7J5S","download_json":"https://pith.science/pith/JULDF2DXXQIZRDM2EA2DOC7J5S.json","view_paper":"https://pith.science/paper/JULDF2DX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.01913&json=true","fetch_graph":"https://pith.science/api/pith-number/JULDF2DXXQIZRDM2EA2DOC7J5S/graph.json","fetch_events":"https://pith.science/api/pith-number/JULDF2DXXQIZRDM2EA2DOC7J5S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JULDF2DXXQIZRDM2EA2DOC7J5S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JULDF2DXXQIZRDM2EA2DOC7J5S/action/storage_attestation","attest_author":"https://pith.science/pith/JULDF2DXXQIZRDM2EA2DOC7J5S/action/author_attestation","sign_citation":"https://pith.science/pith/JULDF2DXXQIZRDM2EA2DOC7J5S/action/citation_signature","submit_replication":"https://pith.science/pith/JULDF2DXXQIZRDM2EA2DOC7J5S/action/replication_record"}},"created_at":"2026-08-04T02:07:37.428218+00:00","updated_at":"2026-08-04T02:07:37.428218+00:00"}