{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SZMFKUZCJGDFJXXUBGZTIN2JGS","short_pith_number":"pith:SZMFKUZC","schema_version":"1.0","canonical_sha256":"9658555322498654def409b3343749349903177958313418be1fdeeaf4afad6d","source":{"kind":"arxiv","id":"2606.12871","version":1},"attestation_state":"computed","paper":{"title":"DailyReport: An Open-ended Benchmark for Evaluating Search Agents on Daily Search Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jingxuan Han, Licheng Zhang, Lin Qiu, Mingyang Zhu, Wei Liu, Xuezhi Cao, Xunliang Cai, Youpeng Wang, Zhendong Mao, Zheren Fu, Ziwen Wang","submitted_at":"2026-06-11T03:59:07Z","abstract_excerpt":"Search Agents (SAs) typically leverage large language models (LLMs) to support complex information-seeking tasks by autonomously exploring web sources and synthesizing information into comprehensive responses. For SAs evaluation, prior benchmarks mainly focus on specialized tasks that are unlikely to arise in real-world user scenarios. Moreover, their reliance on coarse task-level rubrics often limits evaluation interpretability. To bridge this gap, we introduce DailyReport, an open-ended benchmark to evaluate SA capabilities on daily search tasks. It contains 150 open-ended tasks with 3,546 a"},"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":"2606.12871","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-11T03:59:07Z","cross_cats_sorted":[],"title_canon_sha256":"7d5dd9e0df3b6d7ed722e4c6a9b6791b02280ff442b434ad341e4a7d45006baf","abstract_canon_sha256":"744eb335ededfe60ef35546c23c8073abc87e140a87402a31a7fdc16b2845379"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T01:08:56.010080Z","signature_b64":"GplgmiOrYE44OuQNLNsGZoSNjv2qJpwqn6dOQDCuZWd2FAVGb+Gvfx3GKDWSJLdfg5NNJ9uOzbkAcRAF/r05AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9658555322498654def409b3343749349903177958313418be1fdeeaf4afad6d","last_reissued_at":"2026-06-12T01:08:56.009284Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T01:08:56.009284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DailyReport: An Open-ended Benchmark for Evaluating Search Agents on Daily Search Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jingxuan Han, Licheng Zhang, Lin Qiu, Mingyang Zhu, Wei Liu, Xuezhi Cao, Xunliang Cai, Youpeng Wang, Zhendong Mao, Zheren Fu, Ziwen Wang","submitted_at":"2026-06-11T03:59:07Z","abstract_excerpt":"Search Agents (SAs) typically leverage large language models (LLMs) to support complex information-seeking tasks by autonomously exploring web sources and synthesizing information into comprehensive responses. For SAs evaluation, prior benchmarks mainly focus on specialized tasks that are unlikely to arise in real-world user scenarios. Moreover, their reliance on coarse task-level rubrics often limits evaluation interpretability. To bridge this gap, we introduce DailyReport, an open-ended benchmark to evaluate SA capabilities on daily search tasks. It contains 150 open-ended tasks with 3,546 a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.12871","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/2606.12871/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":"2606.12871","created_at":"2026-06-12T01:08:56.009423+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.12871v1","created_at":"2026-06-12T01:08:56.009423+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.12871","created_at":"2026-06-12T01:08:56.009423+00:00"},{"alias_kind":"pith_short_12","alias_value":"SZMFKUZCJGDF","created_at":"2026-06-12T01:08:56.009423+00:00"},{"alias_kind":"pith_short_16","alias_value":"SZMFKUZCJGDFJXXU","created_at":"2026-06-12T01:08:56.009423+00:00"},{"alias_kind":"pith_short_8","alias_value":"SZMFKUZC","created_at":"2026-06-12T01:08:56.009423+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/SZMFKUZCJGDFJXXUBGZTIN2JGS","json":"https://pith.science/pith/SZMFKUZCJGDFJXXUBGZTIN2JGS.json","graph_json":"https://pith.science/api/pith-number/SZMFKUZCJGDFJXXUBGZTIN2JGS/graph.json","events_json":"https://pith.science/api/pith-number/SZMFKUZCJGDFJXXUBGZTIN2JGS/events.json","paper":"https://pith.science/paper/SZMFKUZC"},"agent_actions":{"view_html":"https://pith.science/pith/SZMFKUZCJGDFJXXUBGZTIN2JGS","download_json":"https://pith.science/pith/SZMFKUZCJGDFJXXUBGZTIN2JGS.json","view_paper":"https://pith.science/paper/SZMFKUZC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.12871&json=true","fetch_graph":"https://pith.science/api/pith-number/SZMFKUZCJGDFJXXUBGZTIN2JGS/graph.json","fetch_events":"https://pith.science/api/pith-number/SZMFKUZCJGDFJXXUBGZTIN2JGS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SZMFKUZCJGDFJXXUBGZTIN2JGS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SZMFKUZCJGDFJXXUBGZTIN2JGS/action/storage_attestation","attest_author":"https://pith.science/pith/SZMFKUZCJGDFJXXUBGZTIN2JGS/action/author_attestation","sign_citation":"https://pith.science/pith/SZMFKUZCJGDFJXXUBGZTIN2JGS/action/citation_signature","submit_replication":"https://pith.science/pith/SZMFKUZCJGDFJXXUBGZTIN2JGS/action/replication_record"}},"created_at":"2026-06-12T01:08:56.009423+00:00","updated_at":"2026-06-12T01:08:56.009423+00:00"}