{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SZMFKUZCJGDFJXXUBGZTIN2JGS","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":"744eb335ededfe60ef35546c23c8073abc87e140a87402a31a7fdc16b2845379","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-11T03:59:07Z","title_canon_sha256":"7d5dd9e0df3b6d7ed722e4c6a9b6791b02280ff442b434ad341e4a7d45006baf"},"schema_version":"1.0","source":{"id":"2606.12871","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.12871","created_at":"2026-06-12T01:08:56Z"},{"alias_kind":"arxiv_version","alias_value":"2606.12871v1","created_at":"2026-06-12T01:08:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.12871","created_at":"2026-06-12T01:08:56Z"},{"alias_kind":"pith_short_12","alias_value":"SZMFKUZCJGDF","created_at":"2026-06-12T01:08:56Z"},{"alias_kind":"pith_short_16","alias_value":"SZMFKUZCJGDFJXXU","created_at":"2026-06-12T01:08:56Z"},{"alias_kind":"pith_short_8","alias_value":"SZMFKUZC","created_at":"2026-06-12T01:08:56Z"}],"graph_snapshots":[{"event_id":"sha256:78d909827e419531c91ed9b134fceae353ddf8c7563e305c7bfdb8ec4ed1b3e7","target":"graph","created_at":"2026-06-12T01:08:56Z","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/2606.12871/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jingxuan Han, Licheng Zhang, Lin Qiu, Mingyang Zhu, Wei Liu, Xuezhi Cao, Xunliang Cai, Youpeng Wang, Zhendong Mao, Zheren Fu, Ziwen Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-11T03:59:07Z","title":"DailyReport: An Open-ended Benchmark for Evaluating Search Agents on Daily Search Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.12871","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:e172f5c94fe14601218117f31ee35902f6087bedc8fe5310dbca50d929949538","target":"record","created_at":"2026-06-12T01:08:56Z","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":"744eb335ededfe60ef35546c23c8073abc87e140a87402a31a7fdc16b2845379","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-11T03:59:07Z","title_canon_sha256":"7d5dd9e0df3b6d7ed722e4c6a9b6791b02280ff442b434ad341e4a7d45006baf"},"schema_version":"1.0","source":{"id":"2606.12871","kind":"arxiv","version":1}},"canonical_sha256":"9658555322498654def409b3343749349903177958313418be1fdeeaf4afad6d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9658555322498654def409b3343749349903177958313418be1fdeeaf4afad6d","first_computed_at":"2026-06-12T01:08:56.009284Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-12T01:08:56.009284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GplgmiOrYE44OuQNLNsGZoSNjv2qJpwqn6dOQDCuZWd2FAVGb+Gvfx3GKDWSJLdfg5NNJ9uOzbkAcRAF/r05AQ==","signature_status":"signed_v1","signed_at":"2026-06-12T01:08:56.010080Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.12871","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e172f5c94fe14601218117f31ee35902f6087bedc8fe5310dbca50d929949538","sha256:78d909827e419531c91ed9b134fceae353ddf8c7563e305c7bfdb8ec4ed1b3e7"],"state_sha256":"f905ccbffd010bcf265ae71728d292bf13aebe4f1c6ec09af574a4973a4fe328"}