{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3JIWLAUTGURF2JQDFH747QTYTT","short_pith_number":"pith:3JIWLAUT","schema_version":"1.0","canonical_sha256":"da5165829335225d260329ffcfc2789cee5bbc0ea58d04d5263aaeb46a2ddf48","source":{"kind":"arxiv","id":"2605.27882","version":1},"attestation_state":"computed","paper":{"title":"VibeSearchBench: Benchmarking Long-horizon Proactive Search in the Wild","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Xiaohongshu Inc","submitted_at":"2026-05-27T03:06:18Z","abstract_excerpt":"LLM-based agents score well on search benchmarks, yet real users consistently find results unsatisfying, revealing a persistent evaluation-experience gap. We attribute this gap to existing benchmarks' reliance on over-specified queries, single-turn interactions, and fixed-schema evaluation, none of which reflect real search behavior where users and agents collaboratively refine vague intent through multi-turn dialogue. We term this paradigm VibeSearch and introduce VibeSearchBench, a benchmark comprising 200 manually curated bilingual (Chinese and English) tasks across 20 domains, split into V"},"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":"2605.27882","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-27T03:06:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"abd118fdbf33e3b2c61f99dc92e2653a468a629b2b2479b904f2876b2b05b8e2","abstract_canon_sha256":"808dd195511b4865a37bf81b192488dee8cc93f7b24aab6a363545ea1969be86"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:04:51.182336Z","signature_b64":"iwDpP94gu3N0nQkUEzYLfHxCGEAFCAcaKpe6hIObRfdEPgZV+dZD3OaQwbvpJLxa+Eq0Louk96Ost+xigi2CAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da5165829335225d260329ffcfc2789cee5bbc0ea58d04d5263aaeb46a2ddf48","last_reissued_at":"2026-05-28T01:04:51.181960Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:04:51.181960Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VibeSearchBench: Benchmarking Long-horizon Proactive Search in the Wild","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Xiaohongshu Inc","submitted_at":"2026-05-27T03:06:18Z","abstract_excerpt":"LLM-based agents score well on search benchmarks, yet real users consistently find results unsatisfying, revealing a persistent evaluation-experience gap. We attribute this gap to existing benchmarks' reliance on over-specified queries, single-turn interactions, and fixed-schema evaluation, none of which reflect real search behavior where users and agents collaboratively refine vague intent through multi-turn dialogue. We term this paradigm VibeSearch and introduce VibeSearchBench, a benchmark comprising 200 manually curated bilingual (Chinese and English) tasks across 20 domains, split into V"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27882","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/2605.27882/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":"2605.27882","created_at":"2026-05-28T01:04:51.182021+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.27882v1","created_at":"2026-05-28T01:04:51.182021+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27882","created_at":"2026-05-28T01:04:51.182021+00:00"},{"alias_kind":"pith_short_12","alias_value":"3JIWLAUTGURF","created_at":"2026-05-28T01:04:51.182021+00:00"},{"alias_kind":"pith_short_16","alias_value":"3JIWLAUTGURF2JQD","created_at":"2026-05-28T01:04:51.182021+00:00"},{"alias_kind":"pith_short_8","alias_value":"3JIWLAUT","created_at":"2026-05-28T01:04:51.182021+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/3JIWLAUTGURF2JQDFH747QTYTT","json":"https://pith.science/pith/3JIWLAUTGURF2JQDFH747QTYTT.json","graph_json":"https://pith.science/api/pith-number/3JIWLAUTGURF2JQDFH747QTYTT/graph.json","events_json":"https://pith.science/api/pith-number/3JIWLAUTGURF2JQDFH747QTYTT/events.json","paper":"https://pith.science/paper/3JIWLAUT"},"agent_actions":{"view_html":"https://pith.science/pith/3JIWLAUTGURF2JQDFH747QTYTT","download_json":"https://pith.science/pith/3JIWLAUTGURF2JQDFH747QTYTT.json","view_paper":"https://pith.science/paper/3JIWLAUT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.27882&json=true","fetch_graph":"https://pith.science/api/pith-number/3JIWLAUTGURF2JQDFH747QTYTT/graph.json","fetch_events":"https://pith.science/api/pith-number/3JIWLAUTGURF2JQDFH747QTYTT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3JIWLAUTGURF2JQDFH747QTYTT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3JIWLAUTGURF2JQDFH747QTYTT/action/storage_attestation","attest_author":"https://pith.science/pith/3JIWLAUTGURF2JQDFH747QTYTT/action/author_attestation","sign_citation":"https://pith.science/pith/3JIWLAUTGURF2JQDFH747QTYTT/action/citation_signature","submit_replication":"https://pith.science/pith/3JIWLAUTGURF2JQDFH747QTYTT/action/replication_record"}},"created_at":"2026-05-28T01:04:51.182021+00:00","updated_at":"2026-05-28T01:04:51.182021+00:00"}