{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:3JIWLAUTGURF2JQDFH747QTYTT","short_pith_number":"pith:3JIWLAUT","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"},"canonical_sha256":"da5165829335225d260329ffcfc2789cee5bbc0ea58d04d5263aaeb46a2ddf48","source":{"kind":"arxiv","id":"2605.27882","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.27882","created_at":"2026-05-28T01:04:51Z"},{"alias_kind":"arxiv_version","alias_value":"2605.27882v1","created_at":"2026-05-28T01:04:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27882","created_at":"2026-05-28T01:04:51Z"},{"alias_kind":"pith_short_12","alias_value":"3JIWLAUTGURF","created_at":"2026-05-28T01:04:51Z"},{"alias_kind":"pith_short_16","alias_value":"3JIWLAUTGURF2JQD","created_at":"2026-05-28T01:04:51Z"},{"alias_kind":"pith_short_8","alias_value":"3JIWLAUT","created_at":"2026-05-28T01:04:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:3JIWLAUTGURF2JQDFH747QTYTT","target":"record","payload":{"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"},"canonical_sha256":"da5165829335225d260329ffcfc2789cee5bbc0ea58d04d5263aaeb46a2ddf48","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"},"source_kind":"arxiv","source_id":"2605.27882","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-28T01:04:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PbhKccwNRsRIrf51TesPZQTn+RUo65y6E/SvfFMlxwgPCaCci7EU/bjraKYlmilzVa/2KTqg9wic/EmT6ymeCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T20:42:52.831479Z"},"content_sha256":"2bfe81889ce67229297c3aceae19bffdc96677dacace877dbb3e310bfa976822","schema_version":"1.0","event_id":"sha256:2bfe81889ce67229297c3aceae19bffdc96677dacace877dbb3e310bfa976822"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:3JIWLAUTGURF2JQDFH747QTYTT","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-28T01:04:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kVSVDhDb58k/E2W+mitFyDk0RrGneOP7SkBprYEf/crzzJAgI0jUYtb0mjUMUa30bK7tCzGPXRXKx+mUhEgRCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T20:42:52.831854Z"},"content_sha256":"c2a884a9e58650db403e161d7b943d770c41deb9d1f8e474c057cc4e793c9af8","schema_version":"1.0","event_id":"sha256:c2a884a9e58650db403e161d7b943d770c41deb9d1f8e474c057cc4e793c9af8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3JIWLAUTGURF2JQDFH747QTYTT/bundle.json","state_url":"https://pith.science/pith/3JIWLAUTGURF2JQDFH747QTYTT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3JIWLAUTGURF2JQDFH747QTYTT/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-29T20:42:52Z","links":{"resolver":"https://pith.science/pith/3JIWLAUTGURF2JQDFH747QTYTT","bundle":"https://pith.science/pith/3JIWLAUTGURF2JQDFH747QTYTT/bundle.json","state":"https://pith.science/pith/3JIWLAUTGURF2JQDFH747QTYTT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3JIWLAUTGURF2JQDFH747QTYTT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3JIWLAUTGURF2JQDFH747QTYTT","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":"808dd195511b4865a37bf81b192488dee8cc93f7b24aab6a363545ea1969be86","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-27T03:06:18Z","title_canon_sha256":"abd118fdbf33e3b2c61f99dc92e2653a468a629b2b2479b904f2876b2b05b8e2"},"schema_version":"1.0","source":{"id":"2605.27882","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.27882","created_at":"2026-05-28T01:04:51Z"},{"alias_kind":"arxiv_version","alias_value":"2605.27882v1","created_at":"2026-05-28T01:04:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27882","created_at":"2026-05-28T01:04:51Z"},{"alias_kind":"pith_short_12","alias_value":"3JIWLAUTGURF","created_at":"2026-05-28T01:04:51Z"},{"alias_kind":"pith_short_16","alias_value":"3JIWLAUTGURF2JQD","created_at":"2026-05-28T01:04:51Z"},{"alias_kind":"pith_short_8","alias_value":"3JIWLAUT","created_at":"2026-05-28T01:04:51Z"}],"graph_snapshots":[{"event_id":"sha256:c2a884a9e58650db403e161d7b943d770c41deb9d1f8e474c057cc4e793c9af8","target":"graph","created_at":"2026-05-28T01:04:51Z","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/2605.27882/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Xiaohongshu Inc","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-27T03:06:18Z","title":"VibeSearchBench: Benchmarking Long-horizon Proactive Search in the Wild"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27882","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":"sha256:2bfe81889ce67229297c3aceae19bffdc96677dacace877dbb3e310bfa976822","target":"record","created_at":"2026-05-28T01:04:51Z","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":"808dd195511b4865a37bf81b192488dee8cc93f7b24aab6a363545ea1969be86","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-27T03:06:18Z","title_canon_sha256":"abd118fdbf33e3b2c61f99dc92e2653a468a629b2b2479b904f2876b2b05b8e2"},"schema_version":"1.0","source":{"id":"2605.27882","kind":"arxiv","version":1}},"canonical_sha256":"da5165829335225d260329ffcfc2789cee5bbc0ea58d04d5263aaeb46a2ddf48","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"da5165829335225d260329ffcfc2789cee5bbc0ea58d04d5263aaeb46a2ddf48","first_computed_at":"2026-05-28T01:04:51.181960Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T01:04:51.181960Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iwDpP94gu3N0nQkUEzYLfHxCGEAFCAcaKpe6hIObRfdEPgZV+dZD3OaQwbvpJLxa+Eq0Louk96Ost+xigi2CAQ==","signature_status":"signed_v1","signed_at":"2026-05-28T01:04:51.182336Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.27882","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2bfe81889ce67229297c3aceae19bffdc96677dacace877dbb3e310bfa976822","sha256:c2a884a9e58650db403e161d7b943d770c41deb9d1f8e474c057cc4e793c9af8"],"state_sha256":"c09cb69f120dd0517c3240c076d556245170baf5fe9f6688190943779cbb9893"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r3LhndgRFPK/BW1FWTeLs7DBUpiNsYhLgoDbLFsev2p3+OgdTPa7r+nxiw48qZXPczx7a68egIjTAKBYt8zuAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-29T20:42:52.833854Z","bundle_sha256":"b5752ec5cf60b15decf24a8afc16724de77a10599b65d9fb293f1a7b5983b737"}}