{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FLJ2NOJIRYLVISLHM3XGLQF5PF","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":"0fd3301c77baf0e06d0e7607b8a5a1f9026a5e61c2a54a2bc23a714ed44a4c24","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-11T09:48:32Z","title_canon_sha256":"ea85a3a01daafc2e64b92fea9d7b3ea9b855e100c5d40aad91c0c9bc3380cc9d"},"schema_version":"1.0","source":{"id":"2606.13120","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.13120","created_at":"2026-06-12T01:09:41Z"},{"alias_kind":"arxiv_version","alias_value":"2606.13120v1","created_at":"2026-06-12T01:09:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.13120","created_at":"2026-06-12T01:09:41Z"},{"alias_kind":"pith_short_12","alias_value":"FLJ2NOJIRYLV","created_at":"2026-06-12T01:09:41Z"},{"alias_kind":"pith_short_16","alias_value":"FLJ2NOJIRYLVISLH","created_at":"2026-06-12T01:09:41Z"},{"alias_kind":"pith_short_8","alias_value":"FLJ2NOJI","created_at":"2026-06-12T01:09:41Z"}],"graph_snapshots":[{"event_id":"sha256:f2400282dae982027916b0824d35cf8ad0b7e803c81e8ce79e5398ebe21e3f9b","target":"graph","created_at":"2026-06-12T01:09:41Z","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/2606.13120/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Search Agents -- large language models augmented with search tools -- have intensified the need for future-proof evaluation benchmarks. Existing benchmarks such as BrowseComp rely on static knowledge, making them vulnerable to test-set contamination and parametric memorization. Consequently, models can achieve high scores through fact recall rather than genuine retrieval, obscuring true browsing competence via reasoning shortcuts.\n  In this paper, we introduce EvoBrowseComp, an evolving benchmark of 400 English and 400 Chinese contamination-free complex questions synthesized via live-web trave","authors_text":"Fandong Meng, Jiaan Wang, Lianzhe Huang, Xianfeng Zeng, Yunhan Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-11T09:48:32Z","title":"EvoBrowseComp: Benchmarking Search Agents on Evolving Knowledge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.13120","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:c4b32bc87857396a53a7d3ea2fd44fe6d981694757b64b369583d11173acc846","target":"record","created_at":"2026-06-12T01:09:41Z","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":"0fd3301c77baf0e06d0e7607b8a5a1f9026a5e61c2a54a2bc23a714ed44a4c24","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-11T09:48:32Z","title_canon_sha256":"ea85a3a01daafc2e64b92fea9d7b3ea9b855e100c5d40aad91c0c9bc3380cc9d"},"schema_version":"1.0","source":{"id":"2606.13120","kind":"arxiv","version":1}},"canonical_sha256":"2ad3a6b9288e1754496766ee65c0bd797aea14c76df544d467c477a440314bb6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2ad3a6b9288e1754496766ee65c0bd797aea14c76df544d467c477a440314bb6","first_computed_at":"2026-06-12T01:09:41.366970Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-12T01:09:41.366970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"54BjyTgoBlAKKHRJIurHj8Kc0TmoOexm+t1NFRdvphIK2+sQrCTXxNz1FddGRZEAnQXlj4AiijsaKWrfwzVuDw==","signature_status":"signed_v1","signed_at":"2026-06-12T01:09:41.367869Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.13120","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c4b32bc87857396a53a7d3ea2fd44fe6d981694757b64b369583d11173acc846","sha256:f2400282dae982027916b0824d35cf8ad0b7e803c81e8ce79e5398ebe21e3f9b"],"state_sha256":"f28da06eb3f3e9085822c66bf5a46bf38813458669c4d9ec7b64be241ef0888c"}