{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LAN5VRYUQT5HM65KPEPCELB2MB","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":"99c74a2347006b255e71fef678f25778aaedb235b5ac95748f3749b014f76b58","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-03-10T23:50:30Z","title_canon_sha256":"81bae4ef1a8f07830b7bd25284e47cebed3404cd463a650b36ec2b46dee47dde"},"schema_version":"1.0","source":{"id":"2503.07919","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.07919","created_at":"2026-07-05T11:42:27Z"},{"alias_kind":"arxiv_version","alias_value":"2503.07919v3","created_at":"2026-07-05T11:42:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.07919","created_at":"2026-07-05T11:42:27Z"},{"alias_kind":"pith_short_12","alias_value":"LAN5VRYUQT5H","created_at":"2026-07-05T11:42:27Z"},{"alias_kind":"pith_short_16","alias_value":"LAN5VRYUQT5HM65K","created_at":"2026-07-05T11:42:27Z"},{"alias_kind":"pith_short_8","alias_value":"LAN5VRYU","created_at":"2026-07-05T11:42:27Z"}],"graph_snapshots":[{"event_id":"sha256:8b5b6cfcdc57b5f083d5817d1783ab01ac87b5bfa2470d3bad9ce0d691a6684d","target":"graph","created_at":"2026-07-05T11:42:27Z","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/2503.07919/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern web agents possess computer use abilities that allow them to interact with webpages by sending commands to a virtual keyboard and mouse. While such agents have considerable potential to assist human users with complex tasks, evaluating their capabilities in real-world settings poses a major challenge. To this end, we introduce BEARCUBS, a \"smallbut mighty\" benchmark of 111 information-seeking questions designed to evaluate a web agent's ability to search, browse, and identify factual information from the web. Unlike prior web agent benchmarks, solving BEARCUBS requires (1) accessing liv","authors_text":"Chau Minh Pham, Katherine Thai, Mazin Nadaf, Mohit Iyyer, Yapei Chang, Yixiao Song","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-03-10T23:50:30Z","title":"BEARCUBS: A benchmark for computer-using web agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.07919","kind":"arxiv","version":3},"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":"sha256:00e997458ca8af09729df886512d1cfe15970bfdf39f5a76aab85a90d0d994e9","target":"record","created_at":"2026-07-05T11:42:27Z","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":"99c74a2347006b255e71fef678f25778aaedb235b5ac95748f3749b014f76b58","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-03-10T23:50:30Z","title_canon_sha256":"81bae4ef1a8f07830b7bd25284e47cebed3404cd463a650b36ec2b46dee47dde"},"schema_version":"1.0","source":{"id":"2503.07919","kind":"arxiv","version":3}},"canonical_sha256":"581bdac71484fa767baa791e222c3a606ec321fed3bfbaa56a89988590ed42e9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"581bdac71484fa767baa791e222c3a606ec321fed3bfbaa56a89988590ed42e9","first_computed_at":"2026-07-05T11:42:27.047927Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:42:27.047927Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bHwkpdcridjX+pv6pVibHvZPQ9Sw9FU2rnGnIyL1ujBWpw8BsBa0GSzg6rfBBCewk1S0FZslnNKfPz0YHd7yBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:42:27.048434Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.07919","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:00e997458ca8af09729df886512d1cfe15970bfdf39f5a76aab85a90d0d994e9","sha256:8b5b6cfcdc57b5f083d5817d1783ab01ac87b5bfa2470d3bad9ce0d691a6684d"],"state_sha256":"f07efded34bc6789b0c4b4adeef86342a45139debd26d51915b3bd11490f8598"}