{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:V3CLH7PVJPJ4Z7PBJKB5OICTHZ","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":"4da52b22370cc42d66d7e26d452926fa09f3bb5229a9fccf6ee43159d9eac4cd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-22T06:03:01Z","title_canon_sha256":"389856e2432ee585770ad1eefc4b1fad9b43a8a99253133518620735ac3ec684"},"schema_version":"1.0","source":{"id":"2605.23262","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.23262","created_at":"2026-05-25T02:01:46Z"},{"alias_kind":"arxiv_version","alias_value":"2605.23262v1","created_at":"2026-05-25T02:01:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23262","created_at":"2026-05-25T02:01:46Z"},{"alias_kind":"pith_short_12","alias_value":"V3CLH7PVJPJ4","created_at":"2026-05-25T02:01:46Z"},{"alias_kind":"pith_short_16","alias_value":"V3CLH7PVJPJ4Z7PB","created_at":"2026-05-25T02:01:46Z"},{"alias_kind":"pith_short_8","alias_value":"V3CLH7PV","created_at":"2026-05-25T02:01:46Z"}],"graph_snapshots":[{"event_id":"sha256:8f939b3c07d9530800e52147ebffbf9ad8fa4fc8bc3d88582b043cc0f9ea9c64","target":"graph","created_at":"2026-05-25T02:01:46Z","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/2605.23262/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The development of LLM agents has led to a growing body of work on knowledge-work AI, including coding, research, and healthcare. However, current knowledge-work evaluation and benchmark design still largely follow the logic of traditional NLP tasks. As a result, higher benchmark performance does not reliably show that a system can carry out knowledge work in real-world deployment settings. This paper contributes a three-step approach for making explicit how benchmarked tasks represent the work claims attached to their scores: defining the work activity under evaluation, specifying the tested ","authors_text":"Cyrus Ayubcha, Hongbin Na, Levi Lian, Yining Hua","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-22T06:03:01Z","title":"Design and Report Benchmarks for Knowledge Work"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23262","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":"sha256:0cb2727b2b559430b027091cf2277d6f22b09879743bad2fa56229e25c46c125","target":"record","created_at":"2026-05-25T02:01:46Z","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":"4da52b22370cc42d66d7e26d452926fa09f3bb5229a9fccf6ee43159d9eac4cd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-22T06:03:01Z","title_canon_sha256":"389856e2432ee585770ad1eefc4b1fad9b43a8a99253133518620735ac3ec684"},"schema_version":"1.0","source":{"id":"2605.23262","kind":"arxiv","version":1}},"canonical_sha256":"aec4b3fdf54bd3ccfde14a83d720533e79a0bd4362ea335475d5532728d8d549","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aec4b3fdf54bd3ccfde14a83d720533e79a0bd4362ea335475d5532728d8d549","first_computed_at":"2026-05-25T02:01:46.253990Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-25T02:01:46.253990Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UG3NlxT6Re5D4i1fjhzsy4spY8Iq7TdFUc5GWOPlkAmtrB7z90pFTXyAnWLdRETSjXTDr/Rlpw/DckvNbLwnCg==","signature_status":"signed_v1","signed_at":"2026-05-25T02:01:46.254829Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.23262","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0cb2727b2b559430b027091cf2277d6f22b09879743bad2fa56229e25c46c125","sha256:8f939b3c07d9530800e52147ebffbf9ad8fa4fc8bc3d88582b043cc0f9ea9c64"],"state_sha256":"2cdd247a0c3adaacc1517058c992e49e46af9089d63fd936847c8f18b876bb8a"}