{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:V3CLH7PVJPJ4Z7PBJKB5OICTHZ","short_pith_number":"pith:V3CLH7PV","schema_version":"1.0","canonical_sha256":"aec4b3fdf54bd3ccfde14a83d720533e79a0bd4362ea335475d5532728d8d549","source":{"kind":"arxiv","id":"2605.23262","version":1},"attestation_state":"computed","paper":{"title":"Design and Report Benchmarks for Knowledge Work","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Cyrus Ayubcha, Hongbin Na, Levi Lian, Yining Hua","submitted_at":"2026-05-22T06:03:01Z","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 "},"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":"2605.23262","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-22T06:03:01Z","cross_cats_sorted":[],"title_canon_sha256":"389856e2432ee585770ad1eefc4b1fad9b43a8a99253133518620735ac3ec684","abstract_canon_sha256":"4da52b22370cc42d66d7e26d452926fa09f3bb5229a9fccf6ee43159d9eac4cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:01:46.254829Z","signature_b64":"UG3NlxT6Re5D4i1fjhzsy4spY8Iq7TdFUc5GWOPlkAmtrB7z90pFTXyAnWLdRETSjXTDr/Rlpw/DckvNbLwnCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aec4b3fdf54bd3ccfde14a83d720533e79a0bd4362ea335475d5532728d8d549","last_reissued_at":"2026-05-25T02:01:46.253990Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:01:46.253990Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Design and Report Benchmarks for Knowledge Work","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Cyrus Ayubcha, Hongbin Na, Levi Lian, Yining Hua","submitted_at":"2026-05-22T06:03:01Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23262","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/2605.23262/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":"2605.23262","created_at":"2026-05-25T02:01:46.254150+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.23262v1","created_at":"2026-05-25T02:01:46.254150+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23262","created_at":"2026-05-25T02:01:46.254150+00:00"},{"alias_kind":"pith_short_12","alias_value":"V3CLH7PVJPJ4","created_at":"2026-05-25T02:01:46.254150+00:00"},{"alias_kind":"pith_short_16","alias_value":"V3CLH7PVJPJ4Z7PB","created_at":"2026-05-25T02:01:46.254150+00:00"},{"alias_kind":"pith_short_8","alias_value":"V3CLH7PV","created_at":"2026-05-25T02:01:46.254150+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/V3CLH7PVJPJ4Z7PBJKB5OICTHZ","json":"https://pith.science/pith/V3CLH7PVJPJ4Z7PBJKB5OICTHZ.json","graph_json":"https://pith.science/api/pith-number/V3CLH7PVJPJ4Z7PBJKB5OICTHZ/graph.json","events_json":"https://pith.science/api/pith-number/V3CLH7PVJPJ4Z7PBJKB5OICTHZ/events.json","paper":"https://pith.science/paper/V3CLH7PV"},"agent_actions":{"view_html":"https://pith.science/pith/V3CLH7PVJPJ4Z7PBJKB5OICTHZ","download_json":"https://pith.science/pith/V3CLH7PVJPJ4Z7PBJKB5OICTHZ.json","view_paper":"https://pith.science/paper/V3CLH7PV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.23262&json=true","fetch_graph":"https://pith.science/api/pith-number/V3CLH7PVJPJ4Z7PBJKB5OICTHZ/graph.json","fetch_events":"https://pith.science/api/pith-number/V3CLH7PVJPJ4Z7PBJKB5OICTHZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V3CLH7PVJPJ4Z7PBJKB5OICTHZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V3CLH7PVJPJ4Z7PBJKB5OICTHZ/action/storage_attestation","attest_author":"https://pith.science/pith/V3CLH7PVJPJ4Z7PBJKB5OICTHZ/action/author_attestation","sign_citation":"https://pith.science/pith/V3CLH7PVJPJ4Z7PBJKB5OICTHZ/action/citation_signature","submit_replication":"https://pith.science/pith/V3CLH7PVJPJ4Z7PBJKB5OICTHZ/action/replication_record"}},"created_at":"2026-05-25T02:01:46.254150+00:00","updated_at":"2026-05-25T02:01:46.254150+00:00"}