{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EEVNLC5AG2MVX3KAXGOOSJECKR","short_pith_number":"pith:EEVNLC5A","schema_version":"1.0","canonical_sha256":"212ad58ba036995bed40b99ce924825453518d7f8c06f040db5c37de6486abd2","source":{"kind":"arxiv","id":"2606.29955","version":1},"attestation_state":"computed","paper":{"title":"SpreadsheetBench 2: Evaluating Agents on End-to-End Business Spreadsheet Workflows","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Abhiram Chundru, Armin Schoepf, Bohan Zhang, Daniel Woloch, Guangyu Robert Yang, Jean Lin, Jian Zhu, Jing Zhang, Peter Yiliu Wang, Samuel Jacob, Siddharth Nagisetty, Spencer Mateega, Yuzheng Zhang, Zeyao Ma","submitted_at":"2026-06-29T08:33:52Z","abstract_excerpt":"Spreadsheets are widely used for business analysis, financial modeling, reporting, and decision-making. However, most existing spreadsheet benchmarks evaluate isolated operations such as single-formula generation or local cell edits, and therefore fail to capture end-to-end workflows in realistic business settings. We introduce \\textsc{SpreadsheetBench 2}, a workflow-level benchmark for spreadsheet agents that covers three task categories: generation, debugging, and visualization. The benchmark is constructed from authentic business data, including financial reports and corporate filings, and "},"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":"2606.29955","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2026-06-29T08:33:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bc411b29caf3411a157888c5e05f6c824a89f1d465b4778f0471d3e97157eb87","abstract_canon_sha256":"c9b40edde5cfcc50670b221e4b0d2238ff2c3ba3e306c4cde36ab2f121a9285f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:17:42.615619Z","signature_b64":"Agkquhi9KFcMukExp3ecw2NeggOSYKBVhpxm2P+0FxQsuXfanPYcAbAUlgajoQ97fMkkyK14vFDK3B8fVbxBAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"212ad58ba036995bed40b99ce924825453518d7f8c06f040db5c37de6486abd2","last_reissued_at":"2026-06-30T02:17:42.614912Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:17:42.614912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SpreadsheetBench 2: Evaluating Agents on End-to-End Business Spreadsheet Workflows","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Abhiram Chundru, Armin Schoepf, Bohan Zhang, Daniel Woloch, Guangyu Robert Yang, Jean Lin, Jian Zhu, Jing Zhang, Peter Yiliu Wang, Samuel Jacob, Siddharth Nagisetty, Spencer Mateega, Yuzheng Zhang, Zeyao Ma","submitted_at":"2026-06-29T08:33:52Z","abstract_excerpt":"Spreadsheets are widely used for business analysis, financial modeling, reporting, and decision-making. However, most existing spreadsheet benchmarks evaluate isolated operations such as single-formula generation or local cell edits, and therefore fail to capture end-to-end workflows in realistic business settings. We introduce \\textsc{SpreadsheetBench 2}, a workflow-level benchmark for spreadsheet agents that covers three task categories: generation, debugging, and visualization. The benchmark is constructed from authentic business data, including financial reports and corporate filings, and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29955","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/2606.29955/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":"2606.29955","created_at":"2026-06-30T02:17:42.614993+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.29955v1","created_at":"2026-06-30T02:17:42.614993+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29955","created_at":"2026-06-30T02:17:42.614993+00:00"},{"alias_kind":"pith_short_12","alias_value":"EEVNLC5AG2MV","created_at":"2026-06-30T02:17:42.614993+00:00"},{"alias_kind":"pith_short_16","alias_value":"EEVNLC5AG2MVX3KA","created_at":"2026-06-30T02:17:42.614993+00:00"},{"alias_kind":"pith_short_8","alias_value":"EEVNLC5A","created_at":"2026-06-30T02:17:42.614993+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/EEVNLC5AG2MVX3KAXGOOSJECKR","json":"https://pith.science/pith/EEVNLC5AG2MVX3KAXGOOSJECKR.json","graph_json":"https://pith.science/api/pith-number/EEVNLC5AG2MVX3KAXGOOSJECKR/graph.json","events_json":"https://pith.science/api/pith-number/EEVNLC5AG2MVX3KAXGOOSJECKR/events.json","paper":"https://pith.science/paper/EEVNLC5A"},"agent_actions":{"view_html":"https://pith.science/pith/EEVNLC5AG2MVX3KAXGOOSJECKR","download_json":"https://pith.science/pith/EEVNLC5AG2MVX3KAXGOOSJECKR.json","view_paper":"https://pith.science/paper/EEVNLC5A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.29955&json=true","fetch_graph":"https://pith.science/api/pith-number/EEVNLC5AG2MVX3KAXGOOSJECKR/graph.json","fetch_events":"https://pith.science/api/pith-number/EEVNLC5AG2MVX3KAXGOOSJECKR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EEVNLC5AG2MVX3KAXGOOSJECKR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EEVNLC5AG2MVX3KAXGOOSJECKR/action/storage_attestation","attest_author":"https://pith.science/pith/EEVNLC5AG2MVX3KAXGOOSJECKR/action/author_attestation","sign_citation":"https://pith.science/pith/EEVNLC5AG2MVX3KAXGOOSJECKR/action/citation_signature","submit_replication":"https://pith.science/pith/EEVNLC5AG2MVX3KAXGOOSJECKR/action/replication_record"}},"created_at":"2026-06-30T02:17:42.614993+00:00","updated_at":"2026-06-30T02:17:42.614993+00:00"}