{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:EEVNLC5AG2MVX3KAXGOOSJECKR","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":"c9b40edde5cfcc50670b221e4b0d2238ff2c3ba3e306c4cde36ab2f121a9285f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2026-06-29T08:33:52Z","title_canon_sha256":"bc411b29caf3411a157888c5e05f6c824a89f1d465b4778f0471d3e97157eb87"},"schema_version":"1.0","source":{"id":"2606.29955","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.29955","created_at":"2026-06-30T02:17:42Z"},{"alias_kind":"arxiv_version","alias_value":"2606.29955v1","created_at":"2026-06-30T02:17:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29955","created_at":"2026-06-30T02:17:42Z"},{"alias_kind":"pith_short_12","alias_value":"EEVNLC5AG2MV","created_at":"2026-06-30T02:17:42Z"},{"alias_kind":"pith_short_16","alias_value":"EEVNLC5AG2MVX3KA","created_at":"2026-06-30T02:17:42Z"},{"alias_kind":"pith_short_8","alias_value":"EEVNLC5A","created_at":"2026-06-30T02:17:42Z"}],"graph_snapshots":[{"event_id":"sha256:350c50b71857e88a5ebb514f6d523ff9e69fea410cab40d22291a493094b8c56","target":"graph","created_at":"2026-06-30T02:17:42Z","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/2606.29955/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","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","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2026-06-29T08:33:52Z","title":"SpreadsheetBench 2: Evaluating Agents on End-to-End Business Spreadsheet Workflows"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29955","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":"sha256:1394ce246b3d237fd5abe2bf36577bbc06d55a96898bfb31d281e7e769499375","target":"record","created_at":"2026-06-30T02:17:42Z","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":"c9b40edde5cfcc50670b221e4b0d2238ff2c3ba3e306c4cde36ab2f121a9285f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2026-06-29T08:33:52Z","title_canon_sha256":"bc411b29caf3411a157888c5e05f6c824a89f1d465b4778f0471d3e97157eb87"},"schema_version":"1.0","source":{"id":"2606.29955","kind":"arxiv","version":1}},"canonical_sha256":"212ad58ba036995bed40b99ce924825453518d7f8c06f040db5c37de6486abd2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"212ad58ba036995bed40b99ce924825453518d7f8c06f040db5c37de6486abd2","first_computed_at":"2026-06-30T02:17:42.614912Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T02:17:42.614912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Agkquhi9KFcMukExp3ecw2NeggOSYKBVhpxm2P+0FxQsuXfanPYcAbAUlgajoQ97fMkkyK14vFDK3B8fVbxBAA==","signature_status":"signed_v1","signed_at":"2026-06-30T02:17:42.615619Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.29955","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1394ce246b3d237fd5abe2bf36577bbc06d55a96898bfb31d281e7e769499375","sha256:350c50b71857e88a5ebb514f6d523ff9e69fea410cab40d22291a493094b8c56"],"state_sha256":"5f4279e8c5c94cc5c856e87bd1d5982d13f0a1677f1d0caf1c3e26e664712db1"}