{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VP7OFQOKINDXO3UOOQNYCBK72E","short_pith_number":"pith:VP7OFQOK","schema_version":"1.0","canonical_sha256":"abfee2c1ca4347776e8e741b81055fd100360fe835e47533f877101c69573340","source":{"kind":"arxiv","id":"2603.10002","version":2},"attestation_state":"computed","paper":{"title":"SpreadsheetArena: Decomposing Preference in LLM Generation of Spreadsheet Workbooks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chen Bo Calvin Zhang, Clara Na, Emma Strubell, John Ling, Manasi Sharma, Michael Handley, Srivatsa Kundurthy, Zach Kirshner","submitted_at":"2026-02-16T14:24:36Z","abstract_excerpt":"We consider the task of end-to-end spreadsheet generation, where language models produce spreadsheet artifacts to satisfy users' explicit and implicit constraints, specified in natural language. We introduce SpreadsheetArena, a platform for evaluating models' performance on the task via blind pairwise preference votes of LLM-generated spreadsheet workbooks. As with other complex, open-ended tasks, relevant evaluation criteria can vary greatly across use cases, often in ways that are difficult to formalize. Compared to general dialogue or text generation settings, spreadsheet generation present"},"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":"2603.10002","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-16T14:24:36Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"bd1163caf9bfaae6c93e30106421afd24c89fea715ec6f054c45770237a022d5","abstract_canon_sha256":"0b077f21dbc2e868db9261bcf204a27dcde851810dadb4c9ded8d1a5f6e49aad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T00:15:53.377368Z","signature_b64":"SNdlZzWrZe1iqJ96lyzf4fDCKcQCOIUTF5LwQpYhlf/HRDtjvC9au3E43gH+QbgPosmA7kwj1BdDWU1ZT03nDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"abfee2c1ca4347776e8e741b81055fd100360fe835e47533f877101c69573340","last_reissued_at":"2026-07-07T00:15:53.376255Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T00:15:53.376255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SpreadsheetArena: Decomposing Preference in LLM Generation of Spreadsheet Workbooks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chen Bo Calvin Zhang, Clara Na, Emma Strubell, John Ling, Manasi Sharma, Michael Handley, Srivatsa Kundurthy, Zach Kirshner","submitted_at":"2026-02-16T14:24:36Z","abstract_excerpt":"We consider the task of end-to-end spreadsheet generation, where language models produce spreadsheet artifacts to satisfy users' explicit and implicit constraints, specified in natural language. We introduce SpreadsheetArena, a platform for evaluating models' performance on the task via blind pairwise preference votes of LLM-generated spreadsheet workbooks. As with other complex, open-ended tasks, relevant evaluation criteria can vary greatly across use cases, often in ways that are difficult to formalize. Compared to general dialogue or text generation settings, spreadsheet generation present"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.10002","kind":"arxiv","version":2},"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/2603.10002/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":"2603.10002","created_at":"2026-07-07T00:15:53.376398+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.10002v2","created_at":"2026-07-07T00:15:53.376398+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.10002","created_at":"2026-07-07T00:15:53.376398+00:00"},{"alias_kind":"pith_short_12","alias_value":"VP7OFQOKINDX","created_at":"2026-07-07T00:15:53.376398+00:00"},{"alias_kind":"pith_short_16","alias_value":"VP7OFQOKINDXO3UO","created_at":"2026-07-07T00:15:53.376398+00:00"},{"alias_kind":"pith_short_8","alias_value":"VP7OFQOK","created_at":"2026-07-07T00:15:53.376398+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.30907","citing_title":"BlueFin: Benchmarking LLM Agents on Financial Spreadsheets","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VP7OFQOKINDXO3UOOQNYCBK72E","json":"https://pith.science/pith/VP7OFQOKINDXO3UOOQNYCBK72E.json","graph_json":"https://pith.science/api/pith-number/VP7OFQOKINDXO3UOOQNYCBK72E/graph.json","events_json":"https://pith.science/api/pith-number/VP7OFQOKINDXO3UOOQNYCBK72E/events.json","paper":"https://pith.science/paper/VP7OFQOK"},"agent_actions":{"view_html":"https://pith.science/pith/VP7OFQOKINDXO3UOOQNYCBK72E","download_json":"https://pith.science/pith/VP7OFQOKINDXO3UOOQNYCBK72E.json","view_paper":"https://pith.science/paper/VP7OFQOK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.10002&json=true","fetch_graph":"https://pith.science/api/pith-number/VP7OFQOKINDXO3UOOQNYCBK72E/graph.json","fetch_events":"https://pith.science/api/pith-number/VP7OFQOKINDXO3UOOQNYCBK72E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VP7OFQOKINDXO3UOOQNYCBK72E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VP7OFQOKINDXO3UOOQNYCBK72E/action/storage_attestation","attest_author":"https://pith.science/pith/VP7OFQOKINDXO3UOOQNYCBK72E/action/author_attestation","sign_citation":"https://pith.science/pith/VP7OFQOKINDXO3UOOQNYCBK72E/action/citation_signature","submit_replication":"https://pith.science/pith/VP7OFQOKINDXO3UOOQNYCBK72E/action/replication_record"}},"created_at":"2026-07-07T00:15:53.376398+00:00","updated_at":"2026-07-07T00:15:53.376398+00:00"}