{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VP7OFQOKINDXO3UOOQNYCBK72E","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":"0b077f21dbc2e868db9261bcf204a27dcde851810dadb4c9ded8d1a5f6e49aad","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-16T14:24:36Z","title_canon_sha256":"bd1163caf9bfaae6c93e30106421afd24c89fea715ec6f054c45770237a022d5"},"schema_version":"1.0","source":{"id":"2603.10002","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.10002","created_at":"2026-07-07T00:15:53Z"},{"alias_kind":"arxiv_version","alias_value":"2603.10002v2","created_at":"2026-07-07T00:15:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.10002","created_at":"2026-07-07T00:15:53Z"},{"alias_kind":"pith_short_12","alias_value":"VP7OFQOKINDX","created_at":"2026-07-07T00:15:53Z"},{"alias_kind":"pith_short_16","alias_value":"VP7OFQOKINDXO3UO","created_at":"2026-07-07T00:15:53Z"},{"alias_kind":"pith_short_8","alias_value":"VP7OFQOK","created_at":"2026-07-07T00:15:53Z"}],"graph_snapshots":[{"event_id":"sha256:357b9327ac046cf77fe2c25fb828c69d93abfb35308376bb62b0b8cc6da3e3bb","target":"graph","created_at":"2026-07-07T00:15:53Z","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/2603.10002/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chen Bo Calvin Zhang, Clara Na, Emma Strubell, John Ling, Manasi Sharma, Michael Handley, Srivatsa Kundurthy, Zach Kirshner","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-16T14:24:36Z","title":"SpreadsheetArena: Decomposing Preference in LLM Generation of Spreadsheet Workbooks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.10002","kind":"arxiv","version":2},"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":"sha256:45cf3019c147bf061a27d4e2b0d75a155a86298d21017013409cd427f67d2c10","target":"record","created_at":"2026-07-07T00:15:53Z","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":"0b077f21dbc2e868db9261bcf204a27dcde851810dadb4c9ded8d1a5f6e49aad","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-16T14:24:36Z","title_canon_sha256":"bd1163caf9bfaae6c93e30106421afd24c89fea715ec6f054c45770237a022d5"},"schema_version":"1.0","source":{"id":"2603.10002","kind":"arxiv","version":2}},"canonical_sha256":"abfee2c1ca4347776e8e741b81055fd100360fe835e47533f877101c69573340","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"abfee2c1ca4347776e8e741b81055fd100360fe835e47533f877101c69573340","first_computed_at":"2026-07-07T00:15:53.376255Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T00:15:53.376255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SNdlZzWrZe1iqJ96lyzf4fDCKcQCOIUTF5LwQpYhlf/HRDtjvC9au3E43gH+QbgPosmA7kwj1BdDWU1ZT03nDg==","signature_status":"signed_v1","signed_at":"2026-07-07T00:15:53.377368Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.10002","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:45cf3019c147bf061a27d4e2b0d75a155a86298d21017013409cd427f67d2c10","sha256:357b9327ac046cf77fe2c25fb828c69d93abfb35308376bb62b0b8cc6da3e3bb"],"state_sha256":"9ed9c7a09ae576864872308dccd5369587d117da26723d493eb6e388c45f21fe"}