{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JG76IPARX4JQ5WAOKQN56GH6DV","short_pith_number":"pith:JG76IPAR","schema_version":"1.0","canonical_sha256":"49bfe43c11bf130ed80e541bdf18fe1d6e10ec28de7f815075ea00ae7255915d","source":{"kind":"arxiv","id":"2508.11715","version":1},"attestation_state":"computed","paper":{"title":"Benchmark Dataset Generation and Evaluation for Excel Formula Repair with LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Ananya Singha, Chaya Binet, Emmanuel Aboah Boateng, Harshita Sahijwani, Keegan Choudhury, Miguel Di Luca, Nick Hausman, Oryan Rokeah Chen, Sadid Hasan, Sulaiman Vesal, Tianwei Chen, Vu Le, Walt Williams","submitted_at":"2025-08-14T16:43:35Z","abstract_excerpt":"Excel is a pervasive yet often complex tool, particularly for novice users, where runtime errors arising from logical mistakes or misinterpretations of functions pose a significant challenge. While large language models (LLMs) offer promising assistance by explaining formula errors, the automated correction of these semantic runtime errors remains an open problem. A primary challenge to advancing models for such scenarios is the severe lack of high-quality, comprehensive datasets for training and rigorous evaluation. This paper addresses this gap by introducing a novel approach for constructin"},"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":"2508.11715","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-08-14T16:43:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"11c82f29f3f207414cb176ebf6435d76f9b5f90c93035d7a304fe8fecc2ce841","abstract_canon_sha256":"145c6628a3da7043130d2823240baa151bf19d80bb6c420da1fbadf515e02460"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:52.961799Z","signature_b64":"K3yAFgT6TghALcmMOKItrusbGbz/AN2noM1Q5/zrhqsV+XcmuskYlqjmXorlPcrmtf9Dzehp1z8LD6Y3yZmcAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"49bfe43c11bf130ed80e541bdf18fe1d6e10ec28de7f815075ea00ae7255915d","last_reissued_at":"2026-07-05T11:54:52.961346Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:52.961346Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmark Dataset Generation and Evaluation for Excel Formula Repair with LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Ananya Singha, Chaya Binet, Emmanuel Aboah Boateng, Harshita Sahijwani, Keegan Choudhury, Miguel Di Luca, Nick Hausman, Oryan Rokeah Chen, Sadid Hasan, Sulaiman Vesal, Tianwei Chen, Vu Le, Walt Williams","submitted_at":"2025-08-14T16:43:35Z","abstract_excerpt":"Excel is a pervasive yet often complex tool, particularly for novice users, where runtime errors arising from logical mistakes or misinterpretations of functions pose a significant challenge. While large language models (LLMs) offer promising assistance by explaining formula errors, the automated correction of these semantic runtime errors remains an open problem. A primary challenge to advancing models for such scenarios is the severe lack of high-quality, comprehensive datasets for training and rigorous evaluation. This paper addresses this gap by introducing a novel approach for constructin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.11715","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/2508.11715/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":"2508.11715","created_at":"2026-07-05T11:54:52.961405+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.11715v1","created_at":"2026-07-05T11:54:52.961405+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.11715","created_at":"2026-07-05T11:54:52.961405+00:00"},{"alias_kind":"pith_short_12","alias_value":"JG76IPARX4JQ","created_at":"2026-07-05T11:54:52.961405+00:00"},{"alias_kind":"pith_short_16","alias_value":"JG76IPARX4JQ5WAO","created_at":"2026-07-05T11:54:52.961405+00:00"},{"alias_kind":"pith_short_8","alias_value":"JG76IPAR","created_at":"2026-07-05T11:54:52.961405+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/JG76IPARX4JQ5WAOKQN56GH6DV","json":"https://pith.science/pith/JG76IPARX4JQ5WAOKQN56GH6DV.json","graph_json":"https://pith.science/api/pith-number/JG76IPARX4JQ5WAOKQN56GH6DV/graph.json","events_json":"https://pith.science/api/pith-number/JG76IPARX4JQ5WAOKQN56GH6DV/events.json","paper":"https://pith.science/paper/JG76IPAR"},"agent_actions":{"view_html":"https://pith.science/pith/JG76IPARX4JQ5WAOKQN56GH6DV","download_json":"https://pith.science/pith/JG76IPARX4JQ5WAOKQN56GH6DV.json","view_paper":"https://pith.science/paper/JG76IPAR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.11715&json=true","fetch_graph":"https://pith.science/api/pith-number/JG76IPARX4JQ5WAOKQN56GH6DV/graph.json","fetch_events":"https://pith.science/api/pith-number/JG76IPARX4JQ5WAOKQN56GH6DV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JG76IPARX4JQ5WAOKQN56GH6DV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JG76IPARX4JQ5WAOKQN56GH6DV/action/storage_attestation","attest_author":"https://pith.science/pith/JG76IPARX4JQ5WAOKQN56GH6DV/action/author_attestation","sign_citation":"https://pith.science/pith/JG76IPARX4JQ5WAOKQN56GH6DV/action/citation_signature","submit_replication":"https://pith.science/pith/JG76IPARX4JQ5WAOKQN56GH6DV/action/replication_record"}},"created_at":"2026-07-05T11:54:52.961405+00:00","updated_at":"2026-07-05T11:54:52.961405+00:00"}