{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LIUSTR6RUDCFGGBI6NUYCHY7V7","short_pith_number":"pith:LIUSTR6R","schema_version":"1.0","canonical_sha256":"5a2929c7d1a0c4531828f369811f1fafc70d31a38eeaf4e836d23562f4639185","source":{"kind":"arxiv","id":"2310.14495","version":1},"attestation_state":"computed","paper":{"title":"InstructExcel: A Benchmark for Natural Language Instruction in Excel","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Benjamin Van Durme, Carina Negreanu, Chitta Baral, Christian Poelitz, Elnaz Nouri, Justin Payan, Mukul Singh, Rasika Chakravarthy, Subhro Roy, Swaroop Mishra","submitted_at":"2023-10-23T02:00:55Z","abstract_excerpt":"With the evolution of Large Language Models (LLMs) we can solve increasingly more complex NLP tasks across various domains, including spreadsheets. This work investigates whether LLMs can generate code (Excel OfficeScripts, a TypeScript API for executing many tasks in Excel) that solves Excel specific tasks provided via natural language user instructions. To do so we introduce a new large-scale benchmark, InstructExcel, created by leveraging the 'Automate' feature in Excel to automatically generate OfficeScripts from users' actions. Our benchmark includes over 10k samples covering 170+ Excel o"},"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":"2310.14495","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-23T02:00:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"67fa5da0405eca4bb2a910f41b2fd5ecf80f32953ea04a1ffac9c20d96e23f1e","abstract_canon_sha256":"b28c71f7ba77039d517ff8ad3bfa56a99e28fed481653d16123499e6a2c537bb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:03:45.189441Z","signature_b64":"jdVH+X9bW4MB+IUSD65Cjnyt5TQ80Uc8i35/1Eoi1WRHS0kYBH5ElpeKG+/oj94ccJXgH8GwIaqXswhMlUCHCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a2929c7d1a0c4531828f369811f1fafc70d31a38eeaf4e836d23562f4639185","last_reissued_at":"2026-07-05T07:03:45.188945Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:03:45.188945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InstructExcel: A Benchmark for Natural Language Instruction in Excel","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Benjamin Van Durme, Carina Negreanu, Chitta Baral, Christian Poelitz, Elnaz Nouri, Justin Payan, Mukul Singh, Rasika Chakravarthy, Subhro Roy, Swaroop Mishra","submitted_at":"2023-10-23T02:00:55Z","abstract_excerpt":"With the evolution of Large Language Models (LLMs) we can solve increasingly more complex NLP tasks across various domains, including spreadsheets. This work investigates whether LLMs can generate code (Excel OfficeScripts, a TypeScript API for executing many tasks in Excel) that solves Excel specific tasks provided via natural language user instructions. To do so we introduce a new large-scale benchmark, InstructExcel, created by leveraging the 'Automate' feature in Excel to automatically generate OfficeScripts from users' actions. Our benchmark includes over 10k samples covering 170+ Excel o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.14495","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/2310.14495/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":"2310.14495","created_at":"2026-07-05T07:03:45.189002+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.14495v1","created_at":"2026-07-05T07:03:45.189002+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.14495","created_at":"2026-07-05T07:03:45.189002+00:00"},{"alias_kind":"pith_short_12","alias_value":"LIUSTR6RUDCF","created_at":"2026-07-05T07:03:45.189002+00:00"},{"alias_kind":"pith_short_16","alias_value":"LIUSTR6RUDCFGGBI","created_at":"2026-07-05T07:03:45.189002+00:00"},{"alias_kind":"pith_short_8","alias_value":"LIUSTR6R","created_at":"2026-07-05T07:03:45.189002+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.21816","citing_title":"From Task to Tutorial: An Automated GUI Framework for Excel Tutorial Document and Video Creation","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LIUSTR6RUDCFGGBI6NUYCHY7V7","json":"https://pith.science/pith/LIUSTR6RUDCFGGBI6NUYCHY7V7.json","graph_json":"https://pith.science/api/pith-number/LIUSTR6RUDCFGGBI6NUYCHY7V7/graph.json","events_json":"https://pith.science/api/pith-number/LIUSTR6RUDCFGGBI6NUYCHY7V7/events.json","paper":"https://pith.science/paper/LIUSTR6R"},"agent_actions":{"view_html":"https://pith.science/pith/LIUSTR6RUDCFGGBI6NUYCHY7V7","download_json":"https://pith.science/pith/LIUSTR6RUDCFGGBI6NUYCHY7V7.json","view_paper":"https://pith.science/paper/LIUSTR6R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.14495&json=true","fetch_graph":"https://pith.science/api/pith-number/LIUSTR6RUDCFGGBI6NUYCHY7V7/graph.json","fetch_events":"https://pith.science/api/pith-number/LIUSTR6RUDCFGGBI6NUYCHY7V7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LIUSTR6RUDCFGGBI6NUYCHY7V7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LIUSTR6RUDCFGGBI6NUYCHY7V7/action/storage_attestation","attest_author":"https://pith.science/pith/LIUSTR6RUDCFGGBI6NUYCHY7V7/action/author_attestation","sign_citation":"https://pith.science/pith/LIUSTR6RUDCFGGBI6NUYCHY7V7/action/citation_signature","submit_replication":"https://pith.science/pith/LIUSTR6RUDCFGGBI6NUYCHY7V7/action/replication_record"}},"created_at":"2026-07-05T07:03:45.189002+00:00","updated_at":"2026-07-05T07:03:45.189002+00:00"}