{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AFVUJZKW2JUNBA5YZ2OQSG5DCM","short_pith_number":"pith:AFVUJZKW","schema_version":"1.0","canonical_sha256":"016b44e556d268d083b8ce9d091ba3130cbada005b248ff5bc4aadd27ebb9d96","source":{"kind":"arxiv","id":"2608.07873","version":1},"attestation_state":"computed","paper":{"title":"Back to the Future: A workbook time machine for spread sheet creation benchmarks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Agamdeep Singh, Ananya Singha, Gust Verbruggen, Mansi Uniyal, Mukul Singh, Priyanshu Gupta, Sumit Gulwani, Vu Le","submitted_at":"2026-08-08T02:57:50Z","abstract_excerpt":"We introduce the workbook time machine, a pipeline that automatically creates benchmarks evaluating the ability of language models to create derived objects in spreadsheets (formulas, charts, pivot tables, and conditional formatting). Applied to public workbook corpora, it produces wtmcorpus--a collection of (input workbook, output workbook, query) triples spanning four artifact types and varying complexity. From this corpus we curate wtmbench, a 150-task evaluation benchmark with queries at three levels of specificity. We evaluate existing spreadsheet manipulation agents and baselines on wtmb"},"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":"2608.07873","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-08T02:57:50Z","cross_cats_sorted":[],"title_canon_sha256":"c64b54ad331000bc1d811fe8f75b64d9691e2e78e4574bc090bf8d7c01d260f5","abstract_canon_sha256":"90401e7fa0a42384ef78b5e624b86fb813846b4c4b433ba91b083e922610e539"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T01:18:47.863740Z","signature_b64":"2iP40ptb++NgcTKHVB8gBSJXAYmS1/SNuLYs8uv+KjpMnINUAnqDYLP45iXD2lF8wet9URgve5Nc0ndqHzYaBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"016b44e556d268d083b8ce9d091ba3130cbada005b248ff5bc4aadd27ebb9d96","last_reissued_at":"2026-08-11T01:18:47.860986Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T01:18:47.860986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Back to the Future: A workbook time machine for spread sheet creation benchmarks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Agamdeep Singh, Ananya Singha, Gust Verbruggen, Mansi Uniyal, Mukul Singh, Priyanshu Gupta, Sumit Gulwani, Vu Le","submitted_at":"2026-08-08T02:57:50Z","abstract_excerpt":"We introduce the workbook time machine, a pipeline that automatically creates benchmarks evaluating the ability of language models to create derived objects in spreadsheets (formulas, charts, pivot tables, and conditional formatting). Applied to public workbook corpora, it produces wtmcorpus--a collection of (input workbook, output workbook, query) triples spanning four artifact types and varying complexity. From this corpus we curate wtmbench, a 150-task evaluation benchmark with queries at three levels of specificity. We evaluate existing spreadsheet manipulation agents and baselines on wtmb"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.07873","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/2608.07873/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":"2608.07873","created_at":"2026-08-11T01:18:47.861904+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.07873v1","created_at":"2026-08-11T01:18:47.861904+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.07873","created_at":"2026-08-11T01:18:47.861904+00:00"},{"alias_kind":"pith_short_12","alias_value":"AFVUJZKW2JUN","created_at":"2026-08-11T01:18:47.861904+00:00"},{"alias_kind":"pith_short_16","alias_value":"AFVUJZKW2JUNBA5Y","created_at":"2026-08-11T01:18:47.861904+00:00"},{"alias_kind":"pith_short_8","alias_value":"AFVUJZKW","created_at":"2026-08-11T01:18:47.861904+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/AFVUJZKW2JUNBA5YZ2OQSG5DCM","json":"https://pith.science/pith/AFVUJZKW2JUNBA5YZ2OQSG5DCM.json","graph_json":"https://pith.science/api/pith-number/AFVUJZKW2JUNBA5YZ2OQSG5DCM/graph.json","events_json":"https://pith.science/api/pith-number/AFVUJZKW2JUNBA5YZ2OQSG5DCM/events.json","paper":"https://pith.science/paper/AFVUJZKW"},"agent_actions":{"view_html":"https://pith.science/pith/AFVUJZKW2JUNBA5YZ2OQSG5DCM","download_json":"https://pith.science/pith/AFVUJZKW2JUNBA5YZ2OQSG5DCM.json","view_paper":"https://pith.science/paper/AFVUJZKW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.07873&json=true","fetch_graph":"https://pith.science/api/pith-number/AFVUJZKW2JUNBA5YZ2OQSG5DCM/graph.json","fetch_events":"https://pith.science/api/pith-number/AFVUJZKW2JUNBA5YZ2OQSG5DCM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AFVUJZKW2JUNBA5YZ2OQSG5DCM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AFVUJZKW2JUNBA5YZ2OQSG5DCM/action/storage_attestation","attest_author":"https://pith.science/pith/AFVUJZKW2JUNBA5YZ2OQSG5DCM/action/author_attestation","sign_citation":"https://pith.science/pith/AFVUJZKW2JUNBA5YZ2OQSG5DCM/action/citation_signature","submit_replication":"https://pith.science/pith/AFVUJZKW2JUNBA5YZ2OQSG5DCM/action/replication_record"}},"created_at":"2026-08-11T01:18:47.861904+00:00","updated_at":"2026-08-11T01:18:47.861904+00:00"}