{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3G6DGG77VKEMRY2T3TX5VSCYE6","short_pith_number":"pith:3G6DGG77","schema_version":"1.0","canonical_sha256":"d9bc331bffaa88c8e353dcefdac85827a48aac0744158ef2255906ca88193006","source":{"kind":"arxiv","id":"2406.14991","version":2},"attestation_state":"computed","paper":{"title":"SpreadsheetBench: Towards Challenging Real World Spreadsheet Manipulation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.CL","authors_text":"Bohan Zhang, Jie Tang, Jifan Yu, Jing Zhang, Sijia Luo, Xiaohan Zhang, Xiaokang Zhang, Xi Wang, Zeyao Ma","submitted_at":"2024-06-21T09:06:45Z","abstract_excerpt":"We introduce SpreadsheetBench, a challenging spreadsheet manipulation benchmark exclusively derived from real-world scenarios, designed to immerse current large language models (LLMs) in the actual workflow of spreadsheet users. Unlike existing benchmarks that rely on synthesized queries and simplified spreadsheet files, SpreadsheetBench is built from 912 real questions gathered from online Excel forums, which reflect the intricate needs of users. The associated spreadsheets from the forums contain a variety of tabular data such as multiple tables, non-standard relational tables, and abundant "},"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":"2406.14991","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-21T09:06:45Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"d21ba57db2e0259d2a0e95c3b7765f7aa0478b2b32d88bbde34b8b9d035d7d96","abstract_canon_sha256":"13e3623f0dc65acd7cb28fbd7bef7f6e7bd9d33d90840c1a1747e82addbe1eeb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:21:45.914720Z","signature_b64":"nlfG1LKpx2J7PHpG10gErR8aOc8wtjOYKDKl5gHOBjKJ8Wvn/iExFo/tYhnQXr4UNkEELEQI11b6AqWQ9F3/Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9bc331bffaa88c8e353dcefdac85827a48aac0744158ef2255906ca88193006","last_reissued_at":"2026-07-05T09:21:45.914225Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:21:45.914225Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SpreadsheetBench: Towards Challenging Real World Spreadsheet Manipulation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.CL","authors_text":"Bohan Zhang, Jie Tang, Jifan Yu, Jing Zhang, Sijia Luo, Xiaohan Zhang, Xiaokang Zhang, Xi Wang, Zeyao Ma","submitted_at":"2024-06-21T09:06:45Z","abstract_excerpt":"We introduce SpreadsheetBench, a challenging spreadsheet manipulation benchmark exclusively derived from real-world scenarios, designed to immerse current large language models (LLMs) in the actual workflow of spreadsheet users. Unlike existing benchmarks that rely on synthesized queries and simplified spreadsheet files, SpreadsheetBench is built from 912 real questions gathered from online Excel forums, which reflect the intricate needs of users. The associated spreadsheets from the forums contain a variety of tabular data such as multiple tables, non-standard relational tables, and abundant "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.14991","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/2406.14991/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":"2406.14991","created_at":"2026-07-05T09:21:45.914285+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.14991v2","created_at":"2026-07-05T09:21:45.914285+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.14991","created_at":"2026-07-05T09:21:45.914285+00:00"},{"alias_kind":"pith_short_12","alias_value":"3G6DGG77VKEM","created_at":"2026-07-05T09:21:45.914285+00:00"},{"alias_kind":"pith_short_16","alias_value":"3G6DGG77VKEMRY2T","created_at":"2026-07-05T09:21:45.914285+00:00"},{"alias_kind":"pith_short_8","alias_value":"3G6DGG77","created_at":"2026-07-05T09:21:45.914285+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20333","citing_title":"SoftSkill: Behavioral Compression for Contextual Adaptation","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20475","citing_title":"Marginal Advantage Accumulation for Memory-Driven Agent Self-Evolution","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17321","citing_title":"ProCUA-SFT Technical Report","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00248","citing_title":"Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21347","citing_title":"Insights Generator: Systematic Corpus-Level Trace Diagnostics for LLM Agents","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2412.04272","citing_title":"PoTable: Towards Systematic Thinking via Plan-then-Execute Stage Reasoning on Tables","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21347","citing_title":"Insights Generator: Systematic Corpus-Level Trace Diagnostics for LLM Agents","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21347","citing_title":"Insights Generator: Systematic Corpus-Level Trace Diagnostics for LLM Agents","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16986","citing_title":"Skills on the Fly: Test-Time Adaptive Skill Synthesis for LLM Agents","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23853","citing_title":"ClawTrace: Cost-Aware Tracing for LLM Agent Skill Distillation","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3G6DGG77VKEMRY2T3TX5VSCYE6","json":"https://pith.science/pith/3G6DGG77VKEMRY2T3TX5VSCYE6.json","graph_json":"https://pith.science/api/pith-number/3G6DGG77VKEMRY2T3TX5VSCYE6/graph.json","events_json":"https://pith.science/api/pith-number/3G6DGG77VKEMRY2T3TX5VSCYE6/events.json","paper":"https://pith.science/paper/3G6DGG77"},"agent_actions":{"view_html":"https://pith.science/pith/3G6DGG77VKEMRY2T3TX5VSCYE6","download_json":"https://pith.science/pith/3G6DGG77VKEMRY2T3TX5VSCYE6.json","view_paper":"https://pith.science/paper/3G6DGG77","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.14991&json=true","fetch_graph":"https://pith.science/api/pith-number/3G6DGG77VKEMRY2T3TX5VSCYE6/graph.json","fetch_events":"https://pith.science/api/pith-number/3G6DGG77VKEMRY2T3TX5VSCYE6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3G6DGG77VKEMRY2T3TX5VSCYE6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3G6DGG77VKEMRY2T3TX5VSCYE6/action/storage_attestation","attest_author":"https://pith.science/pith/3G6DGG77VKEMRY2T3TX5VSCYE6/action/author_attestation","sign_citation":"https://pith.science/pith/3G6DGG77VKEMRY2T3TX5VSCYE6/action/citation_signature","submit_replication":"https://pith.science/pith/3G6DGG77VKEMRY2T3TX5VSCYE6/action/replication_record"}},"created_at":"2026-07-05T09:21:45.914285+00:00","updated_at":"2026-07-05T09:21:45.914285+00:00"}