{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WYLXQ47QUI7MQYR5SDD33HRVXP","short_pith_number":"pith:WYLXQ47Q","schema_version":"1.0","canonical_sha256":"b6177873f0a23ec8623d90c7bd9e35bbcc12eae97d04372ab79b50172836d1aa","source":{"kind":"arxiv","id":"2605.22642","version":1},"attestation_state":"computed","paper":{"title":"Spreadsheet-RL: Advancing Large Language Model Agents on Realistic Spreadsheet Tasks via Reinforcement Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Banghao Chi, Hanchao Yu, Jingcheng Yang, Jize Jiang, Klara Nahrstedt, Mingyuan Wu, Minjia Zhang, Rui Hou, Shengyi Qian, Xiangjun Fan, Yining Xie, Zhaoheng Li","submitted_at":"2026-05-21T15:47:41Z","abstract_excerpt":"Spreadsheet systems (e.g., Microsoft Excel, Google Sheets) play a central role in modern data-centric workflows. As AI agents grow increasingly capable of automating complex tasks, such as controlling computers and generating presentations, building an AI-driven spreadsheet agent has emerged as a promising research direction. Most existing spreadsheet agents rely on specialized prompting over general-purpose LLMs; while this design has potentials on simple spreadsheet operations, it struggles to manage the complex, multi-step workflows typical of real-world applications.\n  We introduce Spreads"},"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":"2605.22642","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-21T15:47:41Z","cross_cats_sorted":[],"title_canon_sha256":"c7b6251e3dfe01889a40fa5d2885a74fb7dc2c8742af20320671ac0fc586f412","abstract_canon_sha256":"53193490b1920a907abaca4c66b71c66098249fe3db62012be8e30b224f9ab2e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T02:04:47.530674Z","signature_b64":"TXV3Gfi4mwOTrWvAXTRmqJUIkNQ7GKqfmilvvnnQGuP/JkiyzdyUkq10jK0rJxbWteiZ1SNMgN8psMG106bfBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b6177873f0a23ec8623d90c7bd9e35bbcc12eae97d04372ab79b50172836d1aa","last_reissued_at":"2026-05-22T02:04:47.530015Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T02:04:47.530015Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spreadsheet-RL: Advancing Large Language Model Agents on Realistic Spreadsheet Tasks via Reinforcement Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Banghao Chi, Hanchao Yu, Jingcheng Yang, Jize Jiang, Klara Nahrstedt, Mingyuan Wu, Minjia Zhang, Rui Hou, Shengyi Qian, Xiangjun Fan, Yining Xie, Zhaoheng Li","submitted_at":"2026-05-21T15:47:41Z","abstract_excerpt":"Spreadsheet systems (e.g., Microsoft Excel, Google Sheets) play a central role in modern data-centric workflows. As AI agents grow increasingly capable of automating complex tasks, such as controlling computers and generating presentations, building an AI-driven spreadsheet agent has emerged as a promising research direction. Most existing spreadsheet agents rely on specialized prompting over general-purpose LLMs; while this design has potentials on simple spreadsheet operations, it struggles to manage the complex, multi-step workflows typical of real-world applications.\n  We introduce Spreads"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22642","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/2605.22642/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":"2605.22642","created_at":"2026-05-22T02:04:47.530095+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.22642v1","created_at":"2026-05-22T02:04:47.530095+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22642","created_at":"2026-05-22T02:04:47.530095+00:00"},{"alias_kind":"pith_short_12","alias_value":"WYLXQ47QUI7M","created_at":"2026-05-22T02:04:47.530095+00:00"},{"alias_kind":"pith_short_16","alias_value":"WYLXQ47QUI7MQYR5","created_at":"2026-05-22T02:04:47.530095+00:00"},{"alias_kind":"pith_short_8","alias_value":"WYLXQ47Q","created_at":"2026-05-22T02:04:47.530095+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/WYLXQ47QUI7MQYR5SDD33HRVXP","json":"https://pith.science/pith/WYLXQ47QUI7MQYR5SDD33HRVXP.json","graph_json":"https://pith.science/api/pith-number/WYLXQ47QUI7MQYR5SDD33HRVXP/graph.json","events_json":"https://pith.science/api/pith-number/WYLXQ47QUI7MQYR5SDD33HRVXP/events.json","paper":"https://pith.science/paper/WYLXQ47Q"},"agent_actions":{"view_html":"https://pith.science/pith/WYLXQ47QUI7MQYR5SDD33HRVXP","download_json":"https://pith.science/pith/WYLXQ47QUI7MQYR5SDD33HRVXP.json","view_paper":"https://pith.science/paper/WYLXQ47Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.22642&json=true","fetch_graph":"https://pith.science/api/pith-number/WYLXQ47QUI7MQYR5SDD33HRVXP/graph.json","fetch_events":"https://pith.science/api/pith-number/WYLXQ47QUI7MQYR5SDD33HRVXP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WYLXQ47QUI7MQYR5SDD33HRVXP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WYLXQ47QUI7MQYR5SDD33HRVXP/action/storage_attestation","attest_author":"https://pith.science/pith/WYLXQ47QUI7MQYR5SDD33HRVXP/action/author_attestation","sign_citation":"https://pith.science/pith/WYLXQ47QUI7MQYR5SDD33HRVXP/action/citation_signature","submit_replication":"https://pith.science/pith/WYLXQ47QUI7MQYR5SDD33HRVXP/action/replication_record"}},"created_at":"2026-05-22T02:04:47.530095+00:00","updated_at":"2026-05-22T02:04:47.530095+00:00"}