{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FAFZNG2LCAYPOT7SXNBKCIRWSO","short_pith_number":"pith:FAFZNG2L","schema_version":"1.0","canonical_sha256":"280b969b4b1030f74ff2bb42a1223693abfcae9bb92233bdd807df9953f4c132","source":{"kind":"arxiv","id":"2607.11185","version":1},"attestation_state":"computed","paper":{"title":"SCALECUA: Scaling Computer Use Agents with Verifiable Task Synthesis and Efficient Online RL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bohao Jing, Bowen Lv, Hanchen Zhang, Hanyu Lai, Jie Tang, Shuntian Yao, Xiao Liu, Yanxiao Zhao, Yanyu Ren, Yuxiao Dong","submitted_at":"2026-07-13T07:32:35Z","abstract_excerpt":"Computer use agents (CUAs) are emerging as a powerful interface for automating complex digital workflows through visual perception and GUI execution. Online reinforcement learning with verifiable rewards (RLVR) has emerged as a key direction for scaling their capabilities. However, this paradigm is bottlenecked by verifiable data scarcity and online RL inefficiency. To break these barriers, we introduce ScaleCUA, a unified framework that scales online RL for CUAs via verifiable task synthesis and efficient training. At the data level, we design VeriGen, an end-to-end framework for generating v"},"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":"2607.11185","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-13T07:32:35Z","cross_cats_sorted":[],"title_canon_sha256":"c9ac8cbc4bad18fc1c856f1461d14af81f442cb894ac04be96a69aa7545839af","abstract_canon_sha256":"db457211d33b2132bc3b5fcd676b9fa87801e91e5013e9982bfc7ad0b318a2e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T01:22:21.130555Z","signature_b64":"1wUd13iTZOXxmLdhstguiUeBeL9WwGzv+VK695BTaDWtdH1TkBJculoH4RSjpYB1d94AkywQkR364YBi49y2Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"280b969b4b1030f74ff2bb42a1223693abfcae9bb92233bdd807df9953f4c132","last_reissued_at":"2026-07-14T01:22:21.129693Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T01:22:21.129693Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SCALECUA: Scaling Computer Use Agents with Verifiable Task Synthesis and Efficient Online RL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bohao Jing, Bowen Lv, Hanchen Zhang, Hanyu Lai, Jie Tang, Shuntian Yao, Xiao Liu, Yanxiao Zhao, Yanyu Ren, Yuxiao Dong","submitted_at":"2026-07-13T07:32:35Z","abstract_excerpt":"Computer use agents (CUAs) are emerging as a powerful interface for automating complex digital workflows through visual perception and GUI execution. Online reinforcement learning with verifiable rewards (RLVR) has emerged as a key direction for scaling their capabilities. However, this paradigm is bottlenecked by verifiable data scarcity and online RL inefficiency. To break these barriers, we introduce ScaleCUA, a unified framework that scales online RL for CUAs via verifiable task synthesis and efficient training. At the data level, we design VeriGen, an end-to-end framework for generating v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.11185","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/2607.11185/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":"2607.11185","created_at":"2026-07-14T01:22:21.130137+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.11185v1","created_at":"2026-07-14T01:22:21.130137+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.11185","created_at":"2026-07-14T01:22:21.130137+00:00"},{"alias_kind":"pith_short_12","alias_value":"FAFZNG2LCAYP","created_at":"2026-07-14T01:22:21.130137+00:00"},{"alias_kind":"pith_short_16","alias_value":"FAFZNG2LCAYPOT7S","created_at":"2026-07-14T01:22:21.130137+00:00"},{"alias_kind":"pith_short_8","alias_value":"FAFZNG2L","created_at":"2026-07-14T01:22:21.130137+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/FAFZNG2LCAYPOT7SXNBKCIRWSO","json":"https://pith.science/pith/FAFZNG2LCAYPOT7SXNBKCIRWSO.json","graph_json":"https://pith.science/api/pith-number/FAFZNG2LCAYPOT7SXNBKCIRWSO/graph.json","events_json":"https://pith.science/api/pith-number/FAFZNG2LCAYPOT7SXNBKCIRWSO/events.json","paper":"https://pith.science/paper/FAFZNG2L"},"agent_actions":{"view_html":"https://pith.science/pith/FAFZNG2LCAYPOT7SXNBKCIRWSO","download_json":"https://pith.science/pith/FAFZNG2LCAYPOT7SXNBKCIRWSO.json","view_paper":"https://pith.science/paper/FAFZNG2L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.11185&json=true","fetch_graph":"https://pith.science/api/pith-number/FAFZNG2LCAYPOT7SXNBKCIRWSO/graph.json","fetch_events":"https://pith.science/api/pith-number/FAFZNG2LCAYPOT7SXNBKCIRWSO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FAFZNG2LCAYPOT7SXNBKCIRWSO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FAFZNG2LCAYPOT7SXNBKCIRWSO/action/storage_attestation","attest_author":"https://pith.science/pith/FAFZNG2LCAYPOT7SXNBKCIRWSO/action/author_attestation","sign_citation":"https://pith.science/pith/FAFZNG2LCAYPOT7SXNBKCIRWSO/action/citation_signature","submit_replication":"https://pith.science/pith/FAFZNG2LCAYPOT7SXNBKCIRWSO/action/replication_record"}},"created_at":"2026-07-14T01:22:21.130137+00:00","updated_at":"2026-07-14T01:22:21.130137+00:00"}