{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5J43PPXHHIDBQABCYAVAX3BR7M","short_pith_number":"pith:5J43PPXH","schema_version":"1.0","canonical_sha256":"ea79b7bee73a06180022c02a0bec31fb09cd22d0bfe2790f70b949ac7d0a207b","source":{"kind":"arxiv","id":"2410.18963","version":1},"attestation_state":"computed","paper":{"title":"OSCAR: Operating System Control via State-Aware Reasoning and Re-Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Bang Liu, Xiaoqiang Wang","submitted_at":"2024-10-24T17:58:08Z","abstract_excerpt":"Large language models (LLMs) and large multimodal models (LMMs) have shown great potential in automating complex tasks like web browsing and gaming. However, their ability to generalize across diverse applications remains limited, hindering broader utility. To address this challenge, we present OSCAR: Operating System Control via state-Aware reasoning and Re-planning. OSCAR is a generalist agent designed to autonomously navigate and interact with various desktop and mobile applications through standardized controls, such as mouse and keyboard inputs, while processing screen images to fulfill u"},"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":"2410.18963","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-10-24T17:58:08Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"da0a8ff1bad9c1adddbd52b6c37fbde99a29f4db8d324e30e4b169bfe329dd66","abstract_canon_sha256":"beda4d5bb8eff6460dc373abe39ce11e0c46ff4dd51f4a16f34ce0cc2dbbf7bb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:25:22.620058Z","signature_b64":"femahLd6/XTyylfdwMcRh5JQALhWLYYjkBi0uybsj+WAiEeA7yZHLH1FlozjFafWr7RAV4R91aEzK/gK9L8wAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea79b7bee73a06180022c02a0bec31fb09cd22d0bfe2790f70b949ac7d0a207b","last_reissued_at":"2026-07-05T09:25:22.619502Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:25:22.619502Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OSCAR: Operating System Control via State-Aware Reasoning and Re-Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Bang Liu, Xiaoqiang Wang","submitted_at":"2024-10-24T17:58:08Z","abstract_excerpt":"Large language models (LLMs) and large multimodal models (LMMs) have shown great potential in automating complex tasks like web browsing and gaming. However, their ability to generalize across diverse applications remains limited, hindering broader utility. To address this challenge, we present OSCAR: Operating System Control via state-Aware reasoning and Re-planning. OSCAR is a generalist agent designed to autonomously navigate and interact with various desktop and mobile applications through standardized controls, such as mouse and keyboard inputs, while processing screen images to fulfill u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.18963","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/2410.18963/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":"2410.18963","created_at":"2026-07-05T09:25:22.619561+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.18963v1","created_at":"2026-07-05T09:25:22.619561+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.18963","created_at":"2026-07-05T09:25:22.619561+00:00"},{"alias_kind":"pith_short_12","alias_value":"5J43PPXHHIDB","created_at":"2026-07-05T09:25:22.619561+00:00"},{"alias_kind":"pith_short_16","alias_value":"5J43PPXHHIDBQABC","created_at":"2026-07-05T09:25:22.619561+00:00"},{"alias_kind":"pith_short_8","alias_value":"5J43PPXH","created_at":"2026-07-05T09:25:22.619561+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21740","citing_title":"Training the Orchestrator: A Supervised Approach to End-to-End PDDL Planning with LLM Agents","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2504.01990","citing_title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","ref_index":275,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16883","citing_title":"SE-GA: Memory-Augmented Self-Evolution for GUI Agents","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11514","citing_title":"FlowSteer: Prompt-Only Workflow Steering Exposes Planning-Time Vulnerabilities in Multi-Agent LLM Systems","ref_index":54,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5J43PPXHHIDBQABCYAVAX3BR7M","json":"https://pith.science/pith/5J43PPXHHIDBQABCYAVAX3BR7M.json","graph_json":"https://pith.science/api/pith-number/5J43PPXHHIDBQABCYAVAX3BR7M/graph.json","events_json":"https://pith.science/api/pith-number/5J43PPXHHIDBQABCYAVAX3BR7M/events.json","paper":"https://pith.science/paper/5J43PPXH"},"agent_actions":{"view_html":"https://pith.science/pith/5J43PPXHHIDBQABCYAVAX3BR7M","download_json":"https://pith.science/pith/5J43PPXHHIDBQABCYAVAX3BR7M.json","view_paper":"https://pith.science/paper/5J43PPXH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.18963&json=true","fetch_graph":"https://pith.science/api/pith-number/5J43PPXHHIDBQABCYAVAX3BR7M/graph.json","fetch_events":"https://pith.science/api/pith-number/5J43PPXHHIDBQABCYAVAX3BR7M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5J43PPXHHIDBQABCYAVAX3BR7M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5J43PPXHHIDBQABCYAVAX3BR7M/action/storage_attestation","attest_author":"https://pith.science/pith/5J43PPXHHIDBQABCYAVAX3BR7M/action/author_attestation","sign_citation":"https://pith.science/pith/5J43PPXHHIDBQABCYAVAX3BR7M/action/citation_signature","submit_replication":"https://pith.science/pith/5J43PPXHHIDBQABCYAVAX3BR7M/action/replication_record"}},"created_at":"2026-07-05T09:25:22.619561+00:00","updated_at":"2026-07-05T09:25:22.619561+00:00"}