{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:N66HTWI5FARGLAC7PCC4SNHS5D","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"cebc726cf33ee457bd1684bc5228fb9e3af612dbfb4b6b1c01af3390fdd018f3","cross_cats_sorted":["cs.CL","cs.HC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-01-08T15:45:21Z","title_canon_sha256":"8fc259d270c011636a66d419af2f801bfc52a71260442d980e628c833d24659e"},"schema_version":"1.0","source":{"id":"2501.04575","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.04575","created_at":"2026-07-05T09:58:37Z"},{"alias_kind":"arxiv_version","alias_value":"2501.04575v1","created_at":"2026-07-05T09:58:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.04575","created_at":"2026-07-05T09:58:37Z"},{"alias_kind":"pith_short_12","alias_value":"N66HTWI5FARG","created_at":"2026-07-05T09:58:37Z"},{"alias_kind":"pith_short_16","alias_value":"N66HTWI5FARGLAC7","created_at":"2026-07-05T09:58:37Z"},{"alias_kind":"pith_short_8","alias_value":"N66HTWI5","created_at":"2026-07-05T09:58:37Z"}],"graph_snapshots":[{"event_id":"sha256:7f5ecea4b3f07f611d5e22482f28fd0c8e035f23b690e8ab26e7a7602b683105","target":"graph","created_at":"2026-07-05T09:58:37Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2501.04575/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Graphical User Interface (GUI) Agents, powered by multimodal large language models (MLLMs), have shown great potential for task automation on computing devices such as computers and mobile phones. However, existing agents face challenges in multi-step reasoning and reliance on textual annotations, limiting their effectiveness. We introduce \\textit{InfiGUIAgent}, an MLLM-based GUI Agent trained with a two-stage supervised fine-tuning pipeline. Stage 1 enhances fundamental skills such as GUI understanding and grounding, while Stage 2 integrates hierarchical reasoning and expectation-reflection r","authors_text":"Congkai Xie, Fei Wu, Hongxia Yang, Pengxiang Li, Shengyu Zhang, Xiaotian Han, Xinchen Xu, Xueyu Hu, Yuhang Liu, Zishu Wei","cross_cats":["cs.CL","cs.HC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-01-08T15:45:21Z","title":"InfiGUIAgent: A Multimodal Generalist GUI Agent with Native Reasoning and Reflection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.04575","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:dbdcbd3ccf345926215d93fd31868545ddeb48c742979d507c10e5ec813b1fbd","target":"record","created_at":"2026-07-05T09:58:37Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"cebc726cf33ee457bd1684bc5228fb9e3af612dbfb4b6b1c01af3390fdd018f3","cross_cats_sorted":["cs.CL","cs.HC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-01-08T15:45:21Z","title_canon_sha256":"8fc259d270c011636a66d419af2f801bfc52a71260442d980e628c833d24659e"},"schema_version":"1.0","source":{"id":"2501.04575","kind":"arxiv","version":1}},"canonical_sha256":"6fbc79d91d282265805f7885c934f2e8c1da8e61ade1a1401685ab7b33fec96f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6fbc79d91d282265805f7885c934f2e8c1da8e61ade1a1401685ab7b33fec96f","first_computed_at":"2026-07-05T09:58:37.536548Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:58:37.536548Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qFwccPjxepLbGYg966hfnuTN/0cqkU2rMv9QMLr/awbHaKPPKOxitggrwfRmvx0yNiB/PlIIB0t6b2YVRZuFCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:58:37.537026Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.04575","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dbdcbd3ccf345926215d93fd31868545ddeb48c742979d507c10e5ec813b1fbd","sha256:7f5ecea4b3f07f611d5e22482f28fd0c8e035f23b690e8ab26e7a7602b683105"],"state_sha256":"7fd5d509c6e88abfce028e72765d5c90822b6f4bb6bc9363a870f6a84a876381"}