{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2YONC357W5ADMFKF757VZSXF6B","short_pith_number":"pith:2YONC357","schema_version":"1.0","canonical_sha256":"d61cd16fbfb740361545ff7f5ccae5f052613c4e88ec8bbfd39c0e404afcf368","source":{"kind":"arxiv","id":"2608.05587","version":1},"attestation_state":"computed","paper":{"title":"StepReflect: Structured UI Transition Reflection for Mobile GUI Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Li Gu, Linqiang Guo, Tse-Hsun (Peter) Chen, Wei Liu, Yang Wang","submitted_at":"2026-08-06T04:17:27Z","abstract_excerpt":"Autonomous mobile GUI agents require accurate action reflection for reliable long-horizon execution. Existing approaches rely on open-ended multimodal reasoning after each action, which is costly and poorly matched to the structured nature of GUI state transitions. We propose StepReflect, which formulates per-step GUI reflection as supervised structured prediction conditioned on explicit transition specifications and paired visual evidence. StepReflect is trained through a staged pipeline combining supervised fine-tuning, teacher-student distillation, and preference- and reward-based refinemen"},"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":"2608.05587","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-06T04:17:27Z","cross_cats_sorted":[],"title_canon_sha256":"15c2088dc82d4a1d220bafddc58af05f890a6f57763337b20c842768c976b8b9","abstract_canon_sha256":"6795272acf68c87a6d8832b37733286533615ba0fa83e43deddbb0b897283bc4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-07T00:50:09.730430Z","signature_b64":"oMKxd+mjt4bfBrH7dWcelEEhLSfr/snjB7bDVy4J0e8tB3xkBCu7XFjRGZwmvt0P4JvsAMdzyDpwSrSfLVZOAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d61cd16fbfb740361545ff7f5ccae5f052613c4e88ec8bbfd39c0e404afcf368","last_reissued_at":"2026-08-07T00:50:09.728919Z","signature_status":"signed_v1","first_computed_at":"2026-08-07T00:50:09.728919Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"StepReflect: Structured UI Transition Reflection for Mobile GUI Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Li Gu, Linqiang Guo, Tse-Hsun (Peter) Chen, Wei Liu, Yang Wang","submitted_at":"2026-08-06T04:17:27Z","abstract_excerpt":"Autonomous mobile GUI agents require accurate action reflection for reliable long-horizon execution. Existing approaches rely on open-ended multimodal reasoning after each action, which is costly and poorly matched to the structured nature of GUI state transitions. We propose StepReflect, which formulates per-step GUI reflection as supervised structured prediction conditioned on explicit transition specifications and paired visual evidence. StepReflect is trained through a staged pipeline combining supervised fine-tuning, teacher-student distillation, and preference- and reward-based refinemen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.05587","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/2608.05587/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":"2608.05587","created_at":"2026-08-07T00:50:09.730413+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.05587v1","created_at":"2026-08-07T00:50:09.730413+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.05587","created_at":"2026-08-07T00:50:09.730413+00:00"},{"alias_kind":"pith_short_12","alias_value":"2YONC357W5AD","created_at":"2026-08-07T00:50:09.730413+00:00"},{"alias_kind":"pith_short_16","alias_value":"2YONC357W5ADMFKF","created_at":"2026-08-07T00:50:09.730413+00:00"},{"alias_kind":"pith_short_8","alias_value":"2YONC357","created_at":"2026-08-07T00:50:09.730413+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/2YONC357W5ADMFKF757VZSXF6B","json":"https://pith.science/pith/2YONC357W5ADMFKF757VZSXF6B.json","graph_json":"https://pith.science/api/pith-number/2YONC357W5ADMFKF757VZSXF6B/graph.json","events_json":"https://pith.science/api/pith-number/2YONC357W5ADMFKF757VZSXF6B/events.json","paper":"https://pith.science/paper/2YONC357"},"agent_actions":{"view_html":"https://pith.science/pith/2YONC357W5ADMFKF757VZSXF6B","download_json":"https://pith.science/pith/2YONC357W5ADMFKF757VZSXF6B.json","view_paper":"https://pith.science/paper/2YONC357","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.05587&json=true","fetch_graph":"https://pith.science/api/pith-number/2YONC357W5ADMFKF757VZSXF6B/graph.json","fetch_events":"https://pith.science/api/pith-number/2YONC357W5ADMFKF757VZSXF6B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2YONC357W5ADMFKF757VZSXF6B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2YONC357W5ADMFKF757VZSXF6B/action/storage_attestation","attest_author":"https://pith.science/pith/2YONC357W5ADMFKF757VZSXF6B/action/author_attestation","sign_citation":"https://pith.science/pith/2YONC357W5ADMFKF757VZSXF6B/action/citation_signature","submit_replication":"https://pith.science/pith/2YONC357W5ADMFKF757VZSXF6B/action/replication_record"}},"created_at":"2026-08-07T00:50:09.730413+00:00","updated_at":"2026-08-07T00:50:09.730413+00:00"}