{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DIJBDTCQN3V3JJJ3SQEMQ26UKP","short_pith_number":"pith:DIJBDTCQ","schema_version":"1.0","canonical_sha256":"1a1211cc506eebb4a53b9408c86bd453ea150fcf49c8a27bef08bff55e501640","source":{"kind":"arxiv","id":"2505.00416","version":1},"attestation_state":"computed","paper":{"title":"ScaleTrack: Scaling and back-tracking Automated GUI Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jing Huang, Jingyuan Chen, Liming Zheng, Lin Ma, Shuai Fu, Wenkang Han, Yufeng Zhong, Zhixiong Zeng","submitted_at":"2025-05-01T09:27:13Z","abstract_excerpt":"Automated GUI agents aims to facilitate user interaction by automatically performing complex tasks in digital environments, such as web, mobile, desktop devices. It receives textual task instruction and GUI description to generate executable actions (\\emph{e.g.}, click) and operation boxes step by step. Training a GUI agent mainly involves grounding and planning stages, in which the GUI grounding focuses on finding the execution coordinates according to the task, while the planning stage aims to predict the next action based on historical actions. However, previous work suffers from the limita"},"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":"2505.00416","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-01T09:27:13Z","cross_cats_sorted":[],"title_canon_sha256":"69a1419ed6713a7517e82e744f9cd36c7fb7295171334ef33c2e15574effd20c","abstract_canon_sha256":"c9c5f34553fbf6abf2575cd81f109f4ccbbf594398c44c3a85b6d246d9b7d490"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:57:13.248092Z","signature_b64":"1zK42P98bSRF7MDxtuUMfLLaA3bpa7GtQtSZsjpLXu1oiP+EVULoPaTwOD4hZPOgJIzvmv0daLerIO9Z8LpKCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a1211cc506eebb4a53b9408c86bd453ea150fcf49c8a27bef08bff55e501640","last_reissued_at":"2026-07-05T10:57:13.247556Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:57:13.247556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ScaleTrack: Scaling and back-tracking Automated GUI Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jing Huang, Jingyuan Chen, Liming Zheng, Lin Ma, Shuai Fu, Wenkang Han, Yufeng Zhong, Zhixiong Zeng","submitted_at":"2025-05-01T09:27:13Z","abstract_excerpt":"Automated GUI agents aims to facilitate user interaction by automatically performing complex tasks in digital environments, such as web, mobile, desktop devices. It receives textual task instruction and GUI description to generate executable actions (\\emph{e.g.}, click) and operation boxes step by step. Training a GUI agent mainly involves grounding and planning stages, in which the GUI grounding focuses on finding the execution coordinates according to the task, while the planning stage aims to predict the next action based on historical actions. However, previous work suffers from the limita"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.00416","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/2505.00416/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":"2505.00416","created_at":"2026-07-05T10:57:13.247618+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.00416v1","created_at":"2026-07-05T10:57:13.247618+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.00416","created_at":"2026-07-05T10:57:13.247618+00:00"},{"alias_kind":"pith_short_12","alias_value":"DIJBDTCQN3V3","created_at":"2026-07-05T10:57:13.247618+00:00"},{"alias_kind":"pith_short_16","alias_value":"DIJBDTCQN3V3JJJ3","created_at":"2026-07-05T10:57:13.247618+00:00"},{"alias_kind":"pith_short_8","alias_value":"DIJBDTCQ","created_at":"2026-07-05T10:57:13.247618+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.24168","citing_title":"MGA: Memory-Driven GUI Agent for Observation-Centric Interaction","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2512.19396","citing_title":"EchoTrail-GUI: Building Actionable Memory for GUI Agents via Critic-Guided Self-Exploration","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DIJBDTCQN3V3JJJ3SQEMQ26UKP","json":"https://pith.science/pith/DIJBDTCQN3V3JJJ3SQEMQ26UKP.json","graph_json":"https://pith.science/api/pith-number/DIJBDTCQN3V3JJJ3SQEMQ26UKP/graph.json","events_json":"https://pith.science/api/pith-number/DIJBDTCQN3V3JJJ3SQEMQ26UKP/events.json","paper":"https://pith.science/paper/DIJBDTCQ"},"agent_actions":{"view_html":"https://pith.science/pith/DIJBDTCQN3V3JJJ3SQEMQ26UKP","download_json":"https://pith.science/pith/DIJBDTCQN3V3JJJ3SQEMQ26UKP.json","view_paper":"https://pith.science/paper/DIJBDTCQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.00416&json=true","fetch_graph":"https://pith.science/api/pith-number/DIJBDTCQN3V3JJJ3SQEMQ26UKP/graph.json","fetch_events":"https://pith.science/api/pith-number/DIJBDTCQN3V3JJJ3SQEMQ26UKP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DIJBDTCQN3V3JJJ3SQEMQ26UKP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DIJBDTCQN3V3JJJ3SQEMQ26UKP/action/storage_attestation","attest_author":"https://pith.science/pith/DIJBDTCQN3V3JJJ3SQEMQ26UKP/action/author_attestation","sign_citation":"https://pith.science/pith/DIJBDTCQN3V3JJJ3SQEMQ26UKP/action/citation_signature","submit_replication":"https://pith.science/pith/DIJBDTCQN3V3JJJ3SQEMQ26UKP/action/replication_record"}},"created_at":"2026-07-05T10:57:13.247618+00:00","updated_at":"2026-07-05T10:57:13.247618+00:00"}