{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CA3RCSDOK4ND6ZUH32J6BCNSDQ","short_pith_number":"pith:CA3RCSDO","schema_version":"1.0","canonical_sha256":"103711486e571a3f6687de93e089b21c386e17302fe8fc586f924dbb6a9ace2b","source":{"kind":"arxiv","id":"2608.11191","version":1},"attestation_state":"computed","paper":{"title":"Test-Time Self-Evolving GUI Visual Grounding via Reflection-Guided On-Policy Self-Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Shiyu Xuan, Zechao Li","submitted_at":"2026-08-11T17:50:25Z","abstract_excerpt":"GUI Visual Grounding is a fundamental capability for GUI agents. Existing models typically freeze their parameters after deployment, limiting their ability to adapt to unseen interfaces. Although recent methods attempt to adapt models via test-time reinforcement learning, they cannot reflect upon failed exploration. To overcome this, we propose a Test-Time Self-Evolving framework that enables models to improve after deployment without human-annotated ground truth. It constructs a closed-loop of Exploration, Evaluation, Reflection, and Internalization. Specifically, the agent first explores uns"},"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":"2608.11191","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-11T17:50:25Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"a19da2e367447a876eac9ce1baacab468402bd094f5f7a9f47cf03e4cae9c2ad","abstract_canon_sha256":"71619f689f45c9a25b062c7ce227fa97c5e291bbd9f153bb223e11c348ab16d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-12T01:24:46.904614Z","signature_b64":"xBOIWkmcLU4Ewpx3nB8Vn59OhLd8MIQp/pjPfFf3Lozr8ml6Ly67i2TspPnWaiCQD4Cy0dDArMv6A+0TzwmnDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"103711486e571a3f6687de93e089b21c386e17302fe8fc586f924dbb6a9ace2b","last_reissued_at":"2026-08-12T01:24:46.903099Z","signature_status":"signed_v1","first_computed_at":"2026-08-12T01:24:46.903099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Test-Time Self-Evolving GUI Visual Grounding via Reflection-Guided On-Policy Self-Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Shiyu Xuan, Zechao Li","submitted_at":"2026-08-11T17:50:25Z","abstract_excerpt":"GUI Visual Grounding is a fundamental capability for GUI agents. Existing models typically freeze their parameters after deployment, limiting their ability to adapt to unseen interfaces. Although recent methods attempt to adapt models via test-time reinforcement learning, they cannot reflect upon failed exploration. To overcome this, we propose a Test-Time Self-Evolving framework that enables models to improve after deployment without human-annotated ground truth. It constructs a closed-loop of Exploration, Evaluation, Reflection, and Internalization. Specifically, the agent first explores uns"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.11191","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/2608.11191/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":"2608.11191","created_at":"2026-08-12T01:24:46.906927+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.11191v1","created_at":"2026-08-12T01:24:46.906927+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.11191","created_at":"2026-08-12T01:24:46.906927+00:00"},{"alias_kind":"pith_short_12","alias_value":"CA3RCSDOK4ND","created_at":"2026-08-12T01:24:46.906927+00:00"},{"alias_kind":"pith_short_16","alias_value":"CA3RCSDOK4ND6ZUH","created_at":"2026-08-12T01:24:46.906927+00:00"},{"alias_kind":"pith_short_8","alias_value":"CA3RCSDO","created_at":"2026-08-12T01:24:46.906927+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/CA3RCSDOK4ND6ZUH32J6BCNSDQ","json":"https://pith.science/pith/CA3RCSDOK4ND6ZUH32J6BCNSDQ.json","graph_json":"https://pith.science/api/pith-number/CA3RCSDOK4ND6ZUH32J6BCNSDQ/graph.json","events_json":"https://pith.science/api/pith-number/CA3RCSDOK4ND6ZUH32J6BCNSDQ/events.json","paper":"https://pith.science/paper/CA3RCSDO"},"agent_actions":{"view_html":"https://pith.science/pith/CA3RCSDOK4ND6ZUH32J6BCNSDQ","download_json":"https://pith.science/pith/CA3RCSDOK4ND6ZUH32J6BCNSDQ.json","view_paper":"https://pith.science/paper/CA3RCSDO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.11191&json=true","fetch_graph":"https://pith.science/api/pith-number/CA3RCSDOK4ND6ZUH32J6BCNSDQ/graph.json","fetch_events":"https://pith.science/api/pith-number/CA3RCSDOK4ND6ZUH32J6BCNSDQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CA3RCSDOK4ND6ZUH32J6BCNSDQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CA3RCSDOK4ND6ZUH32J6BCNSDQ/action/storage_attestation","attest_author":"https://pith.science/pith/CA3RCSDOK4ND6ZUH32J6BCNSDQ/action/author_attestation","sign_citation":"https://pith.science/pith/CA3RCSDOK4ND6ZUH32J6BCNSDQ/action/citation_signature","submit_replication":"https://pith.science/pith/CA3RCSDOK4ND6ZUH32J6BCNSDQ/action/replication_record"}},"created_at":"2026-08-12T01:24:46.906927+00:00","updated_at":"2026-08-12T01:24:46.906927+00:00"}