{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UQQL5LOIVA67RQVNU4QSDJOPB3","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":"76ce4205d89e7a9b8684ff9aa254544a9b731ad62eb9e7855afa957d1de01e98","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-08T04:56:57Z","title_canon_sha256":"c499b21ed0d6f662622cc5b49e4ec283837d74a0b5313e54f69d2b830188e234"},"schema_version":"1.0","source":{"id":"2507.05673","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.05673","created_at":"2026-07-05T11:33:34Z"},{"alias_kind":"arxiv_version","alias_value":"2507.05673v1","created_at":"2026-07-05T11:33:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.05673","created_at":"2026-07-05T11:33:34Z"},{"alias_kind":"pith_short_12","alias_value":"UQQL5LOIVA67","created_at":"2026-07-05T11:33:34Z"},{"alias_kind":"pith_short_16","alias_value":"UQQL5LOIVA67RQVN","created_at":"2026-07-05T11:33:34Z"},{"alias_kind":"pith_short_8","alias_value":"UQQL5LOI","created_at":"2026-07-05T11:33:34Z"}],"graph_snapshots":[{"event_id":"sha256:0ad8c578964db3184645b7f903dd59355486007ec546776519525b2837326584","target":"graph","created_at":"2026-07-05T11:33:34Z","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/2507.05673/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual agent models for automating human activities on Graphical User Interfaces (GUIs) have emerged as a promising research direction, driven by advances in large Vision Language Models (VLMs). A critical challenge in GUI automation is the precise grounding of interface elements across diverse platforms. Existing vision-only GUI agents directly ground elements from large and cluttered screenshots, requiring them to process substantial irrelevant information that compromises their accuracy. In addition, these approaches typically employ basic cross-entropy loss for learning grounding objective","authors_text":"Joonhyung Park, Kunwar Yashraj Singh, Peng Tang, R. Manmatha, Sagnik Das, Shabnam Ghadar, Srikar Appalaraju","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-08T04:56:57Z","title":"R-VLM: Region-Aware Vision Language Model for Precise GUI Grounding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.05673","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":"sha256:5e0765f6b9c8f180de9246c7b8b772232ac1e976b69290f3c805b4c9328328f6","target":"record","created_at":"2026-07-05T11:33:34Z","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":"76ce4205d89e7a9b8684ff9aa254544a9b731ad62eb9e7855afa957d1de01e98","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-08T04:56:57Z","title_canon_sha256":"c499b21ed0d6f662622cc5b49e4ec283837d74a0b5313e54f69d2b830188e234"},"schema_version":"1.0","source":{"id":"2507.05673","kind":"arxiv","version":1}},"canonical_sha256":"a420beadc8a83df8c2ada72121a5cf0ec1f6526ecaff1b23fec403bbc79c0138","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a420beadc8a83df8c2ada72121a5cf0ec1f6526ecaff1b23fec403bbc79c0138","first_computed_at":"2026-07-05T11:33:34.398875Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:33:34.398875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XbEFRACDZp2X1OeQ4NDog4gz4LQqOdiVbgndRJwePXP2MUqXuultY4NU3f/sW0ERAf06/hTeGLVQAgxeN9RKDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:33:34.399309Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.05673","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5e0765f6b9c8f180de9246c7b8b772232ac1e976b69290f3c805b4c9328328f6","sha256:0ad8c578964db3184645b7f903dd59355486007ec546776519525b2837326584"],"state_sha256":"36d60dfcf6b54632e1a08217a6e50c6b4939de02e578022dad7eb0c54f88acba"}