{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Y3YFRFBAJQDVKP6DWAS5DIURPU","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":"f329b1ca5dfca0bdfb836cdd117a90a9d34e1cd5af27bd7a5ceb447e4e9e84da","cross_cats_sorted":["cs.AI","cs.CL","cs.HC","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-11-02T05:34:21Z","title_canon_sha256":"0ad1952a20f7cf5bd4e70f8674afb5a2facc6104d433338d17619181c115304d"},"schema_version":"1.0","source":{"id":"2511.00810","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.00810","created_at":"2026-07-01T01:17:42Z"},{"alias_kind":"arxiv_version","alias_value":"2511.00810v4","created_at":"2026-07-01T01:17:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.00810","created_at":"2026-07-01T01:17:42Z"},{"alias_kind":"pith_short_12","alias_value":"Y3YFRFBAJQDV","created_at":"2026-07-01T01:17:42Z"},{"alias_kind":"pith_short_16","alias_value":"Y3YFRFBAJQDVKP6D","created_at":"2026-07-01T01:17:42Z"},{"alias_kind":"pith_short_8","alias_value":"Y3YFRFBA","created_at":"2026-07-01T01:17:42Z"}],"graph_snapshots":[{"event_id":"sha256:c4eaf2b8b89c96d5d2f9a03f41d434c1401bc655f09b8106ede9a9dcce76785a","target":"graph","created_at":"2026-07-01T01:17:42Z","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/2511.00810/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Graphical user interface (GUI) grounding is a key capability for computer-use agents, mapping natural-language instructions to actionable regions on the screen. Existing Multimodal Large Language Model (MLLM) approaches typically formulate GUI grounding as a text-based coordinate generation task. However, directly generating precise coordinates from visual inputs is challenging and often data-intensive. A more intuitive strategy is to first identify instruction-relevant visual patches and then determine the exact click location within them. Motivated by recent observations that general MLLMs e","authors_text":"Changyou Chen, Hao Tan, Jihyung Kil, Ruiyi Zhang, Shijie Zhou, Viet Dac Lai, Wanrong Zhu","cross_cats":["cs.AI","cs.CL","cs.HC","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-11-02T05:34:21Z","title":"GUI-AIMA: Aligning Intrinsic Multimodal Attention with a Context Anchor for GUI Grounding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.00810","kind":"arxiv","version":4},"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":"sha256:9c3f7eec1748f5173deb762d405738476fa4f37174a0a489e4989b1b07506689","target":"record","created_at":"2026-07-01T01:17:42Z","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":"f329b1ca5dfca0bdfb836cdd117a90a9d34e1cd5af27bd7a5ceb447e4e9e84da","cross_cats_sorted":["cs.AI","cs.CL","cs.HC","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-11-02T05:34:21Z","title_canon_sha256":"0ad1952a20f7cf5bd4e70f8674afb5a2facc6104d433338d17619181c115304d"},"schema_version":"1.0","source":{"id":"2511.00810","kind":"arxiv","version":4}},"canonical_sha256":"c6f05894204c07553fc3b025d1a2917d0aa73810da618ce9cbd66a1febfed1e9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c6f05894204c07553fc3b025d1a2917d0aa73810da618ce9cbd66a1febfed1e9","first_computed_at":"2026-07-01T01:17:42.691635Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-01T01:17:42.691635Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NYbF8NMI1kdjHwMEpUCUV7RMVAjejK5YULM4VbgFtdQs0OCPrv+OWu+y+61mlip0L2AjF1aravV85729XX3XAg==","signature_status":"signed_v1","signed_at":"2026-07-01T01:17:42.692174Z","signed_message":"canonical_sha256_bytes"},"source_id":"2511.00810","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9c3f7eec1748f5173deb762d405738476fa4f37174a0a489e4989b1b07506689","sha256:c4eaf2b8b89c96d5d2f9a03f41d434c1401bc655f09b8106ede9a9dcce76785a"],"state_sha256":"2ce424b19e34f07b19ca2af210bab62f4946415c534bb616bd21fd07d4d69d70"}