{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4DAPOLSIRYQXCQFDW4IGJUQJUL","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":"4c325c6fd72a4abde25831f847c8a64e86d4f953a79aa0a1576b8eaef53696b9","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-12T09:12:30Z","title_canon_sha256":"53a6dc10a4ba5874432d18ab46555605b0f8d7ea06548c935a0ccb207e3ba9e7"},"schema_version":"1.0","source":{"id":"2502.08226","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.08226","created_at":"2026-07-05T10:14:08Z"},{"alias_kind":"arxiv_version","alias_value":"2502.08226v2","created_at":"2026-07-05T10:14:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.08226","created_at":"2026-07-05T10:14:08Z"},{"alias_kind":"pith_short_12","alias_value":"4DAPOLSIRYQX","created_at":"2026-07-05T10:14:08Z"},{"alias_kind":"pith_short_16","alias_value":"4DAPOLSIRYQXCQFD","created_at":"2026-07-05T10:14:08Z"},{"alias_kind":"pith_short_8","alias_value":"4DAPOLSI","created_at":"2026-07-05T10:14:08Z"}],"graph_snapshots":[{"event_id":"sha256:7beb707c68a24149731397f1509fe56c926619d2d48b6b33954c41bc8e3ba3d0","target":"graph","created_at":"2026-07-05T10:14:08Z","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/2502.08226/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in Large Vision Language Models (LVLMs) have enabled the development of LVLM-based Graphical User Interface (GUI) agents under various paradigms. Training-based approaches, such as CogAgent and SeeClick, struggle with cross-dataset and cross-platform generalization due to their reliance on dataset-specific training. Generalist LVLMs, such as GPT-4V, employ Set-of-Marks (SoM) for action grounding, but obtaining SoM labels requires metadata like HTML source, which is not consistently available across platforms. Moreover, existing methods often specialize in singular GUI tasks","authors_text":"Kunal Singh, Mukund Khanna, Shreyas Singh","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-12T09:12:30Z","title":"TRISHUL: Towards Region Identification and Screen Hierarchy Understanding for Large VLM based GUI Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.08226","kind":"arxiv","version":2},"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":"sha256:62dfe1ff6a4055c1fc3007b18ba000b67d681e52d5c843683cc76a69e0cd8314","target":"record","created_at":"2026-07-05T10:14:08Z","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":"4c325c6fd72a4abde25831f847c8a64e86d4f953a79aa0a1576b8eaef53696b9","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-12T09:12:30Z","title_canon_sha256":"53a6dc10a4ba5874432d18ab46555605b0f8d7ea06548c935a0ccb207e3ba9e7"},"schema_version":"1.0","source":{"id":"2502.08226","kind":"arxiv","version":2}},"canonical_sha256":"e0c0f72e488e217140a3b71064d209a2eaa2e677a98dccc7305397612d0b3963","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e0c0f72e488e217140a3b71064d209a2eaa2e677a98dccc7305397612d0b3963","first_computed_at":"2026-07-05T10:14:08.913840Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:14:08.913840Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p2HNRCzeze5bSZ8NOcMLSt27725zy/VzjEy5w5GZw20YdKpXr2mO1RwOh1PELsSjcCmVWfq6cMHwjZoM1NohBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:14:08.914353Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.08226","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:62dfe1ff6a4055c1fc3007b18ba000b67d681e52d5c843683cc76a69e0cd8314","sha256:7beb707c68a24149731397f1509fe56c926619d2d48b6b33954c41bc8e3ba3d0"],"state_sha256":"8733a9bdd2ff712be524fe0ca2902ccc6ba70e1839760ba4651e5634cbe21ffd"}