{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4DAPOLSIRYQXCQFDW4IGJUQJUL","short_pith_number":"pith:4DAPOLSI","schema_version":"1.0","canonical_sha256":"e0c0f72e488e217140a3b71064d209a2eaa2e677a98dccc7305397612d0b3963","source":{"kind":"arxiv","id":"2502.08226","version":2},"attestation_state":"computed","paper":{"title":"TRISHUL: Towards Region Identification and Screen Hierarchy Understanding for Large VLM based GUI Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Kunal Singh, Mukund Khanna, Shreyas Singh","submitted_at":"2025-02-12T09:12:30Z","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"},"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":"2502.08226","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-12T09:12:30Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"53a6dc10a4ba5874432d18ab46555605b0f8d7ea06548c935a0ccb207e3ba9e7","abstract_canon_sha256":"4c325c6fd72a4abde25831f847c8a64e86d4f953a79aa0a1576b8eaef53696b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:08.914353Z","signature_b64":"p2HNRCzeze5bSZ8NOcMLSt27725zy/VzjEy5w5GZw20YdKpXr2mO1RwOh1PELsSjcCmVWfq6cMHwjZoM1NohBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e0c0f72e488e217140a3b71064d209a2eaa2e677a98dccc7305397612d0b3963","last_reissued_at":"2026-07-05T10:14:08.913840Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:08.913840Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TRISHUL: Towards Region Identification and Screen Hierarchy Understanding for Large VLM based GUI Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Kunal Singh, Mukund Khanna, Shreyas Singh","submitted_at":"2025-02-12T09:12:30Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.08226","kind":"arxiv","version":2},"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/2502.08226/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":"2502.08226","created_at":"2026-07-05T10:14:08.913900+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.08226v2","created_at":"2026-07-05T10:14:08.913900+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.08226","created_at":"2026-07-05T10:14:08.913900+00:00"},{"alias_kind":"pith_short_12","alias_value":"4DAPOLSIRYQX","created_at":"2026-07-05T10:14:08.913900+00:00"},{"alias_kind":"pith_short_16","alias_value":"4DAPOLSIRYQXCQFD","created_at":"2026-07-05T10:14:08.913900+00:00"},{"alias_kind":"pith_short_8","alias_value":"4DAPOLSI","created_at":"2026-07-05T10:14:08.913900+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.27859","citing_title":"Rethinking Agentic Reinforcement Learning In Large Language Models","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2411.18279","citing_title":"Large Language Model-Brained GUI Agents: A Survey","ref_index":233,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27859","citing_title":"Rethinking Agentic Reinforcement Learning In Large Language Models","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27859","citing_title":"Rethinking Agentic Reinforcement Learning In Large Language Models","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4DAPOLSIRYQXCQFDW4IGJUQJUL","json":"https://pith.science/pith/4DAPOLSIRYQXCQFDW4IGJUQJUL.json","graph_json":"https://pith.science/api/pith-number/4DAPOLSIRYQXCQFDW4IGJUQJUL/graph.json","events_json":"https://pith.science/api/pith-number/4DAPOLSIRYQXCQFDW4IGJUQJUL/events.json","paper":"https://pith.science/paper/4DAPOLSI"},"agent_actions":{"view_html":"https://pith.science/pith/4DAPOLSIRYQXCQFDW4IGJUQJUL","download_json":"https://pith.science/pith/4DAPOLSIRYQXCQFDW4IGJUQJUL.json","view_paper":"https://pith.science/paper/4DAPOLSI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.08226&json=true","fetch_graph":"https://pith.science/api/pith-number/4DAPOLSIRYQXCQFDW4IGJUQJUL/graph.json","fetch_events":"https://pith.science/api/pith-number/4DAPOLSIRYQXCQFDW4IGJUQJUL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4DAPOLSIRYQXCQFDW4IGJUQJUL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4DAPOLSIRYQXCQFDW4IGJUQJUL/action/storage_attestation","attest_author":"https://pith.science/pith/4DAPOLSIRYQXCQFDW4IGJUQJUL/action/author_attestation","sign_citation":"https://pith.science/pith/4DAPOLSIRYQXCQFDW4IGJUQJUL/action/citation_signature","submit_replication":"https://pith.science/pith/4DAPOLSIRYQXCQFDW4IGJUQJUL/action/replication_record"}},"created_at":"2026-07-05T10:14:08.913900+00:00","updated_at":"2026-07-05T10:14:08.913900+00:00"}