{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SAHKLTD2WSHH2VISM3RXJXB2U6","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":"9e8b42bca5d26b6ab788736bf58aa6bb0962e92ee7b4f313746d2f55e22728ff","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T03:33:02Z","title_canon_sha256":"ff1b08f3ed01bf7a59af9fe1446e9d94adaf2886a5ac4951616289e59218aa3a"},"schema_version":"1.0","source":{"id":"2506.23491","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.23491","created_at":"2026-07-05T11:39:12Z"},{"alias_kind":"arxiv_version","alias_value":"2506.23491v3","created_at":"2026-07-05T11:39:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23491","created_at":"2026-07-05T11:39:12Z"},{"alias_kind":"pith_short_12","alias_value":"SAHKLTD2WSHH","created_at":"2026-07-05T11:39:12Z"},{"alias_kind":"pith_short_16","alias_value":"SAHKLTD2WSHH2VIS","created_at":"2026-07-05T11:39:12Z"},{"alias_kind":"pith_short_8","alias_value":"SAHKLTD2","created_at":"2026-07-05T11:39:12Z"}],"graph_snapshots":[{"event_id":"sha256:bf398aeec72391c54dff27bd9f5d79c91e7311804f403774641d0d79f362857c","target":"graph","created_at":"2026-07-05T11:39:12Z","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/2506.23491/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we present ZonUI-3B, a lightweight Vision-Language Model (VLM) that can be fully trained on a single consumer-grade GPU (RTX 4090) while delivering performance comparable to significantly larger models on GUI grounding tasks. The model incorporates several key innovations: (i) combine cross-platform, multi-resolution dataset of 24K examples from diverse sources including mobile, desktop, and web GUI screenshots to effectively address data scarcity in high-resolution desktop environments; (ii) a two-stage fine-tuning strategy, where initial cross-platform training establishes rob","authors_text":"ShengJing Yang, Tzer-Jen Wei, ZongHan Hsieh","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T03:33:02Z","title":"ZonUI-3B: A Lightweight Vision-Language Model for Cross-Resolution GUI Grounding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23491","kind":"arxiv","version":3},"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":"sha256:08a21992fa3184c6ca5289fbca805991b0de81d40e0527184b38dc9eea96d968","target":"record","created_at":"2026-07-05T11:39:12Z","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":"9e8b42bca5d26b6ab788736bf58aa6bb0962e92ee7b4f313746d2f55e22728ff","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T03:33:02Z","title_canon_sha256":"ff1b08f3ed01bf7a59af9fe1446e9d94adaf2886a5ac4951616289e59218aa3a"},"schema_version":"1.0","source":{"id":"2506.23491","kind":"arxiv","version":3}},"canonical_sha256":"900ea5cc7ab48e7d551266e374dc3aa78732826d2d83db5816e4b3fb4984c416","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"900ea5cc7ab48e7d551266e374dc3aa78732826d2d83db5816e4b3fb4984c416","first_computed_at":"2026-07-05T11:39:12.614972Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:39:12.614972Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SWgNErzmT9AJr2TsnTxcgRd0MrSsrMz9y61vqhuEBQHAgmvudk+lcoWt2sJqZodZeZwAglAQNSTFic5AB6frCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:39:12.615480Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.23491","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:08a21992fa3184c6ca5289fbca805991b0de81d40e0527184b38dc9eea96d968","sha256:bf398aeec72391c54dff27bd9f5d79c91e7311804f403774641d0d79f362857c"],"state_sha256":"65601adc4b783ad7e13ae22683724b24ff15f7ced6c391fe70cfdd9d9571850c"}