{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JSVSV57KALAGUS7TLIMRPRJ6PS","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":"7d17162ab0b01a73aa4cbd4dad30e7f05a91bc3eb9165e1a318a857fc057e7be","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T08:50:34Z","title_canon_sha256":"f77309a43dffa75c46a3ba17529241cb9e68ff9e1762fadd6eb8e282fb2ba1b7"},"schema_version":"1.0","source":{"id":"2605.29615","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.29615","created_at":"2026-05-29T01:05:51Z"},{"alias_kind":"arxiv_version","alias_value":"2605.29615v1","created_at":"2026-05-29T01:05:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29615","created_at":"2026-05-29T01:05:51Z"},{"alias_kind":"pith_short_12","alias_value":"JSVSV57KALAG","created_at":"2026-05-29T01:05:51Z"},{"alias_kind":"pith_short_16","alias_value":"JSVSV57KALAGUS7T","created_at":"2026-05-29T01:05:51Z"},{"alias_kind":"pith_short_8","alias_value":"JSVSV57K","created_at":"2026-05-29T01:05:51Z"}],"graph_snapshots":[{"event_id":"sha256:bf127289a847a1b677d9f341fd2a84ca791f217846163c90e6a7825a52dd9ac6","target":"graph","created_at":"2026-05-29T01:05:51Z","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/2605.29615/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models (VLMs) have made strong progress on high-level image-text alignment, yet their ability to perceive subtle visual differences remains limited. We study this problem in rendered web interfaces, where localized visual changes are both a diagnostic test of fine-grained perception and a practical requirement for GUI agents and design tools. We introduce \\textbf{DiffSpot}, a code-driven benchmark for open-ended spot-the-difference on web interfaces. DiffSpot constructs controlled image pairs by mutating a single CSS property of a target element in self-contained HTML, re-rende","authors_text":"Aiwei Liu, Linhao Zhang, Xiao Zhou, Yuan Liu","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T08:50:34Z","title":"DiffSpot: Can VLMs Spot Fine-Grained Visual Differences in Web Interfaces?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29615","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":"sha256:0f4675f94c7f70a8a66721c1e08679b84b1a716b5c4d96500b61c6f00352088f","target":"record","created_at":"2026-05-29T01:05:51Z","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":"7d17162ab0b01a73aa4cbd4dad30e7f05a91bc3eb9165e1a318a857fc057e7be","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T08:50:34Z","title_canon_sha256":"f77309a43dffa75c46a3ba17529241cb9e68ff9e1762fadd6eb8e282fb2ba1b7"},"schema_version":"1.0","source":{"id":"2605.29615","kind":"arxiv","version":1}},"canonical_sha256":"4cab2af7ea02c06a4bf35a1917c53e7cb8ae5b6e417a369618ab858ea98c707d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4cab2af7ea02c06a4bf35a1917c53e7cb8ae5b6e417a369618ab858ea98c707d","first_computed_at":"2026-05-29T01:05:51.105247Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T01:05:51.105247Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zu+uEE17Rc/HwJGyvfyHiVqnUVKoSv8NiUxT7jsrv2fEIGcnqu6wcZssH/kyHhlSqoc0S5J5oHbLVvyK+uyCDQ==","signature_status":"signed_v1","signed_at":"2026-05-29T01:05:51.106054Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.29615","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0f4675f94c7f70a8a66721c1e08679b84b1a716b5c4d96500b61c6f00352088f","sha256:bf127289a847a1b677d9f341fd2a84ca791f217846163c90e6a7825a52dd9ac6"],"state_sha256":"ff309d244fcbef43b7fb1ac748a15ef4b0570d021ba8a2f160caf8e2c46f5147"}