{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JSVSV57KALAGUS7TLIMRPRJ6PS","short_pith_number":"pith:JSVSV57K","schema_version":"1.0","canonical_sha256":"4cab2af7ea02c06a4bf35a1917c53e7cb8ae5b6e417a369618ab858ea98c707d","source":{"kind":"arxiv","id":"2605.29615","version":1},"attestation_state":"computed","paper":{"title":"DiffSpot: Can VLMs Spot Fine-Grained Visual Differences in Web Interfaces?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Aiwei Liu, Linhao Zhang, Xiao Zhou, Yuan Liu","submitted_at":"2026-05-28T08:50:34Z","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"},"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":"2605.29615","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T08:50:34Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"f77309a43dffa75c46a3ba17529241cb9e68ff9e1762fadd6eb8e282fb2ba1b7","abstract_canon_sha256":"7d17162ab0b01a73aa4cbd4dad30e7f05a91bc3eb9165e1a318a857fc057e7be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:05:51.106054Z","signature_b64":"zu+uEE17Rc/HwJGyvfyHiVqnUVKoSv8NiUxT7jsrv2fEIGcnqu6wcZssH/kyHhlSqoc0S5J5oHbLVvyK+uyCDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4cab2af7ea02c06a4bf35a1917c53e7cb8ae5b6e417a369618ab858ea98c707d","last_reissued_at":"2026-05-29T01:05:51.105247Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:05:51.105247Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiffSpot: Can VLMs Spot Fine-Grained Visual Differences in Web Interfaces?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Aiwei Liu, Linhao Zhang, Xiao Zhou, Yuan Liu","submitted_at":"2026-05-28T08:50:34Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29615","kind":"arxiv","version":1},"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/2605.29615/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":"2605.29615","created_at":"2026-05-29T01:05:51.105385+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.29615v1","created_at":"2026-05-29T01:05:51.105385+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29615","created_at":"2026-05-29T01:05:51.105385+00:00"},{"alias_kind":"pith_short_12","alias_value":"JSVSV57KALAG","created_at":"2026-05-29T01:05:51.105385+00:00"},{"alias_kind":"pith_short_16","alias_value":"JSVSV57KALAGUS7T","created_at":"2026-05-29T01:05:51.105385+00:00"},{"alias_kind":"pith_short_8","alias_value":"JSVSV57K","created_at":"2026-05-29T01:05:51.105385+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JSVSV57KALAGUS7TLIMRPRJ6PS","json":"https://pith.science/pith/JSVSV57KALAGUS7TLIMRPRJ6PS.json","graph_json":"https://pith.science/api/pith-number/JSVSV57KALAGUS7TLIMRPRJ6PS/graph.json","events_json":"https://pith.science/api/pith-number/JSVSV57KALAGUS7TLIMRPRJ6PS/events.json","paper":"https://pith.science/paper/JSVSV57K"},"agent_actions":{"view_html":"https://pith.science/pith/JSVSV57KALAGUS7TLIMRPRJ6PS","download_json":"https://pith.science/pith/JSVSV57KALAGUS7TLIMRPRJ6PS.json","view_paper":"https://pith.science/paper/JSVSV57K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.29615&json=true","fetch_graph":"https://pith.science/api/pith-number/JSVSV57KALAGUS7TLIMRPRJ6PS/graph.json","fetch_events":"https://pith.science/api/pith-number/JSVSV57KALAGUS7TLIMRPRJ6PS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JSVSV57KALAGUS7TLIMRPRJ6PS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JSVSV57KALAGUS7TLIMRPRJ6PS/action/storage_attestation","attest_author":"https://pith.science/pith/JSVSV57KALAGUS7TLIMRPRJ6PS/action/author_attestation","sign_citation":"https://pith.science/pith/JSVSV57KALAGUS7TLIMRPRJ6PS/action/citation_signature","submit_replication":"https://pith.science/pith/JSVSV57KALAGUS7TLIMRPRJ6PS/action/replication_record"}},"created_at":"2026-05-29T01:05:51.105385+00:00","updated_at":"2026-05-29T01:05:51.105385+00:00"}