{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:JSVSV57KALAGUS7TLIMRPRJ6PS","short_pith_number":"pith:JSVSV57K","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"},"canonical_sha256":"4cab2af7ea02c06a4bf35a1917c53e7cb8ae5b6e417a369618ab858ea98c707d","source":{"kind":"arxiv","id":"2605.29615","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:JSVSV57KALAGUS7TLIMRPRJ6PS","target":"record","payload":{"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"},"canonical_sha256":"4cab2af7ea02c06a4bf35a1917c53e7cb8ae5b6e417a369618ab858ea98c707d","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"},"source_kind":"arxiv","source_id":"2605.29615","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-29T01:05:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5TWBmpOx3YoWxyB2/NaAmTHDVRg/rBOzX1YKFim9ZlxlEK9vpGWHk5gJzkkEq7GhLGjRFS8zEB7rS02brQ29BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T15:01:22.984495Z"},"content_sha256":"0f4675f94c7f70a8a66721c1e08679b84b1a716b5c4d96500b61c6f00352088f","schema_version":"1.0","event_id":"sha256:0f4675f94c7f70a8a66721c1e08679b84b1a716b5c4d96500b61c6f00352088f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:JSVSV57KALAGUS7TLIMRPRJ6PS","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-29T01:05:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aVBdQJjncAl0X11MNOZw+yIQk0t/OPvAhtKK2vL18kdNe83L2Jvwxf9Y56jSPdDJimJSszIPSCzI60liR6eNCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T15:01:22.984878Z"},"content_sha256":"bf127289a847a1b677d9f341fd2a84ca791f217846163c90e6a7825a52dd9ac6","schema_version":"1.0","event_id":"sha256:bf127289a847a1b677d9f341fd2a84ca791f217846163c90e6a7825a52dd9ac6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JSVSV57KALAGUS7TLIMRPRJ6PS/bundle.json","state_url":"https://pith.science/pith/JSVSV57KALAGUS7TLIMRPRJ6PS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JSVSV57KALAGUS7TLIMRPRJ6PS/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-01T15:01:22Z","links":{"resolver":"https://pith.science/pith/JSVSV57KALAGUS7TLIMRPRJ6PS","bundle":"https://pith.science/pith/JSVSV57KALAGUS7TLIMRPRJ6PS/bundle.json","state":"https://pith.science/pith/JSVSV57KALAGUS7TLIMRPRJ6PS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JSVSV57KALAGUS7TLIMRPRJ6PS/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JU3a89Sf39QlvZn5texo2wa4/pmiaK4uwUsHOq5wNy0vPReAdijormjnXtdd2CTBtfByNWDUyiSjtiEEW1EFAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-01T15:01:22.987089Z","bundle_sha256":"94c146e05f11a9898100d72bb81cfb6030c50de3cafec32095051f981677ec5c"}}