{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:OO5GDB66YBSNLH3XYRFTN6W2A7","short_pith_number":"pith:OO5GDB66","canonical_record":{"source":{"id":"2504.01952","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-02T17:56:42Z","cross_cats_sorted":[],"title_canon_sha256":"79a335124418bd91583a4c6a845a7efff739d319bbd8da8f067bab68cfa9549d","abstract_canon_sha256":"10aa190b4b28e134e8a8b137d9939b2f544ad358a5184aebbd3635ee843d747b"},"schema_version":"1.0"},"canonical_sha256":"73ba6187dec064d59f77c44b36fada07e133d60f2052a2d6db52cd6dc15eaad9","source":{"kind":"arxiv","id":"2504.01952","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.01952","created_at":"2026-07-05T10:43:32Z"},{"alias_kind":"arxiv_version","alias_value":"2504.01952v1","created_at":"2026-07-05T10:43:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.01952","created_at":"2026-07-05T10:43:32Z"},{"alias_kind":"pith_short_12","alias_value":"OO5GDB66YBSN","created_at":"2026-07-05T10:43:32Z"},{"alias_kind":"pith_short_16","alias_value":"OO5GDB66YBSNLH3X","created_at":"2026-07-05T10:43:32Z"},{"alias_kind":"pith_short_8","alias_value":"OO5GDB66","created_at":"2026-07-05T10:43:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:OO5GDB66YBSNLH3XYRFTN6W2A7","target":"record","payload":{"canonical_record":{"source":{"id":"2504.01952","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-02T17:56:42Z","cross_cats_sorted":[],"title_canon_sha256":"79a335124418bd91583a4c6a845a7efff739d319bbd8da8f067bab68cfa9549d","abstract_canon_sha256":"10aa190b4b28e134e8a8b137d9939b2f544ad358a5184aebbd3635ee843d747b"},"schema_version":"1.0"},"canonical_sha256":"73ba6187dec064d59f77c44b36fada07e133d60f2052a2d6db52cd6dc15eaad9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:43:32.220496Z","signature_b64":"i8wqcEKkA5smwZpHYoKjMkcZoaUGP9TW+F+2rBXgkzpOp2Xy2uVF9q36pD/hnO1Bd7uuuCXuOKG5REJquPq9Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73ba6187dec064d59f77c44b36fada07e133d60f2052a2d6db52cd6dc15eaad9","last_reissued_at":"2026-07-05T10:43:32.220009Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:43:32.220009Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.01952","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":"2026-07-05T10:43:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"06/ASd5zET4vf1Oxkay5i35+d4wQtv9M/mZOhGj787cQ3pXEiqGGnamGdi3cn2sXRjmBqU1jQqv6RrX+8T34Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T19:51:31.683346Z"},"content_sha256":"41fb6d0f6718bc85542179f7584b475f657ce74b44f951e0949933b877e49ade","schema_version":"1.0","event_id":"sha256:41fb6d0f6718bc85542179f7584b475f657ce74b44f951e0949933b877e49ade"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:OO5GDB66YBSNLH3XYRFTN6W2A7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Image Difference Grounding with Natural Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Erdong Hu, Jing Liu, Wenxuan Wang, Xinlong Wang, Yepeng Tang, Yisi Zhang, Zijia Zhao","submitted_at":"2025-04-02T17:56:42Z","abstract_excerpt":"Visual grounding (VG) typically focuses on locating regions of interest within an image using natural language, and most existing VG methods are limited to single-image interpretations. This limits their applicability in real-world scenarios like automatic surveillance, where detecting subtle but meaningful visual differences across multiple images is crucial. Besides, previous work on image difference understanding (IDU) has either focused on detecting all change regions without cross-modal text guidance, or on providing coarse-grained descriptions of differences. Therefore, to push towards f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.01952","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/2504.01952/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":"2026-07-05T10:43:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vs6mbsodwNNM9qrSLQk+WVs+wPsxEHlMKsdLXGCkd6cSnJGBTAmHccmA+MkpUTar7PtO6uVZDnMuN+xOJ5sNBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T19:51:31.683868Z"},"content_sha256":"a4e402c466a26e8009945cad71b521f4e63120726615a8c3c2f18e2676ecf727","schema_version":"1.0","event_id":"sha256:a4e402c466a26e8009945cad71b521f4e63120726615a8c3c2f18e2676ecf727"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OO5GDB66YBSNLH3XYRFTN6W2A7/bundle.json","state_url":"https://pith.science/pith/OO5GDB66YBSNLH3XYRFTN6W2A7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OO5GDB66YBSNLH3XYRFTN6W2A7/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":"2026-08-12T19:51:31Z","links":{"resolver":"https://pith.science/pith/OO5GDB66YBSNLH3XYRFTN6W2A7","bundle":"https://pith.science/pith/OO5GDB66YBSNLH3XYRFTN6W2A7/bundle.json","state":"https://pith.science/pith/OO5GDB66YBSNLH3XYRFTN6W2A7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OO5GDB66YBSNLH3XYRFTN6W2A7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OO5GDB66YBSNLH3XYRFTN6W2A7","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":"10aa190b4b28e134e8a8b137d9939b2f544ad358a5184aebbd3635ee843d747b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-02T17:56:42Z","title_canon_sha256":"79a335124418bd91583a4c6a845a7efff739d319bbd8da8f067bab68cfa9549d"},"schema_version":"1.0","source":{"id":"2504.01952","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.01952","created_at":"2026-07-05T10:43:32Z"},{"alias_kind":"arxiv_version","alias_value":"2504.01952v1","created_at":"2026-07-05T10:43:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.01952","created_at":"2026-07-05T10:43:32Z"},{"alias_kind":"pith_short_12","alias_value":"OO5GDB66YBSN","created_at":"2026-07-05T10:43:32Z"},{"alias_kind":"pith_short_16","alias_value":"OO5GDB66YBSNLH3X","created_at":"2026-07-05T10:43:32Z"},{"alias_kind":"pith_short_8","alias_value":"OO5GDB66","created_at":"2026-07-05T10:43:32Z"}],"graph_snapshots":[{"event_id":"sha256:a4e402c466a26e8009945cad71b521f4e63120726615a8c3c2f18e2676ecf727","target":"graph","created_at":"2026-07-05T10:43:32Z","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/2504.01952/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual grounding (VG) typically focuses on locating regions of interest within an image using natural language, and most existing VG methods are limited to single-image interpretations. This limits their applicability in real-world scenarios like automatic surveillance, where detecting subtle but meaningful visual differences across multiple images is crucial. Besides, previous work on image difference understanding (IDU) has either focused on detecting all change regions without cross-modal text guidance, or on providing coarse-grained descriptions of differences. Therefore, to push towards f","authors_text":"Erdong Hu, Jing Liu, Wenxuan Wang, Xinlong Wang, Yepeng Tang, Yisi Zhang, Zijia Zhao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-02T17:56:42Z","title":"Image Difference Grounding with Natural Language"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.01952","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":"sha256:41fb6d0f6718bc85542179f7584b475f657ce74b44f951e0949933b877e49ade","target":"record","created_at":"2026-07-05T10:43:32Z","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":"10aa190b4b28e134e8a8b137d9939b2f544ad358a5184aebbd3635ee843d747b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-02T17:56:42Z","title_canon_sha256":"79a335124418bd91583a4c6a845a7efff739d319bbd8da8f067bab68cfa9549d"},"schema_version":"1.0","source":{"id":"2504.01952","kind":"arxiv","version":1}},"canonical_sha256":"73ba6187dec064d59f77c44b36fada07e133d60f2052a2d6db52cd6dc15eaad9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"73ba6187dec064d59f77c44b36fada07e133d60f2052a2d6db52cd6dc15eaad9","first_computed_at":"2026-07-05T10:43:32.220009Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:43:32.220009Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i8wqcEKkA5smwZpHYoKjMkcZoaUGP9TW+F+2rBXgkzpOp2Xy2uVF9q36pD/hnO1Bd7uuuCXuOKG5REJquPq9Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T10:43:32.220496Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.01952","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:41fb6d0f6718bc85542179f7584b475f657ce74b44f951e0949933b877e49ade","sha256:a4e402c466a26e8009945cad71b521f4e63120726615a8c3c2f18e2676ecf727"],"state_sha256":"1c04e153b026fba746f481ed3b8f5950d86ac2f066d490eb9b74fa5072a1aa8d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PfXON57k/2nNrjgmTzWndlTlZIFCg3S0I4/FZqtAddr1QXNMze11MCgJgpRzimtr7JjR3bjNgbOKduQiD2MAAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T19:51:31.687738Z","bundle_sha256":"33a1df1a8da8564f530c138f35af464c2b744ce9d2226470bf0b07866967c7de"}}