{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:M3WSTZWAXWON4MGQZV3JQVU74Q","short_pith_number":"pith:M3WSTZWA","canonical_record":{"source":{"id":"2505.18594","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-24T08:41:51Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"694db9f07ef0007247152c28662bc3d1635a2b842364e356b4a4fd2b6e039d74","abstract_canon_sha256":"0a135d4748a30a9f855282da6758b7ac0a8a87dd04805077bb7cdd9f3070a9cd"},"schema_version":"1.0"},"canonical_sha256":"66ed29e6c0bd9cde30d0cd7698569fe40d2bd3a9c97e967f472664eabca0ebce","source":{"kind":"arxiv","id":"2505.18594","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.18594","created_at":"2026-07-05T11:09:16Z"},{"alias_kind":"arxiv_version","alias_value":"2505.18594v1","created_at":"2026-07-05T11:09:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18594","created_at":"2026-07-05T11:09:16Z"},{"alias_kind":"pith_short_12","alias_value":"M3WSTZWAXWON","created_at":"2026-07-05T11:09:16Z"},{"alias_kind":"pith_short_16","alias_value":"M3WSTZWAXWON4MGQ","created_at":"2026-07-05T11:09:16Z"},{"alias_kind":"pith_short_8","alias_value":"M3WSTZWA","created_at":"2026-07-05T11:09:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:M3WSTZWAXWON4MGQZV3JQVU74Q","target":"record","payload":{"canonical_record":{"source":{"id":"2505.18594","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-24T08:41:51Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"694db9f07ef0007247152c28662bc3d1635a2b842364e356b4a4fd2b6e039d74","abstract_canon_sha256":"0a135d4748a30a9f855282da6758b7ac0a8a87dd04805077bb7cdd9f3070a9cd"},"schema_version":"1.0"},"canonical_sha256":"66ed29e6c0bd9cde30d0cd7698569fe40d2bd3a9c97e967f472664eabca0ebce","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:16.247849Z","signature_b64":"wtc8yLO33Ub8fbzBOSAMAgRSi3jkSYyvGZ0TLZj/D3muJI45TAyun4u/OJ67RxaEqNonDZm/rk3Pg2Zo1ciLBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66ed29e6c0bd9cde30d0cd7698569fe40d2bd3a9c97e967f472664eabca0ebce","last_reissued_at":"2026-07-05T11:09:16.247336Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:16.247336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.18594","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":"2026-07-05T11:09:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nNe2TjFR1YPG4fPS9gtBs/tCepDP7ORh72djOuShCYIalw8TTAa6J/UuVnTCCU+chyt/Ri31kyEpqfNhC/ewBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T21:58:37.797927Z"},"content_sha256":"81810d831d407181e9ec7078e2b532e4431e4ff3a83090bc63a780cbe4b76a2b","schema_version":"1.0","event_id":"sha256:81810d831d407181e9ec7078e2b532e4431e4ff3a83090bc63a780cbe4b76a2b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:M3WSTZWAXWON4MGQZV3JQVU74Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"EvdCLIP: Improving Vision-Language Retrieval with Entity Visual Descriptions from Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CV","authors_text":"Gang Wang, Guanghao Meng, Jieming Zhu, Jinpeng Wang, Letian Zhang, Qing Li, Rui Zhang, Sunan He, Tao Dai, Yong Jiang","submitted_at":"2025-05-24T08:41:51Z","abstract_excerpt":"Vision-language retrieval (VLR) has attracted significant attention in both academia and industry, which involves using text (or images) as queries to retrieve corresponding images (or text). However, existing methods often neglect the rich visual semantics knowledge of entities, thus leading to incorrect retrieval results. To address this problem, we propose the Entity Visual Description enhanced CLIP (EvdCLIP), designed to leverage the visual knowledge of entities to enrich queries. Specifically, since humans recognize entities through visual cues, we employ a large language model (LLM) to g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18594","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/2505.18594/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":"2026-07-05T11:09:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Od6dX6f8YLEPtfGdm3+RIBknQR5ERp5iJ2FlCqdWH10QH0tFpOVhL8/qmoQPHGwNia0Nt4T70D/x03tKJLZoDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T21:58:37.798789Z"},"content_sha256":"5ae5591c72084a9ea5b441efb2eab492648c42ec6b291659e4404136bcf91476","schema_version":"1.0","event_id":"sha256:5ae5591c72084a9ea5b441efb2eab492648c42ec6b291659e4404136bcf91476"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M3WSTZWAXWON4MGQZV3JQVU74Q/bundle.json","state_url":"https://pith.science/pith/M3WSTZWAXWON4MGQZV3JQVU74Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M3WSTZWAXWON4MGQZV3JQVU74Q/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":"2026-07-07T21:58:37Z","links":{"resolver":"https://pith.science/pith/M3WSTZWAXWON4MGQZV3JQVU74Q","bundle":"https://pith.science/pith/M3WSTZWAXWON4MGQZV3JQVU74Q/bundle.json","state":"https://pith.science/pith/M3WSTZWAXWON4MGQZV3JQVU74Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M3WSTZWAXWON4MGQZV3JQVU74Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:M3WSTZWAXWON4MGQZV3JQVU74Q","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":"0a135d4748a30a9f855282da6758b7ac0a8a87dd04805077bb7cdd9f3070a9cd","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-24T08:41:51Z","title_canon_sha256":"694db9f07ef0007247152c28662bc3d1635a2b842364e356b4a4fd2b6e039d74"},"schema_version":"1.0","source":{"id":"2505.18594","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.18594","created_at":"2026-07-05T11:09:16Z"},{"alias_kind":"arxiv_version","alias_value":"2505.18594v1","created_at":"2026-07-05T11:09:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18594","created_at":"2026-07-05T11:09:16Z"},{"alias_kind":"pith_short_12","alias_value":"M3WSTZWAXWON","created_at":"2026-07-05T11:09:16Z"},{"alias_kind":"pith_short_16","alias_value":"M3WSTZWAXWON4MGQ","created_at":"2026-07-05T11:09:16Z"},{"alias_kind":"pith_short_8","alias_value":"M3WSTZWA","created_at":"2026-07-05T11:09:16Z"}],"graph_snapshots":[{"event_id":"sha256:5ae5591c72084a9ea5b441efb2eab492648c42ec6b291659e4404136bcf91476","target":"graph","created_at":"2026-07-05T11:09:16Z","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/2505.18594/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language retrieval (VLR) has attracted significant attention in both academia and industry, which involves using text (or images) as queries to retrieve corresponding images (or text). However, existing methods often neglect the rich visual semantics knowledge of entities, thus leading to incorrect retrieval results. To address this problem, we propose the Entity Visual Description enhanced CLIP (EvdCLIP), designed to leverage the visual knowledge of entities to enrich queries. Specifically, since humans recognize entities through visual cues, we employ a large language model (LLM) to g","authors_text":"Gang Wang, Guanghao Meng, Jieming Zhu, Jinpeng Wang, Letian Zhang, Qing Li, Rui Zhang, Sunan He, Tao Dai, Yong Jiang","cross_cats":["cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-24T08:41:51Z","title":"EvdCLIP: Improving Vision-Language Retrieval with Entity Visual Descriptions from Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18594","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":"sha256:81810d831d407181e9ec7078e2b532e4431e4ff3a83090bc63a780cbe4b76a2b","target":"record","created_at":"2026-07-05T11:09:16Z","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":"0a135d4748a30a9f855282da6758b7ac0a8a87dd04805077bb7cdd9f3070a9cd","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-24T08:41:51Z","title_canon_sha256":"694db9f07ef0007247152c28662bc3d1635a2b842364e356b4a4fd2b6e039d74"},"schema_version":"1.0","source":{"id":"2505.18594","kind":"arxiv","version":1}},"canonical_sha256":"66ed29e6c0bd9cde30d0cd7698569fe40d2bd3a9c97e967f472664eabca0ebce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"66ed29e6c0bd9cde30d0cd7698569fe40d2bd3a9c97e967f472664eabca0ebce","first_computed_at":"2026-07-05T11:09:16.247336Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:16.247336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wtc8yLO33Ub8fbzBOSAMAgRSi3jkSYyvGZ0TLZj/D3muJI45TAyun4u/OJ67RxaEqNonDZm/rk3Pg2Zo1ciLBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:16.247849Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.18594","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:81810d831d407181e9ec7078e2b532e4431e4ff3a83090bc63a780cbe4b76a2b","sha256:5ae5591c72084a9ea5b441efb2eab492648c42ec6b291659e4404136bcf91476"],"state_sha256":"c91e51cd8a4b21be34bc51c42cdfb1cde8331289500ef04880e07b80f9765aaf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xBj3uWSkvYYbjlgr2oO4E07/caWu6E/YD+UABdEOEUw+Bra/o8k79L135HRQ2eY7BqHzKsYOQ8k8uhZGPerRBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T21:58:37.802378Z","bundle_sha256":"57591ed2da378653e45ad5d468116530c78c26edd48b4268a94eb117cfcba612"}}