{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:BBGYH46DZ4OLTJ5ZW7U75UW5L3","short_pith_number":"pith:BBGYH46D","canonical_record":{"source":{"id":"2504.07718","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-10T13:09:52Z","cross_cats_sorted":[],"title_canon_sha256":"d1b520b5e9e021ca4fa1ab87b55ebd39660a16618ec0204dae693e0b6f1eb2eb","abstract_canon_sha256":"d94f202c36b83420f15b9900c3f6b6f747905354dc69ad54eb6ab525cbd4b355"},"schema_version":"1.0"},"canonical_sha256":"084d83f3c3cf1cb9a7b9b7e9fed2dd5eef96e1f367fd96431dfaab6c3c04246f","source":{"kind":"arxiv","id":"2504.07718","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.07718","created_at":"2026-07-05T10:47:13Z"},{"alias_kind":"arxiv_version","alias_value":"2504.07718v1","created_at":"2026-07-05T10:47:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.07718","created_at":"2026-07-05T10:47:13Z"},{"alias_kind":"pith_short_12","alias_value":"BBGYH46DZ4OL","created_at":"2026-07-05T10:47:13Z"},{"alias_kind":"pith_short_16","alias_value":"BBGYH46DZ4OLTJ5Z","created_at":"2026-07-05T10:47:13Z"},{"alias_kind":"pith_short_8","alias_value":"BBGYH46D","created_at":"2026-07-05T10:47:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:BBGYH46DZ4OLTJ5ZW7U75UW5L3","target":"record","payload":{"canonical_record":{"source":{"id":"2504.07718","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-10T13:09:52Z","cross_cats_sorted":[],"title_canon_sha256":"d1b520b5e9e021ca4fa1ab87b55ebd39660a16618ec0204dae693e0b6f1eb2eb","abstract_canon_sha256":"d94f202c36b83420f15b9900c3f6b6f747905354dc69ad54eb6ab525cbd4b355"},"schema_version":"1.0"},"canonical_sha256":"084d83f3c3cf1cb9a7b9b7e9fed2dd5eef96e1f367fd96431dfaab6c3c04246f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:47:13.782285Z","signature_b64":"uQospeCtoco9ukha5vvGRvFR0V3S8xrsqlqX1XP0+DscYPjEOD8mquzi2IuIYtGeDpq/8rH5zJTUucV3eKboCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"084d83f3c3cf1cb9a7b9b7e9fed2dd5eef96e1f367fd96431dfaab6c3c04246f","last_reissued_at":"2026-07-05T10:47:13.781820Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:47:13.781820Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.07718","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":"2026-07-05T10:47:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bNNBz5Tz3nwUqnnqWsOHU5I8/wa85CalSTid3snA6ENIbGi1EU/Jl0HXVhHA4LetDMfRIf2SXrLCzIj7oqDLCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T16:25:01.271514Z"},"content_sha256":"90a2df867460ee9237ac2d75d7c5d8f84f473931aed42993bce99d5629b9836e","schema_version":"1.0","event_id":"sha256:90a2df867460ee9237ac2d75d7c5d8f84f473931aed42993bce99d5629b9836e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:BBGYH46DZ4OLTJ5ZW7U75UW5L3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-modal Reference Learning for Fine-grained Text-to-Image Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Chen, Limin Su, Shiliang Zhang, Wei Zeng, Zehong Ma","submitted_at":"2025-04-10T13:09:52Z","abstract_excerpt":"Fine-grained text-to-image retrieval aims to retrieve a fine-grained target image with a given text query. Existing methods typically assume that each training image is accurately depicted by its textual descriptions. However, textual descriptions can be ambiguous and fail to depict discriminative visual details in images, leading to inaccurate representation learning. To alleviate the effects of text ambiguity, we propose a Multi-Modal Reference learning framework to learn robust representations. We first propose a multi-modal reference construction module to aggregate all visual and textual "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.07718","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/2504.07718/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":"2026-07-05T10:47:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KOrgNxdjU/tGc+EtM8dmwdKvY1waJVIxJiUa8x7xKQc0tgYfFw5kcXN3orh4AL8TBRuOqNtLWwE13U6fWtPvCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T16:25:01.273554Z"},"content_sha256":"e7e407e67a3676e65bcb1fca601d63c1812cc867e19826ce874db5150a1bc664","schema_version":"1.0","event_id":"sha256:e7e407e67a3676e65bcb1fca601d63c1812cc867e19826ce874db5150a1bc664"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BBGYH46DZ4OLTJ5ZW7U75UW5L3/bundle.json","state_url":"https://pith.science/pith/BBGYH46DZ4OLTJ5ZW7U75UW5L3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BBGYH46DZ4OLTJ5ZW7U75UW5L3/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":"2026-08-10T16:25:01Z","links":{"resolver":"https://pith.science/pith/BBGYH46DZ4OLTJ5ZW7U75UW5L3","bundle":"https://pith.science/pith/BBGYH46DZ4OLTJ5ZW7U75UW5L3/bundle.json","state":"https://pith.science/pith/BBGYH46DZ4OLTJ5ZW7U75UW5L3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BBGYH46DZ4OLTJ5ZW7U75UW5L3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BBGYH46DZ4OLTJ5ZW7U75UW5L3","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":"d94f202c36b83420f15b9900c3f6b6f747905354dc69ad54eb6ab525cbd4b355","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-10T13:09:52Z","title_canon_sha256":"d1b520b5e9e021ca4fa1ab87b55ebd39660a16618ec0204dae693e0b6f1eb2eb"},"schema_version":"1.0","source":{"id":"2504.07718","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.07718","created_at":"2026-07-05T10:47:13Z"},{"alias_kind":"arxiv_version","alias_value":"2504.07718v1","created_at":"2026-07-05T10:47:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.07718","created_at":"2026-07-05T10:47:13Z"},{"alias_kind":"pith_short_12","alias_value":"BBGYH46DZ4OL","created_at":"2026-07-05T10:47:13Z"},{"alias_kind":"pith_short_16","alias_value":"BBGYH46DZ4OLTJ5Z","created_at":"2026-07-05T10:47:13Z"},{"alias_kind":"pith_short_8","alias_value":"BBGYH46D","created_at":"2026-07-05T10:47:13Z"}],"graph_snapshots":[{"event_id":"sha256:e7e407e67a3676e65bcb1fca601d63c1812cc867e19826ce874db5150a1bc664","target":"graph","created_at":"2026-07-05T10:47:13Z","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/2504.07718/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fine-grained text-to-image retrieval aims to retrieve a fine-grained target image with a given text query. Existing methods typically assume that each training image is accurately depicted by its textual descriptions. However, textual descriptions can be ambiguous and fail to depict discriminative visual details in images, leading to inaccurate representation learning. To alleviate the effects of text ambiguity, we propose a Multi-Modal Reference learning framework to learn robust representations. We first propose a multi-modal reference construction module to aggregate all visual and textual ","authors_text":"Hao Chen, Limin Su, Shiliang Zhang, Wei Zeng, Zehong Ma","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-10T13:09:52Z","title":"Multi-modal Reference Learning for Fine-grained Text-to-Image Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.07718","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":"sha256:90a2df867460ee9237ac2d75d7c5d8f84f473931aed42993bce99d5629b9836e","target":"record","created_at":"2026-07-05T10:47:13Z","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":"d94f202c36b83420f15b9900c3f6b6f747905354dc69ad54eb6ab525cbd4b355","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-10T13:09:52Z","title_canon_sha256":"d1b520b5e9e021ca4fa1ab87b55ebd39660a16618ec0204dae693e0b6f1eb2eb"},"schema_version":"1.0","source":{"id":"2504.07718","kind":"arxiv","version":1}},"canonical_sha256":"084d83f3c3cf1cb9a7b9b7e9fed2dd5eef96e1f367fd96431dfaab6c3c04246f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"084d83f3c3cf1cb9a7b9b7e9fed2dd5eef96e1f367fd96431dfaab6c3c04246f","first_computed_at":"2026-07-05T10:47:13.781820Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:47:13.781820Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uQospeCtoco9ukha5vvGRvFR0V3S8xrsqlqX1XP0+DscYPjEOD8mquzi2IuIYtGeDpq/8rH5zJTUucV3eKboCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:47:13.782285Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.07718","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:90a2df867460ee9237ac2d75d7c5d8f84f473931aed42993bce99d5629b9836e","sha256:e7e407e67a3676e65bcb1fca601d63c1812cc867e19826ce874db5150a1bc664"],"state_sha256":"109f047962ae9c9925f2b92ac24a3df1a6e9d923e263ce213dada0f937654446"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YQScnFjK7K3XEHvRshFZz2tY8OLgl0IQBiu1YgYiWD/QTfs9cQZauplAx7MyjMqVlQ9sj6dIKz+qNmsff449DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T16:25:01.279335Z","bundle_sha256":"ad7d93998204bf2883e8d5bfda383f03d3981e6174a22d869d5f43690a6e86ec"}}