{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LAUXDK4H37CT5BBVWSXEK2WBLQ","short_pith_number":"pith:LAUXDK4H","schema_version":"1.0","canonical_sha256":"582971ab87dfc53e8435b4ae456ac15c3ee2948f11493257b97263189ee64f7c","source":{"kind":"arxiv","id":"2308.14263","version":3},"attestation_state":"computed","paper":{"title":"Cross-Modal Retrieval: A Systematic Review of Methods and Future Directions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.IR","authors_text":"Fengling Li, Heng Tao Shen, Jingjing Li, Lei Zhu, Tianshi Wang, Zheng Zhang","submitted_at":"2023-08-28T02:38:17Z","abstract_excerpt":"With the exponential surge in diverse multi-modal data, traditional uni-modal retrieval methods struggle to meet the needs of users seeking access to data across various modalities. To address this, cross-modal retrieval has emerged, enabling interaction across modalities, facilitating semantic matching, and leveraging complementarity and consistency between heterogeneous data. Although prior literature has reviewed the field of cross-modal retrieval, it suffers from numerous deficiencies in terms of timeliness, taxonomy, and comprehensiveness. This paper conducts a comprehensive review of cro"},"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":"2308.14263","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-08-28T02:38:17Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"dd8614d3771eb08a55fa857f2d7c528590dffc7a0fb4a1b9768556cc42352134","abstract_canon_sha256":"7636c5fda05ebb89d36d9eac395e27511b5746e9600392cc0c032c37ee8eb7a6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:12:55.855038Z","signature_b64":"mLL7ywoCQhh33XlfDE2H3TBCE4SUpT4fPUy5kU/q0r2zw3ZdScqhC4sXsow0k5fTHpcN56ZZ5e3CSjH4RswYDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"582971ab87dfc53e8435b4ae456ac15c3ee2948f11493257b97263189ee64f7c","last_reissued_at":"2026-07-05T09:12:55.854593Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:12:55.854593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross-Modal Retrieval: A Systematic Review of Methods and Future Directions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.IR","authors_text":"Fengling Li, Heng Tao Shen, Jingjing Li, Lei Zhu, Tianshi Wang, Zheng Zhang","submitted_at":"2023-08-28T02:38:17Z","abstract_excerpt":"With the exponential surge in diverse multi-modal data, traditional uni-modal retrieval methods struggle to meet the needs of users seeking access to data across various modalities. To address this, cross-modal retrieval has emerged, enabling interaction across modalities, facilitating semantic matching, and leveraging complementarity and consistency between heterogeneous data. Although prior literature has reviewed the field of cross-modal retrieval, it suffers from numerous deficiencies in terms of timeliness, taxonomy, and comprehensiveness. This paper conducts a comprehensive review of cro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.14263","kind":"arxiv","version":3},"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/2308.14263/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":"2308.14263","created_at":"2026-07-05T09:12:55.854651+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.14263v3","created_at":"2026-07-05T09:12:55.854651+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.14263","created_at":"2026-07-05T09:12:55.854651+00:00"},{"alias_kind":"pith_short_12","alias_value":"LAUXDK4H37CT","created_at":"2026-07-05T09:12:55.854651+00:00"},{"alias_kind":"pith_short_16","alias_value":"LAUXDK4H37CT5BBV","created_at":"2026-07-05T09:12:55.854651+00:00"},{"alias_kind":"pith_short_8","alias_value":"LAUXDK4H","created_at":"2026-07-05T09:12:55.854651+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.15882","citing_title":"Document Haystack: A Long Context Multimodal Image/Document Understanding Vision LLM Benchmark","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LAUXDK4H37CT5BBVWSXEK2WBLQ","json":"https://pith.science/pith/LAUXDK4H37CT5BBVWSXEK2WBLQ.json","graph_json":"https://pith.science/api/pith-number/LAUXDK4H37CT5BBVWSXEK2WBLQ/graph.json","events_json":"https://pith.science/api/pith-number/LAUXDK4H37CT5BBVWSXEK2WBLQ/events.json","paper":"https://pith.science/paper/LAUXDK4H"},"agent_actions":{"view_html":"https://pith.science/pith/LAUXDK4H37CT5BBVWSXEK2WBLQ","download_json":"https://pith.science/pith/LAUXDK4H37CT5BBVWSXEK2WBLQ.json","view_paper":"https://pith.science/paper/LAUXDK4H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.14263&json=true","fetch_graph":"https://pith.science/api/pith-number/LAUXDK4H37CT5BBVWSXEK2WBLQ/graph.json","fetch_events":"https://pith.science/api/pith-number/LAUXDK4H37CT5BBVWSXEK2WBLQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LAUXDK4H37CT5BBVWSXEK2WBLQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LAUXDK4H37CT5BBVWSXEK2WBLQ/action/storage_attestation","attest_author":"https://pith.science/pith/LAUXDK4H37CT5BBVWSXEK2WBLQ/action/author_attestation","sign_citation":"https://pith.science/pith/LAUXDK4H37CT5BBVWSXEK2WBLQ/action/citation_signature","submit_replication":"https://pith.science/pith/LAUXDK4H37CT5BBVWSXEK2WBLQ/action/replication_record"}},"created_at":"2026-07-05T09:12:55.854651+00:00","updated_at":"2026-07-05T09:12:55.854651+00:00"}