{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:W6LD32XSTCI425C4CJ4KXXTRS6","short_pith_number":"pith:W6LD32XS","schema_version":"1.0","canonical_sha256":"b7963deaf29891cd745c1278abde7197bcfbce321ac75d4145eca6819d4e4055","source":{"kind":"arxiv","id":"2402.05391","version":4},"attestation_state":"computed","paper":{"title":"Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.IR","cs.LG"],"primary_cat":"cs.AI","authors_text":"Huajun Chen, Jeff Z. Pan, Jiaoyan Chen, Jiaqi Li, Lingbing Guo, Ningyu Zhang, Qian Li, Wen Zhang, Xiang Chen, Xiaoze Liu, Yichi Zhang, Yin Fang, Yushan Zhu, Yuxia Geng, Zhuo Chen","submitted_at":"2024-02-08T04:04:36Z","abstract_excerpt":"Knowledge Graphs (KGs) play a pivotal role in advancing various AI applications, with the semantic web community's exploration into multi-modal dimensions unlocking new avenues for innovation. In this survey, we carefully review over 300 articles, focusing on KG-aware research in two principal aspects: KG-driven Multi-Modal (KG4MM) learning, where KGs support multi-modal tasks, and Multi-Modal Knowledge Graph (MM4KG), which extends KG studies into the MMKG realm. We begin by defining KGs and MMKGs, then explore their construction progress. Our review includes two primary task categories: KG-aw"},"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":"2402.05391","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-02-08T04:04:36Z","cross_cats_sorted":["cs.CV","cs.IR","cs.LG"],"title_canon_sha256":"9e9472b53c2f20f46e21971c78c7259a5ba212ed908e709ccd01de7b09c538f9","abstract_canon_sha256":"a3b4aa34c4857115464eacfa99a00a53e85e80c616dc58ed967958c447021214"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:49:17.854690Z","signature_b64":"GMVqhumM4T29efNQZMa5YHJAuEqIGBs1wERX4Yd+d0LqzMNZgXV/Y56g148bzlCdNy7kTlysovkFC01ZqBN0BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7963deaf29891cd745c1278abde7197bcfbce321ac75d4145eca6819d4e4055","last_reissued_at":"2026-07-05T07:49:17.854218Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:49:17.854218Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.IR","cs.LG"],"primary_cat":"cs.AI","authors_text":"Huajun Chen, Jeff Z. Pan, Jiaoyan Chen, Jiaqi Li, Lingbing Guo, Ningyu Zhang, Qian Li, Wen Zhang, Xiang Chen, Xiaoze Liu, Yichi Zhang, Yin Fang, Yushan Zhu, Yuxia Geng, Zhuo Chen","submitted_at":"2024-02-08T04:04:36Z","abstract_excerpt":"Knowledge Graphs (KGs) play a pivotal role in advancing various AI applications, with the semantic web community's exploration into multi-modal dimensions unlocking new avenues for innovation. In this survey, we carefully review over 300 articles, focusing on KG-aware research in two principal aspects: KG-driven Multi-Modal (KG4MM) learning, where KGs support multi-modal tasks, and Multi-Modal Knowledge Graph (MM4KG), which extends KG studies into the MMKG realm. We begin by defining KGs and MMKGs, then explore their construction progress. Our review includes two primary task categories: KG-aw"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.05391","kind":"arxiv","version":4},"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/2402.05391/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":"2402.05391","created_at":"2026-07-05T07:49:17.854272+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.05391v4","created_at":"2026-07-05T07:49:17.854272+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.05391","created_at":"2026-07-05T07:49:17.854272+00:00"},{"alias_kind":"pith_short_12","alias_value":"W6LD32XSTCI4","created_at":"2026-07-05T07:49:17.854272+00:00"},{"alias_kind":"pith_short_16","alias_value":"W6LD32XSTCI425C4","created_at":"2026-07-05T07:49:17.854272+00:00"},{"alias_kind":"pith_short_8","alias_value":"W6LD32XS","created_at":"2026-07-05T07:49:17.854272+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06869","citing_title":"Evidence-Based Intelligent Diagnostic and Therapeutic Visualization System with Large Language Models: Multi-Turn Interaction and Multimodal Treatment Plan Generation","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06869","citing_title":"Evidence-Based Intelligent Diagnostic and Therapeutic Visualization System with Large Language Models: Multi-Turn Interaction and Multimodal Treatment Plan Generation","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2411.14072","citing_title":"The Master-Slave Encoder Model for Improving Patent Text Summarization: A New Approach to Combining Specifications and Claims","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2510.21828","citing_title":"Structured and Abstractive Reasoning on Multi-modal Relational Knowledge Images","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02778","citing_title":"When Modalities Remember: Continual Learning for Multimodal Knowledge Graphs","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25693","citing_title":"RADD: Retrieval-Augmented Discrete Diffusion for Multi-Modal Knowledge Graph Completion","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20283","citing_title":"Multi-Perspective Evidence Synthesis and Reasoning for Unsupervised Multimodal Entity Linking","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W6LD32XSTCI425C4CJ4KXXTRS6","json":"https://pith.science/pith/W6LD32XSTCI425C4CJ4KXXTRS6.json","graph_json":"https://pith.science/api/pith-number/W6LD32XSTCI425C4CJ4KXXTRS6/graph.json","events_json":"https://pith.science/api/pith-number/W6LD32XSTCI425C4CJ4KXXTRS6/events.json","paper":"https://pith.science/paper/W6LD32XS"},"agent_actions":{"view_html":"https://pith.science/pith/W6LD32XSTCI425C4CJ4KXXTRS6","download_json":"https://pith.science/pith/W6LD32XSTCI425C4CJ4KXXTRS6.json","view_paper":"https://pith.science/paper/W6LD32XS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.05391&json=true","fetch_graph":"https://pith.science/api/pith-number/W6LD32XSTCI425C4CJ4KXXTRS6/graph.json","fetch_events":"https://pith.science/api/pith-number/W6LD32XSTCI425C4CJ4KXXTRS6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W6LD32XSTCI425C4CJ4KXXTRS6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W6LD32XSTCI425C4CJ4KXXTRS6/action/storage_attestation","attest_author":"https://pith.science/pith/W6LD32XSTCI425C4CJ4KXXTRS6/action/author_attestation","sign_citation":"https://pith.science/pith/W6LD32XSTCI425C4CJ4KXXTRS6/action/citation_signature","submit_replication":"https://pith.science/pith/W6LD32XSTCI425C4CJ4KXXTRS6/action/replication_record"}},"created_at":"2026-07-05T07:49:17.854272+00:00","updated_at":"2026-07-05T07:49:17.854272+00:00"}