{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6L6NVUPN6JRQTSNHOIK7HGTTY4","short_pith_number":"pith:6L6NVUPN","schema_version":"1.0","canonical_sha256":"f2fcdad1edf26309c9a77215f39a73c71baba405658c76a9c694ed83d8e13c63","source":{"kind":"arxiv","id":"2507.20620","version":1},"attestation_state":"computed","paper":{"title":"Complementarity-driven Representation Learning for Multi-modal Knowledge Graph Completion","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Lijian Li","submitted_at":"2025-07-28T08:35:11Z","abstract_excerpt":"Multi-modal Knowledge Graph Completion (MMKGC) aims to uncover hidden world knowledge in multimodal knowledge graphs by leveraging both multimodal and structural entity information. However, the inherent imbalance in multimodal knowledge graphs, where modality distributions vary across entities, poses challenges in utilizing additional modality data for robust entity representation. Existing MMKGC methods typically rely on attention or gate-based fusion mechanisms but overlook complementarity contained in multi-modal data. In this paper, we propose a novel framework named Mixture of Complement"},"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":"2507.20620","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-28T08:35:11Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"d5bb8aa8aa1ab51025eba236d9998779378f1e9f2a552229c85ed196c9a7ebfa","abstract_canon_sha256":"e4e797f6e39aa246492d2b31b46a31474a0f4681b5390d486300ef5090eb9cb4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:22.640364Z","signature_b64":"xW94CkxtimUJt89wYn4NbSYl0X9uI2TSyT7wEHtJTNtUcw3SldaEVN7UVZn+M+nF5HVeoPrLtuTHXvTRLG8pCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2fcdad1edf26309c9a77215f39a73c71baba405658c76a9c694ed83d8e13c63","last_reissued_at":"2026-07-05T11:44:22.640003Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:22.640003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Complementarity-driven Representation Learning for Multi-modal Knowledge Graph Completion","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Lijian Li","submitted_at":"2025-07-28T08:35:11Z","abstract_excerpt":"Multi-modal Knowledge Graph Completion (MMKGC) aims to uncover hidden world knowledge in multimodal knowledge graphs by leveraging both multimodal and structural entity information. However, the inherent imbalance in multimodal knowledge graphs, where modality distributions vary across entities, poses challenges in utilizing additional modality data for robust entity representation. Existing MMKGC methods typically rely on attention or gate-based fusion mechanisms but overlook complementarity contained in multi-modal data. In this paper, we propose a novel framework named Mixture of Complement"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.20620","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/2507.20620/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":"2507.20620","created_at":"2026-07-05T11:44:22.640056+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.20620v1","created_at":"2026-07-05T11:44:22.640056+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.20620","created_at":"2026-07-05T11:44:22.640056+00:00"},{"alias_kind":"pith_short_12","alias_value":"6L6NVUPN6JRQ","created_at":"2026-07-05T11:44:22.640056+00:00"},{"alias_kind":"pith_short_16","alias_value":"6L6NVUPN6JRQTSNH","created_at":"2026-07-05T11:44:22.640056+00:00"},{"alias_kind":"pith_short_8","alias_value":"6L6NVUPN","created_at":"2026-07-05T11:44:22.640056+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6L6NVUPN6JRQTSNHOIK7HGTTY4","json":"https://pith.science/pith/6L6NVUPN6JRQTSNHOIK7HGTTY4.json","graph_json":"https://pith.science/api/pith-number/6L6NVUPN6JRQTSNHOIK7HGTTY4/graph.json","events_json":"https://pith.science/api/pith-number/6L6NVUPN6JRQTSNHOIK7HGTTY4/events.json","paper":"https://pith.science/paper/6L6NVUPN"},"agent_actions":{"view_html":"https://pith.science/pith/6L6NVUPN6JRQTSNHOIK7HGTTY4","download_json":"https://pith.science/pith/6L6NVUPN6JRQTSNHOIK7HGTTY4.json","view_paper":"https://pith.science/paper/6L6NVUPN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.20620&json=true","fetch_graph":"https://pith.science/api/pith-number/6L6NVUPN6JRQTSNHOIK7HGTTY4/graph.json","fetch_events":"https://pith.science/api/pith-number/6L6NVUPN6JRQTSNHOIK7HGTTY4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6L6NVUPN6JRQTSNHOIK7HGTTY4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6L6NVUPN6JRQTSNHOIK7HGTTY4/action/storage_attestation","attest_author":"https://pith.science/pith/6L6NVUPN6JRQTSNHOIK7HGTTY4/action/author_attestation","sign_citation":"https://pith.science/pith/6L6NVUPN6JRQTSNHOIK7HGTTY4/action/citation_signature","submit_replication":"https://pith.science/pith/6L6NVUPN6JRQTSNHOIK7HGTTY4/action/replication_record"}},"created_at":"2026-07-05T11:44:22.640056+00:00","updated_at":"2026-07-05T11:44:22.640056+00:00"}