{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:A6JQZEIKZZRDWLPWFSEFWZTWRV","short_pith_number":"pith:A6JQZEIK","schema_version":"1.0","canonical_sha256":"07930c910ace623b2df62c885b66768d5a7ffd9501d34c911b3bf2f83e2b7750","source":{"kind":"arxiv","id":"2607.15592","version":1},"attestation_state":"computed","paper":{"title":"MGDT: MLLM-Guided Diffusion Transformer with Relation-Adaptive Mixture-of-Experts for Multimodal Knowledge Graph Completion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Guanhua Ye, Kangkang Lu, Lei Shi, Meiyu Liang, Wei Huang, Wu Liu, Xu Hou, Yawen Li, Zhe Xue","submitted_at":"2026-07-17T03:39:43Z","abstract_excerpt":"Multimodal Knowledge Graph Completion (MKGC) requires inferring missing entities from structural, textual, and visual cues. Existing diffusion-based MKGC methods usually denoise directly on raw multimodal features. Such a design forces the denoiser to simultaneously perform relation-dependent cue selection, cross-modal semantic alignment, and structure-aware entity generation, which introduces noisy and semantically inconsistent conditions for diffusion and consequently leads to suboptimal completion performance. To address this limitation, we propose MGDT: MLLM-Guided Diffusion Transformer wi"},"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":"2607.15592","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-17T03:39:43Z","cross_cats_sorted":[],"title_canon_sha256":"f4d81bfbc734e6f9aee458b5d146db80a9241350cbafc0301044f736aa5d69a0","abstract_canon_sha256":"ea88e28405cc64755aa48210a8cd231e56f9635533a1dbd9bb3ba7a6e44cea74"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-20T00:18:42.221275Z","signature_b64":"EDnDdBoob1MAPBnmah5RPQyvhjEw48m/mK3XmA55oKIiRgrZ8WwZTmc9bdEXfUHM/DRnkMjMih4bLJz7d+HfDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07930c910ace623b2df62c885b66768d5a7ffd9501d34c911b3bf2f83e2b7750","last_reissued_at":"2026-07-20T00:18:42.220472Z","signature_status":"signed_v1","first_computed_at":"2026-07-20T00:18:42.220472Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MGDT: MLLM-Guided Diffusion Transformer with Relation-Adaptive Mixture-of-Experts for Multimodal Knowledge Graph Completion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Guanhua Ye, Kangkang Lu, Lei Shi, Meiyu Liang, Wei Huang, Wu Liu, Xu Hou, Yawen Li, Zhe Xue","submitted_at":"2026-07-17T03:39:43Z","abstract_excerpt":"Multimodal Knowledge Graph Completion (MKGC) requires inferring missing entities from structural, textual, and visual cues. Existing diffusion-based MKGC methods usually denoise directly on raw multimodal features. Such a design forces the denoiser to simultaneously perform relation-dependent cue selection, cross-modal semantic alignment, and structure-aware entity generation, which introduces noisy and semantically inconsistent conditions for diffusion and consequently leads to suboptimal completion performance. To address this limitation, we propose MGDT: MLLM-Guided Diffusion Transformer wi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.15592","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/2607.15592/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":"2607.15592","created_at":"2026-07-20T00:18:42.220877+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.15592v1","created_at":"2026-07-20T00:18:42.220877+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.15592","created_at":"2026-07-20T00:18:42.220877+00:00"},{"alias_kind":"pith_short_12","alias_value":"A6JQZEIKZZRD","created_at":"2026-07-20T00:18:42.220877+00:00"},{"alias_kind":"pith_short_16","alias_value":"A6JQZEIKZZRDWLPW","created_at":"2026-07-20T00:18:42.220877+00:00"},{"alias_kind":"pith_short_8","alias_value":"A6JQZEIK","created_at":"2026-07-20T00:18:42.220877+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/A6JQZEIKZZRDWLPWFSEFWZTWRV","json":"https://pith.science/pith/A6JQZEIKZZRDWLPWFSEFWZTWRV.json","graph_json":"https://pith.science/api/pith-number/A6JQZEIKZZRDWLPWFSEFWZTWRV/graph.json","events_json":"https://pith.science/api/pith-number/A6JQZEIKZZRDWLPWFSEFWZTWRV/events.json","paper":"https://pith.science/paper/A6JQZEIK"},"agent_actions":{"view_html":"https://pith.science/pith/A6JQZEIKZZRDWLPWFSEFWZTWRV","download_json":"https://pith.science/pith/A6JQZEIKZZRDWLPWFSEFWZTWRV.json","view_paper":"https://pith.science/paper/A6JQZEIK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.15592&json=true","fetch_graph":"https://pith.science/api/pith-number/A6JQZEIKZZRDWLPWFSEFWZTWRV/graph.json","fetch_events":"https://pith.science/api/pith-number/A6JQZEIKZZRDWLPWFSEFWZTWRV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A6JQZEIKZZRDWLPWFSEFWZTWRV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A6JQZEIKZZRDWLPWFSEFWZTWRV/action/storage_attestation","attest_author":"https://pith.science/pith/A6JQZEIKZZRDWLPWFSEFWZTWRV/action/author_attestation","sign_citation":"https://pith.science/pith/A6JQZEIKZZRDWLPWFSEFWZTWRV/action/citation_signature","submit_replication":"https://pith.science/pith/A6JQZEIKZZRDWLPWFSEFWZTWRV/action/replication_record"}},"created_at":"2026-07-20T00:18:42.220877+00:00","updated_at":"2026-07-20T00:18:42.220877+00:00"}