{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:A372MQ7XF2BTWKRJ72LANX73J2","short_pith_number":"pith:A372MQ7X","schema_version":"1.0","canonical_sha256":"06ffa643f72e833b2a29fe9606dffb4e92c716ce0d23b96e46c43aa20094b407","source":{"kind":"arxiv","id":"2506.10282","version":1},"attestation_state":"computed","paper":{"title":"Graph-MLLM: Harnessing Multimodal Large Language Models for Multimodal Graph Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chuanhao Ji, Daochen Zha, Dongzhe Fan, Jiacheng Shen, Jiajin Liu, Qiaoyu Tan","submitted_at":"2025-06-12T01:44:46Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in representing and understanding diverse modalities. However, they typically focus on modality alignment in a pairwise manner while overlooking structural relationships across data points. Integrating multimodality with structured graph information (i.e., multimodal graphs, MMGs) is essential for real-world applications such as social networks, healthcare, and recommendation systems. Existing MMG learning methods fall into three paradigms based on how they leverage MLLMs: Encoder, Aligner, and Predictor. MLLM-a"},"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":"2506.10282","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-12T01:44:46Z","cross_cats_sorted":[],"title_canon_sha256":"94db9427c48bdffe3b29e29853b9858fe6d616d9281460aab6bfb35fb7ce1669","abstract_canon_sha256":"3f719af074399a13f178d32e6fc5db9c9fba3b8f15480b7078fa73468c505b23"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:20.580516Z","signature_b64":"7BRUoMtB2Tri5cfD3yIwzAMsImrvB6fYAM5G9xOBizy0Nu81U89v7UX3hFU9rP6Ht7DAzQrhAuOgq4QbFahGAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"06ffa643f72e833b2a29fe9606dffb4e92c716ce0d23b96e46c43aa20094b407","last_reissued_at":"2026-07-05T11:20:20.580026Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:20.580026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Graph-MLLM: Harnessing Multimodal Large Language Models for Multimodal Graph Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chuanhao Ji, Daochen Zha, Dongzhe Fan, Jiacheng Shen, Jiajin Liu, Qiaoyu Tan","submitted_at":"2025-06-12T01:44:46Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in representing and understanding diverse modalities. However, they typically focus on modality alignment in a pairwise manner while overlooking structural relationships across data points. Integrating multimodality with structured graph information (i.e., multimodal graphs, MMGs) is essential for real-world applications such as social networks, healthcare, and recommendation systems. Existing MMG learning methods fall into three paradigms based on how they leverage MLLMs: Encoder, Aligner, and Predictor. MLLM-a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.10282","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/2506.10282/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":"2506.10282","created_at":"2026-07-05T11:20:20.580092+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.10282v1","created_at":"2026-07-05T11:20:20.580092+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.10282","created_at":"2026-07-05T11:20:20.580092+00:00"},{"alias_kind":"pith_short_12","alias_value":"A372MQ7XF2BT","created_at":"2026-07-05T11:20:20.580092+00:00"},{"alias_kind":"pith_short_16","alias_value":"A372MQ7XF2BTWKRJ","created_at":"2026-07-05T11:20:20.580092+00:00"},{"alias_kind":"pith_short_8","alias_value":"A372MQ7X","created_at":"2026-07-05T11:20:20.580092+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.32016","citing_title":"FedLAB: Traceable Semantic Codebooks for Federated Multimodal Graph Foundation Learning","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11468","citing_title":"CAMPA: Efficient and Aligned Multimodal Graph Learning via Decoupled Propagation and Aggregation","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A372MQ7XF2BTWKRJ72LANX73J2","json":"https://pith.science/pith/A372MQ7XF2BTWKRJ72LANX73J2.json","graph_json":"https://pith.science/api/pith-number/A372MQ7XF2BTWKRJ72LANX73J2/graph.json","events_json":"https://pith.science/api/pith-number/A372MQ7XF2BTWKRJ72LANX73J2/events.json","paper":"https://pith.science/paper/A372MQ7X"},"agent_actions":{"view_html":"https://pith.science/pith/A372MQ7XF2BTWKRJ72LANX73J2","download_json":"https://pith.science/pith/A372MQ7XF2BTWKRJ72LANX73J2.json","view_paper":"https://pith.science/paper/A372MQ7X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.10282&json=true","fetch_graph":"https://pith.science/api/pith-number/A372MQ7XF2BTWKRJ72LANX73J2/graph.json","fetch_events":"https://pith.science/api/pith-number/A372MQ7XF2BTWKRJ72LANX73J2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A372MQ7XF2BTWKRJ72LANX73J2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A372MQ7XF2BTWKRJ72LANX73J2/action/storage_attestation","attest_author":"https://pith.science/pith/A372MQ7XF2BTWKRJ72LANX73J2/action/author_attestation","sign_citation":"https://pith.science/pith/A372MQ7XF2BTWKRJ72LANX73J2/action/citation_signature","submit_replication":"https://pith.science/pith/A372MQ7XF2BTWKRJ72LANX73J2/action/replication_record"}},"created_at":"2026-07-05T11:20:20.580092+00:00","updated_at":"2026-07-05T11:20:20.580092+00:00"}