{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:SQAHZOBMVROOM3MBJ2GJ6X5UWE","short_pith_number":"pith:SQAHZOBM","schema_version":"1.0","canonical_sha256":"94007cb82cac5ce66d814e8c9f5fb4b113541c7d450f2fc86e8e32d1aee4e648","source":{"kind":"arxiv","id":"2210.09946","version":2},"attestation_state":"computed","paper":{"title":"MMGA: Multimodal Learning with Graph Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.MM","authors_text":"Donghong Cai, Quanjin Tao, Xiang Ren, Xiao Feng, Xuan Yang, Yang Yang","submitted_at":"2022-10-18T15:50:31Z","abstract_excerpt":"Multimodal pre-training breaks down the modality barriers and allows the individual modalities to be mutually augmented with information, resulting in significant advances in representation learning. However, graph modality, as a very general and important form of data, cannot be easily interacted with other modalities because of its non-regular nature. In this paper, we propose MMGA (Multimodal learning with Graph Alignment), a novel multimodal pre-training framework to incorporate information from graph (social network), image and text modalities on social media to enhance user representatio"},"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":"2210.09946","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2022-10-18T15:50:31Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"b58c8d2b066d3c8a7ee8bdfcaaef2f4a46e26b004d6bba98f610f82ae9aed124","abstract_canon_sha256":"a2d75f678659b29d73b7cf3a6b925c1abf2ecbe3a45a014ecc6ccdc3026ace0a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:11:44.022116Z","signature_b64":"Qz83okr4CeVhEXUVtR/A6P025CWYe/vG1qKJ0c7V9InYge+RZilr62sVJINEIqpF1nyaqSRyCoOSgHnML1OBBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94007cb82cac5ce66d814e8c9f5fb4b113541c7d450f2fc86e8e32d1aee4e648","last_reissued_at":"2026-07-05T05:11:44.021683Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:11:44.021683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MMGA: Multimodal Learning with Graph Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.MM","authors_text":"Donghong Cai, Quanjin Tao, Xiang Ren, Xiao Feng, Xuan Yang, Yang Yang","submitted_at":"2022-10-18T15:50:31Z","abstract_excerpt":"Multimodal pre-training breaks down the modality barriers and allows the individual modalities to be mutually augmented with information, resulting in significant advances in representation learning. However, graph modality, as a very general and important form of data, cannot be easily interacted with other modalities because of its non-regular nature. In this paper, we propose MMGA (Multimodal learning with Graph Alignment), a novel multimodal pre-training framework to incorporate information from graph (social network), image and text modalities on social media to enhance user representatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.09946","kind":"arxiv","version":2},"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/2210.09946/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":"2210.09946","created_at":"2026-07-05T05:11:44.021751+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.09946v2","created_at":"2026-07-05T05:11:44.021751+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.09946","created_at":"2026-07-05T05:11:44.021751+00:00"},{"alias_kind":"pith_short_12","alias_value":"SQAHZOBMVROO","created_at":"2026-07-05T05:11:44.021751+00:00"},{"alias_kind":"pith_short_16","alias_value":"SQAHZOBMVROOM3MB","created_at":"2026-07-05T05:11:44.021751+00:00"},{"alias_kind":"pith_short_8","alias_value":"SQAHZOBM","created_at":"2026-07-05T05:11:44.021751+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/SQAHZOBMVROOM3MBJ2GJ6X5UWE","json":"https://pith.science/pith/SQAHZOBMVROOM3MBJ2GJ6X5UWE.json","graph_json":"https://pith.science/api/pith-number/SQAHZOBMVROOM3MBJ2GJ6X5UWE/graph.json","events_json":"https://pith.science/api/pith-number/SQAHZOBMVROOM3MBJ2GJ6X5UWE/events.json","paper":"https://pith.science/paper/SQAHZOBM"},"agent_actions":{"view_html":"https://pith.science/pith/SQAHZOBMVROOM3MBJ2GJ6X5UWE","download_json":"https://pith.science/pith/SQAHZOBMVROOM3MBJ2GJ6X5UWE.json","view_paper":"https://pith.science/paper/SQAHZOBM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.09946&json=true","fetch_graph":"https://pith.science/api/pith-number/SQAHZOBMVROOM3MBJ2GJ6X5UWE/graph.json","fetch_events":"https://pith.science/api/pith-number/SQAHZOBMVROOM3MBJ2GJ6X5UWE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SQAHZOBMVROOM3MBJ2GJ6X5UWE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SQAHZOBMVROOM3MBJ2GJ6X5UWE/action/storage_attestation","attest_author":"https://pith.science/pith/SQAHZOBMVROOM3MBJ2GJ6X5UWE/action/author_attestation","sign_citation":"https://pith.science/pith/SQAHZOBMVROOM3MBJ2GJ6X5UWE/action/citation_signature","submit_replication":"https://pith.science/pith/SQAHZOBMVROOM3MBJ2GJ6X5UWE/action/replication_record"}},"created_at":"2026-07-05T05:11:44.021751+00:00","updated_at":"2026-07-05T05:11:44.021751+00:00"}