{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ENWNQPY3PIGQ46A7CQNF7A3J4C","short_pith_number":"pith:ENWNQPY3","schema_version":"1.0","canonical_sha256":"236cd83f1b7a0d0e781f141a5f8369e0aeb8088c73e8ab3eb3e961275fe46460","source":{"kind":"arxiv","id":"2507.05624","version":2},"attestation_state":"computed","paper":{"title":"ADMC: Attention-based Diffusion Model for Missing Modalities Feature Completion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jiangjia Yan, Juan Chen, Liangze Yin, Peng Xiangli, Wei Zhang, Yuhan Li","submitted_at":"2025-07-08T03:08:52Z","abstract_excerpt":"Multimodal emotion and intent recognition is essential for automated human-computer interaction, It aims to analyze users' speech, text, and visual information to predict their emotions or intent. One of the significant challenges is that missing modalities due to sensor malfunctions or incomplete data. Traditional methods that attempt to reconstruct missing information often suffer from over-coupling and imprecise generation processes, leading to suboptimal outcomes. To address these issues, we introduce an Attention-based Diffusion model for Missing Modalities feature Completion (ADMC). Our "},"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":"2507.05624","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-08T03:08:52Z","cross_cats_sorted":[],"title_canon_sha256":"d69a75110baf1894149340eef281b133ace01e0d5ea57179ae15750e5d47aa66","abstract_canon_sha256":"6f89c0b48bd96c96c16e6cf0de92942cb8c2551d931dd96e69976fb833cd889e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:17:12.092488Z","signature_b64":"PwxSLo90FyzFEzuFSLEls1/b2mDggrIBF6OwmV2iEIaK8uhMAbWT6KNEWbBB3lmRoS0t59M1RA0f0gtLlrpKCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"236cd83f1b7a0d0e781f141a5f8369e0aeb8088c73e8ab3eb3e961275fe46460","last_reissued_at":"2026-07-03T01:17:12.092069Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:17:12.092069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ADMC: Attention-based Diffusion Model for Missing Modalities Feature Completion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jiangjia Yan, Juan Chen, Liangze Yin, Peng Xiangli, Wei Zhang, Yuhan Li","submitted_at":"2025-07-08T03:08:52Z","abstract_excerpt":"Multimodal emotion and intent recognition is essential for automated human-computer interaction, It aims to analyze users' speech, text, and visual information to predict their emotions or intent. One of the significant challenges is that missing modalities due to sensor malfunctions or incomplete data. Traditional methods that attempt to reconstruct missing information often suffer from over-coupling and imprecise generation processes, leading to suboptimal outcomes. To address these issues, we introduce an Attention-based Diffusion model for Missing Modalities feature Completion (ADMC). Our "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.05624","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/2507.05624/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":"2507.05624","created_at":"2026-07-03T01:17:12.092125+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.05624v2","created_at":"2026-07-03T01:17:12.092125+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.05624","created_at":"2026-07-03T01:17:12.092125+00:00"},{"alias_kind":"pith_short_12","alias_value":"ENWNQPY3PIGQ","created_at":"2026-07-03T01:17:12.092125+00:00"},{"alias_kind":"pith_short_16","alias_value":"ENWNQPY3PIGQ46A7","created_at":"2026-07-03T01:17:12.092125+00:00"},{"alias_kind":"pith_short_8","alias_value":"ENWNQPY3","created_at":"2026-07-03T01:17:12.092125+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2602.03151","citing_title":"Enhancing Foundation VLM Robustness to Missing Modality: Scalable Diffusion for Bi-directional Feature Restoration","ref_index":60,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ENWNQPY3PIGQ46A7CQNF7A3J4C","json":"https://pith.science/pith/ENWNQPY3PIGQ46A7CQNF7A3J4C.json","graph_json":"https://pith.science/api/pith-number/ENWNQPY3PIGQ46A7CQNF7A3J4C/graph.json","events_json":"https://pith.science/api/pith-number/ENWNQPY3PIGQ46A7CQNF7A3J4C/events.json","paper":"https://pith.science/paper/ENWNQPY3"},"agent_actions":{"view_html":"https://pith.science/pith/ENWNQPY3PIGQ46A7CQNF7A3J4C","download_json":"https://pith.science/pith/ENWNQPY3PIGQ46A7CQNF7A3J4C.json","view_paper":"https://pith.science/paper/ENWNQPY3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.05624&json=true","fetch_graph":"https://pith.science/api/pith-number/ENWNQPY3PIGQ46A7CQNF7A3J4C/graph.json","fetch_events":"https://pith.science/api/pith-number/ENWNQPY3PIGQ46A7CQNF7A3J4C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ENWNQPY3PIGQ46A7CQNF7A3J4C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ENWNQPY3PIGQ46A7CQNF7A3J4C/action/storage_attestation","attest_author":"https://pith.science/pith/ENWNQPY3PIGQ46A7CQNF7A3J4C/action/author_attestation","sign_citation":"https://pith.science/pith/ENWNQPY3PIGQ46A7CQNF7A3J4C/action/citation_signature","submit_replication":"https://pith.science/pith/ENWNQPY3PIGQ46A7CQNF7A3J4C/action/replication_record"}},"created_at":"2026-07-03T01:17:12.092125+00:00","updated_at":"2026-07-03T01:17:12.092125+00:00"}