{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GXOYTINI6E6TK65W4HH66EMYKQ","short_pith_number":"pith:GXOYTINI","schema_version":"1.0","canonical_sha256":"35dd89a1a8f13d357bb6e1cfef11985432cdc3df6e21dc1b0fcb708b8cdd7f59","source":{"kind":"arxiv","id":"2404.18947","version":3},"attestation_state":"computed","paper":{"title":"Multimodal Fusion on Low-quality Data: A Comprehensive Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Cai Xu, Changqing Zhang, Cheng Deng, Di Hu, Huazhu Fu, Jie Wen, Qinghua Hu, Qingyang Zhang, Xi Peng, Yake Wei, Zongbo Han","submitted_at":"2024-04-27T07:22:28Z","abstract_excerpt":"Multimodal fusion focuses on integrating information from multiple modalities with the goal of more accurate prediction, which has achieved remarkable progress in a wide range of scenarios, including autonomous driving and medical diagnosis. However, the reliability of multimodal fusion remains largely unexplored especially under low-quality data settings. This paper surveys the common challenges and recent advances of multimodal fusion in the wild and presents them in a comprehensive taxonomy. From a data-centric view, we identify four main challenges that are faced by multimodal fusion on lo"},"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":"2404.18947","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-27T07:22:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"36bcba21a9a72aa5e4d54fef5a1f90b7d69b54ce654ea956051d9423e83d3c48","abstract_canon_sha256":"25225e354d46a1f8f3ba948b30df5262ecb5d7eae222f629c6f0ad4262bf973c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:29:28.249569Z","signature_b64":"VTwb2uj3jQc9QX/lTMTXOSBDPIKTAVBAc9jtaZuFZchylrkxET6rmyuBpQyRLpw0Q1D65V1J+jtQcIxptqx9AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35dd89a1a8f13d357bb6e1cfef11985432cdc3df6e21dc1b0fcb708b8cdd7f59","last_reissued_at":"2026-07-05T09:29:28.249049Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:29:28.249049Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multimodal Fusion on Low-quality Data: A Comprehensive Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Cai Xu, Changqing Zhang, Cheng Deng, Di Hu, Huazhu Fu, Jie Wen, Qinghua Hu, Qingyang Zhang, Xi Peng, Yake Wei, Zongbo Han","submitted_at":"2024-04-27T07:22:28Z","abstract_excerpt":"Multimodal fusion focuses on integrating information from multiple modalities with the goal of more accurate prediction, which has achieved remarkable progress in a wide range of scenarios, including autonomous driving and medical diagnosis. However, the reliability of multimodal fusion remains largely unexplored especially under low-quality data settings. This paper surveys the common challenges and recent advances of multimodal fusion in the wild and presents them in a comprehensive taxonomy. From a data-centric view, we identify four main challenges that are faced by multimodal fusion on lo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.18947","kind":"arxiv","version":3},"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/2404.18947/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":"2404.18947","created_at":"2026-07-05T09:29:28.249119+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.18947v3","created_at":"2026-07-05T09:29:28.249119+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.18947","created_at":"2026-07-05T09:29:28.249119+00:00"},{"alias_kind":"pith_short_12","alias_value":"GXOYTINI6E6T","created_at":"2026-07-05T09:29:28.249119+00:00"},{"alias_kind":"pith_short_16","alias_value":"GXOYTINI6E6TK65W","created_at":"2026-07-05T09:29:28.249119+00:00"},{"alias_kind":"pith_short_8","alias_value":"GXOYTINI","created_at":"2026-07-05T09:29:28.249119+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":14,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12495","citing_title":"Missing-Token Prompted Reliability-Aware Fusion for Robust Polyglot Speaker Identification","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2408.07331","citing_title":"RSEA-MVGNN: Multi-View Graph Neural Network with Reliable Structural Enhancement and Aggregation","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2502.02871","citing_title":"Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning","ref_index":249,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21565","citing_title":"Leveraging Self-Paced Curriculum Learning for Enhanced Modality Balance in Multimodal Conversational Emotion Recognition","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2511.06452","citing_title":"MULTIBENCH++: A Unified and Comprehensive Multimodal Fusion Benchmarking Across Specialized Domains","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2601.22853","citing_title":"Inference-Time Dynamic Modality Selection for Incomplete Multimodal Classification","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2602.16197","citing_title":"ModalImmune: Immunity Driven Unlearning via Self Destructive Training","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07361","citing_title":"BLEG: LLM Functions as Powerful fMRI Graph-Enhancer for Brain Network Analysis","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03820","citing_title":"Multimodal Learning on Low-Quality Data with Conformal Predictive Self-Calibration","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27259","citing_title":"VTBench: A Multimodal Framework for Time-Series Classification with Chart-Based Representations","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26186","citing_title":"FASH-iCNN: Making Editorial Fashion Identity Inspectable Through Multimodal CNN Probing","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05121","citing_title":"Beyond Semantics: An Evidential Reasoning-Aware Multi-View Learning Framework for Trustworthy Mental Health Prediction","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18460","citing_title":"Learning Invariant Modality Representation for Robust Multimodal Learning from a Causal Inference Perspective","ref_index":299,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20283","citing_title":"Multi-Perspective Evidence Synthesis and Reasoning for Unsupervised Multimodal Entity Linking","ref_index":58,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GXOYTINI6E6TK65W4HH66EMYKQ","json":"https://pith.science/pith/GXOYTINI6E6TK65W4HH66EMYKQ.json","graph_json":"https://pith.science/api/pith-number/GXOYTINI6E6TK65W4HH66EMYKQ/graph.json","events_json":"https://pith.science/api/pith-number/GXOYTINI6E6TK65W4HH66EMYKQ/events.json","paper":"https://pith.science/paper/GXOYTINI"},"agent_actions":{"view_html":"https://pith.science/pith/GXOYTINI6E6TK65W4HH66EMYKQ","download_json":"https://pith.science/pith/GXOYTINI6E6TK65W4HH66EMYKQ.json","view_paper":"https://pith.science/paper/GXOYTINI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.18947&json=true","fetch_graph":"https://pith.science/api/pith-number/GXOYTINI6E6TK65W4HH66EMYKQ/graph.json","fetch_events":"https://pith.science/api/pith-number/GXOYTINI6E6TK65W4HH66EMYKQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GXOYTINI6E6TK65W4HH66EMYKQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GXOYTINI6E6TK65W4HH66EMYKQ/action/storage_attestation","attest_author":"https://pith.science/pith/GXOYTINI6E6TK65W4HH66EMYKQ/action/author_attestation","sign_citation":"https://pith.science/pith/GXOYTINI6E6TK65W4HH66EMYKQ/action/citation_signature","submit_replication":"https://pith.science/pith/GXOYTINI6E6TK65W4HH66EMYKQ/action/replication_record"}},"created_at":"2026-07-05T09:29:28.249119+00:00","updated_at":"2026-07-05T09:29:28.249119+00:00"}