{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IJVSGTW4D5YE4G2QDRLBIHOVFP","short_pith_number":"pith:IJVSGTW4","schema_version":"1.0","canonical_sha256":"426b234edc1f704e1b501c56141dd52bfd6d9aaea25a453046c3735b2551867d","source":{"kind":"arxiv","id":"2506.01490","version":1},"attestation_state":"computed","paper":{"title":"Confidence-Aware Self-Distillation for Multimodal Sentiment Analysis with Incomplete Modalities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Feilong Tang, Jionglong Su, Shijin Wang, Yanxi Luo, Yulong Li, Zhongxing Xu","submitted_at":"2025-06-02T09:48:41Z","abstract_excerpt":"Multimodal sentiment analysis (MSA) aims to understand human sentiment through multimodal data. In real-world scenarios, practical factors often lead to uncertain modality missingness. Existing methods for handling modality missingness are based on data reconstruction or common subspace projections. However, these methods neglect the confidence in multimodal combinations and impose constraints on intra-class representation, hindering the capture of modality-specific information and resulting in suboptimal performance. To address these challenges, we propose a Confidence-Aware Self-Distillation"},"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":"2506.01490","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T09:48:41Z","cross_cats_sorted":[],"title_canon_sha256":"3294e524ce50df7c48b3180b0151ad0e93590671bb31f9ea01550c823663b7e0","abstract_canon_sha256":"3e7109e59d4629549e930cbeede27a6f76caa6e94145cdb96d63a821cc9d926a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:14.581110Z","signature_b64":"v90Yif7jk0s8ppsyjvZmqj55lurlxghjgXEk+rpM5VqFLP/fvuAxEK5oi+r8GvXlFiyCGWPBzutHHM7bS2jNCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"426b234edc1f704e1b501c56141dd52bfd6d9aaea25a453046c3735b2551867d","last_reissued_at":"2026-07-05T11:14:14.580615Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:14.580615Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Confidence-Aware Self-Distillation for Multimodal Sentiment Analysis with Incomplete Modalities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Feilong Tang, Jionglong Su, Shijin Wang, Yanxi Luo, Yulong Li, Zhongxing Xu","submitted_at":"2025-06-02T09:48:41Z","abstract_excerpt":"Multimodal sentiment analysis (MSA) aims to understand human sentiment through multimodal data. In real-world scenarios, practical factors often lead to uncertain modality missingness. Existing methods for handling modality missingness are based on data reconstruction or common subspace projections. However, these methods neglect the confidence in multimodal combinations and impose constraints on intra-class representation, hindering the capture of modality-specific information and resulting in suboptimal performance. To address these challenges, we propose a Confidence-Aware Self-Distillation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01490","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/2506.01490/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":"2506.01490","created_at":"2026-07-05T11:14:14.580675+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01490v1","created_at":"2026-07-05T11:14:14.580675+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01490","created_at":"2026-07-05T11:14:14.580675+00:00"},{"alias_kind":"pith_short_12","alias_value":"IJVSGTW4D5YE","created_at":"2026-07-05T11:14:14.580675+00:00"},{"alias_kind":"pith_short_16","alias_value":"IJVSGTW4D5YE4G2Q","created_at":"2026-07-05T11:14:14.580675+00:00"},{"alias_kind":"pith_short_8","alias_value":"IJVSGTW4","created_at":"2026-07-05T11:14:14.580675+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30994","citing_title":"Dynamic Interaction-Aware and Causality-Disentangled Framework for Multimodal Sentiment Analysis","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IJVSGTW4D5YE4G2QDRLBIHOVFP","json":"https://pith.science/pith/IJVSGTW4D5YE4G2QDRLBIHOVFP.json","graph_json":"https://pith.science/api/pith-number/IJVSGTW4D5YE4G2QDRLBIHOVFP/graph.json","events_json":"https://pith.science/api/pith-number/IJVSGTW4D5YE4G2QDRLBIHOVFP/events.json","paper":"https://pith.science/paper/IJVSGTW4"},"agent_actions":{"view_html":"https://pith.science/pith/IJVSGTW4D5YE4G2QDRLBIHOVFP","download_json":"https://pith.science/pith/IJVSGTW4D5YE4G2QDRLBIHOVFP.json","view_paper":"https://pith.science/paper/IJVSGTW4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01490&json=true","fetch_graph":"https://pith.science/api/pith-number/IJVSGTW4D5YE4G2QDRLBIHOVFP/graph.json","fetch_events":"https://pith.science/api/pith-number/IJVSGTW4D5YE4G2QDRLBIHOVFP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IJVSGTW4D5YE4G2QDRLBIHOVFP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IJVSGTW4D5YE4G2QDRLBIHOVFP/action/storage_attestation","attest_author":"https://pith.science/pith/IJVSGTW4D5YE4G2QDRLBIHOVFP/action/author_attestation","sign_citation":"https://pith.science/pith/IJVSGTW4D5YE4G2QDRLBIHOVFP/action/citation_signature","submit_replication":"https://pith.science/pith/IJVSGTW4D5YE4G2QDRLBIHOVFP/action/replication_record"}},"created_at":"2026-07-05T11:14:14.580675+00:00","updated_at":"2026-07-05T11:14:14.580675+00:00"}