{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:FDJMRD545XBBQXCMB5SUUDALSK","short_pith_number":"pith:FDJMRD54","schema_version":"1.0","canonical_sha256":"28d2c88fbcedc2185c4c0f654a0c0b9297923ac269ac23eee43406fd22c772bd","source":{"kind":"arxiv","id":"2109.00412","version":2},"attestation_state":"computed","paper":{"title":"Improving Multimodal Fusion with Hierarchical Mutual Information Maximization for Multimodal Sentiment Analysis","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hui Chen, Soujanya Poria, Wei Han","submitted_at":"2021-09-01T14:45:16Z","abstract_excerpt":"In multimodal sentiment analysis (MSA), the performance of a model highly depends on the quality of synthesized embeddings. These embeddings are generated from the upstream process called multimodal fusion, which aims to extract and combine the input unimodal raw data to produce a richer multimodal representation. Previous work either back-propagates the task loss or manipulates the geometric property of feature spaces to produce favorable fusion results, which neglects the preservation of critical task-related information that flows from input to the fusion results. In this work, we propose 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":"2109.00412","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-01T14:45:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"26d73dfa6280aad92befc0c0e72efabf9586de0f65f5295d21b587a43082293a","abstract_canon_sha256":"d6f1df09d3a202de653422509ba1ffcffbf572e0921703cb09ace61112034b6c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:14:56.902338Z","signature_b64":"SjPKvQWvR5vnFZfmrK2NMKk1OmofWPjLzpMEferIeoi/NeKdIU1yC4oe0CzfKWQYI6Zk2pKmQHD7OHSilAZoAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28d2c88fbcedc2185c4c0f654a0c0b9297923ac269ac23eee43406fd22c772bd","last_reissued_at":"2026-07-05T03:14:56.901871Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:14:56.901871Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Multimodal Fusion with Hierarchical Mutual Information Maximization for Multimodal Sentiment Analysis","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hui Chen, Soujanya Poria, Wei Han","submitted_at":"2021-09-01T14:45:16Z","abstract_excerpt":"In multimodal sentiment analysis (MSA), the performance of a model highly depends on the quality of synthesized embeddings. These embeddings are generated from the upstream process called multimodal fusion, which aims to extract and combine the input unimodal raw data to produce a richer multimodal representation. Previous work either back-propagates the task loss or manipulates the geometric property of feature spaces to produce favorable fusion results, which neglects the preservation of critical task-related information that flows from input to the fusion results. In this work, we propose a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.00412","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/2109.00412/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":"2109.00412","created_at":"2026-07-05T03:14:56.901934+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.00412v2","created_at":"2026-07-05T03:14:56.901934+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.00412","created_at":"2026-07-05T03:14:56.901934+00:00"},{"alias_kind":"pith_short_12","alias_value":"FDJMRD545XBB","created_at":"2026-07-05T03:14:56.901934+00:00"},{"alias_kind":"pith_short_16","alias_value":"FDJMRD545XBBQXCM","created_at":"2026-07-05T03:14:56.901934+00:00"},{"alias_kind":"pith_short_8","alias_value":"FDJMRD54","created_at":"2026-07-05T03:14:56.901934+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06285","citing_title":"TRACE: A Temporal Conditional Estimation for Multimodal Time Series Foundation Models","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30994","citing_title":"Dynamic Interaction-Aware and Causality-Disentangled Framework for Multimodal Sentiment Analysis","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2312.06950","citing_title":"READ: Recurrent Adapter with Partial Video-Language Alignment for Parameter-Efficient Transfer Learning in Low-Resource Video-Language Modeling","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16889","citing_title":"Controlling Decision Drift in Multimodal Sentiment Analysis with Missing Modalities","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09468","citing_title":"Mitigating Multimodal Inconsistency via Cognitive Dual-Pathway Reasoning for Intent Recognition","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12518","citing_title":"Enhance-then-Balance Modality Collaboration for Robust Multimodal Sentiment Analysis","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FDJMRD545XBBQXCMB5SUUDALSK","json":"https://pith.science/pith/FDJMRD545XBBQXCMB5SUUDALSK.json","graph_json":"https://pith.science/api/pith-number/FDJMRD545XBBQXCMB5SUUDALSK/graph.json","events_json":"https://pith.science/api/pith-number/FDJMRD545XBBQXCMB5SUUDALSK/events.json","paper":"https://pith.science/paper/FDJMRD54"},"agent_actions":{"view_html":"https://pith.science/pith/FDJMRD545XBBQXCMB5SUUDALSK","download_json":"https://pith.science/pith/FDJMRD545XBBQXCMB5SUUDALSK.json","view_paper":"https://pith.science/paper/FDJMRD54","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.00412&json=true","fetch_graph":"https://pith.science/api/pith-number/FDJMRD545XBBQXCMB5SUUDALSK/graph.json","fetch_events":"https://pith.science/api/pith-number/FDJMRD545XBBQXCMB5SUUDALSK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FDJMRD545XBBQXCMB5SUUDALSK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FDJMRD545XBBQXCMB5SUUDALSK/action/storage_attestation","attest_author":"https://pith.science/pith/FDJMRD545XBBQXCMB5SUUDALSK/action/author_attestation","sign_citation":"https://pith.science/pith/FDJMRD545XBBQXCMB5SUUDALSK/action/citation_signature","submit_replication":"https://pith.science/pith/FDJMRD545XBBQXCMB5SUUDALSK/action/replication_record"}},"created_at":"2026-07-05T03:14:56.901934+00:00","updated_at":"2026-07-05T03:14:56.901934+00:00"}