{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:RQOCHXUSI2ZX37DRBOVT3AI6UY","short_pith_number":"pith:RQOCHXUS","schema_version":"1.0","canonical_sha256":"8c1c23de9246b37dfc710bab3d811ea62acca4b43429da02d9a6745b9a761840","source":{"kind":"arxiv","id":"2109.00922","version":2},"attestation_state":"computed","paper":{"title":"Improving Multimodal fusion via Mutual Dependency Maximisation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Chloe Clavel, Emile Chapuis, Matthieu Labeau, Pierre Colombo","submitted_at":"2021-08-31T06:26:26Z","abstract_excerpt":"Multimodal sentiment analysis is a trending area of research, and the multimodal fusion is one of its most active topic. Acknowledging humans communicate through a variety of channels (i.e visual, acoustic, linguistic), multimodal systems aim at integrating different unimodal representations into a synthetic one. So far, a consequent effort has been made on developing complex architectures allowing the fusion of these modalities. However, such systems are mainly trained by minimising simple losses such as $L_1$ or cross-entropy. In this work, we investigate unexplored penalties and propose a s"},"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":"2109.00922","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-08-31T06:26:26Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"b2e773af395fcef6b92c1e9f008b7f8bf7472ad7692e7b94a95be0f974f6ea7e","abstract_canon_sha256":"42312c01d2ebb7d42bb5caa7bdb0e7e99a6576b7765f1e81c988f95e5ed058a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:12:50.648131Z","signature_b64":"f2aNYIQjlaHP2/OQpfusnuk9P6TQgslQcZn54Tj4mXEOfmDrIau1ZwpDssEV0PitLHNoBuVr/tzbOzv8YoLYCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c1c23de9246b37dfc710bab3d811ea62acca4b43429da02d9a6745b9a761840","last_reissued_at":"2026-07-05T03:12:50.647723Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:12:50.647723Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Multimodal fusion via Mutual Dependency Maximisation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Chloe Clavel, Emile Chapuis, Matthieu Labeau, Pierre Colombo","submitted_at":"2021-08-31T06:26:26Z","abstract_excerpt":"Multimodal sentiment analysis is a trending area of research, and the multimodal fusion is one of its most active topic. Acknowledging humans communicate through a variety of channels (i.e visual, acoustic, linguistic), multimodal systems aim at integrating different unimodal representations into a synthetic one. So far, a consequent effort has been made on developing complex architectures allowing the fusion of these modalities. However, such systems are mainly trained by minimising simple losses such as $L_1$ or cross-entropy. In this work, we investigate unexplored penalties and propose a s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.00922","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/2109.00922/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":"2109.00922","created_at":"2026-07-05T03:12:50.647792+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.00922v2","created_at":"2026-07-05T03:12:50.647792+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.00922","created_at":"2026-07-05T03:12:50.647792+00:00"},{"alias_kind":"pith_short_12","alias_value":"RQOCHXUSI2ZX","created_at":"2026-07-05T03:12:50.647792+00:00"},{"alias_kind":"pith_short_16","alias_value":"RQOCHXUSI2ZX37DR","created_at":"2026-07-05T03:12:50.647792+00:00"},{"alias_kind":"pith_short_8","alias_value":"RQOCHXUS","created_at":"2026-07-05T03:12:50.647792+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.01240","citing_title":"Asymmetric Reinforcing against Multi-modal Representation Bias","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RQOCHXUSI2ZX37DRBOVT3AI6UY","json":"https://pith.science/pith/RQOCHXUSI2ZX37DRBOVT3AI6UY.json","graph_json":"https://pith.science/api/pith-number/RQOCHXUSI2ZX37DRBOVT3AI6UY/graph.json","events_json":"https://pith.science/api/pith-number/RQOCHXUSI2ZX37DRBOVT3AI6UY/events.json","paper":"https://pith.science/paper/RQOCHXUS"},"agent_actions":{"view_html":"https://pith.science/pith/RQOCHXUSI2ZX37DRBOVT3AI6UY","download_json":"https://pith.science/pith/RQOCHXUSI2ZX37DRBOVT3AI6UY.json","view_paper":"https://pith.science/paper/RQOCHXUS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.00922&json=true","fetch_graph":"https://pith.science/api/pith-number/RQOCHXUSI2ZX37DRBOVT3AI6UY/graph.json","fetch_events":"https://pith.science/api/pith-number/RQOCHXUSI2ZX37DRBOVT3AI6UY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RQOCHXUSI2ZX37DRBOVT3AI6UY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RQOCHXUSI2ZX37DRBOVT3AI6UY/action/storage_attestation","attest_author":"https://pith.science/pith/RQOCHXUSI2ZX37DRBOVT3AI6UY/action/author_attestation","sign_citation":"https://pith.science/pith/RQOCHXUSI2ZX37DRBOVT3AI6UY/action/citation_signature","submit_replication":"https://pith.science/pith/RQOCHXUSI2ZX37DRBOVT3AI6UY/action/replication_record"}},"created_at":"2026-07-05T03:12:50.647792+00:00","updated_at":"2026-07-05T03:12:50.647792+00:00"}