{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:76LZRTHSWARK4MREINEDTCHWCT","short_pith_number":"pith:76LZRTHS","schema_version":"1.0","canonical_sha256":"ff9798ccf2b022ae322443483988f614c49cf462089a20644b0605b35b252a5a","source":{"kind":"arxiv","id":"2404.02359","version":3},"attestation_state":"computed","paper":{"title":"Attribution Regularization for Multimodal Paradigms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Eric Nyberg, Jayant Sravan Tamarapalli, Jonathan Francis, Sahiti Yerramilli","submitted_at":"2024-04-02T23:05:56Z","abstract_excerpt":"Multimodal machine learning has gained significant attention in recent years due to its potential for integrating information from multiple modalities to enhance learning and decision-making processes. However, it is commonly observed that unimodal models outperform multimodal models, despite the latter having access to richer information. Additionally, the influence of a single modality often dominates the decision-making process, resulting in suboptimal performance. This research project aims to address these challenges by proposing a novel regularization term that encourages multimodal mode"},"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":"2404.02359","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-02T23:05:56Z","cross_cats_sorted":[],"title_canon_sha256":"bb857aad07a64469305fff5c5b23137853e0d309ec4fde5c2e3e7dfe5a20bd33","abstract_canon_sha256":"4d33faa4c91c592f453a039779db26e07357cceb6fd8a378e060b4c404950029"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:09:09.482951Z","signature_b64":"xJF6ZJQDUgiUSvL1y87YU1sKUCvN0/V1BoHmdp/dSEhiUxZZqadi4FTHMQp4/8LIoYHOv9eQuLjvxDSjbWmIAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff9798ccf2b022ae322443483988f614c49cf462089a20644b0605b35b252a5a","last_reissued_at":"2026-07-05T12:09:09.482301Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:09:09.482301Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Attribution Regularization for Multimodal Paradigms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Eric Nyberg, Jayant Sravan Tamarapalli, Jonathan Francis, Sahiti Yerramilli","submitted_at":"2024-04-02T23:05:56Z","abstract_excerpt":"Multimodal machine learning has gained significant attention in recent years due to its potential for integrating information from multiple modalities to enhance learning and decision-making processes. However, it is commonly observed that unimodal models outperform multimodal models, despite the latter having access to richer information. Additionally, the influence of a single modality often dominates the decision-making process, resulting in suboptimal performance. This research project aims to address these challenges by proposing a novel regularization term that encourages multimodal mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.02359","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/2404.02359/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":"2404.02359","created_at":"2026-07-05T12:09:09.482392+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.02359v3","created_at":"2026-07-05T12:09:09.482392+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.02359","created_at":"2026-07-05T12:09:09.482392+00:00"},{"alias_kind":"pith_short_12","alias_value":"76LZRTHSWARK","created_at":"2026-07-05T12:09:09.482392+00:00"},{"alias_kind":"pith_short_16","alias_value":"76LZRTHSWARK4MRE","created_at":"2026-07-05T12:09:09.482392+00:00"},{"alias_kind":"pith_short_8","alias_value":"76LZRTHS","created_at":"2026-07-05T12:09:09.482392+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.13332","citing_title":"Explicit Reasoning Makes Better Judges: A Systematic Study on Accuracy, Efficiency, and Robustness","ref_index":60,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/76LZRTHSWARK4MREINEDTCHWCT","json":"https://pith.science/pith/76LZRTHSWARK4MREINEDTCHWCT.json","graph_json":"https://pith.science/api/pith-number/76LZRTHSWARK4MREINEDTCHWCT/graph.json","events_json":"https://pith.science/api/pith-number/76LZRTHSWARK4MREINEDTCHWCT/events.json","paper":"https://pith.science/paper/76LZRTHS"},"agent_actions":{"view_html":"https://pith.science/pith/76LZRTHSWARK4MREINEDTCHWCT","download_json":"https://pith.science/pith/76LZRTHSWARK4MREINEDTCHWCT.json","view_paper":"https://pith.science/paper/76LZRTHS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.02359&json=true","fetch_graph":"https://pith.science/api/pith-number/76LZRTHSWARK4MREINEDTCHWCT/graph.json","fetch_events":"https://pith.science/api/pith-number/76LZRTHSWARK4MREINEDTCHWCT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/76LZRTHSWARK4MREINEDTCHWCT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/76LZRTHSWARK4MREINEDTCHWCT/action/storage_attestation","attest_author":"https://pith.science/pith/76LZRTHSWARK4MREINEDTCHWCT/action/author_attestation","sign_citation":"https://pith.science/pith/76LZRTHSWARK4MREINEDTCHWCT/action/citation_signature","submit_replication":"https://pith.science/pith/76LZRTHSWARK4MREINEDTCHWCT/action/replication_record"}},"created_at":"2026-07-05T12:09:09.482392+00:00","updated_at":"2026-07-05T12:09:09.482392+00:00"}