{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:B5JGPCMIYN5QN4SIKKZ7PCZKUW","short_pith_number":"pith:B5JGPCMI","schema_version":"1.0","canonical_sha256":"0f52678988c37b06f24852b3f78b2aa592c048dac7da35e1e1ee3092bd3e8b6d","source":{"kind":"arxiv","id":"2505.19996","version":1},"attestation_state":"computed","paper":{"title":"Learning Optimal Multimodal Information Bottleneck Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jun Wang, Qilong Wu, Xiaobo Sun, Yiyang Shao","submitted_at":"2025-05-26T13:48:07Z","abstract_excerpt":"Leveraging high-quality joint representations from multimodal data can greatly enhance model performance in various machine-learning based applications. Recent multimodal learning methods, based on the multimodal information bottleneck (MIB) principle, aim to generate optimal MIB with maximal task-relevant information and minimal superfluous information via regularization. However, these methods often set ad hoc regularization weights and overlook imbalanced task-relevant information across modalities, limiting their ability to achieve optimal MIB. To address this gap, we propose a novel multi"},"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":"2505.19996","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-26T13:48:07Z","cross_cats_sorted":[],"title_canon_sha256":"014eeb55e4cc9374b6408cebed579806e1df54ef0ff66f7f20fd78a9e82da44c","abstract_canon_sha256":"91e66fb2a67b40ab349c784211b1812b5f2a56c7b55d1267680142d533cc7cd6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:51.057560Z","signature_b64":"Icw+Q9Fh0AmZRjPnOIwCRNfQt6tm5VspQ3qkQSvoIDSSUVW8fMq5ZO3zx1qMP+C2NUvpq0ZFtU0WO3QV9EYECQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f52678988c37b06f24852b3f78b2aa592c048dac7da35e1e1ee3092bd3e8b6d","last_reissued_at":"2026-07-05T11:09:51.057063Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:51.057063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Optimal Multimodal Information Bottleneck Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jun Wang, Qilong Wu, Xiaobo Sun, Yiyang Shao","submitted_at":"2025-05-26T13:48:07Z","abstract_excerpt":"Leveraging high-quality joint representations from multimodal data can greatly enhance model performance in various machine-learning based applications. Recent multimodal learning methods, based on the multimodal information bottleneck (MIB) principle, aim to generate optimal MIB with maximal task-relevant information and minimal superfluous information via regularization. However, these methods often set ad hoc regularization weights and overlook imbalanced task-relevant information across modalities, limiting their ability to achieve optimal MIB. To address this gap, we propose a novel multi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19996","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/2505.19996/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":"2505.19996","created_at":"2026-07-05T11:09:51.057122+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.19996v1","created_at":"2026-07-05T11:09:51.057122+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19996","created_at":"2026-07-05T11:09:51.057122+00:00"},{"alias_kind":"pith_short_12","alias_value":"B5JGPCMIYN5Q","created_at":"2026-07-05T11:09:51.057122+00:00"},{"alias_kind":"pith_short_16","alias_value":"B5JGPCMIYN5QN4SI","created_at":"2026-07-05T11:09:51.057122+00:00"},{"alias_kind":"pith_short_8","alias_value":"B5JGPCMI","created_at":"2026-07-05T11:09:51.057122+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.31504","citing_title":"When Are Multimodal Predictions Biologically Supported? A Diagnostic Evaluation Framework","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B5JGPCMIYN5QN4SIKKZ7PCZKUW","json":"https://pith.science/pith/B5JGPCMIYN5QN4SIKKZ7PCZKUW.json","graph_json":"https://pith.science/api/pith-number/B5JGPCMIYN5QN4SIKKZ7PCZKUW/graph.json","events_json":"https://pith.science/api/pith-number/B5JGPCMIYN5QN4SIKKZ7PCZKUW/events.json","paper":"https://pith.science/paper/B5JGPCMI"},"agent_actions":{"view_html":"https://pith.science/pith/B5JGPCMIYN5QN4SIKKZ7PCZKUW","download_json":"https://pith.science/pith/B5JGPCMIYN5QN4SIKKZ7PCZKUW.json","view_paper":"https://pith.science/paper/B5JGPCMI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.19996&json=true","fetch_graph":"https://pith.science/api/pith-number/B5JGPCMIYN5QN4SIKKZ7PCZKUW/graph.json","fetch_events":"https://pith.science/api/pith-number/B5JGPCMIYN5QN4SIKKZ7PCZKUW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B5JGPCMIYN5QN4SIKKZ7PCZKUW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B5JGPCMIYN5QN4SIKKZ7PCZKUW/action/storage_attestation","attest_author":"https://pith.science/pith/B5JGPCMIYN5QN4SIKKZ7PCZKUW/action/author_attestation","sign_citation":"https://pith.science/pith/B5JGPCMIYN5QN4SIKKZ7PCZKUW/action/citation_signature","submit_replication":"https://pith.science/pith/B5JGPCMIYN5QN4SIKKZ7PCZKUW/action/replication_record"}},"created_at":"2026-07-05T11:09:51.057122+00:00","updated_at":"2026-07-05T11:09:51.057122+00:00"}