{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JTTCUSVG3NZJ3FNID2G6UNZQPS","short_pith_number":"pith:JTTCUSVG","schema_version":"1.0","canonical_sha256":"4ce62a4aa6db729d95a81e8dea37307c929d1fc9c622b16047fe4ef7f0e6ad6b","source":{"kind":"arxiv","id":"2404.17951","version":1},"attestation_state":"computed","paper":{"title":"Cauchy-Schwarz Divergence Information Bottleneck for Regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jose C. Principe, Robert Jenssen, Shujian Yu, Sigurd L{\\o}kse, Xi Yu","submitted_at":"2024-04-27T16:13:05Z","abstract_excerpt":"The information bottleneck (IB) approach is popular to improve the generalization, robustness and explainability of deep neural networks. Essentially, it aims to find a minimum sufficient representation $\\mathbf{t}$ by striking a trade-off between a compression term $I(\\mathbf{x};\\mathbf{t})$ and a prediction term $I(y;\\mathbf{t})$, where $I(\\cdot;\\cdot)$ refers to the mutual information (MI). MI is for the IB for the most part expressed in terms of the Kullback-Leibler (KL) divergence, which in the regression case corresponds to prediction based on mean squared error (MSE) loss with Gaussian "},"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":"2404.17951","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-27T16:13:05Z","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"title_canon_sha256":"e89f534ee5f0527d35461f8a06d825f4015e781ca02910e5fdc6e514c30eb31d","abstract_canon_sha256":"b7092a78357be18766bed26594f8536652503bdf4e7aea95458d3c5712a9c243"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:12:56.136262Z","signature_b64":"u9Am5P3ajiaFrLt2S5QWw9m296PErwWMXbGFDL9C6DjSSB4k8ydLC0xLVLyWoMPmX7Cfi+hemli+mWV/CFrVAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ce62a4aa6db729d95a81e8dea37307c929d1fc9c622b16047fe4ef7f0e6ad6b","last_reissued_at":"2026-07-05T08:12:56.135764Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:12:56.135764Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cauchy-Schwarz Divergence Information Bottleneck for Regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jose C. Principe, Robert Jenssen, Shujian Yu, Sigurd L{\\o}kse, Xi Yu","submitted_at":"2024-04-27T16:13:05Z","abstract_excerpt":"The information bottleneck (IB) approach is popular to improve the generalization, robustness and explainability of deep neural networks. Essentially, it aims to find a minimum sufficient representation $\\mathbf{t}$ by striking a trade-off between a compression term $I(\\mathbf{x};\\mathbf{t})$ and a prediction term $I(y;\\mathbf{t})$, where $I(\\cdot;\\cdot)$ refers to the mutual information (MI). MI is for the IB for the most part expressed in terms of the Kullback-Leibler (KL) divergence, which in the regression case corresponds to prediction based on mean squared error (MSE) loss with Gaussian "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.17951","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/2404.17951/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":"2404.17951","created_at":"2026-07-05T08:12:56.135825+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.17951v1","created_at":"2026-07-05T08:12:56.135825+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.17951","created_at":"2026-07-05T08:12:56.135825+00:00"},{"alias_kind":"pith_short_12","alias_value":"JTTCUSVG3NZJ","created_at":"2026-07-05T08:12:56.135825+00:00"},{"alias_kind":"pith_short_16","alias_value":"JTTCUSVG3NZJ3FNI","created_at":"2026-07-05T08:12:56.135825+00:00"},{"alias_kind":"pith_short_8","alias_value":"JTTCUSVG","created_at":"2026-07-05T08:12:56.135825+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.08222","citing_title":"Structured IB: Improving Information Bottleneck with Structured Feature Learning","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JTTCUSVG3NZJ3FNID2G6UNZQPS","json":"https://pith.science/pith/JTTCUSVG3NZJ3FNID2G6UNZQPS.json","graph_json":"https://pith.science/api/pith-number/JTTCUSVG3NZJ3FNID2G6UNZQPS/graph.json","events_json":"https://pith.science/api/pith-number/JTTCUSVG3NZJ3FNID2G6UNZQPS/events.json","paper":"https://pith.science/paper/JTTCUSVG"},"agent_actions":{"view_html":"https://pith.science/pith/JTTCUSVG3NZJ3FNID2G6UNZQPS","download_json":"https://pith.science/pith/JTTCUSVG3NZJ3FNID2G6UNZQPS.json","view_paper":"https://pith.science/paper/JTTCUSVG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.17951&json=true","fetch_graph":"https://pith.science/api/pith-number/JTTCUSVG3NZJ3FNID2G6UNZQPS/graph.json","fetch_events":"https://pith.science/api/pith-number/JTTCUSVG3NZJ3FNID2G6UNZQPS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JTTCUSVG3NZJ3FNID2G6UNZQPS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JTTCUSVG3NZJ3FNID2G6UNZQPS/action/storage_attestation","attest_author":"https://pith.science/pith/JTTCUSVG3NZJ3FNID2G6UNZQPS/action/author_attestation","sign_citation":"https://pith.science/pith/JTTCUSVG3NZJ3FNID2G6UNZQPS/action/citation_signature","submit_replication":"https://pith.science/pith/JTTCUSVG3NZJ3FNID2G6UNZQPS/action/replication_record"}},"created_at":"2026-07-05T08:12:56.135825+00:00","updated_at":"2026-07-05T08:12:56.135825+00:00"}