{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WSBV4JTSRGPMPUSNLL55LL6H4B","short_pith_number":"pith:WSBV4JTS","schema_version":"1.0","canonical_sha256":"b4835e2672899ec7d24d5afbd5afc7e04f355db1452f5c6d17cfe94d99d1dc70","source":{"kind":"arxiv","id":"2409.07325","version":2},"attestation_state":"computed","paper":{"title":"Statistically Valid Information Bottleneck via Multiple Hypothesis Testing","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG","math.IT"],"primary_cat":"cs.IT","authors_text":"Amirmohammad Farzaneh, Osvaldo Simeone","submitted_at":"2024-09-11T15:04:32Z","abstract_excerpt":"The information bottleneck (IB) problem is a widely studied framework in machine learning for extracting compressed features that are informative for downstream tasks. However, current approaches to solving the IB problem rely on a heuristic tuning of hyperparameters, offering no guarantees that the learned features satisfy information-theoretic constraints. In this work, we introduce a statistically valid solution to this problem, referred to as IB via multiple hypothesis testing (IB-MHT), which ensures that the learned features meet the IB constraints with high probability, regardless of the"},"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":"2409.07325","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IT","submitted_at":"2024-09-11T15:04:32Z","cross_cats_sorted":["cs.LG","math.IT"],"title_canon_sha256":"90ccebd554fe6107d491a86b825e0858ef4f92232041fb00830fa37156e39182","abstract_canon_sha256":"90f5d1e1d701719caec5d8d078088010f56430ec094d633ec948172e27813082"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:29.772433Z","signature_b64":"0ugIV0fYV04HzyoJRX4mWMlywKvJY0SP2ou+3ZppVGvV2eHEsAURsN/R4+6lqGaALeZwfKnF5jd6vDF0PzuCBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4835e2672899ec7d24d5afbd5afc7e04f355db1452f5c6d17cfe94d99d1dc70","last_reissued_at":"2026-07-05T09:18:29.771951Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:29.771951Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Statistically Valid Information Bottleneck via Multiple Hypothesis Testing","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG","math.IT"],"primary_cat":"cs.IT","authors_text":"Amirmohammad Farzaneh, Osvaldo Simeone","submitted_at":"2024-09-11T15:04:32Z","abstract_excerpt":"The information bottleneck (IB) problem is a widely studied framework in machine learning for extracting compressed features that are informative for downstream tasks. However, current approaches to solving the IB problem rely on a heuristic tuning of hyperparameters, offering no guarantees that the learned features satisfy information-theoretic constraints. In this work, we introduce a statistically valid solution to this problem, referred to as IB via multiple hypothesis testing (IB-MHT), which ensures that the learned features meet the IB constraints with high probability, regardless of the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.07325","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/2409.07325/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":"2409.07325","created_at":"2026-07-05T09:18:29.772003+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.07325v2","created_at":"2026-07-05T09:18:29.772003+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.07325","created_at":"2026-07-05T09:18:29.772003+00:00"},{"alias_kind":"pith_short_12","alias_value":"WSBV4JTSRGPM","created_at":"2026-07-05T09:18:29.772003+00:00"},{"alias_kind":"pith_short_16","alias_value":"WSBV4JTSRGPMPUSN","created_at":"2026-07-05T09:18:29.772003+00:00"},{"alias_kind":"pith_short_8","alias_value":"WSBV4JTS","created_at":"2026-07-05T09:18:29.772003+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.04206","citing_title":"Ensuring Reliability via Hyperparameter Selection: Review and Advances","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WSBV4JTSRGPMPUSNLL55LL6H4B","json":"https://pith.science/pith/WSBV4JTSRGPMPUSNLL55LL6H4B.json","graph_json":"https://pith.science/api/pith-number/WSBV4JTSRGPMPUSNLL55LL6H4B/graph.json","events_json":"https://pith.science/api/pith-number/WSBV4JTSRGPMPUSNLL55LL6H4B/events.json","paper":"https://pith.science/paper/WSBV4JTS"},"agent_actions":{"view_html":"https://pith.science/pith/WSBV4JTSRGPMPUSNLL55LL6H4B","download_json":"https://pith.science/pith/WSBV4JTSRGPMPUSNLL55LL6H4B.json","view_paper":"https://pith.science/paper/WSBV4JTS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.07325&json=true","fetch_graph":"https://pith.science/api/pith-number/WSBV4JTSRGPMPUSNLL55LL6H4B/graph.json","fetch_events":"https://pith.science/api/pith-number/WSBV4JTSRGPMPUSNLL55LL6H4B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WSBV4JTSRGPMPUSNLL55LL6H4B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WSBV4JTSRGPMPUSNLL55LL6H4B/action/storage_attestation","attest_author":"https://pith.science/pith/WSBV4JTSRGPMPUSNLL55LL6H4B/action/author_attestation","sign_citation":"https://pith.science/pith/WSBV4JTSRGPMPUSNLL55LL6H4B/action/citation_signature","submit_replication":"https://pith.science/pith/WSBV4JTSRGPMPUSNLL55LL6H4B/action/replication_record"}},"created_at":"2026-07-05T09:18:29.772003+00:00","updated_at":"2026-07-05T09:18:29.772003+00:00"}