{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:OUQR2AEVTPK32QK767NGWDNMAT","short_pith_number":"pith:OUQR2AEV","schema_version":"1.0","canonical_sha256":"75211d00959bd5bd415ff7da6b0dac04db9f7eca08f1d5a56a540d43969c6f5d","source":{"kind":"arxiv","id":"1808.07593","version":4},"attestation_state":"computed","paper":{"title":"Caveats for information bottleneck in deterministic scenarios","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Artemy Kolchinsky, Brendan D. Tracey, Steven Van Kuyk","submitted_at":"2018-08-23T00:13:18Z","abstract_excerpt":"Information bottleneck (IB) is a method for extracting information from one random variable $X$ that is relevant for predicting another random variable $Y$. To do so, IB identifies an intermediate \"bottleneck\" variable $T$ that has low mutual information $I(X;T)$ and high mutual information $I(Y;T)$. The \"IB curve\" characterizes the set of bottleneck variables that achieve maximal $I(Y;T)$ for a given $I(X;T)$, and is typically explored by maximizing the \"IB Lagrangian\", $I(Y;T) - \\beta I(X;T)$. In some cases, $Y$ is a deterministic function of $X$, including many classification problems in su"},"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":"1808.07593","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-08-23T00:13:18Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a5fd7d42c82bf649812d3fc3420e60ea6b89eb108c42e4fd03303729b6ecc385","abstract_canon_sha256":"8f798a7b1331d8a6ec64f672422887a33b487571b261b8e53db39aba6b725a58"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:17:22.535960Z","signature_b64":"eI9gvYSyQAlv1LUSVl4+XuudF1XhCtYdxC9rtak2DVX6iOWLiB8ASU7+9C1j6N7KeY9JWclNDvGZhzAZXWqtCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75211d00959bd5bd415ff7da6b0dac04db9f7eca08f1d5a56a540d43969c6f5d","last_reissued_at":"2026-07-05T05:17:22.535375Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:17:22.535375Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Caveats for information bottleneck in deterministic scenarios","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Artemy Kolchinsky, Brendan D. Tracey, Steven Van Kuyk","submitted_at":"2018-08-23T00:13:18Z","abstract_excerpt":"Information bottleneck (IB) is a method for extracting information from one random variable $X$ that is relevant for predicting another random variable $Y$. To do so, IB identifies an intermediate \"bottleneck\" variable $T$ that has low mutual information $I(X;T)$ and high mutual information $I(Y;T)$. The \"IB curve\" characterizes the set of bottleneck variables that achieve maximal $I(Y;T)$ for a given $I(X;T)$, and is typically explored by maximizing the \"IB Lagrangian\", $I(Y;T) - \\beta I(X;T)$. In some cases, $Y$ is a deterministic function of $X$, including many classification problems in su"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.07593","kind":"arxiv","version":4},"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/1808.07593/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":"1808.07593","created_at":"2026-07-05T05:17:22.535434+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.07593v4","created_at":"2026-07-05T05:17:22.535434+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.07593","created_at":"2026-07-05T05:17:22.535434+00:00"},{"alias_kind":"pith_short_12","alias_value":"OUQR2AEVTPK3","created_at":"2026-07-05T05:17:22.535434+00:00"},{"alias_kind":"pith_short_16","alias_value":"OUQR2AEVTPK32QK7","created_at":"2026-07-05T05:17:22.535434+00:00"},{"alias_kind":"pith_short_8","alias_value":"OUQR2AEV","created_at":"2026-07-05T05:17:22.535434+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.18455","citing_title":"Generalization Guarantees for Multi-View Representation Learning and Application to Regularization via Gaussian Product Mixture Prior","ref_index":53,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OUQR2AEVTPK32QK767NGWDNMAT","json":"https://pith.science/pith/OUQR2AEVTPK32QK767NGWDNMAT.json","graph_json":"https://pith.science/api/pith-number/OUQR2AEVTPK32QK767NGWDNMAT/graph.json","events_json":"https://pith.science/api/pith-number/OUQR2AEVTPK32QK767NGWDNMAT/events.json","paper":"https://pith.science/paper/OUQR2AEV"},"agent_actions":{"view_html":"https://pith.science/pith/OUQR2AEVTPK32QK767NGWDNMAT","download_json":"https://pith.science/pith/OUQR2AEVTPK32QK767NGWDNMAT.json","view_paper":"https://pith.science/paper/OUQR2AEV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.07593&json=true","fetch_graph":"https://pith.science/api/pith-number/OUQR2AEVTPK32QK767NGWDNMAT/graph.json","fetch_events":"https://pith.science/api/pith-number/OUQR2AEVTPK32QK767NGWDNMAT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OUQR2AEVTPK32QK767NGWDNMAT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OUQR2AEVTPK32QK767NGWDNMAT/action/storage_attestation","attest_author":"https://pith.science/pith/OUQR2AEVTPK32QK767NGWDNMAT/action/author_attestation","sign_citation":"https://pith.science/pith/OUQR2AEVTPK32QK767NGWDNMAT/action/citation_signature","submit_replication":"https://pith.science/pith/OUQR2AEVTPK32QK767NGWDNMAT/action/replication_record"}},"created_at":"2026-07-05T05:17:22.535434+00:00","updated_at":"2026-07-05T05:17:22.535434+00:00"}