{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:XQ4MX73SULX34ZO7NEDICNL4MS","short_pith_number":"pith:XQ4MX73S","schema_version":"1.0","canonical_sha256":"bc38cbff72a2efbe65df690681357c64bb34a79e853aa4c10da07d6644b1e602","source":{"kind":"arxiv","id":"1705.02436","version":9},"attestation_state":"computed","paper":{"title":"Nonlinear Information Bottleneck","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.IT","stat.ML"],"primary_cat":"cs.IT","authors_text":"Artemy Kolchinsky, Brendan D. Tracey, David H. Wolpert","submitted_at":"2017-05-06T03:13:21Z","abstract_excerpt":"Information bottleneck (IB) is a technique for extracting information in one random variable $X$ that is relevant for predicting another random variable $Y$. IB works by encoding $X$ in a compressed \"bottleneck\" random variable $M$ from which $Y$ can be accurately decoded. However, finding the optimal bottleneck variable involves a difficult optimization problem, which until recently has been considered for only two limited cases: discrete $X$ and $Y$ with small state spaces, and continuous $X$ and $Y$ with a Gaussian joint distribution (in which case optimal encoding and decoding maps are lin"},"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":"1705.02436","kind":"arxiv","version":9},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2017-05-06T03:13:21Z","cross_cats_sorted":["cs.LG","math.IT","stat.ML"],"title_canon_sha256":"526cf7eac7858085928d49ee7182f0f3b841ddb247c713e22d7186e1236f7cf1","abstract_canon_sha256":"7fb810e7df2e493848f1b59034332958240bf5daa0c2e578e0ea5276f3c90f0a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:17:22.281944Z","signature_b64":"8Xo07JYms3v7qqCBTZVfxLXz9PspSa3rvM1tsD+nKW90is6sa20zZaODaTxaKyae20ZY9T5MKL8O8ghAwNjiBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc38cbff72a2efbe65df690681357c64bb34a79e853aa4c10da07d6644b1e602","last_reissued_at":"2026-07-05T05:17:22.281463Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:17:22.281463Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Nonlinear Information Bottleneck","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.IT","stat.ML"],"primary_cat":"cs.IT","authors_text":"Artemy Kolchinsky, Brendan D. Tracey, David H. Wolpert","submitted_at":"2017-05-06T03:13:21Z","abstract_excerpt":"Information bottleneck (IB) is a technique for extracting information in one random variable $X$ that is relevant for predicting another random variable $Y$. IB works by encoding $X$ in a compressed \"bottleneck\" random variable $M$ from which $Y$ can be accurately decoded. However, finding the optimal bottleneck variable involves a difficult optimization problem, which until recently has been considered for only two limited cases: discrete $X$ and $Y$ with small state spaces, and continuous $X$ and $Y$ with a Gaussian joint distribution (in which case optimal encoding and decoding maps are lin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.02436","kind":"arxiv","version":9},"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/1705.02436/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":"1705.02436","created_at":"2026-07-05T05:17:22.281515+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.02436v9","created_at":"2026-07-05T05:17:22.281515+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.02436","created_at":"2026-07-05T05:17:22.281515+00:00"},{"alias_kind":"pith_short_12","alias_value":"XQ4MX73SULX3","created_at":"2026-07-05T05:17:22.281515+00:00"},{"alias_kind":"pith_short_16","alias_value":"XQ4MX73SULX34ZO7","created_at":"2026-07-05T05:17:22.281515+00:00"},{"alias_kind":"pith_short_8","alias_value":"XQ4MX73S","created_at":"2026-07-05T05:17:22.281515+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.01580","citing_title":"The HSIC Bottleneck: Deep Learning without Back-Propagation","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XQ4MX73SULX34ZO7NEDICNL4MS","json":"https://pith.science/pith/XQ4MX73SULX34ZO7NEDICNL4MS.json","graph_json":"https://pith.science/api/pith-number/XQ4MX73SULX34ZO7NEDICNL4MS/graph.json","events_json":"https://pith.science/api/pith-number/XQ4MX73SULX34ZO7NEDICNL4MS/events.json","paper":"https://pith.science/paper/XQ4MX73S"},"agent_actions":{"view_html":"https://pith.science/pith/XQ4MX73SULX34ZO7NEDICNL4MS","download_json":"https://pith.science/pith/XQ4MX73SULX34ZO7NEDICNL4MS.json","view_paper":"https://pith.science/paper/XQ4MX73S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.02436&json=true","fetch_graph":"https://pith.science/api/pith-number/XQ4MX73SULX34ZO7NEDICNL4MS/graph.json","fetch_events":"https://pith.science/api/pith-number/XQ4MX73SULX34ZO7NEDICNL4MS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XQ4MX73SULX34ZO7NEDICNL4MS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XQ4MX73SULX34ZO7NEDICNL4MS/action/storage_attestation","attest_author":"https://pith.science/pith/XQ4MX73SULX34ZO7NEDICNL4MS/action/author_attestation","sign_citation":"https://pith.science/pith/XQ4MX73SULX34ZO7NEDICNL4MS/action/citation_signature","submit_replication":"https://pith.science/pith/XQ4MX73SULX34ZO7NEDICNL4MS/action/replication_record"}},"created_at":"2026-07-05T05:17:22.281515+00:00","updated_at":"2026-07-05T05:17:22.281515+00:00"}