{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:HFW7LVUENI2ILJLKGM7ATJUMCN","short_pith_number":"pith:HFW7LVUE","schema_version":"1.0","canonical_sha256":"396df5d6846a3485a56a333e09a68c1371adbb21743dabe208941153870f3f26","source":{"kind":"arxiv","id":"1907.07331","version":1},"attestation_state":"computed","paper":{"title":"Learnability for the Information Bottleneck","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ian Fischer, Isaac L. Chuang, Max Tegmark, Tailin Wu","submitted_at":"2019-07-17T04:48:01Z","abstract_excerpt":"The Information Bottleneck (IB) method (\\cite{tishby2000information}) provides an insightful and principled approach for balancing compression and prediction for representation learning. The IB objective $I(X;Z)-\\beta I(Y;Z)$ employs a Lagrange multiplier $\\beta$ to tune this trade-off. However, in practice, not only is $\\beta$ chosen empirically without theoretical guidance, there is also a lack of theoretical understanding between $\\beta$, learnability, the intrinsic nature of the dataset and model capacity. In this paper, we show that if $\\beta$ is improperly chosen, learning cannot happen "},"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":"1907.07331","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-17T04:48:01Z","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"title_canon_sha256":"6f05d3445f4fae3907a8ff86008a43a5b4ea4c2e1cc0a41e134ec551f993fd1c","abstract_canon_sha256":"6f117d1469077aab5fb7f20ba0e40dcbfe2c24d1621b6aca5b8225a37828d237"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:13:51.238599Z","signature_b64":"ARAQqltD3c4h5KlAzr928YkfO6cb9HaPlhHsgcojbqxaoA3UZlkWluXcgyA3+Fr7j78yFKDgkEheXrLSS0l0CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"396df5d6846a3485a56a333e09a68c1371adbb21743dabe208941153870f3f26","last_reissued_at":"2026-07-05T00:13:51.238175Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:13:51.238175Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learnability for the Information Bottleneck","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ian Fischer, Isaac L. Chuang, Max Tegmark, Tailin Wu","submitted_at":"2019-07-17T04:48:01Z","abstract_excerpt":"The Information Bottleneck (IB) method (\\cite{tishby2000information}) provides an insightful and principled approach for balancing compression and prediction for representation learning. The IB objective $I(X;Z)-\\beta I(Y;Z)$ employs a Lagrange multiplier $\\beta$ to tune this trade-off. However, in practice, not only is $\\beta$ chosen empirically without theoretical guidance, there is also a lack of theoretical understanding between $\\beta$, learnability, the intrinsic nature of the dataset and model capacity. In this paper, we show that if $\\beta$ is improperly chosen, learning cannot happen "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.07331","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/1907.07331/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":"1907.07331","created_at":"2026-07-05T00:13:51.238231+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.07331v1","created_at":"2026-07-05T00:13:51.238231+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.07331","created_at":"2026-07-05T00:13:51.238231+00:00"},{"alias_kind":"pith_short_12","alias_value":"HFW7LVUENI2I","created_at":"2026-07-05T00:13:51.238231+00:00"},{"alias_kind":"pith_short_16","alias_value":"HFW7LVUENI2ILJLK","created_at":"2026-07-05T00:13:51.238231+00:00"},{"alias_kind":"pith_short_8","alias_value":"HFW7LVUE","created_at":"2026-07-05T00:13:51.238231+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.08961","citing_title":"Pareto-optimal data compression for binary classification tasks","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HFW7LVUENI2ILJLKGM7ATJUMCN","json":"https://pith.science/pith/HFW7LVUENI2ILJLKGM7ATJUMCN.json","graph_json":"https://pith.science/api/pith-number/HFW7LVUENI2ILJLKGM7ATJUMCN/graph.json","events_json":"https://pith.science/api/pith-number/HFW7LVUENI2ILJLKGM7ATJUMCN/events.json","paper":"https://pith.science/paper/HFW7LVUE"},"agent_actions":{"view_html":"https://pith.science/pith/HFW7LVUENI2ILJLKGM7ATJUMCN","download_json":"https://pith.science/pith/HFW7LVUENI2ILJLKGM7ATJUMCN.json","view_paper":"https://pith.science/paper/HFW7LVUE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.07331&json=true","fetch_graph":"https://pith.science/api/pith-number/HFW7LVUENI2ILJLKGM7ATJUMCN/graph.json","fetch_events":"https://pith.science/api/pith-number/HFW7LVUENI2ILJLKGM7ATJUMCN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HFW7LVUENI2ILJLKGM7ATJUMCN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HFW7LVUENI2ILJLKGM7ATJUMCN/action/storage_attestation","attest_author":"https://pith.science/pith/HFW7LVUENI2ILJLKGM7ATJUMCN/action/author_attestation","sign_citation":"https://pith.science/pith/HFW7LVUENI2ILJLKGM7ATJUMCN/action/citation_signature","submit_replication":"https://pith.science/pith/HFW7LVUENI2ILJLKGM7ATJUMCN/action/replication_record"}},"created_at":"2026-07-05T00:13:51.238231+00:00","updated_at":"2026-07-05T00:13:51.238231+00:00"}