{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5ANSXHVIUW5QBZDYQO67U7T7UJ","short_pith_number":"pith:5ANSXHVI","schema_version":"1.0","canonical_sha256":"e81b2b9ea8a5bb00e47883bdfa7e7fa27617e30a76c4df5377fe2c40f937942f","source":{"kind":"arxiv","id":"2305.00876","version":2},"attestation_state":"computed","paper":{"title":"Exactly Tight Information-Theoretic Generalization Error Bound for the Quadratic Gaussian Problem","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["math.IT","stat.ML"],"primary_cat":"cs.IT","authors_text":"Chao Tian, Ruida Zhou, Tie Liu","submitted_at":"2023-05-01T15:22:58Z","abstract_excerpt":"We provide a new information-theoretic generalization error bound that is exactly tight (i.e., matching even the constant) for the canonical quadratic Gaussian (location) problem. Most existing bounds are order-wise loose in this setting, which has raised concerns about the fundamental capability of information-theoretic bounds in reasoning the generalization behavior for machine learning. The proposed new bound adopts the individual-sample-based approach proposed by Bu et al., but also has several key new ingredients. Firstly, instead of applying the change of measure inequality on the loss f"},"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":"2305.00876","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IT","submitted_at":"2023-05-01T15:22:58Z","cross_cats_sorted":["math.IT","stat.ML"],"title_canon_sha256":"64702e921d810f17faca664caf4fbce4096df7f66d8331b909aa28390bd78bfc","abstract_canon_sha256":"7d9d2b20c61309937ec2d187240a5df6dffa04bca41229202f065bdadd18e0e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:11:55.548243Z","signature_b64":"9IhWiDnGehoueQC3/iq3cV/IGQG9+/Q1MFccS8KTPEPcOX52k5jsXfMQohyrsQo+gzf5SRLAHFb62lxLW7AyBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e81b2b9ea8a5bb00e47883bdfa7e7fa27617e30a76c4df5377fe2c40f937942f","last_reissued_at":"2026-07-05T07:11:55.547757Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:11:55.547757Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exactly Tight Information-Theoretic Generalization Error Bound for the Quadratic Gaussian Problem","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["math.IT","stat.ML"],"primary_cat":"cs.IT","authors_text":"Chao Tian, Ruida Zhou, Tie Liu","submitted_at":"2023-05-01T15:22:58Z","abstract_excerpt":"We provide a new information-theoretic generalization error bound that is exactly tight (i.e., matching even the constant) for the canonical quadratic Gaussian (location) problem. Most existing bounds are order-wise loose in this setting, which has raised concerns about the fundamental capability of information-theoretic bounds in reasoning the generalization behavior for machine learning. The proposed new bound adopts the individual-sample-based approach proposed by Bu et al., but also has several key new ingredients. Firstly, instead of applying the change of measure inequality on the loss f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.00876","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/2305.00876/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":"2305.00876","created_at":"2026-07-05T07:11:55.547818+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.00876v2","created_at":"2026-07-05T07:11:55.547818+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.00876","created_at":"2026-07-05T07:11:55.547818+00:00"},{"alias_kind":"pith_short_12","alias_value":"5ANSXHVIUW5Q","created_at":"2026-07-05T07:11:55.547818+00:00"},{"alias_kind":"pith_short_16","alias_value":"5ANSXHVIUW5QBZDY","created_at":"2026-07-05T07:11:55.547818+00:00"},{"alias_kind":"pith_short_8","alias_value":"5ANSXHVI","created_at":"2026-07-05T07:11:55.547818+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.07861","citing_title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","ref_index":79,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5ANSXHVIUW5QBZDYQO67U7T7UJ","json":"https://pith.science/pith/5ANSXHVIUW5QBZDYQO67U7T7UJ.json","graph_json":"https://pith.science/api/pith-number/5ANSXHVIUW5QBZDYQO67U7T7UJ/graph.json","events_json":"https://pith.science/api/pith-number/5ANSXHVIUW5QBZDYQO67U7T7UJ/events.json","paper":"https://pith.science/paper/5ANSXHVI"},"agent_actions":{"view_html":"https://pith.science/pith/5ANSXHVIUW5QBZDYQO67U7T7UJ","download_json":"https://pith.science/pith/5ANSXHVIUW5QBZDYQO67U7T7UJ.json","view_paper":"https://pith.science/paper/5ANSXHVI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.00876&json=true","fetch_graph":"https://pith.science/api/pith-number/5ANSXHVIUW5QBZDYQO67U7T7UJ/graph.json","fetch_events":"https://pith.science/api/pith-number/5ANSXHVIUW5QBZDYQO67U7T7UJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5ANSXHVIUW5QBZDYQO67U7T7UJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5ANSXHVIUW5QBZDYQO67U7T7UJ/action/storage_attestation","attest_author":"https://pith.science/pith/5ANSXHVIUW5QBZDYQO67U7T7UJ/action/author_attestation","sign_citation":"https://pith.science/pith/5ANSXHVIUW5QBZDYQO67U7T7UJ/action/citation_signature","submit_replication":"https://pith.science/pith/5ANSXHVIUW5QBZDYQO67U7T7UJ/action/replication_record"}},"created_at":"2026-07-05T07:11:55.547818+00:00","updated_at":"2026-07-05T07:11:55.547818+00:00"}