{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XIREOBBAPK3ZFCGTH6YYPEUEJO","short_pith_number":"pith:XIREOBBA","schema_version":"1.0","canonical_sha256":"ba224704207ab79288d33fb18792844b88793878497b7dc55a99fef47afef0ca","source":{"kind":"arxiv","id":"2401.02904","version":1},"attestation_state":"computed","paper":{"title":"Class-wise Generalization Error: an Information-Theoretic Analysis","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Firas Laakom, Moncef Gabbouj, Yuheng Bu","submitted_at":"2024-01-05T17:05:14Z","abstract_excerpt":"Existing generalization theories of supervised learning typically take a holistic approach and provide bounds for the expected generalization over the whole data distribution, which implicitly assumes that the model generalizes similarly for all the classes. In practice, however, there are significant variations in generalization performance among different classes, which cannot be captured by the existing generalization bounds. In this work, we tackle this problem by theoretically studying the class-generalization error, which quantifies the generalization performance of each individual class"},"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":"2401.02904","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-05T17:05:14Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"71dacd58f3e845d4f5624fd246009e985fb09ee3256a5f76130ba4049c7dd8f4","abstract_canon_sha256":"658b238c04efca5da0206fc590be348c4af2af12cd9a67cc5c5c450c79914bb0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:30:39.931228Z","signature_b64":"+H+2zcKqcru2G4em9w1iaE0U8Bnzx/R5IvIheRfZ8w8xorxKVJ6xxyVXks688F5X45xlQNE6GR8sSvEjihp5Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba224704207ab79288d33fb18792844b88793878497b7dc55a99fef47afef0ca","last_reissued_at":"2026-07-05T07:30:39.930814Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:30:39.930814Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Class-wise Generalization Error: an Information-Theoretic Analysis","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Firas Laakom, Moncef Gabbouj, Yuheng Bu","submitted_at":"2024-01-05T17:05:14Z","abstract_excerpt":"Existing generalization theories of supervised learning typically take a holistic approach and provide bounds for the expected generalization over the whole data distribution, which implicitly assumes that the model generalizes similarly for all the classes. In practice, however, there are significant variations in generalization performance among different classes, which cannot be captured by the existing generalization bounds. In this work, we tackle this problem by theoretically studying the class-generalization error, which quantifies the generalization performance of each individual class"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.02904","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/2401.02904/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":"2401.02904","created_at":"2026-07-05T07:30:39.930870+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.02904v1","created_at":"2026-07-05T07:30:39.930870+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.02904","created_at":"2026-07-05T07:30:39.930870+00:00"},{"alias_kind":"pith_short_12","alias_value":"XIREOBBAPK3Z","created_at":"2026-07-05T07:30:39.930870+00:00"},{"alias_kind":"pith_short_16","alias_value":"XIREOBBAPK3ZFCGT","created_at":"2026-07-05T07:30:39.930870+00:00"},{"alias_kind":"pith_short_8","alias_value":"XIREOBBA","created_at":"2026-07-05T07:30:39.930870+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.23448","citing_title":"An Information-Theoretic Analysis of OOD Generalization in Meta-Reinforcement Learning","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XIREOBBAPK3ZFCGTH6YYPEUEJO","json":"https://pith.science/pith/XIREOBBAPK3ZFCGTH6YYPEUEJO.json","graph_json":"https://pith.science/api/pith-number/XIREOBBAPK3ZFCGTH6YYPEUEJO/graph.json","events_json":"https://pith.science/api/pith-number/XIREOBBAPK3ZFCGTH6YYPEUEJO/events.json","paper":"https://pith.science/paper/XIREOBBA"},"agent_actions":{"view_html":"https://pith.science/pith/XIREOBBAPK3ZFCGTH6YYPEUEJO","download_json":"https://pith.science/pith/XIREOBBAPK3ZFCGTH6YYPEUEJO.json","view_paper":"https://pith.science/paper/XIREOBBA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.02904&json=true","fetch_graph":"https://pith.science/api/pith-number/XIREOBBAPK3ZFCGTH6YYPEUEJO/graph.json","fetch_events":"https://pith.science/api/pith-number/XIREOBBAPK3ZFCGTH6YYPEUEJO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XIREOBBAPK3ZFCGTH6YYPEUEJO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XIREOBBAPK3ZFCGTH6YYPEUEJO/action/storage_attestation","attest_author":"https://pith.science/pith/XIREOBBAPK3ZFCGTH6YYPEUEJO/action/author_attestation","sign_citation":"https://pith.science/pith/XIREOBBAPK3ZFCGTH6YYPEUEJO/action/citation_signature","submit_replication":"https://pith.science/pith/XIREOBBAPK3ZFCGTH6YYPEUEJO/action/replication_record"}},"created_at":"2026-07-05T07:30:39.930870+00:00","updated_at":"2026-07-05T07:30:39.930870+00:00"}