{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IXTUQC4HQBNFNLPYDINHSTJNXM","short_pith_number":"pith:IXTUQC4H","schema_version":"1.0","canonical_sha256":"45e7480b87805a56adf81a1a794d2dbb39139d22efb04a2acc88b6a26e901524","source":{"kind":"arxiv","id":"2607.22931","version":1},"attestation_state":"computed","paper":{"title":"Spectral-Aware Analytic Class-Incremental Learning for Long-Tailed Distributions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Dimitris Metaxas, Hai Nguyen, Nam Le, Quan Dao, Quyen Tran, Trung Le, Zhuowei Li","submitted_at":"2026-07-24T22:12:15Z","abstract_excerpt":"Analytic Continual Learning (ACL) offers a computationally efficient alternative to gradient-based approaches. Recent ACL methods are based on Recursive Least Squares (RLS) and have achieved the state-of-the-art results compared to other alternatives. However, they falter significantly in Class-Incremental Learning scenarios characterized by Long-Tailed distributions. While the ill-conditioning of the autocorrelation (Gram) matrix is a known limitation of RLS, we demonstrate that class imbalance exacerbates this issue into a distinct spectral pathology: \"tail\" classes suffer from severe spectr"},"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":"2607.22931","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-24T22:12:15Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"80f4c12bdd2460b222038b4f499ad94de6b54c0bc45f20dd86972fae8d684570","abstract_canon_sha256":"ea406d525c86d5c7fa60352ef0dbccce5853ebd7323f7859bfa5d036fb8c8c52"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T00:22:02.742611Z","signature_b64":"kF1lCUezpMMI8OaW/vkXULdvH2+a77mkQmGED+uuFMv+f248aKi6eO69bYsvma64uIY2ooz2/tw+1ums1UVoCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45e7480b87805a56adf81a1a794d2dbb39139d22efb04a2acc88b6a26e901524","last_reissued_at":"2026-07-28T00:22:02.741703Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T00:22:02.741703Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spectral-Aware Analytic Class-Incremental Learning for Long-Tailed Distributions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Dimitris Metaxas, Hai Nguyen, Nam Le, Quan Dao, Quyen Tran, Trung Le, Zhuowei Li","submitted_at":"2026-07-24T22:12:15Z","abstract_excerpt":"Analytic Continual Learning (ACL) offers a computationally efficient alternative to gradient-based approaches. Recent ACL methods are based on Recursive Least Squares (RLS) and have achieved the state-of-the-art results compared to other alternatives. However, they falter significantly in Class-Incremental Learning scenarios characterized by Long-Tailed distributions. While the ill-conditioning of the autocorrelation (Gram) matrix is a known limitation of RLS, we demonstrate that class imbalance exacerbates this issue into a distinct spectral pathology: \"tail\" classes suffer from severe spectr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22931","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/2607.22931/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":"2607.22931","created_at":"2026-07-28T00:22:02.742169+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.22931v1","created_at":"2026-07-28T00:22:02.742169+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22931","created_at":"2026-07-28T00:22:02.742169+00:00"},{"alias_kind":"pith_short_12","alias_value":"IXTUQC4HQBNF","created_at":"2026-07-28T00:22:02.742169+00:00"},{"alias_kind":"pith_short_16","alias_value":"IXTUQC4HQBNFNLPY","created_at":"2026-07-28T00:22:02.742169+00:00"},{"alias_kind":"pith_short_8","alias_value":"IXTUQC4H","created_at":"2026-07-28T00:22:02.742169+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IXTUQC4HQBNFNLPYDINHSTJNXM","json":"https://pith.science/pith/IXTUQC4HQBNFNLPYDINHSTJNXM.json","graph_json":"https://pith.science/api/pith-number/IXTUQC4HQBNFNLPYDINHSTJNXM/graph.json","events_json":"https://pith.science/api/pith-number/IXTUQC4HQBNFNLPYDINHSTJNXM/events.json","paper":"https://pith.science/paper/IXTUQC4H"},"agent_actions":{"view_html":"https://pith.science/pith/IXTUQC4HQBNFNLPYDINHSTJNXM","download_json":"https://pith.science/pith/IXTUQC4HQBNFNLPYDINHSTJNXM.json","view_paper":"https://pith.science/paper/IXTUQC4H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.22931&json=true","fetch_graph":"https://pith.science/api/pith-number/IXTUQC4HQBNFNLPYDINHSTJNXM/graph.json","fetch_events":"https://pith.science/api/pith-number/IXTUQC4HQBNFNLPYDINHSTJNXM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IXTUQC4HQBNFNLPYDINHSTJNXM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IXTUQC4HQBNFNLPYDINHSTJNXM/action/storage_attestation","attest_author":"https://pith.science/pith/IXTUQC4HQBNFNLPYDINHSTJNXM/action/author_attestation","sign_citation":"https://pith.science/pith/IXTUQC4HQBNFNLPYDINHSTJNXM/action/citation_signature","submit_replication":"https://pith.science/pith/IXTUQC4HQBNFNLPYDINHSTJNXM/action/replication_record"}},"created_at":"2026-07-28T00:22:02.742169+00:00","updated_at":"2026-07-28T00:22:02.742169+00:00"}