{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OFTAD5AGYNUJHMYGBSQJDRWU6J","short_pith_number":"pith:OFTAD5AG","schema_version":"1.0","canonical_sha256":"716601f406c36893b3060ca091c6d4f26cb9e89a25ccdce712f39fc3895c0ec3","source":{"kind":"arxiv","id":"2505.22602","version":1},"attestation_state":"computed","paper":{"title":"One Rank at a Time: Cascading Error Dynamics in Sequential Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","math.OC"],"primary_cat":"cs.LG","authors_text":"Anastasios Kyrillidis, Fangshuo (Jasper) Liao, Mahtab Alizadeh Vandchali","submitted_at":"2025-05-28T17:16:24Z","abstract_excerpt":"Sequential learning -- where complex tasks are broken down into simpler, hierarchical components -- has emerged as a paradigm in AI. This paper views sequential learning through the lens of low-rank linear regression, focusing specifically on how errors propagate when learning rank-1 subspaces sequentially. We present an analysis framework that decomposes the learning process into a series of rank-1 estimation problems, where each subsequent estimation depends on the accuracy of previous steps. Our contribution is a characterization of the error propagation in this sequential process, establis"},"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":"2505.22602","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-28T17:16:24Z","cross_cats_sorted":["cs.AI","math.OC"],"title_canon_sha256":"59a7dddd8718c89bca68a06950aee48acf55c9962b88a7978047e4a072e0bd9b","abstract_canon_sha256":"0f7daad8009c8a0aaddbd2ee059bc16134b1825b92bf2316800cbc0f00331293"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:27.504132Z","signature_b64":"LVkHiRmrLGHUnhcy6k7gVyZoFxRQWdAr0x0px3E0rRZiA/GtEWkEHqtNituk2YvRbLOeoscNH0TMOQGj4XQ4DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"716601f406c36893b3060ca091c6d4f26cb9e89a25ccdce712f39fc3895c0ec3","last_reissued_at":"2026-07-05T11:11:27.503617Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:27.503617Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"One Rank at a Time: Cascading Error Dynamics in Sequential Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","math.OC"],"primary_cat":"cs.LG","authors_text":"Anastasios Kyrillidis, Fangshuo (Jasper) Liao, Mahtab Alizadeh Vandchali","submitted_at":"2025-05-28T17:16:24Z","abstract_excerpt":"Sequential learning -- where complex tasks are broken down into simpler, hierarchical components -- has emerged as a paradigm in AI. This paper views sequential learning through the lens of low-rank linear regression, focusing specifically on how errors propagate when learning rank-1 subspaces sequentially. We present an analysis framework that decomposes the learning process into a series of rank-1 estimation problems, where each subsequent estimation depends on the accuracy of previous steps. Our contribution is a characterization of the error propagation in this sequential process, establis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22602","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/2505.22602/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":"2505.22602","created_at":"2026-07-05T11:11:27.503677+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.22602v1","created_at":"2026-07-05T11:11:27.503677+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22602","created_at":"2026-07-05T11:11:27.503677+00:00"},{"alias_kind":"pith_short_12","alias_value":"OFTAD5AGYNUJ","created_at":"2026-07-05T11:11:27.503677+00:00"},{"alias_kind":"pith_short_16","alias_value":"OFTAD5AGYNUJHMYG","created_at":"2026-07-05T11:11:27.503677+00:00"},{"alias_kind":"pith_short_8","alias_value":"OFTAD5AG","created_at":"2026-07-05T11:11:27.503677+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.10741","citing_title":"AdaPaD: Adaptive Parallel Deflation for PEFT with Self-Correcting Rank Discovery","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OFTAD5AGYNUJHMYGBSQJDRWU6J","json":"https://pith.science/pith/OFTAD5AGYNUJHMYGBSQJDRWU6J.json","graph_json":"https://pith.science/api/pith-number/OFTAD5AGYNUJHMYGBSQJDRWU6J/graph.json","events_json":"https://pith.science/api/pith-number/OFTAD5AGYNUJHMYGBSQJDRWU6J/events.json","paper":"https://pith.science/paper/OFTAD5AG"},"agent_actions":{"view_html":"https://pith.science/pith/OFTAD5AGYNUJHMYGBSQJDRWU6J","download_json":"https://pith.science/pith/OFTAD5AGYNUJHMYGBSQJDRWU6J.json","view_paper":"https://pith.science/paper/OFTAD5AG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.22602&json=true","fetch_graph":"https://pith.science/api/pith-number/OFTAD5AGYNUJHMYGBSQJDRWU6J/graph.json","fetch_events":"https://pith.science/api/pith-number/OFTAD5AGYNUJHMYGBSQJDRWU6J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OFTAD5AGYNUJHMYGBSQJDRWU6J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OFTAD5AGYNUJHMYGBSQJDRWU6J/action/storage_attestation","attest_author":"https://pith.science/pith/OFTAD5AGYNUJHMYGBSQJDRWU6J/action/author_attestation","sign_citation":"https://pith.science/pith/OFTAD5AGYNUJHMYGBSQJDRWU6J/action/citation_signature","submit_replication":"https://pith.science/pith/OFTAD5AGYNUJHMYGBSQJDRWU6J/action/replication_record"}},"created_at":"2026-07-05T11:11:27.503677+00:00","updated_at":"2026-07-05T11:11:27.503677+00:00"}