{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PLIO37BT4GHF4SAWKRWIMO36WO","short_pith_number":"pith:PLIO37BT","schema_version":"1.0","canonical_sha256":"7ad0edfc33e18e5e4816546c863b7eb39d4e231eb81b72626483802b4f60bbb9","source":{"kind":"arxiv","id":"2504.16763","version":1},"attestation_state":"computed","paper":{"title":"Noise-Tolerant Coreset-Based Class Incremental Continual Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Aswin Raghavan, Edison Mucllari, Zachary Alan Daniels","submitted_at":"2025-04-23T14:34:20Z","abstract_excerpt":"Many applications of computer vision require the ability to adapt to novel data distributions after deployment. Adaptation requires algorithms capable of continual learning (CL). Continual learners must be plastic to adapt to novel tasks while minimizing forgetting of previous tasks.However, CL opens up avenues for noise to enter the training pipeline and disrupt the CL. This work focuses on label noise and instance noise in the context of class-incremental learning (CIL), where new classes are added to a classifier over time, and there is no access to external data from past classes. We aim t"},"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":"2504.16763","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-23T14:34:20Z","cross_cats_sorted":["cs.AI","cs.CV","cs.NE"],"title_canon_sha256":"740927cb63190cd839ab61b7ed75a9d8f47ca7dd9e5bb3fd19dace5aabc4f3e3","abstract_canon_sha256":"ee3b9c7c1a169fb3c20817913c64024bb70ead2698f9b103cbe867e9eb80d1d3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:53:04.214834Z","signature_b64":"TD25TXDmycB/KJSnm8NYcZVTsRFNjMVQ9z8951+Zb6jzs/xr6nfaig/D4Kn56/l/njc0OdAdmEkMQBxA5rk3Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ad0edfc33e18e5e4816546c863b7eb39d4e231eb81b72626483802b4f60bbb9","last_reissued_at":"2026-07-05T10:53:04.214366Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:53:04.214366Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Noise-Tolerant Coreset-Based Class Incremental Continual Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Aswin Raghavan, Edison Mucllari, Zachary Alan Daniels","submitted_at":"2025-04-23T14:34:20Z","abstract_excerpt":"Many applications of computer vision require the ability to adapt to novel data distributions after deployment. Adaptation requires algorithms capable of continual learning (CL). Continual learners must be plastic to adapt to novel tasks while minimizing forgetting of previous tasks.However, CL opens up avenues for noise to enter the training pipeline and disrupt the CL. This work focuses on label noise and instance noise in the context of class-incremental learning (CIL), where new classes are added to a classifier over time, and there is no access to external data from past classes. We aim t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.16763","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/2504.16763/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":"2504.16763","created_at":"2026-07-05T10:53:04.214421+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.16763v1","created_at":"2026-07-05T10:53:04.214421+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.16763","created_at":"2026-07-05T10:53:04.214421+00:00"},{"alias_kind":"pith_short_12","alias_value":"PLIO37BT4GHF","created_at":"2026-07-05T10:53:04.214421+00:00"},{"alias_kind":"pith_short_16","alias_value":"PLIO37BT4GHF4SAW","created_at":"2026-07-05T10:53:04.214421+00:00"},{"alias_kind":"pith_short_8","alias_value":"PLIO37BT","created_at":"2026-07-05T10:53:04.214421+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/PLIO37BT4GHF4SAWKRWIMO36WO","json":"https://pith.science/pith/PLIO37BT4GHF4SAWKRWIMO36WO.json","graph_json":"https://pith.science/api/pith-number/PLIO37BT4GHF4SAWKRWIMO36WO/graph.json","events_json":"https://pith.science/api/pith-number/PLIO37BT4GHF4SAWKRWIMO36WO/events.json","paper":"https://pith.science/paper/PLIO37BT"},"agent_actions":{"view_html":"https://pith.science/pith/PLIO37BT4GHF4SAWKRWIMO36WO","download_json":"https://pith.science/pith/PLIO37BT4GHF4SAWKRWIMO36WO.json","view_paper":"https://pith.science/paper/PLIO37BT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.16763&json=true","fetch_graph":"https://pith.science/api/pith-number/PLIO37BT4GHF4SAWKRWIMO36WO/graph.json","fetch_events":"https://pith.science/api/pith-number/PLIO37BT4GHF4SAWKRWIMO36WO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PLIO37BT4GHF4SAWKRWIMO36WO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PLIO37BT4GHF4SAWKRWIMO36WO/action/storage_attestation","attest_author":"https://pith.science/pith/PLIO37BT4GHF4SAWKRWIMO36WO/action/author_attestation","sign_citation":"https://pith.science/pith/PLIO37BT4GHF4SAWKRWIMO36WO/action/citation_signature","submit_replication":"https://pith.science/pith/PLIO37BT4GHF4SAWKRWIMO36WO/action/replication_record"}},"created_at":"2026-07-05T10:53:04.214421+00:00","updated_at":"2026-07-05T10:53:04.214421+00:00"}