{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:STN3VFCACEK5AN4ZSHGIJFLJVE","short_pith_number":"pith:STN3VFCA","schema_version":"1.0","canonical_sha256":"94dbba94401115d0379991cc849569a910611feef469fe433b8a22e15202d3a9","source":{"kind":"arxiv","id":"2207.00005","version":2},"attestation_state":"computed","paper":{"title":"Class Impression for Data-free Incremental Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Purang Abolmaesumi, Sana Ayromlou, Teresa Tsang, Xiaoxiao Li","submitted_at":"2022-06-26T06:20:17Z","abstract_excerpt":"Standard deep learning-based classification approaches require collecting all samples from all classes in advance and are trained offline. This paradigm may not be practical in real-world clinical applications, where new classes are incrementally introduced through the addition of new data. Class incremental learning is a strategy allowing learning from such data. However, a major challenge is catastrophic forgetting, i.e., performance degradation on previous classes when adapting a trained model to new data. Prior methodologies to alleviate this challenge save a portion of training data requi"},"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":"2207.00005","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-26T06:20:17Z","cross_cats_sorted":["cs.AI","cs.LG","eess.IV"],"title_canon_sha256":"ee92a9b45545397545d8718aa3965fb292597bbc4c2c154ad3f9d444f4cb639d","abstract_canon_sha256":"575759dc8d11e1184b00f166b54e337a228a98800901f47708810a81db6466cc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:37:07.199755Z","signature_b64":"fn2ZontnPSDH/sKKmgok/SOrTrJxwa6tqpgkWdxQoD/7A3D/Vif5ji5tH0/Qy2I8SnFsP4uRMdrDLXEeAfAHAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94dbba94401115d0379991cc849569a910611feef469fe433b8a22e15202d3a9","last_reissued_at":"2026-07-05T04:37:07.199285Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:37:07.199285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Class Impression for Data-free Incremental Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Purang Abolmaesumi, Sana Ayromlou, Teresa Tsang, Xiaoxiao Li","submitted_at":"2022-06-26T06:20:17Z","abstract_excerpt":"Standard deep learning-based classification approaches require collecting all samples from all classes in advance and are trained offline. This paradigm may not be practical in real-world clinical applications, where new classes are incrementally introduced through the addition of new data. Class incremental learning is a strategy allowing learning from such data. However, a major challenge is catastrophic forgetting, i.e., performance degradation on previous classes when adapting a trained model to new data. Prior methodologies to alleviate this challenge save a portion of training data requi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.00005","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/2207.00005/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":"2207.00005","created_at":"2026-07-05T04:37:07.199352+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.00005v2","created_at":"2026-07-05T04:37:07.199352+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.00005","created_at":"2026-07-05T04:37:07.199352+00:00"},{"alias_kind":"pith_short_12","alias_value":"STN3VFCACEK5","created_at":"2026-07-05T04:37:07.199352+00:00"},{"alias_kind":"pith_short_16","alias_value":"STN3VFCACEK5AN4Z","created_at":"2026-07-05T04:37:07.199352+00:00"},{"alias_kind":"pith_short_8","alias_value":"STN3VFCA","created_at":"2026-07-05T04:37:07.199352+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/STN3VFCACEK5AN4ZSHGIJFLJVE","json":"https://pith.science/pith/STN3VFCACEK5AN4ZSHGIJFLJVE.json","graph_json":"https://pith.science/api/pith-number/STN3VFCACEK5AN4ZSHGIJFLJVE/graph.json","events_json":"https://pith.science/api/pith-number/STN3VFCACEK5AN4ZSHGIJFLJVE/events.json","paper":"https://pith.science/paper/STN3VFCA"},"agent_actions":{"view_html":"https://pith.science/pith/STN3VFCACEK5AN4ZSHGIJFLJVE","download_json":"https://pith.science/pith/STN3VFCACEK5AN4ZSHGIJFLJVE.json","view_paper":"https://pith.science/paper/STN3VFCA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.00005&json=true","fetch_graph":"https://pith.science/api/pith-number/STN3VFCACEK5AN4ZSHGIJFLJVE/graph.json","fetch_events":"https://pith.science/api/pith-number/STN3VFCACEK5AN4ZSHGIJFLJVE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/STN3VFCACEK5AN4ZSHGIJFLJVE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/STN3VFCACEK5AN4ZSHGIJFLJVE/action/storage_attestation","attest_author":"https://pith.science/pith/STN3VFCACEK5AN4ZSHGIJFLJVE/action/author_attestation","sign_citation":"https://pith.science/pith/STN3VFCACEK5AN4ZSHGIJFLJVE/action/citation_signature","submit_replication":"https://pith.science/pith/STN3VFCACEK5AN4ZSHGIJFLJVE/action/replication_record"}},"created_at":"2026-07-05T04:37:07.199352+00:00","updated_at":"2026-07-05T04:37:07.199352+00:00"}