{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:XSYLGXBHCQD4HBLZ64QP62KBMG","short_pith_number":"pith:XSYLGXBH","schema_version":"1.0","canonical_sha256":"bcb0b35c271407c38579f720ff694161b2e75bbd7a8db710f6f3bff4190727f7","source":{"kind":"arxiv","id":"2010.15277","version":3},"attestation_state":"computed","paper":{"title":"Class-incremental learning: survey and performance evaluation on image classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Andrew D. Bagdanov, Bartlomiej Twardowski, Joost Van De Weijer, Marc Masana, Mikel Menta, Xialei Liu","submitted_at":"2020-10-28T23:28:15Z","abstract_excerpt":"For future learning systems, incremental learning is desirable because it allows for: efficient resource usage by eliminating the need to retrain from scratch at the arrival of new data; reduced memory usage by preventing or limiting the amount of data required to be stored -- also important when privacy limitations are imposed; and learning that more closely resembles human learning. The main challenge for incremental learning is catastrophic forgetting, which refers to the precipitous drop in performance on previously learned tasks after learning a new one. Incremental learning of deep neura"},"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":"2010.15277","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-28T23:28:15Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"9c9b27ee4e675621ba411ac5f30061e3697d9860674d398066e952cce1497f2b","abstract_canon_sha256":"8e12845839faddc2295207ad3ef5fc670907c3df52c4bd7a9e2479c3d68a16a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:04:59.023879Z","signature_b64":"Z9ABPjuJ+hxA/7RWYDAnXFEM7hhEbFDb9u2GKxaxSYPnlYIvhSvlK/gA1iUh4MOKm9fycTjTzM3Q4lm2vbRMAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bcb0b35c271407c38579f720ff694161b2e75bbd7a8db710f6f3bff4190727f7","last_reissued_at":"2026-07-05T05:04:59.023452Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:04:59.023452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Class-incremental learning: survey and performance evaluation on image classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Andrew D. Bagdanov, Bartlomiej Twardowski, Joost Van De Weijer, Marc Masana, Mikel Menta, Xialei Liu","submitted_at":"2020-10-28T23:28:15Z","abstract_excerpt":"For future learning systems, incremental learning is desirable because it allows for: efficient resource usage by eliminating the need to retrain from scratch at the arrival of new data; reduced memory usage by preventing or limiting the amount of data required to be stored -- also important when privacy limitations are imposed; and learning that more closely resembles human learning. The main challenge for incremental learning is catastrophic forgetting, which refers to the precipitous drop in performance on previously learned tasks after learning a new one. Incremental learning of deep neura"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.15277","kind":"arxiv","version":3},"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/2010.15277/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":"2010.15277","created_at":"2026-07-05T05:04:59.023512+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.15277v3","created_at":"2026-07-05T05:04:59.023512+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.15277","created_at":"2026-07-05T05:04:59.023512+00:00"},{"alias_kind":"pith_short_12","alias_value":"XSYLGXBHCQD4","created_at":"2026-07-05T05:04:59.023512+00:00"},{"alias_kind":"pith_short_16","alias_value":"XSYLGXBHCQD4HBLZ","created_at":"2026-07-05T05:04:59.023512+00:00"},{"alias_kind":"pith_short_8","alias_value":"XSYLGXBH","created_at":"2026-07-05T05:04:59.023512+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26097","citing_title":"Forgetting in Language Models: Capacity, Optimization, and Self-Generated Replay","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XSYLGXBHCQD4HBLZ64QP62KBMG","json":"https://pith.science/pith/XSYLGXBHCQD4HBLZ64QP62KBMG.json","graph_json":"https://pith.science/api/pith-number/XSYLGXBHCQD4HBLZ64QP62KBMG/graph.json","events_json":"https://pith.science/api/pith-number/XSYLGXBHCQD4HBLZ64QP62KBMG/events.json","paper":"https://pith.science/paper/XSYLGXBH"},"agent_actions":{"view_html":"https://pith.science/pith/XSYLGXBHCQD4HBLZ64QP62KBMG","download_json":"https://pith.science/pith/XSYLGXBHCQD4HBLZ64QP62KBMG.json","view_paper":"https://pith.science/paper/XSYLGXBH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.15277&json=true","fetch_graph":"https://pith.science/api/pith-number/XSYLGXBHCQD4HBLZ64QP62KBMG/graph.json","fetch_events":"https://pith.science/api/pith-number/XSYLGXBHCQD4HBLZ64QP62KBMG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XSYLGXBHCQD4HBLZ64QP62KBMG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XSYLGXBHCQD4HBLZ64QP62KBMG/action/storage_attestation","attest_author":"https://pith.science/pith/XSYLGXBHCQD4HBLZ64QP62KBMG/action/author_attestation","sign_citation":"https://pith.science/pith/XSYLGXBHCQD4HBLZ64QP62KBMG/action/citation_signature","submit_replication":"https://pith.science/pith/XSYLGXBHCQD4HBLZ64QP62KBMG/action/replication_record"}},"created_at":"2026-07-05T05:04:59.023512+00:00","updated_at":"2026-07-05T05:04:59.023512+00:00"}