{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VNBPGRJ5V2JZQINE7SVU6GW5Z5","short_pith_number":"pith:VNBPGRJ5","schema_version":"1.0","canonical_sha256":"ab42f3453dae939821a4fcab4f1addcf7140be196c02bc56be9bce5e95bfe974","source":{"kind":"arxiv","id":"2305.18806","version":2},"attestation_state":"computed","paper":{"title":"Prediction Error-based Classification for Class-Incremental Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Gido M. van de Ven, Micha{\\l} Zaj\\k{a}c, Tinne Tuytelaars","submitted_at":"2023-05-30T07:43:35Z","abstract_excerpt":"Class-incremental learning (CIL) is a particularly challenging variant of continual learning, where the goal is to learn to discriminate between all classes presented in an incremental fashion. Existing approaches often suffer from excessive forgetting and imbalance of the scores assigned to classes that have not been seen together during training. In this study, we introduce a novel approach, Prediction Error-based Classification (PEC), which differs from traditional discriminative and generative classification paradigms. PEC computes a class score by measuring the prediction error of a model"},"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":"2305.18806","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-30T07:43:35Z","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"title_canon_sha256":"20d5e308ae0cc43c2d53c58b443edcb1791e1c134d4e187d572b8887a0112461","abstract_canon_sha256":"2e35d26654eee7e67510ab9f3e62784e37a63d99e7a661619192cc840d58ffbd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:54:01.285533Z","signature_b64":"RLe0xRd+DWN17UTpBl/u83pMxAl5Pjm34Z5fpvHfutZ9SS9TvjV25cmLPseXgFHY5J+6TpP0eT36X0LJRbwlBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab42f3453dae939821a4fcab4f1addcf7140be196c02bc56be9bce5e95bfe974","last_reissued_at":"2026-07-05T07:54:01.285005Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:54:01.285005Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prediction Error-based Classification for Class-Incremental Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Gido M. van de Ven, Micha{\\l} Zaj\\k{a}c, Tinne Tuytelaars","submitted_at":"2023-05-30T07:43:35Z","abstract_excerpt":"Class-incremental learning (CIL) is a particularly challenging variant of continual learning, where the goal is to learn to discriminate between all classes presented in an incremental fashion. Existing approaches often suffer from excessive forgetting and imbalance of the scores assigned to classes that have not been seen together during training. In this study, we introduce a novel approach, Prediction Error-based Classification (PEC), which differs from traditional discriminative and generative classification paradigms. PEC computes a class score by measuring the prediction error of a model"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18806","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/2305.18806/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":"2305.18806","created_at":"2026-07-05T07:54:01.285068+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.18806v2","created_at":"2026-07-05T07:54:01.285068+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18806","created_at":"2026-07-05T07:54:01.285068+00:00"},{"alias_kind":"pith_short_12","alias_value":"VNBPGRJ5V2JZ","created_at":"2026-07-05T07:54:01.285068+00:00"},{"alias_kind":"pith_short_16","alias_value":"VNBPGRJ5V2JZQINE","created_at":"2026-07-05T07:54:01.285068+00:00"},{"alias_kind":"pith_short_8","alias_value":"VNBPGRJ5","created_at":"2026-07-05T07:54:01.285068+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.05926","citing_title":"Autoencoder-Based Hybrid Replay for Class-Incremental Learning","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VNBPGRJ5V2JZQINE7SVU6GW5Z5","json":"https://pith.science/pith/VNBPGRJ5V2JZQINE7SVU6GW5Z5.json","graph_json":"https://pith.science/api/pith-number/VNBPGRJ5V2JZQINE7SVU6GW5Z5/graph.json","events_json":"https://pith.science/api/pith-number/VNBPGRJ5V2JZQINE7SVU6GW5Z5/events.json","paper":"https://pith.science/paper/VNBPGRJ5"},"agent_actions":{"view_html":"https://pith.science/pith/VNBPGRJ5V2JZQINE7SVU6GW5Z5","download_json":"https://pith.science/pith/VNBPGRJ5V2JZQINE7SVU6GW5Z5.json","view_paper":"https://pith.science/paper/VNBPGRJ5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.18806&json=true","fetch_graph":"https://pith.science/api/pith-number/VNBPGRJ5V2JZQINE7SVU6GW5Z5/graph.json","fetch_events":"https://pith.science/api/pith-number/VNBPGRJ5V2JZQINE7SVU6GW5Z5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VNBPGRJ5V2JZQINE7SVU6GW5Z5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VNBPGRJ5V2JZQINE7SVU6GW5Z5/action/storage_attestation","attest_author":"https://pith.science/pith/VNBPGRJ5V2JZQINE7SVU6GW5Z5/action/author_attestation","sign_citation":"https://pith.science/pith/VNBPGRJ5V2JZQINE7SVU6GW5Z5/action/citation_signature","submit_replication":"https://pith.science/pith/VNBPGRJ5V2JZQINE7SVU6GW5Z5/action/replication_record"}},"created_at":"2026-07-05T07:54:01.285068+00:00","updated_at":"2026-07-05T07:54:01.285068+00:00"}