{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:A5KV7JKFI76ELNIXW53JADR5ZY","short_pith_number":"pith:A5KV7JKF","schema_version":"1.0","canonical_sha256":"07555fa54547fc45b517b776900e3dce21fa3dadd2b8640e668c1a353af05c02","source":{"kind":"arxiv","id":"2305.16559","version":1},"attestation_state":"computed","paper":{"title":"Teamwork Is Not Always Good: An Empirical Study of Classifier Drift in Class-incremental Information Extraction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Lifu Huang, Minqian Liu","submitted_at":"2023-05-26T00:57:43Z","abstract_excerpt":"Class-incremental learning (CIL) aims to develop a learning system that can continually learn new classes from a data stream without forgetting previously learned classes. When learning classes incrementally, the classifier must be constantly updated to incorporate new classes, and the drift in decision boundary may lead to severe forgetting. This fundamental challenge, however, has not yet been studied extensively, especially in the setting where no samples from old classes are stored for rehearsal. In this paper, we take a closer look at how the drift in the classifier leads to forgetting, a"},"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":"2305.16559","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-26T00:57:43Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3d52f5b583e223b016143efe41796ffd3efb66c23b27d25341900c8178a5e38b","abstract_canon_sha256":"dd13d58da5039260a296be55a2a8be017134e12981bf6ca4e7ec88bf83bede9a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:14:14.340460Z","signature_b64":"LTmqPPhZZKu9I8fmFd36GaLzIdEv/WKE9Ick5PqhKoIKPAfXse26vv223d+ReORCqOmK5a6eVAmIbbF2tke3Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07555fa54547fc45b517b776900e3dce21fa3dadd2b8640e668c1a353af05c02","last_reissued_at":"2026-07-05T06:14:14.340077Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:14:14.340077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Teamwork Is Not Always Good: An Empirical Study of Classifier Drift in Class-incremental Information Extraction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Lifu Huang, Minqian Liu","submitted_at":"2023-05-26T00:57:43Z","abstract_excerpt":"Class-incremental learning (CIL) aims to develop a learning system that can continually learn new classes from a data stream without forgetting previously learned classes. When learning classes incrementally, the classifier must be constantly updated to incorporate new classes, and the drift in decision boundary may lead to severe forgetting. This fundamental challenge, however, has not yet been studied extensively, especially in the setting where no samples from old classes are stored for rehearsal. In this paper, we take a closer look at how the drift in the classifier leads to forgetting, a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.16559","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/2305.16559/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":"2305.16559","created_at":"2026-07-05T06:14:14.340130+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.16559v1","created_at":"2026-07-05T06:14:14.340130+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.16559","created_at":"2026-07-05T06:14:14.340130+00:00"},{"alias_kind":"pith_short_12","alias_value":"A5KV7JKFI76E","created_at":"2026-07-05T06:14:14.340130+00:00"},{"alias_kind":"pith_short_16","alias_value":"A5KV7JKFI76ELNIX","created_at":"2026-07-05T06:14:14.340130+00:00"},{"alias_kind":"pith_short_8","alias_value":"A5KV7JKF","created_at":"2026-07-05T06:14:14.340130+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.13453","citing_title":"Spurious Forgetting in Continual Learning of Language Models","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A5KV7JKFI76ELNIXW53JADR5ZY","json":"https://pith.science/pith/A5KV7JKFI76ELNIXW53JADR5ZY.json","graph_json":"https://pith.science/api/pith-number/A5KV7JKFI76ELNIXW53JADR5ZY/graph.json","events_json":"https://pith.science/api/pith-number/A5KV7JKFI76ELNIXW53JADR5ZY/events.json","paper":"https://pith.science/paper/A5KV7JKF"},"agent_actions":{"view_html":"https://pith.science/pith/A5KV7JKFI76ELNIXW53JADR5ZY","download_json":"https://pith.science/pith/A5KV7JKFI76ELNIXW53JADR5ZY.json","view_paper":"https://pith.science/paper/A5KV7JKF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.16559&json=true","fetch_graph":"https://pith.science/api/pith-number/A5KV7JKFI76ELNIXW53JADR5ZY/graph.json","fetch_events":"https://pith.science/api/pith-number/A5KV7JKFI76ELNIXW53JADR5ZY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A5KV7JKFI76ELNIXW53JADR5ZY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A5KV7JKFI76ELNIXW53JADR5ZY/action/storage_attestation","attest_author":"https://pith.science/pith/A5KV7JKFI76ELNIXW53JADR5ZY/action/author_attestation","sign_citation":"https://pith.science/pith/A5KV7JKFI76ELNIXW53JADR5ZY/action/citation_signature","submit_replication":"https://pith.science/pith/A5KV7JKFI76ELNIXW53JADR5ZY/action/replication_record"}},"created_at":"2026-07-05T06:14:14.340130+00:00","updated_at":"2026-07-05T06:14:14.340130+00:00"}