{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:C73A3BZ2IAU6OJP5BXKH2ISACJ","short_pith_number":"pith:C73A3BZ2","schema_version":"1.0","canonical_sha256":"17f60d873a4029e725fd0dd47d224012510fc950e077f871ded3ebda08aafb39","source":{"kind":"arxiv","id":"1902.00829","version":1},"attestation_state":"computed","paper":{"title":"Incremental Learning with Maximum Entropy Regularization: Rethinking Forgetting and Intransigence","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Dahyun Kim, Jihwan Bae, Jonghyun Choi, Yeonsik Jo","submitted_at":"2019-02-03T02:09:26Z","abstract_excerpt":"Incremental learning suffers from two challenging problems; forgetting of old knowledge and intransigence on learning new knowledge. Prediction by the model incrementally learned with a subset of the dataset are thus uncertain and the uncertainty accumulates through the tasks by knowledge transfer. To prevent overfitting to the uncertain knowledge, we propose to penalize confident fitting to the uncertain knowledge by the Maximum Entropy Regularizer (MER). Additionally, to reduce class imbalance and induce a self-paced curriculum on new classes, we exclude a few samples from the new classes in"},"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":"1902.00829","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2019-02-03T02:09:26Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"f2746723413ee25de7f1341f72e05dfd0545b4e8423d66eca1ce7786b84d603c","abstract_canon_sha256":"c1b68ce256d29a3afdb28b8527c0a2767fd7e8cd63425f9f20820765297f6152"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:52.036480Z","signature_b64":"knIHT8XniJ0BXCpdbfqWot4fBiiJYlf5FGbM4JeXcPxEku5IwmN7BKbG7tAayafMYkVzSqlIGJ1Ul3epiItrBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17f60d873a4029e725fd0dd47d224012510fc950e077f871ded3ebda08aafb39","last_reissued_at":"2026-05-17T23:54:52.036053Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:52.036053Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Incremental Learning with Maximum Entropy Regularization: Rethinking Forgetting and Intransigence","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Dahyun Kim, Jihwan Bae, Jonghyun Choi, Yeonsik Jo","submitted_at":"2019-02-03T02:09:26Z","abstract_excerpt":"Incremental learning suffers from two challenging problems; forgetting of old knowledge and intransigence on learning new knowledge. Prediction by the model incrementally learned with a subset of the dataset are thus uncertain and the uncertainty accumulates through the tasks by knowledge transfer. To prevent overfitting to the uncertain knowledge, we propose to penalize confident fitting to the uncertain knowledge by the Maximum Entropy Regularizer (MER). Additionally, to reduce class imbalance and induce a self-paced curriculum on new classes, we exclude a few samples from the new classes in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.00829","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":""},"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":"1902.00829","created_at":"2026-05-17T23:54:52.036115+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.00829v1","created_at":"2026-05-17T23:54:52.036115+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.00829","created_at":"2026-05-17T23:54:52.036115+00:00"},{"alias_kind":"pith_short_12","alias_value":"C73A3BZ2IAU6","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_16","alias_value":"C73A3BZ2IAU6OJP5","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_8","alias_value":"C73A3BZ2","created_at":"2026-05-18T12:33:12.712433+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.06678","citing_title":"Online Clustering of Seafloor Imagery for Interpretation during Long-Term AUV Operations","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C73A3BZ2IAU6OJP5BXKH2ISACJ","json":"https://pith.science/pith/C73A3BZ2IAU6OJP5BXKH2ISACJ.json","graph_json":"https://pith.science/api/pith-number/C73A3BZ2IAU6OJP5BXKH2ISACJ/graph.json","events_json":"https://pith.science/api/pith-number/C73A3BZ2IAU6OJP5BXKH2ISACJ/events.json","paper":"https://pith.science/paper/C73A3BZ2"},"agent_actions":{"view_html":"https://pith.science/pith/C73A3BZ2IAU6OJP5BXKH2ISACJ","download_json":"https://pith.science/pith/C73A3BZ2IAU6OJP5BXKH2ISACJ.json","view_paper":"https://pith.science/paper/C73A3BZ2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.00829&json=true","fetch_graph":"https://pith.science/api/pith-number/C73A3BZ2IAU6OJP5BXKH2ISACJ/graph.json","fetch_events":"https://pith.science/api/pith-number/C73A3BZ2IAU6OJP5BXKH2ISACJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C73A3BZ2IAU6OJP5BXKH2ISACJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C73A3BZ2IAU6OJP5BXKH2ISACJ/action/storage_attestation","attest_author":"https://pith.science/pith/C73A3BZ2IAU6OJP5BXKH2ISACJ/action/author_attestation","sign_citation":"https://pith.science/pith/C73A3BZ2IAU6OJP5BXKH2ISACJ/action/citation_signature","submit_replication":"https://pith.science/pith/C73A3BZ2IAU6OJP5BXKH2ISACJ/action/replication_record"}},"created_at":"2026-05-17T23:54:52.036115+00:00","updated_at":"2026-05-17T23:54:52.036115+00:00"}