{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:ULTU3HBYWCWWDFX6QEKJOS5BZC","short_pith_number":"pith:ULTU3HBY","schema_version":"1.0","canonical_sha256":"a2e74d9c38b0ad6196fe8114974ba1c89738c61176fdbc0235232d7b41ddfded","source":{"kind":"arxiv","id":"1807.09536","version":2},"attestation_state":"computed","paper":{"title":"End-to-End Incremental Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cordelia Schmid, Francisco M. Castro, Karteek Alahari, Manuel J. Mar\\'in-Jim\\'enez, Nicol\\'as Guil","submitted_at":"2018-07-25T11:38:25Z","abstract_excerpt":"Although deep learning approaches have stood out in recent years due to their state-of-the-art results, they continue to suffer from catastrophic forgetting, a dramatic decrease in overall performance when training with new classes added incrementally. This is due to current neural network architectures requiring the entire dataset, consisting of all the samples from the old as well as the new classes, to update the model -a requirement that becomes easily unsustainable as the number of classes grows. We address this issue with our approach to learn deep neural networks incrementally, using ne"},"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":"1807.09536","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-25T11:38:25Z","cross_cats_sorted":[],"title_canon_sha256":"46abcbc0039fabafccc625a7d13d659cef605b9b36fcda3014ca7ceb48295bdd","abstract_canon_sha256":"be32a4e91d89329cd16e8a841213c01a60f6ffee6d825c629db56de0ab0fe51f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:37.289592Z","signature_b64":"0p30K9evmBKHo1HlGKC+actBzcuUvKdryqOzMTQB3qKctOW0zPIC/giCcAeQ1WnhL14MQgWmWc3vNhEovCs4Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2e74d9c38b0ad6196fe8114974ba1c89738c61176fdbc0235232d7b41ddfded","last_reissued_at":"2026-05-18T00:06:37.289100Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:37.289100Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"End-to-End Incremental Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cordelia Schmid, Francisco M. Castro, Karteek Alahari, Manuel J. Mar\\'in-Jim\\'enez, Nicol\\'as Guil","submitted_at":"2018-07-25T11:38:25Z","abstract_excerpt":"Although deep learning approaches have stood out in recent years due to their state-of-the-art results, they continue to suffer from catastrophic forgetting, a dramatic decrease in overall performance when training with new classes added incrementally. This is due to current neural network architectures requiring the entire dataset, consisting of all the samples from the old as well as the new classes, to update the model -a requirement that becomes easily unsustainable as the number of classes grows. We address this issue with our approach to learn deep neural networks incrementally, using ne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.09536","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":""},"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":"1807.09536","created_at":"2026-05-18T00:06:37.289175+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.09536v2","created_at":"2026-05-18T00:06:37.289175+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.09536","created_at":"2026-05-18T00:06:37.289175+00:00"},{"alias_kind":"pith_short_12","alias_value":"ULTU3HBYWCWW","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_16","alias_value":"ULTU3HBYWCWWDFX6","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_8","alias_value":"ULTU3HBY","created_at":"2026-05-18T12:32:56.356000+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/ULTU3HBYWCWWDFX6QEKJOS5BZC","json":"https://pith.science/pith/ULTU3HBYWCWWDFX6QEKJOS5BZC.json","graph_json":"https://pith.science/api/pith-number/ULTU3HBYWCWWDFX6QEKJOS5BZC/graph.json","events_json":"https://pith.science/api/pith-number/ULTU3HBYWCWWDFX6QEKJOS5BZC/events.json","paper":"https://pith.science/paper/ULTU3HBY"},"agent_actions":{"view_html":"https://pith.science/pith/ULTU3HBYWCWWDFX6QEKJOS5BZC","download_json":"https://pith.science/pith/ULTU3HBYWCWWDFX6QEKJOS5BZC.json","view_paper":"https://pith.science/paper/ULTU3HBY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.09536&json=true","fetch_graph":"https://pith.science/api/pith-number/ULTU3HBYWCWWDFX6QEKJOS5BZC/graph.json","fetch_events":"https://pith.science/api/pith-number/ULTU3HBYWCWWDFX6QEKJOS5BZC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ULTU3HBYWCWWDFX6QEKJOS5BZC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ULTU3HBYWCWWDFX6QEKJOS5BZC/action/storage_attestation","attest_author":"https://pith.science/pith/ULTU3HBYWCWWDFX6QEKJOS5BZC/action/author_attestation","sign_citation":"https://pith.science/pith/ULTU3HBYWCWWDFX6QEKJOS5BZC/action/citation_signature","submit_replication":"https://pith.science/pith/ULTU3HBYWCWWDFX6QEKJOS5BZC/action/replication_record"}},"created_at":"2026-05-18T00:06:37.289175+00:00","updated_at":"2026-05-18T00:06:37.289175+00:00"}