{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:U7HBW6WFIOLV3KPX45HXATD65N","short_pith_number":"pith:U7HBW6WF","schema_version":"1.0","canonical_sha256":"a7ce1b7ac543975da9f7e74f704c7eeb4e5cf5e608c673c68ae15a11160f511e","source":{"kind":"arxiv","id":"1903.08671","version":5},"attestation_state":"computed","paper":{"title":"Gradient based sample selection for online continual 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":"Baptiste Goujaud, Min Lin, Rahaf Aljundi, Yoshua Bengio","submitted_at":"2019-03-20T18:01:55Z","abstract_excerpt":"A continual learning agent learns online with a non-stationary and never-ending stream of data. The key to such learning process is to overcome the catastrophic forgetting of previously seen data, which is a well known problem of neural networks. To prevent forgetting, a replay buffer is usually employed to store the previous data for the purpose of rehearsal. Previous works often depend on task boundary and i.i.d. assumptions to properly select samples for the replay buffer. In this work, we formulate sample selection as a constraint reduction problem based on the constrained optimization vie"},"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":"1903.08671","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-20T18:01:55Z","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"title_canon_sha256":"8cca81845d60acad91cba50068e6d03b285676d7b9a696407d11241375b7b2d8","abstract_canon_sha256":"27c02cb6f5ac9350e70300ec65ffb035a0c7d028d3e03f5b8cb0ec716e6cc4fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:16:03.480210Z","signature_b64":"Wg7iJwZHBJ2XGLLh1coqNSSs3ODE8+El/WmfdXmRmFDqo6UWziQ2L8jpkKRCwRRwyDSR23PPv5HfY50RfV83Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7ce1b7ac543975da9f7e74f704c7eeb4e5cf5e608c673c68ae15a11160f511e","last_reissued_at":"2026-07-05T00:16:03.479739Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:16:03.479739Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gradient based sample selection for online continual 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":"Baptiste Goujaud, Min Lin, Rahaf Aljundi, Yoshua Bengio","submitted_at":"2019-03-20T18:01:55Z","abstract_excerpt":"A continual learning agent learns online with a non-stationary and never-ending stream of data. The key to such learning process is to overcome the catastrophic forgetting of previously seen data, which is a well known problem of neural networks. To prevent forgetting, a replay buffer is usually employed to store the previous data for the purpose of rehearsal. Previous works often depend on task boundary and i.i.d. assumptions to properly select samples for the replay buffer. In this work, we formulate sample selection as a constraint reduction problem based on the constrained optimization vie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.08671","kind":"arxiv","version":5},"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/1903.08671/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":"1903.08671","created_at":"2026-07-05T00:16:03.479796+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.08671v5","created_at":"2026-07-05T00:16:03.479796+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.08671","created_at":"2026-07-05T00:16:03.479796+00:00"},{"alias_kind":"pith_short_12","alias_value":"U7HBW6WFIOLV","created_at":"2026-07-05T00:16:03.479796+00:00"},{"alias_kind":"pith_short_16","alias_value":"U7HBW6WFIOLV3KPX","created_at":"2026-07-05T00:16:03.479796+00:00"},{"alias_kind":"pith_short_8","alias_value":"U7HBW6WF","created_at":"2026-07-05T00:16:03.479796+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.21240","citing_title":"Class Incremental Continual Learning with Self-Organizing Maps and Variational Autoencoders Using Synthetic Replay","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U7HBW6WFIOLV3KPX45HXATD65N","json":"https://pith.science/pith/U7HBW6WFIOLV3KPX45HXATD65N.json","graph_json":"https://pith.science/api/pith-number/U7HBW6WFIOLV3KPX45HXATD65N/graph.json","events_json":"https://pith.science/api/pith-number/U7HBW6WFIOLV3KPX45HXATD65N/events.json","paper":"https://pith.science/paper/U7HBW6WF"},"agent_actions":{"view_html":"https://pith.science/pith/U7HBW6WFIOLV3KPX45HXATD65N","download_json":"https://pith.science/pith/U7HBW6WFIOLV3KPX45HXATD65N.json","view_paper":"https://pith.science/paper/U7HBW6WF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.08671&json=true","fetch_graph":"https://pith.science/api/pith-number/U7HBW6WFIOLV3KPX45HXATD65N/graph.json","fetch_events":"https://pith.science/api/pith-number/U7HBW6WFIOLV3KPX45HXATD65N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U7HBW6WFIOLV3KPX45HXATD65N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U7HBW6WFIOLV3KPX45HXATD65N/action/storage_attestation","attest_author":"https://pith.science/pith/U7HBW6WFIOLV3KPX45HXATD65N/action/author_attestation","sign_citation":"https://pith.science/pith/U7HBW6WFIOLV3KPX45HXATD65N/action/citation_signature","submit_replication":"https://pith.science/pith/U7HBW6WFIOLV3KPX45HXATD65N/action/replication_record"}},"created_at":"2026-07-05T00:16:03.479796+00:00","updated_at":"2026-07-05T00:16:03.479796+00:00"}