{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:IMKBVCNFVGXIZTR6ZISNKINNCP","short_pith_number":"pith:IMKBVCNF","schema_version":"1.0","canonical_sha256":"43141a89a5a9ae8cce3eca24d521ad13cf248baaeaa5dd6da139fed5637f2afc","source":{"kind":"arxiv","id":"2106.01085","version":4},"attestation_state":"computed","paper":{"title":"Online Coreset Selection for Rehearsal-based Continual Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Divyam Madaan, Eunho Yang, Jaehong Yoon, Sung Ju Hwang","submitted_at":"2021-06-02T11:39:25Z","abstract_excerpt":"A dataset is a shred of crucial evidence to describe a task. However, each data point in the dataset does not have the same potential, as some of the data points can be more representative or informative than others. This unequal importance among the data points may have a large impact in rehearsal-based continual learning, where we store a subset of the training examples (coreset) to be replayed later to alleviate catastrophic forgetting. In continual learning, the quality of the samples stored in the coreset directly affects the model's effectiveness and efficiency. The coreset selection pro"},"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":"2106.01085","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-02T11:39:25Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"72d52385a395d80a9a7562575218d0a37110b0f7938863f54ef0998b18b9546b","abstract_canon_sha256":"7c70aa8c0fa58df0296a0ea9edd96b0e15ffd8f74240e96b91b494051938be43"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:06:15.084408Z","signature_b64":"a4hJM/Yb6o/2IEh9LaZdWRMCa8if1kRzvqMixNkn3kY7bF8cUxe+kWHuxSdYR3dDf1UhF+jkQdSdv5aVoisFCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43141a89a5a9ae8cce3eca24d521ad13cf248baaeaa5dd6da139fed5637f2afc","last_reissued_at":"2026-07-05T04:06:15.083852Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:06:15.083852Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Online Coreset Selection for Rehearsal-based Continual Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Divyam Madaan, Eunho Yang, Jaehong Yoon, Sung Ju Hwang","submitted_at":"2021-06-02T11:39:25Z","abstract_excerpt":"A dataset is a shred of crucial evidence to describe a task. However, each data point in the dataset does not have the same potential, as some of the data points can be more representative or informative than others. This unequal importance among the data points may have a large impact in rehearsal-based continual learning, where we store a subset of the training examples (coreset) to be replayed later to alleviate catastrophic forgetting. In continual learning, the quality of the samples stored in the coreset directly affects the model's effectiveness and efficiency. The coreset selection pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.01085","kind":"arxiv","version":4},"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/2106.01085/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":"2106.01085","created_at":"2026-07-05T04:06:15.083910+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.01085v4","created_at":"2026-07-05T04:06:15.083910+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.01085","created_at":"2026-07-05T04:06:15.083910+00:00"},{"alias_kind":"pith_short_12","alias_value":"IMKBVCNFVGXI","created_at":"2026-07-05T04:06:15.083910+00:00"},{"alias_kind":"pith_short_16","alias_value":"IMKBVCNFVGXIZTR6","created_at":"2026-07-05T04:06:15.083910+00:00"},{"alias_kind":"pith_short_8","alias_value":"IMKBVCNF","created_at":"2026-07-05T04:06:15.083910+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23969","citing_title":"SLAP: Stratified Loss-based Pruning for On-Policy Data-Efficient Instruction Tuning","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17367","citing_title":"Bridging Data Trials and Task Barriers: A Unified Framework for Sketch Biometric Identification","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17396","citing_title":"Representation-Guided Parameter-Efficient LLM Unlearning","ref_index":138,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IMKBVCNFVGXIZTR6ZISNKINNCP","json":"https://pith.science/pith/IMKBVCNFVGXIZTR6ZISNKINNCP.json","graph_json":"https://pith.science/api/pith-number/IMKBVCNFVGXIZTR6ZISNKINNCP/graph.json","events_json":"https://pith.science/api/pith-number/IMKBVCNFVGXIZTR6ZISNKINNCP/events.json","paper":"https://pith.science/paper/IMKBVCNF"},"agent_actions":{"view_html":"https://pith.science/pith/IMKBVCNFVGXIZTR6ZISNKINNCP","download_json":"https://pith.science/pith/IMKBVCNFVGXIZTR6ZISNKINNCP.json","view_paper":"https://pith.science/paper/IMKBVCNF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.01085&json=true","fetch_graph":"https://pith.science/api/pith-number/IMKBVCNFVGXIZTR6ZISNKINNCP/graph.json","fetch_events":"https://pith.science/api/pith-number/IMKBVCNFVGXIZTR6ZISNKINNCP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IMKBVCNFVGXIZTR6ZISNKINNCP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IMKBVCNFVGXIZTR6ZISNKINNCP/action/storage_attestation","attest_author":"https://pith.science/pith/IMKBVCNFVGXIZTR6ZISNKINNCP/action/author_attestation","sign_citation":"https://pith.science/pith/IMKBVCNFVGXIZTR6ZISNKINNCP/action/citation_signature","submit_replication":"https://pith.science/pith/IMKBVCNFVGXIZTR6ZISNKINNCP/action/replication_record"}},"created_at":"2026-07-05T04:06:15.083910+00:00","updated_at":"2026-07-05T04:06:15.083910+00:00"}