{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:7E2MXYL6IK4TM5BA3CERCVYJUF","short_pith_number":"pith:7E2MXYL6","schema_version":"1.0","canonical_sha256":"f934cbe17e42b9367420d889115709a152f229cd7aae9bafdec5cc21fab79f71","source":{"kind":"arxiv","id":"2011.12216","version":3},"attestation_state":"computed","paper":{"title":"Energy-Based Models for Continual Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Gido M. van de Ven, Igor Mordatch, Shuang Li, Yilun Du","submitted_at":"2020-11-24T17:08:13Z","abstract_excerpt":"We motivate Energy-Based Models (EBMs) as a promising model class for continual learning problems. Instead of tackling continual learning via the use of external memory, growing models, or regularization, EBMs change the underlying training objective to cause less interference with previously learned information. Our proposed version of EBMs for continual learning is simple, efficient, and outperforms baseline methods by a large margin on several benchmarks. Moreover, our proposed contrastive divergence-based training objective can be combined with other continual learning methods, resulting i"},"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":"2011.12216","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-24T17:08:13Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"d17c1b5e7bd58fcaea239d6be5fbb8c9936e2244c61ad77e5b1c6fb8efead0e9","abstract_canon_sha256":"adb13df8e64e76f33bd86f8466daad89130e012ed37625588811fc27dabffa83"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:23:48.719415Z","signature_b64":"JLfDuOesHaYgLZRQN1GNzMMdUAdkzVsGx+wlFMydI/QDt9N6Bl10QchEnTxq6sT9FtwpBs6l4XzgBMfvuaQgBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f934cbe17e42b9367420d889115709a152f229cd7aae9bafdec5cc21fab79f71","last_reissued_at":"2026-07-05T10:23:48.718647Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:23:48.718647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Energy-Based Models for Continual Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Gido M. van de Ven, Igor Mordatch, Shuang Li, Yilun Du","submitted_at":"2020-11-24T17:08:13Z","abstract_excerpt":"We motivate Energy-Based Models (EBMs) as a promising model class for continual learning problems. Instead of tackling continual learning via the use of external memory, growing models, or regularization, EBMs change the underlying training objective to cause less interference with previously learned information. Our proposed version of EBMs for continual learning is simple, efficient, and outperforms baseline methods by a large margin on several benchmarks. Moreover, our proposed contrastive divergence-based training objective can be combined with other continual learning methods, resulting i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.12216","kind":"arxiv","version":3},"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/2011.12216/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":"2011.12216","created_at":"2026-07-05T10:23:48.718726+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.12216v3","created_at":"2026-07-05T10:23:48.718726+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.12216","created_at":"2026-07-05T10:23:48.718726+00:00"},{"alias_kind":"pith_short_12","alias_value":"7E2MXYL6IK4T","created_at":"2026-07-05T10:23:48.718726+00:00"},{"alias_kind":"pith_short_16","alias_value":"7E2MXYL6IK4TM5BA","created_at":"2026-07-05T10:23:48.718726+00:00"},{"alias_kind":"pith_short_8","alias_value":"7E2MXYL6","created_at":"2026-07-05T10:23:48.718726+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.05926","citing_title":"Autoencoder-Based Hybrid Replay for Class-Incremental Learning","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7E2MXYL6IK4TM5BA3CERCVYJUF","json":"https://pith.science/pith/7E2MXYL6IK4TM5BA3CERCVYJUF.json","graph_json":"https://pith.science/api/pith-number/7E2MXYL6IK4TM5BA3CERCVYJUF/graph.json","events_json":"https://pith.science/api/pith-number/7E2MXYL6IK4TM5BA3CERCVYJUF/events.json","paper":"https://pith.science/paper/7E2MXYL6"},"agent_actions":{"view_html":"https://pith.science/pith/7E2MXYL6IK4TM5BA3CERCVYJUF","download_json":"https://pith.science/pith/7E2MXYL6IK4TM5BA3CERCVYJUF.json","view_paper":"https://pith.science/paper/7E2MXYL6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.12216&json=true","fetch_graph":"https://pith.science/api/pith-number/7E2MXYL6IK4TM5BA3CERCVYJUF/graph.json","fetch_events":"https://pith.science/api/pith-number/7E2MXYL6IK4TM5BA3CERCVYJUF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7E2MXYL6IK4TM5BA3CERCVYJUF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7E2MXYL6IK4TM5BA3CERCVYJUF/action/storage_attestation","attest_author":"https://pith.science/pith/7E2MXYL6IK4TM5BA3CERCVYJUF/action/author_attestation","sign_citation":"https://pith.science/pith/7E2MXYL6IK4TM5BA3CERCVYJUF/action/citation_signature","submit_replication":"https://pith.science/pith/7E2MXYL6IK4TM5BA3CERCVYJUF/action/replication_record"}},"created_at":"2026-07-05T10:23:48.718726+00:00","updated_at":"2026-07-05T10:23:48.718726+00:00"}