{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:5ZADS3OKDZLHXQAMVN2KSQEHGK","short_pith_number":"pith:5ZADS3OK","schema_version":"1.0","canonical_sha256":"ee40396dca1e567bc00cab74a9408732a1ee65a846860ca99be5a0bf1a113716","source":{"kind":"arxiv","id":"1711.09601","version":4},"attestation_state":"computed","paper":{"title":"Memory Aware Synapses: Learning what (not) to forget","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.CV","authors_text":"Francesca Babiloni, Marcus Rohrbach, Mohamed Elhoseiny, Rahaf Aljundi, Tinne Tuytelaars","submitted_at":"2017-11-27T09:48:44Z","abstract_excerpt":"Humans can learn in a continuous manner. Old rarely utilized knowledge can be overwritten by new incoming information while important, frequently used knowledge is prevented from being erased. In artificial learning systems, lifelong learning so far has focused mainly on accumulating knowledge over tasks and overcoming catastrophic forgetting. In this paper, we argue that, given the limited model capacity and the unlimited new information to be learned, knowledge has to be preserved or erased selectively. Inspired by neuroplasticity, we propose a novel approach for lifelong learning, coined Me"},"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":"1711.09601","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-27T09:48:44Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"8cdf0e2f1339e410d5febd4953798bbb347c105a12b76cbdc17bd4988db8277f","abstract_canon_sha256":"cc1108e1660929412423d255182d5c5a2998b6525600b913767cff8f6f9e68e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:04:05.020022Z","signature_b64":"FmcZG6/0zclmodXm7ThaZXnH1b5+w1JBwVh/Id/vlgfhjngEzzCWihqyFC8sEGe8Rfoe4jonRrY7lnN3GCchCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee40396dca1e567bc00cab74a9408732a1ee65a846860ca99be5a0bf1a113716","last_reissued_at":"2026-05-18T00:04:05.019432Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:04:05.019432Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Memory Aware Synapses: Learning what (not) to forget","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.CV","authors_text":"Francesca Babiloni, Marcus Rohrbach, Mohamed Elhoseiny, Rahaf Aljundi, Tinne Tuytelaars","submitted_at":"2017-11-27T09:48:44Z","abstract_excerpt":"Humans can learn in a continuous manner. Old rarely utilized knowledge can be overwritten by new incoming information while important, frequently used knowledge is prevented from being erased. In artificial learning systems, lifelong learning so far has focused mainly on accumulating knowledge over tasks and overcoming catastrophic forgetting. In this paper, we argue that, given the limited model capacity and the unlimited new information to be learned, knowledge has to be preserved or erased selectively. Inspired by neuroplasticity, we propose a novel approach for lifelong learning, coined Me"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.09601","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":""},"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":"1711.09601","created_at":"2026-05-18T00:04:05.019540+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.09601v4","created_at":"2026-05-18T00:04:05.019540+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.09601","created_at":"2026-05-18T00:04:05.019540+00:00"},{"alias_kind":"pith_short_12","alias_value":"5ZADS3OKDZLH","created_at":"2026-05-18T12:31:03.183658+00:00"},{"alias_kind":"pith_short_16","alias_value":"5ZADS3OKDZLHXQAM","created_at":"2026-05-18T12:31:03.183658+00:00"},{"alias_kind":"pith_short_8","alias_value":"5ZADS3OK","created_at":"2026-05-18T12:31:03.183658+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2605.20296","citing_title":"Spectral Unforgetting: Post-Hoc Recovery of Damaged Capabilities Without Retraining","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19080","citing_title":"MANGO: Meta-Adaptive Network Gradient Optimization for Online Continual Learning","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"1911.05507","citing_title":"Compressive Transformers for Long-Range Sequence Modelling","ref_index":75,"is_internal_anchor":true},{"citing_arxiv_id":"2604.17051","citing_title":"Efficient Task Adaptation in Large Language Models via Selective Parameter Optimization","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5ZADS3OKDZLHXQAMVN2KSQEHGK","json":"https://pith.science/pith/5ZADS3OKDZLHXQAMVN2KSQEHGK.json","graph_json":"https://pith.science/api/pith-number/5ZADS3OKDZLHXQAMVN2KSQEHGK/graph.json","events_json":"https://pith.science/api/pith-number/5ZADS3OKDZLHXQAMVN2KSQEHGK/events.json","paper":"https://pith.science/paper/5ZADS3OK"},"agent_actions":{"view_html":"https://pith.science/pith/5ZADS3OKDZLHXQAMVN2KSQEHGK","download_json":"https://pith.science/pith/5ZADS3OKDZLHXQAMVN2KSQEHGK.json","view_paper":"https://pith.science/paper/5ZADS3OK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.09601&json=true","fetch_graph":"https://pith.science/api/pith-number/5ZADS3OKDZLHXQAMVN2KSQEHGK/graph.json","fetch_events":"https://pith.science/api/pith-number/5ZADS3OKDZLHXQAMVN2KSQEHGK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5ZADS3OKDZLHXQAMVN2KSQEHGK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5ZADS3OKDZLHXQAMVN2KSQEHGK/action/storage_attestation","attest_author":"https://pith.science/pith/5ZADS3OKDZLHXQAMVN2KSQEHGK/action/author_attestation","sign_citation":"https://pith.science/pith/5ZADS3OKDZLHXQAMVN2KSQEHGK/action/citation_signature","submit_replication":"https://pith.science/pith/5ZADS3OKDZLHXQAMVN2KSQEHGK/action/replication_record"}},"created_at":"2026-05-18T00:04:05.019540+00:00","updated_at":"2026-05-18T00:04:05.019540+00:00"}