{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ZXJN37V7JRJHCC2J224UVTPBCU","short_pith_number":"pith:ZXJN37V7","schema_version":"1.0","canonical_sha256":"cdd2ddfebf4c52710b49d6b94acde1152bee27c146e310b78f6a4bff7b7968fe","source":{"kind":"arxiv","id":"2101.07592","version":1},"attestation_state":"computed","paper":{"title":"Synaptic metaplasticity in binarized neural networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Axel Laborieux, Damien Querlioz, Maxence Ernoult, Tifenn Hirtzlin","submitted_at":"2021-01-19T12:32:07Z","abstract_excerpt":"Unlike the brain, artificial neural networks, including state-of-the-art deep neural networks for computer vision, are subject to \"catastrophic forgetting\": they rapidly forget the previous task when trained on a new one. Neuroscience suggests that biological synapses avoid this issue through the process of synaptic consolidation and metaplasticity: the plasticity itself changes upon repeated synaptic events. In this work, we show that this concept of metaplasticity can be transferred to a particular type of deep neural networks, binarized neural networks, to reduce catastrophic forgetting."},"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":"2101.07592","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2021-01-19T12:32:07Z","cross_cats_sorted":[],"title_canon_sha256":"544612d774b82b137af5c19e23fdf2a1485c7d61fcbaba672c0835398f98a2b9","abstract_canon_sha256":"bd50ea9cee12a4908897b43edc538968b6c6c4420d8094befc79dcaeec6e5efe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:47:04.189197Z","signature_b64":"htg8IOQjIjtRcQ2Ki8Muh4PfWno3M/aqzJyFhMEoP+KoPorEWhLToahRGldLIPqO5vjReS2GB992c7VT0GWJDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cdd2ddfebf4c52710b49d6b94acde1152bee27c146e310b78f6a4bff7b7968fe","last_reissued_at":"2026-07-05T02:47:04.188833Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:47:04.188833Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Synaptic metaplasticity in binarized neural networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Axel Laborieux, Damien Querlioz, Maxence Ernoult, Tifenn Hirtzlin","submitted_at":"2021-01-19T12:32:07Z","abstract_excerpt":"Unlike the brain, artificial neural networks, including state-of-the-art deep neural networks for computer vision, are subject to \"catastrophic forgetting\": they rapidly forget the previous task when trained on a new one. Neuroscience suggests that biological synapses avoid this issue through the process of synaptic consolidation and metaplasticity: the plasticity itself changes upon repeated synaptic events. In this work, we show that this concept of metaplasticity can be transferred to a particular type of deep neural networks, binarized neural networks, to reduce catastrophic forgetting."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.07592","kind":"arxiv","version":1},"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/2101.07592/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":"2101.07592","created_at":"2026-07-05T02:47:04.188898+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.07592v1","created_at":"2026-07-05T02:47:04.188898+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.07592","created_at":"2026-07-05T02:47:04.188898+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZXJN37V7JRJH","created_at":"2026-07-05T02:47:04.188898+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZXJN37V7JRJHCC2J","created_at":"2026-07-05T02:47:04.188898+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZXJN37V7","created_at":"2026-07-05T02:47:04.188898+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/ZXJN37V7JRJHCC2J224UVTPBCU","json":"https://pith.science/pith/ZXJN37V7JRJHCC2J224UVTPBCU.json","graph_json":"https://pith.science/api/pith-number/ZXJN37V7JRJHCC2J224UVTPBCU/graph.json","events_json":"https://pith.science/api/pith-number/ZXJN37V7JRJHCC2J224UVTPBCU/events.json","paper":"https://pith.science/paper/ZXJN37V7"},"agent_actions":{"view_html":"https://pith.science/pith/ZXJN37V7JRJHCC2J224UVTPBCU","download_json":"https://pith.science/pith/ZXJN37V7JRJHCC2J224UVTPBCU.json","view_paper":"https://pith.science/paper/ZXJN37V7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.07592&json=true","fetch_graph":"https://pith.science/api/pith-number/ZXJN37V7JRJHCC2J224UVTPBCU/graph.json","fetch_events":"https://pith.science/api/pith-number/ZXJN37V7JRJHCC2J224UVTPBCU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZXJN37V7JRJHCC2J224UVTPBCU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZXJN37V7JRJHCC2J224UVTPBCU/action/storage_attestation","attest_author":"https://pith.science/pith/ZXJN37V7JRJHCC2J224UVTPBCU/action/author_attestation","sign_citation":"https://pith.science/pith/ZXJN37V7JRJHCC2J224UVTPBCU/action/citation_signature","submit_replication":"https://pith.science/pith/ZXJN37V7JRJHCC2J224UVTPBCU/action/replication_record"}},"created_at":"2026-07-05T02:47:04.188898+00:00","updated_at":"2026-07-05T02:47:04.188898+00:00"}