{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:XGIEVM76HSC6WFMZZKMUZUJ7BS","short_pith_number":"pith:XGIEVM76","schema_version":"1.0","canonical_sha256":"b9904ab3fe3c85eb1599ca994cd13f0c9be5ae02855c7aa12f62dbc42bc0a14d","source":{"kind":"arxiv","id":"2110.13611","version":1},"attestation_state":"computed","paper":{"title":"Dendritic Self-Organizing Maps for Continual Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG","q-bio.NC"],"primary_cat":"cs.NE","authors_text":"Kosmas Pinitas, Panayiota Poirazi, Spyridon Chavlis","submitted_at":"2021-10-18T14:47:19Z","abstract_excerpt":"Current deep learning architectures show remarkable performance when trained in large-scale, controlled datasets. However, the predictive ability of these architectures significantly decreases when learning new classes incrementally. This is due to their inclination to forget the knowledge acquired from previously seen data, a phenomenon termed catastrophic-forgetting. On the other hand, Self-Organizing Maps (SOMs) can model the input space utilizing constrained k-means and thus maintain past knowledge. Here, we propose a novel algorithm inspired by biological neurons, termed Dendritic-Self-Or"},"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":"2110.13611","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2021-10-18T14:47:19Z","cross_cats_sorted":["cs.CV","cs.LG","q-bio.NC"],"title_canon_sha256":"8c399085d0c578ea00a5dc45219d967b763c01ec903737cf51f30cd82eb62b47","abstract_canon_sha256":"30b5a6961e7b7da4fe3575c292a7a2394a227280653f7804b66a5f12f01b1c9e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:25:40.920137Z","signature_b64":"zHidRW1L22gviv7V2At8qh/mFMcGvGrS7kpjtwsJQFYZfv0FmH6Cur7YyErSagET2Mu86Vds1CBvJ3ollihyDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9904ab3fe3c85eb1599ca994cd13f0c9be5ae02855c7aa12f62dbc42bc0a14d","last_reissued_at":"2026-07-05T03:25:40.919717Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:25:40.919717Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dendritic Self-Organizing Maps for Continual Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG","q-bio.NC"],"primary_cat":"cs.NE","authors_text":"Kosmas Pinitas, Panayiota Poirazi, Spyridon Chavlis","submitted_at":"2021-10-18T14:47:19Z","abstract_excerpt":"Current deep learning architectures show remarkable performance when trained in large-scale, controlled datasets. However, the predictive ability of these architectures significantly decreases when learning new classes incrementally. This is due to their inclination to forget the knowledge acquired from previously seen data, a phenomenon termed catastrophic-forgetting. On the other hand, Self-Organizing Maps (SOMs) can model the input space utilizing constrained k-means and thus maintain past knowledge. Here, we propose a novel algorithm inspired by biological neurons, termed Dendritic-Self-Or"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.13611","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/2110.13611/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":"2110.13611","created_at":"2026-07-05T03:25:40.919777+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.13611v1","created_at":"2026-07-05T03:25:40.919777+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.13611","created_at":"2026-07-05T03:25:40.919777+00:00"},{"alias_kind":"pith_short_12","alias_value":"XGIEVM76HSC6","created_at":"2026-07-05T03:25:40.919777+00:00"},{"alias_kind":"pith_short_16","alias_value":"XGIEVM76HSC6WFMZ","created_at":"2026-07-05T03:25:40.919777+00:00"},{"alias_kind":"pith_short_8","alias_value":"XGIEVM76","created_at":"2026-07-05T03:25:40.919777+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":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XGIEVM76HSC6WFMZZKMUZUJ7BS","json":"https://pith.science/pith/XGIEVM76HSC6WFMZZKMUZUJ7BS.json","graph_json":"https://pith.science/api/pith-number/XGIEVM76HSC6WFMZZKMUZUJ7BS/graph.json","events_json":"https://pith.science/api/pith-number/XGIEVM76HSC6WFMZZKMUZUJ7BS/events.json","paper":"https://pith.science/paper/XGIEVM76"},"agent_actions":{"view_html":"https://pith.science/pith/XGIEVM76HSC6WFMZZKMUZUJ7BS","download_json":"https://pith.science/pith/XGIEVM76HSC6WFMZZKMUZUJ7BS.json","view_paper":"https://pith.science/paper/XGIEVM76","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.13611&json=true","fetch_graph":"https://pith.science/api/pith-number/XGIEVM76HSC6WFMZZKMUZUJ7BS/graph.json","fetch_events":"https://pith.science/api/pith-number/XGIEVM76HSC6WFMZZKMUZUJ7BS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XGIEVM76HSC6WFMZZKMUZUJ7BS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XGIEVM76HSC6WFMZZKMUZUJ7BS/action/storage_attestation","attest_author":"https://pith.science/pith/XGIEVM76HSC6WFMZZKMUZUJ7BS/action/author_attestation","sign_citation":"https://pith.science/pith/XGIEVM76HSC6WFMZZKMUZUJ7BS/action/citation_signature","submit_replication":"https://pith.science/pith/XGIEVM76HSC6WFMZZKMUZUJ7BS/action/replication_record"}},"created_at":"2026-07-05T03:25:40.919777+00:00","updated_at":"2026-07-05T03:25:40.919777+00:00"}