{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:DZXZXWU4A7AFX5XG7QFZTJ2UMT","short_pith_number":"pith:DZXZXWU4","schema_version":"1.0","canonical_sha256":"1e6f9bda9c07c05bf6e6fc0b99a75464dedf60393b050c391ca5dac2204ea121","source":{"kind":"arxiv","id":"2206.09117","version":1},"attestation_state":"computed","paper":{"title":"NISPA: Neuro-Inspired Stability-Plasticity Adaptation for Continual Learning in Sparse Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Constantine Dovrolis, Mustafa Burak Gurbuz","submitted_at":"2022-06-18T04:56:49Z","abstract_excerpt":"The goal of continual learning (CL) is to learn different tasks over time. The main desiderata associated with CL are to maintain performance on older tasks, leverage the latter to improve learning of future tasks, and to introduce minimal overhead in the training process (for instance, to not require a growing model or retraining). We propose the Neuro-Inspired Stability-Plasticity Adaptation (NISPA) architecture that addresses these desiderata through a sparse neural network with fixed density. NISPA forms stable paths to preserve learned knowledge from older tasks. Also, NISPA uses connecti"},"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":"2206.09117","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-18T04:56:49Z","cross_cats_sorted":[],"title_canon_sha256":"12a0cbcaf2375f33a6bc220333025f31dedec31dd781937bd9c5df3c272fbe22","abstract_canon_sha256":"e756818a4e2ed1bbd59c60acf436b34d6a65f49986e4782bfe9a0f4d41b98002"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:33:04.228814Z","signature_b64":"Igd+1h4gwO4HivEqjuIw3M2BcFvlow38mcRdougaFoXdz3DY8tqf4f6mmSfH+E6XwpiCV29IjSpxbckycRS2AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e6f9bda9c07c05bf6e6fc0b99a75464dedf60393b050c391ca5dac2204ea121","last_reissued_at":"2026-07-05T04:33:04.228356Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:33:04.228356Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NISPA: Neuro-Inspired Stability-Plasticity Adaptation for Continual Learning in Sparse Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Constantine Dovrolis, Mustafa Burak Gurbuz","submitted_at":"2022-06-18T04:56:49Z","abstract_excerpt":"The goal of continual learning (CL) is to learn different tasks over time. The main desiderata associated with CL are to maintain performance on older tasks, leverage the latter to improve learning of future tasks, and to introduce minimal overhead in the training process (for instance, to not require a growing model or retraining). We propose the Neuro-Inspired Stability-Plasticity Adaptation (NISPA) architecture that addresses these desiderata through a sparse neural network with fixed density. NISPA forms stable paths to preserve learned knowledge from older tasks. Also, NISPA uses connecti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.09117","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/2206.09117/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":"2206.09117","created_at":"2026-07-05T04:33:04.228420+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.09117v1","created_at":"2026-07-05T04:33:04.228420+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.09117","created_at":"2026-07-05T04:33:04.228420+00:00"},{"alias_kind":"pith_short_12","alias_value":"DZXZXWU4A7AF","created_at":"2026-07-05T04:33:04.228420+00:00"},{"alias_kind":"pith_short_16","alias_value":"DZXZXWU4A7AFX5XG","created_at":"2026-07-05T04:33:04.228420+00:00"},{"alias_kind":"pith_short_8","alias_value":"DZXZXWU4","created_at":"2026-07-05T04:33:04.228420+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.04870","citing_title":"IPSeg: Image Posterior Mitigates Semantic Drift in Class-Incremental Segmentation","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DZXZXWU4A7AFX5XG7QFZTJ2UMT","json":"https://pith.science/pith/DZXZXWU4A7AFX5XG7QFZTJ2UMT.json","graph_json":"https://pith.science/api/pith-number/DZXZXWU4A7AFX5XG7QFZTJ2UMT/graph.json","events_json":"https://pith.science/api/pith-number/DZXZXWU4A7AFX5XG7QFZTJ2UMT/events.json","paper":"https://pith.science/paper/DZXZXWU4"},"agent_actions":{"view_html":"https://pith.science/pith/DZXZXWU4A7AFX5XG7QFZTJ2UMT","download_json":"https://pith.science/pith/DZXZXWU4A7AFX5XG7QFZTJ2UMT.json","view_paper":"https://pith.science/paper/DZXZXWU4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.09117&json=true","fetch_graph":"https://pith.science/api/pith-number/DZXZXWU4A7AFX5XG7QFZTJ2UMT/graph.json","fetch_events":"https://pith.science/api/pith-number/DZXZXWU4A7AFX5XG7QFZTJ2UMT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DZXZXWU4A7AFX5XG7QFZTJ2UMT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DZXZXWU4A7AFX5XG7QFZTJ2UMT/action/storage_attestation","attest_author":"https://pith.science/pith/DZXZXWU4A7AFX5XG7QFZTJ2UMT/action/author_attestation","sign_citation":"https://pith.science/pith/DZXZXWU4A7AFX5XG7QFZTJ2UMT/action/citation_signature","submit_replication":"https://pith.science/pith/DZXZXWU4A7AFX5XG7QFZTJ2UMT/action/replication_record"}},"created_at":"2026-07-05T04:33:04.228420+00:00","updated_at":"2026-07-05T04:33:04.228420+00:00"}