{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CCQTAR2KYGV4ZHTNVCLQUKFBEL","short_pith_number":"pith:CCQTAR2K","schema_version":"1.0","canonical_sha256":"10a130474ac1abcc9e6da8970a28a122c0b5f2873dd850034000d06657e37089","source":{"kind":"arxiv","id":"2608.00630","version":1},"attestation_state":"computed","paper":{"title":"Relative Parameter Importance in Task-Agnostic Replay-Free Continual Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ikechukwu Nkisi-Orji, Malavika Suresh, Nirmalie Wiratunga","submitted_at":"2026-08-01T12:38:55Z","abstract_excerpt":"Achieving continual learning (CL) with deep neural networks requires balancing stability and plasticity while enabling knowledge transfer. In this work, we focus on offline learning algorithms under the constraints: (I) no access to training data from prior tasks (II) no access to task-id at inference time. We introduce a novel measure, the relative parameter-importance, which measures the relative importance of each parameter with respect to both the current and past tasks. Parameters with high relative importance are interpreted as more important for maintaining past-task stability and thus "},"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":"2608.00630","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-01T12:38:55Z","cross_cats_sorted":[],"title_canon_sha256":"e47aa7d77a70fc9ca61a66fd95477cff155b36e0d3e4a5a5b9b866697b99fc07","abstract_canon_sha256":"2607c5a016abb34e0b7624a2bf096953562b14456dfb45d1af891fa5f656735d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T00:38:07.916070Z","signature_b64":"C3Z7PsQwt0+a234OdLTAJEtXGsgRdYWScoFe7s74P/nK2sffDWCbtgAkKjgAFLkmthtThgHkI4zfOveIO6FSBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10a130474ac1abcc9e6da8970a28a122c0b5f2873dd850034000d06657e37089","last_reissued_at":"2026-08-04T00:38:07.914603Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T00:38:07.914603Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Relative Parameter Importance in Task-Agnostic Replay-Free Continual Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ikechukwu Nkisi-Orji, Malavika Suresh, Nirmalie Wiratunga","submitted_at":"2026-08-01T12:38:55Z","abstract_excerpt":"Achieving continual learning (CL) with deep neural networks requires balancing stability and plasticity while enabling knowledge transfer. In this work, we focus on offline learning algorithms under the constraints: (I) no access to training data from prior tasks (II) no access to task-id at inference time. We introduce a novel measure, the relative parameter-importance, which measures the relative importance of each parameter with respect to both the current and past tasks. Parameters with high relative importance are interpreted as more important for maintaining past-task stability and thus "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00630","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/2608.00630/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":"2608.00630","created_at":"2026-08-04T00:38:07.915812+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.00630v1","created_at":"2026-08-04T00:38:07.915812+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00630","created_at":"2026-08-04T00:38:07.915812+00:00"},{"alias_kind":"pith_short_12","alias_value":"CCQTAR2KYGV4","created_at":"2026-08-04T00:38:07.915812+00:00"},{"alias_kind":"pith_short_16","alias_value":"CCQTAR2KYGV4ZHTN","created_at":"2026-08-04T00:38:07.915812+00:00"},{"alias_kind":"pith_short_8","alias_value":"CCQTAR2K","created_at":"2026-08-04T00:38:07.915812+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/CCQTAR2KYGV4ZHTNVCLQUKFBEL","json":"https://pith.science/pith/CCQTAR2KYGV4ZHTNVCLQUKFBEL.json","graph_json":"https://pith.science/api/pith-number/CCQTAR2KYGV4ZHTNVCLQUKFBEL/graph.json","events_json":"https://pith.science/api/pith-number/CCQTAR2KYGV4ZHTNVCLQUKFBEL/events.json","paper":"https://pith.science/paper/CCQTAR2K"},"agent_actions":{"view_html":"https://pith.science/pith/CCQTAR2KYGV4ZHTNVCLQUKFBEL","download_json":"https://pith.science/pith/CCQTAR2KYGV4ZHTNVCLQUKFBEL.json","view_paper":"https://pith.science/paper/CCQTAR2K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.00630&json=true","fetch_graph":"https://pith.science/api/pith-number/CCQTAR2KYGV4ZHTNVCLQUKFBEL/graph.json","fetch_events":"https://pith.science/api/pith-number/CCQTAR2KYGV4ZHTNVCLQUKFBEL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CCQTAR2KYGV4ZHTNVCLQUKFBEL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CCQTAR2KYGV4ZHTNVCLQUKFBEL/action/storage_attestation","attest_author":"https://pith.science/pith/CCQTAR2KYGV4ZHTNVCLQUKFBEL/action/author_attestation","sign_citation":"https://pith.science/pith/CCQTAR2KYGV4ZHTNVCLQUKFBEL/action/citation_signature","submit_replication":"https://pith.science/pith/CCQTAR2KYGV4ZHTNVCLQUKFBEL/action/replication_record"}},"created_at":"2026-08-04T00:38:07.915812+00:00","updated_at":"2026-08-04T00:38:07.915812+00:00"}