{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AQXP25U7QAPGETPBEJ4D3C2TED","short_pith_number":"pith:AQXP25U7","schema_version":"1.0","canonical_sha256":"042efd769f801e624de122783d8b5320dc3232c1e90eaed483a0952ccafb7cf0","source":{"kind":"arxiv","id":"2312.00840","version":2},"attestation_state":"computed","paper":{"title":"Towards Redundancy-Free Sub-networks in Continual Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Cheng Chen, Heng Tao Shen, Jingkuan Song, Lianli Gao","submitted_at":"2023-12-01T02:29:52Z","abstract_excerpt":"Catastrophic Forgetting (CF) is a prominent issue in continual learning. Parameter isolation addresses this challenge by masking a sub-network for each task to mitigate interference with old tasks. However, these sub-networks are constructed relying on weight magnitude, which does not necessarily correspond to the importance of weights, resulting in maintaining unimportant weights and constructing redundant sub-networks. To overcome this limitation, inspired by information bottleneck, which removes redundancy between adjacent network layers, we propose \\textbf{\\underline{I}nformation \\underlin"},"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":"2312.00840","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-01T02:29:52Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"2cffe3c75b2b27f3d5ae6b449d0631661c6d3277d40a4223187982dc6f9776ff","abstract_canon_sha256":"7c11cdb7e71ac2162b1ae3ec5f08d66dee072961155cbc46c227da5eab3e2f88"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:32:25.334626Z","signature_b64":"VKdCQcel1F/ulgx7FLb/A46sWxSkGoXuiHGBHNZt1IRGC7P9PkobNVxTR1KVGeBtHFKjzR/vDxiQOFQ4BE1hAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"042efd769f801e624de122783d8b5320dc3232c1e90eaed483a0952ccafb7cf0","last_reissued_at":"2026-07-05T07:32:25.334138Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:32:25.334138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Redundancy-Free Sub-networks in Continual Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Cheng Chen, Heng Tao Shen, Jingkuan Song, Lianli Gao","submitted_at":"2023-12-01T02:29:52Z","abstract_excerpt":"Catastrophic Forgetting (CF) is a prominent issue in continual learning. Parameter isolation addresses this challenge by masking a sub-network for each task to mitigate interference with old tasks. However, these sub-networks are constructed relying on weight magnitude, which does not necessarily correspond to the importance of weights, resulting in maintaining unimportant weights and constructing redundant sub-networks. To overcome this limitation, inspired by information bottleneck, which removes redundancy between adjacent network layers, we propose \\textbf{\\underline{I}nformation \\underlin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.00840","kind":"arxiv","version":2},"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/2312.00840/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":"2312.00840","created_at":"2026-07-05T07:32:25.334194+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.00840v2","created_at":"2026-07-05T07:32:25.334194+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.00840","created_at":"2026-07-05T07:32:25.334194+00:00"},{"alias_kind":"pith_short_12","alias_value":"AQXP25U7QAPG","created_at":"2026-07-05T07:32:25.334194+00:00"},{"alias_kind":"pith_short_16","alias_value":"AQXP25U7QAPGETPB","created_at":"2026-07-05T07:32:25.334194+00:00"},{"alias_kind":"pith_short_8","alias_value":"AQXP25U7","created_at":"2026-07-05T07:32:25.334194+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.04897","citing_title":"Online Continual Learning: A Systematic Literature Review of Approaches, Challenges, and Benchmarks","ref_index":55,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AQXP25U7QAPGETPBEJ4D3C2TED","json":"https://pith.science/pith/AQXP25U7QAPGETPBEJ4D3C2TED.json","graph_json":"https://pith.science/api/pith-number/AQXP25U7QAPGETPBEJ4D3C2TED/graph.json","events_json":"https://pith.science/api/pith-number/AQXP25U7QAPGETPBEJ4D3C2TED/events.json","paper":"https://pith.science/paper/AQXP25U7"},"agent_actions":{"view_html":"https://pith.science/pith/AQXP25U7QAPGETPBEJ4D3C2TED","download_json":"https://pith.science/pith/AQXP25U7QAPGETPBEJ4D3C2TED.json","view_paper":"https://pith.science/paper/AQXP25U7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.00840&json=true","fetch_graph":"https://pith.science/api/pith-number/AQXP25U7QAPGETPBEJ4D3C2TED/graph.json","fetch_events":"https://pith.science/api/pith-number/AQXP25U7QAPGETPBEJ4D3C2TED/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AQXP25U7QAPGETPBEJ4D3C2TED/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AQXP25U7QAPGETPBEJ4D3C2TED/action/storage_attestation","attest_author":"https://pith.science/pith/AQXP25U7QAPGETPBEJ4D3C2TED/action/author_attestation","sign_citation":"https://pith.science/pith/AQXP25U7QAPGETPBEJ4D3C2TED/action/citation_signature","submit_replication":"https://pith.science/pith/AQXP25U7QAPGETPBEJ4D3C2TED/action/replication_record"}},"created_at":"2026-07-05T07:32:25.334194+00:00","updated_at":"2026-07-05T07:32:25.334194+00:00"}