{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BPO55MVPK34ICLFESKHIUTJETH","short_pith_number":"pith:BPO55MVP","schema_version":"1.0","canonical_sha256":"0bdddeb2af56f8812ca4928e8a4d2499e30c230ba63d00f1d28bdf97654b4c9d","source":{"kind":"arxiv","id":"2303.14962","version":1},"attestation_state":"computed","paper":{"title":"Forget-free Continual Learning with Soft-Winning SubNetworks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Chang D. Yoo, Haeyong Kang, Jaehong Yoon, Sultan Rizky Madjid, Sung Ju Hwang","submitted_at":"2023-03-27T07:53:23Z","abstract_excerpt":"Inspired by Regularized Lottery Ticket Hypothesis (RLTH), which states that competitive smooth (non-binary) subnetworks exist within a dense network in continual learning tasks, we investigate two proposed architecture-based continual learning methods which sequentially learn and select adaptive binary- (WSN) and non-binary Soft-Subnetworks (SoftNet) for each task. WSN and SoftNet jointly learn the regularized model weights and task-adaptive non-binary masks of subnetworks associated with each task whilst attempting to select a small set of weights to be activated (winning ticket) by reusing w"},"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":"2303.14962","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-27T07:53:23Z","cross_cats_sorted":["cs.AI","cs.CV","cs.NE"],"title_canon_sha256":"ede32542d10e1438a500b642c33a9ca76c3e75e1ac237096941953ce5eb0b1a3","abstract_canon_sha256":"2cb2e9c3f41dc74ddf0073270c653ca1331e5664773dc83c262a0521710ecbc4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:54:48.363955Z","signature_b64":"KtY8XDSXAZ3EPYCHf0Qhl1dMxPvj7dGTNQpFPqRjoWyl/2UUpZd3zNHwO98JeIla2oRg4zh0XQjQsVZ6/qtCDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0bdddeb2af56f8812ca4928e8a4d2499e30c230ba63d00f1d28bdf97654b4c9d","last_reissued_at":"2026-07-05T05:54:48.363519Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:54:48.363519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Forget-free Continual Learning with Soft-Winning SubNetworks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Chang D. Yoo, Haeyong Kang, Jaehong Yoon, Sultan Rizky Madjid, Sung Ju Hwang","submitted_at":"2023-03-27T07:53:23Z","abstract_excerpt":"Inspired by Regularized Lottery Ticket Hypothesis (RLTH), which states that competitive smooth (non-binary) subnetworks exist within a dense network in continual learning tasks, we investigate two proposed architecture-based continual learning methods which sequentially learn and select adaptive binary- (WSN) and non-binary Soft-Subnetworks (SoftNet) for each task. WSN and SoftNet jointly learn the regularized model weights and task-adaptive non-binary masks of subnetworks associated with each task whilst attempting to select a small set of weights to be activated (winning ticket) by reusing w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.14962","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/2303.14962/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":"2303.14962","created_at":"2026-07-05T05:54:48.363574+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.14962v1","created_at":"2026-07-05T05:54:48.363574+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.14962","created_at":"2026-07-05T05:54:48.363574+00:00"},{"alias_kind":"pith_short_12","alias_value":"BPO55MVPK34I","created_at":"2026-07-05T05:54:48.363574+00:00"},{"alias_kind":"pith_short_16","alias_value":"BPO55MVPK34ICLFE","created_at":"2026-07-05T05:54:48.363574+00:00"},{"alias_kind":"pith_short_8","alias_value":"BPO55MVP","created_at":"2026-07-05T05:54:48.363574+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.20033","citing_title":"Mitigating Catastrophic Forgetting in the Incremental Learning of Medical Images","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BPO55MVPK34ICLFESKHIUTJETH","json":"https://pith.science/pith/BPO55MVPK34ICLFESKHIUTJETH.json","graph_json":"https://pith.science/api/pith-number/BPO55MVPK34ICLFESKHIUTJETH/graph.json","events_json":"https://pith.science/api/pith-number/BPO55MVPK34ICLFESKHIUTJETH/events.json","paper":"https://pith.science/paper/BPO55MVP"},"agent_actions":{"view_html":"https://pith.science/pith/BPO55MVPK34ICLFESKHIUTJETH","download_json":"https://pith.science/pith/BPO55MVPK34ICLFESKHIUTJETH.json","view_paper":"https://pith.science/paper/BPO55MVP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.14962&json=true","fetch_graph":"https://pith.science/api/pith-number/BPO55MVPK34ICLFESKHIUTJETH/graph.json","fetch_events":"https://pith.science/api/pith-number/BPO55MVPK34ICLFESKHIUTJETH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BPO55MVPK34ICLFESKHIUTJETH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BPO55MVPK34ICLFESKHIUTJETH/action/storage_attestation","attest_author":"https://pith.science/pith/BPO55MVPK34ICLFESKHIUTJETH/action/author_attestation","sign_citation":"https://pith.science/pith/BPO55MVPK34ICLFESKHIUTJETH/action/citation_signature","submit_replication":"https://pith.science/pith/BPO55MVPK34ICLFESKHIUTJETH/action/replication_record"}},"created_at":"2026-07-05T05:54:48.363574+00:00","updated_at":"2026-07-05T05:54:48.363574+00:00"}