{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ZV55RI7WO7RLJ6IU4KVGKREPAP","short_pith_number":"pith:ZV55RI7W","canonical_record":{"source":{"id":"2412.10869","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-14T15:43:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7115a9089beccf3c1fccd6e55e542c09a9e6471a90996906711da943f679e103","abstract_canon_sha256":"048f29ee53ebcb97cde5393ae4feb1395d30d4d6af70d2078400d719dd315bee"},"schema_version":"1.0"},"canonical_sha256":"cd7bd8a3f677e2b4f914e2aa65448f03f65a870e5b88c945d0d4e5b661928bd5","source":{"kind":"arxiv","id":"2412.10869","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.10869","created_at":"2026-07-05T12:11:14Z"},{"alias_kind":"arxiv_version","alias_value":"2412.10869v3","created_at":"2026-07-05T12:11:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10869","created_at":"2026-07-05T12:11:14Z"},{"alias_kind":"pith_short_12","alias_value":"ZV55RI7WO7RL","created_at":"2026-07-05T12:11:14Z"},{"alias_kind":"pith_short_16","alias_value":"ZV55RI7WO7RLJ6IU","created_at":"2026-07-05T12:11:14Z"},{"alias_kind":"pith_short_8","alias_value":"ZV55RI7W","created_at":"2026-07-05T12:11:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ZV55RI7WO7RLJ6IU4KVGKREPAP","target":"record","payload":{"canonical_record":{"source":{"id":"2412.10869","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-14T15:43:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7115a9089beccf3c1fccd6e55e542c09a9e6471a90996906711da943f679e103","abstract_canon_sha256":"048f29ee53ebcb97cde5393ae4feb1395d30d4d6af70d2078400d719dd315bee"},"schema_version":"1.0"},"canonical_sha256":"cd7bd8a3f677e2b4f914e2aa65448f03f65a870e5b88c945d0d4e5b661928bd5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:11:14.671876Z","signature_b64":"hL7CQslaVmh40C+HMnOYmsrw/osExuQo5bPJBfltuMprGrYuinlQOl3ijWNdANMNguD+aVXnjNPdK+W+EWGwAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd7bd8a3f677e2b4f914e2aa65448f03f65a870e5b88c945d0d4e5b661928bd5","last_reissued_at":"2026-07-05T12:11:14.671286Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:11:14.671286Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.10869","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:11:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KAgXYZPnKQaZn1grUpGCq4/+lB/c62/+p1GuK5Dxni3IwACyy1FygC5cj2YtIGjsDZ0dkj36VwJdodXhqK/3AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T03:39:56.143499Z"},"content_sha256":"5be4499aa17f296eb5f3a57db6006810739faba22ce02f4fcb988e0efae1fd44","schema_version":"1.0","event_id":"sha256:5be4499aa17f296eb5f3a57db6006810739faba22ce02f4fcb988e0efae1fd44"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ZV55RI7WO7RLJ6IU4KVGKREPAP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TinySubNets: An efficient and low capacity continual learning strategy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dominik \\.Zurek, Kamil Faber, Marcin Pietro\\'n, Roberto Corizzo","submitted_at":"2024-12-14T15:43:38Z","abstract_excerpt":"Continual Learning (CL) is a highly relevant setting gaining traction in recent machine learning research. Among CL works, architectural and hybrid strategies are particularly effective due to their potential to adapt the model architecture as new tasks are presented. However, many existing solutions do not efficiently exploit model sparsity, and are prone to capacity saturation due to their inefficient use of available weights, which limits the number of learnable tasks. In this paper, we propose TinySubNets (TSN), a novel architectural CL strategy that addresses the issues through the unique"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10869","kind":"arxiv","version":3},"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/2412.10869/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:11:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c6XtsOCaxyMbukCXT9n77K6zv0LbLw9VeDDvdHgqrv0BI1At2eLlnD1lC7Y7CIaodcHldzklWhnchcvPi637AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T03:39:56.143916Z"},"content_sha256":"4823db5cac1077523ad4581076a5a3e1e89c09719ccb170f8b569c15a43991c2","schema_version":"1.0","event_id":"sha256:4823db5cac1077523ad4581076a5a3e1e89c09719ccb170f8b569c15a43991c2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZV55RI7WO7RLJ6IU4KVGKREPAP/bundle.json","state_url":"https://pith.science/pith/ZV55RI7WO7RLJ6IU4KVGKREPAP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZV55RI7WO7RLJ6IU4KVGKREPAP/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-09T03:39:56Z","links":{"resolver":"https://pith.science/pith/ZV55RI7WO7RLJ6IU4KVGKREPAP","bundle":"https://pith.science/pith/ZV55RI7WO7RLJ6IU4KVGKREPAP/bundle.json","state":"https://pith.science/pith/ZV55RI7WO7RLJ6IU4KVGKREPAP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZV55RI7WO7RLJ6IU4KVGKREPAP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZV55RI7WO7RLJ6IU4KVGKREPAP","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"048f29ee53ebcb97cde5393ae4feb1395d30d4d6af70d2078400d719dd315bee","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-14T15:43:38Z","title_canon_sha256":"7115a9089beccf3c1fccd6e55e542c09a9e6471a90996906711da943f679e103"},"schema_version":"1.0","source":{"id":"2412.10869","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.10869","created_at":"2026-07-05T12:11:14Z"},{"alias_kind":"arxiv_version","alias_value":"2412.10869v3","created_at":"2026-07-05T12:11:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10869","created_at":"2026-07-05T12:11:14Z"},{"alias_kind":"pith_short_12","alias_value":"ZV55RI7WO7RL","created_at":"2026-07-05T12:11:14Z"},{"alias_kind":"pith_short_16","alias_value":"ZV55RI7WO7RLJ6IU","created_at":"2026-07-05T12:11:14Z"},{"alias_kind":"pith_short_8","alias_value":"ZV55RI7W","created_at":"2026-07-05T12:11:14Z"}],"graph_snapshots":[{"event_id":"sha256:4823db5cac1077523ad4581076a5a3e1e89c09719ccb170f8b569c15a43991c2","target":"graph","created_at":"2026-07-05T12:11:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2412.10869/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Continual Learning (CL) is a highly relevant setting gaining traction in recent machine learning research. Among CL works, architectural and hybrid strategies are particularly effective due to their potential to adapt the model architecture as new tasks are presented. However, many existing solutions do not efficiently exploit model sparsity, and are prone to capacity saturation due to their inefficient use of available weights, which limits the number of learnable tasks. In this paper, we propose TinySubNets (TSN), a novel architectural CL strategy that addresses the issues through the unique","authors_text":"Dominik \\.Zurek, Kamil Faber, Marcin Pietro\\'n, Roberto Corizzo","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-14T15:43:38Z","title":"TinySubNets: An efficient and low capacity continual learning strategy"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10869","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5be4499aa17f296eb5f3a57db6006810739faba22ce02f4fcb988e0efae1fd44","target":"record","created_at":"2026-07-05T12:11:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"048f29ee53ebcb97cde5393ae4feb1395d30d4d6af70d2078400d719dd315bee","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-14T15:43:38Z","title_canon_sha256":"7115a9089beccf3c1fccd6e55e542c09a9e6471a90996906711da943f679e103"},"schema_version":"1.0","source":{"id":"2412.10869","kind":"arxiv","version":3}},"canonical_sha256":"cd7bd8a3f677e2b4f914e2aa65448f03f65a870e5b88c945d0d4e5b661928bd5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cd7bd8a3f677e2b4f914e2aa65448f03f65a870e5b88c945d0d4e5b661928bd5","first_computed_at":"2026-07-05T12:11:14.671286Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:11:14.671286Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hL7CQslaVmh40C+HMnOYmsrw/osExuQo5bPJBfltuMprGrYuinlQOl3ijWNdANMNguD+aVXnjNPdK+W+EWGwAA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:11:14.671876Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.10869","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5be4499aa17f296eb5f3a57db6006810739faba22ce02f4fcb988e0efae1fd44","sha256:4823db5cac1077523ad4581076a5a3e1e89c09719ccb170f8b569c15a43991c2"],"state_sha256":"fd7f7dadd5f8556042aafdd00138443ae05dd89069a8e0113103ef98f1a75063"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eAo+H+23f4VX/nlPw/iXuhKniu1n0YngjDsPR4LP9oMuLAxXq/X0pwsXBGa/pg9E5zBJS+K5chFkHPZiDg5GAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T03:39:56.145924Z","bundle_sha256":"37643bbd3fbf29063f275af8ef1a10552c68be0b9c47803cbdfa5a304a4c3e8d"}}