{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UY4KWLYEEISD6EBVNUMD5DWTSJ","short_pith_number":"pith:UY4KWLYE","schema_version":"1.0","canonical_sha256":"a638ab2f0422243f10356d183e8ed392624f37fc4f92dc2ee91dbd98c5da18e3","source":{"kind":"arxiv","id":"2412.00776","version":4},"attestation_state":"computed","paper":{"title":"Learning Mamba as a Continual Learner: Meta-learning Selective State Space Models for Efficient Continual Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chongyang Zhao, Dong Gong","submitted_at":"2024-12-01T11:43:46Z","abstract_excerpt":"Continual learning (CL) aims to efficiently learn from a non-stationary data stream, without storing or recomputing all seen samples. CL enables prediction on new tasks by incorporating sequential training samples. Building on this connection between CL and sequential modeling, meta-continual learning (MCL) aims to meta-learn an efficient continual learner as a sequence prediction model, with advanced sequence models like Transformers being natural choices. However, despite decent performance, Transformers rely on a linearly growing cache to store all past representations, conflicting with CL'"},"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":"2412.00776","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-01T11:43:46Z","cross_cats_sorted":[],"title_canon_sha256":"cf4470b010e549b43914b485cd87f03f237c4a20ee30dba8177a4fae58d4118a","abstract_canon_sha256":"7439a65b0dd82fb5f02e54867f47b408cbc8941428beedca5cf7c7c50c551d0c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:04.629392Z","signature_b64":"H1+yHxIfWWYheW/uoijM6E+x9aqdH1GH4QNTSOn8BgOqzneTMwuYXUHxWKsn9z2EpK7Wv1F7r/jtD6poMikfDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a638ab2f0422243f10356d183e8ed392624f37fc4f92dc2ee91dbd98c5da18e3","last_reissued_at":"2026-07-05T11:09:04.628912Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:04.628912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Mamba as a Continual Learner: Meta-learning Selective State Space Models for Efficient Continual Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chongyang Zhao, Dong Gong","submitted_at":"2024-12-01T11:43:46Z","abstract_excerpt":"Continual learning (CL) aims to efficiently learn from a non-stationary data stream, without storing or recomputing all seen samples. CL enables prediction on new tasks by incorporating sequential training samples. Building on this connection between CL and sequential modeling, meta-continual learning (MCL) aims to meta-learn an efficient continual learner as a sequence prediction model, with advanced sequence models like Transformers being natural choices. However, despite decent performance, Transformers rely on a linearly growing cache to store all past representations, conflicting with CL'"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00776","kind":"arxiv","version":4},"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/2412.00776/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":"2412.00776","created_at":"2026-07-05T11:09:04.628970+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.00776v4","created_at":"2026-07-05T11:09:04.628970+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00776","created_at":"2026-07-05T11:09:04.628970+00:00"},{"alias_kind":"pith_short_12","alias_value":"UY4KWLYEEISD","created_at":"2026-07-05T11:09:04.628970+00:00"},{"alias_kind":"pith_short_16","alias_value":"UY4KWLYEEISD6EBV","created_at":"2026-07-05T11:09:04.628970+00:00"},{"alias_kind":"pith_short_8","alias_value":"UY4KWLYE","created_at":"2026-07-05T11:09:04.628970+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.18604","citing_title":"Exemplar-Free Continual Learning for State Space Models","ref_index":64,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UY4KWLYEEISD6EBVNUMD5DWTSJ","json":"https://pith.science/pith/UY4KWLYEEISD6EBVNUMD5DWTSJ.json","graph_json":"https://pith.science/api/pith-number/UY4KWLYEEISD6EBVNUMD5DWTSJ/graph.json","events_json":"https://pith.science/api/pith-number/UY4KWLYEEISD6EBVNUMD5DWTSJ/events.json","paper":"https://pith.science/paper/UY4KWLYE"},"agent_actions":{"view_html":"https://pith.science/pith/UY4KWLYEEISD6EBVNUMD5DWTSJ","download_json":"https://pith.science/pith/UY4KWLYEEISD6EBVNUMD5DWTSJ.json","view_paper":"https://pith.science/paper/UY4KWLYE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.00776&json=true","fetch_graph":"https://pith.science/api/pith-number/UY4KWLYEEISD6EBVNUMD5DWTSJ/graph.json","fetch_events":"https://pith.science/api/pith-number/UY4KWLYEEISD6EBVNUMD5DWTSJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UY4KWLYEEISD6EBVNUMD5DWTSJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UY4KWLYEEISD6EBVNUMD5DWTSJ/action/storage_attestation","attest_author":"https://pith.science/pith/UY4KWLYEEISD6EBVNUMD5DWTSJ/action/author_attestation","sign_citation":"https://pith.science/pith/UY4KWLYEEISD6EBVNUMD5DWTSJ/action/citation_signature","submit_replication":"https://pith.science/pith/UY4KWLYEEISD6EBVNUMD5DWTSJ/action/replication_record"}},"created_at":"2026-07-05T11:09:04.628970+00:00","updated_at":"2026-07-05T11:09:04.628970+00:00"}