{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YJUHBDGL4BVEFNMHCNXUMSUBW3","short_pith_number":"pith:YJUHBDGL","schema_version":"1.0","canonical_sha256":"c268708ccbe06a42b587136f464a81b6db8df6e42d3c43b473854b10b547ab1b","source":{"kind":"arxiv","id":"2605.30198","version":1},"attestation_state":"computed","paper":{"title":"Active Continual Learning with Metaplastic Binary Bayesian Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Damien Querlioz, Djohan Bonnet, Kellian Cottart, Th\\'eo Ballet","submitted_at":"2026-05-28T16:36:53Z","abstract_excerpt":"Always-on edge systems must keep learning as conditions change under tight compute budgets and must detect unreliable predictions. Bayesian binary neural networks are attractive in this setting, but mean-field Bernoulli posteriors can saturate on long non-stationary streams, wiping out epistemic uncertainty and freezing plasticity. We propose BiMU, derived from a bounded-memory variational objective that balances stability, plasticity, and forgetting. BiMU combines a data term with controlled relaxation toward the prior and an uncertainty-dependent step size that prevents saturation and sustai"},"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":"2605.30198","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T16:36:53Z","cross_cats_sorted":[],"title_canon_sha256":"b571562852a0fac23c515e026feec074f904d9f61a2dae0475038287c7f38620","abstract_canon_sha256":"d8a6eb01afd6775686f592fb0b79bc9981543d73e1de631e1b07c5b748eae7e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:06:12.590710Z","signature_b64":"YqtghkEJb/pbnZlN8ZToCXp0sVgDEg1TcusrcziN0yFTpKDbGM0DjtATqNZmwcxMqpd/IliN+sM/jAF56Ec0Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c268708ccbe06a42b587136f464a81b6db8df6e42d3c43b473854b10b547ab1b","last_reissued_at":"2026-05-29T02:06:12.590355Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:06:12.590355Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Active Continual Learning with Metaplastic Binary Bayesian Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Damien Querlioz, Djohan Bonnet, Kellian Cottart, Th\\'eo Ballet","submitted_at":"2026-05-28T16:36:53Z","abstract_excerpt":"Always-on edge systems must keep learning as conditions change under tight compute budgets and must detect unreliable predictions. Bayesian binary neural networks are attractive in this setting, but mean-field Bernoulli posteriors can saturate on long non-stationary streams, wiping out epistemic uncertainty and freezing plasticity. We propose BiMU, derived from a bounded-memory variational objective that balances stability, plasticity, and forgetting. BiMU combines a data term with controlled relaxation toward the prior and an uncertainty-dependent step size that prevents saturation and sustai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30198","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/2605.30198/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":"2605.30198","created_at":"2026-05-29T02:06:12.590418+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.30198v1","created_at":"2026-05-29T02:06:12.590418+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30198","created_at":"2026-05-29T02:06:12.590418+00:00"},{"alias_kind":"pith_short_12","alias_value":"YJUHBDGL4BVE","created_at":"2026-05-29T02:06:12.590418+00:00"},{"alias_kind":"pith_short_16","alias_value":"YJUHBDGL4BVEFNMH","created_at":"2026-05-29T02:06:12.590418+00:00"},{"alias_kind":"pith_short_8","alias_value":"YJUHBDGL","created_at":"2026-05-29T02:06:12.590418+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/YJUHBDGL4BVEFNMHCNXUMSUBW3","json":"https://pith.science/pith/YJUHBDGL4BVEFNMHCNXUMSUBW3.json","graph_json":"https://pith.science/api/pith-number/YJUHBDGL4BVEFNMHCNXUMSUBW3/graph.json","events_json":"https://pith.science/api/pith-number/YJUHBDGL4BVEFNMHCNXUMSUBW3/events.json","paper":"https://pith.science/paper/YJUHBDGL"},"agent_actions":{"view_html":"https://pith.science/pith/YJUHBDGL4BVEFNMHCNXUMSUBW3","download_json":"https://pith.science/pith/YJUHBDGL4BVEFNMHCNXUMSUBW3.json","view_paper":"https://pith.science/paper/YJUHBDGL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.30198&json=true","fetch_graph":"https://pith.science/api/pith-number/YJUHBDGL4BVEFNMHCNXUMSUBW3/graph.json","fetch_events":"https://pith.science/api/pith-number/YJUHBDGL4BVEFNMHCNXUMSUBW3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YJUHBDGL4BVEFNMHCNXUMSUBW3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YJUHBDGL4BVEFNMHCNXUMSUBW3/action/storage_attestation","attest_author":"https://pith.science/pith/YJUHBDGL4BVEFNMHCNXUMSUBW3/action/author_attestation","sign_citation":"https://pith.science/pith/YJUHBDGL4BVEFNMHCNXUMSUBW3/action/citation_signature","submit_replication":"https://pith.science/pith/YJUHBDGL4BVEFNMHCNXUMSUBW3/action/replication_record"}},"created_at":"2026-05-29T02:06:12.590418+00:00","updated_at":"2026-05-29T02:06:12.590418+00:00"}