{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:VM77NHLHOOODXL6FSJ43U7FTKW","short_pith_number":"pith:VM77NHLH","schema_version":"1.0","canonical_sha256":"ab3ff69d67739c3bafc59279ba7cb355b9e3ad33f205af994a28f9d074889db3","source":{"kind":"arxiv","id":"1906.02425","version":2},"attestation_state":"computed","paper":{"title":"Uncertainty-guided Continual Learning with Bayesian Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Marcus Rohrbach, Mohamed Elhoseiny, Sayna Ebrahimi, Trevor Darrell","submitted_at":"2019-06-06T05:40:25Z","abstract_excerpt":"Continual learning aims to learn new tasks without forgetting previously learned ones. This is especially challenging when one cannot access data from previous tasks and when the model has a fixed capacity. Current regularization-based continual learning algorithms need an external representation and extra computation to measure the parameters' \\textit{importance}. In contrast, we propose Uncertainty-guided Continual Bayesian Neural Networks (UCB), where the learning rate adapts according to the uncertainty defined in the probability distribution of the weights in networks. Uncertainty is a na"},"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":"1906.02425","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-06T05:40:25Z","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"title_canon_sha256":"c0ef7a053883be7e7b6e6a88bb640e4e6cf1ec7af1a31081187026fb6824423d","abstract_canon_sha256":"94b97c032c267ff2f8f8eadd04399f8eaa69afc372c2135df6e0c5e974c525da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:42:31.270310Z","signature_b64":"jhyPr5cHDTujQoDucblSNUrni1rwp+DtUcITRtsJzZ31YHfxAPvL2p8qQ8fKxTMlRcFvJlhMXROY9BaYgNFtCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab3ff69d67739c3bafc59279ba7cb355b9e3ad33f205af994a28f9d074889db3","last_reissued_at":"2026-07-05T00:42:31.269707Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:42:31.269707Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Uncertainty-guided Continual Learning with Bayesian Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Marcus Rohrbach, Mohamed Elhoseiny, Sayna Ebrahimi, Trevor Darrell","submitted_at":"2019-06-06T05:40:25Z","abstract_excerpt":"Continual learning aims to learn new tasks without forgetting previously learned ones. This is especially challenging when one cannot access data from previous tasks and when the model has a fixed capacity. Current regularization-based continual learning algorithms need an external representation and extra computation to measure the parameters' \\textit{importance}. In contrast, we propose Uncertainty-guided Continual Bayesian Neural Networks (UCB), where the learning rate adapts according to the uncertainty defined in the probability distribution of the weights in networks. Uncertainty is a na"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.02425","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/1906.02425/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":"1906.02425","created_at":"2026-07-05T00:42:31.269779+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.02425v2","created_at":"2026-07-05T00:42:31.269779+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.02425","created_at":"2026-07-05T00:42:31.269779+00:00"},{"alias_kind":"pith_short_12","alias_value":"VM77NHLHOOOD","created_at":"2026-07-05T00:42:31.269779+00:00"},{"alias_kind":"pith_short_16","alias_value":"VM77NHLHOOODXL6F","created_at":"2026-07-05T00:42:31.269779+00:00"},{"alias_kind":"pith_short_8","alias_value":"VM77NHLH","created_at":"2026-07-05T00:42:31.269779+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.02959","citing_title":"A Novel Active Learning Approach to Label One Million Unknown Malware Variants","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VM77NHLHOOODXL6FSJ43U7FTKW","json":"https://pith.science/pith/VM77NHLHOOODXL6FSJ43U7FTKW.json","graph_json":"https://pith.science/api/pith-number/VM77NHLHOOODXL6FSJ43U7FTKW/graph.json","events_json":"https://pith.science/api/pith-number/VM77NHLHOOODXL6FSJ43U7FTKW/events.json","paper":"https://pith.science/paper/VM77NHLH"},"agent_actions":{"view_html":"https://pith.science/pith/VM77NHLHOOODXL6FSJ43U7FTKW","download_json":"https://pith.science/pith/VM77NHLHOOODXL6FSJ43U7FTKW.json","view_paper":"https://pith.science/paper/VM77NHLH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.02425&json=true","fetch_graph":"https://pith.science/api/pith-number/VM77NHLHOOODXL6FSJ43U7FTKW/graph.json","fetch_events":"https://pith.science/api/pith-number/VM77NHLHOOODXL6FSJ43U7FTKW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VM77NHLHOOODXL6FSJ43U7FTKW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VM77NHLHOOODXL6FSJ43U7FTKW/action/storage_attestation","attest_author":"https://pith.science/pith/VM77NHLHOOODXL6FSJ43U7FTKW/action/author_attestation","sign_citation":"https://pith.science/pith/VM77NHLHOOODXL6FSJ43U7FTKW/action/citation_signature","submit_replication":"https://pith.science/pith/VM77NHLHOOODXL6FSJ43U7FTKW/action/replication_record"}},"created_at":"2026-07-05T00:42:31.269779+00:00","updated_at":"2026-07-05T00:42:31.269779+00:00"}