{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:ZUPGOOEAUHFEPNXF6ZT7OS4I3Q","short_pith_number":"pith:ZUPGOOEA","schema_version":"1.0","canonical_sha256":"cd1e673880a1ca47b6e5f667f74b88dc2b5c8f8aeb96f000b4541a72ec3c131c","source":{"kind":"arxiv","id":"1905.12019","version":5},"attestation_state":"computed","paper":{"title":"Unified Probabilistic Deep Continual Learning through Generative Replay and Open Set Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Iuliia Pliushch, Martin Mundt, Sagnik Majumder, Visvanathan Ramesh, Yongwon Hong","submitted_at":"2019-05-28T18:26:04Z","abstract_excerpt":"Modern deep neural networks are well known to be brittle in the face of unknown data instances and recognition of the latter remains a challenge. Although it is inevitable for continual-learning systems to encounter such unseen concepts, the corresponding literature appears to nonetheless focus primarily on alleviating catastrophic interference with learned representations. In this work, we introduce a probabilistic approach that connects these perspectives based on variational inference in a single deep autoencoder model. Specifically, we propose to bound the approximate posterior by fitting "},"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":"1905.12019","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-05-28T18:26:04Z","cross_cats_sorted":["cs.CV","cs.NE","stat.ML"],"title_canon_sha256":"63299a340e708f5c8b6ca37a99e2d3526ccf2edc8cb09a69b40f33cf3835e431","abstract_canon_sha256":"648420051f5195a232e1f47dfa1474bdfaeb3dfdac936550b56a30f13417f86e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:10:33.445924Z","signature_b64":"p0lSJ0t/Uoe8QgjM99j+QvaWcwrCFNY5It0S2rKZB/uVCfbRX40SjVkgRQJtg1SEPGCxFaK8JNkw0oxGkBMyAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd1e673880a1ca47b6e5f667f74b88dc2b5c8f8aeb96f000b4541a72ec3c131c","last_reissued_at":"2026-07-05T04:10:33.445449Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:10:33.445449Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unified Probabilistic Deep Continual Learning through Generative Replay and Open Set Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Iuliia Pliushch, Martin Mundt, Sagnik Majumder, Visvanathan Ramesh, Yongwon Hong","submitted_at":"2019-05-28T18:26:04Z","abstract_excerpt":"Modern deep neural networks are well known to be brittle in the face of unknown data instances and recognition of the latter remains a challenge. Although it is inevitable for continual-learning systems to encounter such unseen concepts, the corresponding literature appears to nonetheless focus primarily on alleviating catastrophic interference with learned representations. In this work, we introduce a probabilistic approach that connects these perspectives based on variational inference in a single deep autoencoder model. Specifically, we propose to bound the approximate posterior by fitting "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.12019","kind":"arxiv","version":5},"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/1905.12019/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":"1905.12019","created_at":"2026-07-05T04:10:33.445513+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.12019v5","created_at":"2026-07-05T04:10:33.445513+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.12019","created_at":"2026-07-05T04:10:33.445513+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZUPGOOEAUHFE","created_at":"2026-07-05T04:10:33.445513+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZUPGOOEAUHFEPNXF","created_at":"2026-07-05T04:10:33.445513+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZUPGOOEA","created_at":"2026-07-05T04:10:33.445513+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.09625","citing_title":"Open Set Recognition Through Deep Neural Network Uncertainty: Does Out-of-Distribution Detection Require Generative Classifiers?","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZUPGOOEAUHFEPNXF6ZT7OS4I3Q","json":"https://pith.science/pith/ZUPGOOEAUHFEPNXF6ZT7OS4I3Q.json","graph_json":"https://pith.science/api/pith-number/ZUPGOOEAUHFEPNXF6ZT7OS4I3Q/graph.json","events_json":"https://pith.science/api/pith-number/ZUPGOOEAUHFEPNXF6ZT7OS4I3Q/events.json","paper":"https://pith.science/paper/ZUPGOOEA"},"agent_actions":{"view_html":"https://pith.science/pith/ZUPGOOEAUHFEPNXF6ZT7OS4I3Q","download_json":"https://pith.science/pith/ZUPGOOEAUHFEPNXF6ZT7OS4I3Q.json","view_paper":"https://pith.science/paper/ZUPGOOEA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.12019&json=true","fetch_graph":"https://pith.science/api/pith-number/ZUPGOOEAUHFEPNXF6ZT7OS4I3Q/graph.json","fetch_events":"https://pith.science/api/pith-number/ZUPGOOEAUHFEPNXF6ZT7OS4I3Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZUPGOOEAUHFEPNXF6ZT7OS4I3Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZUPGOOEAUHFEPNXF6ZT7OS4I3Q/action/storage_attestation","attest_author":"https://pith.science/pith/ZUPGOOEAUHFEPNXF6ZT7OS4I3Q/action/author_attestation","sign_citation":"https://pith.science/pith/ZUPGOOEAUHFEPNXF6ZT7OS4I3Q/action/citation_signature","submit_replication":"https://pith.science/pith/ZUPGOOEAUHFEPNXF6ZT7OS4I3Q/action/replication_record"}},"created_at":"2026-07-05T04:10:33.445513+00:00","updated_at":"2026-07-05T04:10:33.445513+00:00"}