{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:RPDJMICBKHFSPGD3JWJA67QR4H","short_pith_number":"pith:RPDJMICB","schema_version":"1.0","canonical_sha256":"8bc696204151cb27987b4d920f7e11e1e51ec652751adbcb27d256370a6ccabd","source":{"kind":"arxiv","id":"1906.00654","version":1},"attestation_state":"computed","paper":{"title":"Continual Learning of New Sound Classes using Generative Replay","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Cem Subakan, Efthymios Tzinis, Laurent Charlin, Paris Smaragdis, Zhepei Wang","submitted_at":"2019-06-03T09:20:18Z","abstract_excerpt":"Continual learning consists in incrementally training a model on a sequence of datasets and testing on the union of all datasets. In this paper, we examine continual learning for the problem of sound classification, in which we wish to refine already trained models to learn new sound classes. In practice one does not want to maintain all past training data and retrain from scratch, but naively updating a model with new data(sets) results in a degradation of already learned tasks, which is referred to as \"catastrophic forgetting.\" We develop a generative replay procedure for generating training"},"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":"1906.00654","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-03T09:20:18Z","cross_cats_sorted":["cs.SD","eess.AS","stat.ML"],"title_canon_sha256":"5e7ae37ab58bd07c9ef97f5875e96f47f30486b6066ac608fc920b82006d4692","abstract_canon_sha256":"84592adeb148964ec1384e70541fad043732ee15651fa22a5a85f1e45577c41c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:24.229602Z","signature_b64":"lDHB1bIG/zB7mnKp2b54VHKQZv2iIbergBNuglh/Wb9NIAF158bNmS3eZpZPpRQrrwHx6MsU25VsKL0YaToBAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8bc696204151cb27987b4d920f7e11e1e51ec652751adbcb27d256370a6ccabd","last_reissued_at":"2026-05-17T23:44:24.228993Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:24.228993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Continual Learning of New Sound Classes using Generative Replay","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Cem Subakan, Efthymios Tzinis, Laurent Charlin, Paris Smaragdis, Zhepei Wang","submitted_at":"2019-06-03T09:20:18Z","abstract_excerpt":"Continual learning consists in incrementally training a model on a sequence of datasets and testing on the union of all datasets. In this paper, we examine continual learning for the problem of sound classification, in which we wish to refine already trained models to learn new sound classes. In practice one does not want to maintain all past training data and retrain from scratch, but naively updating a model with new data(sets) results in a degradation of already learned tasks, which is referred to as \"catastrophic forgetting.\" We develop a generative replay procedure for generating training"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.00654","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":""},"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":"1906.00654","created_at":"2026-05-17T23:44:24.229085+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.00654v1","created_at":"2026-05-17T23:44:24.229085+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.00654","created_at":"2026-05-17T23:44:24.229085+00:00"},{"alias_kind":"pith_short_12","alias_value":"RPDJMICBKHFS","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_16","alias_value":"RPDJMICBKHFSPGD3","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_8","alias_value":"RPDJMICB","created_at":"2026-05-18T12:33:27.125529+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/RPDJMICBKHFSPGD3JWJA67QR4H","json":"https://pith.science/pith/RPDJMICBKHFSPGD3JWJA67QR4H.json","graph_json":"https://pith.science/api/pith-number/RPDJMICBKHFSPGD3JWJA67QR4H/graph.json","events_json":"https://pith.science/api/pith-number/RPDJMICBKHFSPGD3JWJA67QR4H/events.json","paper":"https://pith.science/paper/RPDJMICB"},"agent_actions":{"view_html":"https://pith.science/pith/RPDJMICBKHFSPGD3JWJA67QR4H","download_json":"https://pith.science/pith/RPDJMICBKHFSPGD3JWJA67QR4H.json","view_paper":"https://pith.science/paper/RPDJMICB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.00654&json=true","fetch_graph":"https://pith.science/api/pith-number/RPDJMICBKHFSPGD3JWJA67QR4H/graph.json","fetch_events":"https://pith.science/api/pith-number/RPDJMICBKHFSPGD3JWJA67QR4H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RPDJMICBKHFSPGD3JWJA67QR4H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RPDJMICBKHFSPGD3JWJA67QR4H/action/storage_attestation","attest_author":"https://pith.science/pith/RPDJMICBKHFSPGD3JWJA67QR4H/action/author_attestation","sign_citation":"https://pith.science/pith/RPDJMICBKHFSPGD3JWJA67QR4H/action/citation_signature","submit_replication":"https://pith.science/pith/RPDJMICBKHFSPGD3JWJA67QR4H/action/replication_record"}},"created_at":"2026-05-17T23:44:24.229085+00:00","updated_at":"2026-05-17T23:44:24.229085+00:00"}