{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GXZVIZYVES34MW3MO5CC3M6QXV","short_pith_number":"pith:GXZVIZYV","schema_version":"1.0","canonical_sha256":"35f354671524b7c65b6c77442db3d0bd7493630012db48c31e790f2c6a7b0fe2","source":{"kind":"arxiv","id":"2405.10992","version":1},"attestation_state":"computed","paper":{"title":"Overcoming Catastrophic Forgetting by Exemplar Selection in Task-oriented Dialogue System","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chen Chen, Chengwei Qin, Qiang Zhang, Ruizhe Li, Yuanyuan Chen, Yuchen Hu","submitted_at":"2024-05-16T10:54:46Z","abstract_excerpt":"Intelligent task-oriented dialogue systems (ToDs) are expected to continuously acquire new knowledge, also known as Continual Learning (CL), which is crucial to fit ever-changing user needs. However, catastrophic forgetting dramatically degrades the model performance in face of a long streamed curriculum. In this paper, we aim to overcome the forgetting problem in ToDs and propose a method (HESIT) with hyper-gradient-based exemplar strategy, which samples influential exemplars for periodic retraining. Instead of unilaterally observing data or models, HESIT adopts a profound exemplar selection "},"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":"2405.10992","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-16T10:54:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f3f3628be4a41ade62aa50f2d101e6cc997567caf23d04c0e4e21a87bf74260d","abstract_canon_sha256":"33df8630d09b238367f70ce1ff02b3f853d42a35eaf445e036e5e1609b6d3352"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:20:31.237164Z","signature_b64":"lZ5w4Lho+CXAOb4WHO8tX5xc/cugsg+PUKFpyUf0UU+XaE35UI22kRvWqlbvEhDi/aZA0cXa6RQwh69hMpV5Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35f354671524b7c65b6c77442db3d0bd7493630012db48c31e790f2c6a7b0fe2","last_reissued_at":"2026-07-05T08:20:31.236650Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:20:31.236650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Overcoming Catastrophic Forgetting by Exemplar Selection in Task-oriented Dialogue System","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chen Chen, Chengwei Qin, Qiang Zhang, Ruizhe Li, Yuanyuan Chen, Yuchen Hu","submitted_at":"2024-05-16T10:54:46Z","abstract_excerpt":"Intelligent task-oriented dialogue systems (ToDs) are expected to continuously acquire new knowledge, also known as Continual Learning (CL), which is crucial to fit ever-changing user needs. However, catastrophic forgetting dramatically degrades the model performance in face of a long streamed curriculum. In this paper, we aim to overcome the forgetting problem in ToDs and propose a method (HESIT) with hyper-gradient-based exemplar strategy, which samples influential exemplars for periodic retraining. Instead of unilaterally observing data or models, HESIT adopts a profound exemplar selection "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.10992","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/2405.10992/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":"2405.10992","created_at":"2026-07-05T08:20:31.236714+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.10992v1","created_at":"2026-07-05T08:20:31.236714+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.10992","created_at":"2026-07-05T08:20:31.236714+00:00"},{"alias_kind":"pith_short_12","alias_value":"GXZVIZYVES34","created_at":"2026-07-05T08:20:31.236714+00:00"},{"alias_kind":"pith_short_16","alias_value":"GXZVIZYVES34MW3M","created_at":"2026-07-05T08:20:31.236714+00:00"},{"alias_kind":"pith_short_8","alias_value":"GXZVIZYV","created_at":"2026-07-05T08:20:31.236714+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/GXZVIZYVES34MW3MO5CC3M6QXV","json":"https://pith.science/pith/GXZVIZYVES34MW3MO5CC3M6QXV.json","graph_json":"https://pith.science/api/pith-number/GXZVIZYVES34MW3MO5CC3M6QXV/graph.json","events_json":"https://pith.science/api/pith-number/GXZVIZYVES34MW3MO5CC3M6QXV/events.json","paper":"https://pith.science/paper/GXZVIZYV"},"agent_actions":{"view_html":"https://pith.science/pith/GXZVIZYVES34MW3MO5CC3M6QXV","download_json":"https://pith.science/pith/GXZVIZYVES34MW3MO5CC3M6QXV.json","view_paper":"https://pith.science/paper/GXZVIZYV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.10992&json=true","fetch_graph":"https://pith.science/api/pith-number/GXZVIZYVES34MW3MO5CC3M6QXV/graph.json","fetch_events":"https://pith.science/api/pith-number/GXZVIZYVES34MW3MO5CC3M6QXV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GXZVIZYVES34MW3MO5CC3M6QXV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GXZVIZYVES34MW3MO5CC3M6QXV/action/storage_attestation","attest_author":"https://pith.science/pith/GXZVIZYVES34MW3MO5CC3M6QXV/action/author_attestation","sign_citation":"https://pith.science/pith/GXZVIZYVES34MW3MO5CC3M6QXV/action/citation_signature","submit_replication":"https://pith.science/pith/GXZVIZYVES34MW3MO5CC3M6QXV/action/replication_record"}},"created_at":"2026-07-05T08:20:31.236714+00:00","updated_at":"2026-07-05T08:20:31.236714+00:00"}