{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:XTIYPLVL3V42IDZL72KUP235QD","short_pith_number":"pith:XTIYPLVL","schema_version":"1.0","canonical_sha256":"bcd187aeabdd79a40f2bfe9547eb7d80dfc90ede4d2e2420561a317ecb436730","source":{"kind":"arxiv","id":"1712.09943","version":3},"attestation_state":"computed","paper":{"title":"Toward Continual Learning for Conversational Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CL","authors_text":"Sungjin Lee","submitted_at":"2017-12-28T17:21:42Z","abstract_excerpt":"While end-to-end neural conversation models have led to promising advances in reducing hand-crafted features and errors induced by the traditional complex system architecture, they typically require an enormous amount of data due to the lack of modularity. Previous studies adopted a hybrid approach with knowledge-based components either to abstract out domain-specific information or to augment data to cover more diverse patterns. On the contrary, we propose to directly address the problem using recent developments in the space of continual learning for neural models. Specifically, we adopt a d"},"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":"1712.09943","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-12-28T17:21:42Z","cross_cats_sorted":["cs.AI","cs.HC"],"title_canon_sha256":"8b0104bd7f3ac8484fc5f1265d74e5cd7595a3ad5f97c5fa88ce410686f239a1","abstract_canon_sha256":"75a549f7827d0c454ab3fd06537057e46294661cea148fbb81a56b515b0c3de4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:26:23.146689Z","signature_b64":"xb+g4N2xnz1cDs/OAYeCOyAy9OBiNEOiTAhj8UGBx99IB8wsdS9fvxM3CvruH5LXCyO+6/tNT3EAU4ZelBi7Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bcd187aeabdd79a40f2bfe9547eb7d80dfc90ede4d2e2420561a317ecb436730","last_reissued_at":"2026-05-18T00:26:23.146015Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:26:23.146015Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Toward Continual Learning for Conversational Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CL","authors_text":"Sungjin Lee","submitted_at":"2017-12-28T17:21:42Z","abstract_excerpt":"While end-to-end neural conversation models have led to promising advances in reducing hand-crafted features and errors induced by the traditional complex system architecture, they typically require an enormous amount of data due to the lack of modularity. Previous studies adopted a hybrid approach with knowledge-based components either to abstract out domain-specific information or to augment data to cover more diverse patterns. On the contrary, we propose to directly address the problem using recent developments in the space of continual learning for neural models. Specifically, we adopt a d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.09943","kind":"arxiv","version":3},"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":"1712.09943","created_at":"2026-05-18T00:26:23.146127+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.09943v3","created_at":"2026-05-18T00:26:23.146127+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.09943","created_at":"2026-05-18T00:26:23.146127+00:00"},{"alias_kind":"pith_short_12","alias_value":"XTIYPLVL3V42","created_at":"2026-05-18T12:31:56.362134+00:00"},{"alias_kind":"pith_short_16","alias_value":"XTIYPLVL3V42IDZL","created_at":"2026-05-18T12:31:56.362134+00:00"},{"alias_kind":"pith_short_8","alias_value":"XTIYPLVL","created_at":"2026-05-18T12:31:56.362134+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2403.14608","citing_title":"Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey","ref_index":167,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XTIYPLVL3V42IDZL72KUP235QD","json":"https://pith.science/pith/XTIYPLVL3V42IDZL72KUP235QD.json","graph_json":"https://pith.science/api/pith-number/XTIYPLVL3V42IDZL72KUP235QD/graph.json","events_json":"https://pith.science/api/pith-number/XTIYPLVL3V42IDZL72KUP235QD/events.json","paper":"https://pith.science/paper/XTIYPLVL"},"agent_actions":{"view_html":"https://pith.science/pith/XTIYPLVL3V42IDZL72KUP235QD","download_json":"https://pith.science/pith/XTIYPLVL3V42IDZL72KUP235QD.json","view_paper":"https://pith.science/paper/XTIYPLVL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.09943&json=true","fetch_graph":"https://pith.science/api/pith-number/XTIYPLVL3V42IDZL72KUP235QD/graph.json","fetch_events":"https://pith.science/api/pith-number/XTIYPLVL3V42IDZL72KUP235QD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XTIYPLVL3V42IDZL72KUP235QD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XTIYPLVL3V42IDZL72KUP235QD/action/storage_attestation","attest_author":"https://pith.science/pith/XTIYPLVL3V42IDZL72KUP235QD/action/author_attestation","sign_citation":"https://pith.science/pith/XTIYPLVL3V42IDZL72KUP235QD/action/citation_signature","submit_replication":"https://pith.science/pith/XTIYPLVL3V42IDZL72KUP235QD/action/replication_record"}},"created_at":"2026-05-18T00:26:23.146127+00:00","updated_at":"2026-05-18T00:26:23.146127+00:00"}