{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:VKJPPWRJD64ZTGALCVHEO6U2NA","short_pith_number":"pith:VKJPPWRJ","schema_version":"1.0","canonical_sha256":"aa92f7da291fb999980b154e477a9a68334089cfc5c66bcacd4c522b7546a31b","source":{"kind":"arxiv","id":"2112.10021","version":1},"attestation_state":"computed","paper":{"title":"Continual Learning with Knowledge Transfer for Sentiment Classification","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.NE"],"primary_cat":"cs.CL","authors_text":"Bing Liu, Hao Wang, Lei Shu, Zixuan Ke","submitted_at":"2021-12-18T22:58:21Z","abstract_excerpt":"This paper studies continual learning (CL) for sentiment classification (SC). In this setting, the CL system learns a sequence of SC tasks incrementally in a neural network, where each task builds a classifier to classify the sentiment of reviews of a particular product category or domain. Two natural questions are: Can the system transfer the knowledge learned in the past from the previous tasks to the new task to help it learn a better model for the new task? And, can old models for previous tasks be improved in the process as well? This paper proposes a novel technique called KAN to achieve"},"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":"2112.10021","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-18T22:58:21Z","cross_cats_sorted":["cs.AI","cs.LG","cs.NE"],"title_canon_sha256":"f3f7ace8ea9c314d25513825e00aef6964fd7dac203a9c37610e8cdbaf9576ec","abstract_canon_sha256":"4b0d74d3c8c2ce09fbea53c3e39064fa6e0e83c7c64bdf9ebbb7eb1d2b4c7731"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:42:10.246094Z","signature_b64":"r6/RtmX1AGs2wL+gdfVqpT+nW3+8MkM+K9i2e6az+A3UWahdyRxlFdRdD78MRYbDtGp1g4d5hbR4x1MBfhySAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa92f7da291fb999980b154e477a9a68334089cfc5c66bcacd4c522b7546a31b","last_reissued_at":"2026-07-05T03:42:10.245672Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:42:10.245672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Continual Learning with Knowledge Transfer for Sentiment Classification","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.NE"],"primary_cat":"cs.CL","authors_text":"Bing Liu, Hao Wang, Lei Shu, Zixuan Ke","submitted_at":"2021-12-18T22:58:21Z","abstract_excerpt":"This paper studies continual learning (CL) for sentiment classification (SC). In this setting, the CL system learns a sequence of SC tasks incrementally in a neural network, where each task builds a classifier to classify the sentiment of reviews of a particular product category or domain. Two natural questions are: Can the system transfer the knowledge learned in the past from the previous tasks to the new task to help it learn a better model for the new task? And, can old models for previous tasks be improved in the process as well? This paper proposes a novel technique called KAN to achieve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.10021","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/2112.10021/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":"2112.10021","created_at":"2026-07-05T03:42:10.245738+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.10021v1","created_at":"2026-07-05T03:42:10.245738+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.10021","created_at":"2026-07-05T03:42:10.245738+00:00"},{"alias_kind":"pith_short_12","alias_value":"VKJPPWRJD64Z","created_at":"2026-07-05T03:42:10.245738+00:00"},{"alias_kind":"pith_short_16","alias_value":"VKJPPWRJD64ZTGAL","created_at":"2026-07-05T03:42:10.245738+00:00"},{"alias_kind":"pith_short_8","alias_value":"VKJPPWRJ","created_at":"2026-07-05T03:42:10.245738+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/VKJPPWRJD64ZTGALCVHEO6U2NA","json":"https://pith.science/pith/VKJPPWRJD64ZTGALCVHEO6U2NA.json","graph_json":"https://pith.science/api/pith-number/VKJPPWRJD64ZTGALCVHEO6U2NA/graph.json","events_json":"https://pith.science/api/pith-number/VKJPPWRJD64ZTGALCVHEO6U2NA/events.json","paper":"https://pith.science/paper/VKJPPWRJ"},"agent_actions":{"view_html":"https://pith.science/pith/VKJPPWRJD64ZTGALCVHEO6U2NA","download_json":"https://pith.science/pith/VKJPPWRJD64ZTGALCVHEO6U2NA.json","view_paper":"https://pith.science/paper/VKJPPWRJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.10021&json=true","fetch_graph":"https://pith.science/api/pith-number/VKJPPWRJD64ZTGALCVHEO6U2NA/graph.json","fetch_events":"https://pith.science/api/pith-number/VKJPPWRJD64ZTGALCVHEO6U2NA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VKJPPWRJD64ZTGALCVHEO6U2NA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VKJPPWRJD64ZTGALCVHEO6U2NA/action/storage_attestation","attest_author":"https://pith.science/pith/VKJPPWRJD64ZTGALCVHEO6U2NA/action/author_attestation","sign_citation":"https://pith.science/pith/VKJPPWRJD64ZTGALCVHEO6U2NA/action/citation_signature","submit_replication":"https://pith.science/pith/VKJPPWRJD64ZTGALCVHEO6U2NA/action/replication_record"}},"created_at":"2026-07-05T03:42:10.245738+00:00","updated_at":"2026-07-05T03:42:10.245738+00:00"}