{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:H6WG4OFMQ5M62B22ES3EESEUB6","short_pith_number":"pith:H6WG4OFM","schema_version":"1.0","canonical_sha256":"3fac6e38ac8759ed075a24b64248940f9e6904b4db2dd62bf0c07c931fea551a","source":{"kind":"arxiv","id":"2112.02995","version":1},"attestation_state":"computed","paper":{"title":"TaskDrop: A Competitive Baseline for Continual Learning of Sentiment Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jianping Mei, Qianwei Zhou, Rui Yan, Yilun Zheng","submitted_at":"2021-11-05T15:32:23Z","abstract_excerpt":"In this paper, we study the multi-task sentiment classification problem in the continual learning setting, i.e., a model is sequentially trained to classifier the sentiment of reviews of products in a particular category. The use of common sentiment words in reviews of different product categories leads to large cross-task similarity, which differentiates it from continual learning in other domains. This knowledge sharing nature renders forgetting reduction focused approaches less effective for the problem under consideration. Unlike existing approaches, where task-specific masks are learned w"},"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":"2112.02995","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-11-05T15:32:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2f11cb283ce90e28428e5e15267a411d3729cd605dc0de1b5e483eb5c2680f4d","abstract_canon_sha256":"02bbfa585b88c881e2aa6b7188c224792326a26b456cafef69af78e558bdede6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:38:00.314463Z","signature_b64":"DnwWyyBzTPyPKC/8ojXrrO9B28+s6I7mI8VIYzo+FYXC7jxA7jVh4pO4fm23IlQlBEuKM/R4ilLzAHqsRISuCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3fac6e38ac8759ed075a24b64248940f9e6904b4db2dd62bf0c07c931fea551a","last_reissued_at":"2026-07-05T03:38:00.313995Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:38:00.313995Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TaskDrop: A Competitive Baseline for Continual Learning of Sentiment Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jianping Mei, Qianwei Zhou, Rui Yan, Yilun Zheng","submitted_at":"2021-11-05T15:32:23Z","abstract_excerpt":"In this paper, we study the multi-task sentiment classification problem in the continual learning setting, i.e., a model is sequentially trained to classifier the sentiment of reviews of products in a particular category. The use of common sentiment words in reviews of different product categories leads to large cross-task similarity, which differentiates it from continual learning in other domains. This knowledge sharing nature renders forgetting reduction focused approaches less effective for the problem under consideration. Unlike existing approaches, where task-specific masks are learned w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.02995","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/2112.02995/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":"2112.02995","created_at":"2026-07-05T03:38:00.314051+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.02995v1","created_at":"2026-07-05T03:38:00.314051+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.02995","created_at":"2026-07-05T03:38:00.314051+00:00"},{"alias_kind":"pith_short_12","alias_value":"H6WG4OFMQ5M6","created_at":"2026-07-05T03:38:00.314051+00:00"},{"alias_kind":"pith_short_16","alias_value":"H6WG4OFMQ5M62B22","created_at":"2026-07-05T03:38:00.314051+00:00"},{"alias_kind":"pith_short_8","alias_value":"H6WG4OFM","created_at":"2026-07-05T03:38:00.314051+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/H6WG4OFMQ5M62B22ES3EESEUB6","json":"https://pith.science/pith/H6WG4OFMQ5M62B22ES3EESEUB6.json","graph_json":"https://pith.science/api/pith-number/H6WG4OFMQ5M62B22ES3EESEUB6/graph.json","events_json":"https://pith.science/api/pith-number/H6WG4OFMQ5M62B22ES3EESEUB6/events.json","paper":"https://pith.science/paper/H6WG4OFM"},"agent_actions":{"view_html":"https://pith.science/pith/H6WG4OFMQ5M62B22ES3EESEUB6","download_json":"https://pith.science/pith/H6WG4OFMQ5M62B22ES3EESEUB6.json","view_paper":"https://pith.science/paper/H6WG4OFM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.02995&json=true","fetch_graph":"https://pith.science/api/pith-number/H6WG4OFMQ5M62B22ES3EESEUB6/graph.json","fetch_events":"https://pith.science/api/pith-number/H6WG4OFMQ5M62B22ES3EESEUB6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H6WG4OFMQ5M62B22ES3EESEUB6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H6WG4OFMQ5M62B22ES3EESEUB6/action/storage_attestation","attest_author":"https://pith.science/pith/H6WG4OFMQ5M62B22ES3EESEUB6/action/author_attestation","sign_citation":"https://pith.science/pith/H6WG4OFMQ5M62B22ES3EESEUB6/action/citation_signature","submit_replication":"https://pith.science/pith/H6WG4OFMQ5M62B22ES3EESEUB6/action/replication_record"}},"created_at":"2026-07-05T03:38:00.314051+00:00","updated_at":"2026-07-05T03:38:00.314051+00:00"}