{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PGN56X2FPLSK2X7TCSSPDH6ATZ","short_pith_number":"pith:PGN56X2F","schema_version":"1.0","canonical_sha256":"799bdf5f457ae4ad5ff314a4f19fc09e55eaab5ad615b6c93154d98e5fc8b5ff","source":{"kind":"arxiv","id":"2502.00305","version":1},"attestation_state":"computed","paper":{"title":"DEUCE: Dual-diversity Enhancement and Uncertainty-awareness for Cold-start Active Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"C. L. Philip Chen, Jiaxin Guo, Shuzhen Li, Tong Zhang","submitted_at":"2025-02-01T04:00:03Z","abstract_excerpt":"Cold-start active learning (CSAL) selects valuable instances from an unlabeled dataset for manual annotation. It provides high-quality data at a low annotation cost for label-scarce text classification. However, existing CSAL methods overlook weak classes and hard representative examples, resulting in biased learning. To address these issues, this paper proposes a novel dual-diversity enhancing and uncertainty-aware (DEUCE) framework for CSAL. Specifically, DEUCE leverages a pretrained language model (PLM) to efficiently extract textual representations, class predictions, and predictive uncert"},"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":"2502.00305","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-01T04:00:03Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"92092803db219d73027323940e39afced90197774a1fac222f53938b9eff8d46","abstract_canon_sha256":"5cf153db1cc8c7603fafb40745d3ae5fee6f911d29b62f0935260c86311159bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:08:31.851580Z","signature_b64":"GJuH16g1cJ5IueoGuBgw2f+iC/W1uoaIWo0SBVWLK4BgNeJyrEJALRc0bJtUyYXo4H3ebpIzEfVWxsWtBuweAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"799bdf5f457ae4ad5ff314a4f19fc09e55eaab5ad615b6c93154d98e5fc8b5ff","last_reissued_at":"2026-07-05T10:08:31.851134Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:08:31.851134Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DEUCE: Dual-diversity Enhancement and Uncertainty-awareness for Cold-start Active Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"C. L. Philip Chen, Jiaxin Guo, Shuzhen Li, Tong Zhang","submitted_at":"2025-02-01T04:00:03Z","abstract_excerpt":"Cold-start active learning (CSAL) selects valuable instances from an unlabeled dataset for manual annotation. It provides high-quality data at a low annotation cost for label-scarce text classification. However, existing CSAL methods overlook weak classes and hard representative examples, resulting in biased learning. To address these issues, this paper proposes a novel dual-diversity enhancing and uncertainty-aware (DEUCE) framework for CSAL. Specifically, DEUCE leverages a pretrained language model (PLM) to efficiently extract textual representations, class predictions, and predictive uncert"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.00305","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/2502.00305/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":"2502.00305","created_at":"2026-07-05T10:08:31.851193+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.00305v1","created_at":"2026-07-05T10:08:31.851193+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.00305","created_at":"2026-07-05T10:08:31.851193+00:00"},{"alias_kind":"pith_short_12","alias_value":"PGN56X2FPLSK","created_at":"2026-07-05T10:08:31.851193+00:00"},{"alias_kind":"pith_short_16","alias_value":"PGN56X2FPLSK2X7T","created_at":"2026-07-05T10:08:31.851193+00:00"},{"alias_kind":"pith_short_8","alias_value":"PGN56X2F","created_at":"2026-07-05T10:08:31.851193+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/PGN56X2FPLSK2X7TCSSPDH6ATZ","json":"https://pith.science/pith/PGN56X2FPLSK2X7TCSSPDH6ATZ.json","graph_json":"https://pith.science/api/pith-number/PGN56X2FPLSK2X7TCSSPDH6ATZ/graph.json","events_json":"https://pith.science/api/pith-number/PGN56X2FPLSK2X7TCSSPDH6ATZ/events.json","paper":"https://pith.science/paper/PGN56X2F"},"agent_actions":{"view_html":"https://pith.science/pith/PGN56X2FPLSK2X7TCSSPDH6ATZ","download_json":"https://pith.science/pith/PGN56X2FPLSK2X7TCSSPDH6ATZ.json","view_paper":"https://pith.science/paper/PGN56X2F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.00305&json=true","fetch_graph":"https://pith.science/api/pith-number/PGN56X2FPLSK2X7TCSSPDH6ATZ/graph.json","fetch_events":"https://pith.science/api/pith-number/PGN56X2FPLSK2X7TCSSPDH6ATZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PGN56X2FPLSK2X7TCSSPDH6ATZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PGN56X2FPLSK2X7TCSSPDH6ATZ/action/storage_attestation","attest_author":"https://pith.science/pith/PGN56X2FPLSK2X7TCSSPDH6ATZ/action/author_attestation","sign_citation":"https://pith.science/pith/PGN56X2FPLSK2X7TCSSPDH6ATZ/action/citation_signature","submit_replication":"https://pith.science/pith/PGN56X2FPLSK2X7TCSSPDH6ATZ/action/replication_record"}},"created_at":"2026-07-05T10:08:31.851193+00:00","updated_at":"2026-07-05T10:08:31.851193+00:00"}