{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7J2PPLM4OT6HM4G437N5PPYABD","short_pith_number":"pith:7J2PPLM4","schema_version":"1.0","canonical_sha256":"fa74f7ad9c74fc7670dcdfdbd7bf0008e65a5d98ca1896cf8b2eaf4e64b8e60f","source":{"kind":"arxiv","id":"2502.03292","version":1},"attestation_state":"computed","paper":{"title":"ALPET: Active Few-shot Learning for Citation Worthiness Detection in Low-Resource Wikipedia Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aida Halitaj, Arkaitz Zubiaga","submitted_at":"2025-02-05T15:49:41Z","abstract_excerpt":"Citation Worthiness Detection (CWD) consists in determining which sentences, within an article or collection, should be backed up with a citation to validate the information it provides. This study, introduces ALPET, a framework combining Active Learning (AL) and Pattern-Exploiting Training (PET), to enhance CWD for languages with limited data resources. Applied to Catalan, Basque, and Albanian Wikipedia datasets, ALPET outperforms the existing CCW baseline while reducing the amount of labeled data in some cases above 80\\%. ALPET's performance plateaus after 300 labeled samples, showing it sui"},"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":"2502.03292","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-05T15:49:41Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"e8a0e1154e82cef2d30f4c464a89e6d03d183d96a302eca8c07f0bc46314bbd2","abstract_canon_sha256":"df684507eac0012d7afb42007e8292a7ef17f740cd81d7a7a1bbabf6748da68a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:10:02.636877Z","signature_b64":"Pkicbls2s/jAmsnBNvUC6D8GSmAUM+cxnC493bns1t+pVvMptxB5w5iXva6f1QiQkmyNsq1v/e0s3sKOp65nDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa74f7ad9c74fc7670dcdfdbd7bf0008e65a5d98ca1896cf8b2eaf4e64b8e60f","last_reissued_at":"2026-07-05T10:10:02.636287Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:10:02.636287Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ALPET: Active Few-shot Learning for Citation Worthiness Detection in Low-Resource Wikipedia Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aida Halitaj, Arkaitz Zubiaga","submitted_at":"2025-02-05T15:49:41Z","abstract_excerpt":"Citation Worthiness Detection (CWD) consists in determining which sentences, within an article or collection, should be backed up with a citation to validate the information it provides. This study, introduces ALPET, a framework combining Active Learning (AL) and Pattern-Exploiting Training (PET), to enhance CWD for languages with limited data resources. Applied to Catalan, Basque, and Albanian Wikipedia datasets, ALPET outperforms the existing CCW baseline while reducing the amount of labeled data in some cases above 80\\%. ALPET's performance plateaus after 300 labeled samples, showing it sui"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.03292","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/2502.03292/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":"2502.03292","created_at":"2026-07-05T10:10:02.636384+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.03292v1","created_at":"2026-07-05T10:10:02.636384+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.03292","created_at":"2026-07-05T10:10:02.636384+00:00"},{"alias_kind":"pith_short_12","alias_value":"7J2PPLM4OT6H","created_at":"2026-07-05T10:10:02.636384+00:00"},{"alias_kind":"pith_short_16","alias_value":"7J2PPLM4OT6HM4G4","created_at":"2026-07-05T10:10:02.636384+00:00"},{"alias_kind":"pith_short_8","alias_value":"7J2PPLM4","created_at":"2026-07-05T10:10:02.636384+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/7J2PPLM4OT6HM4G437N5PPYABD","json":"https://pith.science/pith/7J2PPLM4OT6HM4G437N5PPYABD.json","graph_json":"https://pith.science/api/pith-number/7J2PPLM4OT6HM4G437N5PPYABD/graph.json","events_json":"https://pith.science/api/pith-number/7J2PPLM4OT6HM4G437N5PPYABD/events.json","paper":"https://pith.science/paper/7J2PPLM4"},"agent_actions":{"view_html":"https://pith.science/pith/7J2PPLM4OT6HM4G437N5PPYABD","download_json":"https://pith.science/pith/7J2PPLM4OT6HM4G437N5PPYABD.json","view_paper":"https://pith.science/paper/7J2PPLM4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.03292&json=true","fetch_graph":"https://pith.science/api/pith-number/7J2PPLM4OT6HM4G437N5PPYABD/graph.json","fetch_events":"https://pith.science/api/pith-number/7J2PPLM4OT6HM4G437N5PPYABD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7J2PPLM4OT6HM4G437N5PPYABD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7J2PPLM4OT6HM4G437N5PPYABD/action/storage_attestation","attest_author":"https://pith.science/pith/7J2PPLM4OT6HM4G437N5PPYABD/action/author_attestation","sign_citation":"https://pith.science/pith/7J2PPLM4OT6HM4G437N5PPYABD/action/citation_signature","submit_replication":"https://pith.science/pith/7J2PPLM4OT6HM4G437N5PPYABD/action/replication_record"}},"created_at":"2026-07-05T10:10:02.636384+00:00","updated_at":"2026-07-05T10:10:02.636384+00:00"}