{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:VA5FQIP4ZDFKNLPXB2LMKBLSHA","short_pith_number":"pith:VA5FQIP4","schema_version":"1.0","canonical_sha256":"a83a5821fcc8caa6adf70e96c505723808f24ebf5e2bfc9b26c4712c6038896b","source":{"kind":"arxiv","id":"1611.04122","version":1},"attestation_state":"computed","paper":{"title":"Cross-lingual Dataless Classification for Languages with Small Wikipedia Presence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dan Roth, Stephen Mayhew, Yangqiu Song","submitted_at":"2016-11-13T12:20:33Z","abstract_excerpt":"This paper presents an approach to classify documents in any language into an English topical label space, without any text categorization training data. The approach, Cross-Lingual Dataless Document Classification (CLDDC) relies on mapping the English labels or short category description into a Wikipedia-based semantic representation, and on the use of the target language Wikipedia. Consequently, performance could suffer when Wikipedia in the target language is small. In this paper, we focus on languages with small Wikipedias, (Small-Wikipedia languages, SWLs). We use a word-level dictionary "},"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":"1611.04122","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-11-13T12:20:33Z","cross_cats_sorted":[],"title_canon_sha256":"8d10c5a0640748fd07d52a40ed47255737e56f54b61b49659095d1bb35dba413","abstract_canon_sha256":"eea541cfc471a812a0746fe0b945097b709f78eaa0c1bffd907dfe00b6a36590"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:59:17.481081Z","signature_b64":"CaAa4dmrxLxM+QEA1jyDK7E2PnhryG2WUiSPreWat9evzE9KjXW+uSsso779BgpTpvd0kho9k7B8JorSERPeBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a83a5821fcc8caa6adf70e96c505723808f24ebf5e2bfc9b26c4712c6038896b","last_reissued_at":"2026-05-18T00:59:17.480456Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:59:17.480456Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross-lingual Dataless Classification for Languages with Small Wikipedia Presence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dan Roth, Stephen Mayhew, Yangqiu Song","submitted_at":"2016-11-13T12:20:33Z","abstract_excerpt":"This paper presents an approach to classify documents in any language into an English topical label space, without any text categorization training data. The approach, Cross-Lingual Dataless Document Classification (CLDDC) relies on mapping the English labels or short category description into a Wikipedia-based semantic representation, and on the use of the target language Wikipedia. Consequently, performance could suffer when Wikipedia in the target language is small. In this paper, we focus on languages with small Wikipedias, (Small-Wikipedia languages, SWLs). We use a word-level dictionary "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.04122","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":""},"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":"1611.04122","created_at":"2026-05-18T00:59:17.480537+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.04122v1","created_at":"2026-05-18T00:59:17.480537+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.04122","created_at":"2026-05-18T00:59:17.480537+00:00"},{"alias_kind":"pith_short_12","alias_value":"VA5FQIP4ZDFK","created_at":"2026-05-18T12:30:48.956258+00:00"},{"alias_kind":"pith_short_16","alias_value":"VA5FQIP4ZDFKNLPX","created_at":"2026-05-18T12:30:48.956258+00:00"},{"alias_kind":"pith_short_8","alias_value":"VA5FQIP4","created_at":"2026-05-18T12:30:48.956258+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/VA5FQIP4ZDFKNLPXB2LMKBLSHA","json":"https://pith.science/pith/VA5FQIP4ZDFKNLPXB2LMKBLSHA.json","graph_json":"https://pith.science/api/pith-number/VA5FQIP4ZDFKNLPXB2LMKBLSHA/graph.json","events_json":"https://pith.science/api/pith-number/VA5FQIP4ZDFKNLPXB2LMKBLSHA/events.json","paper":"https://pith.science/paper/VA5FQIP4"},"agent_actions":{"view_html":"https://pith.science/pith/VA5FQIP4ZDFKNLPXB2LMKBLSHA","download_json":"https://pith.science/pith/VA5FQIP4ZDFKNLPXB2LMKBLSHA.json","view_paper":"https://pith.science/paper/VA5FQIP4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.04122&json=true","fetch_graph":"https://pith.science/api/pith-number/VA5FQIP4ZDFKNLPXB2LMKBLSHA/graph.json","fetch_events":"https://pith.science/api/pith-number/VA5FQIP4ZDFKNLPXB2LMKBLSHA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VA5FQIP4ZDFKNLPXB2LMKBLSHA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VA5FQIP4ZDFKNLPXB2LMKBLSHA/action/storage_attestation","attest_author":"https://pith.science/pith/VA5FQIP4ZDFKNLPXB2LMKBLSHA/action/author_attestation","sign_citation":"https://pith.science/pith/VA5FQIP4ZDFKNLPXB2LMKBLSHA/action/citation_signature","submit_replication":"https://pith.science/pith/VA5FQIP4ZDFKNLPXB2LMKBLSHA/action/replication_record"}},"created_at":"2026-05-18T00:59:17.480537+00:00","updated_at":"2026-05-18T00:59:17.480537+00:00"}