{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QQP6G32XZPITKCDZB5UUST6ANJ","short_pith_number":"pith:QQP6G32X","schema_version":"1.0","canonical_sha256":"841fe36f57cbd13508790f69494fc06a7119e772441d44bdb0e7c9b5813a6830","source":{"kind":"arxiv","id":"2406.07331","version":1},"attestation_state":"computed","paper":{"title":"Text Information Retrieval in Tetun: A Preliminary Study","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Gabriel de Jesus","submitted_at":"2024-06-11T15:01:03Z","abstract_excerpt":"Tetun is one of Timor-Leste's official languages alongside Portuguese. It is a low-resource language with over 932,400 speakers that started developing when Timor-Leste restored its independence in 2002. The media mainly uses Tetun, and more than ten national online newspapers actively broadcast news in Tetun every day. However, since information retrieval-based solutions for Tetun do not exist, finding Tetun information on the internet is challenging. This work aims to investigate and develop solutions that can enable the application of information retrieval techniques to develop search solut"},"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":"2406.07331","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-06-11T15:01:03Z","cross_cats_sorted":[],"title_canon_sha256":"de917c49f8708450106be56272759d29e7247d458c91d418ea41656407bb75c1","abstract_canon_sha256":"dd4b0c0471a17c0d4d908df47a009f67f8a2be3e4a5dc4f3fd25200d15496932"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:30:21.714819Z","signature_b64":"NWGbMtnoweti/guozJPSt+CLQWoogZekxDnC02eNvGHjk4ov1NnGtaN5ukGuBuE1WBygM1GqPYMdUjcBV5WkBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"841fe36f57cbd13508790f69494fc06a7119e772441d44bdb0e7c9b5813a6830","last_reissued_at":"2026-07-05T08:30:21.714226Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:30:21.714226Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Text Information Retrieval in Tetun: A Preliminary Study","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Gabriel de Jesus","submitted_at":"2024-06-11T15:01:03Z","abstract_excerpt":"Tetun is one of Timor-Leste's official languages alongside Portuguese. It is a low-resource language with over 932,400 speakers that started developing when Timor-Leste restored its independence in 2002. The media mainly uses Tetun, and more than ten national online newspapers actively broadcast news in Tetun every day. However, since information retrieval-based solutions for Tetun do not exist, finding Tetun information on the internet is challenging. This work aims to investigate and develop solutions that can enable the application of information retrieval techniques to develop search solut"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07331","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/2406.07331/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":"2406.07331","created_at":"2026-07-05T08:30:21.714303+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.07331v1","created_at":"2026-07-05T08:30:21.714303+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07331","created_at":"2026-07-05T08:30:21.714303+00:00"},{"alias_kind":"pith_short_12","alias_value":"QQP6G32XZPIT","created_at":"2026-07-05T08:30:21.714303+00:00"},{"alias_kind":"pith_short_16","alias_value":"QQP6G32XZPITKCDZ","created_at":"2026-07-05T08:30:21.714303+00:00"},{"alias_kind":"pith_short_8","alias_value":"QQP6G32X","created_at":"2026-07-05T08:30:21.714303+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.12262","citing_title":"Low-resource Machine Translation: what for? who for? An observational study on a dedicated Tetun language translation service","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QQP6G32XZPITKCDZB5UUST6ANJ","json":"https://pith.science/pith/QQP6G32XZPITKCDZB5UUST6ANJ.json","graph_json":"https://pith.science/api/pith-number/QQP6G32XZPITKCDZB5UUST6ANJ/graph.json","events_json":"https://pith.science/api/pith-number/QQP6G32XZPITKCDZB5UUST6ANJ/events.json","paper":"https://pith.science/paper/QQP6G32X"},"agent_actions":{"view_html":"https://pith.science/pith/QQP6G32XZPITKCDZB5UUST6ANJ","download_json":"https://pith.science/pith/QQP6G32XZPITKCDZB5UUST6ANJ.json","view_paper":"https://pith.science/paper/QQP6G32X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.07331&json=true","fetch_graph":"https://pith.science/api/pith-number/QQP6G32XZPITKCDZB5UUST6ANJ/graph.json","fetch_events":"https://pith.science/api/pith-number/QQP6G32XZPITKCDZB5UUST6ANJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QQP6G32XZPITKCDZB5UUST6ANJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QQP6G32XZPITKCDZB5UUST6ANJ/action/storage_attestation","attest_author":"https://pith.science/pith/QQP6G32XZPITKCDZB5UUST6ANJ/action/author_attestation","sign_citation":"https://pith.science/pith/QQP6G32XZPITKCDZB5UUST6ANJ/action/citation_signature","submit_replication":"https://pith.science/pith/QQP6G32XZPITKCDZB5UUST6ANJ/action/replication_record"}},"created_at":"2026-07-05T08:30:21.714303+00:00","updated_at":"2026-07-05T08:30:21.714303+00:00"}