{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LZGZZDNIDYUQULQRMXMLYOWUUV","short_pith_number":"pith:LZGZZDNI","schema_version":"1.0","canonical_sha256":"5e4d9c8da81e290a2e1165d8bc3ad4a5631cb44fd12100c9b8246d699b2143d5","source":{"kind":"arxiv","id":"2406.07299","version":1},"attestation_state":"computed","paper":{"title":"Exploring Large Language Models for Relevance Judgments in Tetun","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Gabriel de Jesus, S\\'ergio Nunes","submitted_at":"2024-06-11T14:28:24Z","abstract_excerpt":"The Cranfield paradigm has served as a foundational approach for developing test collections, with relevance judgments typically conducted by human assessors. However, the emergence of large language models (LLMs) has introduced new possibilities for automating these tasks. This paper explores the feasibility of using LLMs to automate relevance assessments, particularly within the context of low-resource languages. In our study, LLMs are employed to automate relevance judgment tasks, by providing a series of query-document pairs in Tetun as the input text. The models are tasked with assigning "},"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":"2406.07299","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-06-11T14:28:24Z","cross_cats_sorted":[],"title_canon_sha256":"833fadc40517391614e84b06384b9001c759d6a2d2d832987842bb60ad53a635","abstract_canon_sha256":"f590409e9f7b3a522a3ec139f3772e49eda81e4083ddf294bda967c9615cf756"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:30:21.266281Z","signature_b64":"yWPMu3asXDEiF67G6RzNIpN/vccjxVv9mm9+BEZp3oyKjZM4+4YoJgHWcCLrkED+id7DAOBePTTFA+QbYCttCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e4d9c8da81e290a2e1165d8bc3ad4a5631cb44fd12100c9b8246d699b2143d5","last_reissued_at":"2026-07-05T08:30:21.265772Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:30:21.265772Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Large Language Models for Relevance Judgments in Tetun","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Gabriel de Jesus, S\\'ergio Nunes","submitted_at":"2024-06-11T14:28:24Z","abstract_excerpt":"The Cranfield paradigm has served as a foundational approach for developing test collections, with relevance judgments typically conducted by human assessors. However, the emergence of large language models (LLMs) has introduced new possibilities for automating these tasks. This paper explores the feasibility of using LLMs to automate relevance assessments, particularly within the context of low-resource languages. In our study, LLMs are employed to automate relevance judgment tasks, by providing a series of query-document pairs in Tetun as the input text. The models are tasked with assigning "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07299","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/2406.07299/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":"2406.07299","created_at":"2026-07-05T08:30:21.265835+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.07299v1","created_at":"2026-07-05T08:30:21.265835+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07299","created_at":"2026-07-05T08:30:21.265835+00:00"},{"alias_kind":"pith_short_12","alias_value":"LZGZZDNIDYUQ","created_at":"2026-07-05T08:30:21.265835+00:00"},{"alias_kind":"pith_short_16","alias_value":"LZGZZDNIDYUQULQR","created_at":"2026-07-05T08:30:21.265835+00:00"},{"alias_kind":"pith_short_8","alias_value":"LZGZZDNI","created_at":"2026-07-05T08:30:21.265835+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.02139","citing_title":"When LLMs Disagree: Diagnosing Relevance Filtering Bias and Retrieval Divergence in SDG Search","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LZGZZDNIDYUQULQRMXMLYOWUUV","json":"https://pith.science/pith/LZGZZDNIDYUQULQRMXMLYOWUUV.json","graph_json":"https://pith.science/api/pith-number/LZGZZDNIDYUQULQRMXMLYOWUUV/graph.json","events_json":"https://pith.science/api/pith-number/LZGZZDNIDYUQULQRMXMLYOWUUV/events.json","paper":"https://pith.science/paper/LZGZZDNI"},"agent_actions":{"view_html":"https://pith.science/pith/LZGZZDNIDYUQULQRMXMLYOWUUV","download_json":"https://pith.science/pith/LZGZZDNIDYUQULQRMXMLYOWUUV.json","view_paper":"https://pith.science/paper/LZGZZDNI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.07299&json=true","fetch_graph":"https://pith.science/api/pith-number/LZGZZDNIDYUQULQRMXMLYOWUUV/graph.json","fetch_events":"https://pith.science/api/pith-number/LZGZZDNIDYUQULQRMXMLYOWUUV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LZGZZDNIDYUQULQRMXMLYOWUUV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LZGZZDNIDYUQULQRMXMLYOWUUV/action/storage_attestation","attest_author":"https://pith.science/pith/LZGZZDNIDYUQULQRMXMLYOWUUV/action/author_attestation","sign_citation":"https://pith.science/pith/LZGZZDNIDYUQULQRMXMLYOWUUV/action/citation_signature","submit_replication":"https://pith.science/pith/LZGZZDNIDYUQULQRMXMLYOWUUV/action/replication_record"}},"created_at":"2026-07-05T08:30:21.265835+00:00","updated_at":"2026-07-05T08:30:21.265835+00:00"}