{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:X64VIAD7UWR4S42SH6KL3DBRS2","short_pith_number":"pith:X64VIAD7","schema_version":"1.0","canonical_sha256":"bfb954007fa5a3c973523f94bd8c319683c8723e7ef364d124dde61a62242c85","source":{"kind":"arxiv","id":"2502.07131","version":3},"attestation_state":"computed","paper":{"title":"TWICE: What Advantages Can Low-Resource Domain-Specific Embedding Model Bring? -- A Case Study on Korea Financial Texts","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["q-fin.CP"],"primary_cat":"cs.CL","authors_text":"Hanwool Lee, Sara Yu, Sungbum Jung, Yewon Hwang","submitted_at":"2025-02-10T23:49:39Z","abstract_excerpt":"Domain specificity of embedding models is critical for effective performance. However, existing benchmarks, such as FinMTEB, are primarily designed for high-resource languages, leaving low-resource settings, such as Korean, under-explored. Directly translating established English benchmarks often fails to capture the linguistic and cultural nuances present in low-resource domains. In this paper, titled TWICE: What Advantages Can Low-Resource Domain-Specific Embedding Models Bring? A Case Study on Korea Financial Texts, we introduce KorFinMTEB, a novel benchmark for the Korean financial domain,"},"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":"2502.07131","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-10T23:49:39Z","cross_cats_sorted":["q-fin.CP"],"title_canon_sha256":"64f3d402b7bf1d4cb37146b9ba9a14e1f27c709ee68eff463eaa45b3d1da5c28","abstract_canon_sha256":"260db3fb9c09bb284c3822a76998673cca31da7cb4923909d7b8da9f09c5822d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:42:42.976334Z","signature_b64":"8pWGGyeNmB5SmxBoIVxm537V9aVnpB4Qevx96Mbz8AMuhxjbOCh/AsSr1hocxHVQEZS7l/a7mYnVExKIqWdACw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bfb954007fa5a3c973523f94bd8c319683c8723e7ef364d124dde61a62242c85","last_reissued_at":"2026-07-05T10:42:42.975695Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:42:42.975695Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TWICE: What Advantages Can Low-Resource Domain-Specific Embedding Model Bring? -- A Case Study on Korea Financial Texts","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["q-fin.CP"],"primary_cat":"cs.CL","authors_text":"Hanwool Lee, Sara Yu, Sungbum Jung, Yewon Hwang","submitted_at":"2025-02-10T23:49:39Z","abstract_excerpt":"Domain specificity of embedding models is critical for effective performance. However, existing benchmarks, such as FinMTEB, are primarily designed for high-resource languages, leaving low-resource settings, such as Korean, under-explored. Directly translating established English benchmarks often fails to capture the linguistic and cultural nuances present in low-resource domains. In this paper, titled TWICE: What Advantages Can Low-Resource Domain-Specific Embedding Models Bring? A Case Study on Korea Financial Texts, we introduce KorFinMTEB, a novel benchmark for the Korean financial domain,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07131","kind":"arxiv","version":3},"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/2502.07131/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":"2502.07131","created_at":"2026-07-05T10:42:42.975753+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.07131v3","created_at":"2026-07-05T10:42:42.975753+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07131","created_at":"2026-07-05T10:42:42.975753+00:00"},{"alias_kind":"pith_short_12","alias_value":"X64VIAD7UWR4","created_at":"2026-07-05T10:42:42.975753+00:00"},{"alias_kind":"pith_short_16","alias_value":"X64VIAD7UWR4S42S","created_at":"2026-07-05T10:42:42.975753+00:00"},{"alias_kind":"pith_short_8","alias_value":"X64VIAD7","created_at":"2026-07-05T10:42:42.975753+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/X64VIAD7UWR4S42SH6KL3DBRS2","json":"https://pith.science/pith/X64VIAD7UWR4S42SH6KL3DBRS2.json","graph_json":"https://pith.science/api/pith-number/X64VIAD7UWR4S42SH6KL3DBRS2/graph.json","events_json":"https://pith.science/api/pith-number/X64VIAD7UWR4S42SH6KL3DBRS2/events.json","paper":"https://pith.science/paper/X64VIAD7"},"agent_actions":{"view_html":"https://pith.science/pith/X64VIAD7UWR4S42SH6KL3DBRS2","download_json":"https://pith.science/pith/X64VIAD7UWR4S42SH6KL3DBRS2.json","view_paper":"https://pith.science/paper/X64VIAD7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.07131&json=true","fetch_graph":"https://pith.science/api/pith-number/X64VIAD7UWR4S42SH6KL3DBRS2/graph.json","fetch_events":"https://pith.science/api/pith-number/X64VIAD7UWR4S42SH6KL3DBRS2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X64VIAD7UWR4S42SH6KL3DBRS2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X64VIAD7UWR4S42SH6KL3DBRS2/action/storage_attestation","attest_author":"https://pith.science/pith/X64VIAD7UWR4S42SH6KL3DBRS2/action/author_attestation","sign_citation":"https://pith.science/pith/X64VIAD7UWR4S42SH6KL3DBRS2/action/citation_signature","submit_replication":"https://pith.science/pith/X64VIAD7UWR4S42SH6KL3DBRS2/action/replication_record"}},"created_at":"2026-07-05T10:42:42.975753+00:00","updated_at":"2026-07-05T10:42:42.975753+00:00"}