{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2PI23XDGZZNDYBKS7B57BIMDG6","short_pith_number":"pith:2PI23XDG","schema_version":"1.0","canonical_sha256":"d3d1addc66ce5a3c0552f87bf0a183378312878f3bd10d9df45207c572f63a58","source":{"kind":"arxiv","id":"2406.02396","version":1},"attestation_state":"computed","paper":{"title":"The Scandinavian Embedding Benchmarks: Comprehensive Assessment of Multilingual and Monolingual Text Embedding","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Kenneth Enevoldsen, Kristoffer Laigaard Nielbo, M\\'arton Kardos, Niklas Muennighoff","submitted_at":"2024-06-04T15:11:27Z","abstract_excerpt":"The evaluation of English text embeddings has transitioned from evaluating a handful of datasets to broad coverage across many tasks through benchmarks such as MTEB. However, this is not the case for multilingual text embeddings due to a lack of available benchmarks. To address this problem, we introduce the Scandinavian Embedding Benchmark (SEB). SEB is a comprehensive framework that enables text embedding evaluation for Scandinavian languages across 24 tasks, 10 subtasks, and 4 task categories. Building on SEB, we evaluate more than 26 models, uncovering significant performance disparities b"},"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":"2406.02396","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-04T15:11:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"64e1df7b5d2d3f82c0f755db7a79f6dfaf78e63405af4446424a013240420181","abstract_canon_sha256":"2444d2753dfb97b2594a50bd312a61d01df99edda891a355aecc6fd76330e8ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:19.282840Z","signature_b64":"WmfJl5JisF5/cx7tS7ItUee70O6qMLjdMTEen6PuaY7TbyQvzXaPoWrKsKZjBN2lIrt7s+mcXmaTOOVtEBHsBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3d1addc66ce5a3c0552f87bf0a183378312878f3bd10d9df45207c572f63a58","last_reissued_at":"2026-07-05T08:27:19.282432Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:19.282432Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Scandinavian Embedding Benchmarks: Comprehensive Assessment of Multilingual and Monolingual Text Embedding","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Kenneth Enevoldsen, Kristoffer Laigaard Nielbo, M\\'arton Kardos, Niklas Muennighoff","submitted_at":"2024-06-04T15:11:27Z","abstract_excerpt":"The evaluation of English text embeddings has transitioned from evaluating a handful of datasets to broad coverage across many tasks through benchmarks such as MTEB. However, this is not the case for multilingual text embeddings due to a lack of available benchmarks. To address this problem, we introduce the Scandinavian Embedding Benchmark (SEB). SEB is a comprehensive framework that enables text embedding evaluation for Scandinavian languages across 24 tasks, 10 subtasks, and 4 task categories. Building on SEB, we evaluate more than 26 models, uncovering significant performance disparities b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02396","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/2406.02396/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":"2406.02396","created_at":"2026-07-05T08:27:19.282493+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.02396v1","created_at":"2026-07-05T08:27:19.282493+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02396","created_at":"2026-07-05T08:27:19.282493+00:00"},{"alias_kind":"pith_short_12","alias_value":"2PI23XDGZZND","created_at":"2026-07-05T08:27:19.282493+00:00"},{"alias_kind":"pith_short_16","alias_value":"2PI23XDGZZNDYBKS","created_at":"2026-07-05T08:27:19.282493+00:00"},{"alias_kind":"pith_short_8","alias_value":"2PI23XDG","created_at":"2026-07-05T08:27:19.282493+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22778","citing_title":"HAKARI-Bench: A Lightweight Benchmark for Comparing Retrieval Architectures and Efficiency Settings under Unified Conditions","ref_index":90,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2PI23XDGZZNDYBKS7B57BIMDG6","json":"https://pith.science/pith/2PI23XDGZZNDYBKS7B57BIMDG6.json","graph_json":"https://pith.science/api/pith-number/2PI23XDGZZNDYBKS7B57BIMDG6/graph.json","events_json":"https://pith.science/api/pith-number/2PI23XDGZZNDYBKS7B57BIMDG6/events.json","paper":"https://pith.science/paper/2PI23XDG"},"agent_actions":{"view_html":"https://pith.science/pith/2PI23XDGZZNDYBKS7B57BIMDG6","download_json":"https://pith.science/pith/2PI23XDGZZNDYBKS7B57BIMDG6.json","view_paper":"https://pith.science/paper/2PI23XDG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.02396&json=true","fetch_graph":"https://pith.science/api/pith-number/2PI23XDGZZNDYBKS7B57BIMDG6/graph.json","fetch_events":"https://pith.science/api/pith-number/2PI23XDGZZNDYBKS7B57BIMDG6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2PI23XDGZZNDYBKS7B57BIMDG6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2PI23XDGZZNDYBKS7B57BIMDG6/action/storage_attestation","attest_author":"https://pith.science/pith/2PI23XDGZZNDYBKS7B57BIMDG6/action/author_attestation","sign_citation":"https://pith.science/pith/2PI23XDGZZNDYBKS7B57BIMDG6/action/citation_signature","submit_replication":"https://pith.science/pith/2PI23XDGZZNDYBKS7B57BIMDG6/action/replication_record"}},"created_at":"2026-07-05T08:27:19.282493+00:00","updated_at":"2026-07-05T08:27:19.282493+00:00"}