{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EZMN3N2RDQZTKEU4IR6UDD6MVH","short_pith_number":"pith:EZMN3N2R","schema_version":"1.0","canonical_sha256":"2658ddb7511c3335129c447d418fcca9e7968c156a1751bd554546a4f19547dc","source":{"kind":"arxiv","id":"2606.13647","version":1},"attestation_state":"computed","paper":{"title":"SkMTEB: Slovak Massive Text Embedding Benchmark and Model Adaptation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Andrej Ridzik, Daniel Hl\\'adek, Marek \\v{S}uppa, Nat\\'alia K\\v{n}a\\v{z}ekov\\'a, Vikt\\'oria Ondrejov\\'a","submitted_at":"2026-06-11T17:50:06Z","abstract_excerpt":"We introduce SkMTEB, the first comprehensive MTEB-style text embedding benchmark for Slovak, a low-resource West Slavic language, comprising 31 datasets across 7 task types -- nearly 4$\\times$ the depth of existing multilingual benchmark coverage for Slovak. Our evaluation of 31 embedding models reveals that large instruction-tuned multilingual models achieve the strongest performance, while existing Slovak-specific models trained for NLU tasks transfer poorly to embedding tasks. To address the need for efficient, locally-deployable Slovak embeddings, we develop \\texttt{e5-sk-small} (45M param"},"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":"2606.13647","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-11T17:50:06Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c2d037d080b9315fdf311ecb224f3619618a34dcdfc750130a16e69ae1a56613","abstract_canon_sha256":"4b93d29c60a4aef7e6909d7524f8d7ba10ba889beb200f9685c280e845e08f46"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T01:10:20.961123Z","signature_b64":"890S6KuUyfm7jjzHezDKBy/G6LiNlv6+LNB2zBlWSL5ywuUMPoO3hG9/AOmLubf7kDQAMtlkfYaa+GBfM/OYCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2658ddb7511c3335129c447d418fcca9e7968c156a1751bd554546a4f19547dc","last_reissued_at":"2026-06-12T01:10:20.960299Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T01:10:20.960299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SkMTEB: Slovak Massive Text Embedding Benchmark and Model Adaptation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Andrej Ridzik, Daniel Hl\\'adek, Marek \\v{S}uppa, Nat\\'alia K\\v{n}a\\v{z}ekov\\'a, Vikt\\'oria Ondrejov\\'a","submitted_at":"2026-06-11T17:50:06Z","abstract_excerpt":"We introduce SkMTEB, the first comprehensive MTEB-style text embedding benchmark for Slovak, a low-resource West Slavic language, comprising 31 datasets across 7 task types -- nearly 4$\\times$ the depth of existing multilingual benchmark coverage for Slovak. Our evaluation of 31 embedding models reveals that large instruction-tuned multilingual models achieve the strongest performance, while existing Slovak-specific models trained for NLU tasks transfer poorly to embedding tasks. To address the need for efficient, locally-deployable Slovak embeddings, we develop \\texttt{e5-sk-small} (45M param"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.13647","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/2606.13647/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":"2606.13647","created_at":"2026-06-12T01:10:20.960437+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.13647v1","created_at":"2026-06-12T01:10:20.960437+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.13647","created_at":"2026-06-12T01:10:20.960437+00:00"},{"alias_kind":"pith_short_12","alias_value":"EZMN3N2RDQZT","created_at":"2026-06-12T01:10:20.960437+00:00"},{"alias_kind":"pith_short_16","alias_value":"EZMN3N2RDQZTKEU4","created_at":"2026-06-12T01:10:20.960437+00:00"},{"alias_kind":"pith_short_8","alias_value":"EZMN3N2R","created_at":"2026-06-12T01:10:20.960437+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/EZMN3N2RDQZTKEU4IR6UDD6MVH","json":"https://pith.science/pith/EZMN3N2RDQZTKEU4IR6UDD6MVH.json","graph_json":"https://pith.science/api/pith-number/EZMN3N2RDQZTKEU4IR6UDD6MVH/graph.json","events_json":"https://pith.science/api/pith-number/EZMN3N2RDQZTKEU4IR6UDD6MVH/events.json","paper":"https://pith.science/paper/EZMN3N2R"},"agent_actions":{"view_html":"https://pith.science/pith/EZMN3N2RDQZTKEU4IR6UDD6MVH","download_json":"https://pith.science/pith/EZMN3N2RDQZTKEU4IR6UDD6MVH.json","view_paper":"https://pith.science/paper/EZMN3N2R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.13647&json=true","fetch_graph":"https://pith.science/api/pith-number/EZMN3N2RDQZTKEU4IR6UDD6MVH/graph.json","fetch_events":"https://pith.science/api/pith-number/EZMN3N2RDQZTKEU4IR6UDD6MVH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EZMN3N2RDQZTKEU4IR6UDD6MVH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EZMN3N2RDQZTKEU4IR6UDD6MVH/action/storage_attestation","attest_author":"https://pith.science/pith/EZMN3N2RDQZTKEU4IR6UDD6MVH/action/author_attestation","sign_citation":"https://pith.science/pith/EZMN3N2RDQZTKEU4IR6UDD6MVH/action/citation_signature","submit_replication":"https://pith.science/pith/EZMN3N2RDQZTKEU4IR6UDD6MVH/action/replication_record"}},"created_at":"2026-06-12T01:10:20.960437+00:00","updated_at":"2026-06-12T01:10:20.960437+00:00"}