{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZEAFJGLUBO7DUTC374G2F7ONDD","short_pith_number":"pith:ZEAFJGLU","schema_version":"1.0","canonical_sha256":"c9005499740bbe3a4c5bff0da2fdcd18f59f3937309b54156850ad187195ff15","source":{"kind":"arxiv","id":"2506.20203","version":1},"attestation_state":"computed","paper":{"title":"Intrinsic vs. Extrinsic Evaluation of Czech Sentence Embeddings: Semantic Relevance Doesn't Help with MT Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ond\\v{r}ej Bojar, Petra Baran\\v{c}\\'ikov\\'a","submitted_at":"2025-06-25T07:46:17Z","abstract_excerpt":"In this paper, we compare Czech-specific and multilingual sentence embedding models through intrinsic and extrinsic evaluation paradigms. For intrinsic evaluation, we employ Costra, a complex sentence transformation dataset, and several Semantic Textual Similarity (STS) benchmarks to assess the ability of the embeddings to capture linguistic phenomena such as semantic similarity, temporal aspects, and stylistic variations. In the extrinsic evaluation, we fine-tune each embedding model using COMET-based metrics for machine translation evaluation.\n  Our experiments reveal an interesting disconne"},"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":"2506.20203","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-25T07:46:17Z","cross_cats_sorted":[],"title_canon_sha256":"e6304935fbde8acd01a5b8f4009f035f01a91204440bf77151e351f90554200e","abstract_canon_sha256":"daed37b4172fc089f8ae2d2e06080755efd6f62a85ea289aafafdd837c9a78e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:27:01.879051Z","signature_b64":"pX+GBg0C2Y3nCLkKnxbbwOwpa67C5LKo45fMGd6BpZAqJFoSvGDoxkdDhHY4bkevnMvQtlQQrOGRX8V2hY8eDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c9005499740bbe3a4c5bff0da2fdcd18f59f3937309b54156850ad187195ff15","last_reissued_at":"2026-07-05T11:27:01.878498Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:27:01.878498Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Intrinsic vs. Extrinsic Evaluation of Czech Sentence Embeddings: Semantic Relevance Doesn't Help with MT Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ond\\v{r}ej Bojar, Petra Baran\\v{c}\\'ikov\\'a","submitted_at":"2025-06-25T07:46:17Z","abstract_excerpt":"In this paper, we compare Czech-specific and multilingual sentence embedding models through intrinsic and extrinsic evaluation paradigms. For intrinsic evaluation, we employ Costra, a complex sentence transformation dataset, and several Semantic Textual Similarity (STS) benchmarks to assess the ability of the embeddings to capture linguistic phenomena such as semantic similarity, temporal aspects, and stylistic variations. In the extrinsic evaluation, we fine-tune each embedding model using COMET-based metrics for machine translation evaluation.\n  Our experiments reveal an interesting disconne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.20203","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/2506.20203/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":"2506.20203","created_at":"2026-07-05T11:27:01.878562+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.20203v1","created_at":"2026-07-05T11:27:01.878562+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.20203","created_at":"2026-07-05T11:27:01.878562+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZEAFJGLUBO7D","created_at":"2026-07-05T11:27:01.878562+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZEAFJGLUBO7DUTC3","created_at":"2026-07-05T11:27:01.878562+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZEAFJGLU","created_at":"2026-07-05T11:27:01.878562+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/ZEAFJGLUBO7DUTC374G2F7ONDD","json":"https://pith.science/pith/ZEAFJGLUBO7DUTC374G2F7ONDD.json","graph_json":"https://pith.science/api/pith-number/ZEAFJGLUBO7DUTC374G2F7ONDD/graph.json","events_json":"https://pith.science/api/pith-number/ZEAFJGLUBO7DUTC374G2F7ONDD/events.json","paper":"https://pith.science/paper/ZEAFJGLU"},"agent_actions":{"view_html":"https://pith.science/pith/ZEAFJGLUBO7DUTC374G2F7ONDD","download_json":"https://pith.science/pith/ZEAFJGLUBO7DUTC374G2F7ONDD.json","view_paper":"https://pith.science/paper/ZEAFJGLU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.20203&json=true","fetch_graph":"https://pith.science/api/pith-number/ZEAFJGLUBO7DUTC374G2F7ONDD/graph.json","fetch_events":"https://pith.science/api/pith-number/ZEAFJGLUBO7DUTC374G2F7ONDD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZEAFJGLUBO7DUTC374G2F7ONDD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZEAFJGLUBO7DUTC374G2F7ONDD/action/storage_attestation","attest_author":"https://pith.science/pith/ZEAFJGLUBO7DUTC374G2F7ONDD/action/author_attestation","sign_citation":"https://pith.science/pith/ZEAFJGLUBO7DUTC374G2F7ONDD/action/citation_signature","submit_replication":"https://pith.science/pith/ZEAFJGLUBO7DUTC374G2F7ONDD/action/replication_record"}},"created_at":"2026-07-05T11:27:01.878562+00:00","updated_at":"2026-07-05T11:27:01.878562+00:00"}