{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VGQXWLYZTKLVGUZSSMSK2YHD6E","short_pith_number":"pith:VGQXWLYZ","schema_version":"1.0","canonical_sha256":"a9a17b2f199a975353329324ad60e3f1205a961886091f1241cce03a7d777c33","source":{"kind":"arxiv","id":"2311.13921","version":1},"attestation_state":"computed","paper":{"title":"Some Like It Small: Czech Semantic Embedding Models for Industry Applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Jakub N\\'aplava, Ji\\v{r}\\'i Bedn\\'a\\v{r}, Ond\\v{r}ej Lisick\\'y, Petra Baran\\v{c}\\'ikov\\'a","submitted_at":"2023-11-23T11:14:13Z","abstract_excerpt":"This article focuses on the development and evaluation of Small-sized Czech sentence embedding models. Small models are important components for real-time industry applications in resource-constrained environments. Given the limited availability of labeled Czech data, alternative approaches, including pre-training, knowledge distillation, and unsupervised contrastive fine-tuning, are investigated. Comprehensive intrinsic and extrinsic analyses are conducted, showcasing the competitive performance of our models compared to significantly larger counterparts, with approximately 8 times smaller si"},"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":"2311.13921","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-23T11:14:13Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"11bea6c1f7022f5bd16a201845f35f7e257c397a3a742891003ee2c790406c3d","abstract_canon_sha256":"a3e01b477a0c53c41b8515f82c8371b522644baf241ee97827fc3d3ecd2123f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:16:10.551641Z","signature_b64":"zCTH4MIWyeaL+FR3iEqKGSbmaQ5nwhkIiHMcLShKA5h3JjR73VKnQmyaWuWG9muinq19OOMki3P0rUyTQna8DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9a17b2f199a975353329324ad60e3f1205a961886091f1241cce03a7d777c33","last_reissued_at":"2026-07-05T07:16:10.551085Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:16:10.551085Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Some Like It Small: Czech Semantic Embedding Models for Industry Applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Jakub N\\'aplava, Ji\\v{r}\\'i Bedn\\'a\\v{r}, Ond\\v{r}ej Lisick\\'y, Petra Baran\\v{c}\\'ikov\\'a","submitted_at":"2023-11-23T11:14:13Z","abstract_excerpt":"This article focuses on the development and evaluation of Small-sized Czech sentence embedding models. Small models are important components for real-time industry applications in resource-constrained environments. Given the limited availability of labeled Czech data, alternative approaches, including pre-training, knowledge distillation, and unsupervised contrastive fine-tuning, are investigated. Comprehensive intrinsic and extrinsic analyses are conducted, showcasing the competitive performance of our models compared to significantly larger counterparts, with approximately 8 times smaller si"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.13921","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/2311.13921/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":"2311.13921","created_at":"2026-07-05T07:16:10.551154+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.13921v1","created_at":"2026-07-05T07:16:10.551154+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.13921","created_at":"2026-07-05T07:16:10.551154+00:00"},{"alias_kind":"pith_short_12","alias_value":"VGQXWLYZTKLV","created_at":"2026-07-05T07:16:10.551154+00:00"},{"alias_kind":"pith_short_16","alias_value":"VGQXWLYZTKLVGUZS","created_at":"2026-07-05T07:16:10.551154+00:00"},{"alias_kind":"pith_short_8","alias_value":"VGQXWLYZ","created_at":"2026-07-05T07:16:10.551154+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.12921","citing_title":"A Comparative Study of Text Retrieval Models on DaReCzech","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VGQXWLYZTKLVGUZSSMSK2YHD6E","json":"https://pith.science/pith/VGQXWLYZTKLVGUZSSMSK2YHD6E.json","graph_json":"https://pith.science/api/pith-number/VGQXWLYZTKLVGUZSSMSK2YHD6E/graph.json","events_json":"https://pith.science/api/pith-number/VGQXWLYZTKLVGUZSSMSK2YHD6E/events.json","paper":"https://pith.science/paper/VGQXWLYZ"},"agent_actions":{"view_html":"https://pith.science/pith/VGQXWLYZTKLVGUZSSMSK2YHD6E","download_json":"https://pith.science/pith/VGQXWLYZTKLVGUZSSMSK2YHD6E.json","view_paper":"https://pith.science/paper/VGQXWLYZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.13921&json=true","fetch_graph":"https://pith.science/api/pith-number/VGQXWLYZTKLVGUZSSMSK2YHD6E/graph.json","fetch_events":"https://pith.science/api/pith-number/VGQXWLYZTKLVGUZSSMSK2YHD6E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VGQXWLYZTKLVGUZSSMSK2YHD6E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VGQXWLYZTKLVGUZSSMSK2YHD6E/action/storage_attestation","attest_author":"https://pith.science/pith/VGQXWLYZTKLVGUZSSMSK2YHD6E/action/author_attestation","sign_citation":"https://pith.science/pith/VGQXWLYZTKLVGUZSSMSK2YHD6E/action/citation_signature","submit_replication":"https://pith.science/pith/VGQXWLYZTKLVGUZSSMSK2YHD6E/action/replication_record"}},"created_at":"2026-07-05T07:16:10.551154+00:00","updated_at":"2026-07-05T07:16:10.551154+00:00"}