{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:DYRGM7JTQYJHBQAONALLRNGIO7","short_pith_number":"pith:DYRGM7JT","schema_version":"1.0","canonical_sha256":"1e22667d33861270c00e6816b8b4c877f0148dcb99075a7d63dd0aae4a6af525","source":{"kind":"arxiv","id":"2112.01810","version":1},"attestation_state":"computed","paper":{"title":"Siamese BERT-based Model for Web Search Relevance Ranking Evaluated on a New Czech Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Daniel \\v{S}tancl, Jakub N\\'aplava, Mat\\v{e}j Koci\\'an, Vladim\\'ir Kadlec","submitted_at":"2021-12-03T09:45:18Z","abstract_excerpt":"Web search engines focus on serving highly relevant results within hundreds of milliseconds. Pre-trained language transformer models such as BERT are therefore hard to use in this scenario due to their high computational demands. We present our real-time approach to the document ranking problem leveraging a BERT-based siamese architecture. The model is already deployed in a commercial search engine and it improves production performance by more than 3%. For further research and evaluation, we release DaReCzech, a unique data set of 1.6 million Czech user query-document pairs with manually assi"},"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":"2112.01810","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-12-03T09:45:18Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"16ad5b709f604e12e445b41799f2fc1dbaf07376059b80f67f46e78b0a1afc19","abstract_canon_sha256":"55b0554376c9059f1627f7fba0b00c08bbf55022a747fb22e4fc73f1629d41b6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:37:32.607448Z","signature_b64":"ZjwIXsqNI8CQmaHTmVNwmhHy+nR2pzRQiSI4htGvnErVkTAdS5S2KTZtzTaUGO6OsvXlXfw9hM3KZWXVAChIAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e22667d33861270c00e6816b8b4c877f0148dcb99075a7d63dd0aae4a6af525","last_reissued_at":"2026-07-05T03:37:32.606818Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:37:32.606818Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Siamese BERT-based Model for Web Search Relevance Ranking Evaluated on a New Czech Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Daniel \\v{S}tancl, Jakub N\\'aplava, Mat\\v{e}j Koci\\'an, Vladim\\'ir Kadlec","submitted_at":"2021-12-03T09:45:18Z","abstract_excerpt":"Web search engines focus on serving highly relevant results within hundreds of milliseconds. Pre-trained language transformer models such as BERT are therefore hard to use in this scenario due to their high computational demands. We present our real-time approach to the document ranking problem leveraging a BERT-based siamese architecture. The model is already deployed in a commercial search engine and it improves production performance by more than 3%. For further research and evaluation, we release DaReCzech, a unique data set of 1.6 million Czech user query-document pairs with manually assi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.01810","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/2112.01810/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":"2112.01810","created_at":"2026-07-05T03:37:32.606877+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.01810v1","created_at":"2026-07-05T03:37:32.606877+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.01810","created_at":"2026-07-05T03:37:32.606877+00:00"},{"alias_kind":"pith_short_12","alias_value":"DYRGM7JTQYJH","created_at":"2026-07-05T03:37:32.606877+00:00"},{"alias_kind":"pith_short_16","alias_value":"DYRGM7JTQYJHBQAO","created_at":"2026-07-05T03:37:32.606877+00:00"},{"alias_kind":"pith_short_8","alias_value":"DYRGM7JT","created_at":"2026-07-05T03:37:32.606877+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":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DYRGM7JTQYJHBQAONALLRNGIO7","json":"https://pith.science/pith/DYRGM7JTQYJHBQAONALLRNGIO7.json","graph_json":"https://pith.science/api/pith-number/DYRGM7JTQYJHBQAONALLRNGIO7/graph.json","events_json":"https://pith.science/api/pith-number/DYRGM7JTQYJHBQAONALLRNGIO7/events.json","paper":"https://pith.science/paper/DYRGM7JT"},"agent_actions":{"view_html":"https://pith.science/pith/DYRGM7JTQYJHBQAONALLRNGIO7","download_json":"https://pith.science/pith/DYRGM7JTQYJHBQAONALLRNGIO7.json","view_paper":"https://pith.science/paper/DYRGM7JT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.01810&json=true","fetch_graph":"https://pith.science/api/pith-number/DYRGM7JTQYJHBQAONALLRNGIO7/graph.json","fetch_events":"https://pith.science/api/pith-number/DYRGM7JTQYJHBQAONALLRNGIO7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DYRGM7JTQYJHBQAONALLRNGIO7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DYRGM7JTQYJHBQAONALLRNGIO7/action/storage_attestation","attest_author":"https://pith.science/pith/DYRGM7JTQYJHBQAONALLRNGIO7/action/author_attestation","sign_citation":"https://pith.science/pith/DYRGM7JTQYJHBQAONALLRNGIO7/action/citation_signature","submit_replication":"https://pith.science/pith/DYRGM7JTQYJHBQAONALLRNGIO7/action/replication_record"}},"created_at":"2026-07-05T03:37:32.606877+00:00","updated_at":"2026-07-05T03:37:32.606877+00:00"}