{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RES2PA6KQHGVKOHZHWWBAEXAIP","short_pith_number":"pith:RES2PA6K","schema_version":"1.0","canonical_sha256":"8925a783ca81cd5538f93dac1012e043c486454148a672c87e494c358f6bc908","source":{"kind":"arxiv","id":"2501.16533","version":1},"attestation_state":"computed","paper":{"title":"A comparison of data filtering techniques for English-Polish LLM-based machine translation in the biomedical domain","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Christian Hardmeier, J\\'anos M\\'at\\'e, Jorge del Pozo L\\'erida, Kamil Kojs, Miko{\\l}aj Antoni Bara\\'nski","submitted_at":"2025-01-27T22:12:09Z","abstract_excerpt":"Large Language Models (LLMs) have become state-of-the-art in Machine Translation (MT), often trained on massive bilingual parallel corpora scraped from the web, that contain low-quality entries and redundant information, leading to significant computational challenges. Various data filtering methods exist to reduce dataset sizes, but their effectiveness largely varies based on specific language pairs and domains. This paper evaluates the impact of commonly used data filtering techniques, such as LASER, MUSE, and LaBSE, on English-Polish translation within the biomedical domain. By filtering th"},"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":"2501.16533","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-27T22:12:09Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"36a663cd1c53f2aec1b23866e752f56d181d77c5774894e57ae1705dd3734d7d","abstract_canon_sha256":"9b3c4c5ee3482959b63d39480eb1359c4cebb21ad14694e730cb9f2a9a96ad78"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:06:14.768709Z","signature_b64":"poRBzncwtltwairv0JtYahoNYUpOL7EO5aJb1/TKkXFLIcB96wcQDHeJ0la4JvgSjwCpqHiLHS7QM9t1+0jkDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8925a783ca81cd5538f93dac1012e043c486454148a672c87e494c358f6bc908","last_reissued_at":"2026-07-05T10:06:14.768118Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:06:14.768118Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A comparison of data filtering techniques for English-Polish LLM-based machine translation in the biomedical domain","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Christian Hardmeier, J\\'anos M\\'at\\'e, Jorge del Pozo L\\'erida, Kamil Kojs, Miko{\\l}aj Antoni Bara\\'nski","submitted_at":"2025-01-27T22:12:09Z","abstract_excerpt":"Large Language Models (LLMs) have become state-of-the-art in Machine Translation (MT), often trained on massive bilingual parallel corpora scraped from the web, that contain low-quality entries and redundant information, leading to significant computational challenges. Various data filtering methods exist to reduce dataset sizes, but their effectiveness largely varies based on specific language pairs and domains. This paper evaluates the impact of commonly used data filtering techniques, such as LASER, MUSE, and LaBSE, on English-Polish translation within the biomedical domain. By filtering th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.16533","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/2501.16533/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":"2501.16533","created_at":"2026-07-05T10:06:14.768175+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.16533v1","created_at":"2026-07-05T10:06:14.768175+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.16533","created_at":"2026-07-05T10:06:14.768175+00:00"},{"alias_kind":"pith_short_12","alias_value":"RES2PA6KQHGV","created_at":"2026-07-05T10:06:14.768175+00:00"},{"alias_kind":"pith_short_16","alias_value":"RES2PA6KQHGVKOHZ","created_at":"2026-07-05T10:06:14.768175+00:00"},{"alias_kind":"pith_short_8","alias_value":"RES2PA6K","created_at":"2026-07-05T10:06:14.768175+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/RES2PA6KQHGVKOHZHWWBAEXAIP","json":"https://pith.science/pith/RES2PA6KQHGVKOHZHWWBAEXAIP.json","graph_json":"https://pith.science/api/pith-number/RES2PA6KQHGVKOHZHWWBAEXAIP/graph.json","events_json":"https://pith.science/api/pith-number/RES2PA6KQHGVKOHZHWWBAEXAIP/events.json","paper":"https://pith.science/paper/RES2PA6K"},"agent_actions":{"view_html":"https://pith.science/pith/RES2PA6KQHGVKOHZHWWBAEXAIP","download_json":"https://pith.science/pith/RES2PA6KQHGVKOHZHWWBAEXAIP.json","view_paper":"https://pith.science/paper/RES2PA6K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.16533&json=true","fetch_graph":"https://pith.science/api/pith-number/RES2PA6KQHGVKOHZHWWBAEXAIP/graph.json","fetch_events":"https://pith.science/api/pith-number/RES2PA6KQHGVKOHZHWWBAEXAIP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RES2PA6KQHGVKOHZHWWBAEXAIP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RES2PA6KQHGVKOHZHWWBAEXAIP/action/storage_attestation","attest_author":"https://pith.science/pith/RES2PA6KQHGVKOHZHWWBAEXAIP/action/author_attestation","sign_citation":"https://pith.science/pith/RES2PA6KQHGVKOHZHWWBAEXAIP/action/citation_signature","submit_replication":"https://pith.science/pith/RES2PA6KQHGVKOHZHWWBAEXAIP/action/replication_record"}},"created_at":"2026-07-05T10:06:14.768175+00:00","updated_at":"2026-07-05T10:06:14.768175+00:00"}