{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BTVVCIKFC7IZ56HOLLEPJMRQTX","short_pith_number":"pith:BTVVCIKF","schema_version":"1.0","canonical_sha256":"0ceb51214517d19ef8ee5ac8f4b2309dcd88cac0e6a465986217db961eab0c59","source":{"kind":"arxiv","id":"2407.05449","version":2},"attestation_state":"computed","paper":{"title":"SmurfCat at PAN 2024 TextDetox: Alignment of Multilingual Transformers for Text Detoxification","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alexandr Voronin, Elisei Rykov, Ivan Anisimov, Konstantin Zaytsev","submitted_at":"2024-07-07T17:19:34Z","abstract_excerpt":"This paper presents a solution for the Multilingual Text Detoxification task in the PAN-2024 competition of the SmurfCat team. Using data augmentation through machine translation and a special filtering procedure, we collected an additional multilingual parallel dataset for text detoxification. Using the obtained data, we fine-tuned several multilingual sequence-to-sequence models, such as mT0 and Aya, on a text detoxification task. We applied the ORPO alignment technique to the final model. Our final model has only 3.7 billion parameters and achieves state-of-the-art results for the Ukrainian"},"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":"2407.05449","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-07T17:19:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"76c3710df29bcdd3d45ce2194be89a894973a320079597b5315f0c8ec070f4cf","abstract_canon_sha256":"0f94a49bc0178aa4977c6b2b584f00be499674a8e04301ef5c8bcf875724eab5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:42:23.238057Z","signature_b64":"gCeqPfw83zhCZE6p9UTnP31Pzf6WUUbXfWoAxqK8kX4ebHYyHFlCx2zDd1oLv/zM0sW2RBLyHPm8s0XsVqUGAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ceb51214517d19ef8ee5ac8f4b2309dcd88cac0e6a465986217db961eab0c59","last_reissued_at":"2026-07-05T08:42:23.237636Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:42:23.237636Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SmurfCat at PAN 2024 TextDetox: Alignment of Multilingual Transformers for Text Detoxification","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alexandr Voronin, Elisei Rykov, Ivan Anisimov, Konstantin Zaytsev","submitted_at":"2024-07-07T17:19:34Z","abstract_excerpt":"This paper presents a solution for the Multilingual Text Detoxification task in the PAN-2024 competition of the SmurfCat team. Using data augmentation through machine translation and a special filtering procedure, we collected an additional multilingual parallel dataset for text detoxification. Using the obtained data, we fine-tuned several multilingual sequence-to-sequence models, such as mT0 and Aya, on a text detoxification task. We applied the ORPO alignment technique to the final model. Our final model has only 3.7 billion parameters and achieves state-of-the-art results for the Ukrainian"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.05449","kind":"arxiv","version":2},"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/2407.05449/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":"2407.05449","created_at":"2026-07-05T08:42:23.237695+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.05449v2","created_at":"2026-07-05T08:42:23.237695+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.05449","created_at":"2026-07-05T08:42:23.237695+00:00"},{"alias_kind":"pith_short_12","alias_value":"BTVVCIKFC7IZ","created_at":"2026-07-05T08:42:23.237695+00:00"},{"alias_kind":"pith_short_16","alias_value":"BTVVCIKFC7IZ56HO","created_at":"2026-07-05T08:42:23.237695+00:00"},{"alias_kind":"pith_short_8","alias_value":"BTVVCIKF","created_at":"2026-07-05T08:42:23.237695+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26015","citing_title":"The Tatoxa System for Text Detoxification in Low-Resource Languages: The Case of Tatar","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BTVVCIKFC7IZ56HOLLEPJMRQTX","json":"https://pith.science/pith/BTVVCIKFC7IZ56HOLLEPJMRQTX.json","graph_json":"https://pith.science/api/pith-number/BTVVCIKFC7IZ56HOLLEPJMRQTX/graph.json","events_json":"https://pith.science/api/pith-number/BTVVCIKFC7IZ56HOLLEPJMRQTX/events.json","paper":"https://pith.science/paper/BTVVCIKF"},"agent_actions":{"view_html":"https://pith.science/pith/BTVVCIKFC7IZ56HOLLEPJMRQTX","download_json":"https://pith.science/pith/BTVVCIKFC7IZ56HOLLEPJMRQTX.json","view_paper":"https://pith.science/paper/BTVVCIKF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.05449&json=true","fetch_graph":"https://pith.science/api/pith-number/BTVVCIKFC7IZ56HOLLEPJMRQTX/graph.json","fetch_events":"https://pith.science/api/pith-number/BTVVCIKFC7IZ56HOLLEPJMRQTX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BTVVCIKFC7IZ56HOLLEPJMRQTX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BTVVCIKFC7IZ56HOLLEPJMRQTX/action/storage_attestation","attest_author":"https://pith.science/pith/BTVVCIKFC7IZ56HOLLEPJMRQTX/action/author_attestation","sign_citation":"https://pith.science/pith/BTVVCIKFC7IZ56HOLLEPJMRQTX/action/citation_signature","submit_replication":"https://pith.science/pith/BTVVCIKFC7IZ56HOLLEPJMRQTX/action/replication_record"}},"created_at":"2026-07-05T08:42:23.237695+00:00","updated_at":"2026-07-05T08:42:23.237695+00:00"}