{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:2ZBTTTMTC6HRYAVFIBX2ESRDIU","short_pith_number":"pith:2ZBTTTMT","schema_version":"1.0","canonical_sha256":"d64339cd93178f1c02a5406fa24a2345261814057ccf1c78a4ce64357fdd5647","source":{"kind":"arxiv","id":"2104.04739","version":1},"attestation_state":"computed","paper":{"title":"MIPT-NSU-UTMN at SemEval-2021 Task 5: Ensembling Learning with Pre-trained Language Models for Toxic Spans Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Anna Glazkova, Dmitry Morozov, Mikhail Kotyushev","submitted_at":"2021-04-10T11:27:32Z","abstract_excerpt":"This paper describes our system for SemEval-2021 Task 5 on Toxic Spans Detection. We developed ensemble models using BERT-based neural architectures and post-processing to combine tokens into spans. We evaluated several pre-trained language models using various ensemble techniques for toxic span identification and achieved sizable improvements over our baseline fine-tuned BERT models. Finally, our system obtained a F1-score of 67.55% on test data."},"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":"2104.04739","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-10T11:27:32Z","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"title_canon_sha256":"fa08be65111f85ef7b0b717f9f4d7950ff83bf5fc90c1c3a018a61849e277eb4","abstract_canon_sha256":"8b44ffe98a48e5c0bcb92bb94fde297b3ff6f93acd2dda128805bce3826e2e39"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:09:18.161786Z","signature_b64":"0cGOas8xifMKk+gO9U1Ru3B5V85luLeQf0x5aEM6urbqCDgPqZK8PTjlSYgYlylJA/MJ6EaHPQP8hmdHH3prCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d64339cd93178f1c02a5406fa24a2345261814057ccf1c78a4ce64357fdd5647","last_reissued_at":"2026-07-05T03:09:18.161429Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:09:18.161429Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MIPT-NSU-UTMN at SemEval-2021 Task 5: Ensembling Learning with Pre-trained Language Models for Toxic Spans Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Anna Glazkova, Dmitry Morozov, Mikhail Kotyushev","submitted_at":"2021-04-10T11:27:32Z","abstract_excerpt":"This paper describes our system for SemEval-2021 Task 5 on Toxic Spans Detection. We developed ensemble models using BERT-based neural architectures and post-processing to combine tokens into spans. We evaluated several pre-trained language models using various ensemble techniques for toxic span identification and achieved sizable improvements over our baseline fine-tuned BERT models. Finally, our system obtained a F1-score of 67.55% on test data."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.04739","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/2104.04739/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":"2104.04739","created_at":"2026-07-05T03:09:18.161485+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.04739v1","created_at":"2026-07-05T03:09:18.161485+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.04739","created_at":"2026-07-05T03:09:18.161485+00:00"},{"alias_kind":"pith_short_12","alias_value":"2ZBTTTMTC6HR","created_at":"2026-07-05T03:09:18.161485+00:00"},{"alias_kind":"pith_short_16","alias_value":"2ZBTTTMTC6HRYAVF","created_at":"2026-07-05T03:09:18.161485+00:00"},{"alias_kind":"pith_short_8","alias_value":"2ZBTTTMT","created_at":"2026-07-05T03:09:18.161485+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/2ZBTTTMTC6HRYAVFIBX2ESRDIU","json":"https://pith.science/pith/2ZBTTTMTC6HRYAVFIBX2ESRDIU.json","graph_json":"https://pith.science/api/pith-number/2ZBTTTMTC6HRYAVFIBX2ESRDIU/graph.json","events_json":"https://pith.science/api/pith-number/2ZBTTTMTC6HRYAVFIBX2ESRDIU/events.json","paper":"https://pith.science/paper/2ZBTTTMT"},"agent_actions":{"view_html":"https://pith.science/pith/2ZBTTTMTC6HRYAVFIBX2ESRDIU","download_json":"https://pith.science/pith/2ZBTTTMTC6HRYAVFIBX2ESRDIU.json","view_paper":"https://pith.science/paper/2ZBTTTMT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.04739&json=true","fetch_graph":"https://pith.science/api/pith-number/2ZBTTTMTC6HRYAVFIBX2ESRDIU/graph.json","fetch_events":"https://pith.science/api/pith-number/2ZBTTTMTC6HRYAVFIBX2ESRDIU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2ZBTTTMTC6HRYAVFIBX2ESRDIU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2ZBTTTMTC6HRYAVFIBX2ESRDIU/action/storage_attestation","attest_author":"https://pith.science/pith/2ZBTTTMTC6HRYAVFIBX2ESRDIU/action/author_attestation","sign_citation":"https://pith.science/pith/2ZBTTTMTC6HRYAVFIBX2ESRDIU/action/citation_signature","submit_replication":"https://pith.science/pith/2ZBTTTMTC6HRYAVFIBX2ESRDIU/action/replication_record"}},"created_at":"2026-07-05T03:09:18.161485+00:00","updated_at":"2026-07-05T03:09:18.161485+00:00"}