{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:2ZBTTTMTC6HRYAVFIBX2ESRDIU","short_pith_number":"pith:2ZBTTTMT","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"},"canonical_sha256":"d64339cd93178f1c02a5406fa24a2345261814057ccf1c78a4ce64357fdd5647","source":{"kind":"arxiv","id":"2104.04739","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.04739","created_at":"2026-07-05T03:09:18Z"},{"alias_kind":"arxiv_version","alias_value":"2104.04739v1","created_at":"2026-07-05T03:09:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.04739","created_at":"2026-07-05T03:09:18Z"},{"alias_kind":"pith_short_12","alias_value":"2ZBTTTMTC6HR","created_at":"2026-07-05T03:09:18Z"},{"alias_kind":"pith_short_16","alias_value":"2ZBTTTMTC6HRYAVF","created_at":"2026-07-05T03:09:18Z"},{"alias_kind":"pith_short_8","alias_value":"2ZBTTTMT","created_at":"2026-07-05T03:09:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:2ZBTTTMTC6HRYAVFIBX2ESRDIU","target":"record","payload":{"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"},"canonical_sha256":"d64339cd93178f1c02a5406fa24a2345261814057ccf1c78a4ce64357fdd5647","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"},"source_kind":"arxiv","source_id":"2104.04739","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:09:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/jiIqi6zxOSLymXSdFXKUD+RrvXuxmbZ8Rh5VscSzp+uh3fYPvldYtFv7PGC5NJkt6OreOlmMOE4sUNOR2NpBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T16:02:19.994728Z"},"content_sha256":"fd8fac85f8ccc75825fe375b2df0a37e1606e1f89d072a54343dcd6d3767aa6e","schema_version":"1.0","event_id":"sha256:fd8fac85f8ccc75825fe375b2df0a37e1606e1f89d072a54343dcd6d3767aa6e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:2ZBTTTMTC6HRYAVFIBX2ESRDIU","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:09:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"39vT1zm6yl1Ct3EjOzTGMZgRJzBfZp5g5qFNz7vQu2M50sXDwIC5/qmP5QcWp+/L6ZJb7lLQ9AOYeL1l1otKCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T16:02:19.995647Z"},"content_sha256":"2945ecf7359ae68d474b6e2fe16e682d2b1847bc96133298f3112d39f20bb1b0","schema_version":"1.0","event_id":"sha256:2945ecf7359ae68d474b6e2fe16e682d2b1847bc96133298f3112d39f20bb1b0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2ZBTTTMTC6HRYAVFIBX2ESRDIU/bundle.json","state_url":"https://pith.science/pith/2ZBTTTMTC6HRYAVFIBX2ESRDIU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2ZBTTTMTC6HRYAVFIBX2ESRDIU/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-22T16:02:19Z","links":{"resolver":"https://pith.science/pith/2ZBTTTMTC6HRYAVFIBX2ESRDIU","bundle":"https://pith.science/pith/2ZBTTTMTC6HRYAVFIBX2ESRDIU/bundle.json","state":"https://pith.science/pith/2ZBTTTMTC6HRYAVFIBX2ESRDIU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2ZBTTTMTC6HRYAVFIBX2ESRDIU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:2ZBTTTMTC6HRYAVFIBX2ESRDIU","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"8b44ffe98a48e5c0bcb92bb94fde297b3ff6f93acd2dda128805bce3826e2e39","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-10T11:27:32Z","title_canon_sha256":"fa08be65111f85ef7b0b717f9f4d7950ff83bf5fc90c1c3a018a61849e277eb4"},"schema_version":"1.0","source":{"id":"2104.04739","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.04739","created_at":"2026-07-05T03:09:18Z"},{"alias_kind":"arxiv_version","alias_value":"2104.04739v1","created_at":"2026-07-05T03:09:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.04739","created_at":"2026-07-05T03:09:18Z"},{"alias_kind":"pith_short_12","alias_value":"2ZBTTTMTC6HR","created_at":"2026-07-05T03:09:18Z"},{"alias_kind":"pith_short_16","alias_value":"2ZBTTTMTC6HRYAVF","created_at":"2026-07-05T03:09:18Z"},{"alias_kind":"pith_short_8","alias_value":"2ZBTTTMT","created_at":"2026-07-05T03:09:18Z"}],"graph_snapshots":[{"event_id":"sha256:2945ecf7359ae68d474b6e2fe16e682d2b1847bc96133298f3112d39f20bb1b0","target":"graph","created_at":"2026-07-05T03:09:18Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2104.04739/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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.","authors_text":"Anna Glazkova, Dmitry Morozov, Mikhail Kotyushev","cross_cats":["cs.AI","cs.IR","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-10T11:27:32Z","title":"MIPT-NSU-UTMN at SemEval-2021 Task 5: Ensembling Learning with Pre-trained Language Models for Toxic Spans Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.04739","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:fd8fac85f8ccc75825fe375b2df0a37e1606e1f89d072a54343dcd6d3767aa6e","target":"record","created_at":"2026-07-05T03:09:18Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"8b44ffe98a48e5c0bcb92bb94fde297b3ff6f93acd2dda128805bce3826e2e39","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-10T11:27:32Z","title_canon_sha256":"fa08be65111f85ef7b0b717f9f4d7950ff83bf5fc90c1c3a018a61849e277eb4"},"schema_version":"1.0","source":{"id":"2104.04739","kind":"arxiv","version":1}},"canonical_sha256":"d64339cd93178f1c02a5406fa24a2345261814057ccf1c78a4ce64357fdd5647","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d64339cd93178f1c02a5406fa24a2345261814057ccf1c78a4ce64357fdd5647","first_computed_at":"2026-07-05T03:09:18.161429Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:09:18.161429Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0cGOas8xifMKk+gO9U1Ru3B5V85luLeQf0x5aEM6urbqCDgPqZK8PTjlSYgYlylJA/MJ6EaHPQP8hmdHH3prCg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:09:18.161786Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.04739","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fd8fac85f8ccc75825fe375b2df0a37e1606e1f89d072a54343dcd6d3767aa6e","sha256:2945ecf7359ae68d474b6e2fe16e682d2b1847bc96133298f3112d39f20bb1b0"],"state_sha256":"9b23dc55a85b0810ee7a5f4ce1e396dd7fda6920b195306a085c624e480ead60"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Unb0q1OJZW+dr08jef1lRVc2KaxFrPukGDdx4ywgufK+Z9IIfKszApIkPCjHjWlKSqX6AjGF3d6IuNy76Ju1Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T16:02:20.001955Z","bundle_sha256":"6fa729312fbcbf8d18b84c12d18e911855242c73ef2dbab2427578e541a056b1"}}