{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:KTWO4PWDR2UIV5S362QVRQ3RHN","short_pith_number":"pith:KTWO4PWD","schema_version":"1.0","canonical_sha256":"54ecee3ec38ea88af65bf6a158c3713b478dfac454731da783a4aaed86231399","source":{"kind":"arxiv","id":"2102.12254","version":2},"attestation_state":"computed","paper":{"title":"NLRG at SemEval-2021 Task 5: Toxic Spans Detection Leveraging BERT-based Token Classification and Span Prediction Techniques","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Abheesht Sharma, Gunjan Chhablani, Harshit Pandey, Shan Suthaharan, Yash Bhartia","submitted_at":"2021-02-24T12:30:09Z","abstract_excerpt":"Toxicity detection of text has been a popular NLP task in the recent years. In SemEval-2021 Task-5 Toxic Spans Detection, the focus is on detecting toxic spans within passages. Most state-of-the-art span detection approaches employ various techniques, each of which can be broadly classified into Token Classification or Span Prediction approaches. In our paper, we explore simple versions of both of these approaches and their performance on the task. Specifically, we use BERT-based models -- BERT, RoBERTa, and SpanBERT for both approaches. We also combine these approaches and modify them to brin"},"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":"2102.12254","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-02-24T12:30:09Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"00f94b170c0d72042d499818bb6403cafc58f4f7a40eea2e1afef689ce27e3f5","abstract_canon_sha256":"e373748062fac62354ce57dc8b500f0b254c7265febed94d5bbd556245e7a23b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:05:32.690601Z","signature_b64":"uvMrNZGmoi9QU07VPWtgjV7+NKvu4Mdj49KwuY/IytQEhBX2f2lKFwZelxnw7cMTtCkUugpL/kC+ce8Tm7/UCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54ecee3ec38ea88af65bf6a158c3713b478dfac454731da783a4aaed86231399","last_reissued_at":"2026-07-05T03:05:32.690041Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:05:32.690041Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NLRG at SemEval-2021 Task 5: Toxic Spans Detection Leveraging BERT-based Token Classification and Span Prediction Techniques","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Abheesht Sharma, Gunjan Chhablani, Harshit Pandey, Shan Suthaharan, Yash Bhartia","submitted_at":"2021-02-24T12:30:09Z","abstract_excerpt":"Toxicity detection of text has been a popular NLP task in the recent years. In SemEval-2021 Task-5 Toxic Spans Detection, the focus is on detecting toxic spans within passages. Most state-of-the-art span detection approaches employ various techniques, each of which can be broadly classified into Token Classification or Span Prediction approaches. In our paper, we explore simple versions of both of these approaches and their performance on the task. Specifically, we use BERT-based models -- BERT, RoBERTa, and SpanBERT for both approaches. We also combine these approaches and modify them to brin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.12254","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/2102.12254/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":"2102.12254","created_at":"2026-07-05T03:05:32.690102+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.12254v2","created_at":"2026-07-05T03:05:32.690102+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.12254","created_at":"2026-07-05T03:05:32.690102+00:00"},{"alias_kind":"pith_short_12","alias_value":"KTWO4PWDR2UI","created_at":"2026-07-05T03:05:32.690102+00:00"},{"alias_kind":"pith_short_16","alias_value":"KTWO4PWDR2UIV5S3","created_at":"2026-07-05T03:05:32.690102+00:00"},{"alias_kind":"pith_short_8","alias_value":"KTWO4PWD","created_at":"2026-07-05T03:05:32.690102+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.08344","citing_title":"Bangla Grammatical Error Detection Leveraging Transformer-based Token Classification","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KTWO4PWDR2UIV5S362QVRQ3RHN","json":"https://pith.science/pith/KTWO4PWDR2UIV5S362QVRQ3RHN.json","graph_json":"https://pith.science/api/pith-number/KTWO4PWDR2UIV5S362QVRQ3RHN/graph.json","events_json":"https://pith.science/api/pith-number/KTWO4PWDR2UIV5S362QVRQ3RHN/events.json","paper":"https://pith.science/paper/KTWO4PWD"},"agent_actions":{"view_html":"https://pith.science/pith/KTWO4PWDR2UIV5S362QVRQ3RHN","download_json":"https://pith.science/pith/KTWO4PWDR2UIV5S362QVRQ3RHN.json","view_paper":"https://pith.science/paper/KTWO4PWD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.12254&json=true","fetch_graph":"https://pith.science/api/pith-number/KTWO4PWDR2UIV5S362QVRQ3RHN/graph.json","fetch_events":"https://pith.science/api/pith-number/KTWO4PWDR2UIV5S362QVRQ3RHN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KTWO4PWDR2UIV5S362QVRQ3RHN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KTWO4PWDR2UIV5S362QVRQ3RHN/action/storage_attestation","attest_author":"https://pith.science/pith/KTWO4PWDR2UIV5S362QVRQ3RHN/action/author_attestation","sign_citation":"https://pith.science/pith/KTWO4PWDR2UIV5S362QVRQ3RHN/action/citation_signature","submit_replication":"https://pith.science/pith/KTWO4PWDR2UIV5S362QVRQ3RHN/action/replication_record"}},"created_at":"2026-07-05T03:05:32.690102+00:00","updated_at":"2026-07-05T03:05:32.690102+00:00"}