{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:V6P24MEQJ22ZG2ARHHIAQDZFFO","short_pith_number":"pith:V6P24MEQ","schema_version":"1.0","canonical_sha256":"af9fae30904eb593681139d0080f252b899021d5be3f294d039bf2efa3fcd6a1","source":{"kind":"arxiv","id":"2103.09645","version":2},"attestation_state":"computed","paper":{"title":"UniParma at SemEval-2021 Task 5: Toxic Spans Detection Using CharacterBERT and Bag-of-Words Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Akbar Karimi, Andrea Prati, Leonardo Rossi","submitted_at":"2021-03-17T13:39:49Z","abstract_excerpt":"With the ever-increasing availability of digital information, toxic content is also on the rise. Therefore, the detection of this type of language is of paramount importance. We tackle this problem utilizing a combination of a state-of-the-art pre-trained language model (CharacterBERT) and a traditional bag-of-words technique. Since the content is full of toxic words that have not been written according to their dictionary spelling, attendance to individual characters is crucial. Therefore, we use CharacterBERT to extract features based on the word characters. It consists of a CharacterCNN mod"},"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":"2103.09645","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-03-17T13:39:49Z","cross_cats_sorted":[],"title_canon_sha256":"262bdfa140bb60867105dee372ed2e735dfb58d3f7c3a809a650c3a15990d6de","abstract_canon_sha256":"1be35b304518032a3b31deaecac15c922ae4e51e390316ba585b6bf151a69fa0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:30:32.094724Z","signature_b64":"df78xK8WTkM8p73ezdotVv4Im6IPKSTvF0rw9X+sW5XZ19WyXvCreFWxHe8bipWwIdmjgcQ1VyYs5ZKMaI7+Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af9fae30904eb593681139d0080f252b899021d5be3f294d039bf2efa3fcd6a1","last_reissued_at":"2026-07-05T02:30:32.094310Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:30:32.094310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniParma at SemEval-2021 Task 5: Toxic Spans Detection Using CharacterBERT and Bag-of-Words Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Akbar Karimi, Andrea Prati, Leonardo Rossi","submitted_at":"2021-03-17T13:39:49Z","abstract_excerpt":"With the ever-increasing availability of digital information, toxic content is also on the rise. Therefore, the detection of this type of language is of paramount importance. We tackle this problem utilizing a combination of a state-of-the-art pre-trained language model (CharacterBERT) and a traditional bag-of-words technique. Since the content is full of toxic words that have not been written according to their dictionary spelling, attendance to individual characters is crucial. Therefore, we use CharacterBERT to extract features based on the word characters. It consists of a CharacterCNN mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.09645","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/2103.09645/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":"2103.09645","created_at":"2026-07-05T02:30:32.094383+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.09645v2","created_at":"2026-07-05T02:30:32.094383+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.09645","created_at":"2026-07-05T02:30:32.094383+00:00"},{"alias_kind":"pith_short_12","alias_value":"V6P24MEQJ22Z","created_at":"2026-07-05T02:30:32.094383+00:00"},{"alias_kind":"pith_short_16","alias_value":"V6P24MEQJ22ZG2AR","created_at":"2026-07-05T02:30:32.094383+00:00"},{"alias_kind":"pith_short_8","alias_value":"V6P24MEQ","created_at":"2026-07-05T02:30:32.094383+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/V6P24MEQJ22ZG2ARHHIAQDZFFO","json":"https://pith.science/pith/V6P24MEQJ22ZG2ARHHIAQDZFFO.json","graph_json":"https://pith.science/api/pith-number/V6P24MEQJ22ZG2ARHHIAQDZFFO/graph.json","events_json":"https://pith.science/api/pith-number/V6P24MEQJ22ZG2ARHHIAQDZFFO/events.json","paper":"https://pith.science/paper/V6P24MEQ"},"agent_actions":{"view_html":"https://pith.science/pith/V6P24MEQJ22ZG2ARHHIAQDZFFO","download_json":"https://pith.science/pith/V6P24MEQJ22ZG2ARHHIAQDZFFO.json","view_paper":"https://pith.science/paper/V6P24MEQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.09645&json=true","fetch_graph":"https://pith.science/api/pith-number/V6P24MEQJ22ZG2ARHHIAQDZFFO/graph.json","fetch_events":"https://pith.science/api/pith-number/V6P24MEQJ22ZG2ARHHIAQDZFFO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V6P24MEQJ22ZG2ARHHIAQDZFFO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V6P24MEQJ22ZG2ARHHIAQDZFFO/action/storage_attestation","attest_author":"https://pith.science/pith/V6P24MEQJ22ZG2ARHHIAQDZFFO/action/author_attestation","sign_citation":"https://pith.science/pith/V6P24MEQJ22ZG2ARHHIAQDZFFO/action/citation_signature","submit_replication":"https://pith.science/pith/V6P24MEQJ22ZG2ARHHIAQDZFFO/action/replication_record"}},"created_at":"2026-07-05T02:30:32.094383+00:00","updated_at":"2026-07-05T02:30:32.094383+00:00"}