{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:V6P24MEQJ22ZG2ARHHIAQDZFFO","short_pith_number":"pith:V6P24MEQ","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"},"canonical_sha256":"af9fae30904eb593681139d0080f252b899021d5be3f294d039bf2efa3fcd6a1","source":{"kind":"arxiv","id":"2103.09645","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.09645","created_at":"2026-07-05T02:30:32Z"},{"alias_kind":"arxiv_version","alias_value":"2103.09645v2","created_at":"2026-07-05T02:30:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.09645","created_at":"2026-07-05T02:30:32Z"},{"alias_kind":"pith_short_12","alias_value":"V6P24MEQJ22Z","created_at":"2026-07-05T02:30:32Z"},{"alias_kind":"pith_short_16","alias_value":"V6P24MEQJ22ZG2AR","created_at":"2026-07-05T02:30:32Z"},{"alias_kind":"pith_short_8","alias_value":"V6P24MEQ","created_at":"2026-07-05T02:30:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:V6P24MEQJ22ZG2ARHHIAQDZFFO","target":"record","payload":{"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"},"canonical_sha256":"af9fae30904eb593681139d0080f252b899021d5be3f294d039bf2efa3fcd6a1","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"},"source_kind":"arxiv","source_id":"2103.09645","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:30:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KSa0QUN4zU0EppT6FMLHfyuRf8HPWA3dHdtNrLKzOa2gGD9fv0+Ob2yjiHGe/XAbv7X+/Jut1ZQJtXcFzj0sBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:09:13.247198Z"},"content_sha256":"b24a5e3fe39496be165106c2bf44bfd2cf2fa307a3cd1a837eb69180e6fb49fa","schema_version":"1.0","event_id":"sha256:b24a5e3fe39496be165106c2bf44bfd2cf2fa307a3cd1a837eb69180e6fb49fa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:V6P24MEQJ22ZG2ARHHIAQDZFFO","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:30:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sd0SyXlxF/l0oKPGebXzo0NZWOGOfHTRV33wTiFV8Tqds5c12Tl+UuEmAOX+31VyaKF4n2aAaB7JBWsIy09wBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:09:13.247585Z"},"content_sha256":"961a80b6964b2659dcaf9ad9c7b6ca5ebd6c2092896816d29c4ffac77dffd038","schema_version":"1.0","event_id":"sha256:961a80b6964b2659dcaf9ad9c7b6ca5ebd6c2092896816d29c4ffac77dffd038"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V6P24MEQJ22ZG2ARHHIAQDZFFO/bundle.json","state_url":"https://pith.science/pith/V6P24MEQJ22ZG2ARHHIAQDZFFO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V6P24MEQJ22ZG2ARHHIAQDZFFO/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":"2026-07-07T07:09:13Z","links":{"resolver":"https://pith.science/pith/V6P24MEQJ22ZG2ARHHIAQDZFFO","bundle":"https://pith.science/pith/V6P24MEQJ22ZG2ARHHIAQDZFFO/bundle.json","state":"https://pith.science/pith/V6P24MEQJ22ZG2ARHHIAQDZFFO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V6P24MEQJ22ZG2ARHHIAQDZFFO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:V6P24MEQJ22ZG2ARHHIAQDZFFO","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":"1be35b304518032a3b31deaecac15c922ae4e51e390316ba585b6bf151a69fa0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-03-17T13:39:49Z","title_canon_sha256":"262bdfa140bb60867105dee372ed2e735dfb58d3f7c3a809a650c3a15990d6de"},"schema_version":"1.0","source":{"id":"2103.09645","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.09645","created_at":"2026-07-05T02:30:32Z"},{"alias_kind":"arxiv_version","alias_value":"2103.09645v2","created_at":"2026-07-05T02:30:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.09645","created_at":"2026-07-05T02:30:32Z"},{"alias_kind":"pith_short_12","alias_value":"V6P24MEQJ22Z","created_at":"2026-07-05T02:30:32Z"},{"alias_kind":"pith_short_16","alias_value":"V6P24MEQJ22ZG2AR","created_at":"2026-07-05T02:30:32Z"},{"alias_kind":"pith_short_8","alias_value":"V6P24MEQ","created_at":"2026-07-05T02:30:32Z"}],"graph_snapshots":[{"event_id":"sha256:961a80b6964b2659dcaf9ad9c7b6ca5ebd6c2092896816d29c4ffac77dffd038","target":"graph","created_at":"2026-07-05T02:30:32Z","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/2103.09645/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Akbar Karimi, Andrea Prati, Leonardo Rossi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-03-17T13:39:49Z","title":"UniParma at SemEval-2021 Task 5: Toxic Spans Detection Using CharacterBERT and Bag-of-Words Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.09645","kind":"arxiv","version":2},"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:b24a5e3fe39496be165106c2bf44bfd2cf2fa307a3cd1a837eb69180e6fb49fa","target":"record","created_at":"2026-07-05T02:30:32Z","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":"1be35b304518032a3b31deaecac15c922ae4e51e390316ba585b6bf151a69fa0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-03-17T13:39:49Z","title_canon_sha256":"262bdfa140bb60867105dee372ed2e735dfb58d3f7c3a809a650c3a15990d6de"},"schema_version":"1.0","source":{"id":"2103.09645","kind":"arxiv","version":2}},"canonical_sha256":"af9fae30904eb593681139d0080f252b899021d5be3f294d039bf2efa3fcd6a1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"af9fae30904eb593681139d0080f252b899021d5be3f294d039bf2efa3fcd6a1","first_computed_at":"2026-07-05T02:30:32.094310Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:30:32.094310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"df78xK8WTkM8p73ezdotVv4Im6IPKSTvF0rw9X+sW5XZ19WyXvCreFWxHe8bipWwIdmjgcQ1VyYs5ZKMaI7+Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:30:32.094724Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.09645","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b24a5e3fe39496be165106c2bf44bfd2cf2fa307a3cd1a837eb69180e6fb49fa","sha256:961a80b6964b2659dcaf9ad9c7b6ca5ebd6c2092896816d29c4ffac77dffd038"],"state_sha256":"41ddc10f9e431ef87d75fc14842c69563967b550e3a9d9fbc736f9e4954076c9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dn8MtmiO+unI6HUW+ahk+fb0btuDUOauYk17cCfpkz2fIpcQKAq2/rQlIKlbosGz2w2oFPfWgJDQa3ph/KIEDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T07:09:13.249465Z","bundle_sha256":"8b2e787b4b4fb3f50d13deb2c21400dcb47e29eab4b925ddaad434c552660e25"}}