{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:4PVGDVJHNLOMJNAV7LNFCVAVL2","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":"2546a0b420f4f6e44e8d815c1f0045d1ba2747cb08d853350f3c3a34ea63bd83","cross_cats_sorted":["cs.LG","cs.SI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-09T13:05:19Z","title_canon_sha256":"fb986327dc200cc872e7308182f4533a25a985a0cdb26576b4c2d100be533c12"},"schema_version":"1.0","source":{"id":"2010.04543","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.04543","created_at":"2026-07-05T01:41:39Z"},{"alias_kind":"arxiv_version","alias_value":"2010.04543v1","created_at":"2026-07-05T01:41:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.04543","created_at":"2026-07-05T01:41:39Z"},{"alias_kind":"pith_short_12","alias_value":"4PVGDVJHNLOM","created_at":"2026-07-05T01:41:39Z"},{"alias_kind":"pith_short_16","alias_value":"4PVGDVJHNLOMJNAV","created_at":"2026-07-05T01:41:39Z"},{"alias_kind":"pith_short_8","alias_value":"4PVGDVJH","created_at":"2026-07-05T01:41:39Z"}],"graph_snapshots":[{"event_id":"sha256:b30b97cbcf389398d945fb1aeecf425b352feb11821d52a317a514d900b427f7","target":"graph","created_at":"2026-07-05T01:41:39Z","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/2010.04543/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Hate speech and toxic comments are a common concern of social media platform users. Although these comments are, fortunately, the minority in these platforms, they are still capable of causing harm. Therefore, identifying these comments is an important task for studying and preventing the proliferation of toxicity in social media. Previous work in automatically detecting toxic comments focus mainly in English, with very few work in languages like Brazilian Portuguese. In this paper, we propose a new large-scale dataset for Brazilian Portuguese with tweets annotated as either toxic or non-toxic","authors_text":"Carolina Scarton, Diego F. Silva, Jo\\~ao A. Leite, Kalina Bontcheva","cross_cats":["cs.LG","cs.SI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-09T13:05:19Z","title":"Toxic Language Detection in Social Media for Brazilian Portuguese: New Dataset and Multilingual Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.04543","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":"sha256:2e372ede775d1e0b626caed0a51e384fb42c958f7099bc7b925af47afaff7890","target":"record","created_at":"2026-07-05T01:41:39Z","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":"2546a0b420f4f6e44e8d815c1f0045d1ba2747cb08d853350f3c3a34ea63bd83","cross_cats_sorted":["cs.LG","cs.SI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-09T13:05:19Z","title_canon_sha256":"fb986327dc200cc872e7308182f4533a25a985a0cdb26576b4c2d100be533c12"},"schema_version":"1.0","source":{"id":"2010.04543","kind":"arxiv","version":1}},"canonical_sha256":"e3ea61d5276adcc4b415fada5154155ea7fbfb67e53e509ac85107b999de6d6d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e3ea61d5276adcc4b415fada5154155ea7fbfb67e53e509ac85107b999de6d6d","first_computed_at":"2026-07-05T01:41:39.274327Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:41:39.274327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Fd+Zvqr1Sbp7k+aWT+IZ5aloANJ2LLqrRVXtKweYyorkkSBfPm0fFFdGHTU8T6j0rr2DeEzI4WVXwErFmREXCA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:41:39.274755Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.04543","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2e372ede775d1e0b626caed0a51e384fb42c958f7099bc7b925af47afaff7890","sha256:b30b97cbcf389398d945fb1aeecf425b352feb11821d52a317a514d900b427f7"],"state_sha256":"b68edf4f199a1b65d4cdae9c5dffd346cd1593735a7dde2f7702dcb86928d45f"}