{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:3QXRNL7GWELEWEWY2TYEGQKWRV","short_pith_number":"pith:3QXRNL7G","schema_version":"1.0","canonical_sha256":"dc2f16afe6b1164b12d8d4f04341568d45a16982e42a5813e5a0aa4ff7bc789a","source":{"kind":"arxiv","id":"2107.13592","version":3},"attestation_state":"computed","paper":{"title":"Detecting Abusive Albanian","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Erida Nurce, Jorgel Keci, Leon Derczynski","submitted_at":"2021-07-28T18:47:32Z","abstract_excerpt":"The ever growing usage of social media in the recent years has had a direct impact on the increased presence of hate speech and offensive speech in online platforms. Research on effective detection of such content has mainly focused on English and a few other widespread languages, while the leftover majority fail to have the same work put into them and thus cannot benefit from the steady advancements made in the field. In this paper we present \\textsc{Shaj}, an annotated Albanian dataset for hate speech and offensive speech that has been constructed from user-generated content on various socia"},"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":"2107.13592","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-07-28T18:47:32Z","cross_cats_sorted":[],"title_canon_sha256":"34f998889b585b0768288a9549582a8a9362b7c03e43091cb65db2859b62c637","abstract_canon_sha256":"9175ee2b74abe822629fe88fe23439bfe9698f1516d95e848cea0c4691c7931a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:21:48.235649Z","signature_b64":"ZHeT+J5+IlpvmvyAzjY8YYwRUIhDCPIPqawo54fU36cM5SOFL1ryHCLY8so3DMOqqVnJT52bfv9PvFDCtfHiDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc2f16afe6b1164b12d8d4f04341568d45a16982e42a5813e5a0aa4ff7bc789a","last_reissued_at":"2026-07-05T04:21:48.235148Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:21:48.235148Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Detecting Abusive Albanian","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Erida Nurce, Jorgel Keci, Leon Derczynski","submitted_at":"2021-07-28T18:47:32Z","abstract_excerpt":"The ever growing usage of social media in the recent years has had a direct impact on the increased presence of hate speech and offensive speech in online platforms. Research on effective detection of such content has mainly focused on English and a few other widespread languages, while the leftover majority fail to have the same work put into them and thus cannot benefit from the steady advancements made in the field. In this paper we present \\textsc{Shaj}, an annotated Albanian dataset for hate speech and offensive speech that has been constructed from user-generated content on various socia"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.13592","kind":"arxiv","version":3},"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/2107.13592/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":"2107.13592","created_at":"2026-07-05T04:21:48.235205+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.13592v3","created_at":"2026-07-05T04:21:48.235205+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.13592","created_at":"2026-07-05T04:21:48.235205+00:00"},{"alias_kind":"pith_short_12","alias_value":"3QXRNL7GWELE","created_at":"2026-07-05T04:21:48.235205+00:00"},{"alias_kind":"pith_short_16","alias_value":"3QXRNL7GWELEWEWY","created_at":"2026-07-05T04:21:48.235205+00:00"},{"alias_kind":"pith_short_8","alias_value":"3QXRNL7G","created_at":"2026-07-05T04:21:48.235205+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.04350","citing_title":"HatePRISM: Policies, Platforms, and Research Integration. Advancing NLP for Hate Speech Proactive Mitigation","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3QXRNL7GWELEWEWY2TYEGQKWRV","json":"https://pith.science/pith/3QXRNL7GWELEWEWY2TYEGQKWRV.json","graph_json":"https://pith.science/api/pith-number/3QXRNL7GWELEWEWY2TYEGQKWRV/graph.json","events_json":"https://pith.science/api/pith-number/3QXRNL7GWELEWEWY2TYEGQKWRV/events.json","paper":"https://pith.science/paper/3QXRNL7G"},"agent_actions":{"view_html":"https://pith.science/pith/3QXRNL7GWELEWEWY2TYEGQKWRV","download_json":"https://pith.science/pith/3QXRNL7GWELEWEWY2TYEGQKWRV.json","view_paper":"https://pith.science/paper/3QXRNL7G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.13592&json=true","fetch_graph":"https://pith.science/api/pith-number/3QXRNL7GWELEWEWY2TYEGQKWRV/graph.json","fetch_events":"https://pith.science/api/pith-number/3QXRNL7GWELEWEWY2TYEGQKWRV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3QXRNL7GWELEWEWY2TYEGQKWRV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3QXRNL7GWELEWEWY2TYEGQKWRV/action/storage_attestation","attest_author":"https://pith.science/pith/3QXRNL7GWELEWEWY2TYEGQKWRV/action/author_attestation","sign_citation":"https://pith.science/pith/3QXRNL7GWELEWEWY2TYEGQKWRV/action/citation_signature","submit_replication":"https://pith.science/pith/3QXRNL7GWELEWEWY2TYEGQKWRV/action/replication_record"}},"created_at":"2026-07-05T04:21:48.235205+00:00","updated_at":"2026-07-05T04:21:48.235205+00:00"}