{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:F6VGQLWA2WMD2EEACIQ4WMBLBG","short_pith_number":"pith:F6VGQLWA","schema_version":"1.0","canonical_sha256":"2faa682ec0d5983d10801221cb302b09b37ee7db7dd1683c04ae5fa3864ecc69","source":{"kind":"arxiv","id":"2008.12448","version":1},"attestation_state":"computed","paper":{"title":"QutNocturnal@HASOC'19: CNN for Hate Speech and Offensive Content Identification in Hindi Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SI"],"primary_cat":"cs.CL","authors_text":"Md Abul Bashar, Richi Nayak","submitted_at":"2020-08-28T02:44:17Z","abstract_excerpt":"We describe our top-team solution to Task 1 for Hindi in the HASOC contest organised by FIRE 2019. The task is to identify hate speech and offensive language in Hindi. More specifically, it is a binary classification problem where a system is required to classify tweets into two classes: (a) \\emph{Hate and Offensive (HOF)} and (b) \\emph{Not Hate or Offensive (NOT)}. In contrast to the popular idea of pretraining word vectors (a.k.a. word embedding) with a large corpus from a general domain such as Wikipedia, we used a relatively small collection of relevant tweets (i.e. random and sarcasm twee"},"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":"2008.12448","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-08-28T02:44:17Z","cross_cats_sorted":["cs.LG","cs.SI"],"title_canon_sha256":"2f33836ca44ea4a8cdaf4d41a0f5fda357120750cae214ff97fda79985e7d08d","abstract_canon_sha256":"51c8661cda3cd10d6715752290957fc74965a8099d77e6514cab50d7f8db05b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:31:15.289750Z","signature_b64":"dkHIUF56XYN6cQ2RSeTab3E2Q+JyqlY3FW+9pUffp2umcejJjInUbKYccy1nzpsdXAIls4bJpFIrn2BCeQeDDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2faa682ec0d5983d10801221cb302b09b37ee7db7dd1683c04ae5fa3864ecc69","last_reissued_at":"2026-07-05T01:31:15.289394Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:31:15.289394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"QutNocturnal@HASOC'19: CNN for Hate Speech and Offensive Content Identification in Hindi Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SI"],"primary_cat":"cs.CL","authors_text":"Md Abul Bashar, Richi Nayak","submitted_at":"2020-08-28T02:44:17Z","abstract_excerpt":"We describe our top-team solution to Task 1 for Hindi in the HASOC contest organised by FIRE 2019. The task is to identify hate speech and offensive language in Hindi. More specifically, it is a binary classification problem where a system is required to classify tweets into two classes: (a) \\emph{Hate and Offensive (HOF)} and (b) \\emph{Not Hate or Offensive (NOT)}. In contrast to the popular idea of pretraining word vectors (a.k.a. word embedding) with a large corpus from a general domain such as Wikipedia, we used a relatively small collection of relevant tweets (i.e. random and sarcasm twee"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.12448","kind":"arxiv","version":1},"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/2008.12448/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":"2008.12448","created_at":"2026-07-05T01:31:15.289453+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.12448v1","created_at":"2026-07-05T01:31:15.289453+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.12448","created_at":"2026-07-05T01:31:15.289453+00:00"},{"alias_kind":"pith_short_12","alias_value":"F6VGQLWA2WMD","created_at":"2026-07-05T01:31:15.289453+00:00"},{"alias_kind":"pith_short_16","alias_value":"F6VGQLWA2WMD2EEA","created_at":"2026-07-05T01:31:15.289453+00:00"},{"alias_kind":"pith_short_8","alias_value":"F6VGQLWA","created_at":"2026-07-05T01:31:15.289453+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.23930","citing_title":"Leveraging the Potential of Prompt Engineering for Hate Speech Detection in Low-Resource Languages","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F6VGQLWA2WMD2EEACIQ4WMBLBG","json":"https://pith.science/pith/F6VGQLWA2WMD2EEACIQ4WMBLBG.json","graph_json":"https://pith.science/api/pith-number/F6VGQLWA2WMD2EEACIQ4WMBLBG/graph.json","events_json":"https://pith.science/api/pith-number/F6VGQLWA2WMD2EEACIQ4WMBLBG/events.json","paper":"https://pith.science/paper/F6VGQLWA"},"agent_actions":{"view_html":"https://pith.science/pith/F6VGQLWA2WMD2EEACIQ4WMBLBG","download_json":"https://pith.science/pith/F6VGQLWA2WMD2EEACIQ4WMBLBG.json","view_paper":"https://pith.science/paper/F6VGQLWA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.12448&json=true","fetch_graph":"https://pith.science/api/pith-number/F6VGQLWA2WMD2EEACIQ4WMBLBG/graph.json","fetch_events":"https://pith.science/api/pith-number/F6VGQLWA2WMD2EEACIQ4WMBLBG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F6VGQLWA2WMD2EEACIQ4WMBLBG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F6VGQLWA2WMD2EEACIQ4WMBLBG/action/storage_attestation","attest_author":"https://pith.science/pith/F6VGQLWA2WMD2EEACIQ4WMBLBG/action/author_attestation","sign_citation":"https://pith.science/pith/F6VGQLWA2WMD2EEACIQ4WMBLBG/action/citation_signature","submit_replication":"https://pith.science/pith/F6VGQLWA2WMD2EEACIQ4WMBLBG/action/replication_record"}},"created_at":"2026-07-05T01:31:15.289453+00:00","updated_at":"2026-07-05T01:31:15.289453+00:00"}