{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:IBYRAR3IHSKFPHJL5574ZCRUMS","short_pith_number":"pith:IBYRAR3I","schema_version":"1.0","canonical_sha256":"40711047683c94579d2bef7fcc8a3464837c78d1681cc271ca705352e08845bc","source":{"kind":"arxiv","id":"2205.00328","version":1},"attestation_state":"computed","paper":{"title":"HateCheckHIn: Evaluating Hindi Hate Speech Detection Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Animesh Mukherjee, Binny Mathew, Mithun Das, Punyajoy Saha","submitted_at":"2022-04-30T19:09:09Z","abstract_excerpt":"Due to the sheer volume of online hate, the AI and NLP communities have started building models to detect such hateful content. Recently, multilingual hate is a major emerging challenge for automated detection where code-mixing or more than one language have been used for conversation in social media. Typically, hate speech detection models are evaluated by measuring their performance on the held-out test data using metrics such as accuracy and F1-score. While these metrics are useful, it becomes difficult to identify using them where the model is failing, and how to resolve it. To enable more"},"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":"2205.00328","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-30T19:09:09Z","cross_cats_sorted":[],"title_canon_sha256":"7b861d0489e4fb0ecd3cb574d4e05ce528b617ade49805ea764968a0c6f65f65","abstract_canon_sha256":"dd1d0ecca87bb7304c55a11db0ea0a54fe9dcb60997bff5dad2a2ba3f63d6cd9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:22:21.162248Z","signature_b64":"DWr4+vPM9SDbXaZjTU66VogcGDVk6SzXTdEIUElB7T+BZNgnLPhPvyqMrPapmjIDqen47hcWXv+9qDZgfUauAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40711047683c94579d2bef7fcc8a3464837c78d1681cc271ca705352e08845bc","last_reissued_at":"2026-07-05T04:22:21.161797Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:22:21.161797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HateCheckHIn: Evaluating Hindi Hate Speech Detection Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Animesh Mukherjee, Binny Mathew, Mithun Das, Punyajoy Saha","submitted_at":"2022-04-30T19:09:09Z","abstract_excerpt":"Due to the sheer volume of online hate, the AI and NLP communities have started building models to detect such hateful content. Recently, multilingual hate is a major emerging challenge for automated detection where code-mixing or more than one language have been used for conversation in social media. Typically, hate speech detection models are evaluated by measuring their performance on the held-out test data using metrics such as accuracy and F1-score. While these metrics are useful, it becomes difficult to identify using them where the model is failing, and how to resolve it. To enable more"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.00328","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/2205.00328/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":"2205.00328","created_at":"2026-07-05T04:22:21.161853+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.00328v1","created_at":"2026-07-05T04:22:21.161853+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.00328","created_at":"2026-07-05T04:22:21.161853+00:00"},{"alias_kind":"pith_short_12","alias_value":"IBYRAR3IHSKF","created_at":"2026-07-05T04:22:21.161853+00:00"},{"alias_kind":"pith_short_16","alias_value":"IBYRAR3IHSKFPHJL","created_at":"2026-07-05T04:22:21.161853+00:00"},{"alias_kind":"pith_short_8","alias_value":"IBYRAR3I","created_at":"2026-07-05T04:22:21.161853+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":51,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IBYRAR3IHSKFPHJL5574ZCRUMS","json":"https://pith.science/pith/IBYRAR3IHSKFPHJL5574ZCRUMS.json","graph_json":"https://pith.science/api/pith-number/IBYRAR3IHSKFPHJL5574ZCRUMS/graph.json","events_json":"https://pith.science/api/pith-number/IBYRAR3IHSKFPHJL5574ZCRUMS/events.json","paper":"https://pith.science/paper/IBYRAR3I"},"agent_actions":{"view_html":"https://pith.science/pith/IBYRAR3IHSKFPHJL5574ZCRUMS","download_json":"https://pith.science/pith/IBYRAR3IHSKFPHJL5574ZCRUMS.json","view_paper":"https://pith.science/paper/IBYRAR3I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.00328&json=true","fetch_graph":"https://pith.science/api/pith-number/IBYRAR3IHSKFPHJL5574ZCRUMS/graph.json","fetch_events":"https://pith.science/api/pith-number/IBYRAR3IHSKFPHJL5574ZCRUMS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IBYRAR3IHSKFPHJL5574ZCRUMS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IBYRAR3IHSKFPHJL5574ZCRUMS/action/storage_attestation","attest_author":"https://pith.science/pith/IBYRAR3IHSKFPHJL5574ZCRUMS/action/author_attestation","sign_citation":"https://pith.science/pith/IBYRAR3IHSKFPHJL5574ZCRUMS/action/citation_signature","submit_replication":"https://pith.science/pith/IBYRAR3IHSKFPHJL5574ZCRUMS/action/replication_record"}},"created_at":"2026-07-05T04:22:21.161853+00:00","updated_at":"2026-07-05T04:22:21.161853+00:00"}