{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:6TGHMEAA3SI5MLBIVXUYWSJ6UW","short_pith_number":"pith:6TGHMEAA","schema_version":"1.0","canonical_sha256":"f4cc761000dc91d62c28ade98b493ea596a385fa182dd26a586ee2c0c4b86def","source":{"kind":"arxiv","id":"2112.09301","version":1},"attestation_state":"computed","paper":{"title":"Overview of the HASOC Subtrack at FIRE 2021: Hate Speech and Offensive Content Identification in English and Indo-Aryan Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SI"],"primary_cat":"cs.CL","authors_text":"Amit Kumar Jaiswal, Durgesh Nandini, Gautam Kishore Shahi, Hiren Madhu, Johannes Schaefer, Marcos Zampieri, Prasenjit Majumder, Sandip Modha, Shrey Satapara, Tharindu Ranasinghe, Thomas Mandl","submitted_at":"2021-12-17T03:28:54Z","abstract_excerpt":"The widespread of offensive content online such as hate speech poses a growing societal problem. AI tools are necessary for supporting the moderation process at online platforms. For the evaluation of these identification tools, continuous experimentation with data sets in different languages are necessary. The HASOC track (Hate Speech and Offensive Content Identification) is dedicated to develop benchmark data for this purpose. This paper presents the HASOC subtrack for English, Hindi, and Marathi. The data set was assembled from Twitter. This subtrack has two sub-tasks. Task A is a binary cl"},"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":"2112.09301","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-17T03:28:54Z","cross_cats_sorted":["cs.AI","cs.SI"],"title_canon_sha256":"a0985cf236c337e558ac03baa11eaa21f8e19370213ed571c7eb4cfd360f2e84","abstract_canon_sha256":"ba15e68487c851d6763a237f64d9bb38d2fb500f0334b4f71bdd6f68eb8450ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:41:44.815736Z","signature_b64":"R6pIh/98l5knzev/Ehv29eQWRVrGnzO5+cF7X2AtvbutXL4f0PqU7XBihtnofjFgC9LKLvLaBwCkdRtZ2sziAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4cc761000dc91d62c28ade98b493ea596a385fa182dd26a586ee2c0c4b86def","last_reissued_at":"2026-07-05T03:41:44.815373Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:41:44.815373Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Overview of the HASOC Subtrack at FIRE 2021: Hate Speech and Offensive Content Identification in English and Indo-Aryan Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SI"],"primary_cat":"cs.CL","authors_text":"Amit Kumar Jaiswal, Durgesh Nandini, Gautam Kishore Shahi, Hiren Madhu, Johannes Schaefer, Marcos Zampieri, Prasenjit Majumder, Sandip Modha, Shrey Satapara, Tharindu Ranasinghe, Thomas Mandl","submitted_at":"2021-12-17T03:28:54Z","abstract_excerpt":"The widespread of offensive content online such as hate speech poses a growing societal problem. AI tools are necessary for supporting the moderation process at online platforms. For the evaluation of these identification tools, continuous experimentation with data sets in different languages are necessary. The HASOC track (Hate Speech and Offensive Content Identification) is dedicated to develop benchmark data for this purpose. This paper presents the HASOC subtrack for English, Hindi, and Marathi. The data set was assembled from Twitter. This subtrack has two sub-tasks. Task A is a binary cl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.09301","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/2112.09301/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":"2112.09301","created_at":"2026-07-05T03:41:44.815430+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.09301v1","created_at":"2026-07-05T03:41:44.815430+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.09301","created_at":"2026-07-05T03:41:44.815430+00:00"},{"alias_kind":"pith_short_12","alias_value":"6TGHMEAA3SI5","created_at":"2026-07-05T03:41:44.815430+00:00"},{"alias_kind":"pith_short_16","alias_value":"6TGHMEAA3SI5MLBI","created_at":"2026-07-05T03:41:44.815430+00:00"},{"alias_kind":"pith_short_8","alias_value":"6TGHMEAA","created_at":"2026-07-05T03:41:44.815430+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.18576","citing_title":"A Modular Taxonomy for Hate Speech Definitions and Its Impact on Zero-Shot LLM Classification Performance","ref_index":2024,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6TGHMEAA3SI5MLBIVXUYWSJ6UW","json":"https://pith.science/pith/6TGHMEAA3SI5MLBIVXUYWSJ6UW.json","graph_json":"https://pith.science/api/pith-number/6TGHMEAA3SI5MLBIVXUYWSJ6UW/graph.json","events_json":"https://pith.science/api/pith-number/6TGHMEAA3SI5MLBIVXUYWSJ6UW/events.json","paper":"https://pith.science/paper/6TGHMEAA"},"agent_actions":{"view_html":"https://pith.science/pith/6TGHMEAA3SI5MLBIVXUYWSJ6UW","download_json":"https://pith.science/pith/6TGHMEAA3SI5MLBIVXUYWSJ6UW.json","view_paper":"https://pith.science/paper/6TGHMEAA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.09301&json=true","fetch_graph":"https://pith.science/api/pith-number/6TGHMEAA3SI5MLBIVXUYWSJ6UW/graph.json","fetch_events":"https://pith.science/api/pith-number/6TGHMEAA3SI5MLBIVXUYWSJ6UW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6TGHMEAA3SI5MLBIVXUYWSJ6UW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6TGHMEAA3SI5MLBIVXUYWSJ6UW/action/storage_attestation","attest_author":"https://pith.science/pith/6TGHMEAA3SI5MLBIVXUYWSJ6UW/action/author_attestation","sign_citation":"https://pith.science/pith/6TGHMEAA3SI5MLBIVXUYWSJ6UW/action/citation_signature","submit_replication":"https://pith.science/pith/6TGHMEAA3SI5MLBIVXUYWSJ6UW/action/replication_record"}},"created_at":"2026-07-05T03:41:44.815430+00:00","updated_at":"2026-07-05T03:41:44.815430+00:00"}