{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:OXJG4AJKWLWVVYN7AT3BQVCWNZ","short_pith_number":"pith:OXJG4AJK","schema_version":"1.0","canonical_sha256":"75d26e012ab2ed5ae1bf04f61854566e40f2bfca04d27a42aee548a76b953fac","source":{"kind":"arxiv","id":"1802.09416","version":2},"attestation_state":"computed","paper":{"title":"A Quality Type-aware Annotated Corpus and Lexicon for Harassment Research","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amit Sheth, Krishnaprasad Thirunarayan, Lakshika Balasuriya, Mohammadreza Rezvan, Saeedeh Shekarpour, Valerie Shalin","submitted_at":"2018-02-26T15:59:22Z","abstract_excerpt":"Having a quality annotated corpus is essential especially for applied research. Despite the recent focus of Web science community on researching about cyberbullying, the community dose not still have standard benchmarks. In this paper, we publish first, a quality annotated corpus and second, an offensive words lexicon capturing different types type of harassment as (i) sexual harassment, (ii) racial harassment, (iii) appearance-related harassment, (iv) intellectual harassment, and (v) political harassment.We crawled data from Twitter using our offensive lexicon. Then relied on the human judge "},"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":"1802.09416","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-02-26T15:59:22Z","cross_cats_sorted":[],"title_canon_sha256":"4e9d43b8b4c9570fe0ef1e16b37fc83b58d1c7382a92fe7ab39e8f74f0603570","abstract_canon_sha256":"327b8ed9f2bdc61d5b329ef21ec3747d66893590188200101e78f24b1d927b84"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:04.853659Z","signature_b64":"JqrZ8c4AbJd2HLkX7KNdPgHkfDQM0YLGrF/Q6LsZtYNTC4ewJxKYjNHmjCIsnze72XcuKz92DrtkKiEbvnMmCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75d26e012ab2ed5ae1bf04f61854566e40f2bfca04d27a42aee548a76b953fac","last_reissued_at":"2026-05-18T00:15:04.852949Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:04.852949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Quality Type-aware Annotated Corpus and Lexicon for Harassment Research","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amit Sheth, Krishnaprasad Thirunarayan, Lakshika Balasuriya, Mohammadreza Rezvan, Saeedeh Shekarpour, Valerie Shalin","submitted_at":"2018-02-26T15:59:22Z","abstract_excerpt":"Having a quality annotated corpus is essential especially for applied research. Despite the recent focus of Web science community on researching about cyberbullying, the community dose not still have standard benchmarks. In this paper, we publish first, a quality annotated corpus and second, an offensive words lexicon capturing different types type of harassment as (i) sexual harassment, (ii) racial harassment, (iii) appearance-related harassment, (iv) intellectual harassment, and (v) political harassment.We crawled data from Twitter using our offensive lexicon. Then relied on the human judge "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.09416","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1802.09416","created_at":"2026-05-18T00:15:04.853063+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.09416v2","created_at":"2026-05-18T00:15:04.853063+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.09416","created_at":"2026-05-18T00:15:04.853063+00:00"},{"alias_kind":"pith_short_12","alias_value":"OXJG4AJKWLWV","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_16","alias_value":"OXJG4AJKWLWVVYN7","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_8","alias_value":"OXJG4AJK","created_at":"2026-05-18T12:32:43.782077+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OXJG4AJKWLWVVYN7AT3BQVCWNZ","json":"https://pith.science/pith/OXJG4AJKWLWVVYN7AT3BQVCWNZ.json","graph_json":"https://pith.science/api/pith-number/OXJG4AJKWLWVVYN7AT3BQVCWNZ/graph.json","events_json":"https://pith.science/api/pith-number/OXJG4AJKWLWVVYN7AT3BQVCWNZ/events.json","paper":"https://pith.science/paper/OXJG4AJK"},"agent_actions":{"view_html":"https://pith.science/pith/OXJG4AJKWLWVVYN7AT3BQVCWNZ","download_json":"https://pith.science/pith/OXJG4AJKWLWVVYN7AT3BQVCWNZ.json","view_paper":"https://pith.science/paper/OXJG4AJK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.09416&json=true","fetch_graph":"https://pith.science/api/pith-number/OXJG4AJKWLWVVYN7AT3BQVCWNZ/graph.json","fetch_events":"https://pith.science/api/pith-number/OXJG4AJKWLWVVYN7AT3BQVCWNZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OXJG4AJKWLWVVYN7AT3BQVCWNZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OXJG4AJKWLWVVYN7AT3BQVCWNZ/action/storage_attestation","attest_author":"https://pith.science/pith/OXJG4AJKWLWVVYN7AT3BQVCWNZ/action/author_attestation","sign_citation":"https://pith.science/pith/OXJG4AJKWLWVVYN7AT3BQVCWNZ/action/citation_signature","submit_replication":"https://pith.science/pith/OXJG4AJKWLWVVYN7AT3BQVCWNZ/action/replication_record"}},"created_at":"2026-05-18T00:15:04.853063+00:00","updated_at":"2026-05-18T00:15:04.853063+00:00"}