{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:Z5AQBUTGPCETQFMCTQDNCVF3LI","short_pith_number":"pith:Z5AQBUTG","canonical_record":{"source":{"id":"2106.09775","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-17T19:25:39Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"518d2015549954c28ef8f3b4d777532749006ddcf1454fad08a4c4c139b31f00","abstract_canon_sha256":"dbf93292ab72ba87f90e6642abc08c1a73a9836799cba011c6d1f3a2be8071bf"},"schema_version":"1.0"},"canonical_sha256":"cf4100d26678893815829c06d154bb5a12f9281387640597e52d35d830b63aad","source":{"kind":"arxiv","id":"2106.09775","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.09775","created_at":"2026-07-05T03:30:40Z"},{"alias_kind":"arxiv_version","alias_value":"2106.09775v3","created_at":"2026-07-05T03:30:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.09775","created_at":"2026-07-05T03:30:40Z"},{"alias_kind":"pith_short_12","alias_value":"Z5AQBUTGPCET","created_at":"2026-07-05T03:30:40Z"},{"alias_kind":"pith_short_16","alias_value":"Z5AQBUTGPCETQFMC","created_at":"2026-07-05T03:30:40Z"},{"alias_kind":"pith_short_8","alias_value":"Z5AQBUTG","created_at":"2026-07-05T03:30:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:Z5AQBUTGPCETQFMCTQDNCVF3LI","target":"record","payload":{"canonical_record":{"source":{"id":"2106.09775","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-17T19:25:39Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"518d2015549954c28ef8f3b4d777532749006ddcf1454fad08a4c4c139b31f00","abstract_canon_sha256":"dbf93292ab72ba87f90e6642abc08c1a73a9836799cba011c6d1f3a2be8071bf"},"schema_version":"1.0"},"canonical_sha256":"cf4100d26678893815829c06d154bb5a12f9281387640597e52d35d830b63aad","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:30:40.034084Z","signature_b64":"JHRLnP+j+E0eUozs+EWYV9PUmcIIwL2Gvk4hugVH9vaLE+S+hoZ4kEK/vyN2zQfCJaYzKswgKlXlb8JdoKv7Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf4100d26678893815829c06d154bb5a12f9281387640597e52d35d830b63aad","last_reissued_at":"2026-07-05T03:30:40.033694Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:30:40.033694Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.09775","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:30:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c0nI/bQzWmtcYNSxIooHoFZmnHmkr5Oqo3deFQKPrpVi/mCkTpyJPFNqnLw68okybakLmJG+e3GbVBzIGvJ7BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T23:36:31.999798Z"},"content_sha256":"2aaea74b9f6f8062556c175f6ad78249184773f84e60706763c8dc7d02c7d934","schema_version":"1.0","event_id":"sha256:2aaea74b9f6f8062556c175f6ad78249184773f84e60706763c8dc7d02c7d934"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:Z5AQBUTGPCETQFMCTQDNCVF3LI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Information Retrieval Approach to Building Datasets for Hate Speech Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Dhiraj Murthy, Dinesh Balakrishnan, Matthew Lease, Md Mustafizur Rahman, Mucahid Kutlu","submitted_at":"2021-06-17T19:25:39Z","abstract_excerpt":"Building a benchmark dataset for hate speech detection presents various challenges. Firstly, because hate speech is relatively rare, random sampling of tweets to annotate is very inefficient in finding hate speech. To address this, prior datasets often include only tweets matching known \"hate words\". However, restricting data to a pre-defined vocabulary may exclude portions of the real-world phenomenon we seek to model. A second challenge is that definitions of hate speech tend to be highly varying and subjective. Annotators having diverse prior notions of hate speech may not only disagree wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.09775","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/2106.09775/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:30:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Htj0KR1mbVzejqvxtQpW+Ygbc10kP1JOqNijEHy3k0j9lrIji5Mf5erJlHADWL/tY1HAUA6Io6col7OMOeW/CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T23:36:32.000295Z"},"content_sha256":"021c895d9b3af233a78d5e8d185eddde1dc8c7b5677a7627e8251ceb42a9dcbc","schema_version":"1.0","event_id":"sha256:021c895d9b3af233a78d5e8d185eddde1dc8c7b5677a7627e8251ceb42a9dcbc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z5AQBUTGPCETQFMCTQDNCVF3LI/bundle.json","state_url":"https://pith.science/pith/Z5AQBUTGPCETQFMCTQDNCVF3LI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z5AQBUTGPCETQFMCTQDNCVF3LI/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-22T23:36:32Z","links":{"resolver":"https://pith.science/pith/Z5AQBUTGPCETQFMCTQDNCVF3LI","bundle":"https://pith.science/pith/Z5AQBUTGPCETQFMCTQDNCVF3LI/bundle.json","state":"https://pith.science/pith/Z5AQBUTGPCETQFMCTQDNCVF3LI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z5AQBUTGPCETQFMCTQDNCVF3LI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:Z5AQBUTGPCETQFMCTQDNCVF3LI","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"dbf93292ab72ba87f90e6642abc08c1a73a9836799cba011c6d1f3a2be8071bf","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-17T19:25:39Z","title_canon_sha256":"518d2015549954c28ef8f3b4d777532749006ddcf1454fad08a4c4c139b31f00"},"schema_version":"1.0","source":{"id":"2106.09775","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.09775","created_at":"2026-07-05T03:30:40Z"},{"alias_kind":"arxiv_version","alias_value":"2106.09775v3","created_at":"2026-07-05T03:30:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.09775","created_at":"2026-07-05T03:30:40Z"},{"alias_kind":"pith_short_12","alias_value":"Z5AQBUTGPCET","created_at":"2026-07-05T03:30:40Z"},{"alias_kind":"pith_short_16","alias_value":"Z5AQBUTGPCETQFMC","created_at":"2026-07-05T03:30:40Z"},{"alias_kind":"pith_short_8","alias_value":"Z5AQBUTG","created_at":"2026-07-05T03:30:40Z"}],"graph_snapshots":[{"event_id":"sha256:021c895d9b3af233a78d5e8d185eddde1dc8c7b5677a7627e8251ceb42a9dcbc","target":"graph","created_at":"2026-07-05T03:30:40Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2106.09775/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Building a benchmark dataset for hate speech detection presents various challenges. Firstly, because hate speech is relatively rare, random sampling of tweets to annotate is very inefficient in finding hate speech. To address this, prior datasets often include only tweets matching known \"hate words\". However, restricting data to a pre-defined vocabulary may exclude portions of the real-world phenomenon we seek to model. A second challenge is that definitions of hate speech tend to be highly varying and subjective. Annotators having diverse prior notions of hate speech may not only disagree wit","authors_text":"Dhiraj Murthy, Dinesh Balakrishnan, Matthew Lease, Md Mustafizur Rahman, Mucahid Kutlu","cross_cats":["cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-17T19:25:39Z","title":"An Information Retrieval Approach to Building Datasets for Hate Speech Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.09775","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2aaea74b9f6f8062556c175f6ad78249184773f84e60706763c8dc7d02c7d934","target":"record","created_at":"2026-07-05T03:30:40Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"dbf93292ab72ba87f90e6642abc08c1a73a9836799cba011c6d1f3a2be8071bf","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-17T19:25:39Z","title_canon_sha256":"518d2015549954c28ef8f3b4d777532749006ddcf1454fad08a4c4c139b31f00"},"schema_version":"1.0","source":{"id":"2106.09775","kind":"arxiv","version":3}},"canonical_sha256":"cf4100d26678893815829c06d154bb5a12f9281387640597e52d35d830b63aad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cf4100d26678893815829c06d154bb5a12f9281387640597e52d35d830b63aad","first_computed_at":"2026-07-05T03:30:40.033694Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:30:40.033694Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JHRLnP+j+E0eUozs+EWYV9PUmcIIwL2Gvk4hugVH9vaLE+S+hoZ4kEK/vyN2zQfCJaYzKswgKlXlb8JdoKv7Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:30:40.034084Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.09775","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2aaea74b9f6f8062556c175f6ad78249184773f84e60706763c8dc7d02c7d934","sha256:021c895d9b3af233a78d5e8d185eddde1dc8c7b5677a7627e8251ceb42a9dcbc"],"state_sha256":"9845d17b59d66c06aa7ce2dea9c9c7a7bcb9ed8f2c466acc37c7008720dd6a68"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j+aoDMuiEJVjbc90VZx1tamw0af2ZO0QDeDXm/G3I9uLDvxL2Y+lXDiY9QjI7UVOZbcWRTTQaG5DJO1kdP6TAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T23:36:32.004850Z","bundle_sha256":"0acd4515c5e19b56fb0cc983ed8312f7688b2d1e5665e607e26aff6442ff4ff2"}}