{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:YXPZZZ6RSH35RLEUJJSTSTAPMP","short_pith_number":"pith:YXPZZZ6R","canonical_record":{"source":{"id":"2310.02876","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-04T15:10:06Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"a0bff72b65978619f479fdb9733f571186e1ca998b94be63cf0bf297b7f18dd2","abstract_canon_sha256":"cad171137ae59448519ff8f1bfe8e1f9c6c715e170e41ddc4022547b81d59133"},"schema_version":"1.0"},"canonical_sha256":"c5df9ce7d191f7d8ac944a65394c0f63f4e061f7a307d1354e4b93edd58db93c","source":{"kind":"arxiv","id":"2310.02876","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.02876","created_at":"2026-07-05T06:57:14Z"},{"alias_kind":"arxiv_version","alias_value":"2310.02876v1","created_at":"2026-07-05T06:57:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.02876","created_at":"2026-07-05T06:57:14Z"},{"alias_kind":"pith_short_12","alias_value":"YXPZZZ6RSH35","created_at":"2026-07-05T06:57:14Z"},{"alias_kind":"pith_short_16","alias_value":"YXPZZZ6RSH35RLEU","created_at":"2026-07-05T06:57:14Z"},{"alias_kind":"pith_short_8","alias_value":"YXPZZZ6R","created_at":"2026-07-05T06:57:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:YXPZZZ6RSH35RLEUJJSTSTAPMP","target":"record","payload":{"canonical_record":{"source":{"id":"2310.02876","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-04T15:10:06Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"a0bff72b65978619f479fdb9733f571186e1ca998b94be63cf0bf297b7f18dd2","abstract_canon_sha256":"cad171137ae59448519ff8f1bfe8e1f9c6c715e170e41ddc4022547b81d59133"},"schema_version":"1.0"},"canonical_sha256":"c5df9ce7d191f7d8ac944a65394c0f63f4e061f7a307d1354e4b93edd58db93c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:57:14.929865Z","signature_b64":"9UQHVrCmqt5S4eeRXjp5VAVqnDidFwnDJvkAXr0t+2PMxe2nbOg8y7fN6mJOOLiyxD2pLIkKqad1O00AGKJDDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c5df9ce7d191f7d8ac944a65394c0f63f4e061f7a307d1354e4b93edd58db93c","last_reissued_at":"2026-07-05T06:57:14.929410Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:57:14.929410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.02876","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:57:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"86G9SSu3iGWcYoIF+lhZR0c/vQXwi/2wHmDm/FIGw5VSkZLw7GAL2lp7GPqFqHD34sL1fit7RPIpOKyDslJdCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T17:08:56.265330Z"},"content_sha256":"3b60601097ff2ada0cffdb17a6f7824086580c034ed571862829b200c6e5664a","schema_version":"1.0","event_id":"sha256:3b60601097ff2ada0cffdb17a6f7824086580c034ed571862829b200c6e5664a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:YXPZZZ6RSH35RLEUJJSTSTAPMP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hate Speech Detection in Limited Data Contexts using Synthetic Data Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.CL","authors_text":"Aman Khullar, Cuong V. Nguyen, Daniel Nkemelu, Michael L. Best","submitted_at":"2023-10-04T15:10:06Z","abstract_excerpt":"A growing body of work has focused on text classification methods for detecting the increasing amount of hate speech posted online. This progress has been limited to only a select number of highly-resourced languages causing detection systems to either under-perform or not exist in limited data contexts. This is majorly caused by a lack of training data which is expensive to collect and curate in these settings. In this work, we propose a data augmentation approach that addresses the problem of lack of data for online hate speech detection in limited data contexts using synthetic data generati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.02876","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/2310.02876/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":"2026-07-05T06:57:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VbkN8Dds29lCcgEvlCr2aYPvJoRLFeM5dtO07dto+UX+/NFh3+s3ONZuzh/ScDuRSY22ebDRRSaHqB11WUYpBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T17:08:56.265721Z"},"content_sha256":"330270744b84e8ff56f0b550510019b47ee61aab01c1405940dea2cd59c5e25f","schema_version":"1.0","event_id":"sha256:330270744b84e8ff56f0b550510019b47ee61aab01c1405940dea2cd59c5e25f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YXPZZZ6RSH35RLEUJJSTSTAPMP/bundle.json","state_url":"https://pith.science/pith/YXPZZZ6RSH35RLEUJJSTSTAPMP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YXPZZZ6RSH35RLEUJJSTSTAPMP/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":"2026-07-11T17:08:56Z","links":{"resolver":"https://pith.science/pith/YXPZZZ6RSH35RLEUJJSTSTAPMP","bundle":"https://pith.science/pith/YXPZZZ6RSH35RLEUJJSTSTAPMP/bundle.json","state":"https://pith.science/pith/YXPZZZ6RSH35RLEUJJSTSTAPMP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YXPZZZ6RSH35RLEUJJSTSTAPMP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:YXPZZZ6RSH35RLEUJJSTSTAPMP","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":"cad171137ae59448519ff8f1bfe8e1f9c6c715e170e41ddc4022547b81d59133","cross_cats_sorted":["cs.CY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-04T15:10:06Z","title_canon_sha256":"a0bff72b65978619f479fdb9733f571186e1ca998b94be63cf0bf297b7f18dd2"},"schema_version":"1.0","source":{"id":"2310.02876","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.02876","created_at":"2026-07-05T06:57:14Z"},{"alias_kind":"arxiv_version","alias_value":"2310.02876v1","created_at":"2026-07-05T06:57:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.02876","created_at":"2026-07-05T06:57:14Z"},{"alias_kind":"pith_short_12","alias_value":"YXPZZZ6RSH35","created_at":"2026-07-05T06:57:14Z"},{"alias_kind":"pith_short_16","alias_value":"YXPZZZ6RSH35RLEU","created_at":"2026-07-05T06:57:14Z"},{"alias_kind":"pith_short_8","alias_value":"YXPZZZ6R","created_at":"2026-07-05T06:57:14Z"}],"graph_snapshots":[{"event_id":"sha256:330270744b84e8ff56f0b550510019b47ee61aab01c1405940dea2cd59c5e25f","target":"graph","created_at":"2026-07-05T06:57:14Z","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/2310.02876/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A growing body of work has focused on text classification methods for detecting the increasing amount of hate speech posted online. This progress has been limited to only a select number of highly-resourced languages causing detection systems to either under-perform or not exist in limited data contexts. This is majorly caused by a lack of training data which is expensive to collect and curate in these settings. In this work, we propose a data augmentation approach that addresses the problem of lack of data for online hate speech detection in limited data contexts using synthetic data generati","authors_text":"Aman Khullar, Cuong V. Nguyen, Daniel Nkemelu, Michael L. Best","cross_cats":["cs.CY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-04T15:10:06Z","title":"Hate Speech Detection in Limited Data Contexts using Synthetic Data Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.02876","kind":"arxiv","version":1},"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":"sha256:3b60601097ff2ada0cffdb17a6f7824086580c034ed571862829b200c6e5664a","target":"record","created_at":"2026-07-05T06:57:14Z","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":"cad171137ae59448519ff8f1bfe8e1f9c6c715e170e41ddc4022547b81d59133","cross_cats_sorted":["cs.CY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-04T15:10:06Z","title_canon_sha256":"a0bff72b65978619f479fdb9733f571186e1ca998b94be63cf0bf297b7f18dd2"},"schema_version":"1.0","source":{"id":"2310.02876","kind":"arxiv","version":1}},"canonical_sha256":"c5df9ce7d191f7d8ac944a65394c0f63f4e061f7a307d1354e4b93edd58db93c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c5df9ce7d191f7d8ac944a65394c0f63f4e061f7a307d1354e4b93edd58db93c","first_computed_at":"2026-07-05T06:57:14.929410Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:57:14.929410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9UQHVrCmqt5S4eeRXjp5VAVqnDidFwnDJvkAXr0t+2PMxe2nbOg8y7fN6mJOOLiyxD2pLIkKqad1O00AGKJDDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:57:14.929865Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.02876","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3b60601097ff2ada0cffdb17a6f7824086580c034ed571862829b200c6e5664a","sha256:330270744b84e8ff56f0b550510019b47ee61aab01c1405940dea2cd59c5e25f"],"state_sha256":"ddbd75b5680da54807d3bfa41afc050215d72e0620e1470a55cced206e13c623"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4vWNlr3bsnPaGEVVlHOuAtClGY4DkRr/zswcfEP3lVh57kx/cO59A/46EGsOhnvmsR8n4Oygby5AuPjuDCTgAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-11T17:08:56.267979Z","bundle_sha256":"37548f0953cb43fdab5b776c4ac66485814ba60aee26d4bd79b1655956a64ed8"}}