{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:XQSYO3GQPURCR2DIZCXKWHODT4","short_pith_number":"pith:XQSYO3GQ","canonical_record":{"source":{"id":"2402.05624","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-08T12:28:18Z","cross_cats_sorted":["cs.AI","cs.HC"],"title_canon_sha256":"807d97c197b4db4622040da8b70e34e07e4108692812ddc92af2af6e5b76d2ba","abstract_canon_sha256":"88e315777c601292412f63bf62a430b6a563f831ee2fc3d4db9b576ad6d56c67"},"schema_version":"1.0"},"canonical_sha256":"bc25876cd07d2228e868c8aeab1dc39f30e99c6322afb56e3028276a400daf38","source":{"kind":"arxiv","id":"2402.05624","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.05624","created_at":"2026-07-05T07:42:53Z"},{"alias_kind":"arxiv_version","alias_value":"2402.05624v1","created_at":"2026-07-05T07:42:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.05624","created_at":"2026-07-05T07:42:53Z"},{"alias_kind":"pith_short_12","alias_value":"XQSYO3GQPURC","created_at":"2026-07-05T07:42:53Z"},{"alias_kind":"pith_short_16","alias_value":"XQSYO3GQPURCR2DI","created_at":"2026-07-05T07:42:53Z"},{"alias_kind":"pith_short_8","alias_value":"XQSYO3GQ","created_at":"2026-07-05T07:42:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:XQSYO3GQPURCR2DIZCXKWHODT4","target":"record","payload":{"canonical_record":{"source":{"id":"2402.05624","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-08T12:28:18Z","cross_cats_sorted":["cs.AI","cs.HC"],"title_canon_sha256":"807d97c197b4db4622040da8b70e34e07e4108692812ddc92af2af6e5b76d2ba","abstract_canon_sha256":"88e315777c601292412f63bf62a430b6a563f831ee2fc3d4db9b576ad6d56c67"},"schema_version":"1.0"},"canonical_sha256":"bc25876cd07d2228e868c8aeab1dc39f30e99c6322afb56e3028276a400daf38","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:42:53.611778Z","signature_b64":"QqkUjU62BpJ2PYzb+li59SIAGmuARps3cyrG+HqTJrGRexFf0bC2x1PoZqlWoAwhucljis7xcHh91ftoClIeBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc25876cd07d2228e868c8aeab1dc39f30e99c6322afb56e3028276a400daf38","last_reissued_at":"2026-07-05T07:42:53.611297Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:42:53.611297Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.05624","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":"2026-07-05T07:42:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rFAWJhEMZwn60VJ+kS/0Xmv99cu/r6kTpfBWyocwcAJxQATiIUUidu8JXs7ZjvF0xQsnoNjCb1KjRAdEw21GDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T02:54:52.635824Z"},"content_sha256":"7dc40e4abd865992dc0d3a412101ce07028e27a21030433ea1dd2d66d255ad32","schema_version":"1.0","event_id":"sha256:7dc40e4abd865992dc0d3a412101ce07028e27a21030433ea1dd2d66d255ad32"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:XQSYO3GQPURCR2DIZCXKWHODT4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Models for the Detection of Hate, Abuse and Profanity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CL","authors_text":"Aashka Trivedi, Bishwaranjan Bhattacharjee, Christoph Tillmann","submitted_at":"2024-02-08T12:28:18Z","abstract_excerpt":"Large Language Models (LLMs) are the cornerstone for many Natural Language Processing (NLP) tasks like sentiment analysis, document classification, named entity recognition, question answering, summarization, etc. LLMs are often trained on data which originates from the web. This data is prone to having content with Hate, Abuse and Profanity (HAP). For a detailed definition of HAP, please refer to the Appendix. Due to the LLMs being exposed to HAP content during training, the models learn it and may then generate hateful or profane content. For example, when the open-source RoBERTa model (spec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.05624","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/2402.05624/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":"2026-07-05T07:42:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dHuFjgx+tFaVvysiL9maqXSs+WclPs8LCdY/Lsh5gcP5HeVE/FD3jlY27EqHTDrqwUesKaKPS89RnHg3E6hxCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T02:54:52.636193Z"},"content_sha256":"25ede116d346f4402d64379ad8a0ec22fb3b2d091e71fc195d00d5d471da520d","schema_version":"1.0","event_id":"sha256:25ede116d346f4402d64379ad8a0ec22fb3b2d091e71fc195d00d5d471da520d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XQSYO3GQPURCR2DIZCXKWHODT4/bundle.json","state_url":"https://pith.science/pith/XQSYO3GQPURCR2DIZCXKWHODT4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XQSYO3GQPURCR2DIZCXKWHODT4/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":"2026-07-08T02:54:52Z","links":{"resolver":"https://pith.science/pith/XQSYO3GQPURCR2DIZCXKWHODT4","bundle":"https://pith.science/pith/XQSYO3GQPURCR2DIZCXKWHODT4/bundle.json","state":"https://pith.science/pith/XQSYO3GQPURCR2DIZCXKWHODT4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XQSYO3GQPURCR2DIZCXKWHODT4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XQSYO3GQPURCR2DIZCXKWHODT4","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":"88e315777c601292412f63bf62a430b6a563f831ee2fc3d4db9b576ad6d56c67","cross_cats_sorted":["cs.AI","cs.HC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-08T12:28:18Z","title_canon_sha256":"807d97c197b4db4622040da8b70e34e07e4108692812ddc92af2af6e5b76d2ba"},"schema_version":"1.0","source":{"id":"2402.05624","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.05624","created_at":"2026-07-05T07:42:53Z"},{"alias_kind":"arxiv_version","alias_value":"2402.05624v1","created_at":"2026-07-05T07:42:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.05624","created_at":"2026-07-05T07:42:53Z"},{"alias_kind":"pith_short_12","alias_value":"XQSYO3GQPURC","created_at":"2026-07-05T07:42:53Z"},{"alias_kind":"pith_short_16","alias_value":"XQSYO3GQPURCR2DI","created_at":"2026-07-05T07:42:53Z"},{"alias_kind":"pith_short_8","alias_value":"XQSYO3GQ","created_at":"2026-07-05T07:42:53Z"}],"graph_snapshots":[{"event_id":"sha256:25ede116d346f4402d64379ad8a0ec22fb3b2d091e71fc195d00d5d471da520d","target":"graph","created_at":"2026-07-05T07:42:53Z","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/2402.05624/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) are the cornerstone for many Natural Language Processing (NLP) tasks like sentiment analysis, document classification, named entity recognition, question answering, summarization, etc. LLMs are often trained on data which originates from the web. This data is prone to having content with Hate, Abuse and Profanity (HAP). For a detailed definition of HAP, please refer to the Appendix. Due to the LLMs being exposed to HAP content during training, the models learn it and may then generate hateful or profane content. For example, when the open-source RoBERTa model (spec","authors_text":"Aashka Trivedi, Bishwaranjan Bhattacharjee, Christoph Tillmann","cross_cats":["cs.AI","cs.HC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-08T12:28:18Z","title":"Efficient Models for the Detection of Hate, Abuse and Profanity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.05624","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":"sha256:7dc40e4abd865992dc0d3a412101ce07028e27a21030433ea1dd2d66d255ad32","target":"record","created_at":"2026-07-05T07:42:53Z","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":"88e315777c601292412f63bf62a430b6a563f831ee2fc3d4db9b576ad6d56c67","cross_cats_sorted":["cs.AI","cs.HC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-08T12:28:18Z","title_canon_sha256":"807d97c197b4db4622040da8b70e34e07e4108692812ddc92af2af6e5b76d2ba"},"schema_version":"1.0","source":{"id":"2402.05624","kind":"arxiv","version":1}},"canonical_sha256":"bc25876cd07d2228e868c8aeab1dc39f30e99c6322afb56e3028276a400daf38","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bc25876cd07d2228e868c8aeab1dc39f30e99c6322afb56e3028276a400daf38","first_computed_at":"2026-07-05T07:42:53.611297Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:42:53.611297Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QqkUjU62BpJ2PYzb+li59SIAGmuARps3cyrG+HqTJrGRexFf0bC2x1PoZqlWoAwhucljis7xcHh91ftoClIeBg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:42:53.611778Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.05624","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7dc40e4abd865992dc0d3a412101ce07028e27a21030433ea1dd2d66d255ad32","sha256:25ede116d346f4402d64379ad8a0ec22fb3b2d091e71fc195d00d5d471da520d"],"state_sha256":"9f2b1faaca574ceaf29d64204cc62bb5e0e5a2e69f3bd6153b667aea7689f521"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xr+hZqnCXvjUg5eybXhW5wsSjr0b2be85caZKXqPPk/BIIJSp1yJZgM65Ct6JJuUgXcxSX42GQfKlYXVm+nYDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T02:54:52.638218Z","bundle_sha256":"cf86b3f7406a53a4076f3c65e19369cf9bfb60f3ca626b92f6b0ed3dc0ec1e47"}}