{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:YNW5DLYBCBCA4K6I7L52NGDFCB","short_pith_number":"pith:YNW5DLYB","canonical_record":{"source":{"id":"2506.01484","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-02T09:45:05Z","cross_cats_sorted":[],"title_canon_sha256":"bf9036842fb9cadc81c189fe43851c7b0c24290878007a92d8d61be42f97ba87","abstract_canon_sha256":"aef03c91a6468411863956a971570e13176651ac17fb58e7fc7eeeaf10867f5b"},"schema_version":"1.0"},"canonical_sha256":"c36dd1af0110440e2bc8fafba698651068132761fbb7155f2e8969a36737f755","source":{"kind":"arxiv","id":"2506.01484","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.01484","created_at":"2026-07-05T11:16:59Z"},{"alias_kind":"arxiv_version","alias_value":"2506.01484v2","created_at":"2026-07-05T11:16:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01484","created_at":"2026-07-05T11:16:59Z"},{"alias_kind":"pith_short_12","alias_value":"YNW5DLYBCBCA","created_at":"2026-07-05T11:16:59Z"},{"alias_kind":"pith_short_16","alias_value":"YNW5DLYBCBCA4K6I","created_at":"2026-07-05T11:16:59Z"},{"alias_kind":"pith_short_8","alias_value":"YNW5DLYB","created_at":"2026-07-05T11:16:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:YNW5DLYBCBCA4K6I7L52NGDFCB","target":"record","payload":{"canonical_record":{"source":{"id":"2506.01484","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-02T09:45:05Z","cross_cats_sorted":[],"title_canon_sha256":"bf9036842fb9cadc81c189fe43851c7b0c24290878007a92d8d61be42f97ba87","abstract_canon_sha256":"aef03c91a6468411863956a971570e13176651ac17fb58e7fc7eeeaf10867f5b"},"schema_version":"1.0"},"canonical_sha256":"c36dd1af0110440e2bc8fafba698651068132761fbb7155f2e8969a36737f755","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:59.836499Z","signature_b64":"ZvMG2lY1QgJSAlB8hPbG6xoC+zv6yPcKH07GpfPiWcnYgphvfzHvIGylFLhZvRcqnMptdq6e88CtHpDADd5eAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c36dd1af0110440e2bc8fafba698651068132761fbb7155f2e8969a36737f755","last_reissued_at":"2026-07-05T11:16:59.835802Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:59.835802Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.01484","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:16:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0nbMLsd0n4/HRU+JU5mXOyRWwRNns9FIgtzdK/34iaGdMnmbaBuZyJFrG09ieL1U7T8tjSfjYx+Wj4VGP2rJDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T14:13:33.085669Z"},"content_sha256":"d7bf3c30aab636ac647cd55ace110c9aa4dde00d31fe11266a2c31e2282b6f2c","schema_version":"1.0","event_id":"sha256:d7bf3c30aab636ac647cd55ace110c9aa4dde00d31fe11266a2c31e2282b6f2c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:YNW5DLYBCBCA4K6I7L52NGDFCB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLM in the Loop: Creating the ParaDeHate Dataset for Hate Speech Detoxification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ashish Yashwanth Kangen, Ercong Nie, Helmut Schmid, Hinrich Sch\\\"utze, Lukas Kouba, Michael F\\\"arber, Shuzhou Yuan","submitted_at":"2025-06-02T09:45:05Z","abstract_excerpt":"Detoxification, the task of rewriting harmful language into non-toxic text, has become increasingly important amid the growing prevalence of toxic content online. However, high-quality parallel datasets for detoxification, especially for hate speech, remain scarce due to the cost and sensitivity of human annotation. In this paper, we propose a novel LLM-in-the-loop pipeline leveraging GPT-4o-mini for automated detoxification. We first replicate the ParaDetox pipeline by replacing human annotators with an LLM and show that the LLM performs comparably to human annotation. Building on this, we co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01484","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.01484/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":"2026-07-05T11:16:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VnuIT7T/uzyynvIfZqQd0VdCXWFbfE125t/8Bcbomzo7y3xLO5fYwhNsRK+JmDoz8DyZ1MyfQkzA6SDE6N/HDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T14:13:33.086533Z"},"content_sha256":"cab65624b9c366f47042da8509bf0ab238b0ee63933b4bfb20f953e8706bbbe2","schema_version":"1.0","event_id":"sha256:cab65624b9c366f47042da8509bf0ab238b0ee63933b4bfb20f953e8706bbbe2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YNW5DLYBCBCA4K6I7L52NGDFCB/bundle.json","state_url":"https://pith.science/pith/YNW5DLYBCBCA4K6I7L52NGDFCB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YNW5DLYBCBCA4K6I7L52NGDFCB/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":"2026-08-14T14:13:33Z","links":{"resolver":"https://pith.science/pith/YNW5DLYBCBCA4K6I7L52NGDFCB","bundle":"https://pith.science/pith/YNW5DLYBCBCA4K6I7L52NGDFCB/bundle.json","state":"https://pith.science/pith/YNW5DLYBCBCA4K6I7L52NGDFCB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YNW5DLYBCBCA4K6I7L52NGDFCB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YNW5DLYBCBCA4K6I7L52NGDFCB","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":"aef03c91a6468411863956a971570e13176651ac17fb58e7fc7eeeaf10867f5b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-02T09:45:05Z","title_canon_sha256":"bf9036842fb9cadc81c189fe43851c7b0c24290878007a92d8d61be42f97ba87"},"schema_version":"1.0","source":{"id":"2506.01484","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.01484","created_at":"2026-07-05T11:16:59Z"},{"alias_kind":"arxiv_version","alias_value":"2506.01484v2","created_at":"2026-07-05T11:16:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01484","created_at":"2026-07-05T11:16:59Z"},{"alias_kind":"pith_short_12","alias_value":"YNW5DLYBCBCA","created_at":"2026-07-05T11:16:59Z"},{"alias_kind":"pith_short_16","alias_value":"YNW5DLYBCBCA4K6I","created_at":"2026-07-05T11:16:59Z"},{"alias_kind":"pith_short_8","alias_value":"YNW5DLYB","created_at":"2026-07-05T11:16:59Z"}],"graph_snapshots":[{"event_id":"sha256:cab65624b9c366f47042da8509bf0ab238b0ee63933b4bfb20f953e8706bbbe2","target":"graph","created_at":"2026-07-05T11:16:59Z","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/2506.01484/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Detoxification, the task of rewriting harmful language into non-toxic text, has become increasingly important amid the growing prevalence of toxic content online. However, high-quality parallel datasets for detoxification, especially for hate speech, remain scarce due to the cost and sensitivity of human annotation. In this paper, we propose a novel LLM-in-the-loop pipeline leveraging GPT-4o-mini for automated detoxification. We first replicate the ParaDetox pipeline by replacing human annotators with an LLM and show that the LLM performs comparably to human annotation. Building on this, we co","authors_text":"Ashish Yashwanth Kangen, Ercong Nie, Helmut Schmid, Hinrich Sch\\\"utze, Lukas Kouba, Michael F\\\"arber, Shuzhou Yuan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-02T09:45:05Z","title":"LLM in the Loop: Creating the ParaDeHate Dataset for Hate Speech Detoxification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01484","kind":"arxiv","version":2},"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:d7bf3c30aab636ac647cd55ace110c9aa4dde00d31fe11266a2c31e2282b6f2c","target":"record","created_at":"2026-07-05T11:16:59Z","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":"aef03c91a6468411863956a971570e13176651ac17fb58e7fc7eeeaf10867f5b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-02T09:45:05Z","title_canon_sha256":"bf9036842fb9cadc81c189fe43851c7b0c24290878007a92d8d61be42f97ba87"},"schema_version":"1.0","source":{"id":"2506.01484","kind":"arxiv","version":2}},"canonical_sha256":"c36dd1af0110440e2bc8fafba698651068132761fbb7155f2e8969a36737f755","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c36dd1af0110440e2bc8fafba698651068132761fbb7155f2e8969a36737f755","first_computed_at":"2026-07-05T11:16:59.835802Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:16:59.835802Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZvMG2lY1QgJSAlB8hPbG6xoC+zv6yPcKH07GpfPiWcnYgphvfzHvIGylFLhZvRcqnMptdq6e88CtHpDADd5eAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:16:59.836499Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.01484","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d7bf3c30aab636ac647cd55ace110c9aa4dde00d31fe11266a2c31e2282b6f2c","sha256:cab65624b9c366f47042da8509bf0ab238b0ee63933b4bfb20f953e8706bbbe2"],"state_sha256":"769c58e5d2579b37a565f1ef5dba4438ce5e701a37bdea4e4623e2f6703ab629"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NNtqcckXeVXu1RF8yu8kUsOSjHr5KjQH4WThvjiexWwNSoAFTy+DajJ2BuGtN/cDhYs0uSWCnq5HVITV4MCqCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T14:13:33.093919Z","bundle_sha256":"493c15c5dcfa021074de786b66cd3d0fc322d772e089293f9dd5ce51c8be0fd8"}}