{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PM7VT45FNNDORRZV767TTBFDLA","short_pith_number":"pith:PM7VT45F","canonical_record":{"source":{"id":"2406.06369","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-10T15:30:13Z","cross_cats_sorted":[],"title_canon_sha256":"b7f5a1b4a9b79deacc3426269764d2ff9260c9ced93e0b67eba899ab758d7ba2","abstract_canon_sha256":"d696822ce2f2f77c36a91adf726e8d4bb6b6e7bc9eba3bf253b0bece455ec062"},"schema_version":"1.0"},"canonical_sha256":"7b3f59f3a56b46e8c735ffbf3984a3583e3da850d17c47f1553640d28f8ce87f","source":{"kind":"arxiv","id":"2406.06369","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.06369","created_at":"2026-07-05T09:16:49Z"},{"alias_kind":"arxiv_version","alias_value":"2406.06369v4","created_at":"2026-07-05T09:16:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06369","created_at":"2026-07-05T09:16:49Z"},{"alias_kind":"pith_short_12","alias_value":"PM7VT45FNNDO","created_at":"2026-07-05T09:16:49Z"},{"alias_kind":"pith_short_16","alias_value":"PM7VT45FNNDORRZV","created_at":"2026-07-05T09:16:49Z"},{"alias_kind":"pith_short_8","alias_value":"PM7VT45F","created_at":"2026-07-05T09:16:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PM7VT45FNNDORRZV767TTBFDLA","target":"record","payload":{"canonical_record":{"source":{"id":"2406.06369","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-10T15:30:13Z","cross_cats_sorted":[],"title_canon_sha256":"b7f5a1b4a9b79deacc3426269764d2ff9260c9ced93e0b67eba899ab758d7ba2","abstract_canon_sha256":"d696822ce2f2f77c36a91adf726e8d4bb6b6e7bc9eba3bf253b0bece455ec062"},"schema_version":"1.0"},"canonical_sha256":"7b3f59f3a56b46e8c735ffbf3984a3583e3da850d17c47f1553640d28f8ce87f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:16:49.935373Z","signature_b64":"jO29L8gXOD6EoOr9y4zX9glovFcvj72G9YDxDC/gaaVsKvhOBFfa68KuB5pxtlfBYQacTAY2gA4NGkc3ldxtBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b3f59f3a56b46e8c735ffbf3984a3583e3da850d17c47f1553640d28f8ce87f","last_reissued_at":"2026-07-05T09:16:49.934889Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:16:49.934889Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.06369","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:16:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j7HFoW71YNv7pL819zh5mBsI7Dl0qNS3454iejmu4hbqdjnzeAFmEWoXugcxk24I6bKcV0CG6jae+y66JgrjDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:01:17.708705Z"},"content_sha256":"de05aa1b7c1c37192afd1f4990caa1bd7333631bc9507f88012f272c3a00595c","schema_version":"1.0","event_id":"sha256:de05aa1b7c1c37192afd1f4990caa1bd7333631bc9507f88012f272c3a00595c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PM7VT45FNNDORRZV767TTBFDLA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Annotation alignment: Comparing LLM and human annotations of conversational safety","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Emma Pierson, Pang Wei Koh, Rajiv Movva","submitted_at":"2024-06-10T15:30:13Z","abstract_excerpt":"Do LLMs align with human perceptions of safety? We study this question via annotation alignment, the extent to which LLMs and humans agree when annotating the safety of user-chatbot conversations. We leverage the recent DICES dataset (Aroyo et al., 2023), in which 350 conversations are each rated for safety by 112 annotators spanning 10 race-gender groups. GPT-4 achieves a Pearson correlation of $r = 0.59$ with the average annotator rating, \\textit{higher} than the median annotator's correlation with the average ($r=0.51$). We show that larger datasets are needed to resolve whether LLMs exhibi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06369","kind":"arxiv","version":4},"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/2406.06369/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":"2026-07-05T09:16:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+Ts4TCQvAP7RU0B5Hr0FURLwHhlNTI1r9G28J03KCXQpHi+CkkHal5JfA9xp8JGJS/bGF9RrEFI/W3a0YpCuBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:01:17.709065Z"},"content_sha256":"984f7566fa18e1d386b6d4303c4d46849247e9dfde28e0f71fce2c84520b6680","schema_version":"1.0","event_id":"sha256:984f7566fa18e1d386b6d4303c4d46849247e9dfde28e0f71fce2c84520b6680"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PM7VT45FNNDORRZV767TTBFDLA/bundle.json","state_url":"https://pith.science/pith/PM7VT45FNNDORRZV767TTBFDLA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PM7VT45FNNDORRZV767TTBFDLA/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":"2026-07-07T11:01:17Z","links":{"resolver":"https://pith.science/pith/PM7VT45FNNDORRZV767TTBFDLA","bundle":"https://pith.science/pith/PM7VT45FNNDORRZV767TTBFDLA/bundle.json","state":"https://pith.science/pith/PM7VT45FNNDORRZV767TTBFDLA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PM7VT45FNNDORRZV767TTBFDLA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PM7VT45FNNDORRZV767TTBFDLA","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":"d696822ce2f2f77c36a91adf726e8d4bb6b6e7bc9eba3bf253b0bece455ec062","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-10T15:30:13Z","title_canon_sha256":"b7f5a1b4a9b79deacc3426269764d2ff9260c9ced93e0b67eba899ab758d7ba2"},"schema_version":"1.0","source":{"id":"2406.06369","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.06369","created_at":"2026-07-05T09:16:49Z"},{"alias_kind":"arxiv_version","alias_value":"2406.06369v4","created_at":"2026-07-05T09:16:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06369","created_at":"2026-07-05T09:16:49Z"},{"alias_kind":"pith_short_12","alias_value":"PM7VT45FNNDO","created_at":"2026-07-05T09:16:49Z"},{"alias_kind":"pith_short_16","alias_value":"PM7VT45FNNDORRZV","created_at":"2026-07-05T09:16:49Z"},{"alias_kind":"pith_short_8","alias_value":"PM7VT45F","created_at":"2026-07-05T09:16:49Z"}],"graph_snapshots":[{"event_id":"sha256:984f7566fa18e1d386b6d4303c4d46849247e9dfde28e0f71fce2c84520b6680","target":"graph","created_at":"2026-07-05T09:16:49Z","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/2406.06369/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Do LLMs align with human perceptions of safety? We study this question via annotation alignment, the extent to which LLMs and humans agree when annotating the safety of user-chatbot conversations. We leverage the recent DICES dataset (Aroyo et al., 2023), in which 350 conversations are each rated for safety by 112 annotators spanning 10 race-gender groups. GPT-4 achieves a Pearson correlation of $r = 0.59$ with the average annotator rating, \\textit{higher} than the median annotator's correlation with the average ($r=0.51$). We show that larger datasets are needed to resolve whether LLMs exhibi","authors_text":"Emma Pierson, Pang Wei Koh, Rajiv Movva","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-10T15:30:13Z","title":"Annotation alignment: Comparing LLM and human annotations of conversational safety"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06369","kind":"arxiv","version":4},"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:de05aa1b7c1c37192afd1f4990caa1bd7333631bc9507f88012f272c3a00595c","target":"record","created_at":"2026-07-05T09:16:49Z","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":"d696822ce2f2f77c36a91adf726e8d4bb6b6e7bc9eba3bf253b0bece455ec062","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-10T15:30:13Z","title_canon_sha256":"b7f5a1b4a9b79deacc3426269764d2ff9260c9ced93e0b67eba899ab758d7ba2"},"schema_version":"1.0","source":{"id":"2406.06369","kind":"arxiv","version":4}},"canonical_sha256":"7b3f59f3a56b46e8c735ffbf3984a3583e3da850d17c47f1553640d28f8ce87f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7b3f59f3a56b46e8c735ffbf3984a3583e3da850d17c47f1553640d28f8ce87f","first_computed_at":"2026-07-05T09:16:49.934889Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:16:49.934889Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jO29L8gXOD6EoOr9y4zX9glovFcvj72G9YDxDC/gaaVsKvhOBFfa68KuB5pxtlfBYQacTAY2gA4NGkc3ldxtBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:16:49.935373Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.06369","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:de05aa1b7c1c37192afd1f4990caa1bd7333631bc9507f88012f272c3a00595c","sha256:984f7566fa18e1d386b6d4303c4d46849247e9dfde28e0f71fce2c84520b6680"],"state_sha256":"8ae1761887947ec9c90f51ebb098ca8cae637fbd1d3f9716c49f9b6f198cd9ff"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jhu2Gt2Ejutf11kLCcSzg1bGTUM3HQgXJPfaI6upQfzeRJXD1t27dSKnF4uMVg04N2PYNcuiXH8va71yfvUHDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T11:01:17.710877Z","bundle_sha256":"56508c0bb70445036ab3c119f741ff69c1894cfef3d06e34ad0f5dcea722b19a"}}