{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:L3P3CGA6JCHWTXWY5JIJTU5YK5","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":"0d2c60e044b12521178f051c62fae5b20ceed35910c61cfc40c6b3cc7820bad7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.HC","submitted_at":"2023-01-23T13:03:58Z","title_canon_sha256":"ff000bc05b56bea2294fa4be2c90bb3268120b99ddfca78e85b90d5f262565e1"},"schema_version":"1.0","source":{"id":"2301.09406","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.09406","created_at":"2026-07-05T06:09:08Z"},{"alias_kind":"arxiv_version","alias_value":"2301.09406v1","created_at":"2026-07-05T06:09:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.09406","created_at":"2026-07-05T06:09:08Z"},{"alias_kind":"pith_short_12","alias_value":"L3P3CGA6JCHW","created_at":"2026-07-05T06:09:08Z"},{"alias_kind":"pith_short_16","alias_value":"L3P3CGA6JCHWTXWY","created_at":"2026-07-05T06:09:08Z"},{"alias_kind":"pith_short_8","alias_value":"L3P3CGA6","created_at":"2026-07-05T06:09:08Z"}],"graph_snapshots":[{"event_id":"sha256:3f9159f34ea55a9ccd4e901044c3b1f5cffe3391dabdc89946d7e510aaed4771","target":"graph","created_at":"2026-07-05T06:09:08Z","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/2301.09406/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we present findings from an semi-experimental exploration of rater diversity and its influence on safety annotations of conversations generated by humans talking to a generative AI-chat bot. We find significant differences in judgments produced by raters from different geographic regions and annotation platforms, and correlate these perspectives with demographic sub-groups. Our work helps define best practices in model development -- specifically human evaluation of generative models -- on the backdrop of growing work on sociotechnical AI evaluations.","authors_text":"Alex Taylor, Christopher Homan, Ding Wang, Lora Aroyo, Mark Diaz, Vinodkumar Prabhakaran","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.HC","submitted_at":"2023-01-23T13:03:58Z","title":"The Reasonable Effectiveness of Diverse Evaluation Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.09406","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":"sha256:751b40f660ff87d6e57a30548d92e882c7bdde84b458098730d907406edea6d0","target":"record","created_at":"2026-07-05T06:09:08Z","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":"0d2c60e044b12521178f051c62fae5b20ceed35910c61cfc40c6b3cc7820bad7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.HC","submitted_at":"2023-01-23T13:03:58Z","title_canon_sha256":"ff000bc05b56bea2294fa4be2c90bb3268120b99ddfca78e85b90d5f262565e1"},"schema_version":"1.0","source":{"id":"2301.09406","kind":"arxiv","version":1}},"canonical_sha256":"5edfb1181e488f69ded8ea5099d3b85757ffda73d5d982616b273388886ba4ce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5edfb1181e488f69ded8ea5099d3b85757ffda73d5d982616b273388886ba4ce","first_computed_at":"2026-07-05T06:09:08.016529Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:09:08.016529Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pdG/Q3eKuH8Hg30MecsWNvot1iAoPgPlh6Su4fD/I8/SYF4nwrqbp6PgYSfloVaSpsnZQwrvjBmz53Tm3Z5ZAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:09:08.016961Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.09406","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:751b40f660ff87d6e57a30548d92e882c7bdde84b458098730d907406edea6d0","sha256:3f9159f34ea55a9ccd4e901044c3b1f5cffe3391dabdc89946d7e510aaed4771"],"state_sha256":"c1551d17d8eaab421799b2a70cb84bbe70e3a921f26fc527a243279bf9bc50fd"}