{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TZOR2QROB5IO6H5QCG7G54YKCE","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":"aac65acd1bd82f55693bb6d7019b91b474c626e7cc0922bd25d5e38a18a9684e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2024-07-03T19:53:47Z","title_canon_sha256":"f2007470bec7da9175592e876b3b5caae76bdb6cab81ce24f6a32e34acce1177"},"schema_version":"1.0","source":{"id":"2407.03479","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.03479","created_at":"2026-07-05T08:39:55Z"},{"alias_kind":"arxiv_version","alias_value":"2407.03479v1","created_at":"2026-07-05T08:39:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.03479","created_at":"2026-07-05T08:39:55Z"},{"alias_kind":"pith_short_12","alias_value":"TZOR2QROB5IO","created_at":"2026-07-05T08:39:55Z"},{"alias_kind":"pith_short_16","alias_value":"TZOR2QROB5IO6H5Q","created_at":"2026-07-05T08:39:55Z"},{"alias_kind":"pith_short_8","alias_value":"TZOR2QRO","created_at":"2026-07-05T08:39:55Z"}],"graph_snapshots":[{"event_id":"sha256:a8835389bdc57b6272e69bb9bc30e0ea0ebf98f6284344624703b7f9d20a13c3","target":"graph","created_at":"2026-07-05T08:39:55Z","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/2407.03479/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Traditional reference-based metrics, such as BLEU and ROUGE, are less effective for assessing outputs from Large Language Models (LLMs) that produce highly creative or superior-quality text, or in situations where reference outputs are unavailable. While human evaluation remains an option, it is costly and difficult to scale. Recent work using LLMs as evaluators (LLM-as-a-judge) is promising, but trust and reliability remain a significant concern. Integrating human input is crucial to ensure criteria used to evaluate are aligned with the human's intent, and evaluations are robust and consisten","authors_text":"Elizabeth Daly, James Johnson, Martin Santillan Cooper, Michael Desmond, Qian Pan, Rahul Nair, Werner Geyer, Zahra Ashktorab","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2024-07-03T19:53:47Z","title":"Human-Centered Design Recommendations for LLM-as-a-Judge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.03479","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":"sha256:83d977b126f81148a013489681b343a54bac1ecb381b67799745662ac4c108d0","target":"record","created_at":"2026-07-05T08:39:55Z","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":"aac65acd1bd82f55693bb6d7019b91b474c626e7cc0922bd25d5e38a18a9684e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2024-07-03T19:53:47Z","title_canon_sha256":"f2007470bec7da9175592e876b3b5caae76bdb6cab81ce24f6a32e34acce1177"},"schema_version":"1.0","source":{"id":"2407.03479","kind":"arxiv","version":1}},"canonical_sha256":"9e5d1d422e0f50ef1fb011be6ef30a113dbd351f63a082d23904a79f822dd9d7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9e5d1d422e0f50ef1fb011be6ef30a113dbd351f63a082d23904a79f822dd9d7","first_computed_at":"2026-07-05T08:39:55.632619Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:39:55.632619Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jQgKYWvtVh/4cOPYDUXZ49DskSBQDq50k/xNOxrvb80AomFkHI9bWc3+BBEjq0wH9Q7y+8gXW49GUfHPq+ItBw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:39:55.633141Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.03479","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:83d977b126f81148a013489681b343a54bac1ecb381b67799745662ac4c108d0","sha256:a8835389bdc57b6272e69bb9bc30e0ea0ebf98f6284344624703b7f9d20a13c3"],"state_sha256":"2735566fba4227c9a2ff6cc9b5da0bc40f42441e9406582e89c75307d0e306e9"}