{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2ZCOI5YY6QSTINV5O53JZNSKSD","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":"0046bfc28324e68267038e5d84b243cc69b64d551bd912c4ced85789b3d3446d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-12T19:05:43Z","title_canon_sha256":"4d42a22c5bc2d402baa524e9f7bfd218ee85eb87dac21a78c2d044d10e6b45d4"},"schema_version":"1.0","source":{"id":"2406.08598","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.08598","created_at":"2026-07-05T10:34:08Z"},{"alias_kind":"arxiv_version","alias_value":"2406.08598v4","created_at":"2026-07-05T10:34:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.08598","created_at":"2026-07-05T10:34:08Z"},{"alias_kind":"pith_short_12","alias_value":"2ZCOI5YY6QST","created_at":"2026-07-05T10:34:08Z"},{"alias_kind":"pith_short_16","alias_value":"2ZCOI5YY6QSTINV5","created_at":"2026-07-05T10:34:08Z"},{"alias_kind":"pith_short_8","alias_value":"2ZCOI5YY","created_at":"2026-07-05T10:34:08Z"}],"graph_snapshots":[{"event_id":"sha256:c160858a91a2ff552378d8129ffd14bc7c86b173ecdbe8c555600504565aaa11","target":"graph","created_at":"2026-07-05T10:34:08Z","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/2406.08598/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As Large Language Models (LLMs) continue to evolve, evaluating them remains a persistent challenge. Many recent evaluations use LLMs as judges to score outputs from other LLMs, often relying on a single large model like GPT-4o. However, using a single LLM judge is prone to intra-model bias, and many tasks - such as those related to emotional intelligence, creative writing, and persuasiveness - may be too subjective for a single model to judge fairly. We introduce the Language Model Council (LMC), where a group of LLMs collaborate to create tests, respond to them, and evaluate each other's resp","authors_text":"Amanda Cercas Curry, Benjamin Genchel, Flor Miriam Plaza-del-Arco, Justin Zhao","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-12T19:05:43Z","title":"Language Model Council: Democratically Benchmarking Foundation Models on Highly Subjective Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.08598","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":"sha256:9a583002c2b0da22be6e1e9f3bc607362e7435d05e8fa9c327d8189f81c418c4","target":"record","created_at":"2026-07-05T10:34:08Z","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":"0046bfc28324e68267038e5d84b243cc69b64d551bd912c4ced85789b3d3446d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-12T19:05:43Z","title_canon_sha256":"4d42a22c5bc2d402baa524e9f7bfd218ee85eb87dac21a78c2d044d10e6b45d4"},"schema_version":"1.0","source":{"id":"2406.08598","kind":"arxiv","version":4}},"canonical_sha256":"d644e47718f4253436bd77769cb64a90c302497115bc5987d2c36fa63a49450c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d644e47718f4253436bd77769cb64a90c302497115bc5987d2c36fa63a49450c","first_computed_at":"2026-07-05T10:34:08.179273Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:34:08.179273Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"35I3L5QOyhj4neB/26cI1lva0j51UmCuyaKe4UWDuQkF26NW+IUiCyP8MWKWkU5mXfCKd1/ST/ern5rc/qr8CA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:34:08.179815Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.08598","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9a583002c2b0da22be6e1e9f3bc607362e7435d05e8fa9c327d8189f81c418c4","sha256:c160858a91a2ff552378d8129ffd14bc7c86b173ecdbe8c555600504565aaa11"],"state_sha256":"58c0cb0fa5f4411748c249e5ef85f7b345a36c3c6d5e2b2bb10848200e5a8e13"}