{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2ZCOI5YY6QSTINV5O53JZNSKSD","short_pith_number":"pith:2ZCOI5YY","schema_version":"1.0","canonical_sha256":"d644e47718f4253436bd77769cb64a90c302497115bc5987d2c36fa63a49450c","source":{"kind":"arxiv","id":"2406.08598","version":4},"attestation_state":"computed","paper":{"title":"Language Model Council: Democratically Benchmarking Foundation Models on Highly Subjective Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Amanda Cercas Curry, Benjamin Genchel, Flor Miriam Plaza-del-Arco, Justin Zhao","submitted_at":"2024-06-12T19:05:43Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2406.08598","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-12T19:05:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4d42a22c5bc2d402baa524e9f7bfd218ee85eb87dac21a78c2d044d10e6b45d4","abstract_canon_sha256":"0046bfc28324e68267038e5d84b243cc69b64d551bd912c4ced85789b3d3446d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:34:08.179815Z","signature_b64":"35I3L5QOyhj4neB/26cI1lva0j51UmCuyaKe4UWDuQkF26NW+IUiCyP8MWKWkU5mXfCKd1/ST/ern5rc/qr8CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d644e47718f4253436bd77769cb64a90c302497115bc5987d2c36fa63a49450c","last_reissued_at":"2026-07-05T10:34:08.179273Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:34:08.179273Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language Model Council: Democratically Benchmarking Foundation Models on Highly Subjective Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Amanda Cercas Curry, Benjamin Genchel, Flor Miriam Plaza-del-Arco, Justin Zhao","submitted_at":"2024-06-12T19:05:43Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.08598","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/2406.08598/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2406.08598","created_at":"2026-07-05T10:34:08.179337+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.08598v4","created_at":"2026-07-05T10:34:08.179337+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.08598","created_at":"2026-07-05T10:34:08.179337+00:00"},{"alias_kind":"pith_short_12","alias_value":"2ZCOI5YY6QST","created_at":"2026-07-05T10:34:08.179337+00:00"},{"alias_kind":"pith_short_16","alias_value":"2ZCOI5YY6QSTINV5","created_at":"2026-07-05T10:34:08.179337+00:00"},{"alias_kind":"pith_short_8","alias_value":"2ZCOI5YY","created_at":"2026-07-05T10:34:08.179337+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08098","citing_title":"When Does Delegation Beat Majority? A Delegation-Based Aggregator for Multi-Sample LLM Inference","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06996","citing_title":"Self-Preference Bias in Rubric-Based Evaluation of Large Language Models","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2ZCOI5YY6QSTINV5O53JZNSKSD","json":"https://pith.science/pith/2ZCOI5YY6QSTINV5O53JZNSKSD.json","graph_json":"https://pith.science/api/pith-number/2ZCOI5YY6QSTINV5O53JZNSKSD/graph.json","events_json":"https://pith.science/api/pith-number/2ZCOI5YY6QSTINV5O53JZNSKSD/events.json","paper":"https://pith.science/paper/2ZCOI5YY"},"agent_actions":{"view_html":"https://pith.science/pith/2ZCOI5YY6QSTINV5O53JZNSKSD","download_json":"https://pith.science/pith/2ZCOI5YY6QSTINV5O53JZNSKSD.json","view_paper":"https://pith.science/paper/2ZCOI5YY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.08598&json=true","fetch_graph":"https://pith.science/api/pith-number/2ZCOI5YY6QSTINV5O53JZNSKSD/graph.json","fetch_events":"https://pith.science/api/pith-number/2ZCOI5YY6QSTINV5O53JZNSKSD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2ZCOI5YY6QSTINV5O53JZNSKSD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2ZCOI5YY6QSTINV5O53JZNSKSD/action/storage_attestation","attest_author":"https://pith.science/pith/2ZCOI5YY6QSTINV5O53JZNSKSD/action/author_attestation","sign_citation":"https://pith.science/pith/2ZCOI5YY6QSTINV5O53JZNSKSD/action/citation_signature","submit_replication":"https://pith.science/pith/2ZCOI5YY6QSTINV5O53JZNSKSD/action/replication_record"}},"created_at":"2026-07-05T10:34:08.179337+00:00","updated_at":"2026-07-05T10:34:08.179337+00:00"}