{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:73YCYKKUSFXZQ7PZHLH5YLHHKJ","short_pith_number":"pith:73YCYKKU","schema_version":"1.0","canonical_sha256":"fef02c2954916f987df93acfdc2ce752718901d2b5d910961cecea4d2edf8ca2","source":{"kind":"arxiv","id":"2606.21939","version":1},"attestation_state":"computed","paper":{"title":"Beyond Value Benchmarks: Measuring Value-Structure Alignment in Large Language Models via Symmetric Q-Sorts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"China), Deyi Xiong (TJUNLP Lab, Jingting Zheng, Linhao Yu, School of Computer Science, Technology, Tianjin, Tianjin University, Yongqi Leng, Yuqi Ren","submitted_at":"2026-06-20T08:15:41Z","abstract_excerpt":"Large Language Models (LLMs) are increasingly deployed in contexts requiring complex moral reasoning and value trade-offs. However, existing evaluations typically rely on item-level behavioral metrics, which fail to capture how models structurally prioritize competing values as a cohesive system. To address this, we propose a symmetric human-LLM evaluation framework, grounded in Q methodology, to measure value-structure alignment. Under our protocol, humans and models sort an identical 140-item moral statement set into a shared nine-column forced distribution; for LLMs, we elicit strict rankin"},"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":"2606.21939","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-20T08:15:41Z","cross_cats_sorted":[],"title_canon_sha256":"05d016f6194a8fb83bf8a8322e5e3192f4c2d400e865898db14e95ac7079ec89","abstract_canon_sha256":"2f69260ded5c3cf90d2c33c2df9ddb567309b30bebf9b867eee063738c2c4d21"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:03.651299Z","signature_b64":"ODyIHh7oiURh0eSpGe55vJg6Sorq4TbXDdL5CSMNDmXbI+Pje7ytDYVO9v0JtaVeAziIP21XTXuFVfBt1xFUCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fef02c2954916f987df93acfdc2ce752718901d2b5d910961cecea4d2edf8ca2","last_reissued_at":"2026-06-23T02:13:03.650892Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:03.650892Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Value Benchmarks: Measuring Value-Structure Alignment in Large Language Models via Symmetric Q-Sorts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"China), Deyi Xiong (TJUNLP Lab, Jingting Zheng, Linhao Yu, School of Computer Science, Technology, Tianjin, Tianjin University, Yongqi Leng, Yuqi Ren","submitted_at":"2026-06-20T08:15:41Z","abstract_excerpt":"Large Language Models (LLMs) are increasingly deployed in contexts requiring complex moral reasoning and value trade-offs. However, existing evaluations typically rely on item-level behavioral metrics, which fail to capture how models structurally prioritize competing values as a cohesive system. To address this, we propose a symmetric human-LLM evaluation framework, grounded in Q methodology, to measure value-structure alignment. Under our protocol, humans and models sort an identical 140-item moral statement set into a shared nine-column forced distribution; for LLMs, we elicit strict rankin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21939","kind":"arxiv","version":1},"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/2606.21939/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":"2606.21939","created_at":"2026-06-23T02:13:03.650957+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.21939v1","created_at":"2026-06-23T02:13:03.650957+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21939","created_at":"2026-06-23T02:13:03.650957+00:00"},{"alias_kind":"pith_short_12","alias_value":"73YCYKKUSFXZ","created_at":"2026-06-23T02:13:03.650957+00:00"},{"alias_kind":"pith_short_16","alias_value":"73YCYKKUSFXZQ7PZ","created_at":"2026-06-23T02:13:03.650957+00:00"},{"alias_kind":"pith_short_8","alias_value":"73YCYKKU","created_at":"2026-06-23T02:13:03.650957+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/73YCYKKUSFXZQ7PZHLH5YLHHKJ","json":"https://pith.science/pith/73YCYKKUSFXZQ7PZHLH5YLHHKJ.json","graph_json":"https://pith.science/api/pith-number/73YCYKKUSFXZQ7PZHLH5YLHHKJ/graph.json","events_json":"https://pith.science/api/pith-number/73YCYKKUSFXZQ7PZHLH5YLHHKJ/events.json","paper":"https://pith.science/paper/73YCYKKU"},"agent_actions":{"view_html":"https://pith.science/pith/73YCYKKUSFXZQ7PZHLH5YLHHKJ","download_json":"https://pith.science/pith/73YCYKKUSFXZQ7PZHLH5YLHHKJ.json","view_paper":"https://pith.science/paper/73YCYKKU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.21939&json=true","fetch_graph":"https://pith.science/api/pith-number/73YCYKKUSFXZQ7PZHLH5YLHHKJ/graph.json","fetch_events":"https://pith.science/api/pith-number/73YCYKKUSFXZQ7PZHLH5YLHHKJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/73YCYKKUSFXZQ7PZHLH5YLHHKJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/73YCYKKUSFXZQ7PZHLH5YLHHKJ/action/storage_attestation","attest_author":"https://pith.science/pith/73YCYKKUSFXZQ7PZHLH5YLHHKJ/action/author_attestation","sign_citation":"https://pith.science/pith/73YCYKKUSFXZQ7PZHLH5YLHHKJ/action/citation_signature","submit_replication":"https://pith.science/pith/73YCYKKUSFXZQ7PZHLH5YLHHKJ/action/replication_record"}},"created_at":"2026-06-23T02:13:03.650957+00:00","updated_at":"2026-06-23T02:13:03.650957+00:00"}