{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:U3NMQBCZ6C36RADYKHTMYZK42B","short_pith_number":"pith:U3NMQBCZ","schema_version":"1.0","canonical_sha256":"a6dac80459f0b7e8807851e6cc655cd05ac95af4f08d462a1376d07b5d1f9294","source":{"kind":"arxiv","id":"2310.00378","version":4},"attestation_state":"computed","paper":{"title":"ValueDCG: Measuring Comprehensive Human Value Understanding Ability of Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.CL","authors_text":"Fengshuo Bai, Jun Gao, Yaodong Yang, Zhaowei Zhang","submitted_at":"2023-09-30T13:47:55Z","abstract_excerpt":"Personal values are a crucial factor behind human decision-making. Considering that Large Language Models (LLMs) have been shown to impact human decisions significantly, it is essential to make sure they accurately understand human values to ensure their safety. However, evaluating their grasp of these values is complex due to the value's intricate and adaptable nature. We argue that truly understanding values in LLMs requires considering both \"know what\" and \"know why\". To this end, we present a comprehensive evaluation metric, ValueDCG (Value Discriminator-Critique Gap), to quantitatively as"},"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":"2310.00378","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-30T13:47:55Z","cross_cats_sorted":["cs.AI","cs.CY"],"title_canon_sha256":"76868d8e0249c4511363c0904aa9901eaf797b162970ebf0993c07664eedf4db","abstract_canon_sha256":"37a75837d5830d4b0b7242fefa76774506d4933f7067509ceb3b0467c6be3bcf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:31.889912Z","signature_b64":"sUuzh9NWd/APA9bc+MN22NzsxR5gHPm30kQcqPI9TSakEFU57zJ70bglN1Sufq0pNStimtYOFBSPzjTiX9nCBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6dac80459f0b7e8807851e6cc655cd05ac95af4f08d462a1376d07b5d1f9294","last_reissued_at":"2026-07-05T08:32:31.889426Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:31.889426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ValueDCG: Measuring Comprehensive Human Value Understanding Ability of Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.CL","authors_text":"Fengshuo Bai, Jun Gao, Yaodong Yang, Zhaowei Zhang","submitted_at":"2023-09-30T13:47:55Z","abstract_excerpt":"Personal values are a crucial factor behind human decision-making. Considering that Large Language Models (LLMs) have been shown to impact human decisions significantly, it is essential to make sure they accurately understand human values to ensure their safety. However, evaluating their grasp of these values is complex due to the value's intricate and adaptable nature. We argue that truly understanding values in LLMs requires considering both \"know what\" and \"know why\". To this end, we present a comprehensive evaluation metric, ValueDCG (Value Discriminator-Critique Gap), to quantitatively as"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.00378","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/2310.00378/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":"2310.00378","created_at":"2026-07-05T08:32:31.889486+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.00378v4","created_at":"2026-07-05T08:32:31.889486+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.00378","created_at":"2026-07-05T08:32:31.889486+00:00"},{"alias_kind":"pith_short_12","alias_value":"U3NMQBCZ6C36","created_at":"2026-07-05T08:32:31.889486+00:00"},{"alias_kind":"pith_short_16","alias_value":"U3NMQBCZ6C36RADY","created_at":"2026-07-05T08:32:31.889486+00:00"},{"alias_kind":"pith_short_8","alias_value":"U3NMQBCZ","created_at":"2026-07-05T08:32:31.889486+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.04343","citing_title":"Psychologically Enhanced AI Agents","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U3NMQBCZ6C36RADYKHTMYZK42B","json":"https://pith.science/pith/U3NMQBCZ6C36RADYKHTMYZK42B.json","graph_json":"https://pith.science/api/pith-number/U3NMQBCZ6C36RADYKHTMYZK42B/graph.json","events_json":"https://pith.science/api/pith-number/U3NMQBCZ6C36RADYKHTMYZK42B/events.json","paper":"https://pith.science/paper/U3NMQBCZ"},"agent_actions":{"view_html":"https://pith.science/pith/U3NMQBCZ6C36RADYKHTMYZK42B","download_json":"https://pith.science/pith/U3NMQBCZ6C36RADYKHTMYZK42B.json","view_paper":"https://pith.science/paper/U3NMQBCZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.00378&json=true","fetch_graph":"https://pith.science/api/pith-number/U3NMQBCZ6C36RADYKHTMYZK42B/graph.json","fetch_events":"https://pith.science/api/pith-number/U3NMQBCZ6C36RADYKHTMYZK42B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U3NMQBCZ6C36RADYKHTMYZK42B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U3NMQBCZ6C36RADYKHTMYZK42B/action/storage_attestation","attest_author":"https://pith.science/pith/U3NMQBCZ6C36RADYKHTMYZK42B/action/author_attestation","sign_citation":"https://pith.science/pith/U3NMQBCZ6C36RADYKHTMYZK42B/action/citation_signature","submit_replication":"https://pith.science/pith/U3NMQBCZ6C36RADYKHTMYZK42B/action/replication_record"}},"created_at":"2026-07-05T08:32:31.889486+00:00","updated_at":"2026-07-05T08:32:31.889486+00:00"}