{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:366WAVIZB7GQDAROESULQQYOZO","short_pith_number":"pith:366WAVIZ","schema_version":"1.0","canonical_sha256":"dfbd6055190fcd01822e24a8b8430ecb84de3f3c94546f1bf28c12357bfbe447","source":{"kind":"arxiv","id":"2505.01015","version":3},"attestation_state":"computed","paper":{"title":"Value Portrait: Assessing Language Models' Values through Psychometrically and Ecologically Valid Items","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dongmin Choi, Eun-Ju Lee, Jongwook Han, Woojung Song, Yohan Jo","submitted_at":"2025-05-02T05:26:50Z","abstract_excerpt":"The importance of benchmarks for assessing the values of language models has been pronounced due to the growing need of more authentic, human-aligned responses. However, existing benchmarks rely on human or machine annotations that are vulnerable to value-related biases. Furthermore, the tested scenarios often diverge from real-world contexts in which models are commonly used to generate text and express values. To address these issues, we propose the Value Portrait benchmark, a reliable framework for evaluating LLMs' value orientations with two key characteristics. First, the benchmark consis"},"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":"2505.01015","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-02T05:26:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e4c98566c847ebba2d8f174c01cacaff21465f6d28f408c29f018141b9ab2f37","abstract_canon_sha256":"af1666b32181336a2799a11744f2acf726c674393b9f30939a35795357fab3ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:26.652261Z","signature_b64":"gQMBWhdtvojZM7R7SJf9Wi/1GXehbI3tCKRaeqTwyKhf79BPa3mysWF1TZLcD/8BO0QEq/gCNzI4lY/pAzatDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dfbd6055190fcd01822e24a8b8430ecb84de3f3c94546f1bf28c12357bfbe447","last_reissued_at":"2026-07-05T11:19:26.651823Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:26.651823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Value Portrait: Assessing Language Models' Values through Psychometrically and Ecologically Valid Items","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dongmin Choi, Eun-Ju Lee, Jongwook Han, Woojung Song, Yohan Jo","submitted_at":"2025-05-02T05:26:50Z","abstract_excerpt":"The importance of benchmarks for assessing the values of language models has been pronounced due to the growing need of more authentic, human-aligned responses. However, existing benchmarks rely on human or machine annotations that are vulnerable to value-related biases. Furthermore, the tested scenarios often diverge from real-world contexts in which models are commonly used to generate text and express values. To address these issues, we propose the Value Portrait benchmark, a reliable framework for evaluating LLMs' value orientations with two key characteristics. First, the benchmark consis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.01015","kind":"arxiv","version":3},"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/2505.01015/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":"2505.01015","created_at":"2026-07-05T11:19:26.651874+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.01015v3","created_at":"2026-07-05T11:19:26.651874+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.01015","created_at":"2026-07-05T11:19:26.651874+00:00"},{"alias_kind":"pith_short_12","alias_value":"366WAVIZB7GQ","created_at":"2026-07-05T11:19:26.651874+00:00"},{"alias_kind":"pith_short_16","alias_value":"366WAVIZB7GQDARO","created_at":"2026-07-05T11:19:26.651874+00:00"},{"alias_kind":"pith_short_8","alias_value":"366WAVIZ","created_at":"2026-07-05T11:19:26.651874+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/366WAVIZB7GQDAROESULQQYOZO","json":"https://pith.science/pith/366WAVIZB7GQDAROESULQQYOZO.json","graph_json":"https://pith.science/api/pith-number/366WAVIZB7GQDAROESULQQYOZO/graph.json","events_json":"https://pith.science/api/pith-number/366WAVIZB7GQDAROESULQQYOZO/events.json","paper":"https://pith.science/paper/366WAVIZ"},"agent_actions":{"view_html":"https://pith.science/pith/366WAVIZB7GQDAROESULQQYOZO","download_json":"https://pith.science/pith/366WAVIZB7GQDAROESULQQYOZO.json","view_paper":"https://pith.science/paper/366WAVIZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.01015&json=true","fetch_graph":"https://pith.science/api/pith-number/366WAVIZB7GQDAROESULQQYOZO/graph.json","fetch_events":"https://pith.science/api/pith-number/366WAVIZB7GQDAROESULQQYOZO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/366WAVIZB7GQDAROESULQQYOZO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/366WAVIZB7GQDAROESULQQYOZO/action/storage_attestation","attest_author":"https://pith.science/pith/366WAVIZB7GQDAROESULQQYOZO/action/author_attestation","sign_citation":"https://pith.science/pith/366WAVIZB7GQDAROESULQQYOZO/action/citation_signature","submit_replication":"https://pith.science/pith/366WAVIZB7GQDAROESULQQYOZO/action/replication_record"}},"created_at":"2026-07-05T11:19:26.651874+00:00","updated_at":"2026-07-05T11:19:26.651874+00:00"}