{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MY762G5AF6AI5DEF4NGKQAE6HK","short_pith_number":"pith:MY762G5A","schema_version":"1.0","canonical_sha256":"663fed1ba02f808e8c85e34ca8009e3ab2b572d3019a809f6c014bf76cdba16e","source":{"kind":"arxiv","id":"2506.00751","version":1},"attestation_state":"computed","paper":{"title":"Alignment Revisited: Are Large Language Models Consistent in Stated and Revealed Preferences?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Quan Wang, Shuchu Han, Zhuojun Gu","submitted_at":"2025-05-31T23:38:48Z","abstract_excerpt":"Recent advances in Large Language Models (LLMs) highlight the need to align their behaviors with human values. A critical, yet understudied, issue is the potential divergence between an LLM's stated preferences (its reported alignment with general principles) and its revealed preferences (inferred from decisions in contextualized scenarios). Such deviations raise fundamental concerns for the interpretability, trustworthiness, reasoning transparency, and ethical deployment of LLMs, particularly in high-stakes applications. This work formally defines and proposes a method to measure this prefere"},"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":"2506.00751","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-31T23:38:48Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d61a731b654f44c1dca785ec04472abd7bd612e89eb02633cd12e9799e891d84","abstract_canon_sha256":"ba2c469ddf3abaf16ac7e3106ae6d474245db50a132b1cbacd8cc5a0099debc6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:39.901095Z","signature_b64":"5w04lcizybNjoYioGO0GPD+sSbxjFoWqFOck5WFW68Zt/Z9VcP3b90eTLyPIEHjQuxNFXCFRYGdAa355YER0CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"663fed1ba02f808e8c85e34ca8009e3ab2b572d3019a809f6c014bf76cdba16e","last_reissued_at":"2026-07-05T11:13:39.900679Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:39.900679Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Alignment Revisited: Are Large Language Models Consistent in Stated and Revealed Preferences?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Quan Wang, Shuchu Han, Zhuojun Gu","submitted_at":"2025-05-31T23:38:48Z","abstract_excerpt":"Recent advances in Large Language Models (LLMs) highlight the need to align their behaviors with human values. A critical, yet understudied, issue is the potential divergence between an LLM's stated preferences (its reported alignment with general principles) and its revealed preferences (inferred from decisions in contextualized scenarios). Such deviations raise fundamental concerns for the interpretability, trustworthiness, reasoning transparency, and ethical deployment of LLMs, particularly in high-stakes applications. This work formally defines and proposes a method to measure this prefere"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00751","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/2506.00751/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":"2506.00751","created_at":"2026-07-05T11:13:39.900732+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.00751v1","created_at":"2026-07-05T11:13:39.900732+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00751","created_at":"2026-07-05T11:13:39.900732+00:00"},{"alias_kind":"pith_short_12","alias_value":"MY762G5AF6AI","created_at":"2026-07-05T11:13:39.900732+00:00"},{"alias_kind":"pith_short_16","alias_value":"MY762G5AF6AI5DEF","created_at":"2026-07-05T11:13:39.900732+00:00"},{"alias_kind":"pith_short_8","alias_value":"MY762G5A","created_at":"2026-07-05T11:13:39.900732+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.02507","citing_title":"What LLM Agents Say When No One Is Watching: Social Structure and Latent Objective Emergence in Multi-Agent Debates","ref_index":85,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11016","citing_title":"Superficial Beliefs in LLM Decision-Making","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13339","citing_title":"Probing Persona-Dependent Preferences in Language Models","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MY762G5AF6AI5DEF4NGKQAE6HK","json":"https://pith.science/pith/MY762G5AF6AI5DEF4NGKQAE6HK.json","graph_json":"https://pith.science/api/pith-number/MY762G5AF6AI5DEF4NGKQAE6HK/graph.json","events_json":"https://pith.science/api/pith-number/MY762G5AF6AI5DEF4NGKQAE6HK/events.json","paper":"https://pith.science/paper/MY762G5A"},"agent_actions":{"view_html":"https://pith.science/pith/MY762G5AF6AI5DEF4NGKQAE6HK","download_json":"https://pith.science/pith/MY762G5AF6AI5DEF4NGKQAE6HK.json","view_paper":"https://pith.science/paper/MY762G5A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.00751&json=true","fetch_graph":"https://pith.science/api/pith-number/MY762G5AF6AI5DEF4NGKQAE6HK/graph.json","fetch_events":"https://pith.science/api/pith-number/MY762G5AF6AI5DEF4NGKQAE6HK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MY762G5AF6AI5DEF4NGKQAE6HK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MY762G5AF6AI5DEF4NGKQAE6HK/action/storage_attestation","attest_author":"https://pith.science/pith/MY762G5AF6AI5DEF4NGKQAE6HK/action/author_attestation","sign_citation":"https://pith.science/pith/MY762G5AF6AI5DEF4NGKQAE6HK/action/citation_signature","submit_replication":"https://pith.science/pith/MY762G5AF6AI5DEF4NGKQAE6HK/action/replication_record"}},"created_at":"2026-07-05T11:13:39.900732+00:00","updated_at":"2026-07-05T11:13:39.900732+00:00"}