{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HHLYO3PUYXCJYW725WSX5V4SH5","short_pith_number":"pith:HHLYO3PU","schema_version":"1.0","canonical_sha256":"39d7876df4c5c49c5bfaeda57ed7923f6f2f66affa7ba8cc194839bf5e0c8daa","source":{"kind":"arxiv","id":"2605.29791","version":1},"attestation_state":"computed","paper":{"title":"ActTraitBench: Quantifying the Knowledge-Decision Gap in Large Language Models via Human-Grounded Behavioral Validation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenxi Miao, Weikang Li, Yunfang Wu, Yutong Yang","submitted_at":"2026-05-28T11:40:35Z","abstract_excerpt":"While Large Language Models (LLMs) can convincingly simulate personas in explicit self-reports, they often deviate in implicit behavioral decisions, revealing a substantial Knowledge-Decision Gap ($G_{\\text{KD}}$). Existing benchmarks struggle to measure this asymmetry due to limited construct validity, multi-dimensional entanglement, and distributional biases in LLM-based evaluation. To address these issues, we propose ActTraitBench, a human-grounded evaluation framework for measuring personality consistency in LLMs. Grounded in empirical human data, ActTraitBench establishes one-to-one mappi"},"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":"2605.29791","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T11:40:35Z","cross_cats_sorted":[],"title_canon_sha256":"7de2f707b83d5af8299475864ea18d0f4055bd599f4ad9de60dcfcd679c9cac5","abstract_canon_sha256":"fcb98d2a267c0cc65669e53fd90a8fc4b25061c229476f3e8ee119fc460838d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:05:52.546787Z","signature_b64":"xL92kNukxCXtQH5vvc4nDvvqlC4PHlfq9ir+Y/vlp/YWfR5IvMavO0FWcmZtHNUWEOcBnplpR9+SIGuLsEv6Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39d7876df4c5c49c5bfaeda57ed7923f6f2f66affa7ba8cc194839bf5e0c8daa","last_reissued_at":"2026-05-29T02:05:52.545737Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:05:52.545737Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ActTraitBench: Quantifying the Knowledge-Decision Gap in Large Language Models via Human-Grounded Behavioral Validation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenxi Miao, Weikang Li, Yunfang Wu, Yutong Yang","submitted_at":"2026-05-28T11:40:35Z","abstract_excerpt":"While Large Language Models (LLMs) can convincingly simulate personas in explicit self-reports, they often deviate in implicit behavioral decisions, revealing a substantial Knowledge-Decision Gap ($G_{\\text{KD}}$). Existing benchmarks struggle to measure this asymmetry due to limited construct validity, multi-dimensional entanglement, and distributional biases in LLM-based evaluation. To address these issues, we propose ActTraitBench, a human-grounded evaluation framework for measuring personality consistency in LLMs. Grounded in empirical human data, ActTraitBench establishes one-to-one mappi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29791","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/2605.29791/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":"2605.29791","created_at":"2026-05-29T02:05:52.545973+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.29791v1","created_at":"2026-05-29T02:05:52.545973+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29791","created_at":"2026-05-29T02:05:52.545973+00:00"},{"alias_kind":"pith_short_12","alias_value":"HHLYO3PUYXCJ","created_at":"2026-05-29T02:05:52.545973+00:00"},{"alias_kind":"pith_short_16","alias_value":"HHLYO3PUYXCJYW72","created_at":"2026-05-29T02:05:52.545973+00:00"},{"alias_kind":"pith_short_8","alias_value":"HHLYO3PU","created_at":"2026-05-29T02:05:52.545973+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/HHLYO3PUYXCJYW725WSX5V4SH5","json":"https://pith.science/pith/HHLYO3PUYXCJYW725WSX5V4SH5.json","graph_json":"https://pith.science/api/pith-number/HHLYO3PUYXCJYW725WSX5V4SH5/graph.json","events_json":"https://pith.science/api/pith-number/HHLYO3PUYXCJYW725WSX5V4SH5/events.json","paper":"https://pith.science/paper/HHLYO3PU"},"agent_actions":{"view_html":"https://pith.science/pith/HHLYO3PUYXCJYW725WSX5V4SH5","download_json":"https://pith.science/pith/HHLYO3PUYXCJYW725WSX5V4SH5.json","view_paper":"https://pith.science/paper/HHLYO3PU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.29791&json=true","fetch_graph":"https://pith.science/api/pith-number/HHLYO3PUYXCJYW725WSX5V4SH5/graph.json","fetch_events":"https://pith.science/api/pith-number/HHLYO3PUYXCJYW725WSX5V4SH5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HHLYO3PUYXCJYW725WSX5V4SH5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HHLYO3PUYXCJYW725WSX5V4SH5/action/storage_attestation","attest_author":"https://pith.science/pith/HHLYO3PUYXCJYW725WSX5V4SH5/action/author_attestation","sign_citation":"https://pith.science/pith/HHLYO3PUYXCJYW725WSX5V4SH5/action/citation_signature","submit_replication":"https://pith.science/pith/HHLYO3PUYXCJYW725WSX5V4SH5/action/replication_record"}},"created_at":"2026-05-29T02:05:52.545973+00:00","updated_at":"2026-05-29T02:05:52.545973+00:00"}