{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FRKELIBHHADJ27TJLLOE7TEZ7H","short_pith_number":"pith:FRKELIBH","schema_version":"1.0","canonical_sha256":"2c5445a02738069d7e695adc4fcc99f9d120e55482317aef58fcc415b6a44756","source":{"kind":"arxiv","id":"2312.17115","version":2},"attestation_state":"computed","paper":{"title":"How Far Are LLMs from Believable AI? A Benchmark for Evaluating the Believability of Human Behavior Simulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.CL","authors_text":"Jiashuo Wang, Jinlan Fu, Pengfei Liu, Wenjie Li, Yang Xiao, Yi Cheng","submitted_at":"2023-12-28T16:51:11Z","abstract_excerpt":"In recent years, AI has demonstrated remarkable capabilities in simulating human behaviors, particularly those implemented with large language models (LLMs). However, due to the lack of systematic evaluation of LLMs' simulated behaviors, the believability of LLMs among humans remains ambiguous, i.e., it is unclear which behaviors of LLMs are convincingly human-like and which need further improvements. In this work, we design SimulateBench to evaluate the believability of LLMs when simulating human behaviors. In specific, we evaluate the believability of LLMs based on two critical dimensions: 1"},"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":"2312.17115","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-28T16:51:11Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"f186d65c9b217f87d436f6742044dc015f4f49f512d4da01bbc9037594d73936","abstract_canon_sha256":"8ec98e45a43d6c6171a75546376bc49ab21a8fd6ec5400232c9fca494f46cec6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:10.297347Z","signature_b64":"Unr1Bkc2f5y7bRRa44L5RS0aneZ+iHhfhvYtz2Igo/1XwzMqFiZH9r9AsCHl3Pqjofwd9cmuU9jnhaxuI0BIAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c5445a02738069d7e695adc4fcc99f9d120e55482317aef58fcc415b6a44756","last_reissued_at":"2026-07-05T08:32:10.296848Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:10.296848Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How Far Are LLMs from Believable AI? A Benchmark for Evaluating the Believability of Human Behavior Simulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.CL","authors_text":"Jiashuo Wang, Jinlan Fu, Pengfei Liu, Wenjie Li, Yang Xiao, Yi Cheng","submitted_at":"2023-12-28T16:51:11Z","abstract_excerpt":"In recent years, AI has demonstrated remarkable capabilities in simulating human behaviors, particularly those implemented with large language models (LLMs). However, due to the lack of systematic evaluation of LLMs' simulated behaviors, the believability of LLMs among humans remains ambiguous, i.e., it is unclear which behaviors of LLMs are convincingly human-like and which need further improvements. In this work, we design SimulateBench to evaluate the believability of LLMs when simulating human behaviors. In specific, we evaluate the believability of LLMs based on two critical dimensions: 1"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.17115","kind":"arxiv","version":2},"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/2312.17115/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":"2312.17115","created_at":"2026-07-05T08:32:10.296903+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.17115v2","created_at":"2026-07-05T08:32:10.296903+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.17115","created_at":"2026-07-05T08:32:10.296903+00:00"},{"alias_kind":"pith_short_12","alias_value":"FRKELIBHHADJ","created_at":"2026-07-05T08:32:10.296903+00:00"},{"alias_kind":"pith_short_16","alias_value":"FRKELIBHHADJ27TJ","created_at":"2026-07-05T08:32:10.296903+00:00"},{"alias_kind":"pith_short_8","alias_value":"FRKELIBH","created_at":"2026-07-05T08:32:10.296903+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.05250","citing_title":"Decision-aware User Simulation Agent for Evaluating Conversational Recommender Systems","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FRKELIBHHADJ27TJLLOE7TEZ7H","json":"https://pith.science/pith/FRKELIBHHADJ27TJLLOE7TEZ7H.json","graph_json":"https://pith.science/api/pith-number/FRKELIBHHADJ27TJLLOE7TEZ7H/graph.json","events_json":"https://pith.science/api/pith-number/FRKELIBHHADJ27TJLLOE7TEZ7H/events.json","paper":"https://pith.science/paper/FRKELIBH"},"agent_actions":{"view_html":"https://pith.science/pith/FRKELIBHHADJ27TJLLOE7TEZ7H","download_json":"https://pith.science/pith/FRKELIBHHADJ27TJLLOE7TEZ7H.json","view_paper":"https://pith.science/paper/FRKELIBH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.17115&json=true","fetch_graph":"https://pith.science/api/pith-number/FRKELIBHHADJ27TJLLOE7TEZ7H/graph.json","fetch_events":"https://pith.science/api/pith-number/FRKELIBHHADJ27TJLLOE7TEZ7H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FRKELIBHHADJ27TJLLOE7TEZ7H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FRKELIBHHADJ27TJLLOE7TEZ7H/action/storage_attestation","attest_author":"https://pith.science/pith/FRKELIBHHADJ27TJLLOE7TEZ7H/action/author_attestation","sign_citation":"https://pith.science/pith/FRKELIBHHADJ27TJLLOE7TEZ7H/action/citation_signature","submit_replication":"https://pith.science/pith/FRKELIBHHADJ27TJLLOE7TEZ7H/action/replication_record"}},"created_at":"2026-07-05T08:32:10.296903+00:00","updated_at":"2026-07-05T08:32:10.296903+00:00"}