{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IO64IBBTF4AC2EQFX44SKABFWI","short_pith_number":"pith:IO64IBBT","schema_version":"1.0","canonical_sha256":"43bdc404332f002d1205bf39250025b20799c85c359a85ddde0ac52754264d8e","source":{"kind":"arxiv","id":"2502.07853","version":1},"attestation_state":"computed","paper":{"title":"PolicySimEval: A Benchmark for Evaluating Policy Outcomes through Agent-Based Simulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.MA","authors_text":"Jiaju Kang, Luqi Gong, Puyu Han, Tian Zhang","submitted_at":"2025-02-11T12:36:00Z","abstract_excerpt":"With the growing adoption of agent-based models in policy evaluation, a pressing question arises: Can such systems effectively simulate and analyze complex social scenarios to inform policy decisions? Addressing this challenge could significantly enhance the policy-making process, offering researchers and practitioners a systematic way to validate, explore, and refine policy outcomes. To advance this goal, we introduce PolicySimEval, the first benchmark designed to evaluate the capability of agent-based simulations in policy assessment tasks. PolicySimEval aims to reflect the real-world comple"},"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":"2502.07853","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2025-02-11T12:36:00Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"31e3324cd67a302d89a28d977b5be1cc7056f9d469d069c5db13de7da3b37271","abstract_canon_sha256":"56084aab5c0827961092e5bd668a00636848ce72776371be27695d59406406d4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:13:11.136683Z","signature_b64":"4JYYp7Wzll5+KInB9BGJ6FKA/GRfrpuldClfLoDjzUQzne335JTMr5+4U1dcnUyJg5hQKSZaEJKbitDf6a6hCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43bdc404332f002d1205bf39250025b20799c85c359a85ddde0ac52754264d8e","last_reissued_at":"2026-07-05T10:13:11.136167Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:13:11.136167Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PolicySimEval: A Benchmark for Evaluating Policy Outcomes through Agent-Based Simulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.MA","authors_text":"Jiaju Kang, Luqi Gong, Puyu Han, Tian Zhang","submitted_at":"2025-02-11T12:36:00Z","abstract_excerpt":"With the growing adoption of agent-based models in policy evaluation, a pressing question arises: Can such systems effectively simulate and analyze complex social scenarios to inform policy decisions? Addressing this challenge could significantly enhance the policy-making process, offering researchers and practitioners a systematic way to validate, explore, and refine policy outcomes. To advance this goal, we introduce PolicySimEval, the first benchmark designed to evaluate the capability of agent-based simulations in policy assessment tasks. PolicySimEval aims to reflect the real-world comple"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07853","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/2502.07853/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":"2502.07853","created_at":"2026-07-05T10:13:11.136229+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.07853v1","created_at":"2026-07-05T10:13:11.136229+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07853","created_at":"2026-07-05T10:13:11.136229+00:00"},{"alias_kind":"pith_short_12","alias_value":"IO64IBBTF4AC","created_at":"2026-07-05T10:13:11.136229+00:00"},{"alias_kind":"pith_short_16","alias_value":"IO64IBBTF4AC2EQF","created_at":"2026-07-05T10:13:11.136229+00:00"},{"alias_kind":"pith_short_8","alias_value":"IO64IBBT","created_at":"2026-07-05T10:13:11.136229+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.12995","citing_title":"PolicyLLM: Towards Excellent Comprehension of Public Policy for Large Language Models","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IO64IBBTF4AC2EQFX44SKABFWI","json":"https://pith.science/pith/IO64IBBTF4AC2EQFX44SKABFWI.json","graph_json":"https://pith.science/api/pith-number/IO64IBBTF4AC2EQFX44SKABFWI/graph.json","events_json":"https://pith.science/api/pith-number/IO64IBBTF4AC2EQFX44SKABFWI/events.json","paper":"https://pith.science/paper/IO64IBBT"},"agent_actions":{"view_html":"https://pith.science/pith/IO64IBBTF4AC2EQFX44SKABFWI","download_json":"https://pith.science/pith/IO64IBBTF4AC2EQFX44SKABFWI.json","view_paper":"https://pith.science/paper/IO64IBBT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.07853&json=true","fetch_graph":"https://pith.science/api/pith-number/IO64IBBTF4AC2EQFX44SKABFWI/graph.json","fetch_events":"https://pith.science/api/pith-number/IO64IBBTF4AC2EQFX44SKABFWI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IO64IBBTF4AC2EQFX44SKABFWI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IO64IBBTF4AC2EQFX44SKABFWI/action/storage_attestation","attest_author":"https://pith.science/pith/IO64IBBTF4AC2EQFX44SKABFWI/action/author_attestation","sign_citation":"https://pith.science/pith/IO64IBBTF4AC2EQFX44SKABFWI/action/citation_signature","submit_replication":"https://pith.science/pith/IO64IBBTF4AC2EQFX44SKABFWI/action/replication_record"}},"created_at":"2026-07-05T10:13:11.136229+00:00","updated_at":"2026-07-05T10:13:11.136229+00:00"}