{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6IMNXLOHKMOISMVENADQQFXG3C","short_pith_number":"pith:6IMNXLOH","schema_version":"1.0","canonical_sha256":"f218dbadc7531c8932a468070816e6d8b89591e21beadf5205391fecabf9ed64","source":{"kind":"arxiv","id":"2607.14485","version":1},"attestation_state":"computed","paper":{"title":"Step-Level Preference Learning for Generative Agents in Social Simulations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Baicheng Chen, Jian Zhao, Kangda Wang, Lanlan Qiu, Pingyue Sheng, Shunqiang Mao, Tianxing He, Wenchang Gao, Yunfei Ma, Yuyang Tian","submitted_at":"2026-07-16T01:58:53Z","abstract_excerpt":"Large language model (LLM)-based generative agents simulate human behavior through long-horizon decision-making processes that comprise intermediate steps such as planning, memory retrieval, reflection, and action selection. However, fine-grained human annotations of these intermediate steps remain scarce, and existing agents are not grounded in human preferences over such intermediate decisions. To address this gap, we introduce \\method, an interactive simulation interface that enables us to collect step-level human preference supervision over agent decision trajectories, leading to a dataset"},"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":"2607.14485","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-16T01:58:53Z","cross_cats_sorted":[],"title_canon_sha256":"920196e68dae16c21dffaabbf56030a548b470d76f64cd327a901677c4036e13","abstract_canon_sha256":"f480bec93070bca9a769784f39a26cf60d8fa863d85c80c1b8c0b15ed97e8ac4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-17T00:21:14.937224Z","signature_b64":"Ea7fzyBsvavjKU3LnTveC0fl2a7Kh6VNgkoEroD3Row1bDeUV3ieUCgqiuLXyHIJupXuHonhFNO2oVCAF+pYBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f218dbadc7531c8932a468070816e6d8b89591e21beadf5205391fecabf9ed64","last_reissued_at":"2026-07-17T00:21:14.936381Z","signature_status":"signed_v1","first_computed_at":"2026-07-17T00:21:14.936381Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Step-Level Preference Learning for Generative Agents in Social Simulations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Baicheng Chen, Jian Zhao, Kangda Wang, Lanlan Qiu, Pingyue Sheng, Shunqiang Mao, Tianxing He, Wenchang Gao, Yunfei Ma, Yuyang Tian","submitted_at":"2026-07-16T01:58:53Z","abstract_excerpt":"Large language model (LLM)-based generative agents simulate human behavior through long-horizon decision-making processes that comprise intermediate steps such as planning, memory retrieval, reflection, and action selection. However, fine-grained human annotations of these intermediate steps remain scarce, and existing agents are not grounded in human preferences over such intermediate decisions. To address this gap, we introduce \\method, an interactive simulation interface that enables us to collect step-level human preference supervision over agent decision trajectories, leading to a dataset"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.14485","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/2607.14485/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":"2607.14485","created_at":"2026-07-17T00:21:14.936817+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.14485v1","created_at":"2026-07-17T00:21:14.936817+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.14485","created_at":"2026-07-17T00:21:14.936817+00:00"},{"alias_kind":"pith_short_12","alias_value":"6IMNXLOHKMOI","created_at":"2026-07-17T00:21:14.936817+00:00"},{"alias_kind":"pith_short_16","alias_value":"6IMNXLOHKMOISMVE","created_at":"2026-07-17T00:21:14.936817+00:00"},{"alias_kind":"pith_short_8","alias_value":"6IMNXLOH","created_at":"2026-07-17T00:21:14.936817+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/6IMNXLOHKMOISMVENADQQFXG3C","json":"https://pith.science/pith/6IMNXLOHKMOISMVENADQQFXG3C.json","graph_json":"https://pith.science/api/pith-number/6IMNXLOHKMOISMVENADQQFXG3C/graph.json","events_json":"https://pith.science/api/pith-number/6IMNXLOHKMOISMVENADQQFXG3C/events.json","paper":"https://pith.science/paper/6IMNXLOH"},"agent_actions":{"view_html":"https://pith.science/pith/6IMNXLOHKMOISMVENADQQFXG3C","download_json":"https://pith.science/pith/6IMNXLOHKMOISMVENADQQFXG3C.json","view_paper":"https://pith.science/paper/6IMNXLOH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.14485&json=true","fetch_graph":"https://pith.science/api/pith-number/6IMNXLOHKMOISMVENADQQFXG3C/graph.json","fetch_events":"https://pith.science/api/pith-number/6IMNXLOHKMOISMVENADQQFXG3C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6IMNXLOHKMOISMVENADQQFXG3C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6IMNXLOHKMOISMVENADQQFXG3C/action/storage_attestation","attest_author":"https://pith.science/pith/6IMNXLOHKMOISMVENADQQFXG3C/action/author_attestation","sign_citation":"https://pith.science/pith/6IMNXLOHKMOISMVENADQQFXG3C/action/citation_signature","submit_replication":"https://pith.science/pith/6IMNXLOHKMOISMVENADQQFXG3C/action/replication_record"}},"created_at":"2026-07-17T00:21:14.936817+00:00","updated_at":"2026-07-17T00:21:14.936817+00:00"}