{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7Z34SNQIIYT5JIVCARGW3JQDSD","short_pith_number":"pith:7Z34SNQI","schema_version":"1.0","canonical_sha256":"fe77c936084627d4a2a2044d6da60390dd613283a4512844e84c547a9466b3e1","source":{"kind":"arxiv","id":"2407.12393","version":5},"attestation_state":"computed","paper":{"title":"PersLLM: A Personified Training Approach for Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.CL","authors_text":"Huimin Chen, Jiayi Chen, Maosong Sun, Yukun Yan, Yuxuan Chen, Zhenghao Liu, Zheni Zeng, Zhiyuan Liu","submitted_at":"2024-07-17T08:13:22Z","abstract_excerpt":"Large language models (LLMs) exhibit human-like intelligence, enabling them to simulate human behavior and support various applications that require both humanized communication and extensive knowledge reserves. Efforts are made to personify LLMs with special training data or hand-crafted prompts, while correspondingly faced with challenges such as insufficient data usage or rigid behavior patterns. Consequently, personified LLMs fail to capture personified knowledge or express persistent opinion. To fully unlock the potential of LLM personification, we propose PersLLM, a framework for better "},"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":"2407.12393","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-17T08:13:22Z","cross_cats_sorted":["cs.AI","cs.CY"],"title_canon_sha256":"014bdc813f6772b773a64197531970efafdcf67ec4b0e49e8affb4673062c778","abstract_canon_sha256":"638f7e27bcae2f0d6443df10d8d417e7ec82aedd4da1b6d003c16a64ee9510b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:03:15.676298Z","signature_b64":"c1oVUBaNpBx9LMBtVqL7QoLDx8oKidN3XE08z7qFYZbjajklHBJDRZcO7IYZZhzEkNRcDTP+QEJjBdDieLF6Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe77c936084627d4a2a2044d6da60390dd613283a4512844e84c547a9466b3e1","last_reissued_at":"2026-07-05T11:03:15.675751Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:03:15.675751Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PersLLM: A Personified Training Approach for Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.CL","authors_text":"Huimin Chen, Jiayi Chen, Maosong Sun, Yukun Yan, Yuxuan Chen, Zhenghao Liu, Zheni Zeng, Zhiyuan Liu","submitted_at":"2024-07-17T08:13:22Z","abstract_excerpt":"Large language models (LLMs) exhibit human-like intelligence, enabling them to simulate human behavior and support various applications that require both humanized communication and extensive knowledge reserves. Efforts are made to personify LLMs with special training data or hand-crafted prompts, while correspondingly faced with challenges such as insufficient data usage or rigid behavior patterns. Consequently, personified LLMs fail to capture personified knowledge or express persistent opinion. To fully unlock the potential of LLM personification, we propose PersLLM, a framework for better "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12393","kind":"arxiv","version":5},"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/2407.12393/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":"2407.12393","created_at":"2026-07-05T11:03:15.675809+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.12393v5","created_at":"2026-07-05T11:03:15.675809+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12393","created_at":"2026-07-05T11:03:15.675809+00:00"},{"alias_kind":"pith_short_12","alias_value":"7Z34SNQIIYT5","created_at":"2026-07-05T11:03:15.675809+00:00"},{"alias_kind":"pith_short_16","alias_value":"7Z34SNQIIYT5JIVC","created_at":"2026-07-05T11:03:15.675809+00:00"},{"alias_kind":"pith_short_8","alias_value":"7Z34SNQI","created_at":"2026-07-05T11:03:15.675809+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.01378","citing_title":"RALLY: Role-Adaptive LLM-Driven Yoked Navigation for Agentic UAV Swarms","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7Z34SNQIIYT5JIVCARGW3JQDSD","json":"https://pith.science/pith/7Z34SNQIIYT5JIVCARGW3JQDSD.json","graph_json":"https://pith.science/api/pith-number/7Z34SNQIIYT5JIVCARGW3JQDSD/graph.json","events_json":"https://pith.science/api/pith-number/7Z34SNQIIYT5JIVCARGW3JQDSD/events.json","paper":"https://pith.science/paper/7Z34SNQI"},"agent_actions":{"view_html":"https://pith.science/pith/7Z34SNQIIYT5JIVCARGW3JQDSD","download_json":"https://pith.science/pith/7Z34SNQIIYT5JIVCARGW3JQDSD.json","view_paper":"https://pith.science/paper/7Z34SNQI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.12393&json=true","fetch_graph":"https://pith.science/api/pith-number/7Z34SNQIIYT5JIVCARGW3JQDSD/graph.json","fetch_events":"https://pith.science/api/pith-number/7Z34SNQIIYT5JIVCARGW3JQDSD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7Z34SNQIIYT5JIVCARGW3JQDSD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7Z34SNQIIYT5JIVCARGW3JQDSD/action/storage_attestation","attest_author":"https://pith.science/pith/7Z34SNQIIYT5JIVCARGW3JQDSD/action/author_attestation","sign_citation":"https://pith.science/pith/7Z34SNQIIYT5JIVCARGW3JQDSD/action/citation_signature","submit_replication":"https://pith.science/pith/7Z34SNQIIYT5JIVCARGW3JQDSD/action/replication_record"}},"created_at":"2026-07-05T11:03:15.675809+00:00","updated_at":"2026-07-05T11:03:15.675809+00:00"}