{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WM4YBK7GIFSQA4GIYZ5ORZ5Z7H","short_pith_number":"pith:WM4YBK7G","schema_version":"1.0","canonical_sha256":"b33980abe641650070c8c67ae8e7b9f9f858b4072ec2b5722bee6f135b77de1f","source":{"kind":"arxiv","id":"2506.02480","version":1},"attestation_state":"computed","paper":{"title":"ORPP: Self-Optimizing Role-playing Prompts to Enhance Language Model Capabilities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kehai Chen, Liqiang Nie, Min Zhang, Yifan Duan, Yihong Tang","submitted_at":"2025-06-03T05:51:35Z","abstract_excerpt":"High-quality prompts are crucial for eliciting outstanding performance from large language models (LLMs) on complex tasks. Existing research has explored model-driven strategies for prompt optimization. However, these methods often suffer from high computational overhead or require strong optimization capabilities from the model itself, which limits their broad applicability.To address these challenges, we propose ORPP (Optimized Role-Playing Prompt),a framework that enhances model performance by optimizing and generating role-playing prompts. The core idea of ORPP is to confine the prompt sea"},"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":"2506.02480","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-03T05:51:35Z","cross_cats_sorted":[],"title_canon_sha256":"b85fd01f2ae2e3ebb87de857e0754bc818465af1646563222fde7bab3cf10682","abstract_canon_sha256":"f19fbc6bfcaa826a903d8335f3ca2f191d211d356236c2e093086d8a4f43fdcc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:02.737475Z","signature_b64":"B/csbmGqpk6fzgANyf1f+B0u1LVtjputviqR8aWPxZfoJdR8jt2youCIHj0+2yVeVN4pKN78dZ1nYLOTMRrSAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b33980abe641650070c8c67ae8e7b9f9f858b4072ec2b5722bee6f135b77de1f","last_reissued_at":"2026-07-05T11:15:02.736956Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:02.736956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ORPP: Self-Optimizing Role-playing Prompts to Enhance Language Model Capabilities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kehai Chen, Liqiang Nie, Min Zhang, Yifan Duan, Yihong Tang","submitted_at":"2025-06-03T05:51:35Z","abstract_excerpt":"High-quality prompts are crucial for eliciting outstanding performance from large language models (LLMs) on complex tasks. Existing research has explored model-driven strategies for prompt optimization. However, these methods often suffer from high computational overhead or require strong optimization capabilities from the model itself, which limits their broad applicability.To address these challenges, we propose ORPP (Optimized Role-Playing Prompt),a framework that enhances model performance by optimizing and generating role-playing prompts. The core idea of ORPP is to confine the prompt sea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02480","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/2506.02480/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":"2506.02480","created_at":"2026-07-05T11:15:02.737016+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.02480v1","created_at":"2026-07-05T11:15:02.737016+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02480","created_at":"2026-07-05T11:15:02.737016+00:00"},{"alias_kind":"pith_short_12","alias_value":"WM4YBK7GIFSQ","created_at":"2026-07-05T11:15:02.737016+00:00"},{"alias_kind":"pith_short_16","alias_value":"WM4YBK7GIFSQA4GI","created_at":"2026-07-05T11:15:02.737016+00:00"},{"alias_kind":"pith_short_8","alias_value":"WM4YBK7G","created_at":"2026-07-05T11:15:02.737016+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/WM4YBK7GIFSQA4GIYZ5ORZ5Z7H","json":"https://pith.science/pith/WM4YBK7GIFSQA4GIYZ5ORZ5Z7H.json","graph_json":"https://pith.science/api/pith-number/WM4YBK7GIFSQA4GIYZ5ORZ5Z7H/graph.json","events_json":"https://pith.science/api/pith-number/WM4YBK7GIFSQA4GIYZ5ORZ5Z7H/events.json","paper":"https://pith.science/paper/WM4YBK7G"},"agent_actions":{"view_html":"https://pith.science/pith/WM4YBK7GIFSQA4GIYZ5ORZ5Z7H","download_json":"https://pith.science/pith/WM4YBK7GIFSQA4GIYZ5ORZ5Z7H.json","view_paper":"https://pith.science/paper/WM4YBK7G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.02480&json=true","fetch_graph":"https://pith.science/api/pith-number/WM4YBK7GIFSQA4GIYZ5ORZ5Z7H/graph.json","fetch_events":"https://pith.science/api/pith-number/WM4YBK7GIFSQA4GIYZ5ORZ5Z7H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WM4YBK7GIFSQA4GIYZ5ORZ5Z7H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WM4YBK7GIFSQA4GIYZ5ORZ5Z7H/action/storage_attestation","attest_author":"https://pith.science/pith/WM4YBK7GIFSQA4GIYZ5ORZ5Z7H/action/author_attestation","sign_citation":"https://pith.science/pith/WM4YBK7GIFSQA4GIYZ5ORZ5Z7H/action/citation_signature","submit_replication":"https://pith.science/pith/WM4YBK7GIFSQA4GIYZ5ORZ5Z7H/action/replication_record"}},"created_at":"2026-07-05T11:15:02.737016+00:00","updated_at":"2026-07-05T11:15:02.737016+00:00"}