{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:5XHAYDBKWO7RK475YVD7U3C5XM","short_pith_number":"pith:5XHAYDBK","canonical_record":{"source":{"id":"2502.13012","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2025-02-18T16:33:33Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"671e06362bb8c18b643294c0d2535b2b700f62bb4e38060b8339e5db17f2a79a","abstract_canon_sha256":"f97cb729e6eb993b18deb0c87d6abef60da4a540bd301c78a1c2528000dacc52"},"schema_version":"1.0"},"canonical_sha256":"edce0c0c2ab3bf1573fdc547fa6c5dbb181df972ee433c23b72b224c98466341","source":{"kind":"arxiv","id":"2502.13012","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.13012","created_at":"2026-07-05T10:40:17Z"},{"alias_kind":"arxiv_version","alias_value":"2502.13012v3","created_at":"2026-07-05T10:40:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.13012","created_at":"2026-07-05T10:40:17Z"},{"alias_kind":"pith_short_12","alias_value":"5XHAYDBKWO7R","created_at":"2026-07-05T10:40:17Z"},{"alias_kind":"pith_short_16","alias_value":"5XHAYDBKWO7RK475","created_at":"2026-07-05T10:40:17Z"},{"alias_kind":"pith_short_8","alias_value":"5XHAYDBK","created_at":"2026-07-05T10:40:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:5XHAYDBKWO7RK475YVD7U3C5XM","target":"record","payload":{"canonical_record":{"source":{"id":"2502.13012","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2025-02-18T16:33:33Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"671e06362bb8c18b643294c0d2535b2b700f62bb4e38060b8339e5db17f2a79a","abstract_canon_sha256":"f97cb729e6eb993b18deb0c87d6abef60da4a540bd301c78a1c2528000dacc52"},"schema_version":"1.0"},"canonical_sha256":"edce0c0c2ab3bf1573fdc547fa6c5dbb181df972ee433c23b72b224c98466341","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:40:17.100795Z","signature_b64":"+7l7AdPcCgjQp3GNmlcSf08MweDEU5++6B+acLaMS1nklMff3nkSkW3QqkriEAPJ2YZDnmWMBgwkw0gNrAk/DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"edce0c0c2ab3bf1573fdc547fa6c5dbb181df972ee433c23b72b224c98466341","last_reissued_at":"2026-07-05T10:40:17.100111Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:40:17.100111Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.13012","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:40:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jKNAG2hSqiXCIPy7Iqk1AxOtJ6JAHBCkMoCS/YSQr/xXQ69vkMPNRndyxpKZyQFIx+Lwh9I5PlXHMHrFxmF1CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T07:40:32.151184Z"},"content_sha256":"b077e3a3016f7c8b14c86b6eb28fa463a652fbc60bf2caef3c714d94a5e74389","schema_version":"1.0","event_id":"sha256:b077e3a3016f7c8b14c86b6eb28fa463a652fbc60bf2caef3c714d94a5e74389"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:5XHAYDBKWO7RK475YVD7U3C5XM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards a Design Guideline for RPA Evaluation: A Survey of Large Language Model-Based Role-Playing Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.HC","authors_text":"Bingsheng Yao, Chaoran Chen, Dakuo Wang, Ruishi Zou, Toby Jia-Jun Li, Weimin Lyu, Wenyue Hua, Yanfang Ye","submitted_at":"2025-02-18T16:33:33Z","abstract_excerpt":"Role-Playing Agent (RPA) is an increasingly popular type of LLM Agent that simulates human-like behaviors in a variety of tasks. However, evaluating RPAs is challenging due to diverse task requirements and agent designs. This paper proposes an evidence-based, actionable, and generalizable evaluation design guideline for LLM-based RPA by systematically reviewing 1,676 papers published between Jan. 2021 and Dec. 2024. Our analysis identifies six agent attributes, seven task attributes, and seven evaluation metrics from existing literature. Based on these findings, we present an RPA evaluation de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.13012","kind":"arxiv","version":3},"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/2502.13012/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:40:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qws7IMrBF/+JcdXPjUjXjNZpMsZfs0GzFuDmONAp2+G7EfW4v4yzeNgGQ6QP4qgqF4bHFyPGBcqyTCM7aePNCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T07:40:32.151799Z"},"content_sha256":"75a706d4c0d38c3d23cd14d59576c1672f9173bcdb085cb9bbd3701de010e0e6","schema_version":"1.0","event_id":"sha256:75a706d4c0d38c3d23cd14d59576c1672f9173bcdb085cb9bbd3701de010e0e6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5XHAYDBKWO7RK475YVD7U3C5XM/bundle.json","state_url":"https://pith.science/pith/5XHAYDBKWO7RK475YVD7U3C5XM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5XHAYDBKWO7RK475YVD7U3C5XM/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-17T07:40:32Z","links":{"resolver":"https://pith.science/pith/5XHAYDBKWO7RK475YVD7U3C5XM","bundle":"https://pith.science/pith/5XHAYDBKWO7RK475YVD7U3C5XM/bundle.json","state":"https://pith.science/pith/5XHAYDBKWO7RK475YVD7U3C5XM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5XHAYDBKWO7RK475YVD7U3C5XM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5XHAYDBKWO7RK475YVD7U3C5XM","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f97cb729e6eb993b18deb0c87d6abef60da4a540bd301c78a1c2528000dacc52","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2025-02-18T16:33:33Z","title_canon_sha256":"671e06362bb8c18b643294c0d2535b2b700f62bb4e38060b8339e5db17f2a79a"},"schema_version":"1.0","source":{"id":"2502.13012","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.13012","created_at":"2026-07-05T10:40:17Z"},{"alias_kind":"arxiv_version","alias_value":"2502.13012v3","created_at":"2026-07-05T10:40:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.13012","created_at":"2026-07-05T10:40:17Z"},{"alias_kind":"pith_short_12","alias_value":"5XHAYDBKWO7R","created_at":"2026-07-05T10:40:17Z"},{"alias_kind":"pith_short_16","alias_value":"5XHAYDBKWO7RK475","created_at":"2026-07-05T10:40:17Z"},{"alias_kind":"pith_short_8","alias_value":"5XHAYDBK","created_at":"2026-07-05T10:40:17Z"}],"graph_snapshots":[{"event_id":"sha256:75a706d4c0d38c3d23cd14d59576c1672f9173bcdb085cb9bbd3701de010e0e6","target":"graph","created_at":"2026-07-05T10:40:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2502.13012/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Role-Playing Agent (RPA) is an increasingly popular type of LLM Agent that simulates human-like behaviors in a variety of tasks. However, evaluating RPAs is challenging due to diverse task requirements and agent designs. This paper proposes an evidence-based, actionable, and generalizable evaluation design guideline for LLM-based RPA by systematically reviewing 1,676 papers published between Jan. 2021 and Dec. 2024. Our analysis identifies six agent attributes, seven task attributes, and seven evaluation metrics from existing literature. Based on these findings, we present an RPA evaluation de","authors_text":"Bingsheng Yao, Chaoran Chen, Dakuo Wang, Ruishi Zou, Toby Jia-Jun Li, Weimin Lyu, Wenyue Hua, Yanfang Ye","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2025-02-18T16:33:33Z","title":"Towards a Design Guideline for RPA Evaluation: A Survey of Large Language Model-Based Role-Playing Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.13012","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b077e3a3016f7c8b14c86b6eb28fa463a652fbc60bf2caef3c714d94a5e74389","target":"record","created_at":"2026-07-05T10:40:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"f97cb729e6eb993b18deb0c87d6abef60da4a540bd301c78a1c2528000dacc52","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2025-02-18T16:33:33Z","title_canon_sha256":"671e06362bb8c18b643294c0d2535b2b700f62bb4e38060b8339e5db17f2a79a"},"schema_version":"1.0","source":{"id":"2502.13012","kind":"arxiv","version":3}},"canonical_sha256":"edce0c0c2ab3bf1573fdc547fa6c5dbb181df972ee433c23b72b224c98466341","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"edce0c0c2ab3bf1573fdc547fa6c5dbb181df972ee433c23b72b224c98466341","first_computed_at":"2026-07-05T10:40:17.100111Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:40:17.100111Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+7l7AdPcCgjQp3GNmlcSf08MweDEU5++6B+acLaMS1nklMff3nkSkW3QqkriEAPJ2YZDnmWMBgwkw0gNrAk/DA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:40:17.100795Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.13012","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b077e3a3016f7c8b14c86b6eb28fa463a652fbc60bf2caef3c714d94a5e74389","sha256:75a706d4c0d38c3d23cd14d59576c1672f9173bcdb085cb9bbd3701de010e0e6"],"state_sha256":"95b578695abfe8245c5de266ed9cf73ee0eed75eb96a8d911e7f217f1c029a74"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ALKW8oBtDwciOCArAb1z+BB6iy3zJm5DtgdELt6YhlrXmYu5N+DvqEr65mOnm+QSiid4UsdEYiz+R+0mz0p4Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T07:40:32.156669Z","bundle_sha256":"b3e090d4b24e8be2db786e306ad1b4f02eb0ba90a5e86909c8f10ba3fc3db38e"}}