{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KLIHD6R5JAASIKOFBVI72666RV","short_pith_number":"pith:KLIHD6R5","schema_version":"1.0","canonical_sha256":"52d071fa3d48012429c50d51fd7bde8d58038d827c9e320825c78ceac68ed72f","source":{"kind":"arxiv","id":"2603.03915","version":2},"attestation_state":"computed","paper":{"title":"Rethinking Role-Playing Evaluation: Anonymous Benchmarking and a Systematic Study of Personality Effects","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ji-Lun Peng, Yun-Nung Chen","submitted_at":"2026-03-04T10:24:02Z","abstract_excerpt":"Large Language Models (LLMs) have shown remarkable potential in developing role-playing agents (RPAs). However, current evaluation frameworks rely heavily on well-known fictional characters, raising a critical concern: models may be leveraging their internal training memory of these characters rather than demonstrating role-playing capabilities. This reliance often leads to significant performance degradation when RPAs encounter unseen or out-of-distribution personas. To address this, we propose a more rigorous evaluation protocol designed to decouple role-playing proficiency from character re"},"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":"2603.03915","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-03-04T10:24:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"60c7fd876272146a90c7787795071f6866eadceff03fa02df6223c41c3726e0c","abstract_canon_sha256":"891db817b7fdd9aca5ac6d6396d712fabdf34600e074fe719ae09bcd267813ee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:17:17.323295Z","signature_b64":"KAOU9/pL5dktYmUlUj6r4R38UpWhM5wznxXvLB40o7H7alHICdI6+J9fBVngBeVaFwrQI6r70OoZR6rwlaKyDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52d071fa3d48012429c50d51fd7bde8d58038d827c9e320825c78ceac68ed72f","last_reissued_at":"2026-06-30T02:17:17.322419Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:17:17.322419Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Role-Playing Evaluation: Anonymous Benchmarking and a Systematic Study of Personality Effects","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ji-Lun Peng, Yun-Nung Chen","submitted_at":"2026-03-04T10:24:02Z","abstract_excerpt":"Large Language Models (LLMs) have shown remarkable potential in developing role-playing agents (RPAs). However, current evaluation frameworks rely heavily on well-known fictional characters, raising a critical concern: models may be leveraging their internal training memory of these characters rather than demonstrating role-playing capabilities. This reliance often leads to significant performance degradation when RPAs encounter unseen or out-of-distribution personas. To address this, we propose a more rigorous evaluation protocol designed to decouple role-playing proficiency from character re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.03915","kind":"arxiv","version":2},"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/2603.03915/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":"2603.03915","created_at":"2026-06-30T02:17:17.322528+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.03915v2","created_at":"2026-06-30T02:17:17.322528+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.03915","created_at":"2026-06-30T02:17:17.322528+00:00"},{"alias_kind":"pith_short_12","alias_value":"KLIHD6R5JAAS","created_at":"2026-06-30T02:17:17.322528+00:00"},{"alias_kind":"pith_short_16","alias_value":"KLIHD6R5JAASIKOF","created_at":"2026-06-30T02:17:17.322528+00:00"},{"alias_kind":"pith_short_8","alias_value":"KLIHD6R5","created_at":"2026-06-30T02:17:17.322528+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/KLIHD6R5JAASIKOFBVI72666RV","json":"https://pith.science/pith/KLIHD6R5JAASIKOFBVI72666RV.json","graph_json":"https://pith.science/api/pith-number/KLIHD6R5JAASIKOFBVI72666RV/graph.json","events_json":"https://pith.science/api/pith-number/KLIHD6R5JAASIKOFBVI72666RV/events.json","paper":"https://pith.science/paper/KLIHD6R5"},"agent_actions":{"view_html":"https://pith.science/pith/KLIHD6R5JAASIKOFBVI72666RV","download_json":"https://pith.science/pith/KLIHD6R5JAASIKOFBVI72666RV.json","view_paper":"https://pith.science/paper/KLIHD6R5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.03915&json=true","fetch_graph":"https://pith.science/api/pith-number/KLIHD6R5JAASIKOFBVI72666RV/graph.json","fetch_events":"https://pith.science/api/pith-number/KLIHD6R5JAASIKOFBVI72666RV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KLIHD6R5JAASIKOFBVI72666RV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KLIHD6R5JAASIKOFBVI72666RV/action/storage_attestation","attest_author":"https://pith.science/pith/KLIHD6R5JAASIKOFBVI72666RV/action/author_attestation","sign_citation":"https://pith.science/pith/KLIHD6R5JAASIKOFBVI72666RV/action/citation_signature","submit_replication":"https://pith.science/pith/KLIHD6R5JAASIKOFBVI72666RV/action/replication_record"}},"created_at":"2026-06-30T02:17:17.322528+00:00","updated_at":"2026-06-30T02:17:17.322528+00:00"}