{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KLIHD6R5JAASIKOFBVI72666RV","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":"891db817b7fdd9aca5ac6d6396d712fabdf34600e074fe719ae09bcd267813ee","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-03-04T10:24:02Z","title_canon_sha256":"60c7fd876272146a90c7787795071f6866eadceff03fa02df6223c41c3726e0c"},"schema_version":"1.0","source":{"id":"2603.03915","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.03915","created_at":"2026-06-30T02:17:17Z"},{"alias_kind":"arxiv_version","alias_value":"2603.03915v2","created_at":"2026-06-30T02:17:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.03915","created_at":"2026-06-30T02:17:17Z"},{"alias_kind":"pith_short_12","alias_value":"KLIHD6R5JAAS","created_at":"2026-06-30T02:17:17Z"},{"alias_kind":"pith_short_16","alias_value":"KLIHD6R5JAASIKOF","created_at":"2026-06-30T02:17:17Z"},{"alias_kind":"pith_short_8","alias_value":"KLIHD6R5","created_at":"2026-06-30T02:17:17Z"}],"graph_snapshots":[{"event_id":"sha256:6d73548d9b86be1d4df2fbebef39cb1a165d4f32ca106fdd6657145c8dc70e73","target":"graph","created_at":"2026-06-30T02:17:17Z","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/2603.03915/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ji-Lun Peng, Yun-Nung Chen","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-03-04T10:24:02Z","title":"Rethinking Role-Playing Evaluation: Anonymous Benchmarking and a Systematic Study of Personality Effects"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.03915","kind":"arxiv","version":2},"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":"sha256:39ff9260636184036dc217f0812be74a2c13469ecd0cda5aa782ea37313965a7","target":"record","created_at":"2026-06-30T02:17:17Z","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":"891db817b7fdd9aca5ac6d6396d712fabdf34600e074fe719ae09bcd267813ee","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-03-04T10:24:02Z","title_canon_sha256":"60c7fd876272146a90c7787795071f6866eadceff03fa02df6223c41c3726e0c"},"schema_version":"1.0","source":{"id":"2603.03915","kind":"arxiv","version":2}},"canonical_sha256":"52d071fa3d48012429c50d51fd7bde8d58038d827c9e320825c78ceac68ed72f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"52d071fa3d48012429c50d51fd7bde8d58038d827c9e320825c78ceac68ed72f","first_computed_at":"2026-06-30T02:17:17.322419Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T02:17:17.322419Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KAOU9/pL5dktYmUlUj6r4R38UpWhM5wznxXvLB40o7H7alHICdI6+J9fBVngBeVaFwrQI6r70OoZR6rwlaKyDA==","signature_status":"signed_v1","signed_at":"2026-06-30T02:17:17.323295Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.03915","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:39ff9260636184036dc217f0812be74a2c13469ecd0cda5aa782ea37313965a7","sha256:6d73548d9b86be1d4df2fbebef39cb1a165d4f32ca106fdd6657145c8dc70e73"],"state_sha256":"2a86c4e0b5438dc45e68c6d78a8ea5d2eabaa37389aaef3791777d9fa1bf0a0e"}