{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XCRNB3ECFPLNRK35TKN2OKGPAE","short_pith_number":"pith:XCRNB3EC","schema_version":"1.0","canonical_sha256":"b8a2d0ec822bd6d8ab7d9a9ba728cf013c0f2de7a6ca398d2d47e35b2bcd1ea0","source":{"kind":"arxiv","id":"2409.06820","version":4},"attestation_state":"computed","paper":{"title":"PingPong: A Benchmark for Role-Playing Language Models with User Emulation and Multi-Model Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ilya Gusev","submitted_at":"2024-09-10T19:00:44Z","abstract_excerpt":"We introduce a benchmark for evaluating the role-playing capabilities of language models. Our approach leverages different language models to simulate users in dynamic, multi-turn conversations and assess the resulting dialogues. Our methodology involves three main components: a player model that adopts a specific character role, an interrogator model that simulates user behavior in a specific situation, and a judge model ensemble that evaluates conversation quality with 3 metrics: character consistency, entertainment value, and language fluency. We evaluated more than 40 models in both Englis"},"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":"2409.06820","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-10T19:00:44Z","cross_cats_sorted":[],"title_canon_sha256":"88a853b5ce94698e61b954aba73a4749f8f21c4579b01b365bc94bebec4ab1cb","abstract_canon_sha256":"3478769e00ad161652c817c8f61e5d97266ab5234f13dad17b8c9021e21ed835"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:46:38.289849Z","signature_b64":"/fQ1iwhhIJc6G+8brhZ9mPtVS8FW8eR29/7z2NWwYGnAHVTmLKP0StW9fI1d7K3//akzB3Nx83/Wo3Im9oLNAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8a2d0ec822bd6d8ab7d9a9ba728cf013c0f2de7a6ca398d2d47e35b2bcd1ea0","last_reissued_at":"2026-07-05T10:46:38.289335Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:46:38.289335Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PingPong: A Benchmark for Role-Playing Language Models with User Emulation and Multi-Model Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ilya Gusev","submitted_at":"2024-09-10T19:00:44Z","abstract_excerpt":"We introduce a benchmark for evaluating the role-playing capabilities of language models. Our approach leverages different language models to simulate users in dynamic, multi-turn conversations and assess the resulting dialogues. Our methodology involves three main components: a player model that adopts a specific character role, an interrogator model that simulates user behavior in a specific situation, and a judge model ensemble that evaluates conversation quality with 3 metrics: character consistency, entertainment value, and language fluency. We evaluated more than 40 models in both Englis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.06820","kind":"arxiv","version":4},"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/2409.06820/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":"2409.06820","created_at":"2026-07-05T10:46:38.289391+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.06820v4","created_at":"2026-07-05T10:46:38.289391+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.06820","created_at":"2026-07-05T10:46:38.289391+00:00"},{"alias_kind":"pith_short_12","alias_value":"XCRNB3ECFPLN","created_at":"2026-07-05T10:46:38.289391+00:00"},{"alias_kind":"pith_short_16","alias_value":"XCRNB3ECFPLNRK35","created_at":"2026-07-05T10:46:38.289391+00:00"},{"alias_kind":"pith_short_8","alias_value":"XCRNB3EC","created_at":"2026-07-05T10:46:38.289391+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30339","citing_title":"REAR: Test-time Preference Realignment through Reward Decomposition","ref_index":111,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27025","citing_title":"Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization","ref_index":102,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XCRNB3ECFPLNRK35TKN2OKGPAE","json":"https://pith.science/pith/XCRNB3ECFPLNRK35TKN2OKGPAE.json","graph_json":"https://pith.science/api/pith-number/XCRNB3ECFPLNRK35TKN2OKGPAE/graph.json","events_json":"https://pith.science/api/pith-number/XCRNB3ECFPLNRK35TKN2OKGPAE/events.json","paper":"https://pith.science/paper/XCRNB3EC"},"agent_actions":{"view_html":"https://pith.science/pith/XCRNB3ECFPLNRK35TKN2OKGPAE","download_json":"https://pith.science/pith/XCRNB3ECFPLNRK35TKN2OKGPAE.json","view_paper":"https://pith.science/paper/XCRNB3EC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.06820&json=true","fetch_graph":"https://pith.science/api/pith-number/XCRNB3ECFPLNRK35TKN2OKGPAE/graph.json","fetch_events":"https://pith.science/api/pith-number/XCRNB3ECFPLNRK35TKN2OKGPAE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XCRNB3ECFPLNRK35TKN2OKGPAE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XCRNB3ECFPLNRK35TKN2OKGPAE/action/storage_attestation","attest_author":"https://pith.science/pith/XCRNB3ECFPLNRK35TKN2OKGPAE/action/author_attestation","sign_citation":"https://pith.science/pith/XCRNB3ECFPLNRK35TKN2OKGPAE/action/citation_signature","submit_replication":"https://pith.science/pith/XCRNB3ECFPLNRK35TKN2OKGPAE/action/replication_record"}},"created_at":"2026-07-05T10:46:38.289391+00:00","updated_at":"2026-07-05T10:46:38.289391+00:00"}