{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:N2CGLFXQQVG5GHDHDTTBM3XWX4","short_pith_number":"pith:N2CGLFXQ","schema_version":"1.0","canonical_sha256":"6e846596f0854dd31c671ce6166ef6bf0151f675b3af4cef1c0d19a48a3e25d7","source":{"kind":"arxiv","id":"2502.11387","version":1},"attestation_state":"computed","paper":{"title":"RoleMRC: A Fine-Grained Composite Benchmark for Role-Playing and Instruction-Following","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Di Yin, Guodong Shen, Jiazheng Li, Junru Lu, Lin Gui, Siyu An, Xing Sun, Yulan He","submitted_at":"2025-02-17T03:08:37Z","abstract_excerpt":"Role-playing is important for Large Language Models (LLMs) to follow diverse instructions while maintaining role identity and the role's pre-defined ability limits. Existing role-playing datasets mostly contribute to controlling role style and knowledge boundaries, but overlook role-playing in instruction-following scenarios. We introduce a fine-grained role-playing and instruction-following composite benchmark, named RoleMRC, including: (1) Multi-turn dialogues between ideal roles and humans, including free chats or discussions upon given passages; (2) Role-playing machine reading comprehensi"},"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":"2502.11387","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-17T03:08:37Z","cross_cats_sorted":[],"title_canon_sha256":"b62f553054ce4145a5e1d90a90f6175b62038b0305736ec2635159e5a5282085","abstract_canon_sha256":"18a7cff6f2b5dec2029476e5806e3fbe46d53d733dc3cefb037797cb73e664ff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:15:27.557637Z","signature_b64":"3PlvxF5osBfu/BV6oS4YZwtwAldep/zf1eSk3Y+gV8DSMKtScuQRbhiGenuWp4Dw2m0G87Mj5kODegWIZ/VLAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e846596f0854dd31c671ce6166ef6bf0151f675b3af4cef1c0d19a48a3e25d7","last_reissued_at":"2026-07-05T10:15:27.557134Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:15:27.557134Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RoleMRC: A Fine-Grained Composite Benchmark for Role-Playing and Instruction-Following","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Di Yin, Guodong Shen, Jiazheng Li, Junru Lu, Lin Gui, Siyu An, Xing Sun, Yulan He","submitted_at":"2025-02-17T03:08:37Z","abstract_excerpt":"Role-playing is important for Large Language Models (LLMs) to follow diverse instructions while maintaining role identity and the role's pre-defined ability limits. Existing role-playing datasets mostly contribute to controlling role style and knowledge boundaries, but overlook role-playing in instruction-following scenarios. We introduce a fine-grained role-playing and instruction-following composite benchmark, named RoleMRC, including: (1) Multi-turn dialogues between ideal roles and humans, including free chats or discussions upon given passages; (2) Role-playing machine reading comprehensi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.11387","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/2502.11387/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":"2502.11387","created_at":"2026-07-05T10:15:27.557200+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.11387v1","created_at":"2026-07-05T10:15:27.557200+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.11387","created_at":"2026-07-05T10:15:27.557200+00:00"},{"alias_kind":"pith_short_12","alias_value":"N2CGLFXQQVG5","created_at":"2026-07-05T10:15:27.557200+00:00"},{"alias_kind":"pith_short_16","alias_value":"N2CGLFXQQVG5GHDH","created_at":"2026-07-05T10:15:27.557200+00:00"},{"alias_kind":"pith_short_8","alias_value":"N2CGLFXQ","created_at":"2026-07-05T10:15:27.557200+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01552","citing_title":"RoleCDE:Benchmarking and Mitigating Role-Alignment Trade-offs in Role-Playing Agents","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08017","citing_title":"Collaborator or Assistant? How AI Coding Agents Partition Work Across Pull Request Lifecycles","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08017","citing_title":"Collaborator or Assistant? How AI Coding Agents Partition Work Across Pull Request Lifecycles","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N2CGLFXQQVG5GHDHDTTBM3XWX4","json":"https://pith.science/pith/N2CGLFXQQVG5GHDHDTTBM3XWX4.json","graph_json":"https://pith.science/api/pith-number/N2CGLFXQQVG5GHDHDTTBM3XWX4/graph.json","events_json":"https://pith.science/api/pith-number/N2CGLFXQQVG5GHDHDTTBM3XWX4/events.json","paper":"https://pith.science/paper/N2CGLFXQ"},"agent_actions":{"view_html":"https://pith.science/pith/N2CGLFXQQVG5GHDHDTTBM3XWX4","download_json":"https://pith.science/pith/N2CGLFXQQVG5GHDHDTTBM3XWX4.json","view_paper":"https://pith.science/paper/N2CGLFXQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.11387&json=true","fetch_graph":"https://pith.science/api/pith-number/N2CGLFXQQVG5GHDHDTTBM3XWX4/graph.json","fetch_events":"https://pith.science/api/pith-number/N2CGLFXQQVG5GHDHDTTBM3XWX4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N2CGLFXQQVG5GHDHDTTBM3XWX4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N2CGLFXQQVG5GHDHDTTBM3XWX4/action/storage_attestation","attest_author":"https://pith.science/pith/N2CGLFXQQVG5GHDHDTTBM3XWX4/action/author_attestation","sign_citation":"https://pith.science/pith/N2CGLFXQQVG5GHDHDTTBM3XWX4/action/citation_signature","submit_replication":"https://pith.science/pith/N2CGLFXQQVG5GHDHDTTBM3XWX4/action/replication_record"}},"created_at":"2026-07-05T10:15:27.557200+00:00","updated_at":"2026-07-05T10:15:27.557200+00:00"}