{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KXL2EYKIYDFJ2EN3AVX6HGVRTR","short_pith_number":"pith:KXL2EYKI","schema_version":"1.0","canonical_sha256":"55d7a26148c0ca9d11bb056fe39ab19c73ab8b08b3617dfc47d4d567438a745a","source":{"kind":"arxiv","id":"2409.14710","version":2},"attestation_state":"computed","paper":{"title":"ERABAL: Enhancing Role-Playing Agents through Boundary-Aware Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Che Liu, Di Zhang, Fuzheng Zhang, Jiao Ou, Kun Gai, Yihong Tang","submitted_at":"2024-09-23T05:12:13Z","abstract_excerpt":"Role-playing is an emerging application in the field of Human-Computer Interaction (HCI), primarily implemented through the alignment training of a large language model (LLM) with assigned characters. Despite significant progress, role-playing agents (RPLAs) still struggle with maintaining role-consistency across conversations, particularly when confronted with boundary queries subtly related to character attributes. In this paper, we present ERABAL, a framework aimed at enhancing RPLAs' role-playing capabilities through boundary-aware learning. ERABAL encompasses a generation pipeline for rol"},"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":"2409.14710","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-23T05:12:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f6871eff63c6a287b668841dcbf8e262de993b182482e19fb8e02c81019e1bfb","abstract_canon_sha256":"5018c7b17d853b90c481d31bbcd5c657b1fdf4c795896d509f0d518724bdf503"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:23:59.241448Z","signature_b64":"Whzm7RUg/qeWX8JdBlNyq4L4F+cdBPg/Cc8y0urqIXiY3pS1N3fwqduXBuaPHsjFSEhRa9sLgU5ae1DrfCTODQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55d7a26148c0ca9d11bb056fe39ab19c73ab8b08b3617dfc47d4d567438a745a","last_reissued_at":"2026-07-05T09:23:59.240913Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:23:59.240913Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ERABAL: Enhancing Role-Playing Agents through Boundary-Aware Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Che Liu, Di Zhang, Fuzheng Zhang, Jiao Ou, Kun Gai, Yihong Tang","submitted_at":"2024-09-23T05:12:13Z","abstract_excerpt":"Role-playing is an emerging application in the field of Human-Computer Interaction (HCI), primarily implemented through the alignment training of a large language model (LLM) with assigned characters. Despite significant progress, role-playing agents (RPLAs) still struggle with maintaining role-consistency across conversations, particularly when confronted with boundary queries subtly related to character attributes. In this paper, we present ERABAL, a framework aimed at enhancing RPLAs' role-playing capabilities through boundary-aware learning. ERABAL encompasses a generation pipeline for rol"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.14710","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/2409.14710/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":"2409.14710","created_at":"2026-07-05T09:23:59.240983+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.14710v2","created_at":"2026-07-05T09:23:59.240983+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.14710","created_at":"2026-07-05T09:23:59.240983+00:00"},{"alias_kind":"pith_short_12","alias_value":"KXL2EYKIYDFJ","created_at":"2026-07-05T09:23:59.240983+00:00"},{"alias_kind":"pith_short_16","alias_value":"KXL2EYKIYDFJ2EN3","created_at":"2026-07-05T09:23:59.240983+00:00"},{"alias_kind":"pith_short_8","alias_value":"KXL2EYKI","created_at":"2026-07-05T09:23:59.240983+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25632","citing_title":"Staying In Character: Perspective-Bounded Memory For Book-Based Role-Playing Agents","ref_index":47,"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":75,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14169","citing_title":"BOOKMARKS: Efficient Active Storyline Memory for Role-playing","ref_index":122,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KXL2EYKIYDFJ2EN3AVX6HGVRTR","json":"https://pith.science/pith/KXL2EYKIYDFJ2EN3AVX6HGVRTR.json","graph_json":"https://pith.science/api/pith-number/KXL2EYKIYDFJ2EN3AVX6HGVRTR/graph.json","events_json":"https://pith.science/api/pith-number/KXL2EYKIYDFJ2EN3AVX6HGVRTR/events.json","paper":"https://pith.science/paper/KXL2EYKI"},"agent_actions":{"view_html":"https://pith.science/pith/KXL2EYKIYDFJ2EN3AVX6HGVRTR","download_json":"https://pith.science/pith/KXL2EYKIYDFJ2EN3AVX6HGVRTR.json","view_paper":"https://pith.science/paper/KXL2EYKI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.14710&json=true","fetch_graph":"https://pith.science/api/pith-number/KXL2EYKIYDFJ2EN3AVX6HGVRTR/graph.json","fetch_events":"https://pith.science/api/pith-number/KXL2EYKIYDFJ2EN3AVX6HGVRTR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KXL2EYKIYDFJ2EN3AVX6HGVRTR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KXL2EYKIYDFJ2EN3AVX6HGVRTR/action/storage_attestation","attest_author":"https://pith.science/pith/KXL2EYKIYDFJ2EN3AVX6HGVRTR/action/author_attestation","sign_citation":"https://pith.science/pith/KXL2EYKIYDFJ2EN3AVX6HGVRTR/action/citation_signature","submit_replication":"https://pith.science/pith/KXL2EYKIYDFJ2EN3AVX6HGVRTR/action/replication_record"}},"created_at":"2026-07-05T09:23:59.240983+00:00","updated_at":"2026-07-05T09:23:59.240983+00:00"}