{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Q4EQXZIQVC4NU34L65O7CA2PER","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":"7409cde30b15b3d76a706e0ca426371357f6e56252c0822c9b0e80ca5aed6498","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-16T15:55:34Z","title_canon_sha256":"7193d12b625363c5f2bc534f1f7f5a301589b270423a89fc5ffab3c986fa838c"},"schema_version":"1.0","source":{"id":"2412.11912","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.11912","created_at":"2026-07-05T09:49:53Z"},{"alias_kind":"arxiv_version","alias_value":"2412.11912v1","created_at":"2026-07-05T09:49:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11912","created_at":"2026-07-05T09:49:53Z"},{"alias_kind":"pith_short_12","alias_value":"Q4EQXZIQVC4N","created_at":"2026-07-05T09:49:53Z"},{"alias_kind":"pith_short_16","alias_value":"Q4EQXZIQVC4NU34L","created_at":"2026-07-05T09:49:53Z"},{"alias_kind":"pith_short_8","alias_value":"Q4EQXZIQ","created_at":"2026-07-05T09:49:53Z"}],"graph_snapshots":[{"event_id":"sha256:5d792acb93d67c3ea1033db306209e261c0c33f9d1d4bef3aeef5c4bd9691a65","target":"graph","created_at":"2026-07-05T09:49:53Z","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/2412.11912/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Character-based dialogue (aka role-playing) enables users to freely customize characters for interaction, which often relies on LLMs, raising the need to evaluate LLMs' character customization capability. However, existing benchmarks fail to ensure a robust evaluation as they often only involve a single character category or evaluate limited dimensions. Moreover, the sparsity of character features in responses makes feature-focused generative evaluation both ineffective and inefficient. To address these issues, we propose CharacterBench, the largest bilingual generative benchmark, with 22,859 ","authors_text":"Bosi Wen, Guanqun Bi, Hongning Wang, Jinfeng Zhou, Kuntian Tang, Le Zhang, Libiao Peng, Minlie Huang, Pei Ke, Rongsheng Zhang, Tangjie Lv, Xiyao Xiao, Yongkang Huang, Yuxuan Chen, Zhipeng Hu, Zhuang Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-16T15:55:34Z","title":"CharacterBench: Benchmarking Character Customization of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11912","kind":"arxiv","version":1},"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":"sha256:4ad047c754a3ba382d9d93db54456c5ba4beeeff53b5acf6119c04aa9ad91ad8","target":"record","created_at":"2026-07-05T09:49:53Z","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":"7409cde30b15b3d76a706e0ca426371357f6e56252c0822c9b0e80ca5aed6498","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-16T15:55:34Z","title_canon_sha256":"7193d12b625363c5f2bc534f1f7f5a301589b270423a89fc5ffab3c986fa838c"},"schema_version":"1.0","source":{"id":"2412.11912","kind":"arxiv","version":1}},"canonical_sha256":"87090be510a8b8da6f8bf75df1034f24566030d4865bf81ac3e356dfa408d4b6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"87090be510a8b8da6f8bf75df1034f24566030d4865bf81ac3e356dfa408d4b6","first_computed_at":"2026-07-05T09:49:53.447777Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:49:53.447777Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KfoH5mq+rGh8UeVGV3Z0G227ydXeSEXU80HN7DFrQfj/T3iE71DNKAyIG10ugiur15Pc717T2bDR/bWwMsRABA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:49:53.448295Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.11912","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4ad047c754a3ba382d9d93db54456c5ba4beeeff53b5acf6119c04aa9ad91ad8","sha256:5d792acb93d67c3ea1033db306209e261c0c33f9d1d4bef3aeef5c4bd9691a65"],"state_sha256":"a8ae39687be044ec1f563c2df854cd1dc5328d639439814c2b29c5e3476cf0f5"}