{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FBZOOOK6RAEYJII2XSAL5KICQN","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":"d8136084124fb976d7ec64b11f3dd1ad4539d892e7eb329e3265d83c3460cbcf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T17:59:43Z","title_canon_sha256":"2fa923496e93b604874664529db62a5d75bee3348bdb40c1681d56adca2d6560"},"schema_version":"1.0","source":{"id":"2505.22661","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.22661","created_at":"2026-07-05T11:11:28Z"},{"alias_kind":"arxiv_version","alias_value":"2505.22661v1","created_at":"2026-07-05T11:11:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22661","created_at":"2026-07-05T11:11:28Z"},{"alias_kind":"pith_short_12","alias_value":"FBZOOOK6RAEY","created_at":"2026-07-05T11:11:28Z"},{"alias_kind":"pith_short_16","alias_value":"FBZOOOK6RAEYJII2","created_at":"2026-07-05T11:11:28Z"},{"alias_kind":"pith_short_8","alias_value":"FBZOOOK6","created_at":"2026-07-05T11:11:28Z"}],"graph_snapshots":[{"event_id":"sha256:e92428db272a4ea472cfadffee286031d347e381d3ebf2279e1ead659e06dfa7","target":"graph","created_at":"2026-07-05T11:11:28Z","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/2505.22661/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The evaluation of large language models (LLMs) has traditionally relied on static benchmarks, a paradigm that poses two major limitations: (1) predefined test sets lack adaptability to diverse application domains, and (2) standardized evaluation protocols often fail to capture fine-grained assessments of domain-specific knowledge and contextual reasoning abilities. To overcome these challenges, we propose GuessArena, an adaptive evaluation framework grounded in adversarial game-based interactions. Inspired by the interactive structure of the Guess Who I Am? game, our framework seamlessly integ","authors_text":"Bo Tang, Ding Chen, Feiyu Xiong, Qingchen Yu, Simin Niu, Zhiyu Li, Zifan Zheng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T17:59:43Z","title":"GuessArena: Guess Who I Am? A Self-Adaptive Framework for Evaluating LLMs in Domain-Specific Knowledge and Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22661","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:b1335648b34ed9d2900cbe1e94e2ca1d67cd970130558cc0acad8406fdc5036a","target":"record","created_at":"2026-07-05T11:11:28Z","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":"d8136084124fb976d7ec64b11f3dd1ad4539d892e7eb329e3265d83c3460cbcf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T17:59:43Z","title_canon_sha256":"2fa923496e93b604874664529db62a5d75bee3348bdb40c1681d56adca2d6560"},"schema_version":"1.0","source":{"id":"2505.22661","kind":"arxiv","version":1}},"canonical_sha256":"2872e7395e880984a11abc80bea90283617d1140dc3f85c88b0230a115f26e19","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2872e7395e880984a11abc80bea90283617d1140dc3f85c88b0230a115f26e19","first_computed_at":"2026-07-05T11:11:28.559572Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:28.559572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rMvOKdGjeyxnPedj7h14JbVGihLUNDh/2NBGxj1PYi5ARfqHhPAqLiBFs+zilSSdAuMckTTzGGRIvIN7SttGDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:28.560110Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.22661","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b1335648b34ed9d2900cbe1e94e2ca1d67cd970130558cc0acad8406fdc5036a","sha256:e92428db272a4ea472cfadffee286031d347e381d3ebf2279e1ead659e06dfa7"],"state_sha256":"7d11f8ba99daf84451bc3c19af6385aebf198a3b03c1b75036f33efe0f8ae368"}