{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FBZOOOK6RAEYJII2XSAL5KICQN","short_pith_number":"pith:FBZOOOK6","schema_version":"1.0","canonical_sha256":"2872e7395e880984a11abc80bea90283617d1140dc3f85c88b0230a115f26e19","source":{"kind":"arxiv","id":"2505.22661","version":1},"attestation_state":"computed","paper":{"title":"GuessArena: Guess Who I Am? A Self-Adaptive Framework for Evaluating LLMs in Domain-Specific Knowledge and Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bo Tang, Ding Chen, Feiyu Xiong, Qingchen Yu, Simin Niu, Zhiyu Li, Zifan Zheng","submitted_at":"2025-05-28T17:59:43Z","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"},"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":"2505.22661","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T17:59:43Z","cross_cats_sorted":[],"title_canon_sha256":"2fa923496e93b604874664529db62a5d75bee3348bdb40c1681d56adca2d6560","abstract_canon_sha256":"d8136084124fb976d7ec64b11f3dd1ad4539d892e7eb329e3265d83c3460cbcf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:28.560110Z","signature_b64":"rMvOKdGjeyxnPedj7h14JbVGihLUNDh/2NBGxj1PYi5ARfqHhPAqLiBFs+zilSSdAuMckTTzGGRIvIN7SttGDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2872e7395e880984a11abc80bea90283617d1140dc3f85c88b0230a115f26e19","last_reissued_at":"2026-07-05T11:11:28.559572Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:28.559572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GuessArena: Guess Who I Am? A Self-Adaptive Framework for Evaluating LLMs in Domain-Specific Knowledge and Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bo Tang, Ding Chen, Feiyu Xiong, Qingchen Yu, Simin Niu, Zhiyu Li, Zifan Zheng","submitted_at":"2025-05-28T17:59:43Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22661","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/2505.22661/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":"2505.22661","created_at":"2026-07-05T11:11:28.559632+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.22661v1","created_at":"2026-07-05T11:11:28.559632+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22661","created_at":"2026-07-05T11:11:28.559632+00:00"},{"alias_kind":"pith_short_12","alias_value":"FBZOOOK6RAEY","created_at":"2026-07-05T11:11:28.559632+00:00"},{"alias_kind":"pith_short_16","alias_value":"FBZOOOK6RAEYJII2","created_at":"2026-07-05T11:11:28.559632+00:00"},{"alias_kind":"pith_short_8","alias_value":"FBZOOOK6","created_at":"2026-07-05T11:11:28.559632+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FBZOOOK6RAEYJII2XSAL5KICQN","json":"https://pith.science/pith/FBZOOOK6RAEYJII2XSAL5KICQN.json","graph_json":"https://pith.science/api/pith-number/FBZOOOK6RAEYJII2XSAL5KICQN/graph.json","events_json":"https://pith.science/api/pith-number/FBZOOOK6RAEYJII2XSAL5KICQN/events.json","paper":"https://pith.science/paper/FBZOOOK6"},"agent_actions":{"view_html":"https://pith.science/pith/FBZOOOK6RAEYJII2XSAL5KICQN","download_json":"https://pith.science/pith/FBZOOOK6RAEYJII2XSAL5KICQN.json","view_paper":"https://pith.science/paper/FBZOOOK6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.22661&json=true","fetch_graph":"https://pith.science/api/pith-number/FBZOOOK6RAEYJII2XSAL5KICQN/graph.json","fetch_events":"https://pith.science/api/pith-number/FBZOOOK6RAEYJII2XSAL5KICQN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FBZOOOK6RAEYJII2XSAL5KICQN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FBZOOOK6RAEYJII2XSAL5KICQN/action/storage_attestation","attest_author":"https://pith.science/pith/FBZOOOK6RAEYJII2XSAL5KICQN/action/author_attestation","sign_citation":"https://pith.science/pith/FBZOOOK6RAEYJII2XSAL5KICQN/action/citation_signature","submit_replication":"https://pith.science/pith/FBZOOOK6RAEYJII2XSAL5KICQN/action/replication_record"}},"created_at":"2026-07-05T11:11:28.559632+00:00","updated_at":"2026-07-05T11:11:28.559632+00:00"}