{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:C736ZUBGBV2W54DOKSEWM4KLHN","short_pith_number":"pith:C736ZUBG","schema_version":"1.0","canonical_sha256":"17f7ecd0260d756ef06e548966714b3b54d8c4d0bde236d69e67792d48e4570f","source":{"kind":"arxiv","id":"2607.24780","version":1},"attestation_state":"computed","paper":{"title":"LivingArena: Do LLMs Know What Other LLMs Don't? Peer-Probing as Scalable Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Liefeng Bo, Rui Wang, Xingyu Chen, Zhaopeng Tu","submitted_at":"2026-06-19T06:20:58Z","abstract_excerpt":"Evaluating frontier LLMs is challenging: static benchmarks suffer from contamination and saturation -- leaving users unable to distinguish top models and developers blind to specific failure modes -- while human preference is subjective. In this paper, our question is: \\emph{Do LLMs know what other LLMs don't? And can we leverage this dynamic for evaluation?} We present \\textbf{LivingArena}, an automated, contamination-resistant evaluation framework. In this framework, models take turns proposing questions, aiming to pose items that opponents cannot answer correctly. Questioners are encouraged"},"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":"2607.24780","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-19T06:20:58Z","cross_cats_sorted":[],"title_canon_sha256":"6fb738a19669c2eb75950f556897b305e7e2100f875f66a287a3d33dd4bf2270","abstract_canon_sha256":"7a580da1ac40ef4b312039fa49019b2d34c864bcad25f063745db3fc98a05264"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-29T00:24:43.661522Z","signature_b64":"65Unytn22nNbWG/4SgNmOZ41J67r1Wz7EYWYGKod1oGSxQAtai9esrMH1O0SUN4qMsC9ELTlU6gLBMIJ3Lr2Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17f7ecd0260d756ef06e548966714b3b54d8c4d0bde236d69e67792d48e4570f","last_reissued_at":"2026-07-29T00:24:43.660659Z","signature_status":"signed_v1","first_computed_at":"2026-07-29T00:24:43.660659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LivingArena: Do LLMs Know What Other LLMs Don't? Peer-Probing as Scalable Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Liefeng Bo, Rui Wang, Xingyu Chen, Zhaopeng Tu","submitted_at":"2026-06-19T06:20:58Z","abstract_excerpt":"Evaluating frontier LLMs is challenging: static benchmarks suffer from contamination and saturation -- leaving users unable to distinguish top models and developers blind to specific failure modes -- while human preference is subjective. In this paper, our question is: \\emph{Do LLMs know what other LLMs don't? And can we leverage this dynamic for evaluation?} We present \\textbf{LivingArena}, an automated, contamination-resistant evaluation framework. In this framework, models take turns proposing questions, aiming to pose items that opponents cannot answer correctly. Questioners are encouraged"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24780","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/2607.24780/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":"2607.24780","created_at":"2026-07-29T00:24:43.661106+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.24780v1","created_at":"2026-07-29T00:24:43.661106+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24780","created_at":"2026-07-29T00:24:43.661106+00:00"},{"alias_kind":"pith_short_12","alias_value":"C736ZUBGBV2W","created_at":"2026-07-29T00:24:43.661106+00:00"},{"alias_kind":"pith_short_16","alias_value":"C736ZUBGBV2W54DO","created_at":"2026-07-29T00:24:43.661106+00:00"},{"alias_kind":"pith_short_8","alias_value":"C736ZUBG","created_at":"2026-07-29T00:24:43.661106+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/C736ZUBGBV2W54DOKSEWM4KLHN","json":"https://pith.science/pith/C736ZUBGBV2W54DOKSEWM4KLHN.json","graph_json":"https://pith.science/api/pith-number/C736ZUBGBV2W54DOKSEWM4KLHN/graph.json","events_json":"https://pith.science/api/pith-number/C736ZUBGBV2W54DOKSEWM4KLHN/events.json","paper":"https://pith.science/paper/C736ZUBG"},"agent_actions":{"view_html":"https://pith.science/pith/C736ZUBGBV2W54DOKSEWM4KLHN","download_json":"https://pith.science/pith/C736ZUBGBV2W54DOKSEWM4KLHN.json","view_paper":"https://pith.science/paper/C736ZUBG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.24780&json=true","fetch_graph":"https://pith.science/api/pith-number/C736ZUBGBV2W54DOKSEWM4KLHN/graph.json","fetch_events":"https://pith.science/api/pith-number/C736ZUBGBV2W54DOKSEWM4KLHN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C736ZUBGBV2W54DOKSEWM4KLHN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C736ZUBGBV2W54DOKSEWM4KLHN/action/storage_attestation","attest_author":"https://pith.science/pith/C736ZUBGBV2W54DOKSEWM4KLHN/action/author_attestation","sign_citation":"https://pith.science/pith/C736ZUBGBV2W54DOKSEWM4KLHN/action/citation_signature","submit_replication":"https://pith.science/pith/C736ZUBGBV2W54DOKSEWM4KLHN/action/replication_record"}},"created_at":"2026-07-29T00:24:43.661106+00:00","updated_at":"2026-07-29T00:24:43.661106+00:00"}