{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OYXA2CR4YHZIPQFUQYNMM5NIOX","short_pith_number":"pith:OYXA2CR4","schema_version":"1.0","canonical_sha256":"762e0d0a3cc1f287c0b4861ac675a875efcbd7af89ef58785eb0bbed24059041","source":{"kind":"arxiv","id":"2605.30104","version":1},"attestation_state":"computed","paper":{"title":"SEAL: Can Saturated Benchmarks Be Revived by LLM-as-a-Meta-Judge?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chen Ma, Jiamin Chen, Qianben Chen, Qiexiang Wang, Wangchunshu Zhou, Xiaokun Zhang, Yansen Zhang, Yidi Wu, Yuchen Li","submitted_at":"2026-05-28T15:46:54Z","abstract_excerpt":"Widely used language-model benchmarks are increasingly saturated, with frontier systems often receiving near-tied scores that standard metrics cannot resolve. Rather than constructing harder alternatives, we ask whether existing tasks can be made informative again through improved evaluation over the same candidate outputs. Therefore, we present Seeded Elimination with Adaptive LLM-as-a-Meta-Judge, a self-improving evaluation protocol for extracting latent ranking signal from saturated benchmarks. SEAL seeds candidate outputs into a single elimination and evaluates each match with task-level p"},"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":"2605.30104","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T15:46:54Z","cross_cats_sorted":[],"title_canon_sha256":"ce9ca4fd453749fe2166df1276eb16cdae2965a003ae8162a415c62376c6868b","abstract_canon_sha256":"c51bc117e938e5ac65c1c9d9d3a7fdcef4c8f5a38eb59a6d265c2393bbd22845"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:06:09.941050Z","signature_b64":"yWqwzECRAydxj6Z0/Wtb8GRpnt6Ab1gENL2mPSPFRAs7Px7/Jq0TjZ3+SKH5wS0gm8lVhTzlEwxtLEBsXYcIAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"762e0d0a3cc1f287c0b4861ac675a875efcbd7af89ef58785eb0bbed24059041","last_reissued_at":"2026-05-29T02:06:09.940670Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:06:09.940670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SEAL: Can Saturated Benchmarks Be Revived by LLM-as-a-Meta-Judge?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chen Ma, Jiamin Chen, Qianben Chen, Qiexiang Wang, Wangchunshu Zhou, Xiaokun Zhang, Yansen Zhang, Yidi Wu, Yuchen Li","submitted_at":"2026-05-28T15:46:54Z","abstract_excerpt":"Widely used language-model benchmarks are increasingly saturated, with frontier systems often receiving near-tied scores that standard metrics cannot resolve. Rather than constructing harder alternatives, we ask whether existing tasks can be made informative again through improved evaluation over the same candidate outputs. Therefore, we present Seeded Elimination with Adaptive LLM-as-a-Meta-Judge, a self-improving evaluation protocol for extracting latent ranking signal from saturated benchmarks. SEAL seeds candidate outputs into a single elimination and evaluates each match with task-level p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30104","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/2605.30104/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":"2605.30104","created_at":"2026-05-29T02:06:09.940732+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.30104v1","created_at":"2026-05-29T02:06:09.940732+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30104","created_at":"2026-05-29T02:06:09.940732+00:00"},{"alias_kind":"pith_short_12","alias_value":"OYXA2CR4YHZI","created_at":"2026-05-29T02:06:09.940732+00:00"},{"alias_kind":"pith_short_16","alias_value":"OYXA2CR4YHZIPQFU","created_at":"2026-05-29T02:06:09.940732+00:00"},{"alias_kind":"pith_short_8","alias_value":"OYXA2CR4","created_at":"2026-05-29T02:06:09.940732+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/OYXA2CR4YHZIPQFUQYNMM5NIOX","json":"https://pith.science/pith/OYXA2CR4YHZIPQFUQYNMM5NIOX.json","graph_json":"https://pith.science/api/pith-number/OYXA2CR4YHZIPQFUQYNMM5NIOX/graph.json","events_json":"https://pith.science/api/pith-number/OYXA2CR4YHZIPQFUQYNMM5NIOX/events.json","paper":"https://pith.science/paper/OYXA2CR4"},"agent_actions":{"view_html":"https://pith.science/pith/OYXA2CR4YHZIPQFUQYNMM5NIOX","download_json":"https://pith.science/pith/OYXA2CR4YHZIPQFUQYNMM5NIOX.json","view_paper":"https://pith.science/paper/OYXA2CR4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.30104&json=true","fetch_graph":"https://pith.science/api/pith-number/OYXA2CR4YHZIPQFUQYNMM5NIOX/graph.json","fetch_events":"https://pith.science/api/pith-number/OYXA2CR4YHZIPQFUQYNMM5NIOX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OYXA2CR4YHZIPQFUQYNMM5NIOX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OYXA2CR4YHZIPQFUQYNMM5NIOX/action/storage_attestation","attest_author":"https://pith.science/pith/OYXA2CR4YHZIPQFUQYNMM5NIOX/action/author_attestation","sign_citation":"https://pith.science/pith/OYXA2CR4YHZIPQFUQYNMM5NIOX/action/citation_signature","submit_replication":"https://pith.science/pith/OYXA2CR4YHZIPQFUQYNMM5NIOX/action/replication_record"}},"created_at":"2026-05-29T02:06:09.940732+00:00","updated_at":"2026-05-29T02:06:09.940732+00:00"}