{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:73UBGU3BHYM4UPYR6WDZP2RDNT","short_pith_number":"pith:73UBGU3B","schema_version":"1.0","canonical_sha256":"fee81353613e19ca3f11f58797ea236ce28a369c6d4f6d67bf4d897afa247ffe","source":{"kind":"arxiv","id":"2602.14307","version":3},"attestation_state":"computed","paper":{"title":"Benchmarking at the Edge of Comprehension","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Ebey Abraham, Emanuele La Malfa, Eric Sommerlade, Jialin Yu, Jiawei Li, Michael Wooldridge, Oishi Deb, Philip Torr, Samuele Marro, Sunando Sengupta, Yibo Yang","submitted_at":"2026-02-15T20:51:29Z","abstract_excerpt":"As frontier Large Language Models (LLMs) increasingly saturate new benchmarks shortly after they are published, benchmarking itself is at a juncture: if frontier models keep improving, it will become increasingly hard for humans to generate discriminative tasks, provide accurate ground-truth answers, or evaluate complex solutions. If benchmarking becomes infeasible, our ability to measure any progress in AI is at stake. We refer to this scenario as the post-comprehension regime. In this work, we propose Critique-Resilient Benchmarking, an adversarial framework designed to compare models even w"},"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":"2602.14307","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-02-15T20:51:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a127dd8d6e605bbeed1b61ca20014ef6f4e8b03042f7013198a0dd3664948910","abstract_canon_sha256":"b79dc0938f633a8abc846003700068029e58ee98cfa705b77f37a6898fb0131c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:05:41.371527Z","signature_b64":"MyHgSeRPtbFaGA+w/2+PrfKC8JAx6As5QgZCLdIhbvz4yzAMCj1qx0jV0r5prFfZNBIEUyavkCjAxxQwCmfICg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fee81353613e19ca3f11f58797ea236ce28a369c6d4f6d67bf4d897afa247ffe","last_reissued_at":"2026-05-29T02:05:41.370643Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:05:41.370643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking at the Edge of Comprehension","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Ebey Abraham, Emanuele La Malfa, Eric Sommerlade, Jialin Yu, Jiawei Li, Michael Wooldridge, Oishi Deb, Philip Torr, Samuele Marro, Sunando Sengupta, Yibo Yang","submitted_at":"2026-02-15T20:51:29Z","abstract_excerpt":"As frontier Large Language Models (LLMs) increasingly saturate new benchmarks shortly after they are published, benchmarking itself is at a juncture: if frontier models keep improving, it will become increasingly hard for humans to generate discriminative tasks, provide accurate ground-truth answers, or evaluate complex solutions. If benchmarking becomes infeasible, our ability to measure any progress in AI is at stake. We refer to this scenario as the post-comprehension regime. In this work, we propose Critique-Resilient Benchmarking, an adversarial framework designed to compare models even w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.14307","kind":"arxiv","version":3},"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/2602.14307/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":"2602.14307","created_at":"2026-05-29T02:05:41.370773+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.14307v3","created_at":"2026-05-29T02:05:41.370773+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.14307","created_at":"2026-05-29T02:05:41.370773+00:00"},{"alias_kind":"pith_short_12","alias_value":"73UBGU3BHYM4","created_at":"2026-05-29T02:05:41.370773+00:00"},{"alias_kind":"pith_short_16","alias_value":"73UBGU3BHYM4UPYR","created_at":"2026-05-29T02:05:41.370773+00:00"},{"alias_kind":"pith_short_8","alias_value":"73UBGU3B","created_at":"2026-05-29T02:05:41.370773+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/73UBGU3BHYM4UPYR6WDZP2RDNT","json":"https://pith.science/pith/73UBGU3BHYM4UPYR6WDZP2RDNT.json","graph_json":"https://pith.science/api/pith-number/73UBGU3BHYM4UPYR6WDZP2RDNT/graph.json","events_json":"https://pith.science/api/pith-number/73UBGU3BHYM4UPYR6WDZP2RDNT/events.json","paper":"https://pith.science/paper/73UBGU3B"},"agent_actions":{"view_html":"https://pith.science/pith/73UBGU3BHYM4UPYR6WDZP2RDNT","download_json":"https://pith.science/pith/73UBGU3BHYM4UPYR6WDZP2RDNT.json","view_paper":"https://pith.science/paper/73UBGU3B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.14307&json=true","fetch_graph":"https://pith.science/api/pith-number/73UBGU3BHYM4UPYR6WDZP2RDNT/graph.json","fetch_events":"https://pith.science/api/pith-number/73UBGU3BHYM4UPYR6WDZP2RDNT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/73UBGU3BHYM4UPYR6WDZP2RDNT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/73UBGU3BHYM4UPYR6WDZP2RDNT/action/storage_attestation","attest_author":"https://pith.science/pith/73UBGU3BHYM4UPYR6WDZP2RDNT/action/author_attestation","sign_citation":"https://pith.science/pith/73UBGU3BHYM4UPYR6WDZP2RDNT/action/citation_signature","submit_replication":"https://pith.science/pith/73UBGU3BHYM4UPYR6WDZP2RDNT/action/replication_record"}},"created_at":"2026-05-29T02:05:41.370773+00:00","updated_at":"2026-05-29T02:05:41.370773+00:00"}