{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:73UBGU3BHYM4UPYR6WDZP2RDNT","short_pith_number":"pith:73UBGU3B","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"},"canonical_sha256":"fee81353613e19ca3f11f58797ea236ce28a369c6d4f6d67bf4d897afa247ffe","source":{"kind":"arxiv","id":"2602.14307","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.14307","created_at":"2026-05-29T02:05:41Z"},{"alias_kind":"arxiv_version","alias_value":"2602.14307v3","created_at":"2026-05-29T02:05:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.14307","created_at":"2026-05-29T02:05:41Z"},{"alias_kind":"pith_short_12","alias_value":"73UBGU3BHYM4","created_at":"2026-05-29T02:05:41Z"},{"alias_kind":"pith_short_16","alias_value":"73UBGU3BHYM4UPYR","created_at":"2026-05-29T02:05:41Z"},{"alias_kind":"pith_short_8","alias_value":"73UBGU3B","created_at":"2026-05-29T02:05:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:73UBGU3BHYM4UPYR6WDZP2RDNT","target":"record","payload":{"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"},"canonical_sha256":"fee81353613e19ca3f11f58797ea236ce28a369c6d4f6d67bf4d897afa247ffe","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"},"source_kind":"arxiv","source_id":"2602.14307","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-29T02:05:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s5jstSSq5BwHMGhX67CNb1gk8fa85aDI0hrZCHAPw9TOOvywshX50pNeo33XNnFlq3vedB0wvEhuYDolRkNCCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T20:47:48.207429Z"},"content_sha256":"90a3fffdf2843c980a060b3e3c972884edc50a46b0ccba5d19c466b019f89b06","schema_version":"1.0","event_id":"sha256:90a3fffdf2843c980a060b3e3c972884edc50a46b0ccba5d19c466b019f89b06"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:73UBGU3BHYM4UPYR6WDZP2RDNT","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-29T02:05:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L+wpZY6zuPiIPyhOxyFYp5F8EiqUaV9XHf789kc4ow7Ow18YJGO6JHkvOAN01g8eRQekGTD9kLgdec9YtQU9Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T20:47:48.208187Z"},"content_sha256":"d739fd82bd65dad7cb3ba481bd8ae1da8aa9144b8316d791a55b0af8df65cccc","schema_version":"1.0","event_id":"sha256:d739fd82bd65dad7cb3ba481bd8ae1da8aa9144b8316d791a55b0af8df65cccc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/73UBGU3BHYM4UPYR6WDZP2RDNT/bundle.json","state_url":"https://pith.science/pith/73UBGU3BHYM4UPYR6WDZP2RDNT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/73UBGU3BHYM4UPYR6WDZP2RDNT/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-02T20:47:48Z","links":{"resolver":"https://pith.science/pith/73UBGU3BHYM4UPYR6WDZP2RDNT","bundle":"https://pith.science/pith/73UBGU3BHYM4UPYR6WDZP2RDNT/bundle.json","state":"https://pith.science/pith/73UBGU3BHYM4UPYR6WDZP2RDNT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/73UBGU3BHYM4UPYR6WDZP2RDNT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:73UBGU3BHYM4UPYR6WDZP2RDNT","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":"b79dc0938f633a8abc846003700068029e58ee98cfa705b77f37a6898fb0131c","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-02-15T20:51:29Z","title_canon_sha256":"a127dd8d6e605bbeed1b61ca20014ef6f4e8b03042f7013198a0dd3664948910"},"schema_version":"1.0","source":{"id":"2602.14307","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.14307","created_at":"2026-05-29T02:05:41Z"},{"alias_kind":"arxiv_version","alias_value":"2602.14307v3","created_at":"2026-05-29T02:05:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.14307","created_at":"2026-05-29T02:05:41Z"},{"alias_kind":"pith_short_12","alias_value":"73UBGU3BHYM4","created_at":"2026-05-29T02:05:41Z"},{"alias_kind":"pith_short_16","alias_value":"73UBGU3BHYM4UPYR","created_at":"2026-05-29T02:05:41Z"},{"alias_kind":"pith_short_8","alias_value":"73UBGU3B","created_at":"2026-05-29T02:05:41Z"}],"graph_snapshots":[{"event_id":"sha256:d739fd82bd65dad7cb3ba481bd8ae1da8aa9144b8316d791a55b0af8df65cccc","target":"graph","created_at":"2026-05-29T02:05:41Z","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/2602.14307/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-02-15T20:51:29Z","title":"Benchmarking at the Edge of Comprehension"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.14307","kind":"arxiv","version":3},"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":"sha256:90a3fffdf2843c980a060b3e3c972884edc50a46b0ccba5d19c466b019f89b06","target":"record","created_at":"2026-05-29T02:05:41Z","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":"b79dc0938f633a8abc846003700068029e58ee98cfa705b77f37a6898fb0131c","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-02-15T20:51:29Z","title_canon_sha256":"a127dd8d6e605bbeed1b61ca20014ef6f4e8b03042f7013198a0dd3664948910"},"schema_version":"1.0","source":{"id":"2602.14307","kind":"arxiv","version":3}},"canonical_sha256":"fee81353613e19ca3f11f58797ea236ce28a369c6d4f6d67bf4d897afa247ffe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fee81353613e19ca3f11f58797ea236ce28a369c6d4f6d67bf4d897afa247ffe","first_computed_at":"2026-05-29T02:05:41.370643Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T02:05:41.370643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MyHgSeRPtbFaGA+w/2+PrfKC8JAx6As5QgZCLdIhbvz4yzAMCj1qx0jV0r5prFfZNBIEUyavkCjAxxQwCmfICg==","signature_status":"signed_v1","signed_at":"2026-05-29T02:05:41.371527Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.14307","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:90a3fffdf2843c980a060b3e3c972884edc50a46b0ccba5d19c466b019f89b06","sha256:d739fd82bd65dad7cb3ba481bd8ae1da8aa9144b8316d791a55b0af8df65cccc"],"state_sha256":"78b10bbd86984c966bde79ed0119888459bad8501a26f27de17a0575c216b9a1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"px9l9O/TUfiLvKi4hkWQPD2B35dMlMpGMwUzkcRX3NDZHeM43bQ/+rsHklwDsYUt6nQoIVpmAzQF2dxl6o5GCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T20:47:48.211506Z","bundle_sha256":"a637fba9f8038c3b1966cfb48bd5764d121c15224289dcabc35f3f361af481ee"}}