{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:FJVMDCI5CGJ4PXF3XXIWO6LGWH","short_pith_number":"pith:FJVMDCI5","canonical_record":{"source":{"id":"2608.00794","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-01T17:50:12Z","cross_cats_sorted":[],"title_canon_sha256":"1804255789e3e1968d1ffc26573a1cb4a596fd1d595f126d84bf9fb7062fad8e","abstract_canon_sha256":"b7441f555efaaba5f66dfd47d01154cd06b754e85728d5340209cdf9c7775f4e"},"schema_version":"1.0"},"canonical_sha256":"2a6ac1891d1193c7dcbbbdd1677966b1d72069587bc336ccac57c0870cf624f0","source":{"kind":"arxiv","id":"2608.00794","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.00794","created_at":"2026-08-04T01:55:09Z"},{"alias_kind":"arxiv_version","alias_value":"2608.00794v1","created_at":"2026-08-04T01:55:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00794","created_at":"2026-08-04T01:55:09Z"},{"alias_kind":"pith_short_12","alias_value":"FJVMDCI5CGJ4","created_at":"2026-08-04T01:55:09Z"},{"alias_kind":"pith_short_16","alias_value":"FJVMDCI5CGJ4PXF3","created_at":"2026-08-04T01:55:09Z"},{"alias_kind":"pith_short_8","alias_value":"FJVMDCI5","created_at":"2026-08-04T01:55:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:FJVMDCI5CGJ4PXF3XXIWO6LGWH","target":"record","payload":{"canonical_record":{"source":{"id":"2608.00794","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-01T17:50:12Z","cross_cats_sorted":[],"title_canon_sha256":"1804255789e3e1968d1ffc26573a1cb4a596fd1d595f126d84bf9fb7062fad8e","abstract_canon_sha256":"b7441f555efaaba5f66dfd47d01154cd06b754e85728d5340209cdf9c7775f4e"},"schema_version":"1.0"},"canonical_sha256":"2a6ac1891d1193c7dcbbbdd1677966b1d72069587bc336ccac57c0870cf624f0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T01:55:09.654455Z","signature_b64":"mspCEBMi1sFy4cwPfJXbZ5Yc9MDsn4YbaM1FEab3F5ad9rDRpjIEcQ1DNqXB9DmnbuJJfipmmsKRkUcPkLgSCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a6ac1891d1193c7dcbbbdd1677966b1d72069587bc336ccac57c0870cf624f0","last_reissued_at":"2026-08-04T01:55:09.652870Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T01:55:09.652870Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.00794","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-04T01:55:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZXK0IcmTyS6tZELsXlDuuGVDNFXfJ6qT37bm6G50+9FRZb0id95kRmN0CBb1M0zKrNhuOTq3N1+SNNNPYoQaAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T09:56:32.202404Z"},"content_sha256":"640c263725c67b15e73f049d36be6126c45c57ffe4f758b71122e773f87f8368","schema_version":"1.0","event_id":"sha256:640c263725c67b15e73f049d36be6126c45c57ffe4f758b71122e773f87f8368"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:FJVMDCI5CGJ4PXF3XXIWO6LGWH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Measurement Without Validity: The Compounding Reliability Problem in Agentic AI Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"William Caban","submitted_at":"2026-08-01T17:50:12Z","abstract_excerpt":"Agentic AI systems are evaluated using automated benchmarks whose scores justify deployment decisions, safety certifications, and regulatory compliance claims. We present an empirical analysis demonstrating that these scores are systematically less trustworthy than current practice acknowledges.\n  The problem operates at three compounding layers. First, tasks are increasingly generated by language models: audits of ten popular benchmarks found validity flaws in seven and reporting gaps in all ten. Second, human users are replaced by LLM simulators, but calibration studies document inter-simula"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00794","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/2608.00794/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":"2026-08-04T01:55:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rHkRvbRp/fSJJKUBd+malgriBU8JlSofwvBIosUIIIPb95nsMyMpKlbb0UTTRm00PNk7TetPxiQhRxVG+kOVBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T09:56:32.203049Z"},"content_sha256":"66c9530fd3fdf19a541f8d2265636d2ba16694dac38798e947379825b2ee5b82","schema_version":"1.0","event_id":"sha256:66c9530fd3fdf19a541f8d2265636d2ba16694dac38798e947379825b2ee5b82"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FJVMDCI5CGJ4PXF3XXIWO6LGWH/bundle.json","state_url":"https://pith.science/pith/FJVMDCI5CGJ4PXF3XXIWO6LGWH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FJVMDCI5CGJ4PXF3XXIWO6LGWH/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":"2026-08-05T09:56:32Z","links":{"resolver":"https://pith.science/pith/FJVMDCI5CGJ4PXF3XXIWO6LGWH","bundle":"https://pith.science/pith/FJVMDCI5CGJ4PXF3XXIWO6LGWH/bundle.json","state":"https://pith.science/pith/FJVMDCI5CGJ4PXF3XXIWO6LGWH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FJVMDCI5CGJ4PXF3XXIWO6LGWH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FJVMDCI5CGJ4PXF3XXIWO6LGWH","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":"b7441f555efaaba5f66dfd47d01154cd06b754e85728d5340209cdf9c7775f4e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-01T17:50:12Z","title_canon_sha256":"1804255789e3e1968d1ffc26573a1cb4a596fd1d595f126d84bf9fb7062fad8e"},"schema_version":"1.0","source":{"id":"2608.00794","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.00794","created_at":"2026-08-04T01:55:09Z"},{"alias_kind":"arxiv_version","alias_value":"2608.00794v1","created_at":"2026-08-04T01:55:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00794","created_at":"2026-08-04T01:55:09Z"},{"alias_kind":"pith_short_12","alias_value":"FJVMDCI5CGJ4","created_at":"2026-08-04T01:55:09Z"},{"alias_kind":"pith_short_16","alias_value":"FJVMDCI5CGJ4PXF3","created_at":"2026-08-04T01:55:09Z"},{"alias_kind":"pith_short_8","alias_value":"FJVMDCI5","created_at":"2026-08-04T01:55:09Z"}],"graph_snapshots":[{"event_id":"sha256:66c9530fd3fdf19a541f8d2265636d2ba16694dac38798e947379825b2ee5b82","target":"graph","created_at":"2026-08-04T01:55:09Z","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/2608.00794/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Agentic AI systems are evaluated using automated benchmarks whose scores justify deployment decisions, safety certifications, and regulatory compliance claims. We present an empirical analysis demonstrating that these scores are systematically less trustworthy than current practice acknowledges.\n  The problem operates at three compounding layers. First, tasks are increasingly generated by language models: audits of ten popular benchmarks found validity flaws in seven and reporting gaps in all ten. Second, human users are replaced by LLM simulators, but calibration studies document inter-simula","authors_text":"William Caban","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-01T17:50:12Z","title":"Measurement Without Validity: The Compounding Reliability Problem in Agentic AI Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00794","kind":"arxiv","version":1},"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":"sha256:640c263725c67b15e73f049d36be6126c45c57ffe4f758b71122e773f87f8368","target":"record","created_at":"2026-08-04T01:55:09Z","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":"b7441f555efaaba5f66dfd47d01154cd06b754e85728d5340209cdf9c7775f4e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-01T17:50:12Z","title_canon_sha256":"1804255789e3e1968d1ffc26573a1cb4a596fd1d595f126d84bf9fb7062fad8e"},"schema_version":"1.0","source":{"id":"2608.00794","kind":"arxiv","version":1}},"canonical_sha256":"2a6ac1891d1193c7dcbbbdd1677966b1d72069587bc336ccac57c0870cf624f0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2a6ac1891d1193c7dcbbbdd1677966b1d72069587bc336ccac57c0870cf624f0","first_computed_at":"2026-08-04T01:55:09.652870Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T01:55:09.652870Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mspCEBMi1sFy4cwPfJXbZ5Yc9MDsn4YbaM1FEab3F5ad9rDRpjIEcQ1DNqXB9DmnbuJJfipmmsKRkUcPkLgSCQ==","signature_status":"signed_v1","signed_at":"2026-08-04T01:55:09.654455Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.00794","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:640c263725c67b15e73f049d36be6126c45c57ffe4f758b71122e773f87f8368","sha256:66c9530fd3fdf19a541f8d2265636d2ba16694dac38798e947379825b2ee5b82"],"state_sha256":"5430efdc690f17fd983419bdb0222dea826cceb570a6ab907863120619613330"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Nl89+L68ZewVk0h4Fa/kY8Npx9DKQBaZgC5+fsScugRLkIHcB/fJO/8QfQWUhdO8AoDaMD5KGsSCSFH5K6K4BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T09:56:32.209150Z","bundle_sha256":"df89fbfb56a9e319a39bf983d6b77e2fb6c68a7ae036926c05baa9f3d7b1a814"}}