{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZSZB5PARFDOFWWLE54TLHT4432","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":"192b91dec1d46a7aa7df6c5b508523b56284a6091cbfe5c86ce24507657aeaed","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-24T14:55:19Z","title_canon_sha256":"744ca0099228b3a94fe680cc78658da5542d00d2c3b22c86cf7869e32010f917"},"schema_version":"1.0","source":{"id":"2607.22368","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.22368","created_at":"2026-07-27T01:21:16Z"},{"alias_kind":"arxiv_version","alias_value":"2607.22368v1","created_at":"2026-07-27T01:21:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22368","created_at":"2026-07-27T01:21:16Z"},{"alias_kind":"pith_short_12","alias_value":"ZSZB5PARFDOF","created_at":"2026-07-27T01:21:16Z"},{"alias_kind":"pith_short_16","alias_value":"ZSZB5PARFDOFWWLE","created_at":"2026-07-27T01:21:16Z"},{"alias_kind":"pith_short_8","alias_value":"ZSZB5PAR","created_at":"2026-07-27T01:21:16Z"}],"graph_snapshots":[{"event_id":"sha256:6e73a3e3714f23df4f76a8f16b1682d610feb35c83228cb4faa1a9eb1aae3a3b","target":"graph","created_at":"2026-07-27T01:21:16Z","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/2607.22368/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Agent benchmarks increasingly evaluate repository editing, web research, terminal use, and long-horizon interaction. Their scores support capability claims only when the evaluation protocol keeps the intended capability necessary for success. Recent reward-hacking benchmarks and system reports show that agents can instead recover public solutions, read evaluation artifacts, infer generator structure, manipulate feedback, or benefit from invalid scoring paths; existing responses do not provide a common procedure for attributing these shortcuts and quantifying their effect across benchmarks. We ","authors_text":"Bing Luo, Hanck Chen, Jiaqi Shao, Maxm Pan, Wei Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-24T14:55:19Z","title":"Do Agent Benchmarks Measure Capability? Protocol Validity in the Age of Agentic AI"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22368","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":"sha256:868f6ea9ee18da98a36fe779ade6e18ff773f19bb6458536242902dc763a6b1c","target":"record","created_at":"2026-07-27T01:21:16Z","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":"192b91dec1d46a7aa7df6c5b508523b56284a6091cbfe5c86ce24507657aeaed","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-24T14:55:19Z","title_canon_sha256":"744ca0099228b3a94fe680cc78658da5542d00d2c3b22c86cf7869e32010f917"},"schema_version":"1.0","source":{"id":"2607.22368","kind":"arxiv","version":1}},"canonical_sha256":"ccb21ebc1128dc5b5964ef26b3cf9cdead83f7312955a901fe1c18764c50bf97","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ccb21ebc1128dc5b5964ef26b3cf9cdead83f7312955a901fe1c18764c50bf97","first_computed_at":"2026-07-27T01:21:16.917794Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-27T01:21:16.917794Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ipFF61sHT3IuvFHC+LyUyAojy+oMc/gJd7k2wJaUFktml7+8w86Efakrb5MTTUZRoQyRqtVbIY+W7WeOIfgdAQ==","signature_status":"signed_v1","signed_at":"2026-07-27T01:21:16.918660Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.22368","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:868f6ea9ee18da98a36fe779ade6e18ff773f19bb6458536242902dc763a6b1c","sha256:6e73a3e3714f23df4f76a8f16b1682d610feb35c83228cb4faa1a9eb1aae3a3b"],"state_sha256":"4d100c9bd0feacb3ecf0ab00543b83d29f76bb02e2844e931f148a3b64d34301"}