{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FU6KBTTDLSKZWDUVREIC6ZKNG7","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":"2dc7ee65973ba6cd8a5853eff4b7bead12c2dfdcf6b5daee02e62ecdff626a5f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-07T15:44:12Z","title_canon_sha256":"f1b53b7ef0ae7269231d4981ead38c104fa0fafd7c15314ab0a764252e57996b"},"schema_version":"1.0","source":{"id":"2608.07346","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.07346","created_at":"2026-08-10T01:15:06Z"},{"alias_kind":"arxiv_version","alias_value":"2608.07346v1","created_at":"2026-08-10T01:15:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.07346","created_at":"2026-08-10T01:15:06Z"},{"alias_kind":"pith_short_12","alias_value":"FU6KBTTDLSKZ","created_at":"2026-08-10T01:15:06Z"},{"alias_kind":"pith_short_16","alias_value":"FU6KBTTDLSKZWDUV","created_at":"2026-08-10T01:15:06Z"},{"alias_kind":"pith_short_8","alias_value":"FU6KBTTD","created_at":"2026-08-10T01:15:06Z"}],"graph_snapshots":[{"event_id":"sha256:d15fcb0e5da6a4d5ffe06da332b34fb8da9827bda2c2a765612a1bf93eea2e4a","target":"graph","created_at":"2026-08-10T01:15:06Z","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/2608.07346/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the rapid advancement of large language models (LLMs), harnesses have become essential infrastructure for deploying agents across a wide range of domains. The fast-evolving harness ecosystem has also made rigorous capability evaluation increasingly important. However, efficiently building an end-to-end, systematic, and comprehensive evaluation pipeline remains a significant challenge. To address this challenge, we introduce $A^2E$ (Agent Auditing Engine), an end-to-end evaluation engine designed for agent harnesses. $A^2E$ leverages our newly proposed Agent Task Protocol (ATP) to enable t","authors_text":"Chenyue Yu, Guanchu Wang, Haoning Wang, Mingxun Zhang, Na Zou, Xia Hu, Yingjun Shang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-07T15:44:12Z","title":"An End-to-End Agent Auditing Engine"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.07346","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":"sha256:3b01cf0901b40655c2a40d90646141aebb73927e383c31c6495ec4ef829b8ee5","target":"record","created_at":"2026-08-10T01:15:06Z","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":"2dc7ee65973ba6cd8a5853eff4b7bead12c2dfdcf6b5daee02e62ecdff626a5f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-07T15:44:12Z","title_canon_sha256":"f1b53b7ef0ae7269231d4981ead38c104fa0fafd7c15314ab0a764252e57996b"},"schema_version":"1.0","source":{"id":"2608.07346","kind":"arxiv","version":1}},"canonical_sha256":"2d3ca0ce635c959b0e9589102f654d37db071068c572c93ce160b6abb128b847","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2d3ca0ce635c959b0e9589102f654d37db071068c572c93ce160b6abb128b847","first_computed_at":"2026-08-10T01:15:06.395282Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-10T01:15:06.395282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IIarfzlZFPHhIzvMgG+Acw6LSCRgVsgc5U55pR0M30olA6a4dYAid5dtr4YXQ3ukXP3cpafHNHiO78NkUhoGAw==","signature_status":"signed_v1","signed_at":"2026-08-10T01:15:06.397846Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.07346","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3b01cf0901b40655c2a40d90646141aebb73927e383c31c6495ec4ef829b8ee5","sha256:d15fcb0e5da6a4d5ffe06da332b34fb8da9827bda2c2a765612a1bf93eea2e4a"],"state_sha256":"5d4bb308b9e032ed3580f00f31a85f438d43bceda845de3f2a3611fc197f3928"}