{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FU6KBTTDLSKZWDUVREIC6ZKNG7","short_pith_number":"pith:FU6KBTTD","schema_version":"1.0","canonical_sha256":"2d3ca0ce635c959b0e9589102f654d37db071068c572c93ce160b6abb128b847","source":{"kind":"arxiv","id":"2608.07346","version":1},"attestation_state":"computed","paper":{"title":"An End-to-End Agent Auditing Engine","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chenyue Yu, Guanchu Wang, Haoning Wang, Mingxun Zhang, Na Zou, Xia Hu, Yingjun Shang","submitted_at":"2026-08-07T15:44:12Z","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"},"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":"2608.07346","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-07T15:44:12Z","cross_cats_sorted":[],"title_canon_sha256":"f1b53b7ef0ae7269231d4981ead38c104fa0fafd7c15314ab0a764252e57996b","abstract_canon_sha256":"2dc7ee65973ba6cd8a5853eff4b7bead12c2dfdcf6b5daee02e62ecdff626a5f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-10T01:15:06.397846Z","signature_b64":"IIarfzlZFPHhIzvMgG+Acw6LSCRgVsgc5U55pR0M30olA6a4dYAid5dtr4YXQ3ukXP3cpafHNHiO78NkUhoGAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d3ca0ce635c959b0e9589102f654d37db071068c572c93ce160b6abb128b847","last_reissued_at":"2026-08-10T01:15:06.395282Z","signature_status":"signed_v1","first_computed_at":"2026-08-10T01:15:06.395282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An End-to-End Agent Auditing Engine","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chenyue Yu, Guanchu Wang, Haoning Wang, Mingxun Zhang, Na Zou, Xia Hu, Yingjun Shang","submitted_at":"2026-08-07T15:44:12Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.07346","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/2608.07346/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":"2608.07346","created_at":"2026-08-10T01:15:06.396434+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.07346v1","created_at":"2026-08-10T01:15:06.396434+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.07346","created_at":"2026-08-10T01:15:06.396434+00:00"},{"alias_kind":"pith_short_12","alias_value":"FU6KBTTDLSKZ","created_at":"2026-08-10T01:15:06.396434+00:00"},{"alias_kind":"pith_short_16","alias_value":"FU6KBTTDLSKZWDUV","created_at":"2026-08-10T01:15:06.396434+00:00"},{"alias_kind":"pith_short_8","alias_value":"FU6KBTTD","created_at":"2026-08-10T01:15:06.396434+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/FU6KBTTDLSKZWDUVREIC6ZKNG7","json":"https://pith.science/pith/FU6KBTTDLSKZWDUVREIC6ZKNG7.json","graph_json":"https://pith.science/api/pith-number/FU6KBTTDLSKZWDUVREIC6ZKNG7/graph.json","events_json":"https://pith.science/api/pith-number/FU6KBTTDLSKZWDUVREIC6ZKNG7/events.json","paper":"https://pith.science/paper/FU6KBTTD"},"agent_actions":{"view_html":"https://pith.science/pith/FU6KBTTDLSKZWDUVREIC6ZKNG7","download_json":"https://pith.science/pith/FU6KBTTDLSKZWDUVREIC6ZKNG7.json","view_paper":"https://pith.science/paper/FU6KBTTD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.07346&json=true","fetch_graph":"https://pith.science/api/pith-number/FU6KBTTDLSKZWDUVREIC6ZKNG7/graph.json","fetch_events":"https://pith.science/api/pith-number/FU6KBTTDLSKZWDUVREIC6ZKNG7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FU6KBTTDLSKZWDUVREIC6ZKNG7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FU6KBTTDLSKZWDUVREIC6ZKNG7/action/storage_attestation","attest_author":"https://pith.science/pith/FU6KBTTDLSKZWDUVREIC6ZKNG7/action/author_attestation","sign_citation":"https://pith.science/pith/FU6KBTTDLSKZWDUVREIC6ZKNG7/action/citation_signature","submit_replication":"https://pith.science/pith/FU6KBTTDLSKZWDUVREIC6ZKNG7/action/replication_record"}},"created_at":"2026-08-10T01:15:06.396434+00:00","updated_at":"2026-08-10T01:15:06.396434+00:00"}