{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:FU6KBTTDLSKZWDUVREIC6ZKNG7","short_pith_number":"pith:FU6KBTTD","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"},"canonical_sha256":"2d3ca0ce635c959b0e9589102f654d37db071068c572c93ce160b6abb128b847","source":{"kind":"arxiv","id":"2608.07346","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:FU6KBTTDLSKZWDUVREIC6ZKNG7","target":"record","payload":{"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"},"canonical_sha256":"2d3ca0ce635c959b0e9589102f654d37db071068c572c93ce160b6abb128b847","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"},"source_kind":"arxiv","source_id":"2608.07346","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":"2026-08-10T01:15:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hj8KdI8UujwlmfEFU4mTNMqqbvXByYqX3rno0bWNEau0J9A+yruCuWMLtBOKy1Ae7Q2+/EAFzVapOF61u98wCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T01:29:40.762611Z"},"content_sha256":"3b01cf0901b40655c2a40d90646141aebb73927e383c31c6495ec4ef829b8ee5","schema_version":"1.0","event_id":"sha256:3b01cf0901b40655c2a40d90646141aebb73927e383c31c6495ec4ef829b8ee5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:FU6KBTTDLSKZWDUVREIC6ZKNG7","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-10T01:15:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gk4rfea2X/sfEloDhjjhJu0LnNzVZjCha3+RlktmeRJSA5iwvwJMg6SQe/UHLU/NcVv/HxpXg6FTyozlIor0AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T01:29:40.763096Z"},"content_sha256":"d15fcb0e5da6a4d5ffe06da332b34fb8da9827bda2c2a765612a1bf93eea2e4a","schema_version":"1.0","event_id":"sha256:d15fcb0e5da6a4d5ffe06da332b34fb8da9827bda2c2a765612a1bf93eea2e4a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FU6KBTTDLSKZWDUVREIC6ZKNG7/bundle.json","state_url":"https://pith.science/pith/FU6KBTTDLSKZWDUVREIC6ZKNG7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FU6KBTTDLSKZWDUVREIC6ZKNG7/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":"2026-08-11T01:29:40Z","links":{"resolver":"https://pith.science/pith/FU6KBTTDLSKZWDUVREIC6ZKNG7","bundle":"https://pith.science/pith/FU6KBTTDLSKZWDUVREIC6ZKNG7/bundle.json","state":"https://pith.science/pith/FU6KBTTDLSKZWDUVREIC6ZKNG7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FU6KBTTDLSKZWDUVREIC6ZKNG7/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hursIM0/pbJXrOqZ4ilK0fQPFZ/7Z44PcQYL1cvm2VOUhfw0xzIYM4OSDD3K76E+50YdKTrOZRnHwS3PhkJhAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T01:29:40.766845Z","bundle_sha256":"d765729dd743abeed617a8f01f27a19173a7fcb9bf41a13fb490c73a34d62495"}}