{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:65Z2O6G37JX43SE4BREHIQUIJH","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":"90a777b33f95eec7a54e63d9b19a04484f237b0a3958687ca2e64ce91d534b47","cross_cats_sorted":["cs.MA"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-10T21:45:16Z","title_canon_sha256":"e261932a7c1458e2e8706113804326d496124ca5d7a180fbb5392aa30ccfb709"},"schema_version":"1.0","source":{"id":"2607.09996","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.09996","created_at":"2026-07-14T00:18:46Z"},{"alias_kind":"arxiv_version","alias_value":"2607.09996v1","created_at":"2026-07-14T00:18:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.09996","created_at":"2026-07-14T00:18:46Z"},{"alias_kind":"pith_short_12","alias_value":"65Z2O6G37JX4","created_at":"2026-07-14T00:18:46Z"},{"alias_kind":"pith_short_16","alias_value":"65Z2O6G37JX43SE4","created_at":"2026-07-14T00:18:46Z"},{"alias_kind":"pith_short_8","alias_value":"65Z2O6G3","created_at":"2026-07-14T00:18:46Z"}],"graph_snapshots":[{"event_id":"sha256:864e459e0765c77758cadf0cadef3709a422eb5ae2b0558290f57088a2c118b1","target":"graph","created_at":"2026-07-14T00:18:46Z","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/2607.09996/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automated failure attribution uses LLMs to identify where and why agentic systems fail. As agents become more capable, their failures become subtler, making automated attribution increasingly important. We introduce Who&When Pro, a large-scale benchmark for automated failure attribution in agentic systems. Using a strictly controlled pipeline that injects a failure only after exactly replaying a successful prefix, we construct 12,326 failed trajectories with golden labels across 3 modalities and 26 benchmarks covering various scenarios. Beyond benchmarking, we conduct extensive experiments and","authors_text":"Chi Wang, HuaJun Xi, Huazheng Wang, Jiale Liu, Jian Kang, Qingyun Wu, Shaokun Zhang, Tianwei Yue, Yifan Zeng","cross_cats":["cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-10T21:45:16Z","title":"Who&When Pro: Can LLMs Really Attribute Failures in AI Agents?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.09996","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:f604fd43c87c8f2628876281d4ec1d3537748940851788f706ccce4bf9873e0b","target":"record","created_at":"2026-07-14T00:18:46Z","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":"90a777b33f95eec7a54e63d9b19a04484f237b0a3958687ca2e64ce91d534b47","cross_cats_sorted":["cs.MA"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-10T21:45:16Z","title_canon_sha256":"e261932a7c1458e2e8706113804326d496124ca5d7a180fbb5392aa30ccfb709"},"schema_version":"1.0","source":{"id":"2607.09996","kind":"arxiv","version":1}},"canonical_sha256":"f773a778dbfa6fcdc89c0c4874428849f6a9bf7a231bc2647c60ed3f33cfe58b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f773a778dbfa6fcdc89c0c4874428849f6a9bf7a231bc2647c60ed3f33cfe58b","first_computed_at":"2026-07-14T00:18:46.765455Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-14T00:18:46.765455Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ILQogkt40zuVD1M6y8h2RUZ3lyZy2LKuemyfTXVme22kOFeXvnrVkxNAzKHHY3uqMjt5rcZt5MWdN+uIZLxpDA==","signature_status":"signed_v1","signed_at":"2026-07-14T00:18:46.766326Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.09996","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f604fd43c87c8f2628876281d4ec1d3537748940851788f706ccce4bf9873e0b","sha256:864e459e0765c77758cadf0cadef3709a422eb5ae2b0558290f57088a2c118b1"],"state_sha256":"d3eed6d2c49d8fc5b936880f61a95a747e0e5c634a53093a3b2c44adcbe69fb5"}