{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:65Z2O6G37JX43SE4BREHIQUIJH","short_pith_number":"pith:65Z2O6G3","schema_version":"1.0","canonical_sha256":"f773a778dbfa6fcdc89c0c4874428849f6a9bf7a231bc2647c60ed3f33cfe58b","source":{"kind":"arxiv","id":"2607.09996","version":1},"attestation_state":"computed","paper":{"title":"Who&When Pro: Can LLMs Really Attribute Failures in AI Agents?","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.AI","authors_text":"Chi Wang, HuaJun Xi, Huazheng Wang, Jiale Liu, Jian Kang, Qingyun Wu, Shaokun Zhang, Tianwei Yue, Yifan Zeng","submitted_at":"2026-07-10T21:45:16Z","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"},"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":"2607.09996","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-10T21:45:16Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"e261932a7c1458e2e8706113804326d496124ca5d7a180fbb5392aa30ccfb709","abstract_canon_sha256":"90a777b33f95eec7a54e63d9b19a04484f237b0a3958687ca2e64ce91d534b47"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T00:18:46.766326Z","signature_b64":"ILQogkt40zuVD1M6y8h2RUZ3lyZy2LKuemyfTXVme22kOFeXvnrVkxNAzKHHY3uqMjt5rcZt5MWdN+uIZLxpDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f773a778dbfa6fcdc89c0c4874428849f6a9bf7a231bc2647c60ed3f33cfe58b","last_reissued_at":"2026-07-14T00:18:46.765455Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T00:18:46.765455Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Who&When Pro: Can LLMs Really Attribute Failures in AI Agents?","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.AI","authors_text":"Chi Wang, HuaJun Xi, Huazheng Wang, Jiale Liu, Jian Kang, Qingyun Wu, Shaokun Zhang, Tianwei Yue, Yifan Zeng","submitted_at":"2026-07-10T21:45:16Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.09996","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/2607.09996/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":"2607.09996","created_at":"2026-07-14T00:18:46.765909+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.09996v1","created_at":"2026-07-14T00:18:46.765909+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.09996","created_at":"2026-07-14T00:18:46.765909+00:00"},{"alias_kind":"pith_short_12","alias_value":"65Z2O6G37JX4","created_at":"2026-07-14T00:18:46.765909+00:00"},{"alias_kind":"pith_short_16","alias_value":"65Z2O6G37JX43SE4","created_at":"2026-07-14T00:18:46.765909+00:00"},{"alias_kind":"pith_short_8","alias_value":"65Z2O6G3","created_at":"2026-07-14T00:18:46.765909+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/65Z2O6G37JX43SE4BREHIQUIJH","json":"https://pith.science/pith/65Z2O6G37JX43SE4BREHIQUIJH.json","graph_json":"https://pith.science/api/pith-number/65Z2O6G37JX43SE4BREHIQUIJH/graph.json","events_json":"https://pith.science/api/pith-number/65Z2O6G37JX43SE4BREHIQUIJH/events.json","paper":"https://pith.science/paper/65Z2O6G3"},"agent_actions":{"view_html":"https://pith.science/pith/65Z2O6G37JX43SE4BREHIQUIJH","download_json":"https://pith.science/pith/65Z2O6G37JX43SE4BREHIQUIJH.json","view_paper":"https://pith.science/paper/65Z2O6G3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.09996&json=true","fetch_graph":"https://pith.science/api/pith-number/65Z2O6G37JX43SE4BREHIQUIJH/graph.json","fetch_events":"https://pith.science/api/pith-number/65Z2O6G37JX43SE4BREHIQUIJH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/65Z2O6G37JX43SE4BREHIQUIJH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/65Z2O6G37JX43SE4BREHIQUIJH/action/storage_attestation","attest_author":"https://pith.science/pith/65Z2O6G37JX43SE4BREHIQUIJH/action/author_attestation","sign_citation":"https://pith.science/pith/65Z2O6G37JX43SE4BREHIQUIJH/action/citation_signature","submit_replication":"https://pith.science/pith/65Z2O6G37JX43SE4BREHIQUIJH/action/replication_record"}},"created_at":"2026-07-14T00:18:46.765909+00:00","updated_at":"2026-07-14T00:18:46.765909+00:00"}