{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:65Z2O6G37JX43SE4BREHIQUIJH","short_pith_number":"pith:65Z2O6G3","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"},"canonical_sha256":"f773a778dbfa6fcdc89c0c4874428849f6a9bf7a231bc2647c60ed3f33cfe58b","source":{"kind":"arxiv","id":"2607.09996","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:65Z2O6G37JX43SE4BREHIQUIJH","target":"record","payload":{"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"},"canonical_sha256":"f773a778dbfa6fcdc89c0c4874428849f6a9bf7a231bc2647c60ed3f33cfe58b","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"},"source_kind":"arxiv","source_id":"2607.09996","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":"2026-07-14T00:18:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zwDV3cKAJndjdujwQgZGgBZnj5Ey6w7h9WyJHrEF6k1P75lIaDqyI/W4upt+y7P10FEMKbPT9iWE20Dtq30rAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:52:18.596734Z"},"content_sha256":"f604fd43c87c8f2628876281d4ec1d3537748940851788f706ccce4bf9873e0b","schema_version":"1.0","event_id":"sha256:f604fd43c87c8f2628876281d4ec1d3537748940851788f706ccce4bf9873e0b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:65Z2O6G37JX43SE4BREHIQUIJH","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-14T00:18:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IzrDwzZhx731IMLKZSfrRot65a1Rkz9rm+BjecbHDuBM1K2Knhre27NmTkpHltqsLfUWWmVuCXM0iEE9dycFAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:52:18.597246Z"},"content_sha256":"864e459e0765c77758cadf0cadef3709a422eb5ae2b0558290f57088a2c118b1","schema_version":"1.0","event_id":"sha256:864e459e0765c77758cadf0cadef3709a422eb5ae2b0558290f57088a2c118b1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/65Z2O6G37JX43SE4BREHIQUIJH/bundle.json","state_url":"https://pith.science/pith/65Z2O6G37JX43SE4BREHIQUIJH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/65Z2O6G37JX43SE4BREHIQUIJH/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":"2026-08-04T21:52:18Z","links":{"resolver":"https://pith.science/pith/65Z2O6G37JX43SE4BREHIQUIJH","bundle":"https://pith.science/pith/65Z2O6G37JX43SE4BREHIQUIJH/bundle.json","state":"https://pith.science/pith/65Z2O6G37JX43SE4BREHIQUIJH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/65Z2O6G37JX43SE4BREHIQUIJH/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wSmvs0AGl0pFMuPYE8iBaqEPxVOXUr8NhXVq/jZ2bP7ZU31mtl0wgxYiMyYegTx/NXigTY3uUlYpHk/J/5fuDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T21:52:18.623252Z","bundle_sha256":"70ae6252a7112b4c19e28b603649e63c8c705e5b7a67d312aa2811fe7ba8cbbe"}}