{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:G3V4EOWJHHSYNX5M6JEF6MAEOT","short_pith_number":"pith:G3V4EOWJ","canonical_record":{"source":{"id":"2411.01791","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2024-11-04T04:26:16Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d26d9dc871ff446ec89dd2b596457675dc693bbc137020fe02b33ef56317f444","abstract_canon_sha256":"cb8f8342b30c5ad6218534ab33352722a2a8949baa981814893b76f3c528c804"},"schema_version":"1.0"},"canonical_sha256":"36ebc23ac939e586dfacf2485f300474dae17c961cd259c52116c4dfc49a1e62","source":{"kind":"arxiv","id":"2411.01791","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.01791","created_at":"2026-07-05T10:54:13Z"},{"alias_kind":"arxiv_version","alias_value":"2411.01791v2","created_at":"2026-07-05T10:54:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.01791","created_at":"2026-07-05T10:54:13Z"},{"alias_kind":"pith_short_12","alias_value":"G3V4EOWJHHSY","created_at":"2026-07-05T10:54:13Z"},{"alias_kind":"pith_short_16","alias_value":"G3V4EOWJHHSYNX5M","created_at":"2026-07-05T10:54:13Z"},{"alias_kind":"pith_short_8","alias_value":"G3V4EOWJ","created_at":"2026-07-05T10:54:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:G3V4EOWJHHSYNX5M6JEF6MAEOT","target":"record","payload":{"canonical_record":{"source":{"id":"2411.01791","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2024-11-04T04:26:16Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d26d9dc871ff446ec89dd2b596457675dc693bbc137020fe02b33ef56317f444","abstract_canon_sha256":"cb8f8342b30c5ad6218534ab33352722a2a8949baa981814893b76f3c528c804"},"schema_version":"1.0"},"canonical_sha256":"36ebc23ac939e586dfacf2485f300474dae17c961cd259c52116c4dfc49a1e62","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:54:13.831347Z","signature_b64":"+ksy5spMo7cAscqaC0azxiOT+pStgyRc4mnSW/AWqoYUbznq6knKsZa5chCpimPezeqZF7fNJmW3pHizZpjvCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36ebc23ac939e586dfacf2485f300474dae17c961cd259c52116c4dfc49a1e62","last_reissued_at":"2026-07-05T10:54:13.830739Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:54:13.830739Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.01791","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:54:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D/6OgG4qcEHkgbDV+f9pYjNfTD8mDXiJDok406wDwpHpDtPMjCNM3yKSMsUgKhaFeD9Myh4+UV721MxBUuQ9Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T14:55:06.467915Z"},"content_sha256":"edec5a39c87b6bd7fadfe6ed5576249160c90e7db112e17730472d8f1b38cf8e","schema_version":"1.0","event_id":"sha256:edec5a39c87b6bd7fadfe6ed5576249160c90e7db112e17730472d8f1b38cf8e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:G3V4EOWJHHSYNX5M6JEF6MAEOT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Minder: Faulty Machine Detection for Large-scale Distributed Model Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DC","authors_text":"Bo Li, Fuliang Li, Gaohong Liu, Haibin Lin, Hang Zhu, Jianxi Ye, Lei Zhang, Minlan Yu, Shuguang Wang, Xiang Shi, Xingjian Zhang, Yangtao Deng, Zhang Zhang, Zhuo Jiang, Zuquan Song","submitted_at":"2024-11-04T04:26:16Z","abstract_excerpt":"Large-scale distributed model training requires simultaneous training on up to thousands of machines. Faulty machine detection is critical when an unexpected fault occurs in a machine. From our experience, a training task can encounter two faults per day on average, possibly leading to a halt for hours. To address the drawbacks of the time-consuming and labor-intensive manual scrutiny, we propose Minder, an automatic faulty machine detector for distributed training tasks. The key idea of Minder is to automatically and efficiently detect faulty distinctive monitoring metric patterns, which coul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.01791","kind":"arxiv","version":2},"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/2411.01791/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":"2026-07-05T10:54:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nf19hhZ47cziOAYX96BF8E1k2IrnwopAZRxey9NYKSEp6Q3kcvmiCgQAUeseySN4+PRO2AnU3+ACQVwsv7loBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T14:55:06.468448Z"},"content_sha256":"23a148449ed581bd75f526f89201e3f39b86c7dbf2aa04eedf29c33b59b76061","schema_version":"1.0","event_id":"sha256:23a148449ed581bd75f526f89201e3f39b86c7dbf2aa04eedf29c33b59b76061"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G3V4EOWJHHSYNX5M6JEF6MAEOT/bundle.json","state_url":"https://pith.science/pith/G3V4EOWJHHSYNX5M6JEF6MAEOT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G3V4EOWJHHSYNX5M6JEF6MAEOT/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":"2026-08-04T14:55:06Z","links":{"resolver":"https://pith.science/pith/G3V4EOWJHHSYNX5M6JEF6MAEOT","bundle":"https://pith.science/pith/G3V4EOWJHHSYNX5M6JEF6MAEOT/bundle.json","state":"https://pith.science/pith/G3V4EOWJHHSYNX5M6JEF6MAEOT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G3V4EOWJHHSYNX5M6JEF6MAEOT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:G3V4EOWJHHSYNX5M6JEF6MAEOT","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":"cb8f8342b30c5ad6218534ab33352722a2a8949baa981814893b76f3c528c804","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2024-11-04T04:26:16Z","title_canon_sha256":"d26d9dc871ff446ec89dd2b596457675dc693bbc137020fe02b33ef56317f444"},"schema_version":"1.0","source":{"id":"2411.01791","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.01791","created_at":"2026-07-05T10:54:13Z"},{"alias_kind":"arxiv_version","alias_value":"2411.01791v2","created_at":"2026-07-05T10:54:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.01791","created_at":"2026-07-05T10:54:13Z"},{"alias_kind":"pith_short_12","alias_value":"G3V4EOWJHHSY","created_at":"2026-07-05T10:54:13Z"},{"alias_kind":"pith_short_16","alias_value":"G3V4EOWJHHSYNX5M","created_at":"2026-07-05T10:54:13Z"},{"alias_kind":"pith_short_8","alias_value":"G3V4EOWJ","created_at":"2026-07-05T10:54:13Z"}],"graph_snapshots":[{"event_id":"sha256:23a148449ed581bd75f526f89201e3f39b86c7dbf2aa04eedf29c33b59b76061","target":"graph","created_at":"2026-07-05T10:54:13Z","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/2411.01791/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large-scale distributed model training requires simultaneous training on up to thousands of machines. Faulty machine detection is critical when an unexpected fault occurs in a machine. From our experience, a training task can encounter two faults per day on average, possibly leading to a halt for hours. To address the drawbacks of the time-consuming and labor-intensive manual scrutiny, we propose Minder, an automatic faulty machine detector for distributed training tasks. The key idea of Minder is to automatically and efficiently detect faulty distinctive monitoring metric patterns, which coul","authors_text":"Bo Li, Fuliang Li, Gaohong Liu, Haibin Lin, Hang Zhu, Jianxi Ye, Lei Zhang, Minlan Yu, Shuguang Wang, Xiang Shi, Xingjian Zhang, Yangtao Deng, Zhang Zhang, Zhuo Jiang, Zuquan Song","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2024-11-04T04:26:16Z","title":"Minder: Faulty Machine Detection for Large-scale Distributed Model Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.01791","kind":"arxiv","version":2},"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:edec5a39c87b6bd7fadfe6ed5576249160c90e7db112e17730472d8f1b38cf8e","target":"record","created_at":"2026-07-05T10:54:13Z","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":"cb8f8342b30c5ad6218534ab33352722a2a8949baa981814893b76f3c528c804","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2024-11-04T04:26:16Z","title_canon_sha256":"d26d9dc871ff446ec89dd2b596457675dc693bbc137020fe02b33ef56317f444"},"schema_version":"1.0","source":{"id":"2411.01791","kind":"arxiv","version":2}},"canonical_sha256":"36ebc23ac939e586dfacf2485f300474dae17c961cd259c52116c4dfc49a1e62","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"36ebc23ac939e586dfacf2485f300474dae17c961cd259c52116c4dfc49a1e62","first_computed_at":"2026-07-05T10:54:13.830739Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:54:13.830739Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+ksy5spMo7cAscqaC0azxiOT+pStgyRc4mnSW/AWqoYUbznq6knKsZa5chCpimPezeqZF7fNJmW3pHizZpjvCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:54:13.831347Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.01791","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:edec5a39c87b6bd7fadfe6ed5576249160c90e7db112e17730472d8f1b38cf8e","sha256:23a148449ed581bd75f526f89201e3f39b86c7dbf2aa04eedf29c33b59b76061"],"state_sha256":"eb0c70675000d9cfc4ac3740c45227f812cc1b49341a2b9c65d7276edfbd30ae"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"isKBrDg7gMMbiVugv5qgJIMaqdl/wXX3j4F1V5H08R7AHapoI8If1t+1iIOmxPU48/6uQY+gW4WO0wtm/FlnAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T14:55:06.473305Z","bundle_sha256":"abaccc485aa343040926666213c04ad62d268167ce1dbd09d755a869acac1175"}}