{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Q6FISYDFGNVK6IY6PD6734ML7S","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":"700d79e39514e979414e24b60edac1c8d7472ac6628964f363524069bb4b24e2","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-09-03T04:49:20Z","title_canon_sha256":"028ddfd9db9040ec09fff389382314de149c70c7f13204909908a35e3225dbab"},"schema_version":"1.0","source":{"id":"2509.03018","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.03018","created_at":"2026-07-05T12:04:02Z"},{"alias_kind":"arxiv_version","alias_value":"2509.03018v1","created_at":"2026-07-05T12:04:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.03018","created_at":"2026-07-05T12:04:02Z"},{"alias_kind":"pith_short_12","alias_value":"Q6FISYDFGNVK","created_at":"2026-07-05T12:04:02Z"},{"alias_kind":"pith_short_16","alias_value":"Q6FISYDFGNVK6IY6","created_at":"2026-07-05T12:04:02Z"},{"alias_kind":"pith_short_8","alias_value":"Q6FISYDF","created_at":"2026-07-05T12:04:02Z"}],"graph_snapshots":[{"event_id":"sha256:8ab015842bda22b6b0215f9077015fc081eb6b603348becfa7bbc95a05d4035f","target":"graph","created_at":"2026-07-05T12:04:02Z","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/2509.03018/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reliability is essential for ensuring efficiency in LLM training. However, many real-world reliability issues remain difficult to resolve, resulting in wasted resources and degraded model performance. Unfortunately, today's collective communication libraries operate as black boxes, hiding critical information needed for effective root cause analysis. We propose Mycroft, a lightweight distributed tracing and root cause analysis system designed to address previously hidden reliability issues in collective communication. Mycroft's key idea is to trace collective communication states and leverage ","authors_text":"Gaohong Liu, Haohan Xu, Hong Xu, Jianxi Ye, Lei Wang, Lei Zhang, Minlan Yu, Qinlong Wang, Shuguang Wang, Wencong Xiao, Xiaoyun Zhi, Xinlei Zhang, Yang Bai, Yangtao Deng, Zhuo Jiang, Zuquan Song","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-09-03T04:49:20Z","title":"Mycroft: Tracing Dependencies in Collective Communication Towards Reliable LLM Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.03018","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:d889947163d6272788fac480e4d3aaef4abe9a6c7e83c1d08238366ae4b87e17","target":"record","created_at":"2026-07-05T12:04:02Z","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":"700d79e39514e979414e24b60edac1c8d7472ac6628964f363524069bb4b24e2","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-09-03T04:49:20Z","title_canon_sha256":"028ddfd9db9040ec09fff389382314de149c70c7f13204909908a35e3225dbab"},"schema_version":"1.0","source":{"id":"2509.03018","kind":"arxiv","version":1}},"canonical_sha256":"878a896065336aaf231e78fdfdf18bfcb65fd3932f16713a68c0b79644c1501e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"878a896065336aaf231e78fdfdf18bfcb65fd3932f16713a68c0b79644c1501e","first_computed_at":"2026-07-05T12:04:02.017930Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:04:02.017930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bVVCa2hRq/Bqiwv5EhXcRZKc8w0nKUWJ2SCVWVBznhqEC2RnW1IWOw6px+dn11Mb4azPlzW+jiW8ajPjwbdYCA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:04:02.018511Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.03018","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d889947163d6272788fac480e4d3aaef4abe9a6c7e83c1d08238366ae4b87e17","sha256:8ab015842bda22b6b0215f9077015fc081eb6b603348becfa7bbc95a05d4035f"],"state_sha256":"dd1242835478f3baee9e9d7e8f72adac3555181e89238d877c6f3193000b89bf"}