{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GRJEIFO4KPQN6QL2TAIVO2XNEK","short_pith_number":"pith:GRJEIFO4","schema_version":"1.0","canonical_sha256":"34524415dc53e0df417a9811576aed22a0c3cddccab177a1551d770dd398e294","source":{"kind":"arxiv","id":"2608.01975","version":1},"attestation_state":"computed","paper":{"title":"TELLER: Non-intrusive Cross-Layer Root-Cause Analysis for LLM Inference","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.PF"],"primary_cat":"cs.SE","authors_text":"Junyi Li, Pengfei Chen, Ruilin Xu, Zongxuan Xie","submitted_at":"2026-08-03T09:39:11Z","abstract_excerpt":"Large language model (LLM) inference has evolved from an offline workload into a continuously operated software service, yet root-cause analysis remains difficult because a single request spans the inference engine, Python/C++ backend, host CUDA APIs, GPU kernels, and distributed communication. Existing profilers expose raw timelines, while log-based diagnosis often misses cross-layer execution semantics and request-level structure. We present TELLER, a non-intrusive Trace- and Log-aware LLM inference Root-cause analysis framework. TELLER first collects NVTX/CUPTI traces and service logs witho"},"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":"2608.01975","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2026-08-03T09:39:11Z","cross_cats_sorted":["cs.CL","cs.LG","cs.PF"],"title_canon_sha256":"ab2bf1e593d89fea9c71e6150a867386ed9b29db9ff8543250172946fceb250d","abstract_canon_sha256":"b776cc5a8b16b8d55efec0f1572b84cdbb5556a55b9091d23c09b989d71835a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:10:25.356940Z","signature_b64":"hEVVcGcf+J1SpB5W4lxBQh7GCihOvbc6QBNpsVETQTHyZsD8ElnV2qdvsk4plLjL57v83+N06MIFtt/nXXKQBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34524415dc53e0df417a9811576aed22a0c3cddccab177a1551d770dd398e294","last_reissued_at":"2026-08-04T02:10:25.355071Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:10:25.355071Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TELLER: Non-intrusive Cross-Layer Root-Cause Analysis for LLM Inference","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.PF"],"primary_cat":"cs.SE","authors_text":"Junyi Li, Pengfei Chen, Ruilin Xu, Zongxuan Xie","submitted_at":"2026-08-03T09:39:11Z","abstract_excerpt":"Large language model (LLM) inference has evolved from an offline workload into a continuously operated software service, yet root-cause analysis remains difficult because a single request spans the inference engine, Python/C++ backend, host CUDA APIs, GPU kernels, and distributed communication. Existing profilers expose raw timelines, while log-based diagnosis often misses cross-layer execution semantics and request-level structure. We present TELLER, a non-intrusive Trace- and Log-aware LLM inference Root-cause analysis framework. TELLER first collects NVTX/CUPTI traces and service logs witho"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01975","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/2608.01975/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":"2608.01975","created_at":"2026-08-04T02:10:25.356915+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.01975v1","created_at":"2026-08-04T02:10:25.356915+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01975","created_at":"2026-08-04T02:10:25.356915+00:00"},{"alias_kind":"pith_short_12","alias_value":"GRJEIFO4KPQN","created_at":"2026-08-04T02:10:25.356915+00:00"},{"alias_kind":"pith_short_16","alias_value":"GRJEIFO4KPQN6QL2","created_at":"2026-08-04T02:10:25.356915+00:00"},{"alias_kind":"pith_short_8","alias_value":"GRJEIFO4","created_at":"2026-08-04T02:10:25.356915+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/GRJEIFO4KPQN6QL2TAIVO2XNEK","json":"https://pith.science/pith/GRJEIFO4KPQN6QL2TAIVO2XNEK.json","graph_json":"https://pith.science/api/pith-number/GRJEIFO4KPQN6QL2TAIVO2XNEK/graph.json","events_json":"https://pith.science/api/pith-number/GRJEIFO4KPQN6QL2TAIVO2XNEK/events.json","paper":"https://pith.science/paper/GRJEIFO4"},"agent_actions":{"view_html":"https://pith.science/pith/GRJEIFO4KPQN6QL2TAIVO2XNEK","download_json":"https://pith.science/pith/GRJEIFO4KPQN6QL2TAIVO2XNEK.json","view_paper":"https://pith.science/paper/GRJEIFO4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.01975&json=true","fetch_graph":"https://pith.science/api/pith-number/GRJEIFO4KPQN6QL2TAIVO2XNEK/graph.json","fetch_events":"https://pith.science/api/pith-number/GRJEIFO4KPQN6QL2TAIVO2XNEK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GRJEIFO4KPQN6QL2TAIVO2XNEK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GRJEIFO4KPQN6QL2TAIVO2XNEK/action/storage_attestation","attest_author":"https://pith.science/pith/GRJEIFO4KPQN6QL2TAIVO2XNEK/action/author_attestation","sign_citation":"https://pith.science/pith/GRJEIFO4KPQN6QL2TAIVO2XNEK/action/citation_signature","submit_replication":"https://pith.science/pith/GRJEIFO4KPQN6QL2TAIVO2XNEK/action/replication_record"}},"created_at":"2026-08-04T02:10:25.356915+00:00","updated_at":"2026-08-04T02:10:25.356915+00:00"}