{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JVM6B76ZTCDP7UTKRPVGCAKIGK","short_pith_number":"pith:JVM6B76Z","schema_version":"1.0","canonical_sha256":"4d59e0ffd99886ffd26a8bea61014832868e5bb4534fae2a5e3481ed5a88c41e","source":{"kind":"arxiv","id":"2504.04222","version":2},"attestation_state":"computed","paper":{"title":"TrafficLLM: Enhancing Large Language Models for Network Traffic Analysis with Generic Traffic Representation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Ke Xu, Miao Chen, Qilei Yin, Qi Li, Sijia Li, Tianyu Cui, Xinjie Lin","submitted_at":"2025-04-05T16:18:33Z","abstract_excerpt":"Machine learning (ML) powered network traffic analysis has been widely used for the purpose of threat detection. Unfortunately, their generalization across different tasks and unseen data is very limited. Large language models (LLMs), known for their strong generalization capabilities, have shown promising performance in various domains. However, their application to the traffic analysis domain is limited due to significantly different characteristics of network traffic. To address the issue, in this paper, we propose TrafficLLM, which introduces a dual-stage fine-tuning framework to learn gen"},"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":"2504.04222","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-05T16:18:33Z","cross_cats_sorted":["cs.AI","cs.CR"],"title_canon_sha256":"f4eb02e2636bd91c373780f0cc1de0ba4cd908fc320bed46c0f193f8f43d6a66","abstract_canon_sha256":"68e36020995018eb5db552b0f6237896510f5f160d37462cda57f4e420361f30"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:49:16.548096Z","signature_b64":"NnJRJB47C1ULRxHO3W5Y4vI6DssF6AZx9SJfYDT6VcGTLQbu7R6zZ2UalfJoO4Mkhx8C/wQ7xZcOyOkPf+aDBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d59e0ffd99886ffd26a8bea61014832868e5bb4534fae2a5e3481ed5a88c41e","last_reissued_at":"2026-07-05T10:49:16.547638Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:49:16.547638Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TrafficLLM: Enhancing Large Language Models for Network Traffic Analysis with Generic Traffic Representation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Ke Xu, Miao Chen, Qilei Yin, Qi Li, Sijia Li, Tianyu Cui, Xinjie Lin","submitted_at":"2025-04-05T16:18:33Z","abstract_excerpt":"Machine learning (ML) powered network traffic analysis has been widely used for the purpose of threat detection. Unfortunately, their generalization across different tasks and unseen data is very limited. Large language models (LLMs), known for their strong generalization capabilities, have shown promising performance in various domains. However, their application to the traffic analysis domain is limited due to significantly different characteristics of network traffic. To address the issue, in this paper, we propose TrafficLLM, which introduces a dual-stage fine-tuning framework to learn gen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.04222","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/2504.04222/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":"2504.04222","created_at":"2026-07-05T10:49:16.547696+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.04222v2","created_at":"2026-07-05T10:49:16.547696+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.04222","created_at":"2026-07-05T10:49:16.547696+00:00"},{"alias_kind":"pith_short_12","alias_value":"JVM6B76ZTCDP","created_at":"2026-07-05T10:49:16.547696+00:00"},{"alias_kind":"pith_short_16","alias_value":"JVM6B76ZTCDP7UTK","created_at":"2026-07-05T10:49:16.547696+00:00"},{"alias_kind":"pith_short_8","alias_value":"JVM6B76Z","created_at":"2026-07-05T10:49:16.547696+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.29941","citing_title":"TraceCodec: A Compiler-Backed Neural Codec for Stateful Multi-Flow Network Traffic Traces","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29425","citing_title":"ReasonLight: A Multimodal Foundation Model-Enhanced Reinforcement Learning Framework for Zero-Shot Traffic Signal Control","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08140","citing_title":"Multimodal Reasoning with LLM for Encrypted Traffic Interpretation: A Benchmark","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JVM6B76ZTCDP7UTKRPVGCAKIGK","json":"https://pith.science/pith/JVM6B76ZTCDP7UTKRPVGCAKIGK.json","graph_json":"https://pith.science/api/pith-number/JVM6B76ZTCDP7UTKRPVGCAKIGK/graph.json","events_json":"https://pith.science/api/pith-number/JVM6B76ZTCDP7UTKRPVGCAKIGK/events.json","paper":"https://pith.science/paper/JVM6B76Z"},"agent_actions":{"view_html":"https://pith.science/pith/JVM6B76ZTCDP7UTKRPVGCAKIGK","download_json":"https://pith.science/pith/JVM6B76ZTCDP7UTKRPVGCAKIGK.json","view_paper":"https://pith.science/paper/JVM6B76Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.04222&json=true","fetch_graph":"https://pith.science/api/pith-number/JVM6B76ZTCDP7UTKRPVGCAKIGK/graph.json","fetch_events":"https://pith.science/api/pith-number/JVM6B76ZTCDP7UTKRPVGCAKIGK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JVM6B76ZTCDP7UTKRPVGCAKIGK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JVM6B76ZTCDP7UTKRPVGCAKIGK/action/storage_attestation","attest_author":"https://pith.science/pith/JVM6B76ZTCDP7UTKRPVGCAKIGK/action/author_attestation","sign_citation":"https://pith.science/pith/JVM6B76ZTCDP7UTKRPVGCAKIGK/action/citation_signature","submit_replication":"https://pith.science/pith/JVM6B76ZTCDP7UTKRPVGCAKIGK/action/replication_record"}},"created_at":"2026-07-05T10:49:16.547696+00:00","updated_at":"2026-07-05T10:49:16.547696+00:00"}