{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DLLN3PK3HJ3VO2EQ3PXT2YEYM7","short_pith_number":"pith:DLLN3PK3","schema_version":"1.0","canonical_sha256":"1ad6ddbd5b3a77576890dbef3d609867cb701a7f95b11c1044446e3985a0dc93","source":{"kind":"arxiv","id":"2412.01377","version":2},"attestation_state":"computed","paper":{"title":"Adapting Large Language Models to Log Analysis with Interpretable Domain Knowledge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.CL","authors_text":"Boxing Chen, Feiyu Yao, Minggui He, Shenglin Zhang, Shimin Tao, Su Chang, Weibin Meng, Xiaofeng Zhao, Xinhua Yang, Yilun Liu, Yongqian Sun, Yuhe Ji, Yuming Xie","submitted_at":"2024-12-02T11:05:31Z","abstract_excerpt":"Log analysis represents a critical sub-domain within AI applications that facilitates automatic approaches to fault and error management of large-scaled software systems, saving labors of traditional manual methods. While existing solutions using large language models (LLMs) show promise, they are limited by a significant domain gap between natural and log languages (the latter contains rich domain-specific tokens such as status codes, IP addresses, resource pathes), which restricts their effectiveness in real-world applications. However, directly adapting general-purpose LLMs to log analysis "},"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":"2412.01377","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-02T11:05:31Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"d4910c94a8fa18aeb3addec29e4f6c941c4e5cbc7bff005e4e5bc34e30f8332e","abstract_canon_sha256":"b1904c44b215784b2a8bf05eeaa4ece1fda411a92c4f7187c12f245ba8c677c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:59:09.470384Z","signature_b64":"zJO2nuajxd3mNiQkZor3eymMsdZX1yjHOH3NpYKGI2APxECE3EfTD39Gw3C3SWFCLXnq10+tcAI4s6d8zKP5CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ad6ddbd5b3a77576890dbef3d609867cb701a7f95b11c1044446e3985a0dc93","last_reissued_at":"2026-07-05T11:59:09.469900Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:59:09.469900Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adapting Large Language Models to Log Analysis with Interpretable Domain Knowledge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.CL","authors_text":"Boxing Chen, Feiyu Yao, Minggui He, Shenglin Zhang, Shimin Tao, Su Chang, Weibin Meng, Xiaofeng Zhao, Xinhua Yang, Yilun Liu, Yongqian Sun, Yuhe Ji, Yuming Xie","submitted_at":"2024-12-02T11:05:31Z","abstract_excerpt":"Log analysis represents a critical sub-domain within AI applications that facilitates automatic approaches to fault and error management of large-scaled software systems, saving labors of traditional manual methods. While existing solutions using large language models (LLMs) show promise, they are limited by a significant domain gap between natural and log languages (the latter contains rich domain-specific tokens such as status codes, IP addresses, resource pathes), which restricts their effectiveness in real-world applications. However, directly adapting general-purpose LLMs to log analysis "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01377","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/2412.01377/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":"2412.01377","created_at":"2026-07-05T11:59:09.469955+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.01377v2","created_at":"2026-07-05T11:59:09.469955+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01377","created_at":"2026-07-05T11:59:09.469955+00:00"},{"alias_kind":"pith_short_12","alias_value":"DLLN3PK3HJ3V","created_at":"2026-07-05T11:59:09.469955+00:00"},{"alias_kind":"pith_short_16","alias_value":"DLLN3PK3HJ3VO2EQ","created_at":"2026-07-05T11:59:09.469955+00:00"},{"alias_kind":"pith_short_8","alias_value":"DLLN3PK3","created_at":"2026-07-05T11:59:09.469955+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/DLLN3PK3HJ3VO2EQ3PXT2YEYM7","json":"https://pith.science/pith/DLLN3PK3HJ3VO2EQ3PXT2YEYM7.json","graph_json":"https://pith.science/api/pith-number/DLLN3PK3HJ3VO2EQ3PXT2YEYM7/graph.json","events_json":"https://pith.science/api/pith-number/DLLN3PK3HJ3VO2EQ3PXT2YEYM7/events.json","paper":"https://pith.science/paper/DLLN3PK3"},"agent_actions":{"view_html":"https://pith.science/pith/DLLN3PK3HJ3VO2EQ3PXT2YEYM7","download_json":"https://pith.science/pith/DLLN3PK3HJ3VO2EQ3PXT2YEYM7.json","view_paper":"https://pith.science/paper/DLLN3PK3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.01377&json=true","fetch_graph":"https://pith.science/api/pith-number/DLLN3PK3HJ3VO2EQ3PXT2YEYM7/graph.json","fetch_events":"https://pith.science/api/pith-number/DLLN3PK3HJ3VO2EQ3PXT2YEYM7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DLLN3PK3HJ3VO2EQ3PXT2YEYM7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DLLN3PK3HJ3VO2EQ3PXT2YEYM7/action/storage_attestation","attest_author":"https://pith.science/pith/DLLN3PK3HJ3VO2EQ3PXT2YEYM7/action/author_attestation","sign_citation":"https://pith.science/pith/DLLN3PK3HJ3VO2EQ3PXT2YEYM7/action/citation_signature","submit_replication":"https://pith.science/pith/DLLN3PK3HJ3VO2EQ3PXT2YEYM7/action/replication_record"}},"created_at":"2026-07-05T11:59:09.469955+00:00","updated_at":"2026-07-05T11:59:09.469955+00:00"}