{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZIMGEHK3GDF2Z263RHIXQYDRCD","short_pith_number":"pith:ZIMGEHK3","schema_version":"1.0","canonical_sha256":"ca18621d5b30cbacebdb89d178607110e1190302f58124e261bd893d7c3cbb18","source":{"kind":"arxiv","id":"2507.11071","version":1},"attestation_state":"computed","paper":{"title":"LogTinyLLM: Tiny Large Language Models Based Contextual Log Anomaly Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Isaiah Thompson Ocansey, Ritwik Bhattacharya, Tanmay Sen","submitted_at":"2025-07-15T08:04:31Z","abstract_excerpt":"Log anomaly detection using traditional rule based or deep learning based methods is often challenging due to the large volume and highly complex nature of log sequence. So effective way of detection of anomalous sequence of logs is crucial for system maintenance and development. This paper proposes parameter efficient finetuning specifically low rank adaptation (LoRA) and adapter based approaches for finding contextual anomalies in sequence of logs in large log data set. It compares different tiny large language models (LLMs) on the Thunderbird dataset. The results show that LoRA based finetu"},"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":"2507.11071","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-15T08:04:31Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"a26a26099528990e3e541b141b1b9299b5a0875f8039feedca1bd9927adbdba6","abstract_canon_sha256":"e3a328d2fa0159278e74b0b4096f3b199ecea40c8f88433e1affaa07339e84dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:37:31.458176Z","signature_b64":"gVxWKP0SC3CQvhYtXKBVfAGYbbqya0WNZQi7IFO11qAvbUMZ6o2IboZ7CDLaxh3f3nJOKpdDjmla0ZWtjwTbAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca18621d5b30cbacebdb89d178607110e1190302f58124e261bd893d7c3cbb18","last_reissued_at":"2026-07-05T11:37:31.457602Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:37:31.457602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LogTinyLLM: Tiny Large Language Models Based Contextual Log Anomaly Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Isaiah Thompson Ocansey, Ritwik Bhattacharya, Tanmay Sen","submitted_at":"2025-07-15T08:04:31Z","abstract_excerpt":"Log anomaly detection using traditional rule based or deep learning based methods is often challenging due to the large volume and highly complex nature of log sequence. So effective way of detection of anomalous sequence of logs is crucial for system maintenance and development. This paper proposes parameter efficient finetuning specifically low rank adaptation (LoRA) and adapter based approaches for finding contextual anomalies in sequence of logs in large log data set. It compares different tiny large language models (LLMs) on the Thunderbird dataset. The results show that LoRA based finetu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.11071","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/2507.11071/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":"2507.11071","created_at":"2026-07-05T11:37:31.457665+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.11071v1","created_at":"2026-07-05T11:37:31.457665+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.11071","created_at":"2026-07-05T11:37:31.457665+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZIMGEHK3GDF2","created_at":"2026-07-05T11:37:31.457665+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZIMGEHK3GDF2Z263","created_at":"2026-07-05T11:37:31.457665+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZIMGEHK3","created_at":"2026-07-05T11:37:31.457665+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.19118","citing_title":"DP-FlogTinyLLM: Differentially private federated log anomaly detection using Tiny LLMs","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZIMGEHK3GDF2Z263RHIXQYDRCD","json":"https://pith.science/pith/ZIMGEHK3GDF2Z263RHIXQYDRCD.json","graph_json":"https://pith.science/api/pith-number/ZIMGEHK3GDF2Z263RHIXQYDRCD/graph.json","events_json":"https://pith.science/api/pith-number/ZIMGEHK3GDF2Z263RHIXQYDRCD/events.json","paper":"https://pith.science/paper/ZIMGEHK3"},"agent_actions":{"view_html":"https://pith.science/pith/ZIMGEHK3GDF2Z263RHIXQYDRCD","download_json":"https://pith.science/pith/ZIMGEHK3GDF2Z263RHIXQYDRCD.json","view_paper":"https://pith.science/paper/ZIMGEHK3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.11071&json=true","fetch_graph":"https://pith.science/api/pith-number/ZIMGEHK3GDF2Z263RHIXQYDRCD/graph.json","fetch_events":"https://pith.science/api/pith-number/ZIMGEHK3GDF2Z263RHIXQYDRCD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZIMGEHK3GDF2Z263RHIXQYDRCD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZIMGEHK3GDF2Z263RHIXQYDRCD/action/storage_attestation","attest_author":"https://pith.science/pith/ZIMGEHK3GDF2Z263RHIXQYDRCD/action/author_attestation","sign_citation":"https://pith.science/pith/ZIMGEHK3GDF2Z263RHIXQYDRCD/action/citation_signature","submit_replication":"https://pith.science/pith/ZIMGEHK3GDF2Z263RHIXQYDRCD/action/replication_record"}},"created_at":"2026-07-05T11:37:31.457665+00:00","updated_at":"2026-07-05T11:37:31.457665+00:00"}