{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BAB6Z3SJYYSOY3FOX33QG3N5SM","short_pith_number":"pith:BAB6Z3SJ","schema_version":"1.0","canonical_sha256":"0803ecee49c624ec6caebef7036dbd93327bace44a8063f5429a26bc7414319c","source":{"kind":"arxiv","id":"2508.18554","version":1},"attestation_state":"computed","paper":{"title":"SchemaCoder: Automatic Log Schema Extraction Coder with Residual Q-Tree Boosting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chia-Tung Ho, Cunxi Yu, Deming Chen, Haoxing Ren, Lily Jiaxin Wan, Rongjian Liang","submitted_at":"2025-08-25T23:12:45Z","abstract_excerpt":"Log schema extraction is the process of deriving human-readable templates from massive volumes of log data, which is essential yet notoriously labor-intensive. Recent studies have attempted to streamline this task by leveraging Large Language Models (LLMs) for automated schema extraction. However, existing methods invariably rely on predefined regular expressions, necessitating human domain expertise and severely limiting productivity gains. To fundamentally address this limitation, we introduce SchemaCoder, the first fully automated schema extraction framework applicable to a wide range of lo"},"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":"2508.18554","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-25T23:12:45Z","cross_cats_sorted":[],"title_canon_sha256":"e7c06479b513b7b678931bcc988edcf6a6fef2750367f5c0eac9d59f7cd9aa1c","abstract_canon_sha256":"a1dde703c1fe7001dfe2f887ca30feb744735f1076291a6cae2fe9a9984ddf30"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:59:26.601623Z","signature_b64":"ZC1l+0bssKt0ce3ixLrcnJQmCLubiihrgigWJQNbhL/3EZjrVNLnwaFzaNS/anzkkgcz0pH/1mC/eXQHLBhbDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0803ecee49c624ec6caebef7036dbd93327bace44a8063f5429a26bc7414319c","last_reissued_at":"2026-07-05T11:59:26.601158Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:59:26.601158Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SchemaCoder: Automatic Log Schema Extraction Coder with Residual Q-Tree Boosting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chia-Tung Ho, Cunxi Yu, Deming Chen, Haoxing Ren, Lily Jiaxin Wan, Rongjian Liang","submitted_at":"2025-08-25T23:12:45Z","abstract_excerpt":"Log schema extraction is the process of deriving human-readable templates from massive volumes of log data, which is essential yet notoriously labor-intensive. Recent studies have attempted to streamline this task by leveraging Large Language Models (LLMs) for automated schema extraction. However, existing methods invariably rely on predefined regular expressions, necessitating human domain expertise and severely limiting productivity gains. To fundamentally address this limitation, we introduce SchemaCoder, the first fully automated schema extraction framework applicable to a wide range of lo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.18554","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/2508.18554/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":"2508.18554","created_at":"2026-07-05T11:59:26.601216+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.18554v1","created_at":"2026-07-05T11:59:26.601216+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.18554","created_at":"2026-07-05T11:59:26.601216+00:00"},{"alias_kind":"pith_short_12","alias_value":"BAB6Z3SJYYSO","created_at":"2026-07-05T11:59:26.601216+00:00"},{"alias_kind":"pith_short_16","alias_value":"BAB6Z3SJYYSOY3FO","created_at":"2026-07-05T11:59:26.601216+00:00"},{"alias_kind":"pith_short_8","alias_value":"BAB6Z3SJ","created_at":"2026-07-05T11:59:26.601216+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.03245","citing_title":"FVRuleLearner: Operator-Level Reasoning Tree (Op-Tree)-Based Rules Learning for Formal Verification","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BAB6Z3SJYYSOY3FOX33QG3N5SM","json":"https://pith.science/pith/BAB6Z3SJYYSOY3FOX33QG3N5SM.json","graph_json":"https://pith.science/api/pith-number/BAB6Z3SJYYSOY3FOX33QG3N5SM/graph.json","events_json":"https://pith.science/api/pith-number/BAB6Z3SJYYSOY3FOX33QG3N5SM/events.json","paper":"https://pith.science/paper/BAB6Z3SJ"},"agent_actions":{"view_html":"https://pith.science/pith/BAB6Z3SJYYSOY3FOX33QG3N5SM","download_json":"https://pith.science/pith/BAB6Z3SJYYSOY3FOX33QG3N5SM.json","view_paper":"https://pith.science/paper/BAB6Z3SJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.18554&json=true","fetch_graph":"https://pith.science/api/pith-number/BAB6Z3SJYYSOY3FOX33QG3N5SM/graph.json","fetch_events":"https://pith.science/api/pith-number/BAB6Z3SJYYSOY3FOX33QG3N5SM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BAB6Z3SJYYSOY3FOX33QG3N5SM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BAB6Z3SJYYSOY3FOX33QG3N5SM/action/storage_attestation","attest_author":"https://pith.science/pith/BAB6Z3SJYYSOY3FOX33QG3N5SM/action/author_attestation","sign_citation":"https://pith.science/pith/BAB6Z3SJYYSOY3FOX33QG3N5SM/action/citation_signature","submit_replication":"https://pith.science/pith/BAB6Z3SJYYSOY3FOX33QG3N5SM/action/replication_record"}},"created_at":"2026-07-05T11:59:26.601216+00:00","updated_at":"2026-07-05T11:59:26.601216+00:00"}