{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CKURW5MTH34HXSHAEBCYOMUAQ4","short_pith_number":"pith:CKURW5MT","schema_version":"1.0","canonical_sha256":"12a91b75933ef87bc8e02045873280871606cef04e4183900003014ddc4961dd","source":{"kind":"arxiv","id":"2506.01147","version":1},"attestation_state":"computed","paper":{"title":"A Word is Worth 4-bit: Efficient Log Parsing with Binary Coded Decimal Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Giulio Corallo, Prerak Srivastava, Sergey Rybalko","submitted_at":"2025-06-01T20:00:00Z","abstract_excerpt":"System-generated logs are typically converted into categorical log templates through parsing. These templates are crucial for generating actionable insights in various downstream tasks. However, existing parsers often fail to capture fine-grained template details, leading to suboptimal accuracy and reduced utility in downstream tasks requiring precise pattern identification. We propose a character-level log parser utilizing a novel neural architecture that aggregates character embeddings. Our approach estimates a sequence of binary-coded decimals to achieve highly granular log templates extrac"},"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":"2506.01147","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-01T20:00:00Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e82fa0bded3da2f9b54041a1979276d2b84a90436a2ce44ee854aa56d89e71e7","abstract_canon_sha256":"8a5ee77485d8b9b26d9cd2147ad2c32611f7233cafee9467ff0c61107382e832"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:47.268591Z","signature_b64":"oBb2mSgnJsCbW8EfAQLugY3ovIpFtutauVFiewNi/vRcEGK4IDLtFtHqqaiR8e8bihVJZVAoV5ebvZTTGVoLBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12a91b75933ef87bc8e02045873280871606cef04e4183900003014ddc4961dd","last_reissued_at":"2026-07-05T11:13:47.268035Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:47.268035Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Word is Worth 4-bit: Efficient Log Parsing with Binary Coded Decimal Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Giulio Corallo, Prerak Srivastava, Sergey Rybalko","submitted_at":"2025-06-01T20:00:00Z","abstract_excerpt":"System-generated logs are typically converted into categorical log templates through parsing. These templates are crucial for generating actionable insights in various downstream tasks. However, existing parsers often fail to capture fine-grained template details, leading to suboptimal accuracy and reduced utility in downstream tasks requiring precise pattern identification. We propose a character-level log parser utilizing a novel neural architecture that aggregates character embeddings. Our approach estimates a sequence of binary-coded decimals to achieve highly granular log templates extrac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01147","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/2506.01147/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":"2506.01147","created_at":"2026-07-05T11:13:47.268104+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01147v1","created_at":"2026-07-05T11:13:47.268104+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01147","created_at":"2026-07-05T11:13:47.268104+00:00"},{"alias_kind":"pith_short_12","alias_value":"CKURW5MTH34H","created_at":"2026-07-05T11:13:47.268104+00:00"},{"alias_kind":"pith_short_16","alias_value":"CKURW5MTH34HXSHA","created_at":"2026-07-05T11:13:47.268104+00:00"},{"alias_kind":"pith_short_8","alias_value":"CKURW5MT","created_at":"2026-07-05T11:13:47.268104+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/CKURW5MTH34HXSHAEBCYOMUAQ4","json":"https://pith.science/pith/CKURW5MTH34HXSHAEBCYOMUAQ4.json","graph_json":"https://pith.science/api/pith-number/CKURW5MTH34HXSHAEBCYOMUAQ4/graph.json","events_json":"https://pith.science/api/pith-number/CKURW5MTH34HXSHAEBCYOMUAQ4/events.json","paper":"https://pith.science/paper/CKURW5MT"},"agent_actions":{"view_html":"https://pith.science/pith/CKURW5MTH34HXSHAEBCYOMUAQ4","download_json":"https://pith.science/pith/CKURW5MTH34HXSHAEBCYOMUAQ4.json","view_paper":"https://pith.science/paper/CKURW5MT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01147&json=true","fetch_graph":"https://pith.science/api/pith-number/CKURW5MTH34HXSHAEBCYOMUAQ4/graph.json","fetch_events":"https://pith.science/api/pith-number/CKURW5MTH34HXSHAEBCYOMUAQ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CKURW5MTH34HXSHAEBCYOMUAQ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CKURW5MTH34HXSHAEBCYOMUAQ4/action/storage_attestation","attest_author":"https://pith.science/pith/CKURW5MTH34HXSHAEBCYOMUAQ4/action/author_attestation","sign_citation":"https://pith.science/pith/CKURW5MTH34HXSHAEBCYOMUAQ4/action/citation_signature","submit_replication":"https://pith.science/pith/CKURW5MTH34HXSHAEBCYOMUAQ4/action/replication_record"}},"created_at":"2026-07-05T11:13:47.268104+00:00","updated_at":"2026-07-05T11:13:47.268104+00:00"}