{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:C7EGMW2YV7N3YUWVZXAXKIMKST","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"3343b26fb2987e4c0d5b7d02868f02c13a025f0ecebe8b1895416ecba01b9e87","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-08-29T17:47:08Z","title_canon_sha256":"60628991708842859c3325d0fd2256ae8048f3c4d9a91dee629b345c33787b55"},"schema_version":"1.0","source":{"id":"1708.08905","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.08905","created_at":"2026-05-18T00:22:20Z"},{"alias_kind":"arxiv_version","alias_value":"1708.08905v3","created_at":"2026-05-18T00:22:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.08905","created_at":"2026-05-18T00:22:20Z"},{"alias_kind":"pith_short_12","alias_value":"C7EGMW2YV7N3","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_16","alias_value":"C7EGMW2YV7N3YUWV","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_8","alias_value":"C7EGMW2Y","created_at":"2026-05-18T12:31:10Z"}],"graph_snapshots":[{"event_id":"sha256:3352a00e3f2c6b3606b71da4d30b5045f4fdc29341ca2072a18192c9aad122df","target":"graph","created_at":"2026-05-18T00:22:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Organizations routinely accumulate semi-structured log datasets generated as the output of code; these datasets remain unused and uninterpreted, and occupy wasted space - this phenomenon has been colloquially referred to as \"data lake\" problem. One approach to leverage these semi-structured datasets is to convert them into a structured relational format, following which they can be analyzed in conjunction with other datasets. We present Datamaran, an tool that extracts structure from semi-structured log datasets with no human supervision. Datamaran automatically identifies field and record end","authors_text":"Aditya Parameswaran, Silu Huang, Yihan Gao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-08-29T17:47:08Z","title":"Navigating the Data Lake with Datamaran: Automatically Extracting Structure from Log Datasets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.08905","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3f7e1ac8f825c0ea351af9ae31686dbb8057062c012f77588ef1daeaf2efef5a","target":"record","created_at":"2026-05-18T00:22:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"3343b26fb2987e4c0d5b7d02868f02c13a025f0ecebe8b1895416ecba01b9e87","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-08-29T17:47:08Z","title_canon_sha256":"60628991708842859c3325d0fd2256ae8048f3c4d9a91dee629b345c33787b55"},"schema_version":"1.0","source":{"id":"1708.08905","kind":"arxiv","version":3}},"canonical_sha256":"17c8665b58afdbbc52d5cdc175218a94d032290a2c3f768cc26ac09a403a30e6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"17c8665b58afdbbc52d5cdc175218a94d032290a2c3f768cc26ac09a403a30e6","first_computed_at":"2026-05-18T00:22:20.788504Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:22:20.788504Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Co9gBN/qaWSApXFHGcp+tYmIBEhpdbWgTptnm1RpfEroDboGd7rVOI9p+LEmzLdJhhlyiZCilfdzTEVrJO7HBw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:22:20.788916Z","signed_message":"canonical_sha256_bytes"},"source_id":"1708.08905","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3f7e1ac8f825c0ea351af9ae31686dbb8057062c012f77588ef1daeaf2efef5a","sha256:3352a00e3f2c6b3606b71da4d30b5045f4fdc29341ca2072a18192c9aad122df"],"state_sha256":"a00dce0060b649c61a6f41c1494ee0bc4ae324e186b1377a674968dd753c9267"}