{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:C7EGMW2YV7N3YUWVZXAXKIMKST","short_pith_number":"pith:C7EGMW2Y","schema_version":"1.0","canonical_sha256":"17c8665b58afdbbc52d5cdc175218a94d032290a2c3f768cc26ac09a403a30e6","source":{"kind":"arxiv","id":"1708.08905","version":3},"attestation_state":"computed","paper":{"title":"Navigating the Data Lake with Datamaran: Automatically Extracting Structure from Log Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Aditya Parameswaran, Silu Huang, Yihan Gao","submitted_at":"2017-08-29T17:47:08Z","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"},"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":"1708.08905","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-08-29T17:47:08Z","cross_cats_sorted":[],"title_canon_sha256":"60628991708842859c3325d0fd2256ae8048f3c4d9a91dee629b345c33787b55","abstract_canon_sha256":"3343b26fb2987e4c0d5b7d02868f02c13a025f0ecebe8b1895416ecba01b9e87"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:20.788916Z","signature_b64":"Co9gBN/qaWSApXFHGcp+tYmIBEhpdbWgTptnm1RpfEroDboGd7rVOI9p+LEmzLdJhhlyiZCilfdzTEVrJO7HBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17c8665b58afdbbc52d5cdc175218a94d032290a2c3f768cc26ac09a403a30e6","last_reissued_at":"2026-05-18T00:22:20.788504Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:20.788504Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Navigating the Data Lake with Datamaran: Automatically Extracting Structure from Log Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Aditya Parameswaran, Silu Huang, Yihan Gao","submitted_at":"2017-08-29T17:47:08Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.08905","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1708.08905","created_at":"2026-05-18T00:22:20.788563+00:00"},{"alias_kind":"arxiv_version","alias_value":"1708.08905v3","created_at":"2026-05-18T00:22:20.788563+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.08905","created_at":"2026-05-18T00:22:20.788563+00:00"},{"alias_kind":"pith_short_12","alias_value":"C7EGMW2YV7N3","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_16","alias_value":"C7EGMW2YV7N3YUWV","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_8","alias_value":"C7EGMW2Y","created_at":"2026-05-18T12:31:10.602751+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/C7EGMW2YV7N3YUWVZXAXKIMKST","json":"https://pith.science/pith/C7EGMW2YV7N3YUWVZXAXKIMKST.json","graph_json":"https://pith.science/api/pith-number/C7EGMW2YV7N3YUWVZXAXKIMKST/graph.json","events_json":"https://pith.science/api/pith-number/C7EGMW2YV7N3YUWVZXAXKIMKST/events.json","paper":"https://pith.science/paper/C7EGMW2Y"},"agent_actions":{"view_html":"https://pith.science/pith/C7EGMW2YV7N3YUWVZXAXKIMKST","download_json":"https://pith.science/pith/C7EGMW2YV7N3YUWVZXAXKIMKST.json","view_paper":"https://pith.science/paper/C7EGMW2Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1708.08905&json=true","fetch_graph":"https://pith.science/api/pith-number/C7EGMW2YV7N3YUWVZXAXKIMKST/graph.json","fetch_events":"https://pith.science/api/pith-number/C7EGMW2YV7N3YUWVZXAXKIMKST/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C7EGMW2YV7N3YUWVZXAXKIMKST/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C7EGMW2YV7N3YUWVZXAXKIMKST/action/storage_attestation","attest_author":"https://pith.science/pith/C7EGMW2YV7N3YUWVZXAXKIMKST/action/author_attestation","sign_citation":"https://pith.science/pith/C7EGMW2YV7N3YUWVZXAXKIMKST/action/citation_signature","submit_replication":"https://pith.science/pith/C7EGMW2YV7N3YUWVZXAXKIMKST/action/replication_record"}},"created_at":"2026-05-18T00:22:20.788563+00:00","updated_at":"2026-05-18T00:22:20.788563+00:00"}