{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:JBT5GKE4E6I42A54L5XPHEJZQ5","short_pith_number":"pith:JBT5GKE4","schema_version":"1.0","canonical_sha256":"4867d3289c2791cd03bc5f6ef39139875da493c7b26ef80ac266e47a4ae5cbc1","source":{"kind":"arxiv","id":"1905.04037","version":1},"attestation_state":"computed","paper":{"title":"Metadata Management for Textual Documents in Data Lakes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"J\\'er\\^ome Darmont (ERIC), Pegdwend\\'e Sawadogo (ERIC), Tokio Kibata","submitted_at":"2019-05-10T09:46:01Z","abstract_excerpt":"Data lakes have emerged as an alternative to data warehouses for the storage, exploration and analysis of big data. In a data lake, data are stored in a raw state and bear no explicit schema. Thence, an efficient metadata system is essential to avoid the data lake turning to a so-called data swamp. Existing works about managing data lake metadata mostly focus on structured and semi-structured data, with little research on unstructured data. Thus, we propose in this paper a methodological approach to build and manage a metadata system that is specific to textual documents in data lakes. First, "},"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":"1905.04037","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2019-05-10T09:46:01Z","cross_cats_sorted":[],"title_canon_sha256":"09e6834e4a16224fe28563c38f830b5e86b0d32f0edb628c4cc732e347e8b513","abstract_canon_sha256":"684b456cb283aa4ff503d3c9bc6b653c0fb80ddfadb343a552e051a9b9b041b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:34.774280Z","signature_b64":"x4A1TgoGfM1DUBUbDZyZzpIt36/prMioOkxUa1enNTZUYb/4sGNwm1Vjk/RCtaiyVvtoHFrrjRjOp8oFUCVdCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4867d3289c2791cd03bc5f6ef39139875da493c7b26ef80ac266e47a4ae5cbc1","last_reissued_at":"2026-05-17T23:46:34.773569Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:34.773569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Metadata Management for Textual Documents in Data Lakes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"J\\'er\\^ome Darmont (ERIC), Pegdwend\\'e Sawadogo (ERIC), Tokio Kibata","submitted_at":"2019-05-10T09:46:01Z","abstract_excerpt":"Data lakes have emerged as an alternative to data warehouses for the storage, exploration and analysis of big data. In a data lake, data are stored in a raw state and bear no explicit schema. Thence, an efficient metadata system is essential to avoid the data lake turning to a so-called data swamp. Existing works about managing data lake metadata mostly focus on structured and semi-structured data, with little research on unstructured data. Thus, we propose in this paper a methodological approach to build and manage a metadata system that is specific to textual documents in data lakes. First, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.04037","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":""},"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":"1905.04037","created_at":"2026-05-17T23:46:34.773686+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.04037v1","created_at":"2026-05-17T23:46:34.773686+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.04037","created_at":"2026-05-17T23:46:34.773686+00:00"},{"alias_kind":"pith_short_12","alias_value":"JBT5GKE4E6I4","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"JBT5GKE4E6I42A54","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"JBT5GKE4","created_at":"2026-05-18T12:33:18.533446+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/JBT5GKE4E6I42A54L5XPHEJZQ5","json":"https://pith.science/pith/JBT5GKE4E6I42A54L5XPHEJZQ5.json","graph_json":"https://pith.science/api/pith-number/JBT5GKE4E6I42A54L5XPHEJZQ5/graph.json","events_json":"https://pith.science/api/pith-number/JBT5GKE4E6I42A54L5XPHEJZQ5/events.json","paper":"https://pith.science/paper/JBT5GKE4"},"agent_actions":{"view_html":"https://pith.science/pith/JBT5GKE4E6I42A54L5XPHEJZQ5","download_json":"https://pith.science/pith/JBT5GKE4E6I42A54L5XPHEJZQ5.json","view_paper":"https://pith.science/paper/JBT5GKE4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.04037&json=true","fetch_graph":"https://pith.science/api/pith-number/JBT5GKE4E6I42A54L5XPHEJZQ5/graph.json","fetch_events":"https://pith.science/api/pith-number/JBT5GKE4E6I42A54L5XPHEJZQ5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JBT5GKE4E6I42A54L5XPHEJZQ5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JBT5GKE4E6I42A54L5XPHEJZQ5/action/storage_attestation","attest_author":"https://pith.science/pith/JBT5GKE4E6I42A54L5XPHEJZQ5/action/author_attestation","sign_citation":"https://pith.science/pith/JBT5GKE4E6I42A54L5XPHEJZQ5/action/citation_signature","submit_replication":"https://pith.science/pith/JBT5GKE4E6I42A54L5XPHEJZQ5/action/replication_record"}},"created_at":"2026-05-17T23:46:34.773686+00:00","updated_at":"2026-05-17T23:46:34.773686+00:00"}