{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:JBT5GKE4E6I42A54L5XPHEJZQ5","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":"684b456cb283aa4ff503d3c9bc6b653c0fb80ddfadb343a552e051a9b9b041b0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2019-05-10T09:46:01Z","title_canon_sha256":"09e6834e4a16224fe28563c38f830b5e86b0d32f0edb628c4cc732e347e8b513"},"schema_version":"1.0","source":{"id":"1905.04037","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.04037","created_at":"2026-05-17T23:46:34Z"},{"alias_kind":"arxiv_version","alias_value":"1905.04037v1","created_at":"2026-05-17T23:46:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.04037","created_at":"2026-05-17T23:46:34Z"},{"alias_kind":"pith_short_12","alias_value":"JBT5GKE4E6I4","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"JBT5GKE4E6I42A54","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"JBT5GKE4","created_at":"2026-05-18T12:33:18Z"}],"graph_snapshots":[{"event_id":"sha256:8f10bded915f7364f4e47f5670e6c0a474451bc58f78655c63cf9e6770289b8d","target":"graph","created_at":"2026-05-17T23:46:34Z","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":"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, ","authors_text":"J\\'er\\^ome Darmont (ERIC), Pegdwend\\'e Sawadogo (ERIC), Tokio Kibata","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2019-05-10T09:46:01Z","title":"Metadata Management for Textual Documents in Data Lakes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.04037","kind":"arxiv","version":1},"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":"sha256:22210e58dda2ae49861cef4d19091e044dd22803f0ba7adff097dcd2c8b8f73f","target":"record","created_at":"2026-05-17T23:46:34Z","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":"684b456cb283aa4ff503d3c9bc6b653c0fb80ddfadb343a552e051a9b9b041b0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2019-05-10T09:46:01Z","title_canon_sha256":"09e6834e4a16224fe28563c38f830b5e86b0d32f0edb628c4cc732e347e8b513"},"schema_version":"1.0","source":{"id":"1905.04037","kind":"arxiv","version":1}},"canonical_sha256":"4867d3289c2791cd03bc5f6ef39139875da493c7b26ef80ac266e47a4ae5cbc1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4867d3289c2791cd03bc5f6ef39139875da493c7b26ef80ac266e47a4ae5cbc1","first_computed_at":"2026-05-17T23:46:34.773569Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:46:34.773569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"x4A1TgoGfM1DUBUbDZyZzpIt36/prMioOkxUa1enNTZUYb/4sGNwm1Vjk/RCtaiyVvtoHFrrjRjOp8oFUCVdCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:46:34.774280Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.04037","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:22210e58dda2ae49861cef4d19091e044dd22803f0ba7adff097dcd2c8b8f73f","sha256:8f10bded915f7364f4e47f5670e6c0a474451bc58f78655c63cf9e6770289b8d"],"state_sha256":"35c9bc9ed545087bdd0f7bb9ea5e5de42daae1c3afb13ede4804a3107c564cc5"}