{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:KTJ3WJ5WEJWDU5JKZPNTO54WOP","short_pith_number":"pith:KTJ3WJ5W","canonical_record":{"source":{"id":"1803.01384","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2018-03-04T17:08:45Z","cross_cats_sorted":[],"title_canon_sha256":"bc2be63d2b0094858cdd8f9ae8a1b45fe4a8fc27ea20cfa2368cd739a176ace1","abstract_canon_sha256":"906f46331be3fc18f45170df5f0895300738ec0c688e82677001295496c583b6"},"schema_version":"1.0"},"canonical_sha256":"54d3bb27b6226c3a752acbdb37779673ff5eb42a2d6ab1022a8bba16d487cafb","source":{"kind":"arxiv","id":"1803.01384","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.01384","created_at":"2026-05-17T23:50:38Z"},{"alias_kind":"arxiv_version","alias_value":"1803.01384v2","created_at":"2026-05-17T23:50:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.01384","created_at":"2026-05-17T23:50:38Z"},{"alias_kind":"pith_short_12","alias_value":"KTJ3WJ5WEJWD","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"KTJ3WJ5WEJWDU5JK","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"KTJ3WJ5W","created_at":"2026-05-18T12:32:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:KTJ3WJ5WEJWDU5JKZPNTO54WOP","target":"record","payload":{"canonical_record":{"source":{"id":"1803.01384","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2018-03-04T17:08:45Z","cross_cats_sorted":[],"title_canon_sha256":"bc2be63d2b0094858cdd8f9ae8a1b45fe4a8fc27ea20cfa2368cd739a176ace1","abstract_canon_sha256":"906f46331be3fc18f45170df5f0895300738ec0c688e82677001295496c583b6"},"schema_version":"1.0"},"canonical_sha256":"54d3bb27b6226c3a752acbdb37779673ff5eb42a2d6ab1022a8bba16d487cafb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:50:38.754385Z","signature_b64":"NRoHQY9XZ7/Cdpu0f7NVCP52B8PBPT6n3gD3nusYfDE1qSzp/5pj9IaZCohlRj0vhJKcu3SORaPvT3IpRdjbAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54d3bb27b6226c3a752acbdb37779673ff5eb42a2d6ab1022a8bba16d487cafb","last_reissued_at":"2026-05-17T23:50:38.753909Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:50:38.753909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.01384","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:50:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mn4W9ypm7cfVutqSC+fEG17GEjaPzUj2+uU4USBrjH0mU/G+Jdm4kcEyCsZIu+goLY/NUFuUJGafVZytIZlkAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T19:51:42.420445Z"},"content_sha256":"8dafbff355a63cff1b541c6e38f4c97378d140f870d762c84fc95aef675533db","schema_version":"1.0","event_id":"sha256:8dafbff355a63cff1b541c6e38f4c97378d140f870d762c84fc95aef675533db"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:KTJ3WJ5WEJWDU5JKZPNTO54WOP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data Curation with Deep Learning [Vision]","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"AnHai Doan, Mourad Ouzzani, Nan Tang, Saravanan Thirumuruganathan","submitted_at":"2018-03-04T17:08:45Z","abstract_excerpt":"Data curation - the process of discovering, integrating, and cleaning data - is one of the oldest, hardest, yet inevitable data management problems. Despite decades of efforts from both researchers and practitioners, it is still one of the most time consuming and least enjoyable work of data scientists. In most organizations, data curation plays an important role so as to fully unlock the value of big data. Unfortunately, the current solutions are not keeping up with the ever-changing data ecosystem, because they often require substantially high human cost. Meanwhile, deep learning is making s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.01384","kind":"arxiv","version":2},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:50:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cJpX9L70NDm8AWKA/ulIewDdDTcMoq02vpO7kQ3EhW4OXLdEpqWcswwbp9n8LrB9e+ryFZsXAI2Sur6QqX09DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T19:51:42.421018Z"},"content_sha256":"f1ba88b952e0cab10ac335140ea4bf2439aa23d850cc9c13acbcd568adccccad","schema_version":"1.0","event_id":"sha256:f1ba88b952e0cab10ac335140ea4bf2439aa23d850cc9c13acbcd568adccccad"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KTJ3WJ5WEJWDU5JKZPNTO54WOP/bundle.json","state_url":"https://pith.science/pith/KTJ3WJ5WEJWDU5JKZPNTO54WOP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KTJ3WJ5WEJWDU5JKZPNTO54WOP/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-27T19:51:42Z","links":{"resolver":"https://pith.science/pith/KTJ3WJ5WEJWDU5JKZPNTO54WOP","bundle":"https://pith.science/pith/KTJ3WJ5WEJWDU5JKZPNTO54WOP/bundle.json","state":"https://pith.science/pith/KTJ3WJ5WEJWDU5JKZPNTO54WOP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KTJ3WJ5WEJWDU5JKZPNTO54WOP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:KTJ3WJ5WEJWDU5JKZPNTO54WOP","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":"906f46331be3fc18f45170df5f0895300738ec0c688e82677001295496c583b6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2018-03-04T17:08:45Z","title_canon_sha256":"bc2be63d2b0094858cdd8f9ae8a1b45fe4a8fc27ea20cfa2368cd739a176ace1"},"schema_version":"1.0","source":{"id":"1803.01384","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.01384","created_at":"2026-05-17T23:50:38Z"},{"alias_kind":"arxiv_version","alias_value":"1803.01384v2","created_at":"2026-05-17T23:50:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.01384","created_at":"2026-05-17T23:50:38Z"},{"alias_kind":"pith_short_12","alias_value":"KTJ3WJ5WEJWD","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"KTJ3WJ5WEJWDU5JK","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"KTJ3WJ5W","created_at":"2026-05-18T12:32:33Z"}],"graph_snapshots":[{"event_id":"sha256:f1ba88b952e0cab10ac335140ea4bf2439aa23d850cc9c13acbcd568adccccad","target":"graph","created_at":"2026-05-17T23:50:38Z","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 curation - the process of discovering, integrating, and cleaning data - is one of the oldest, hardest, yet inevitable data management problems. Despite decades of efforts from both researchers and practitioners, it is still one of the most time consuming and least enjoyable work of data scientists. In most organizations, data curation plays an important role so as to fully unlock the value of big data. Unfortunately, the current solutions are not keeping up with the ever-changing data ecosystem, because they often require substantially high human cost. Meanwhile, deep learning is making s","authors_text":"AnHai Doan, Mourad Ouzzani, Nan Tang, Saravanan Thirumuruganathan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2018-03-04T17:08:45Z","title":"Data Curation with Deep Learning [Vision]"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.01384","kind":"arxiv","version":2},"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":"sha256:8dafbff355a63cff1b541c6e38f4c97378d140f870d762c84fc95aef675533db","target":"record","created_at":"2026-05-17T23:50:38Z","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":"906f46331be3fc18f45170df5f0895300738ec0c688e82677001295496c583b6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2018-03-04T17:08:45Z","title_canon_sha256":"bc2be63d2b0094858cdd8f9ae8a1b45fe4a8fc27ea20cfa2368cd739a176ace1"},"schema_version":"1.0","source":{"id":"1803.01384","kind":"arxiv","version":2}},"canonical_sha256":"54d3bb27b6226c3a752acbdb37779673ff5eb42a2d6ab1022a8bba16d487cafb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"54d3bb27b6226c3a752acbdb37779673ff5eb42a2d6ab1022a8bba16d487cafb","first_computed_at":"2026-05-17T23:50:38.753909Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:50:38.753909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NRoHQY9XZ7/Cdpu0f7NVCP52B8PBPT6n3gD3nusYfDE1qSzp/5pj9IaZCohlRj0vhJKcu3SORaPvT3IpRdjbAw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:50:38.754385Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.01384","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8dafbff355a63cff1b541c6e38f4c97378d140f870d762c84fc95aef675533db","sha256:f1ba88b952e0cab10ac335140ea4bf2439aa23d850cc9c13acbcd568adccccad"],"state_sha256":"2fe795df15d3ebf25d3b40ab27ffcd26559a2dc6f2fbda0b93e7667d3653c7f9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jyAQ5qBke8a0M0WFpuHoRav+ZGZBEsBcgyeBKAzA6oNhUrzyhIeehSD7m5GlgUUP4Fxo6r0NJMhKA+zzjJTsBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T19:51:42.424065Z","bundle_sha256":"8a79a159fcdc0e6b0d4fbaea470574eeb4604f8b172fab123ca8f9043c01a46d"}}