{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:E7GCENMDO2QNUZEGRSRWL6RPJT","short_pith_number":"pith:E7GCENMD","canonical_record":{"source":{"id":"1911.12674","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2019-11-28T12:37:26Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"d04eee5b2cdabcaf8528016a9c3776779d5cc3d05e0423bac3c1b3bb86baad82","abstract_canon_sha256":"12a6a10721258708e1f8473e6573a0c7cbd6d9a14b71b72063fa9c50645a2fb4"},"schema_version":"1.0"},"canonical_sha256":"27cc22358376a0da64868ca365fa2f4cfa357d3ca710306236c1121d3e950961","source":{"kind":"arxiv","id":"1911.12674","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.12674","created_at":"2026-07-05T00:35:03Z"},{"alias_kind":"arxiv_version","alias_value":"1911.12674v2","created_at":"2026-07-05T00:35:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.12674","created_at":"2026-07-05T00:35:03Z"},{"alias_kind":"pith_short_12","alias_value":"E7GCENMDO2QN","created_at":"2026-07-05T00:35:03Z"},{"alias_kind":"pith_short_16","alias_value":"E7GCENMDO2QNUZEG","created_at":"2026-07-05T00:35:03Z"},{"alias_kind":"pith_short_8","alias_value":"E7GCENMD","created_at":"2026-07-05T00:35:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:E7GCENMDO2QNUZEGRSRWL6RPJT","target":"record","payload":{"canonical_record":{"source":{"id":"1911.12674","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2019-11-28T12:37:26Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"d04eee5b2cdabcaf8528016a9c3776779d5cc3d05e0423bac3c1b3bb86baad82","abstract_canon_sha256":"12a6a10721258708e1f8473e6573a0c7cbd6d9a14b71b72063fa9c50645a2fb4"},"schema_version":"1.0"},"canonical_sha256":"27cc22358376a0da64868ca365fa2f4cfa357d3ca710306236c1121d3e950961","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:35:03.089889Z","signature_b64":"WukKPeO4l7sr7YcA+vbfp7vuctqJ4xZsTPLAEUAlUzylbny3hySupIuwJ7N2R4JZ7iXKpLEd2AvsRRl2oqMLBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"27cc22358376a0da64868ca365fa2f4cfa357d3ca710306236c1121d3e950961","last_reissued_at":"2026-07-05T00:35:03.089441Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:35:03.089441Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1911.12674","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":"2026-07-05T00:35:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D2F6gpR/eTTb/VEd0nXcnIeGdU7KvluI+AvUlkma245ahz/bbvaTkr/jHpR3HQDYWPHF/t0hFS88MXOCQJ7wCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T17:28:40.712235Z"},"content_sha256":"a5fad298a9b41fe4c902a3acd7bada66319dd9e4f197add6ba2ae0d0ecee4562","schema_version":"1.0","event_id":"sha256:a5fad298a9b41fe4c902a3acd7bada66319dd9e4f197add6ba2ae0d0ecee4562"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:E7GCENMDO2QNUZEGRSRWL6RPJT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RETRO: Relation Retrofitting For In-Database Machine Learning on Textual Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.DB","authors_text":"Maik Thiele, Michael G\\\"unther, Wolfgang Lehner","submitted_at":"2019-11-28T12:37:26Z","abstract_excerpt":"There are massive amounts of textual data residing in databases, valuable for many machine learning (ML) tasks. Since ML techniques depend on numerical input representations, word embeddings are increasingly utilized to convert symbolic representations such as text into meaningful numbers. However, a naive one-to-one mapping of each word in a database to a word embedding vector is not sufficient and would lead to poor accuracies in ML tasks. Thus, we argue to additionally incorporate the information given by the database schema into the embedding, e.g. which words appear in the same column or "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.12674","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1911.12674/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T00:35:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nfx7kj24glR5AD9nKiDjNwE2WT5xT4y/n+c1qrj4Pupe7rOMKRXyBifZGi5zBtK3YHugm2fAuahxxzXlz65EDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T17:28:40.713201Z"},"content_sha256":"4344a1e3107dce94271d8ee4e44b681648f2d032bbd09dcf0296e4e4eb9948ac","schema_version":"1.0","event_id":"sha256:4344a1e3107dce94271d8ee4e44b681648f2d032bbd09dcf0296e4e4eb9948ac"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E7GCENMDO2QNUZEGRSRWL6RPJT/bundle.json","state_url":"https://pith.science/pith/E7GCENMDO2QNUZEGRSRWL6RPJT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E7GCENMDO2QNUZEGRSRWL6RPJT/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":"2026-08-15T17:28:40Z","links":{"resolver":"https://pith.science/pith/E7GCENMDO2QNUZEGRSRWL6RPJT","bundle":"https://pith.science/pith/E7GCENMDO2QNUZEGRSRWL6RPJT/bundle.json","state":"https://pith.science/pith/E7GCENMDO2QNUZEGRSRWL6RPJT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E7GCENMDO2QNUZEGRSRWL6RPJT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:E7GCENMDO2QNUZEGRSRWL6RPJT","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":"12a6a10721258708e1f8473e6573a0c7cbd6d9a14b71b72063fa9c50645a2fb4","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2019-11-28T12:37:26Z","title_canon_sha256":"d04eee5b2cdabcaf8528016a9c3776779d5cc3d05e0423bac3c1b3bb86baad82"},"schema_version":"1.0","source":{"id":"1911.12674","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.12674","created_at":"2026-07-05T00:35:03Z"},{"alias_kind":"arxiv_version","alias_value":"1911.12674v2","created_at":"2026-07-05T00:35:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.12674","created_at":"2026-07-05T00:35:03Z"},{"alias_kind":"pith_short_12","alias_value":"E7GCENMDO2QN","created_at":"2026-07-05T00:35:03Z"},{"alias_kind":"pith_short_16","alias_value":"E7GCENMDO2QNUZEG","created_at":"2026-07-05T00:35:03Z"},{"alias_kind":"pith_short_8","alias_value":"E7GCENMD","created_at":"2026-07-05T00:35:03Z"}],"graph_snapshots":[{"event_id":"sha256:4344a1e3107dce94271d8ee4e44b681648f2d032bbd09dcf0296e4e4eb9948ac","target":"graph","created_at":"2026-07-05T00:35:03Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1911.12674/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"There are massive amounts of textual data residing in databases, valuable for many machine learning (ML) tasks. Since ML techniques depend on numerical input representations, word embeddings are increasingly utilized to convert symbolic representations such as text into meaningful numbers. However, a naive one-to-one mapping of each word in a database to a word embedding vector is not sufficient and would lead to poor accuracies in ML tasks. Thus, we argue to additionally incorporate the information given by the database schema into the embedding, e.g. which words appear in the same column or ","authors_text":"Maik Thiele, Michael G\\\"unther, Wolfgang Lehner","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2019-11-28T12:37:26Z","title":"RETRO: Relation Retrofitting For In-Database Machine Learning on Textual Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.12674","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:a5fad298a9b41fe4c902a3acd7bada66319dd9e4f197add6ba2ae0d0ecee4562","target":"record","created_at":"2026-07-05T00:35:03Z","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":"12a6a10721258708e1f8473e6573a0c7cbd6d9a14b71b72063fa9c50645a2fb4","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2019-11-28T12:37:26Z","title_canon_sha256":"d04eee5b2cdabcaf8528016a9c3776779d5cc3d05e0423bac3c1b3bb86baad82"},"schema_version":"1.0","source":{"id":"1911.12674","kind":"arxiv","version":2}},"canonical_sha256":"27cc22358376a0da64868ca365fa2f4cfa357d3ca710306236c1121d3e950961","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"27cc22358376a0da64868ca365fa2f4cfa357d3ca710306236c1121d3e950961","first_computed_at":"2026-07-05T00:35:03.089441Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:35:03.089441Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WukKPeO4l7sr7YcA+vbfp7vuctqJ4xZsTPLAEUAlUzylbny3hySupIuwJ7N2R4JZ7iXKpLEd2AvsRRl2oqMLBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:35:03.089889Z","signed_message":"canonical_sha256_bytes"},"source_id":"1911.12674","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a5fad298a9b41fe4c902a3acd7bada66319dd9e4f197add6ba2ae0d0ecee4562","sha256:4344a1e3107dce94271d8ee4e44b681648f2d032bbd09dcf0296e4e4eb9948ac"],"state_sha256":"2476943067d42edb890e563ee619e89b7c147ea513b3043b200247499c780fb9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Kcch4wQhS/3cchzv/fLxsysvTnEi/DIwdY3aGNC7uAn/VjDAyc7GmL+T5Ye8tWrEglImI2o+lKx7Kdbtv5YVDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T17:28:40.720138Z","bundle_sha256":"095e9986d92efaa33ae81b53bdbf71971f9bcc31f8eea7602af3739b2b4bf4b8"}}