{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:6WCHXNTS2DPGPG3MFPN42FIMYM","short_pith_number":"pith:6WCHXNTS","canonical_record":{"source":{"id":"2010.07386","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2020-10-14T20:12:23Z","cross_cats_sorted":[],"title_canon_sha256":"6f02e887bfc4594f994fb4fc4fd8beee136ce2bcce9f4906fd7a95c27d432a26","abstract_canon_sha256":"fede4b3e9b67599619da19c3870c329ce5ffde226fc58ad0e2c8ad3c1c54fa9e"},"schema_version":"1.0"},"canonical_sha256":"f5847bb672d0de679b6c2bdbcd150cc33a64e076709582e599984ac8f410be7e","source":{"kind":"arxiv","id":"2010.07386","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.07386","created_at":"2026-07-05T02:14:55Z"},{"alias_kind":"arxiv_version","alias_value":"2010.07386v2","created_at":"2026-07-05T02:14:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.07386","created_at":"2026-07-05T02:14:55Z"},{"alias_kind":"pith_short_12","alias_value":"6WCHXNTS2DPG","created_at":"2026-07-05T02:14:55Z"},{"alias_kind":"pith_short_16","alias_value":"6WCHXNTS2DPGPG3M","created_at":"2026-07-05T02:14:55Z"},{"alias_kind":"pith_short_8","alias_value":"6WCHXNTS","created_at":"2026-07-05T02:14:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:6WCHXNTS2DPGPG3MFPN42FIMYM","target":"record","payload":{"canonical_record":{"source":{"id":"2010.07386","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2020-10-14T20:12:23Z","cross_cats_sorted":[],"title_canon_sha256":"6f02e887bfc4594f994fb4fc4fd8beee136ce2bcce9f4906fd7a95c27d432a26","abstract_canon_sha256":"fede4b3e9b67599619da19c3870c329ce5ffde226fc58ad0e2c8ad3c1c54fa9e"},"schema_version":"1.0"},"canonical_sha256":"f5847bb672d0de679b6c2bdbcd150cc33a64e076709582e599984ac8f410be7e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:14:55.456078Z","signature_b64":"naKIZAQask07uNoHwHmxkyT1q6+wrwmH7gCAdMV9TYkpVxfVFLMkaJsIUEZX5yIXgWWEwrF2Ff2EfYATufIjCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5847bb672d0de679b6c2bdbcd150cc33a64e076709582e599984ac8f410be7e","last_reissued_at":"2026-07-05T02:14:55.455548Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:14:55.455548Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2010.07386","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":"2026-07-05T02:14:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v/cPGNpHE/LrreX+3yyNkmSW2NnphEnMC5ZAIJGZvIKClh+yCdACyesu1eCCZYfAXFst46qeq3XxoCzWk12rAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T01:03:42.151789Z"},"content_sha256":"01a547b258455b225fbdeedad22f46a72402a35fe3acf3fd58ac569cdaa9af59","schema_version":"1.0","event_id":"sha256:01a547b258455b225fbdeedad22f46a72402a35fe3acf3fd58ac569cdaa9af59"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:6WCHXNTS2DPGPG3MFPN42FIMYM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Valentine: Evaluating Matching Techniques for Dataset Discovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Andra Ionescu, Angela Bonifati, Asterios Katsifodimos, Christoph Lofi, Christos Koutras, George Siachamis, Jerry Brons, Kyriakos Psarakis, Marios Fragkoulis","submitted_at":"2020-10-14T20:12:23Z","abstract_excerpt":"Data scientists today search large data lakes to discover and integrate datasets. In order to bring together disparate data sources, dataset discovery methods rely on some form of schema matching: the process of establishing correspondences between datasets. Traditionally, schema matching has been used to find matching pairs of columns between a source and a target schema. However, the use of schema matching in dataset discovery methods differs from its original use. Nowadays schema matching serves as a building block for indicating and ranking inter-dataset relationships. Surprisingly, althou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.07386","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/2010.07386/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":"2026-07-05T02:14:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zNbmbKJXl6SmZ0N1iq1Awc6YZ63vjKbh8Vd5psQFeJKujQG7GVT+M/x2rLIDgItQYRq9HT8VsgKN3sQgxwhiCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T01:03:42.152767Z"},"content_sha256":"94e36848dadfd0340831cc4a5852cf2ddc28140823dbd9ef601757418f098ee9","schema_version":"1.0","event_id":"sha256:94e36848dadfd0340831cc4a5852cf2ddc28140823dbd9ef601757418f098ee9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6WCHXNTS2DPGPG3MFPN42FIMYM/bundle.json","state_url":"https://pith.science/pith/6WCHXNTS2DPGPG3MFPN42FIMYM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6WCHXNTS2DPGPG3MFPN42FIMYM/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":"2026-08-07T01:03:42Z","links":{"resolver":"https://pith.science/pith/6WCHXNTS2DPGPG3MFPN42FIMYM","bundle":"https://pith.science/pith/6WCHXNTS2DPGPG3MFPN42FIMYM/bundle.json","state":"https://pith.science/pith/6WCHXNTS2DPGPG3MFPN42FIMYM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6WCHXNTS2DPGPG3MFPN42FIMYM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:6WCHXNTS2DPGPG3MFPN42FIMYM","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":"fede4b3e9b67599619da19c3870c329ce5ffde226fc58ad0e2c8ad3c1c54fa9e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2020-10-14T20:12:23Z","title_canon_sha256":"6f02e887bfc4594f994fb4fc4fd8beee136ce2bcce9f4906fd7a95c27d432a26"},"schema_version":"1.0","source":{"id":"2010.07386","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.07386","created_at":"2026-07-05T02:14:55Z"},{"alias_kind":"arxiv_version","alias_value":"2010.07386v2","created_at":"2026-07-05T02:14:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.07386","created_at":"2026-07-05T02:14:55Z"},{"alias_kind":"pith_short_12","alias_value":"6WCHXNTS2DPG","created_at":"2026-07-05T02:14:55Z"},{"alias_kind":"pith_short_16","alias_value":"6WCHXNTS2DPGPG3M","created_at":"2026-07-05T02:14:55Z"},{"alias_kind":"pith_short_8","alias_value":"6WCHXNTS","created_at":"2026-07-05T02:14:55Z"}],"graph_snapshots":[{"event_id":"sha256:94e36848dadfd0340831cc4a5852cf2ddc28140823dbd9ef601757418f098ee9","target":"graph","created_at":"2026-07-05T02:14:55Z","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/2010.07386/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data scientists today search large data lakes to discover and integrate datasets. In order to bring together disparate data sources, dataset discovery methods rely on some form of schema matching: the process of establishing correspondences between datasets. Traditionally, schema matching has been used to find matching pairs of columns between a source and a target schema. However, the use of schema matching in dataset discovery methods differs from its original use. Nowadays schema matching serves as a building block for indicating and ranking inter-dataset relationships. Surprisingly, althou","authors_text":"Andra Ionescu, Angela Bonifati, Asterios Katsifodimos, Christoph Lofi, Christos Koutras, George Siachamis, Jerry Brons, Kyriakos Psarakis, Marios Fragkoulis","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2020-10-14T20:12:23Z","title":"Valentine: Evaluating Matching Techniques for Dataset Discovery"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.07386","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":"sha256:01a547b258455b225fbdeedad22f46a72402a35fe3acf3fd58ac569cdaa9af59","target":"record","created_at":"2026-07-05T02:14:55Z","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":"fede4b3e9b67599619da19c3870c329ce5ffde226fc58ad0e2c8ad3c1c54fa9e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2020-10-14T20:12:23Z","title_canon_sha256":"6f02e887bfc4594f994fb4fc4fd8beee136ce2bcce9f4906fd7a95c27d432a26"},"schema_version":"1.0","source":{"id":"2010.07386","kind":"arxiv","version":2}},"canonical_sha256":"f5847bb672d0de679b6c2bdbcd150cc33a64e076709582e599984ac8f410be7e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f5847bb672d0de679b6c2bdbcd150cc33a64e076709582e599984ac8f410be7e","first_computed_at":"2026-07-05T02:14:55.455548Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:14:55.455548Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"naKIZAQask07uNoHwHmxkyT1q6+wrwmH7gCAdMV9TYkpVxfVFLMkaJsIUEZX5yIXgWWEwrF2Ff2EfYATufIjCg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:14:55.456078Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.07386","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:01a547b258455b225fbdeedad22f46a72402a35fe3acf3fd58ac569cdaa9af59","sha256:94e36848dadfd0340831cc4a5852cf2ddc28140823dbd9ef601757418f098ee9"],"state_sha256":"61f1f3830232dd235449f94e28352e6b8d41a816b6cc897dfaadada15a05ef77"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9v7adW99qTG5UCTSDpn68tqV/bWwRMkisNGK3FGy5w7RTHyzRHpb12LWox3K6ZGfLM0dtkcDkOO1kpnMTQxHBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T01:03:42.159708Z","bundle_sha256":"5c0644253723ca1b34a11e6a10dd5511f9a7252c555d5385372c98777b43a34d"}}