{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:EOMAVV5HU25WKMJJH43CCO6ULX","short_pith_number":"pith:EOMAVV5H","canonical_record":{"source":{"id":"2102.05716","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-02-10T19:49:10Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"b4f7c505dc892a47f0e4d2b302da0db9ffe8b1c7a05d250293c561b229d334af","abstract_canon_sha256":"b2e9f4df662b2f65341c6b2709155b8d0ab1cdabdee8acfce0f62b48aaaf77e2"},"schema_version":"1.0"},"canonical_sha256":"23980ad7a7a6bb6531293f36213bd45dc92bb16785adaa7eac5cc45915d4b5ac","source":{"kind":"arxiv","id":"2102.05716","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.05716","created_at":"2026-07-05T03:10:02Z"},{"alias_kind":"arxiv_version","alias_value":"2102.05716v2","created_at":"2026-07-05T03:10:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.05716","created_at":"2026-07-05T03:10:02Z"},{"alias_kind":"pith_short_12","alias_value":"EOMAVV5HU25W","created_at":"2026-07-05T03:10:02Z"},{"alias_kind":"pith_short_16","alias_value":"EOMAVV5HU25WKMJJ","created_at":"2026-07-05T03:10:02Z"},{"alias_kind":"pith_short_8","alias_value":"EOMAVV5H","created_at":"2026-07-05T03:10:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:EOMAVV5HU25WKMJJH43CCO6ULX","target":"record","payload":{"canonical_record":{"source":{"id":"2102.05716","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-02-10T19:49:10Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"b4f7c505dc892a47f0e4d2b302da0db9ffe8b1c7a05d250293c561b229d334af","abstract_canon_sha256":"b2e9f4df662b2f65341c6b2709155b8d0ab1cdabdee8acfce0f62b48aaaf77e2"},"schema_version":"1.0"},"canonical_sha256":"23980ad7a7a6bb6531293f36213bd45dc92bb16785adaa7eac5cc45915d4b5ac","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:10:02.322791Z","signature_b64":"j+CtcGOafEdQw1mAdJEU9zLI0qoitdNnqb54IGDCXay3bIYZ4GfjbVZiIUhzoXElnyO5prqDE33eStxChoe/Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23980ad7a7a6bb6531293f36213bd45dc92bb16785adaa7eac5cc45915d4b5ac","last_reissued_at":"2026-07-05T03:10:02.322161Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:10:02.322161Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2102.05716","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":"2026-07-05T03:10:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l6Lyt96FHHl9nxvKa0kGXggcv9M52Z+4jDJCUPKP1gw9r6BF9AlKRAOEt2ORWvnDwF4eFooQsCpqp47urYoDAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T09:03:35.806498Z"},"content_sha256":"476ec98f620a199af19900900be22ef0b1415a77d2da5c40c6ed2e9d98531b84","schema_version":"1.0","event_id":"sha256:476ec98f620a199af19900900be22ef0b1415a77d2da5c40c6ed2e9d98531b84"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:EOMAVV5HU25WKMJJH43CCO6ULX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Auctus: A Dataset Search Engine for Data Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.IR","authors_text":"A\\'ecio Santos, Aline Bessa, Fernando Chirigati, Juliana Freire, R\\'emi Rampin, Sonia Castelo","submitted_at":"2021-02-10T19:49:10Z","abstract_excerpt":"The large volumes of structured data currently available, from Web tables to open-data portals and enterprise data, open up new opportunities for progress in answering many important scientific, societal, and business questions. However, finding relevant data is difficult. While search engines have addressed this problem for Web documents, there are many new challenges involved in supporting the discovery of structured data. We demonstrate how the Auctus dataset search engine addresses some of these challenges. We describe the system architecture and how users can explore datasets through a ri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.05716","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/2102.05716/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":"2026-07-05T03:10:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vaficzeQ5EO/ri5ee9INVidvPFXqySc+wk+5+yzEZxZyzJetLwF3XZaG7PfH9V9yCHNf7tjo9Sgg0gR2OJQtCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T09:03:35.806867Z"},"content_sha256":"2885ec9d95b23f54eccbfeaa75a461f96702c762292592c2cfa8f4d4cf64cfbb","schema_version":"1.0","event_id":"sha256:2885ec9d95b23f54eccbfeaa75a461f96702c762292592c2cfa8f4d4cf64cfbb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EOMAVV5HU25WKMJJH43CCO6ULX/bundle.json","state_url":"https://pith.science/pith/EOMAVV5HU25WKMJJH43CCO6ULX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EOMAVV5HU25WKMJJH43CCO6ULX/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":"2026-08-21T09:03:35Z","links":{"resolver":"https://pith.science/pith/EOMAVV5HU25WKMJJH43CCO6ULX","bundle":"https://pith.science/pith/EOMAVV5HU25WKMJJH43CCO6ULX/bundle.json","state":"https://pith.science/pith/EOMAVV5HU25WKMJJH43CCO6ULX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EOMAVV5HU25WKMJJH43CCO6ULX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:EOMAVV5HU25WKMJJH43CCO6ULX","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":"b2e9f4df662b2f65341c6b2709155b8d0ab1cdabdee8acfce0f62b48aaaf77e2","cross_cats_sorted":["cs.DB"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-02-10T19:49:10Z","title_canon_sha256":"b4f7c505dc892a47f0e4d2b302da0db9ffe8b1c7a05d250293c561b229d334af"},"schema_version":"1.0","source":{"id":"2102.05716","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.05716","created_at":"2026-07-05T03:10:02Z"},{"alias_kind":"arxiv_version","alias_value":"2102.05716v2","created_at":"2026-07-05T03:10:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.05716","created_at":"2026-07-05T03:10:02Z"},{"alias_kind":"pith_short_12","alias_value":"EOMAVV5HU25W","created_at":"2026-07-05T03:10:02Z"},{"alias_kind":"pith_short_16","alias_value":"EOMAVV5HU25WKMJJ","created_at":"2026-07-05T03:10:02Z"},{"alias_kind":"pith_short_8","alias_value":"EOMAVV5H","created_at":"2026-07-05T03:10:02Z"}],"graph_snapshots":[{"event_id":"sha256:2885ec9d95b23f54eccbfeaa75a461f96702c762292592c2cfa8f4d4cf64cfbb","target":"graph","created_at":"2026-07-05T03:10:02Z","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/2102.05716/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The large volumes of structured data currently available, from Web tables to open-data portals and enterprise data, open up new opportunities for progress in answering many important scientific, societal, and business questions. However, finding relevant data is difficult. While search engines have addressed this problem for Web documents, there are many new challenges involved in supporting the discovery of structured data. We demonstrate how the Auctus dataset search engine addresses some of these challenges. We describe the system architecture and how users can explore datasets through a ri","authors_text":"A\\'ecio Santos, Aline Bessa, Fernando Chirigati, Juliana Freire, R\\'emi Rampin, Sonia Castelo","cross_cats":["cs.DB"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-02-10T19:49:10Z","title":"Auctus: A Dataset Search Engine for Data Augmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.05716","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":"sha256:476ec98f620a199af19900900be22ef0b1415a77d2da5c40c6ed2e9d98531b84","target":"record","created_at":"2026-07-05T03:10:02Z","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":"b2e9f4df662b2f65341c6b2709155b8d0ab1cdabdee8acfce0f62b48aaaf77e2","cross_cats_sorted":["cs.DB"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-02-10T19:49:10Z","title_canon_sha256":"b4f7c505dc892a47f0e4d2b302da0db9ffe8b1c7a05d250293c561b229d334af"},"schema_version":"1.0","source":{"id":"2102.05716","kind":"arxiv","version":2}},"canonical_sha256":"23980ad7a7a6bb6531293f36213bd45dc92bb16785adaa7eac5cc45915d4b5ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"23980ad7a7a6bb6531293f36213bd45dc92bb16785adaa7eac5cc45915d4b5ac","first_computed_at":"2026-07-05T03:10:02.322161Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:10:02.322161Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j+CtcGOafEdQw1mAdJEU9zLI0qoitdNnqb54IGDCXay3bIYZ4GfjbVZiIUhzoXElnyO5prqDE33eStxChoe/Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:10:02.322791Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.05716","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:476ec98f620a199af19900900be22ef0b1415a77d2da5c40c6ed2e9d98531b84","sha256:2885ec9d95b23f54eccbfeaa75a461f96702c762292592c2cfa8f4d4cf64cfbb"],"state_sha256":"80b35a128d5bc4f92f91ee0b3b716e1152d2c260afaa11a9ba4b4e4f45440f0d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xKflpGx8E7U2mrg1fxhRJILlg9cLXm4iawIkE7ELOlpfW3e59iZvzCZPuSHmra5WKFNbo0Y4J+rXt8+wdrU0BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T09:03:35.809870Z","bundle_sha256":"f3e0b1ab0d6aedc3c02313a034feba73b257e9841ec2ab0513a7c41b7f048272"}}