{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:HKWAAXESHTCQDV45HW76CP4FWC","short_pith_number":"pith:HKWAAXES","canonical_record":{"source":{"id":"2001.10112","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2020-01-27T22:41:02Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"16583c4253deac2e733a1ad4bb079898dcb46f46b85d26cd764fcd4ccaa1f5bf","abstract_canon_sha256":"ea22ac5a0e9791d5325d6fbefcf57c4703cd7f885d7318a47c2084643f8baa38"},"schema_version":"1.0"},"canonical_sha256":"3aac005c923cc501d79d3dbfe13f85b0995a3d5346ff87f414c3390fb01938fe","source":{"kind":"arxiv","id":"2001.10112","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2001.10112","created_at":"2026-07-05T00:36:49Z"},{"alias_kind":"arxiv_version","alias_value":"2001.10112v1","created_at":"2026-07-05T00:36:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.10112","created_at":"2026-07-05T00:36:49Z"},{"alias_kind":"pith_short_12","alias_value":"HKWAAXESHTCQ","created_at":"2026-07-05T00:36:49Z"},{"alias_kind":"pith_short_16","alias_value":"HKWAAXESHTCQDV45","created_at":"2026-07-05T00:36:49Z"},{"alias_kind":"pith_short_8","alias_value":"HKWAAXES","created_at":"2026-07-05T00:36:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:HKWAAXESHTCQDV45HW76CP4FWC","target":"record","payload":{"canonical_record":{"source":{"id":"2001.10112","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2020-01-27T22:41:02Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"16583c4253deac2e733a1ad4bb079898dcb46f46b85d26cd764fcd4ccaa1f5bf","abstract_canon_sha256":"ea22ac5a0e9791d5325d6fbefcf57c4703cd7f885d7318a47c2084643f8baa38"},"schema_version":"1.0"},"canonical_sha256":"3aac005c923cc501d79d3dbfe13f85b0995a3d5346ff87f414c3390fb01938fe","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:36:49.908039Z","signature_b64":"tp+YR04C/cvwAU19UfRs07VRPuo2AJGn4YvX9XyJimAa0tY2Ms+xPzbcO1Xf92AR/cxT0ww9dBg0H78DhZuBCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3aac005c923cc501d79d3dbfe13f85b0995a3d5346ff87f414c3390fb01938fe","last_reissued_at":"2026-07-05T00:36:49.907638Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:36:49.907638Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2001.10112","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:36:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+6ZaEsReF0lBQz9x8+4ee/E6qbcjih4n5I4HGDguwTH8uAK3cqQVmfO8483oStGNpN+ib9F/r/L9uGOdocmYBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T17:46:55.672629Z"},"content_sha256":"bde4342d6b2f9c8762aea8259d726c4e84fad354913f31e1f550d23ec1a9aefa","schema_version":"1.0","event_id":"sha256:bde4342d6b2f9c8762aea8259d726c4e84fad354913f31e1f550d23ec1a9aefa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:HKWAAXESHTCQDV45HW76CP4FWC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Leveraging Schema Labels to Enhance Dataset Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.IR","authors_text":"Brian D. Davison, Haiyan Jia, Jeff Heflin, Zhiyu Chen","submitted_at":"2020-01-27T22:41:02Z","abstract_excerpt":"A search engine's ability to retrieve desirable datasets is important for data sharing and reuse. Existing dataset search engines typically rely on matching queries to dataset descriptions. However, a user may not have enough prior knowledge to write a query using terms that match with description text.We propose a novel schema label generation model which generates possible schema labels based on dataset table content. We incorporate the generated schema labels into a mixed ranking model which not only considers the relevance between the query and dataset metadata but also the similarity betw"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.10112","kind":"arxiv","version":1},"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/2001.10112/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":"2026-07-05T00:36:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JCKGC9jGknFXOEZVNdgI7W0FnILnE6e1gir0E4Bw3rJcWI8XUmFqqMRz2qycits3zZ2zHQ6XvBSQhkbXwtgnCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T17:46:55.673169Z"},"content_sha256":"18380147797ddb1a6fa2da4fa01f71c53a6fdc44d4b9852bddfc12badabae471","schema_version":"1.0","event_id":"sha256:18380147797ddb1a6fa2da4fa01f71c53a6fdc44d4b9852bddfc12badabae471"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HKWAAXESHTCQDV45HW76CP4FWC/bundle.json","state_url":"https://pith.science/pith/HKWAAXESHTCQDV45HW76CP4FWC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HKWAAXESHTCQDV45HW76CP4FWC/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":"2026-08-19T17:46:55Z","links":{"resolver":"https://pith.science/pith/HKWAAXESHTCQDV45HW76CP4FWC","bundle":"https://pith.science/pith/HKWAAXESHTCQDV45HW76CP4FWC/bundle.json","state":"https://pith.science/pith/HKWAAXESHTCQDV45HW76CP4FWC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HKWAAXESHTCQDV45HW76CP4FWC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:HKWAAXESHTCQDV45HW76CP4FWC","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":"ea22ac5a0e9791d5325d6fbefcf57c4703cd7f885d7318a47c2084643f8baa38","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2020-01-27T22:41:02Z","title_canon_sha256":"16583c4253deac2e733a1ad4bb079898dcb46f46b85d26cd764fcd4ccaa1f5bf"},"schema_version":"1.0","source":{"id":"2001.10112","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2001.10112","created_at":"2026-07-05T00:36:49Z"},{"alias_kind":"arxiv_version","alias_value":"2001.10112v1","created_at":"2026-07-05T00:36:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.10112","created_at":"2026-07-05T00:36:49Z"},{"alias_kind":"pith_short_12","alias_value":"HKWAAXESHTCQ","created_at":"2026-07-05T00:36:49Z"},{"alias_kind":"pith_short_16","alias_value":"HKWAAXESHTCQDV45","created_at":"2026-07-05T00:36:49Z"},{"alias_kind":"pith_short_8","alias_value":"HKWAAXES","created_at":"2026-07-05T00:36:49Z"}],"graph_snapshots":[{"event_id":"sha256:18380147797ddb1a6fa2da4fa01f71c53a6fdc44d4b9852bddfc12badabae471","target":"graph","created_at":"2026-07-05T00:36:49Z","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/2001.10112/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A search engine's ability to retrieve desirable datasets is important for data sharing and reuse. Existing dataset search engines typically rely on matching queries to dataset descriptions. However, a user may not have enough prior knowledge to write a query using terms that match with description text.We propose a novel schema label generation model which generates possible schema labels based on dataset table content. We incorporate the generated schema labels into a mixed ranking model which not only considers the relevance between the query and dataset metadata but also the similarity betw","authors_text":"Brian D. Davison, Haiyan Jia, Jeff Heflin, Zhiyu Chen","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2020-01-27T22:41:02Z","title":"Leveraging Schema Labels to Enhance Dataset Search"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.10112","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:bde4342d6b2f9c8762aea8259d726c4e84fad354913f31e1f550d23ec1a9aefa","target":"record","created_at":"2026-07-05T00:36:49Z","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":"ea22ac5a0e9791d5325d6fbefcf57c4703cd7f885d7318a47c2084643f8baa38","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2020-01-27T22:41:02Z","title_canon_sha256":"16583c4253deac2e733a1ad4bb079898dcb46f46b85d26cd764fcd4ccaa1f5bf"},"schema_version":"1.0","source":{"id":"2001.10112","kind":"arxiv","version":1}},"canonical_sha256":"3aac005c923cc501d79d3dbfe13f85b0995a3d5346ff87f414c3390fb01938fe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3aac005c923cc501d79d3dbfe13f85b0995a3d5346ff87f414c3390fb01938fe","first_computed_at":"2026-07-05T00:36:49.907638Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:36:49.907638Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tp+YR04C/cvwAU19UfRs07VRPuo2AJGn4YvX9XyJimAa0tY2Ms+xPzbcO1Xf92AR/cxT0ww9dBg0H78DhZuBCw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:36:49.908039Z","signed_message":"canonical_sha256_bytes"},"source_id":"2001.10112","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bde4342d6b2f9c8762aea8259d726c4e84fad354913f31e1f550d23ec1a9aefa","sha256:18380147797ddb1a6fa2da4fa01f71c53a6fdc44d4b9852bddfc12badabae471"],"state_sha256":"71bb29f92cf18e92d1dea28f70380058310aae6055673c100590adb387d51ed0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a0pYh3Kpc7VRfu1amvzUBqsTTr1fBKDuoAQoqR76MNpJG4H//1dBaa32hRGu/kQiYRZ9Tku/DOatBX2fskGXDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T17:46:55.678324Z","bundle_sha256":"1882937830018486a966a895a64d7022e57e61c8d4b5ac1f391a8b1f2a159f10"}}