{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:ED3G5PXPM6YSSVDYRKVTVL2XAH","short_pith_number":"pith:ED3G5PXP","schema_version":"1.0","canonical_sha256":"20f66ebeef67b12954788aab3aaf5701fdf2bbe06562404f6dca7073aa0808fb","source":{"kind":"arxiv","id":"1907.01183","version":1},"attestation_state":"computed","paper":{"title":"A Framework for Evaluating Snippet Generation for Dataset Search","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.IR","authors_text":"Evgeny Kharlamov, Gong Cheng, Jeff Z. Pan, Jinchi Chen, Shuxin Li, Xiaxia Wang, Yuzhong Qu","submitted_at":"2019-07-02T05:58:18Z","abstract_excerpt":"Reusing existing datasets is of considerable significance to researchers and developers. Dataset search engines help a user find relevant datasets for reuse. They can present a snippet for each retrieved dataset to explain its relevance to the user's data needs. This emerging problem of snippet generation for dataset search has not received much research attention. To provide a basis for future research, we introduce a framework for quantitatively evaluating the quality of a dataset snippet. The proposed metrics assess the extent to which a snippet matches the query intent and covers the main "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1907.01183","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2019-07-02T05:58:18Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"1ef0e9f655272e9544658fa2e87a3487719a7f83b468c6387876eaa07a5f3e00","abstract_canon_sha256":"6020135805bf5e1c6d9dc3a7022a315471a7d63391115091004c9df2945d444f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:41.047667Z","signature_b64":"NfFNbZNNApyUbpvDF++9dZLfDje9jdJ09EaY0ucm3l4FrflD09kN0RPbry+gI0ElqLx2iQprADG9L1Kt56tuDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20f66ebeef67b12954788aab3aaf5701fdf2bbe06562404f6dca7073aa0808fb","last_reissued_at":"2026-05-17T23:41:41.047115Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:41.047115Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Framework for Evaluating Snippet Generation for Dataset Search","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.IR","authors_text":"Evgeny Kharlamov, Gong Cheng, Jeff Z. Pan, Jinchi Chen, Shuxin Li, Xiaxia Wang, Yuzhong Qu","submitted_at":"2019-07-02T05:58:18Z","abstract_excerpt":"Reusing existing datasets is of considerable significance to researchers and developers. Dataset search engines help a user find relevant datasets for reuse. They can present a snippet for each retrieved dataset to explain its relevance to the user's data needs. This emerging problem of snippet generation for dataset search has not received much research attention. To provide a basis for future research, we introduce a framework for quantitatively evaluating the quality of a dataset snippet. The proposed metrics assess the extent to which a snippet matches the query intent and covers the main "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.01183","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":""},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1907.01183","created_at":"2026-05-17T23:41:41.047195+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.01183v1","created_at":"2026-05-17T23:41:41.047195+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.01183","created_at":"2026-05-17T23:41:41.047195+00:00"},{"alias_kind":"pith_short_12","alias_value":"ED3G5PXPM6YS","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_16","alias_value":"ED3G5PXPM6YSSVDY","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_8","alias_value":"ED3G5PXP","created_at":"2026-05-18T12:33:15.570797+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ED3G5PXPM6YSSVDYRKVTVL2XAH","json":"https://pith.science/pith/ED3G5PXPM6YSSVDYRKVTVL2XAH.json","graph_json":"https://pith.science/api/pith-number/ED3G5PXPM6YSSVDYRKVTVL2XAH/graph.json","events_json":"https://pith.science/api/pith-number/ED3G5PXPM6YSSVDYRKVTVL2XAH/events.json","paper":"https://pith.science/paper/ED3G5PXP"},"agent_actions":{"view_html":"https://pith.science/pith/ED3G5PXPM6YSSVDYRKVTVL2XAH","download_json":"https://pith.science/pith/ED3G5PXPM6YSSVDYRKVTVL2XAH.json","view_paper":"https://pith.science/paper/ED3G5PXP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.01183&json=true","fetch_graph":"https://pith.science/api/pith-number/ED3G5PXPM6YSSVDYRKVTVL2XAH/graph.json","fetch_events":"https://pith.science/api/pith-number/ED3G5PXPM6YSSVDYRKVTVL2XAH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ED3G5PXPM6YSSVDYRKVTVL2XAH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ED3G5PXPM6YSSVDYRKVTVL2XAH/action/storage_attestation","attest_author":"https://pith.science/pith/ED3G5PXPM6YSSVDYRKVTVL2XAH/action/author_attestation","sign_citation":"https://pith.science/pith/ED3G5PXPM6YSSVDYRKVTVL2XAH/action/citation_signature","submit_replication":"https://pith.science/pith/ED3G5PXPM6YSSVDYRKVTVL2XAH/action/replication_record"}},"created_at":"2026-05-17T23:41:41.047195+00:00","updated_at":"2026-05-17T23:41:41.047195+00:00"}