{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FBNWVSECXYWWIPCK345APGN5X4","short_pith_number":"pith:FBNWVSEC","schema_version":"1.0","canonical_sha256":"285b6ac882be2d643c4adf3a0799bdbf21b28f67a436878c80a5a484f1cac709","source":{"kind":"arxiv","id":"2602.14594","version":2},"attestation_state":"computed","paper":{"title":"The Wikidata Query Logs Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hannah Bast, Sebastian Walter","submitted_at":"2026-02-16T09:49:44Z","abstract_excerpt":"We present the Wikidata Query Logs (WDQL) dataset, a dataset consisting of 335k question-query pairs over the Wikidata knowledge graph. It is over 11x larger than the largest existing Wikidata datasets of similar format without relying on template-generated queries. Instead, we construct it using real-world SPARQL queries sent to the Wikidata Query Service and generate questions for them. Since these log-based queries are anonymized, and therefore often do not produce results, a significant amount of effort is needed to convert them back into meaningful SPARQL queries. To achieve this, we pres"},"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":"2602.14594","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-02-16T09:49:44Z","cross_cats_sorted":[],"title_canon_sha256":"b4c14badadb8a4f0e64d1700b89b1704d61d7ffd632816b88799b710515b9546","abstract_canon_sha256":"627437c84b3fb4888e422df5cfe4f6f1743e546470520a26f369cfa25c569e09"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T02:05:40.990807Z","signature_b64":"3S5ITQ4spuU0plFrvWBvu7tUyDU9hNOtCyV6re+GYeUbN801qR4vUzG0ePGH/Zxciyrm10Bh7NyyffIJ3H1VCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"285b6ac882be2d643c4adf3a0799bdbf21b28f67a436878c80a5a484f1cac709","last_reissued_at":"2026-05-20T02:05:40.989811Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T02:05:40.989811Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Wikidata Query Logs Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hannah Bast, Sebastian Walter","submitted_at":"2026-02-16T09:49:44Z","abstract_excerpt":"We present the Wikidata Query Logs (WDQL) dataset, a dataset consisting of 335k question-query pairs over the Wikidata knowledge graph. It is over 11x larger than the largest existing Wikidata datasets of similar format without relying on template-generated queries. Instead, we construct it using real-world SPARQL queries sent to the Wikidata Query Service and generate questions for them. Since these log-based queries are anonymized, and therefore often do not produce results, a significant amount of effort is needed to convert them back into meaningful SPARQL queries. To achieve this, we pres"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.14594","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/2602.14594/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2602.14594","created_at":"2026-05-20T02:05:40.989961+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.14594v2","created_at":"2026-05-20T02:05:40.989961+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.14594","created_at":"2026-05-20T02:05:40.989961+00:00"},{"alias_kind":"pith_short_12","alias_value":"FBNWVSECXYWW","created_at":"2026-05-20T02:05:40.989961+00:00"},{"alias_kind":"pith_short_16","alias_value":"FBNWVSECXYWWIPCK","created_at":"2026-05-20T02:05:40.989961+00:00"},{"alias_kind":"pith_short_8","alias_value":"FBNWVSEC","created_at":"2026-05-20T02:05:40.989961+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.21133","citing_title":"GRISP: Guided Recurrent IRI Selection over SPARQL Skeletons","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FBNWVSECXYWWIPCK345APGN5X4","json":"https://pith.science/pith/FBNWVSECXYWWIPCK345APGN5X4.json","graph_json":"https://pith.science/api/pith-number/FBNWVSECXYWWIPCK345APGN5X4/graph.json","events_json":"https://pith.science/api/pith-number/FBNWVSECXYWWIPCK345APGN5X4/events.json","paper":"https://pith.science/paper/FBNWVSEC"},"agent_actions":{"view_html":"https://pith.science/pith/FBNWVSECXYWWIPCK345APGN5X4","download_json":"https://pith.science/pith/FBNWVSECXYWWIPCK345APGN5X4.json","view_paper":"https://pith.science/paper/FBNWVSEC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.14594&json=true","fetch_graph":"https://pith.science/api/pith-number/FBNWVSECXYWWIPCK345APGN5X4/graph.json","fetch_events":"https://pith.science/api/pith-number/FBNWVSECXYWWIPCK345APGN5X4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FBNWVSECXYWWIPCK345APGN5X4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FBNWVSECXYWWIPCK345APGN5X4/action/storage_attestation","attest_author":"https://pith.science/pith/FBNWVSECXYWWIPCK345APGN5X4/action/author_attestation","sign_citation":"https://pith.science/pith/FBNWVSECXYWWIPCK345APGN5X4/action/citation_signature","submit_replication":"https://pith.science/pith/FBNWVSECXYWWIPCK345APGN5X4/action/replication_record"}},"created_at":"2026-05-20T02:05:40.989961+00:00","updated_at":"2026-05-20T02:05:40.989961+00:00"}