{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WETPMFTSVOMRTF4GU3PFGJZSYG","short_pith_number":"pith:WETPMFTS","schema_version":"1.0","canonical_sha256":"b126f61672ab99199786a6de532732c18e4b94f6b3abe70e6233223762d495f9","source":{"kind":"arxiv","id":"2502.20936","version":1},"attestation_state":"computed","paper":{"title":"WebFAQ: A Multilingual Collection of Natural Q&A Datasets for Dense Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Jelena Mitrovi\\'c, Kanishka Ghosh Dastidar, Laura Caspari, Michael Dinzinger, Michael Granitzer","submitted_at":"2025-02-28T10:46:52Z","abstract_excerpt":"We present WebFAQ, a large-scale collection of open-domain question answering datasets derived from FAQ-style schema.org annotations. In total, the data collection consists of 96 million natural question-answer (QA) pairs across 75 languages, including 47 million (49%) non-English samples. WebFAQ further serves as the foundation for 20 monolingual retrieval benchmarks with a total size of 11.2 million QA pairs (5.9 million non-English). These datasets are carefully curated through refined filtering and near-duplicate detection, yielding high-quality resources for training and evaluating multil"},"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":"2502.20936","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-28T10:46:52Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"083f07f4f1af673d3a60222ba1ad48fe96f99300b3f93b3b03e5d71c58c8b07c","abstract_canon_sha256":"976ecb69a5cd9b703b2e28aedfc6e53def6964643c48de8596411ce1f72649c5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:21:42.371988Z","signature_b64":"XV+CXyo0H2Mo+pQwag7hIJ7OivU9HOy2v6peMPt/gEJ/mjrJU+N2aFCmYrTrEMc2G+diXwhb4lTO1rjgmhuBCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b126f61672ab99199786a6de532732c18e4b94f6b3abe70e6233223762d495f9","last_reissued_at":"2026-07-05T10:21:42.371588Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:21:42.371588Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WebFAQ: A Multilingual Collection of Natural Q&A Datasets for Dense Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Jelena Mitrovi\\'c, Kanishka Ghosh Dastidar, Laura Caspari, Michael Dinzinger, Michael Granitzer","submitted_at":"2025-02-28T10:46:52Z","abstract_excerpt":"We present WebFAQ, a large-scale collection of open-domain question answering datasets derived from FAQ-style schema.org annotations. In total, the data collection consists of 96 million natural question-answer (QA) pairs across 75 languages, including 47 million (49%) non-English samples. WebFAQ further serves as the foundation for 20 monolingual retrieval benchmarks with a total size of 11.2 million QA pairs (5.9 million non-English). These datasets are carefully curated through refined filtering and near-duplicate detection, yielding high-quality resources for training and evaluating multil"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.20936","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/2502.20936/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":"2502.20936","created_at":"2026-07-05T10:21:42.371648+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.20936v1","created_at":"2026-07-05T10:21:42.371648+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.20936","created_at":"2026-07-05T10:21:42.371648+00:00"},{"alias_kind":"pith_short_12","alias_value":"WETPMFTSVOMR","created_at":"2026-07-05T10:21:42.371648+00:00"},{"alias_kind":"pith_short_16","alias_value":"WETPMFTSVOMRTF4G","created_at":"2026-07-05T10:21:42.371648+00:00"},{"alias_kind":"pith_short_8","alias_value":"WETPMFTS","created_at":"2026-07-05T10:21:42.371648+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13647","citing_title":"SkMTEB: Slovak Massive Text Embedding Benchmark and Model Adaptation","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24334","citing_title":"Reducing Redundancy in Retrieval-Augmented Generation through Chunk Filtering","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WETPMFTSVOMRTF4GU3PFGJZSYG","json":"https://pith.science/pith/WETPMFTSVOMRTF4GU3PFGJZSYG.json","graph_json":"https://pith.science/api/pith-number/WETPMFTSVOMRTF4GU3PFGJZSYG/graph.json","events_json":"https://pith.science/api/pith-number/WETPMFTSVOMRTF4GU3PFGJZSYG/events.json","paper":"https://pith.science/paper/WETPMFTS"},"agent_actions":{"view_html":"https://pith.science/pith/WETPMFTSVOMRTF4GU3PFGJZSYG","download_json":"https://pith.science/pith/WETPMFTSVOMRTF4GU3PFGJZSYG.json","view_paper":"https://pith.science/paper/WETPMFTS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.20936&json=true","fetch_graph":"https://pith.science/api/pith-number/WETPMFTSVOMRTF4GU3PFGJZSYG/graph.json","fetch_events":"https://pith.science/api/pith-number/WETPMFTSVOMRTF4GU3PFGJZSYG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WETPMFTSVOMRTF4GU3PFGJZSYG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WETPMFTSVOMRTF4GU3PFGJZSYG/action/storage_attestation","attest_author":"https://pith.science/pith/WETPMFTSVOMRTF4GU3PFGJZSYG/action/author_attestation","sign_citation":"https://pith.science/pith/WETPMFTSVOMRTF4GU3PFGJZSYG/action/citation_signature","submit_replication":"https://pith.science/pith/WETPMFTSVOMRTF4GU3PFGJZSYG/action/replication_record"}},"created_at":"2026-07-05T10:21:42.371648+00:00","updated_at":"2026-07-05T10:21:42.371648+00:00"}