{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WETPMFTSVOMRTF4GU3PFGJZSYG","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":"976ecb69a5cd9b703b2e28aedfc6e53def6964643c48de8596411ce1f72649c5","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-28T10:46:52Z","title_canon_sha256":"083f07f4f1af673d3a60222ba1ad48fe96f99300b3f93b3b03e5d71c58c8b07c"},"schema_version":"1.0","source":{"id":"2502.20936","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.20936","created_at":"2026-07-05T10:21:42Z"},{"alias_kind":"arxiv_version","alias_value":"2502.20936v1","created_at":"2026-07-05T10:21:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.20936","created_at":"2026-07-05T10:21:42Z"},{"alias_kind":"pith_short_12","alias_value":"WETPMFTSVOMR","created_at":"2026-07-05T10:21:42Z"},{"alias_kind":"pith_short_16","alias_value":"WETPMFTSVOMRTF4G","created_at":"2026-07-05T10:21:42Z"},{"alias_kind":"pith_short_8","alias_value":"WETPMFTS","created_at":"2026-07-05T10:21:42Z"}],"graph_snapshots":[{"event_id":"sha256:ae62b9495bc64eba2b567efcae110ac849dd4661da01d931f2a58f98f1ff62fd","target":"graph","created_at":"2026-07-05T10:21:42Z","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/2502.20936/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jelena Mitrovi\\'c, Kanishka Ghosh Dastidar, Laura Caspari, Michael Dinzinger, Michael Granitzer","cross_cats":["cs.AI","cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-28T10:46:52Z","title":"WebFAQ: A Multilingual Collection of Natural Q&A Datasets for Dense Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.20936","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:f9795cb00bb9996a92792f28031dca7e01d48c556d3588976753cbb41f8076f2","target":"record","created_at":"2026-07-05T10:21:42Z","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":"976ecb69a5cd9b703b2e28aedfc6e53def6964643c48de8596411ce1f72649c5","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-28T10:46:52Z","title_canon_sha256":"083f07f4f1af673d3a60222ba1ad48fe96f99300b3f93b3b03e5d71c58c8b07c"},"schema_version":"1.0","source":{"id":"2502.20936","kind":"arxiv","version":1}},"canonical_sha256":"b126f61672ab99199786a6de532732c18e4b94f6b3abe70e6233223762d495f9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b126f61672ab99199786a6de532732c18e4b94f6b3abe70e6233223762d495f9","first_computed_at":"2026-07-05T10:21:42.371588Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:21:42.371588Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XV+CXyo0H2Mo+pQwag7hIJ7OivU9HOy2v6peMPt/gEJ/mjrJU+N2aFCmYrTrEMc2G+diXwhb4lTO1rjgmhuBCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:21:42.371988Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.20936","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f9795cb00bb9996a92792f28031dca7e01d48c556d3588976753cbb41f8076f2","sha256:ae62b9495bc64eba2b567efcae110ac849dd4661da01d931f2a58f98f1ff62fd"],"state_sha256":"459aa3c9045726d13e5eba1fbc3e8065c8915fc886f1d38b4d2adf46770deea9"}