{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:37YMJASOOME3LTAFZYABKSSR3T","short_pith_number":"pith:37YMJASO","schema_version":"1.0","canonical_sha256":"dff0c4824e7309b5cc05ce00154a51dcc8ed81efb4b8fac8feadf16dd1d47ce9","source":{"kind":"arxiv","id":"2106.09248","version":1},"attestation_state":"computed","paper":{"title":"X-FACT: A New Benchmark Dataset for Multilingual Fact Checking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ashim Gupta, Vivek Srikumar","submitted_at":"2021-06-17T05:09:54Z","abstract_excerpt":"In this work, we introduce X-FACT: the largest publicly available multilingual dataset for factual verification of naturally existing real-world claims. The dataset contains short statements in 25 languages and is labeled for veracity by expert fact-checkers. The dataset includes a multilingual evaluation benchmark that measures both out-of-domain generalization, and zero-shot capabilities of the multilingual models. Using state-of-the-art multilingual transformer-based models, we develop several automated fact-checking models that, along with textual claims, make use of additional metadata an"},"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":"2106.09248","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-17T05:09:54Z","cross_cats_sorted":[],"title_canon_sha256":"c657100153a8ff3841c6c097067c024da87f9e511750b7421d14cb5658633059","abstract_canon_sha256":"5e30dd9638856d1479cf9c7305268172180ce5f9d34fcce70210a043700766de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:50:14.111285Z","signature_b64":"cHTRTqQnlRQw/Lm3PvhsVkDkdfa5ywa1NsfMWk7OEoRASOjGuSe1edpjPoxwJTeiaFgOmuWDsZ77MJ4e4ajTCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dff0c4824e7309b5cc05ce00154a51dcc8ed81efb4b8fac8feadf16dd1d47ce9","last_reissued_at":"2026-07-05T02:50:14.110886Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:50:14.110886Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"X-FACT: A New Benchmark Dataset for Multilingual Fact Checking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ashim Gupta, Vivek Srikumar","submitted_at":"2021-06-17T05:09:54Z","abstract_excerpt":"In this work, we introduce X-FACT: the largest publicly available multilingual dataset for factual verification of naturally existing real-world claims. The dataset contains short statements in 25 languages and is labeled for veracity by expert fact-checkers. The dataset includes a multilingual evaluation benchmark that measures both out-of-domain generalization, and zero-shot capabilities of the multilingual models. Using state-of-the-art multilingual transformer-based models, we develop several automated fact-checking models that, along with textual claims, make use of additional metadata an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.09248","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/2106.09248/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":"2106.09248","created_at":"2026-07-05T02:50:14.110945+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.09248v1","created_at":"2026-07-05T02:50:14.110945+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.09248","created_at":"2026-07-05T02:50:14.110945+00:00"},{"alias_kind":"pith_short_12","alias_value":"37YMJASOOME3","created_at":"2026-07-05T02:50:14.110945+00:00"},{"alias_kind":"pith_short_16","alias_value":"37YMJASOOME3LTAF","created_at":"2026-07-05T02:50:14.110945+00:00"},{"alias_kind":"pith_short_8","alias_value":"37YMJASO","created_at":"2026-07-05T02:50:14.110945+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.03292","citing_title":"ALPET: Active Few-shot Learning for Citation Worthiness Detection in Low-Resource Wikipedia Languages","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/37YMJASOOME3LTAFZYABKSSR3T","json":"https://pith.science/pith/37YMJASOOME3LTAFZYABKSSR3T.json","graph_json":"https://pith.science/api/pith-number/37YMJASOOME3LTAFZYABKSSR3T/graph.json","events_json":"https://pith.science/api/pith-number/37YMJASOOME3LTAFZYABKSSR3T/events.json","paper":"https://pith.science/paper/37YMJASO"},"agent_actions":{"view_html":"https://pith.science/pith/37YMJASOOME3LTAFZYABKSSR3T","download_json":"https://pith.science/pith/37YMJASOOME3LTAFZYABKSSR3T.json","view_paper":"https://pith.science/paper/37YMJASO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.09248&json=true","fetch_graph":"https://pith.science/api/pith-number/37YMJASOOME3LTAFZYABKSSR3T/graph.json","fetch_events":"https://pith.science/api/pith-number/37YMJASOOME3LTAFZYABKSSR3T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/37YMJASOOME3LTAFZYABKSSR3T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/37YMJASOOME3LTAFZYABKSSR3T/action/storage_attestation","attest_author":"https://pith.science/pith/37YMJASOOME3LTAFZYABKSSR3T/action/author_attestation","sign_citation":"https://pith.science/pith/37YMJASOOME3LTAFZYABKSSR3T/action/citation_signature","submit_replication":"https://pith.science/pith/37YMJASOOME3LTAFZYABKSSR3T/action/replication_record"}},"created_at":"2026-07-05T02:50:14.110945+00:00","updated_at":"2026-07-05T02:50:14.110945+00:00"}