{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5KDKFQLXYCRTBLWMPN5YEYO3JA","short_pith_number":"pith:5KDKFQLX","schema_version":"1.0","canonical_sha256":"ea86a2c177c0a330aecc7b7b8261db480fff8c972990f00e06e4af95f6c15429","source":{"kind":"arxiv","id":"2505.18136","version":1},"attestation_state":"computed","paper":{"title":"Graph-Linguistic Fusion: Using Language Models for Wikidata Vandalism Detection","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Diego Saez-Trumper, Lydia Pintscher, Mykola Trokhymovych, Ricardo Baeza-Yates","submitted_at":"2025-05-23T17:44:06Z","abstract_excerpt":"We introduce a next-generation vandalism detection system for Wikidata, one of the largest open-source structured knowledge bases on the Web. Wikidata is highly complex: its items incorporate an ever-expanding universe of factual triples and multilingual texts. While edits can alter both structured and textual content, our approach converts all edits into a single space using a method we call Graph2Text. This allows for evaluating all content changes for potential vandalism using a single multilingual language model. This unified approach improves coverage and simplifies maintenance. Experimen"},"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":"2505.18136","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-23T17:44:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9e07640998f5ef981d2f1da0495c487810adbfe96bf1b0a2c0c51030eccbafa1","abstract_canon_sha256":"ed3d7c6c542a809e0bcb17f74673fd2ea29a813583ece98aebea1b06226f273c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:37.023159Z","signature_b64":"fKfgxWWOFX2bICXCk/wx5lElNR5mHVozhF1spxhgIfHDbQlAFVhbKSOtZKvD7szNUqRV/5rn3RvT6O1fRjDGAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea86a2c177c0a330aecc7b7b8261db480fff8c972990f00e06e4af95f6c15429","last_reissued_at":"2026-07-05T11:08:37.022696Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:37.022696Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Graph-Linguistic Fusion: Using Language Models for Wikidata Vandalism Detection","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Diego Saez-Trumper, Lydia Pintscher, Mykola Trokhymovych, Ricardo Baeza-Yates","submitted_at":"2025-05-23T17:44:06Z","abstract_excerpt":"We introduce a next-generation vandalism detection system for Wikidata, one of the largest open-source structured knowledge bases on the Web. Wikidata is highly complex: its items incorporate an ever-expanding universe of factual triples and multilingual texts. While edits can alter both structured and textual content, our approach converts all edits into a single space using a method we call Graph2Text. This allows for evaluating all content changes for potential vandalism using a single multilingual language model. This unified approach improves coverage and simplifies maintenance. Experimen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18136","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/2505.18136/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":"2505.18136","created_at":"2026-07-05T11:08:37.022750+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.18136v1","created_at":"2026-07-05T11:08:37.022750+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18136","created_at":"2026-07-05T11:08:37.022750+00:00"},{"alias_kind":"pith_short_12","alias_value":"5KDKFQLXYCRT","created_at":"2026-07-05T11:08:37.022750+00:00"},{"alias_kind":"pith_short_16","alias_value":"5KDKFQLXYCRTBLWM","created_at":"2026-07-05T11:08:37.022750+00:00"},{"alias_kind":"pith_short_8","alias_value":"5KDKFQLX","created_at":"2026-07-05T11:08:37.022750+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/5KDKFQLXYCRTBLWMPN5YEYO3JA","json":"https://pith.science/pith/5KDKFQLXYCRTBLWMPN5YEYO3JA.json","graph_json":"https://pith.science/api/pith-number/5KDKFQLXYCRTBLWMPN5YEYO3JA/graph.json","events_json":"https://pith.science/api/pith-number/5KDKFQLXYCRTBLWMPN5YEYO3JA/events.json","paper":"https://pith.science/paper/5KDKFQLX"},"agent_actions":{"view_html":"https://pith.science/pith/5KDKFQLXYCRTBLWMPN5YEYO3JA","download_json":"https://pith.science/pith/5KDKFQLXYCRTBLWMPN5YEYO3JA.json","view_paper":"https://pith.science/paper/5KDKFQLX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.18136&json=true","fetch_graph":"https://pith.science/api/pith-number/5KDKFQLXYCRTBLWMPN5YEYO3JA/graph.json","fetch_events":"https://pith.science/api/pith-number/5KDKFQLXYCRTBLWMPN5YEYO3JA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5KDKFQLXYCRTBLWMPN5YEYO3JA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5KDKFQLXYCRTBLWMPN5YEYO3JA/action/storage_attestation","attest_author":"https://pith.science/pith/5KDKFQLXYCRTBLWMPN5YEYO3JA/action/author_attestation","sign_citation":"https://pith.science/pith/5KDKFQLXYCRTBLWMPN5YEYO3JA/action/citation_signature","submit_replication":"https://pith.science/pith/5KDKFQLXYCRTBLWMPN5YEYO3JA/action/replication_record"}},"created_at":"2026-07-05T11:08:37.022750+00:00","updated_at":"2026-07-05T11:08:37.022750+00:00"}