{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:YWM3Q7CHKXUGCTTDVXUXOO5ECK","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":"98af56cf09139db90dd4d2f1feca1d4f5097557633fbe464c7aabaca57cfbe85","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-23T22:14:50Z","title_canon_sha256":"9e1ac86870bbcb5cf277cf25796fbbed95c0bcb98ba2219138923280cdd06857"},"schema_version":"1.0","source":{"id":"2010.12688","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.12688","created_at":"2026-07-05T02:22:38Z"},{"alias_kind":"arxiv_version","alias_value":"2010.12688v2","created_at":"2026-07-05T02:22:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.12688","created_at":"2026-07-05T02:22:38Z"},{"alias_kind":"pith_short_12","alias_value":"YWM3Q7CHKXUG","created_at":"2026-07-05T02:22:38Z"},{"alias_kind":"pith_short_16","alias_value":"YWM3Q7CHKXUGCTTD","created_at":"2026-07-05T02:22:38Z"},{"alias_kind":"pith_short_8","alias_value":"YWM3Q7CH","created_at":"2026-07-05T02:22:38Z"}],"graph_snapshots":[{"event_id":"sha256:c1b0d9f68aea59b4cf2c40536e3d0e001a278dccfc03e4830379c4b6aaf3f32c","target":"graph","created_at":"2026-07-05T02:22:38Z","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/2010.12688/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Prior work on Data-To-Text Generation, the task of converting knowledge graph (KG) triples into natural text, focused on domain-specific benchmark datasets. In this paper, however, we verbalize the entire English Wikidata KG, and discuss the unique challenges associated with a broad, open-domain, large-scale verbalization. We further show that verbalizing a comprehensive, encyclopedic KG like Wikidata can be used to integrate structured KGs and natural language corpora. In contrast to the many architectures that have been developed to integrate these two sources, our approach converts the KG i","authors_text":"Heming Ge, Oshin Agarwal, Rami Al-Rfou, Siamak Shakeri","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-23T22:14:50Z","title":"Knowledge Graph Based Synthetic Corpus Generation for Knowledge-Enhanced Language Model Pre-training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.12688","kind":"arxiv","version":2},"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:e77545e646590383d5a91b752c24d070555c59ecf618e59c290e956f205b9a57","target":"record","created_at":"2026-07-05T02:22:38Z","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":"98af56cf09139db90dd4d2f1feca1d4f5097557633fbe464c7aabaca57cfbe85","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-23T22:14:50Z","title_canon_sha256":"9e1ac86870bbcb5cf277cf25796fbbed95c0bcb98ba2219138923280cdd06857"},"schema_version":"1.0","source":{"id":"2010.12688","kind":"arxiv","version":2}},"canonical_sha256":"c599b87c4755e8614e63ade9773ba412b114fb837671d8c6a31af18eb2c29c7f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c599b87c4755e8614e63ade9773ba412b114fb837671d8c6a31af18eb2c29c7f","first_computed_at":"2026-07-05T02:22:38.961311Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:22:38.961311Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gZOmYs4keqsRKjj9iB5l/U4Pn76ZB90D+vjsTh/OD8sXDiKnJSYhSDsOGYZn5cy+uKCdv+Hthk4Ham20SDbEAw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:22:38.961849Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.12688","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e77545e646590383d5a91b752c24d070555c59ecf618e59c290e956f205b9a57","sha256:c1b0d9f68aea59b4cf2c40536e3d0e001a278dccfc03e4830379c4b6aaf3f32c"],"state_sha256":"d61ba86b086f1b617254dd10fd178341cc197fe8327d0c4f0dd20bdbaf23dd09"}