{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:N2L5ADO3K2OCS4Q67FHNM5RHXT","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":"ea3f1a572289fbfd7ef9cd7165216e15a732b612d550c5619c9b65a7341dca82","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-12T17:37:17Z","title_canon_sha256":"196cb603e86fcfd4e082ddca5f46c829794da04182d29e4ef1a0117f3dfaf5f6"},"schema_version":"1.0","source":{"id":"2505.07784","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.07784","created_at":"2026-07-05T11:14:07Z"},{"alias_kind":"arxiv_version","alias_value":"2505.07784v2","created_at":"2026-07-05T11:14:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07784","created_at":"2026-07-05T11:14:07Z"},{"alias_kind":"pith_short_12","alias_value":"N2L5ADO3K2OC","created_at":"2026-07-05T11:14:07Z"},{"alias_kind":"pith_short_16","alias_value":"N2L5ADO3K2OCS4Q6","created_at":"2026-07-05T11:14:07Z"},{"alias_kind":"pith_short_8","alias_value":"N2L5ADO3","created_at":"2026-07-05T11:14:07Z"}],"graph_snapshots":[{"event_id":"sha256:266dda0c6aa81c90399e1507fd683ef8f9dce4a364a4533b4aafa37f307ff618","target":"graph","created_at":"2026-07-05T11:14:07Z","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/2505.07784/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent improvement in large language model performance have, in all likelihood, been accompanied by improvement in how well they can approximate the distribution of their training data. In this work, we explore the following question: which properties of text domains do LLMs faithfully approximate, and how well do they do so? Applying observational approaches familiar from corpus linguistics, we prompt a commonly used, opensource LLM to regenerate text from two domains of permissively licensed English text which are often contained in LLM training data -- Wikipedia and news text. This regenera","authors_text":"Adina Williams, Da Ju, Hagen Blix","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-12T17:37:17Z","title":"Domain Regeneration: How well do LLMs match syntactic properties of text domains?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07784","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":"sha256:6aaced71441c939a532ed85e799b8191ba5a4efe2787b038819dab13262506c4","target":"record","created_at":"2026-07-05T11:14:07Z","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":"ea3f1a572289fbfd7ef9cd7165216e15a732b612d550c5619c9b65a7341dca82","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-12T17:37:17Z","title_canon_sha256":"196cb603e86fcfd4e082ddca5f46c829794da04182d29e4ef1a0117f3dfaf5f6"},"schema_version":"1.0","source":{"id":"2505.07784","kind":"arxiv","version":2}},"canonical_sha256":"6e97d00ddb569c29721ef94ed67627bcf770070f6fd1c0bc45feaedc2529268e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6e97d00ddb569c29721ef94ed67627bcf770070f6fd1c0bc45feaedc2529268e","first_computed_at":"2026-07-05T11:14:07.284181Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:14:07.284181Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zgB1LAGQKSm3b/EsvOlD40NrHQH+AIXcXjIcOOe85PVccBJfirZVUgxgJDBqEHqw0+JZTlmf3Hc10kE4daHXDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:14:07.284674Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.07784","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6aaced71441c939a532ed85e799b8191ba5a4efe2787b038819dab13262506c4","sha256:266dda0c6aa81c90399e1507fd683ef8f9dce4a364a4533b4aafa37f307ff618"],"state_sha256":"5ebefae835e715d353d5c27fbb4d7eb4a745a29e0a725eaf2bc26d3399ba6f47"}