{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2NBZCLIRPQ7MORM4ACKEJPAIOP","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":"7cc557769a63e0756d5c4dd2c4b35d9d51f637c5a3e6aa350cb9035ba25200b9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-28T19:34:23Z","title_canon_sha256":"7a3b48d6bb678df9a19650a88ce828fdd87fd7acc31372c2dc6f4d174337bf4d"},"schema_version":"1.0","source":{"id":"2407.00211","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.00211","created_at":"2026-07-05T09:16:18Z"},{"alias_kind":"arxiv_version","alias_value":"2407.00211v2","created_at":"2026-07-05T09:16:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.00211","created_at":"2026-07-05T09:16:18Z"},{"alias_kind":"pith_short_12","alias_value":"2NBZCLIRPQ7M","created_at":"2026-07-05T09:16:18Z"},{"alias_kind":"pith_short_16","alias_value":"2NBZCLIRPQ7MORM4","created_at":"2026-07-05T09:16:18Z"},{"alias_kind":"pith_short_8","alias_value":"2NBZCLIR","created_at":"2026-07-05T09:16:18Z"}],"graph_snapshots":[{"event_id":"sha256:1c6f6943c78d5c78701420defdb646fc7669ff8ba9eaf509a9fca53ac88a3717","target":"graph","created_at":"2026-07-05T09:16:18Z","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/2407.00211/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent work on evaluating the diversity of text generated by LLMs has focused on word-level features. Here we offer an analysis of syntactic features to characterize general repetition in models, beyond frequent n-grams. Specifically, we define syntactic templates and show that models tend to produce templated text in downstream tasks at a higher rate than what is found in human-reference texts. We find that most (76%) templates in model-generated text can be found in pre-training data (compared to only 35% of human-authored text), and are not overwritten during fine-tuning processes such as R","authors_text":"Byron C. Wallace, Chantal Shaib, Junyi Jessy Li, Yanai Elazar","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-28T19:34:23Z","title":"Detection and Measurement of Syntactic Templates in Generated Text"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.00211","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":"sha256:64b5d2ed0e93bcbb85aa8442570fe0ba234c70f3599a950714d08ad031909b4a","target":"record","created_at":"2026-07-05T09:16:18Z","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":"7cc557769a63e0756d5c4dd2c4b35d9d51f637c5a3e6aa350cb9035ba25200b9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-28T19:34:23Z","title_canon_sha256":"7a3b48d6bb678df9a19650a88ce828fdd87fd7acc31372c2dc6f4d174337bf4d"},"schema_version":"1.0","source":{"id":"2407.00211","kind":"arxiv","version":2}},"canonical_sha256":"d343912d117c3ec7459c009444bc0873f299431482490c98af2ced82bd56cc0e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d343912d117c3ec7459c009444bc0873f299431482490c98af2ced82bd56cc0e","first_computed_at":"2026-07-05T09:16:18.953327Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:16:18.953327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tdApFoBFViXcevpP0uwQqP2s1ah9BoBrW/LhHFAp2JkydaCd7r/KuHLC7mCHy0Ne12gb5faMZqnBhYBUs1WPBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:16:18.953752Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.00211","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:64b5d2ed0e93bcbb85aa8442570fe0ba234c70f3599a950714d08ad031909b4a","sha256:1c6f6943c78d5c78701420defdb646fc7669ff8ba9eaf509a9fca53ac88a3717"],"state_sha256":"be23b0ff2ebf70c90d88aefa050ab29cc8a3c55295b76ba3dfe2a32e6acd92a7"}