{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZJIE7IH7JDYSHVTEB4CG2LIN73","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":"84c53a76f50fe7c9cac6e458794ec155773bc916b6d59a82779f4023e69c8887","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-18T21:31:19Z","title_canon_sha256":"323751428f342b6147879f49e50cb13a51d32359f90268ac7dddc1353417d32b"},"schema_version":"1.0","source":{"id":"2406.13069","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.13069","created_at":"2026-07-05T11:57:52Z"},{"alias_kind":"arxiv_version","alias_value":"2406.13069v4","created_at":"2026-07-05T11:57:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.13069","created_at":"2026-07-05T11:57:52Z"},{"alias_kind":"pith_short_12","alias_value":"ZJIE7IH7JDYS","created_at":"2026-07-05T11:57:52Z"},{"alias_kind":"pith_short_16","alias_value":"ZJIE7IH7JDYSHVTE","created_at":"2026-07-05T11:57:52Z"},{"alias_kind":"pith_short_8","alias_value":"ZJIE7IH7","created_at":"2026-07-05T11:57:52Z"}],"graph_snapshots":[{"event_id":"sha256:9c315b904c14a1659cfc50c3b7f738e88039a5acd355c7c472298288abf4e12a","target":"graph","created_at":"2026-07-05T11:57:52Z","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/2406.13069/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"How novel are texts generated by language models (LMs) relative to their training corpora? In this work, we investigate the extent to which modern LMs generate $n$-grams from their training data, evaluating both (i) the probability LMs assign to complete training $n$-grams and (ii) $n$-novelty, the proportion of $n$-grams generated by an LM that did not appear in the training data (for arbitrarily large $n$). To enable arbitrary-length $n$-gram search over a corpus in constant time w.r.t. corpus size, we develop Rusty-DAWG, a novel search tool inspired by indexing of genomic data. We compare t","authors_text":"Noah A. Smith, William Merrill, Yanai Elazar","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-18T21:31:19Z","title":"Evaluating $n$-Gram Novelty of Language Models Using Rusty-DAWG"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.13069","kind":"arxiv","version":4},"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:d5d34fc8bf65e7704d30f837fc047e7440c2b69c3245706211c163836a20e12c","target":"record","created_at":"2026-07-05T11:57:52Z","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":"84c53a76f50fe7c9cac6e458794ec155773bc916b6d59a82779f4023e69c8887","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-18T21:31:19Z","title_canon_sha256":"323751428f342b6147879f49e50cb13a51d32359f90268ac7dddc1353417d32b"},"schema_version":"1.0","source":{"id":"2406.13069","kind":"arxiv","version":4}},"canonical_sha256":"ca504fa0ff48f123d6640f046d2d0dfed7220ebbae9c6189a25b3c11958e8070","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ca504fa0ff48f123d6640f046d2d0dfed7220ebbae9c6189a25b3c11958e8070","first_computed_at":"2026-07-05T11:57:52.940108Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:57:52.940108Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5R3CKleS0HejWDOYZrZsmSXncFySIdQe25tFY+l2KxJ7hCU6rJkzE07UG4tRWlU3JCDigoj/ppt3OZ1y5OgWAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:57:52.940589Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.13069","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d5d34fc8bf65e7704d30f837fc047e7440c2b69c3245706211c163836a20e12c","sha256:9c315b904c14a1659cfc50c3b7f738e88039a5acd355c7c472298288abf4e12a"],"state_sha256":"fb63286232431868afedc21415ea1d6615b68c45bebd80fa212627a9b4ef91c9"}