{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZJIE7IH7JDYSHVTEB4CG2LIN73","short_pith_number":"pith:ZJIE7IH7","schema_version":"1.0","canonical_sha256":"ca504fa0ff48f123d6640f046d2d0dfed7220ebbae9c6189a25b3c11958e8070","source":{"kind":"arxiv","id":"2406.13069","version":4},"attestation_state":"computed","paper":{"title":"Evaluating $n$-Gram Novelty of Language Models Using Rusty-DAWG","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Noah A. Smith, William Merrill, Yanai Elazar","submitted_at":"2024-06-18T21:31:19Z","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"},"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":"2406.13069","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-18T21:31:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"323751428f342b6147879f49e50cb13a51d32359f90268ac7dddc1353417d32b","abstract_canon_sha256":"84c53a76f50fe7c9cac6e458794ec155773bc916b6d59a82779f4023e69c8887"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:57:52.940589Z","signature_b64":"5R3CKleS0HejWDOYZrZsmSXncFySIdQe25tFY+l2KxJ7hCU6rJkzE07UG4tRWlU3JCDigoj/ppt3OZ1y5OgWAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca504fa0ff48f123d6640f046d2d0dfed7220ebbae9c6189a25b3c11958e8070","last_reissued_at":"2026-07-05T11:57:52.940108Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:57:52.940108Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating $n$-Gram Novelty of Language Models Using Rusty-DAWG","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Noah A. Smith, William Merrill, Yanai Elazar","submitted_at":"2024-06-18T21:31:19Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.13069","kind":"arxiv","version":4},"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/2406.13069/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":"2406.13069","created_at":"2026-07-05T11:57:52.940163+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.13069v4","created_at":"2026-07-05T11:57:52.940163+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.13069","created_at":"2026-07-05T11:57:52.940163+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZJIE7IH7JDYS","created_at":"2026-07-05T11:57:52.940163+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZJIE7IH7JDYSHVTE","created_at":"2026-07-05T11:57:52.940163+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZJIE7IH7","created_at":"2026-07-05T11:57:52.940163+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.01844","citing_title":"Low-Perplexity LLM-Generated Sequences and Where To Find Them","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZJIE7IH7JDYSHVTEB4CG2LIN73","json":"https://pith.science/pith/ZJIE7IH7JDYSHVTEB4CG2LIN73.json","graph_json":"https://pith.science/api/pith-number/ZJIE7IH7JDYSHVTEB4CG2LIN73/graph.json","events_json":"https://pith.science/api/pith-number/ZJIE7IH7JDYSHVTEB4CG2LIN73/events.json","paper":"https://pith.science/paper/ZJIE7IH7"},"agent_actions":{"view_html":"https://pith.science/pith/ZJIE7IH7JDYSHVTEB4CG2LIN73","download_json":"https://pith.science/pith/ZJIE7IH7JDYSHVTEB4CG2LIN73.json","view_paper":"https://pith.science/paper/ZJIE7IH7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.13069&json=true","fetch_graph":"https://pith.science/api/pith-number/ZJIE7IH7JDYSHVTEB4CG2LIN73/graph.json","fetch_events":"https://pith.science/api/pith-number/ZJIE7IH7JDYSHVTEB4CG2LIN73/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZJIE7IH7JDYSHVTEB4CG2LIN73/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZJIE7IH7JDYSHVTEB4CG2LIN73/action/storage_attestation","attest_author":"https://pith.science/pith/ZJIE7IH7JDYSHVTEB4CG2LIN73/action/author_attestation","sign_citation":"https://pith.science/pith/ZJIE7IH7JDYSHVTEB4CG2LIN73/action/citation_signature","submit_replication":"https://pith.science/pith/ZJIE7IH7JDYSHVTEB4CG2LIN73/action/replication_record"}},"created_at":"2026-07-05T11:57:52.940163+00:00","updated_at":"2026-07-05T11:57:52.940163+00:00"}