{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:O4UE5MLXHPLEMVDH55MNUSPPSX","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":"9077545182495bcd81f32d290f2129febd5a4ca5fb4a48e8bdc3e2693080c1f9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-26T02:42:53Z","title_canon_sha256":"54674eeed6a48b7018ace225f4985ad94c7160a426381144970e3dab2e6affba"},"schema_version":"1.0","source":{"id":"2210.14431","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.14431","created_at":"2026-07-05T05:12:54Z"},{"alias_kind":"arxiv_version","alias_value":"2210.14431v3","created_at":"2026-07-05T05:12:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.14431","created_at":"2026-07-05T05:12:54Z"},{"alias_kind":"pith_short_12","alias_value":"O4UE5MLXHPLE","created_at":"2026-07-05T05:12:54Z"},{"alias_kind":"pith_short_16","alias_value":"O4UE5MLXHPLEMVDH","created_at":"2026-07-05T05:12:54Z"},{"alias_kind":"pith_short_8","alias_value":"O4UE5MLX","created_at":"2026-07-05T05:12:54Z"}],"graph_snapshots":[{"event_id":"sha256:5942b25b833ced238dd4797c5614017f24402d84b421b0e3428fe61e7f2b3d3c","target":"graph","created_at":"2026-07-05T05:12:54Z","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/2210.14431/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"$N$-gram language models (LM) have been largely superseded by neural LMs as the latter exhibits better performance. However, we find that $n$-gram models can achieve satisfactory performance on a large proportion of testing cases, indicating they have already captured abundant knowledge of the language with relatively low computational cost. With this observation, we propose to learn a neural LM that fits the residual between an $n$-gram LM and the real-data distribution. The combination of $n$-gram and neural LMs not only allows the neural part to focus on the deeper understanding of language","authors_text":"Deng Cai, Huayang Li, Jin Xu, Taro Watanabe","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-26T02:42:53Z","title":"$N$-gram Is Back: Residual Learning of Neural Text Generation with $n$-gram Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.14431","kind":"arxiv","version":3},"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":"sha256:26eb86b79cbfdb1391f65cfc9b7aeb669381ef18ea7802eea069da92d9a148db","target":"record","created_at":"2026-07-05T05:12:54Z","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":"9077545182495bcd81f32d290f2129febd5a4ca5fb4a48e8bdc3e2693080c1f9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-26T02:42:53Z","title_canon_sha256":"54674eeed6a48b7018ace225f4985ad94c7160a426381144970e3dab2e6affba"},"schema_version":"1.0","source":{"id":"2210.14431","kind":"arxiv","version":3}},"canonical_sha256":"77284eb1773bd6465467ef58da49ef95cacf6db8d37c0a0074e5b156d50a9c2f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"77284eb1773bd6465467ef58da49ef95cacf6db8d37c0a0074e5b156d50a9c2f","first_computed_at":"2026-07-05T05:12:54.692496Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:12:54.692496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aHzx+eRPexc5bBk8E2XoL5AQHdedf4rnNpCpZMdv2EOcFnruD8hqefCDhCTbhx0ZDHVyfMJL1E73DML90SgEBw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:12:54.692979Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.14431","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:26eb86b79cbfdb1391f65cfc9b7aeb669381ef18ea7802eea069da92d9a148db","sha256:5942b25b833ced238dd4797c5614017f24402d84b421b0e3428fe61e7f2b3d3c"],"state_sha256":"ba411c86b6b27578759e37d70c2478328026d8927aae56e51268f5dcfffd1339"}