{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:HPBQ3PK4MVN3BWIPEEUYJKEPDG","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":"93a8c6be45f9cfdb1c32c34a21ab3383713e3026646ac4937c76f529d03c1a48","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-04-13T12:39:41Z","title_canon_sha256":"86c495c8834c060b5653a5373756a7c66df9a197b9e96744ba3d5fb1d7ee9abc"},"schema_version":"1.0","source":{"id":"1404.3377","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1404.3377","created_at":"2026-05-18T02:54:15Z"},{"alias_kind":"arxiv_version","alias_value":"1404.3377v1","created_at":"2026-05-18T02:54:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1404.3377","created_at":"2026-05-18T02:54:15Z"},{"alias_kind":"pith_short_12","alias_value":"HPBQ3PK4MVN3","created_at":"2026-05-18T12:28:30Z"},{"alias_kind":"pith_short_16","alias_value":"HPBQ3PK4MVN3BWIP","created_at":"2026-05-18T12:28:30Z"},{"alias_kind":"pith_short_8","alias_value":"HPBQ3PK4","created_at":"2026-05-18T12:28:30Z"}],"graph_snapshots":[{"event_id":"sha256:0a37417955a86d464db74867cb038e3082a1551530d18e9148d91119ce04370e","target":"graph","created_at":"2026-05-18T02:54:15Z","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"},"paper":{"abstract_excerpt":"We introduce a novel approach for building language models based on a systematic, recursive exploration of skip n-gram models which are interpolated using modified Kneser-Ney smoothing. Our approach generalizes language models as it contains the classical interpolation with lower order models as a special case. In this paper we motivate, formalize and present our approach. In an extensive empirical experiment over English text corpora we demonstrate that our generalized language models lead to a substantial reduction of perplexity between 3.1% and 12.7% in comparison to traditional language mo","authors_text":"Martin K\\\"orner, Paul Georg Wagner, Rene Pickhardt, Steffen Staab, Thomas Gottron, Till Speicher","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-04-13T12:39:41Z","title":"A Generalized Language Model as the Combination of Skipped n-grams and Modified Kneser-Ney Smoothing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1404.3377","kind":"arxiv","version":1},"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":"sha256:2f2450833651c4176048f209402e023265656f1e15636222e2aa818c5dd3ccc7","target":"record","created_at":"2026-05-18T02:54:15Z","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":"93a8c6be45f9cfdb1c32c34a21ab3383713e3026646ac4937c76f529d03c1a48","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-04-13T12:39:41Z","title_canon_sha256":"86c495c8834c060b5653a5373756a7c66df9a197b9e96744ba3d5fb1d7ee9abc"},"schema_version":"1.0","source":{"id":"1404.3377","kind":"arxiv","version":1}},"canonical_sha256":"3bc30dbd5c655bb0d90f212984a88f19af21809315796124eb3c70445d45c5c6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3bc30dbd5c655bb0d90f212984a88f19af21809315796124eb3c70445d45c5c6","first_computed_at":"2026-05-18T02:54:15.310039Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:54:15.310039Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3ohPVCk/FYWW3kmCIBxqxLvWtHXFj1w9qq6HfDg50rCqdj/VDtVktRfnI0NtjrJfZZ4qdACJbxzxDpu/ECxwDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T02:54:15.310538Z","signed_message":"canonical_sha256_bytes"},"source_id":"1404.3377","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2f2450833651c4176048f209402e023265656f1e15636222e2aa818c5dd3ccc7","sha256:0a37417955a86d464db74867cb038e3082a1551530d18e9148d91119ce04370e"],"state_sha256":"950e6d0b8bd3eb7f0ec68b5e5d518ab1d3b2b66bdeed1639231ca0ea73471309"}