{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:XSABBMGPDOG5K3ZHVMT552KCJ7","short_pith_number":"pith:XSABBMGP","schema_version":"1.0","canonical_sha256":"bc8010b0cf1b8dd56f27ab27dee9424ffd5bc0a2b31836e21ade41cf669a8f94","source":{"kind":"arxiv","id":"1608.04465","version":1},"attestation_state":"computed","paper":{"title":"Fast, Small and Exact: Infinite-order Language Modelling with Compressed Suffix Trees","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ehsan Shareghi, Gholamreza Haffari, Matthias Petri, Trevor Cohn","submitted_at":"2016-08-16T02:33:21Z","abstract_excerpt":"Efficient methods for storing and querying are critical for scaling high-order n-gram language models to large corpora. We propose a language model based on compressed suffix trees, a representation that is highly compact and can be easily held in memory, while supporting queries needed in computing language model probabilities on-the-fly. We present several optimisations which improve query runtimes up to 2500x, despite only incurring a modest increase in construction time and memory usage. For large corpora and high Markov orders, our method is highly competitive with the state-of-the-art Ke"},"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":"1608.04465","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-08-16T02:33:21Z","cross_cats_sorted":[],"title_canon_sha256":"358724f2dfe473d4d48873e3326515617c8dd4315916a809c60e3d0ec10c9860","abstract_canon_sha256":"436b7e9824eedf00a7061667634f0dd7af0236113a71c76ad7952d78a5d7e85d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:08:37.195430Z","signature_b64":"uOQ9zUjArNcjezEhEPEzJN9oPqmZJIzTFDzmtS90b53Z4eUBjZ0GgSRrAuMSSkrR51JrralLRcLXFVuZhmp+Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc8010b0cf1b8dd56f27ab27dee9424ffd5bc0a2b31836e21ade41cf669a8f94","last_reissued_at":"2026-05-18T01:08:37.194623Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:08:37.194623Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fast, Small and Exact: Infinite-order Language Modelling with Compressed Suffix Trees","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ehsan Shareghi, Gholamreza Haffari, Matthias Petri, Trevor Cohn","submitted_at":"2016-08-16T02:33:21Z","abstract_excerpt":"Efficient methods for storing and querying are critical for scaling high-order n-gram language models to large corpora. We propose a language model based on compressed suffix trees, a representation that is highly compact and can be easily held in memory, while supporting queries needed in computing language model probabilities on-the-fly. We present several optimisations which improve query runtimes up to 2500x, despite only incurring a modest increase in construction time and memory usage. For large corpora and high Markov orders, our method is highly competitive with the state-of-the-art Ke"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1608.04465","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1608.04465","created_at":"2026-05-18T01:08:37.194765+00:00"},{"alias_kind":"arxiv_version","alias_value":"1608.04465v1","created_at":"2026-05-18T01:08:37.194765+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.04465","created_at":"2026-05-18T01:08:37.194765+00:00"},{"alias_kind":"pith_short_12","alias_value":"XSABBMGPDOG5","created_at":"2026-05-18T12:30:51.357362+00:00"},{"alias_kind":"pith_short_16","alias_value":"XSABBMGPDOG5K3ZH","created_at":"2026-05-18T12:30:51.357362+00:00"},{"alias_kind":"pith_short_8","alias_value":"XSABBMGP","created_at":"2026-05-18T12:30:51.357362+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XSABBMGPDOG5K3ZHVMT552KCJ7","json":"https://pith.science/pith/XSABBMGPDOG5K3ZHVMT552KCJ7.json","graph_json":"https://pith.science/api/pith-number/XSABBMGPDOG5K3ZHVMT552KCJ7/graph.json","events_json":"https://pith.science/api/pith-number/XSABBMGPDOG5K3ZHVMT552KCJ7/events.json","paper":"https://pith.science/paper/XSABBMGP"},"agent_actions":{"view_html":"https://pith.science/pith/XSABBMGPDOG5K3ZHVMT552KCJ7","download_json":"https://pith.science/pith/XSABBMGPDOG5K3ZHVMT552KCJ7.json","view_paper":"https://pith.science/paper/XSABBMGP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1608.04465&json=true","fetch_graph":"https://pith.science/api/pith-number/XSABBMGPDOG5K3ZHVMT552KCJ7/graph.json","fetch_events":"https://pith.science/api/pith-number/XSABBMGPDOG5K3ZHVMT552KCJ7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XSABBMGPDOG5K3ZHVMT552KCJ7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XSABBMGPDOG5K3ZHVMT552KCJ7/action/storage_attestation","attest_author":"https://pith.science/pith/XSABBMGPDOG5K3ZHVMT552KCJ7/action/author_attestation","sign_citation":"https://pith.science/pith/XSABBMGPDOG5K3ZHVMT552KCJ7/action/citation_signature","submit_replication":"https://pith.science/pith/XSABBMGPDOG5K3ZHVMT552KCJ7/action/replication_record"}},"created_at":"2026-05-18T01:08:37.194765+00:00","updated_at":"2026-05-18T01:08:37.194765+00:00"}