{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:SRBDZ7XBFLIRK2EM57IPDYWSAF","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":"3b8efb54d2c48c0f6cdcdba99b061d02576df008caeb664a1612f9e17f452eb8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-04-23T21:31:22Z","title_canon_sha256":"8c334a8d1924a9e73a4487b54db5359619ff8ab63830b79ee3ab6a6376c735d1"},"schema_version":"1.0","source":{"id":"1704.06986","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.06986","created_at":"2026-05-18T00:45:55Z"},{"alias_kind":"arxiv_version","alias_value":"1704.06986v1","created_at":"2026-05-18T00:45:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.06986","created_at":"2026-05-18T00:45:55Z"},{"alias_kind":"pith_short_12","alias_value":"SRBDZ7XBFLIR","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_16","alias_value":"SRBDZ7XBFLIRK2EM","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_8","alias_value":"SRBDZ7XB","created_at":"2026-05-18T12:31:43Z"}],"graph_snapshots":[{"event_id":"sha256:2204bc4d9cafe7c2d4ce71f0b672041b63dbe4893f21f5f8c482ce5ef0d83667","target":"graph","created_at":"2026-05-18T00:45:55Z","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":"Fixed-vocabulary language models fail to account for one of the most characteristic statistical facts of natural language: the frequent creation and reuse of new word types. Although character-level language models offer a partial solution in that they can create word types not attested in the training corpus, they do not capture the \"bursty\" distribution of such words. In this paper, we augment a hierarchical LSTM language model that generates sequences of word tokens character by character with a caching mechanism that learns to reuse previously generated words. To validate our model we cons","authors_text":"Chris Dyer, Kazuya Kawakami, Phil Blunsom","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-04-23T21:31:22Z","title":"Learning to Create and Reuse Words in Open-Vocabulary Neural Language Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.06986","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:b87c59b17ea9e717b65156c83c9b7b125aacc3c5df91b875cd86e177fe31ffd0","target":"record","created_at":"2026-05-18T00:45:55Z","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":"3b8efb54d2c48c0f6cdcdba99b061d02576df008caeb664a1612f9e17f452eb8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-04-23T21:31:22Z","title_canon_sha256":"8c334a8d1924a9e73a4487b54db5359619ff8ab63830b79ee3ab6a6376c735d1"},"schema_version":"1.0","source":{"id":"1704.06986","kind":"arxiv","version":1}},"canonical_sha256":"94423cfee12ad115688cefd0f1e2d20178295ad2e1c78b12469b31d0a71c0989","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"94423cfee12ad115688cefd0f1e2d20178295ad2e1c78b12469b31d0a71c0989","first_computed_at":"2026-05-18T00:45:55.114731Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:45:55.114731Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JQ6xK73O/8bdO/ytMTpsKrHot8012dZ3fojvJwKH5aXTiVImTMTRyW/Ntj9+IrYGH/ZO00hjpUkw10STO0DHBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:45:55.115433Z","signed_message":"canonical_sha256_bytes"},"source_id":"1704.06986","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b87c59b17ea9e717b65156c83c9b7b125aacc3c5df91b875cd86e177fe31ffd0","sha256:2204bc4d9cafe7c2d4ce71f0b672041b63dbe4893f21f5f8c482ce5ef0d83667"],"state_sha256":"f87f23f57dc2f70b2feaea916fcb6767fddbc37d9efd831f0c1e7a2227196b41"}