{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:SRBDZ7XBFLIRK2EM57IPDYWSAF","short_pith_number":"pith:SRBDZ7XB","schema_version":"1.0","canonical_sha256":"94423cfee12ad115688cefd0f1e2d20178295ad2e1c78b12469b31d0a71c0989","source":{"kind":"arxiv","id":"1704.06986","version":1},"attestation_state":"computed","paper":{"title":"Learning to Create and Reuse Words in Open-Vocabulary Neural Language Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chris Dyer, Kazuya Kawakami, Phil Blunsom","submitted_at":"2017-04-23T21:31:22Z","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"},"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":"1704.06986","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-04-23T21:31:22Z","cross_cats_sorted":[],"title_canon_sha256":"8c334a8d1924a9e73a4487b54db5359619ff8ab63830b79ee3ab6a6376c735d1","abstract_canon_sha256":"3b8efb54d2c48c0f6cdcdba99b061d02576df008caeb664a1612f9e17f452eb8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:45:55.115433Z","signature_b64":"JQ6xK73O/8bdO/ytMTpsKrHot8012dZ3fojvJwKH5aXTiVImTMTRyW/Ntj9+IrYGH/ZO00hjpUkw10STO0DHBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94423cfee12ad115688cefd0f1e2d20178295ad2e1c78b12469b31d0a71c0989","last_reissued_at":"2026-05-18T00:45:55.114731Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:45:55.114731Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Create and Reuse Words in Open-Vocabulary Neural Language Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chris Dyer, Kazuya Kawakami, Phil Blunsom","submitted_at":"2017-04-23T21:31:22Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.06986","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":"1704.06986","created_at":"2026-05-18T00:45:55.114855+00:00"},{"alias_kind":"arxiv_version","alias_value":"1704.06986v1","created_at":"2026-05-18T00:45:55.114855+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.06986","created_at":"2026-05-18T00:45:55.114855+00:00"},{"alias_kind":"pith_short_12","alias_value":"SRBDZ7XBFLIR","created_at":"2026-05-18T12:31:43.269735+00:00"},{"alias_kind":"pith_short_16","alias_value":"SRBDZ7XBFLIRK2EM","created_at":"2026-05-18T12:31:43.269735+00:00"},{"alias_kind":"pith_short_8","alias_value":"SRBDZ7XB","created_at":"2026-05-18T12:31:43.269735+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1911.05507","citing_title":"Compressive Transformers for Long-Range Sequence Modelling","ref_index":65,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SRBDZ7XBFLIRK2EM57IPDYWSAF","json":"https://pith.science/pith/SRBDZ7XBFLIRK2EM57IPDYWSAF.json","graph_json":"https://pith.science/api/pith-number/SRBDZ7XBFLIRK2EM57IPDYWSAF/graph.json","events_json":"https://pith.science/api/pith-number/SRBDZ7XBFLIRK2EM57IPDYWSAF/events.json","paper":"https://pith.science/paper/SRBDZ7XB"},"agent_actions":{"view_html":"https://pith.science/pith/SRBDZ7XBFLIRK2EM57IPDYWSAF","download_json":"https://pith.science/pith/SRBDZ7XBFLIRK2EM57IPDYWSAF.json","view_paper":"https://pith.science/paper/SRBDZ7XB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1704.06986&json=true","fetch_graph":"https://pith.science/api/pith-number/SRBDZ7XBFLIRK2EM57IPDYWSAF/graph.json","fetch_events":"https://pith.science/api/pith-number/SRBDZ7XBFLIRK2EM57IPDYWSAF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SRBDZ7XBFLIRK2EM57IPDYWSAF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SRBDZ7XBFLIRK2EM57IPDYWSAF/action/storage_attestation","attest_author":"https://pith.science/pith/SRBDZ7XBFLIRK2EM57IPDYWSAF/action/author_attestation","sign_citation":"https://pith.science/pith/SRBDZ7XBFLIRK2EM57IPDYWSAF/action/citation_signature","submit_replication":"https://pith.science/pith/SRBDZ7XBFLIRK2EM57IPDYWSAF/action/replication_record"}},"created_at":"2026-05-18T00:45:55.114855+00:00","updated_at":"2026-05-18T00:45:55.114855+00:00"}