{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:MWFE5TYARYFZCXFBW22XIDRFJ6","short_pith_number":"pith:MWFE5TYA","schema_version":"1.0","canonical_sha256":"658a4ecf008e0b915ca1b6b5740e254f80519dc26861bb7268f718281c39e7a3","source":{"kind":"arxiv","id":"1803.08240","version":1},"attestation_state":"computed","paper":{"title":"An Analysis of Neural Language Modeling at Multiple Scales","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.CL","authors_text":"Nitish Shirish Keskar, Richard Socher, Stephen Merity","submitted_at":"2018-03-22T06:25:47Z","abstract_excerpt":"Many of the leading approaches in language modeling introduce novel, complex and specialized architectures. We take existing state-of-the-art word level language models based on LSTMs and QRNNs and extend them to both larger vocabularies as well as character-level granularity. When properly tuned, LSTMs and QRNNs achieve state-of-the-art results on character-level (Penn Treebank, enwik8) and word-level (WikiText-103) datasets, respectively. Results are obtained in only 12 hours (WikiText-103) to 2 days (enwik8) using a single modern GPU."},"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":"1803.08240","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-03-22T06:25:47Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"da63ebfdfa89131993d723492dd79dd6ddd210bcfb4e779b0e2134d3345b20ae","abstract_canon_sha256":"f6d74de7f6c7e18a2eba544088de7364d46c047c80f00733b8771d8b00120318"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:23.332495Z","signature_b64":"g4tIwFhVanfrVgxQIBVcoccl6hk0iL/lSWaLC9r9atGaTxFiPGBjJeSQuMFId/RtznN1iNz28SBk1DCTSEq8Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"658a4ecf008e0b915ca1b6b5740e254f80519dc26861bb7268f718281c39e7a3","last_reissued_at":"2026-05-18T00:20:23.331919Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:23.331919Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Analysis of Neural Language Modeling at Multiple Scales","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.CL","authors_text":"Nitish Shirish Keskar, Richard Socher, Stephen Merity","submitted_at":"2018-03-22T06:25:47Z","abstract_excerpt":"Many of the leading approaches in language modeling introduce novel, complex and specialized architectures. We take existing state-of-the-art word level language models based on LSTMs and QRNNs and extend them to both larger vocabularies as well as character-level granularity. When properly tuned, LSTMs and QRNNs achieve state-of-the-art results on character-level (Penn Treebank, enwik8) and word-level (WikiText-103) datasets, respectively. Results are obtained in only 12 hours (WikiText-103) to 2 days (enwik8) using a single modern GPU."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.08240","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":"1803.08240","created_at":"2026-05-18T00:20:23.332014+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.08240v1","created_at":"2026-05-18T00:20:23.332014+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.08240","created_at":"2026-05-18T00:20:23.332014+00:00"},{"alias_kind":"pith_short_12","alias_value":"MWFE5TYARYFZ","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_16","alias_value":"MWFE5TYARYFZCXFB","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_8","alias_value":"MWFE5TYA","created_at":"2026-05-18T12:32:40.477152+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1906.09379","citing_title":"Evaluating Computational Language Models with Scaling Properties of Natural Language","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"1907.01470","citing_title":"Augmenting Self-attention with Persistent Memory","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MWFE5TYARYFZCXFBW22XIDRFJ6","json":"https://pith.science/pith/MWFE5TYARYFZCXFBW22XIDRFJ6.json","graph_json":"https://pith.science/api/pith-number/MWFE5TYARYFZCXFBW22XIDRFJ6/graph.json","events_json":"https://pith.science/api/pith-number/MWFE5TYARYFZCXFBW22XIDRFJ6/events.json","paper":"https://pith.science/paper/MWFE5TYA"},"agent_actions":{"view_html":"https://pith.science/pith/MWFE5TYARYFZCXFBW22XIDRFJ6","download_json":"https://pith.science/pith/MWFE5TYARYFZCXFBW22XIDRFJ6.json","view_paper":"https://pith.science/paper/MWFE5TYA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.08240&json=true","fetch_graph":"https://pith.science/api/pith-number/MWFE5TYARYFZCXFBW22XIDRFJ6/graph.json","fetch_events":"https://pith.science/api/pith-number/MWFE5TYARYFZCXFBW22XIDRFJ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MWFE5TYARYFZCXFBW22XIDRFJ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MWFE5TYARYFZCXFBW22XIDRFJ6/action/storage_attestation","attest_author":"https://pith.science/pith/MWFE5TYARYFZCXFBW22XIDRFJ6/action/author_attestation","sign_citation":"https://pith.science/pith/MWFE5TYARYFZCXFBW22XIDRFJ6/action/citation_signature","submit_replication":"https://pith.science/pith/MWFE5TYARYFZCXFBW22XIDRFJ6/action/replication_record"}},"created_at":"2026-05-18T00:20:23.332014+00:00","updated_at":"2026-05-18T00:20:23.332014+00:00"}