{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:CLHKTBRW3PAJ2MTUDGSTHAP5HC","short_pith_number":"pith:CLHKTBRW","schema_version":"1.0","canonical_sha256":"12cea98636dbc09d327419a53381fd38b47eade131b49f7cecbebc131d952757","source":{"kind":"arxiv","id":"1808.07910","version":1},"attestation_state":"computed","paper":{"title":"The Importance of Generation Order in Language Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel Duckworth, George E. Dahl, Mohammad Norouzi, Nicolas Ford","submitted_at":"2018-08-23T19:17:24Z","abstract_excerpt":"Neural language models are a critical component of state-of-the-art systems for machine translation, summarization, audio transcription, and other tasks. These language models are almost universally autoregressive in nature, generating sentences one token at a time from left to right. This paper studies the influence of token generation order on model quality via a novel two-pass language model that produces partially-filled sentence \"templates\" and then fills in missing tokens. We compare various strategies for structuring these two passes and observe a surprisingly large variation in model q"},"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":"1808.07910","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-23T19:17:24Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"2a0dd8a6f5deaae6ccf5f851af2ec7887e53bf8d0db941d97817628e0030ec19","abstract_canon_sha256":"5e1771ddc65bbd7ce490b87ec1b1016a934b3c1a9cc8565a59dd64ec671d7d35"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:07:23.031349Z","signature_b64":"I9xAYNidmouFi0NlVNJFmcX/QUqDQTGSNihIGVA71P0oiiIG9Gh6IVnvNiD4JiHWcvvZkJRx8THJXr0N3ARsBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12cea98636dbc09d327419a53381fd38b47eade131b49f7cecbebc131d952757","last_reissued_at":"2026-05-18T00:07:23.030932Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:07:23.030932Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Importance of Generation Order in Language Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel Duckworth, George E. Dahl, Mohammad Norouzi, Nicolas Ford","submitted_at":"2018-08-23T19:17:24Z","abstract_excerpt":"Neural language models are a critical component of state-of-the-art systems for machine translation, summarization, audio transcription, and other tasks. These language models are almost universally autoregressive in nature, generating sentences one token at a time from left to right. This paper studies the influence of token generation order on model quality via a novel two-pass language model that produces partially-filled sentence \"templates\" and then fills in missing tokens. We compare various strategies for structuring these two passes and observe a surprisingly large variation in model q"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.07910","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":"1808.07910","created_at":"2026-05-18T00:07:23.031000+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.07910v1","created_at":"2026-05-18T00:07:23.031000+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.07910","created_at":"2026-05-18T00:07:23.031000+00:00"},{"alias_kind":"pith_short_12","alias_value":"CLHKTBRW3PAJ","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_16","alias_value":"CLHKTBRW3PAJ2MTU","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_8","alias_value":"CLHKTBRW","created_at":"2026-05-18T12:32:16.446611+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.17069","citing_title":"Distilling Specialized Orders for Visual Generation","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CLHKTBRW3PAJ2MTUDGSTHAP5HC","json":"https://pith.science/pith/CLHKTBRW3PAJ2MTUDGSTHAP5HC.json","graph_json":"https://pith.science/api/pith-number/CLHKTBRW3PAJ2MTUDGSTHAP5HC/graph.json","events_json":"https://pith.science/api/pith-number/CLHKTBRW3PAJ2MTUDGSTHAP5HC/events.json","paper":"https://pith.science/paper/CLHKTBRW"},"agent_actions":{"view_html":"https://pith.science/pith/CLHKTBRW3PAJ2MTUDGSTHAP5HC","download_json":"https://pith.science/pith/CLHKTBRW3PAJ2MTUDGSTHAP5HC.json","view_paper":"https://pith.science/paper/CLHKTBRW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.07910&json=true","fetch_graph":"https://pith.science/api/pith-number/CLHKTBRW3PAJ2MTUDGSTHAP5HC/graph.json","fetch_events":"https://pith.science/api/pith-number/CLHKTBRW3PAJ2MTUDGSTHAP5HC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CLHKTBRW3PAJ2MTUDGSTHAP5HC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CLHKTBRW3PAJ2MTUDGSTHAP5HC/action/storage_attestation","attest_author":"https://pith.science/pith/CLHKTBRW3PAJ2MTUDGSTHAP5HC/action/author_attestation","sign_citation":"https://pith.science/pith/CLHKTBRW3PAJ2MTUDGSTHAP5HC/action/citation_signature","submit_replication":"https://pith.science/pith/CLHKTBRW3PAJ2MTUDGSTHAP5HC/action/replication_record"}},"created_at":"2026-05-18T00:07:23.031000+00:00","updated_at":"2026-05-18T00:07:23.031000+00:00"}