{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:7WF3JJXKUB7UBW47WYNSOFVYRM","short_pith_number":"pith:7WF3JJXK","canonical_record":{"source":{"id":"1808.08583","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-26T16:22:30Z","cross_cats_sorted":[],"title_canon_sha256":"c3cb21389f5faf217f7e3ddd97a3627d3d3a49e5967a5a705e6e50ff8f656356","abstract_canon_sha256":"6ed244ef7871a7d4d23f8bc8ec1939783b2a84e259681ad96790832ba886de29"},"schema_version":"1.0"},"canonical_sha256":"fd8bb4a6eaa07f40db9fb61b2716b88b276184c00fc9f6857bdea749590cecbe","source":{"kind":"arxiv","id":"1808.08583","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.08583","created_at":"2026-05-18T00:02:09Z"},{"alias_kind":"arxiv_version","alias_value":"1808.08583v2","created_at":"2026-05-18T00:02:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.08583","created_at":"2026-05-18T00:02:09Z"},{"alias_kind":"pith_short_12","alias_value":"7WF3JJXKUB7U","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"7WF3JJXKUB7UBW47","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"7WF3JJXK","created_at":"2026-05-18T12:32:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:7WF3JJXKUB7UBW47WYNSOFVYRM","target":"record","payload":{"canonical_record":{"source":{"id":"1808.08583","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-26T16:22:30Z","cross_cats_sorted":[],"title_canon_sha256":"c3cb21389f5faf217f7e3ddd97a3627d3d3a49e5967a5a705e6e50ff8f656356","abstract_canon_sha256":"6ed244ef7871a7d4d23f8bc8ec1939783b2a84e259681ad96790832ba886de29"},"schema_version":"1.0"},"canonical_sha256":"fd8bb4a6eaa07f40db9fb61b2716b88b276184c00fc9f6857bdea749590cecbe","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:09.226247Z","signature_b64":"4arrVO3wDDbshRfLEovyUsRmVeDN5bbkFrVEwJJ2Of5jkdbNOsxU3xurKJQ/p+YpRws8R4fVbJUybSpBhktfCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd8bb4a6eaa07f40db9fb61b2716b88b276184c00fc9f6857bdea749590cecbe","last_reissued_at":"2026-05-18T00:02:09.225377Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:09.225377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1808.08583","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:02:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DMV+A0hNaeG610s/PjZq02oFgfyvRFimyTA1FtDlhkMlLxb4EFsD+rsj/FsvFbcXpvWkEPhxdCb+uOQ8U2Z9CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T21:43:26.982034Z"},"content_sha256":"566841eabf19f7162f7d777f75903d992493845afb0e00e6ffbfa548c0c10c35","schema_version":"1.0","event_id":"sha256:566841eabf19f7162f7d777f75903d992493845afb0e00e6ffbfa548c0c10c35"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:7WF3JJXKUB7UBW47WYNSOFVYRM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Semi-Autoregressive Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chunqi Wang, Haiqing Chen, Ji Zhang","submitted_at":"2018-08-26T16:22:30Z","abstract_excerpt":"Existing approaches to neural machine translation are typically autoregressive models. While these models attain state-of-the-art translation quality, they are suffering from low parallelizability and thus slow at decoding long sequences. In this paper, we propose a novel model for fast sequence generation --- the semi-autoregressive Transformer (SAT). The SAT keeps the autoregressive property in global but relieves in local and thus is able to produce multiple successive words in parallel at each time step. Experiments conducted on English-German and Chinese-English translation tasks show tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.08583","kind":"arxiv","version":2},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:02:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZveVYXuD3c6MrzYs4X1noI5bwVeyzwoDu1/Dn3n+D+mu3Z4004e8ZFyVcpP94hM6jev8AVi1eXnIZA+10lz9Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T21:43:26.982399Z"},"content_sha256":"69e2285337c3691aae4cf5ea7c07bc5d3b605e6b7320197ad83c445fa4657ce6","schema_version":"1.0","event_id":"sha256:69e2285337c3691aae4cf5ea7c07bc5d3b605e6b7320197ad83c445fa4657ce6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7WF3JJXKUB7UBW47WYNSOFVYRM/bundle.json","state_url":"https://pith.science/pith/7WF3JJXKUB7UBW47WYNSOFVYRM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7WF3JJXKUB7UBW47WYNSOFVYRM/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-26T21:43:26Z","links":{"resolver":"https://pith.science/pith/7WF3JJXKUB7UBW47WYNSOFVYRM","bundle":"https://pith.science/pith/7WF3JJXKUB7UBW47WYNSOFVYRM/bundle.json","state":"https://pith.science/pith/7WF3JJXKUB7UBW47WYNSOFVYRM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7WF3JJXKUB7UBW47WYNSOFVYRM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:7WF3JJXKUB7UBW47WYNSOFVYRM","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":"6ed244ef7871a7d4d23f8bc8ec1939783b2a84e259681ad96790832ba886de29","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-26T16:22:30Z","title_canon_sha256":"c3cb21389f5faf217f7e3ddd97a3627d3d3a49e5967a5a705e6e50ff8f656356"},"schema_version":"1.0","source":{"id":"1808.08583","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.08583","created_at":"2026-05-18T00:02:09Z"},{"alias_kind":"arxiv_version","alias_value":"1808.08583v2","created_at":"2026-05-18T00:02:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.08583","created_at":"2026-05-18T00:02:09Z"},{"alias_kind":"pith_short_12","alias_value":"7WF3JJXKUB7U","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"7WF3JJXKUB7UBW47","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"7WF3JJXK","created_at":"2026-05-18T12:32:11Z"}],"graph_snapshots":[{"event_id":"sha256:69e2285337c3691aae4cf5ea7c07bc5d3b605e6b7320197ad83c445fa4657ce6","target":"graph","created_at":"2026-05-18T00:02:09Z","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":"Existing approaches to neural machine translation are typically autoregressive models. While these models attain state-of-the-art translation quality, they are suffering from low parallelizability and thus slow at decoding long sequences. In this paper, we propose a novel model for fast sequence generation --- the semi-autoregressive Transformer (SAT). The SAT keeps the autoregressive property in global but relieves in local and thus is able to produce multiple successive words in parallel at each time step. Experiments conducted on English-German and Chinese-English translation tasks show tha","authors_text":"Chunqi Wang, Haiqing Chen, Ji Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-26T16:22:30Z","title":"Semi-Autoregressive Neural Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.08583","kind":"arxiv","version":2},"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":"sha256:566841eabf19f7162f7d777f75903d992493845afb0e00e6ffbfa548c0c10c35","target":"record","created_at":"2026-05-18T00:02:09Z","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":"6ed244ef7871a7d4d23f8bc8ec1939783b2a84e259681ad96790832ba886de29","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-26T16:22:30Z","title_canon_sha256":"c3cb21389f5faf217f7e3ddd97a3627d3d3a49e5967a5a705e6e50ff8f656356"},"schema_version":"1.0","source":{"id":"1808.08583","kind":"arxiv","version":2}},"canonical_sha256":"fd8bb4a6eaa07f40db9fb61b2716b88b276184c00fc9f6857bdea749590cecbe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fd8bb4a6eaa07f40db9fb61b2716b88b276184c00fc9f6857bdea749590cecbe","first_computed_at":"2026-05-18T00:02:09.225377Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:02:09.225377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4arrVO3wDDbshRfLEovyUsRmVeDN5bbkFrVEwJJ2Of5jkdbNOsxU3xurKJQ/p+YpRws8R4fVbJUybSpBhktfCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:02:09.226247Z","signed_message":"canonical_sha256_bytes"},"source_id":"1808.08583","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:566841eabf19f7162f7d777f75903d992493845afb0e00e6ffbfa548c0c10c35","sha256:69e2285337c3691aae4cf5ea7c07bc5d3b605e6b7320197ad83c445fa4657ce6"],"state_sha256":"2c3325ffdf4b96123c1824b4cc8a5fc1d0f11c6b401f93e60b71915ea99291d8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IRYEDyLSLhxJwVSUp+cCookIkxofOGDoCRLYj3ETVzd3pjr7obFvWzA1LU2f3ifgLqIA/NenRvEApGg1sMeZDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T21:43:26.984413Z","bundle_sha256":"c36b01ee2eee369909cb8c612d81442fa881b40de2f3006e3233249837a677ec"}}