{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:KV5TMNKLQ6DIJE3DTMHMMD7XT6","short_pith_number":"pith:KV5TMNKL","canonical_record":{"source":{"id":"2304.11791","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-24T02:30:33Z","cross_cats_sorted":[],"title_canon_sha256":"e4c41bfbfee35caf119812fc11b8354aae8cbecd3cbe02a765451a94f1b79e50","abstract_canon_sha256":"4f13160f6765c8655d21cfc7a311cc250dc903bd5200da1bbba4cbc3d601a95f"},"schema_version":"1.0"},"canonical_sha256":"557b36354b87868493639b0ec60ff79f8be2ac26fb78dd9ebced64b227982372","source":{"kind":"arxiv","id":"2304.11791","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.11791","created_at":"2026-07-05T06:03:37Z"},{"alias_kind":"arxiv_version","alias_value":"2304.11791v1","created_at":"2026-07-05T06:03:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.11791","created_at":"2026-07-05T06:03:37Z"},{"alias_kind":"pith_short_12","alias_value":"KV5TMNKLQ6DI","created_at":"2026-07-05T06:03:37Z"},{"alias_kind":"pith_short_16","alias_value":"KV5TMNKLQ6DIJE3D","created_at":"2026-07-05T06:03:37Z"},{"alias_kind":"pith_short_8","alias_value":"KV5TMNKL","created_at":"2026-07-05T06:03:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:KV5TMNKLQ6DIJE3DTMHMMD7XT6","target":"record","payload":{"canonical_record":{"source":{"id":"2304.11791","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-24T02:30:33Z","cross_cats_sorted":[],"title_canon_sha256":"e4c41bfbfee35caf119812fc11b8354aae8cbecd3cbe02a765451a94f1b79e50","abstract_canon_sha256":"4f13160f6765c8655d21cfc7a311cc250dc903bd5200da1bbba4cbc3d601a95f"},"schema_version":"1.0"},"canonical_sha256":"557b36354b87868493639b0ec60ff79f8be2ac26fb78dd9ebced64b227982372","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:03:37.156660Z","signature_b64":"TCFjuoKDGXg2EJwgffkwArWOY5Jb+oCKT5nWn29HMbBaC9QNXjiZkstf62o2MV+VwyWa7KBpeMFhusuoPRUBBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"557b36354b87868493639b0ec60ff79f8be2ac26fb78dd9ebced64b227982372","last_reissued_at":"2026-07-05T06:03:37.156148Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:03:37.156148Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.11791","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:03:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ho2LiIK271ci8KvJTqYj7na4ttemFEgaTcIWOVdJ3Xdr0UaCvuU1pr5HDt/minSB+KyU5m7c4Cab/wNhVYSpBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T08:04:37.723281Z"},"content_sha256":"ba1f6768eff36afb48046d0ce5a63812bd4b08ade955e957cb854fce18727027","schema_version":"1.0","event_id":"sha256:ba1f6768eff36afb48046d0ce5a63812bd4b08ade955e957cb854fce18727027"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:KV5TMNKLQ6DIJE3DTMHMMD7XT6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Directed Acyclic Transformer Pre-training for High-quality Non-autoregressive Text Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fei Huang, Minlie Huang, Pei Ke","submitted_at":"2023-04-24T02:30:33Z","abstract_excerpt":"Non-AutoRegressive (NAR) text generation models have drawn much attention because of their significantly faster decoding speed and good generation quality in machine translation. However, in a wider range of text generation tasks, existing NAR models lack proper pre-training, making them still far behind the pre-trained autoregressive models. In this paper, we propose Pre-trained Directed Acyclic Transformer (PreDAT) and a novel pre-training task to promote prediction consistency in NAR generation. Experiments on five text generation tasks show that our PreDAT remarkably outperforms existing p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.11791","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2304.11791/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T06:03:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zKg84hJjNZs2mkDCGTjF7RCi111naI4xoBjp/s6pe5qzygHH4dG8fF+Ne3Gjpd4IQVo/S0ZeMrpOYoXGUHhvCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T08:04:37.724225Z"},"content_sha256":"d5e5e6ebfe87db929265fe5e773e2d034e9d10b9a0260f9cce9a0c25214fa4a6","schema_version":"1.0","event_id":"sha256:d5e5e6ebfe87db929265fe5e773e2d034e9d10b9a0260f9cce9a0c25214fa4a6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KV5TMNKLQ6DIJE3DTMHMMD7XT6/bundle.json","state_url":"https://pith.science/pith/KV5TMNKLQ6DIJE3DTMHMMD7XT6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KV5TMNKLQ6DIJE3DTMHMMD7XT6/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":"2026-08-07T08:04:37Z","links":{"resolver":"https://pith.science/pith/KV5TMNKLQ6DIJE3DTMHMMD7XT6","bundle":"https://pith.science/pith/KV5TMNKLQ6DIJE3DTMHMMD7XT6/bundle.json","state":"https://pith.science/pith/KV5TMNKLQ6DIJE3DTMHMMD7XT6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KV5TMNKLQ6DIJE3DTMHMMD7XT6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:KV5TMNKLQ6DIJE3DTMHMMD7XT6","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":"4f13160f6765c8655d21cfc7a311cc250dc903bd5200da1bbba4cbc3d601a95f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-24T02:30:33Z","title_canon_sha256":"e4c41bfbfee35caf119812fc11b8354aae8cbecd3cbe02a765451a94f1b79e50"},"schema_version":"1.0","source":{"id":"2304.11791","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.11791","created_at":"2026-07-05T06:03:37Z"},{"alias_kind":"arxiv_version","alias_value":"2304.11791v1","created_at":"2026-07-05T06:03:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.11791","created_at":"2026-07-05T06:03:37Z"},{"alias_kind":"pith_short_12","alias_value":"KV5TMNKLQ6DI","created_at":"2026-07-05T06:03:37Z"},{"alias_kind":"pith_short_16","alias_value":"KV5TMNKLQ6DIJE3D","created_at":"2026-07-05T06:03:37Z"},{"alias_kind":"pith_short_8","alias_value":"KV5TMNKL","created_at":"2026-07-05T06:03:37Z"}],"graph_snapshots":[{"event_id":"sha256:d5e5e6ebfe87db929265fe5e773e2d034e9d10b9a0260f9cce9a0c25214fa4a6","target":"graph","created_at":"2026-07-05T06:03:37Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2304.11791/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Non-AutoRegressive (NAR) text generation models have drawn much attention because of their significantly faster decoding speed and good generation quality in machine translation. However, in a wider range of text generation tasks, existing NAR models lack proper pre-training, making them still far behind the pre-trained autoregressive models. In this paper, we propose Pre-trained Directed Acyclic Transformer (PreDAT) and a novel pre-training task to promote prediction consistency in NAR generation. Experiments on five text generation tasks show that our PreDAT remarkably outperforms existing p","authors_text":"Fei Huang, Minlie Huang, Pei Ke","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-24T02:30:33Z","title":"Directed Acyclic Transformer Pre-training for High-quality Non-autoregressive Text Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.11791","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:ba1f6768eff36afb48046d0ce5a63812bd4b08ade955e957cb854fce18727027","target":"record","created_at":"2026-07-05T06:03:37Z","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":"4f13160f6765c8655d21cfc7a311cc250dc903bd5200da1bbba4cbc3d601a95f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-24T02:30:33Z","title_canon_sha256":"e4c41bfbfee35caf119812fc11b8354aae8cbecd3cbe02a765451a94f1b79e50"},"schema_version":"1.0","source":{"id":"2304.11791","kind":"arxiv","version":1}},"canonical_sha256":"557b36354b87868493639b0ec60ff79f8be2ac26fb78dd9ebced64b227982372","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"557b36354b87868493639b0ec60ff79f8be2ac26fb78dd9ebced64b227982372","first_computed_at":"2026-07-05T06:03:37.156148Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:03:37.156148Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TCFjuoKDGXg2EJwgffkwArWOY5Jb+oCKT5nWn29HMbBaC9QNXjiZkstf62o2MV+VwyWa7KBpeMFhusuoPRUBBw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:03:37.156660Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.11791","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ba1f6768eff36afb48046d0ce5a63812bd4b08ade955e957cb854fce18727027","sha256:d5e5e6ebfe87db929265fe5e773e2d034e9d10b9a0260f9cce9a0c25214fa4a6"],"state_sha256":"08adc3fc7e64389a13a4ed97cf0c533cb08e24b28f9ba934c392c800dcdac1d3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JgSF5AcmXsdD6f+I4dh/6/b7GN2u6WmndWPRqxxDJHNfQdXZg34YBRgxxmPFIYcivuxTcP0Y/ZN2t7NvtvNaCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T08:04:37.729521Z","bundle_sha256":"8c8426fd5ecb89d87c217d87e7388f0edb7ef2e08308889058df73e094447f8a"}}