{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:YEHDVXKHMCLSFGMKD7RESEG2FW","short_pith_number":"pith:YEHDVXKH","canonical_record":{"source":{"id":"2203.08442","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-16T07:36:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2682bfe4c07e4c856513236095621b00ef3a9db6679d1a79593fbc6ccef17f7a","abstract_canon_sha256":"28507a0d0370aa188d3b7f159916460b3f83489f27e83acc639cdd26e3e3b533"},"schema_version":"1.0"},"canonical_sha256":"c10e3add47609722998a1fe24910da2d99f827665dad6e8d9bedf628f20fa60f","source":{"kind":"arxiv","id":"2203.08442","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.08442","created_at":"2026-07-05T04:05:44Z"},{"alias_kind":"arxiv_version","alias_value":"2203.08442v1","created_at":"2026-07-05T04:05:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.08442","created_at":"2026-07-05T04:05:44Z"},{"alias_kind":"pith_short_12","alias_value":"YEHDVXKHMCLS","created_at":"2026-07-05T04:05:44Z"},{"alias_kind":"pith_short_16","alias_value":"YEHDVXKHMCLSFGMK","created_at":"2026-07-05T04:05:44Z"},{"alias_kind":"pith_short_8","alias_value":"YEHDVXKH","created_at":"2026-07-05T04:05:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:YEHDVXKHMCLSFGMKD7RESEG2FW","target":"record","payload":{"canonical_record":{"source":{"id":"2203.08442","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-16T07:36:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2682bfe4c07e4c856513236095621b00ef3a9db6679d1a79593fbc6ccef17f7a","abstract_canon_sha256":"28507a0d0370aa188d3b7f159916460b3f83489f27e83acc639cdd26e3e3b533"},"schema_version":"1.0"},"canonical_sha256":"c10e3add47609722998a1fe24910da2d99f827665dad6e8d9bedf628f20fa60f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:05:44.695246Z","signature_b64":"a2RHqtWo/lGqtsERJqTrWqERcxjdF8DV8TXMibhPt9/fHfyUli/tAgMWihWtk5DrErUy0VnPhxhs+32cPaQGDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c10e3add47609722998a1fe24910da2d99f827665dad6e8d9bedf628f20fa60f","last_reissued_at":"2026-07-05T04:05:44.694706Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:05:44.694706Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.08442","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":"2026-07-05T04:05:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yCmJcqdGCnRW/qOyE1w7ZAWdlIU3xlcSBemDKcN6jNx/OLrW7FvW8reSer4S369xM4srOD6U0UL4KOTPmLIACQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:11:30.711585Z"},"content_sha256":"7732d783f3cd14381831aaf02ce9449287211ea9b80bbbc26f88490b21f98f68","schema_version":"1.0","event_id":"sha256:7732d783f3cd14381831aaf02ce9449287211ea9b80bbbc26f88490b21f98f68"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:YEHDVXKHMCLSFGMKD7RESEG2FW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Understanding and Improving Sequence-to-Sequence Pretraining for Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Michael Lyu, Shuming Shi, Wenxiang Jiao, Wenxuan Wang, Xing Wang, Yongchang Hao, Zhaopeng Tu","submitted_at":"2022-03-16T07:36:28Z","abstract_excerpt":"In this paper, we present a substantial step in better understanding the SOTA sequence-to-sequence (Seq2Seq) pretraining for neural machine translation~(NMT). We focus on studying the impact of the jointly pretrained decoder, which is the main difference between Seq2Seq pretraining and previous encoder-based pretraining approaches for NMT. By carefully designing experiments on three language pairs, we find that Seq2Seq pretraining is a double-edged sword: On one hand, it helps NMT models to produce more diverse translations and reduce adequacy-related translation errors. On the other hand, the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.08442","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/2203.08442/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":"2026-07-05T04:05:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tPpz4ouwye7Q4FqI3PSdoE7r4wv2g3b6j7NfD8n+pktWBMl1BaafxmzgI/sb1sDIcl52i8maXtfllzB1y5rKBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:11:30.711978Z"},"content_sha256":"ffe55d4f3689b7e851eea690aba749b1e20514e953850177cbf8942bdbc8f3c9","schema_version":"1.0","event_id":"sha256:ffe55d4f3689b7e851eea690aba749b1e20514e953850177cbf8942bdbc8f3c9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YEHDVXKHMCLSFGMKD7RESEG2FW/bundle.json","state_url":"https://pith.science/pith/YEHDVXKHMCLSFGMKD7RESEG2FW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YEHDVXKHMCLSFGMKD7RESEG2FW/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":"2026-07-07T07:11:30Z","links":{"resolver":"https://pith.science/pith/YEHDVXKHMCLSFGMKD7RESEG2FW","bundle":"https://pith.science/pith/YEHDVXKHMCLSFGMKD7RESEG2FW/bundle.json","state":"https://pith.science/pith/YEHDVXKHMCLSFGMKD7RESEG2FW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YEHDVXKHMCLSFGMKD7RESEG2FW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:YEHDVXKHMCLSFGMKD7RESEG2FW","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":"28507a0d0370aa188d3b7f159916460b3f83489f27e83acc639cdd26e3e3b533","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-16T07:36:28Z","title_canon_sha256":"2682bfe4c07e4c856513236095621b00ef3a9db6679d1a79593fbc6ccef17f7a"},"schema_version":"1.0","source":{"id":"2203.08442","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.08442","created_at":"2026-07-05T04:05:44Z"},{"alias_kind":"arxiv_version","alias_value":"2203.08442v1","created_at":"2026-07-05T04:05:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.08442","created_at":"2026-07-05T04:05:44Z"},{"alias_kind":"pith_short_12","alias_value":"YEHDVXKHMCLS","created_at":"2026-07-05T04:05:44Z"},{"alias_kind":"pith_short_16","alias_value":"YEHDVXKHMCLSFGMK","created_at":"2026-07-05T04:05:44Z"},{"alias_kind":"pith_short_8","alias_value":"YEHDVXKH","created_at":"2026-07-05T04:05:44Z"}],"graph_snapshots":[{"event_id":"sha256:ffe55d4f3689b7e851eea690aba749b1e20514e953850177cbf8942bdbc8f3c9","target":"graph","created_at":"2026-07-05T04:05:44Z","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/2203.08442/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we present a substantial step in better understanding the SOTA sequence-to-sequence (Seq2Seq) pretraining for neural machine translation~(NMT). We focus on studying the impact of the jointly pretrained decoder, which is the main difference between Seq2Seq pretraining and previous encoder-based pretraining approaches for NMT. By carefully designing experiments on three language pairs, we find that Seq2Seq pretraining is a double-edged sword: On one hand, it helps NMT models to produce more diverse translations and reduce adequacy-related translation errors. On the other hand, the","authors_text":"Michael Lyu, Shuming Shi, Wenxiang Jiao, Wenxuan Wang, Xing Wang, Yongchang Hao, Zhaopeng Tu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-16T07:36:28Z","title":"Understanding and Improving Sequence-to-Sequence Pretraining for Neural Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.08442","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":"sha256:7732d783f3cd14381831aaf02ce9449287211ea9b80bbbc26f88490b21f98f68","target":"record","created_at":"2026-07-05T04:05:44Z","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":"28507a0d0370aa188d3b7f159916460b3f83489f27e83acc639cdd26e3e3b533","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-16T07:36:28Z","title_canon_sha256":"2682bfe4c07e4c856513236095621b00ef3a9db6679d1a79593fbc6ccef17f7a"},"schema_version":"1.0","source":{"id":"2203.08442","kind":"arxiv","version":1}},"canonical_sha256":"c10e3add47609722998a1fe24910da2d99f827665dad6e8d9bedf628f20fa60f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c10e3add47609722998a1fe24910da2d99f827665dad6e8d9bedf628f20fa60f","first_computed_at":"2026-07-05T04:05:44.694706Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:05:44.694706Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a2RHqtWo/lGqtsERJqTrWqERcxjdF8DV8TXMibhPt9/fHfyUli/tAgMWihWtk5DrErUy0VnPhxhs+32cPaQGDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:05:44.695246Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.08442","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7732d783f3cd14381831aaf02ce9449287211ea9b80bbbc26f88490b21f98f68","sha256:ffe55d4f3689b7e851eea690aba749b1e20514e953850177cbf8942bdbc8f3c9"],"state_sha256":"df543a32e09c3e72503398aba5077dbfb790525c0b1bd0081b04f5c5ee0111b9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bIp617QdSdDlFjpVphZGyeCGQbXTNZgOYAIQsVm5//cFtzvbT0XYqm5vk5hHmR9zREXu10tyeVWIsYBqFw2iCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T07:11:30.714150Z","bundle_sha256":"82fa5eca25272dde502048ed6ccceb91549816f5bc80af954ce628fb5e1d77a4"}}