{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:KKJ43IHYFIXEUVMIYBFAHQGO7X","short_pith_number":"pith:KKJ43IHY","canonical_record":{"source":{"id":"2211.06075","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-11T09:10:14Z","cross_cats_sorted":[],"title_canon_sha256":"a05e6666d9485ccd17ae68f3e0939dcec5057e544bf2db895be9756f23b87ea6","abstract_canon_sha256":"e2f0bf36abf8660d6170f782a3d71051c341bc89a781a7e13065d199bcfc4449"},"schema_version":"1.0"},"canonical_sha256":"5293cda0f82a2e4a5588c04a03c0cefdc54bb401ff36d7ed6cf61441ebc17c4e","source":{"kind":"arxiv","id":"2211.06075","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.06075","created_at":"2026-07-05T05:15:16Z"},{"alias_kind":"arxiv_version","alias_value":"2211.06075v1","created_at":"2026-07-05T05:15:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.06075","created_at":"2026-07-05T05:15:16Z"},{"alias_kind":"pith_short_12","alias_value":"KKJ43IHYFIXE","created_at":"2026-07-05T05:15:16Z"},{"alias_kind":"pith_short_16","alias_value":"KKJ43IHYFIXEUVMI","created_at":"2026-07-05T05:15:16Z"},{"alias_kind":"pith_short_8","alias_value":"KKJ43IHY","created_at":"2026-07-05T05:15:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:KKJ43IHYFIXEUVMIYBFAHQGO7X","target":"record","payload":{"canonical_record":{"source":{"id":"2211.06075","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-11T09:10:14Z","cross_cats_sorted":[],"title_canon_sha256":"a05e6666d9485ccd17ae68f3e0939dcec5057e544bf2db895be9756f23b87ea6","abstract_canon_sha256":"e2f0bf36abf8660d6170f782a3d71051c341bc89a781a7e13065d199bcfc4449"},"schema_version":"1.0"},"canonical_sha256":"5293cda0f82a2e4a5588c04a03c0cefdc54bb401ff36d7ed6cf61441ebc17c4e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:15:16.988694Z","signature_b64":"h5SpOhdO3Yv2bduXbik6bERlU4dzQX6AE7SZvw4yhIcbXUgAUnJt6qXa/o3dDxlZFtYA6CKqUcH/ABOo48JTAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5293cda0f82a2e4a5588c04a03c0cefdc54bb401ff36d7ed6cf61441ebc17c4e","last_reissued_at":"2026-07-05T05:15:16.988300Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:15:16.988300Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.06075","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":"2026-07-05T05:15:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EA+XL5dChsqXlsxBj8nCMmyXsttHnvMtzUqGi8A7ZpCu95DopMDOnD9Yx/XCItsE+bTpQ45dO4qHU52ulnEcBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T08:57:16.205046Z"},"content_sha256":"945e22a75fdfa2409ceb945e747823beee9b6f4d514fea83bb8092f1ce42de8d","schema_version":"1.0","event_id":"sha256:945e22a75fdfa2409ceb945e747823beee9b6f4d514fea83bb8092f1ce42de8d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:KKJ43IHYFIXEUVMIYBFAHQGO7X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Helping the Weak Makes You Strong: Simple Multi-Task Learning Improves Non-Autoregressive Translators","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Shujian Huang, Xinyou Wang, Zaixiang Zheng","submitted_at":"2022-11-11T09:10:14Z","abstract_excerpt":"Recently, non-autoregressive (NAR) neural machine translation models have received increasing attention due to their efficient parallel decoding. However, the probabilistic framework of NAR models necessitates conditional independence assumption on target sequences, falling short of characterizing human language data. This drawback results in less informative learning signals for NAR models under conventional MLE training, thereby yielding unsatisfactory accuracy compared to their autoregressive (AR) counterparts. In this paper, we propose a simple and model-agnostic multi-task learning framew"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.06075","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/2211.06075/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":"2026-07-05T05:15:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MWMOrZ0iFNDm8nZd25nwY+Tk2VtAFsly3FamVN313RvdQOs/VSbeRNUriRFiEAtEDkkN8TfnWNkQrj3JFH6CAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T08:57:16.205875Z"},"content_sha256":"faf7b7a27dd5b4831d02279bc892ae047f9c7284adb46971fe54c43c6d2e0210","schema_version":"1.0","event_id":"sha256:faf7b7a27dd5b4831d02279bc892ae047f9c7284adb46971fe54c43c6d2e0210"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KKJ43IHYFIXEUVMIYBFAHQGO7X/bundle.json","state_url":"https://pith.science/pith/KKJ43IHYFIXEUVMIYBFAHQGO7X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KKJ43IHYFIXEUVMIYBFAHQGO7X/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":"2026-08-14T08:57:16Z","links":{"resolver":"https://pith.science/pith/KKJ43IHYFIXEUVMIYBFAHQGO7X","bundle":"https://pith.science/pith/KKJ43IHYFIXEUVMIYBFAHQGO7X/bundle.json","state":"https://pith.science/pith/KKJ43IHYFIXEUVMIYBFAHQGO7X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KKJ43IHYFIXEUVMIYBFAHQGO7X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:KKJ43IHYFIXEUVMIYBFAHQGO7X","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":"e2f0bf36abf8660d6170f782a3d71051c341bc89a781a7e13065d199bcfc4449","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-11T09:10:14Z","title_canon_sha256":"a05e6666d9485ccd17ae68f3e0939dcec5057e544bf2db895be9756f23b87ea6"},"schema_version":"1.0","source":{"id":"2211.06075","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.06075","created_at":"2026-07-05T05:15:16Z"},{"alias_kind":"arxiv_version","alias_value":"2211.06075v1","created_at":"2026-07-05T05:15:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.06075","created_at":"2026-07-05T05:15:16Z"},{"alias_kind":"pith_short_12","alias_value":"KKJ43IHYFIXE","created_at":"2026-07-05T05:15:16Z"},{"alias_kind":"pith_short_16","alias_value":"KKJ43IHYFIXEUVMI","created_at":"2026-07-05T05:15:16Z"},{"alias_kind":"pith_short_8","alias_value":"KKJ43IHY","created_at":"2026-07-05T05:15:16Z"}],"graph_snapshots":[{"event_id":"sha256:faf7b7a27dd5b4831d02279bc892ae047f9c7284adb46971fe54c43c6d2e0210","target":"graph","created_at":"2026-07-05T05:15:16Z","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/2211.06075/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, non-autoregressive (NAR) neural machine translation models have received increasing attention due to their efficient parallel decoding. However, the probabilistic framework of NAR models necessitates conditional independence assumption on target sequences, falling short of characterizing human language data. This drawback results in less informative learning signals for NAR models under conventional MLE training, thereby yielding unsatisfactory accuracy compared to their autoregressive (AR) counterparts. In this paper, we propose a simple and model-agnostic multi-task learning framew","authors_text":"Shujian Huang, Xinyou Wang, Zaixiang Zheng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-11T09:10:14Z","title":"Helping the Weak Makes You Strong: Simple Multi-Task Learning Improves Non-Autoregressive Translators"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.06075","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":"sha256:945e22a75fdfa2409ceb945e747823beee9b6f4d514fea83bb8092f1ce42de8d","target":"record","created_at":"2026-07-05T05:15:16Z","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":"e2f0bf36abf8660d6170f782a3d71051c341bc89a781a7e13065d199bcfc4449","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-11T09:10:14Z","title_canon_sha256":"a05e6666d9485ccd17ae68f3e0939dcec5057e544bf2db895be9756f23b87ea6"},"schema_version":"1.0","source":{"id":"2211.06075","kind":"arxiv","version":1}},"canonical_sha256":"5293cda0f82a2e4a5588c04a03c0cefdc54bb401ff36d7ed6cf61441ebc17c4e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5293cda0f82a2e4a5588c04a03c0cefdc54bb401ff36d7ed6cf61441ebc17c4e","first_computed_at":"2026-07-05T05:15:16.988300Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:15:16.988300Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h5SpOhdO3Yv2bduXbik6bERlU4dzQX6AE7SZvw4yhIcbXUgAUnJt6qXa/o3dDxlZFtYA6CKqUcH/ABOo48JTAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:15:16.988694Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.06075","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:945e22a75fdfa2409ceb945e747823beee9b6f4d514fea83bb8092f1ce42de8d","sha256:faf7b7a27dd5b4831d02279bc892ae047f9c7284adb46971fe54c43c6d2e0210"],"state_sha256":"5e37ab3f35da2a2ebbdb887102071e310ee5f43967c4181688fbc25eda700c8e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U1P1kW1TKlWLryP3moGQyTu94jH3jP3IB9hF2kRcqhrh0EqOPZ/K0JVPuMW+cr25Az3KIqkkP3111BjVv64gAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T08:57:16.214056Z","bundle_sha256":"3547c451f2896f52f70554eaf80006a8cdabd9da5480fddb56a9764615036edb"}}