{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:BCRAISHWPCVB5U67UNMKQFAJB5","short_pith_number":"pith:BCRAISHW","canonical_record":{"source":{"id":"2109.13097","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-27T14:49:35Z","cross_cats_sorted":[],"title_canon_sha256":"d34bb2c62d3313ce76ac2acdf128b62e935c8bec0c972ea96c58594ab4ce249f","abstract_canon_sha256":"3a964a44c3985efbe11a535c5d48c5e0478cfbe5ee785643ca50a331585aa73c"},"schema_version":"1.0"},"canonical_sha256":"08a20448f678aa1ed3dfa358a814090f4e43626f64ae633c5b23f41786b117b8","source":{"kind":"arxiv","id":"2109.13097","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.13097","created_at":"2026-07-05T03:17:41Z"},{"alias_kind":"arxiv_version","alias_value":"2109.13097v1","created_at":"2026-07-05T03:17:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.13097","created_at":"2026-07-05T03:17:41Z"},{"alias_kind":"pith_short_12","alias_value":"BCRAISHWPCVB","created_at":"2026-07-05T03:17:41Z"},{"alias_kind":"pith_short_16","alias_value":"BCRAISHWPCVB5U67","created_at":"2026-07-05T03:17:41Z"},{"alias_kind":"pith_short_8","alias_value":"BCRAISHW","created_at":"2026-07-05T03:17:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:BCRAISHWPCVB5U67UNMKQFAJB5","target":"record","payload":{"canonical_record":{"source":{"id":"2109.13097","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-27T14:49:35Z","cross_cats_sorted":[],"title_canon_sha256":"d34bb2c62d3313ce76ac2acdf128b62e935c8bec0c972ea96c58594ab4ce249f","abstract_canon_sha256":"3a964a44c3985efbe11a535c5d48c5e0478cfbe5ee785643ca50a331585aa73c"},"schema_version":"1.0"},"canonical_sha256":"08a20448f678aa1ed3dfa358a814090f4e43626f64ae633c5b23f41786b117b8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:17:41.334561Z","signature_b64":"iwYPXr6eFW1h6P3pP5vPTaPsqW7nVn4DEqeRgmbMotUB6GIh4A8GeFvueq5863T6YCX9h8WmPTW5m16UqcDIAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08a20448f678aa1ed3dfa358a814090f4e43626f64ae633c5b23f41786b117b8","last_reissued_at":"2026-07-05T03:17:41.334090Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:17:41.334090Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.13097","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":"2026-07-05T03:17:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JvUerhfldYtu1h7KtV/ywY3riOeY/ywrPefcigUPX9f2pt+kE1bEYaFcWLUS3zy2chNyTHG6MgUYyveJvBGAAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T20:21:13.479688Z"},"content_sha256":"206ddb40e85c3a90fe0de5599638c404e2207f79c9ce9e98b1272280f29e44f4","schema_version":"1.0","event_id":"sha256:206ddb40e85c3a90fe0de5599638c404e2207f79c9ce9e98b1272280f29e44f4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:BCRAISHWPCVB5U67UNMKQFAJB5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Reinforcement Learning for Pivot-based Neural Machine Translation with Non-autoregressive Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Evgeniia Tokarchuk, Hermann Ney, Jan Rosendahl, Pavel Petrushkov, Shahram Khadivi, Tomer Lancewicki, Weiyue Wang","submitted_at":"2021-09-27T14:49:35Z","abstract_excerpt":"Pivot-based neural machine translation (NMT) is commonly used in low-resource setups, especially for translation between non-English language pairs. It benefits from using high resource source-pivot and pivot-target language pairs and an individual system is trained for both sub-tasks. However, these models have no connection during training, and the source-pivot model is not optimized to produce the best translation for the source-target task. In this work, we propose to train a pivot-based NMT system with the reinforcement learning (RL) approach, which has been investigated for various text "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.13097","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/2109.13097/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":"2026-07-05T03:17:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bNlORvLNZ6LhQY2okFczbyCzKeDReIVvVSJtmXctm3/DGwHFciUm/G2A+OZ+w6D7LjWYtlyaw5Ov2+8qrj3RBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T20:21:13.480056Z"},"content_sha256":"d38310969d0728b736aff2f470dab7bc0fdd6607662d308f9872a497f5c90657","schema_version":"1.0","event_id":"sha256:d38310969d0728b736aff2f470dab7bc0fdd6607662d308f9872a497f5c90657"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BCRAISHWPCVB5U67UNMKQFAJB5/bundle.json","state_url":"https://pith.science/pith/BCRAISHWPCVB5U67UNMKQFAJB5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BCRAISHWPCVB5U67UNMKQFAJB5/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":"2026-07-10T20:21:13Z","links":{"resolver":"https://pith.science/pith/BCRAISHWPCVB5U67UNMKQFAJB5","bundle":"https://pith.science/pith/BCRAISHWPCVB5U67UNMKQFAJB5/bundle.json","state":"https://pith.science/pith/BCRAISHWPCVB5U67UNMKQFAJB5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BCRAISHWPCVB5U67UNMKQFAJB5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:BCRAISHWPCVB5U67UNMKQFAJB5","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":"3a964a44c3985efbe11a535c5d48c5e0478cfbe5ee785643ca50a331585aa73c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-27T14:49:35Z","title_canon_sha256":"d34bb2c62d3313ce76ac2acdf128b62e935c8bec0c972ea96c58594ab4ce249f"},"schema_version":"1.0","source":{"id":"2109.13097","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.13097","created_at":"2026-07-05T03:17:41Z"},{"alias_kind":"arxiv_version","alias_value":"2109.13097v1","created_at":"2026-07-05T03:17:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.13097","created_at":"2026-07-05T03:17:41Z"},{"alias_kind":"pith_short_12","alias_value":"BCRAISHWPCVB","created_at":"2026-07-05T03:17:41Z"},{"alias_kind":"pith_short_16","alias_value":"BCRAISHWPCVB5U67","created_at":"2026-07-05T03:17:41Z"},{"alias_kind":"pith_short_8","alias_value":"BCRAISHW","created_at":"2026-07-05T03:17:41Z"}],"graph_snapshots":[{"event_id":"sha256:d38310969d0728b736aff2f470dab7bc0fdd6607662d308f9872a497f5c90657","target":"graph","created_at":"2026-07-05T03:17:41Z","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/2109.13097/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pivot-based neural machine translation (NMT) is commonly used in low-resource setups, especially for translation between non-English language pairs. It benefits from using high resource source-pivot and pivot-target language pairs and an individual system is trained for both sub-tasks. However, these models have no connection during training, and the source-pivot model is not optimized to produce the best translation for the source-target task. In this work, we propose to train a pivot-based NMT system with the reinforcement learning (RL) approach, which has been investigated for various text ","authors_text":"Evgeniia Tokarchuk, Hermann Ney, Jan Rosendahl, Pavel Petrushkov, Shahram Khadivi, Tomer Lancewicki, Weiyue Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-27T14:49:35Z","title":"Towards Reinforcement Learning for Pivot-based Neural Machine Translation with Non-autoregressive Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.13097","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":"sha256:206ddb40e85c3a90fe0de5599638c404e2207f79c9ce9e98b1272280f29e44f4","target":"record","created_at":"2026-07-05T03:17:41Z","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":"3a964a44c3985efbe11a535c5d48c5e0478cfbe5ee785643ca50a331585aa73c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-27T14:49:35Z","title_canon_sha256":"d34bb2c62d3313ce76ac2acdf128b62e935c8bec0c972ea96c58594ab4ce249f"},"schema_version":"1.0","source":{"id":"2109.13097","kind":"arxiv","version":1}},"canonical_sha256":"08a20448f678aa1ed3dfa358a814090f4e43626f64ae633c5b23f41786b117b8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"08a20448f678aa1ed3dfa358a814090f4e43626f64ae633c5b23f41786b117b8","first_computed_at":"2026-07-05T03:17:41.334090Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:17:41.334090Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iwYPXr6eFW1h6P3pP5vPTaPsqW7nVn4DEqeRgmbMotUB6GIh4A8GeFvueq5863T6YCX9h8WmPTW5m16UqcDIAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:17:41.334561Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.13097","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:206ddb40e85c3a90fe0de5599638c404e2207f79c9ce9e98b1272280f29e44f4","sha256:d38310969d0728b736aff2f470dab7bc0fdd6607662d308f9872a497f5c90657"],"state_sha256":"8dd6a7bacc90dcdb7d0dde21de2fc608c856bfaf62e18c0671cfd4b8f7925737"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+nLgWMJnOGl/OD2+/ADI4Rph87f5NPqTRGcV2S6OqFRaK5IBl3dFawOC6/5ybs6z/rE2eehrCWoEvLNOndSGAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-10T20:21:13.482354Z","bundle_sha256":"1fdc3bbccc53dd34ebafe5efce6f4944811fef8c4201acd1cd8ec1858ec176fc"}}