{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:BCTN26DOP2J5JEFQZWR6MPJOOH","short_pith_number":"pith:BCTN26DO","canonical_record":{"source":{"id":"2305.06155","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-07T07:42:22Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"b1309e6c3c03ba51247cd64ceae24ea8e16399ebfddb95658fce37fe87c76fb2","abstract_canon_sha256":"22bb9d852b3448359a1f9d789aa0346e2182f7075331f9f05922616022cc856a"},"schema_version":"1.0"},"canonical_sha256":"08a6dd786e7e93d490b0cda3e63d2e71d03ab52a60a2b34ba274a11d0be0c969","source":{"kind":"arxiv","id":"2305.06155","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.06155","created_at":"2026-07-05T06:09:00Z"},{"alias_kind":"arxiv_version","alias_value":"2305.06155v1","created_at":"2026-07-05T06:09:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.06155","created_at":"2026-07-05T06:09:00Z"},{"alias_kind":"pith_short_12","alias_value":"BCTN26DOP2J5","created_at":"2026-07-05T06:09:00Z"},{"alias_kind":"pith_short_16","alias_value":"BCTN26DOP2J5JEFQ","created_at":"2026-07-05T06:09:00Z"},{"alias_kind":"pith_short_8","alias_value":"BCTN26DO","created_at":"2026-07-05T06:09:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:BCTN26DOP2J5JEFQZWR6MPJOOH","target":"record","payload":{"canonical_record":{"source":{"id":"2305.06155","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-07T07:42:22Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"b1309e6c3c03ba51247cd64ceae24ea8e16399ebfddb95658fce37fe87c76fb2","abstract_canon_sha256":"22bb9d852b3448359a1f9d789aa0346e2182f7075331f9f05922616022cc856a"},"schema_version":"1.0"},"canonical_sha256":"08a6dd786e7e93d490b0cda3e63d2e71d03ab52a60a2b34ba274a11d0be0c969","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:09:00.129907Z","signature_b64":"K7Ox5gVyT2CLJQwwaCDju+MRdIIRaUTNyeoIBsHqJ5/x4eNWIl4AtctzCbo03UqWnQcpOkqH28+020ZG1GwQBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08a6dd786e7e93d490b0cda3e63d2e71d03ab52a60a2b34ba274a11d0be0c969","last_reissued_at":"2026-07-05T06:09:00.129557Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:09:00.129557Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.06155","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":"2026-07-05T06:09:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KzkHOSPE9YddD6793s8mSeqVUwMVLXwfbFau3B7iUTwMZZCQkQdA+Dd7xYnk8mfcGCad489FZ7B2kJTbVH01Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T19:29:44.199468Z"},"content_sha256":"95208bc661b1bf1531e4bcd5885b29772343cb17626012f9a139a504af354b3e","schema_version":"1.0","event_id":"sha256:95208bc661b1bf1531e4bcd5885b29772343cb17626012f9a139a504af354b3e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:BCTN26DOP2J5JEFQZWR6MPJOOH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Leveraging Synthetic Targets for Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Oleksii Hrinchuk, Oleksii Kuchaiev, Sarthak Mittal","submitted_at":"2023-05-07T07:42:22Z","abstract_excerpt":"In this work, we provide a recipe for training machine translation models in a limited resource setting by leveraging synthetic target data generated using a large pre-trained model. We show that consistently across different benchmarks in bilingual, multilingual, and speech translation setups, training models on synthetic targets outperforms training on the actual ground-truth data. This performance gap grows bigger with increasing limits on the amount of available resources in the form of the size of the dataset and the number of parameters in the model. We also provide preliminary analysis "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.06155","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/2305.06155/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":"2026-07-05T06:09:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xiToeLQe42NdbHHZ5EoggkDKK5FpyA7lIHlVE8kiSP6XZ6uozCRjylBh6V9sCDZZofrGfmKdKsJRjB0f6sPxCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T19:29:44.199851Z"},"content_sha256":"f77d647613571caa4700bec97301b81c6dc85dc4abfe347624a15e054cede6c4","schema_version":"1.0","event_id":"sha256:f77d647613571caa4700bec97301b81c6dc85dc4abfe347624a15e054cede6c4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BCTN26DOP2J5JEFQZWR6MPJOOH/bundle.json","state_url":"https://pith.science/pith/BCTN26DOP2J5JEFQZWR6MPJOOH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BCTN26DOP2J5JEFQZWR6MPJOOH/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":"2026-07-13T19:29:44Z","links":{"resolver":"https://pith.science/pith/BCTN26DOP2J5JEFQZWR6MPJOOH","bundle":"https://pith.science/pith/BCTN26DOP2J5JEFQZWR6MPJOOH/bundle.json","state":"https://pith.science/pith/BCTN26DOP2J5JEFQZWR6MPJOOH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BCTN26DOP2J5JEFQZWR6MPJOOH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BCTN26DOP2J5JEFQZWR6MPJOOH","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":"22bb9d852b3448359a1f9d789aa0346e2182f7075331f9f05922616022cc856a","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-07T07:42:22Z","title_canon_sha256":"b1309e6c3c03ba51247cd64ceae24ea8e16399ebfddb95658fce37fe87c76fb2"},"schema_version":"1.0","source":{"id":"2305.06155","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.06155","created_at":"2026-07-05T06:09:00Z"},{"alias_kind":"arxiv_version","alias_value":"2305.06155v1","created_at":"2026-07-05T06:09:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.06155","created_at":"2026-07-05T06:09:00Z"},{"alias_kind":"pith_short_12","alias_value":"BCTN26DOP2J5","created_at":"2026-07-05T06:09:00Z"},{"alias_kind":"pith_short_16","alias_value":"BCTN26DOP2J5JEFQ","created_at":"2026-07-05T06:09:00Z"},{"alias_kind":"pith_short_8","alias_value":"BCTN26DO","created_at":"2026-07-05T06:09:00Z"}],"graph_snapshots":[{"event_id":"sha256:f77d647613571caa4700bec97301b81c6dc85dc4abfe347624a15e054cede6c4","target":"graph","created_at":"2026-07-05T06:09:00Z","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/2305.06155/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we provide a recipe for training machine translation models in a limited resource setting by leveraging synthetic target data generated using a large pre-trained model. We show that consistently across different benchmarks in bilingual, multilingual, and speech translation setups, training models on synthetic targets outperforms training on the actual ground-truth data. This performance gap grows bigger with increasing limits on the amount of available resources in the form of the size of the dataset and the number of parameters in the model. We also provide preliminary analysis ","authors_text":"Oleksii Hrinchuk, Oleksii Kuchaiev, Sarthak Mittal","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-07T07:42:22Z","title":"Leveraging Synthetic Targets for Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.06155","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":"sha256:95208bc661b1bf1531e4bcd5885b29772343cb17626012f9a139a504af354b3e","target":"record","created_at":"2026-07-05T06:09:00Z","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":"22bb9d852b3448359a1f9d789aa0346e2182f7075331f9f05922616022cc856a","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-07T07:42:22Z","title_canon_sha256":"b1309e6c3c03ba51247cd64ceae24ea8e16399ebfddb95658fce37fe87c76fb2"},"schema_version":"1.0","source":{"id":"2305.06155","kind":"arxiv","version":1}},"canonical_sha256":"08a6dd786e7e93d490b0cda3e63d2e71d03ab52a60a2b34ba274a11d0be0c969","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"08a6dd786e7e93d490b0cda3e63d2e71d03ab52a60a2b34ba274a11d0be0c969","first_computed_at":"2026-07-05T06:09:00.129557Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:09:00.129557Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"K7Ox5gVyT2CLJQwwaCDju+MRdIIRaUTNyeoIBsHqJ5/x4eNWIl4AtctzCbo03UqWnQcpOkqH28+020ZG1GwQBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:09:00.129907Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.06155","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:95208bc661b1bf1531e4bcd5885b29772343cb17626012f9a139a504af354b3e","sha256:f77d647613571caa4700bec97301b81c6dc85dc4abfe347624a15e054cede6c4"],"state_sha256":"0478285c6498bcb77b1fa277b8ea30cda3541c2537fe91f30cc9c922af7612ec"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5CM+8TrO1cLTwfa3zU3e20auKGXbIse3nKfvz7KO/hdIb/dkqnKZdM+6eN0MA6TylVuQYA+tAFwvjNt1e1b5BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-13T19:29:44.201987Z","bundle_sha256":"93d402c8c3c4029b8abf0b176417346740abbe0533dd5cc042a0b234b75b3991"}}