{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:NPZSSHYUW6PBKGIKQVZOSZNOOX","short_pith_number":"pith:NPZSSHYU","canonical_record":{"source":{"id":"2202.01994","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-04T06:53:49Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"2a8ac3f328e967083e12b88d0cc007252740bac1fc44656318b8a22d822e212c","abstract_canon_sha256":"1ca3c26ba11c04a15453a4071109437e31239dcf7ffe7d7b86feb1b8238ebe32"},"schema_version":"1.0"},"canonical_sha256":"6bf3291f14b79e15190a8572e965ae75c33a7cf29cf00acc5a5820e81d4f7d35","source":{"kind":"arxiv","id":"2202.01994","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.01994","created_at":"2026-07-05T03:54:07Z"},{"alias_kind":"arxiv_version","alias_value":"2202.01994v1","created_at":"2026-07-05T03:54:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.01994","created_at":"2026-07-05T03:54:07Z"},{"alias_kind":"pith_short_12","alias_value":"NPZSSHYUW6PB","created_at":"2026-07-05T03:54:07Z"},{"alias_kind":"pith_short_16","alias_value":"NPZSSHYUW6PBKGIK","created_at":"2026-07-05T03:54:07Z"},{"alias_kind":"pith_short_8","alias_value":"NPZSSHYU","created_at":"2026-07-05T03:54:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:NPZSSHYUW6PBKGIKQVZOSZNOOX","target":"record","payload":{"canonical_record":{"source":{"id":"2202.01994","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-04T06:53:49Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"2a8ac3f328e967083e12b88d0cc007252740bac1fc44656318b8a22d822e212c","abstract_canon_sha256":"1ca3c26ba11c04a15453a4071109437e31239dcf7ffe7d7b86feb1b8238ebe32"},"schema_version":"1.0"},"canonical_sha256":"6bf3291f14b79e15190a8572e965ae75c33a7cf29cf00acc5a5820e81d4f7d35","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:54:07.854373Z","signature_b64":"LBhrZ8FTNpt8XVB3LQP6ILDZ//fL41nQezptaqXGhwjkVzqbie2t9rbEQAro8zZ7EPU+TRq1R/PP7JQ51o/4DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6bf3291f14b79e15190a8572e965ae75c33a7cf29cf00acc5a5820e81d4f7d35","last_reissued_at":"2026-07-05T03:54:07.853960Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:54:07.853960Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2202.01994","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":"2026-07-05T03:54:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g2Zn9t7AS4Q/tQxBhkqpY1F+FM3PmCp0cQcvDqyKlOBk8y4TgaFz8q3HmzfptvjiNl4xBbNCDiX0hR7h4XgTDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T15:01:05.020750Z"},"content_sha256":"cf7b24d4660040784c5f91fed792785907f76b13ce0faa0a189565ed75e09813","schema_version":"1.0","event_id":"sha256:cf7b24d4660040784c5f91fed792785907f76b13ce0faa0a189565ed75e09813"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:NPZSSHYUW6PBKGIKQVZOSZNOOX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data Scaling Laws in NMT: The Effect of Noise and Architecture","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Ankush Garg, Behnam Neyshabur, Behrooz Ghorbani, Biao Zhang, Colin Cherry, Maxim Krikun, Orhan Firat, Yamini Bansal","submitted_at":"2022-02-04T06:53:49Z","abstract_excerpt":"In this work, we study the effect of varying the architecture and training data quality on the data scaling properties of Neural Machine Translation (NMT). First, we establish that the test loss of encoder-decoder transformer models scales as a power law in the number of training samples, with a dependence on the model size. Then, we systematically vary aspects of the training setup to understand how they impact the data scaling laws. In particular, we change the following (1) Architecture and task setup: We compare to a transformer-LSTM hybrid, and a decoder-only transformer with a language m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.01994","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/2202.01994/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":"2026-07-05T03:54:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dMfggzUs9C9UGierPSZILygh+W9loVhyZ1RdzZg3afXkXfy+lqLSxsNh/rdcYegIsEAkl8fCeg03lNTr82yJCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T15:01:05.022074Z"},"content_sha256":"1b5fbd0fe01d7477879e3ce76e4924bc4ea22c44c438d3dc33aab942936472b8","schema_version":"1.0","event_id":"sha256:1b5fbd0fe01d7477879e3ce76e4924bc4ea22c44c438d3dc33aab942936472b8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NPZSSHYUW6PBKGIKQVZOSZNOOX/bundle.json","state_url":"https://pith.science/pith/NPZSSHYUW6PBKGIKQVZOSZNOOX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NPZSSHYUW6PBKGIKQVZOSZNOOX/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":"2026-08-09T15:01:05Z","links":{"resolver":"https://pith.science/pith/NPZSSHYUW6PBKGIKQVZOSZNOOX","bundle":"https://pith.science/pith/NPZSSHYUW6PBKGIKQVZOSZNOOX/bundle.json","state":"https://pith.science/pith/NPZSSHYUW6PBKGIKQVZOSZNOOX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NPZSSHYUW6PBKGIKQVZOSZNOOX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:NPZSSHYUW6PBKGIKQVZOSZNOOX","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":"1ca3c26ba11c04a15453a4071109437e31239dcf7ffe7d7b86feb1b8238ebe32","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-04T06:53:49Z","title_canon_sha256":"2a8ac3f328e967083e12b88d0cc007252740bac1fc44656318b8a22d822e212c"},"schema_version":"1.0","source":{"id":"2202.01994","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.01994","created_at":"2026-07-05T03:54:07Z"},{"alias_kind":"arxiv_version","alias_value":"2202.01994v1","created_at":"2026-07-05T03:54:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.01994","created_at":"2026-07-05T03:54:07Z"},{"alias_kind":"pith_short_12","alias_value":"NPZSSHYUW6PB","created_at":"2026-07-05T03:54:07Z"},{"alias_kind":"pith_short_16","alias_value":"NPZSSHYUW6PBKGIK","created_at":"2026-07-05T03:54:07Z"},{"alias_kind":"pith_short_8","alias_value":"NPZSSHYU","created_at":"2026-07-05T03:54:07Z"}],"graph_snapshots":[{"event_id":"sha256:1b5fbd0fe01d7477879e3ce76e4924bc4ea22c44c438d3dc33aab942936472b8","target":"graph","created_at":"2026-07-05T03:54:07Z","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/2202.01994/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we study the effect of varying the architecture and training data quality on the data scaling properties of Neural Machine Translation (NMT). First, we establish that the test loss of encoder-decoder transformer models scales as a power law in the number of training samples, with a dependence on the model size. Then, we systematically vary aspects of the training setup to understand how they impact the data scaling laws. In particular, we change the following (1) Architecture and task setup: We compare to a transformer-LSTM hybrid, and a decoder-only transformer with a language m","authors_text":"Ankush Garg, Behnam Neyshabur, Behrooz Ghorbani, Biao Zhang, Colin Cherry, Maxim Krikun, Orhan Firat, Yamini Bansal","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-04T06:53:49Z","title":"Data Scaling Laws in NMT: The Effect of Noise and Architecture"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.01994","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:cf7b24d4660040784c5f91fed792785907f76b13ce0faa0a189565ed75e09813","target":"record","created_at":"2026-07-05T03:54:07Z","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":"1ca3c26ba11c04a15453a4071109437e31239dcf7ffe7d7b86feb1b8238ebe32","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-04T06:53:49Z","title_canon_sha256":"2a8ac3f328e967083e12b88d0cc007252740bac1fc44656318b8a22d822e212c"},"schema_version":"1.0","source":{"id":"2202.01994","kind":"arxiv","version":1}},"canonical_sha256":"6bf3291f14b79e15190a8572e965ae75c33a7cf29cf00acc5a5820e81d4f7d35","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6bf3291f14b79e15190a8572e965ae75c33a7cf29cf00acc5a5820e81d4f7d35","first_computed_at":"2026-07-05T03:54:07.853960Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:54:07.853960Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LBhrZ8FTNpt8XVB3LQP6ILDZ//fL41nQezptaqXGhwjkVzqbie2t9rbEQAro8zZ7EPU+TRq1R/PP7JQ51o/4DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:54:07.854373Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.01994","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cf7b24d4660040784c5f91fed792785907f76b13ce0faa0a189565ed75e09813","sha256:1b5fbd0fe01d7477879e3ce76e4924bc4ea22c44c438d3dc33aab942936472b8"],"state_sha256":"49fef23e1a9c3935c206ce6d065fb506572f37f313492e669d4dfe28906ee005"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9TC0RN5629yEkgPuNInEQVtbK8GLjVul4OOaPw+xFu2kI+R7s2onUfiah6TDumE8mJOGvggy6jGXmfylY8tBAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T15:01:05.029575Z","bundle_sha256":"54913d076d7c1ca8836a028ff870e17a6cb02f61d567c26a2e86060bac3b136d"}}