{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:I2BP5G24VWFBF4WXJ7XT3WGTSD","short_pith_number":"pith:I2BP5G24","canonical_record":{"source":{"id":"1909.08478","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-18T14:38:34Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"089fda96614858cac274b8ef58e56cd8b6b682cbb4ab042c8a54e37e4306a9a6","abstract_canon_sha256":"97a1df658977c7be0788f324bcc4dd060b1ff5e659cb04545d03c876d77a2b17"},"schema_version":"1.0"},"canonical_sha256":"4682fe9b5cad8a12f2d74fef3dd8d390f5c5944529259bf0355bd9dceca3fcff","source":{"kind":"arxiv","id":"1909.08478","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.08478","created_at":"2026-07-05T00:05:31Z"},{"alias_kind":"arxiv_version","alias_value":"1909.08478v1","created_at":"2026-07-05T00:05:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.08478","created_at":"2026-07-05T00:05:31Z"},{"alias_kind":"pith_short_12","alias_value":"I2BP5G24VWFB","created_at":"2026-07-05T00:05:31Z"},{"alias_kind":"pith_short_16","alias_value":"I2BP5G24VWFBF4WX","created_at":"2026-07-05T00:05:31Z"},{"alias_kind":"pith_short_8","alias_value":"I2BP5G24","created_at":"2026-07-05T00:05:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:I2BP5G24VWFBF4WXJ7XT3WGTSD","target":"record","payload":{"canonical_record":{"source":{"id":"1909.08478","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-18T14:38:34Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"089fda96614858cac274b8ef58e56cd8b6b682cbb4ab042c8a54e37e4306a9a6","abstract_canon_sha256":"97a1df658977c7be0788f324bcc4dd060b1ff5e659cb04545d03c876d77a2b17"},"schema_version":"1.0"},"canonical_sha256":"4682fe9b5cad8a12f2d74fef3dd8d390f5c5944529259bf0355bd9dceca3fcff","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:05:31.109403Z","signature_b64":"TsErYhLWUVNuAOtoxJqmqdwJ6glIg1TvNwVypYUbYDxe0preQHgpPMP9iqOD4CAzfm/pfdlQHQiPPoH5wtXaDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4682fe9b5cad8a12f2d74fef3dd8d390f5c5944529259bf0355bd9dceca3fcff","last_reissued_at":"2026-07-05T00:05:31.108992Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:05:31.108992Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1909.08478","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":"2026-07-05T00:05:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zQJLdEVBaUnCoJn+FODg0nw2+ujDRLkYw+P8oO+WeRVr0zRC6h1hStfWAPsOKkid7JFUiXd3pV7l/sNeu8vnDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T16:41:35.112813Z"},"content_sha256":"65b1793e7423b9b7f9ea95aca0eafce46bfacbfc28a26629bbe31077c3846ffa","schema_version":"1.0","event_id":"sha256:65b1793e7423b9b7f9ea95aca0eafce46bfacbfc28a26629bbe31077c3846ffa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:I2BP5G24VWFBF4WXJ7XT3WGTSD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Simple, Scalable Adaptation for Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ankur Bapna, Naveen Arivazhagan, Orhan Firat","submitted_at":"2019-09-18T14:38:34Z","abstract_excerpt":"Fine-tuning pre-trained Neural Machine Translation (NMT) models is the dominant approach for adapting to new languages and domains. However, fine-tuning requires adapting and maintaining a separate model for each target task. We propose a simple yet efficient approach for adaptation in NMT. Our proposed approach consists of injecting tiny task specific adapter layers into a pre-trained model. These lightweight adapters, with just a small fraction of the original model size, adapt the model to multiple individual tasks simultaneously. We evaluate our approach on two tasks: (i) Domain Adaptation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.08478","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/1909.08478/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":"2026-07-05T00:05:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S2zE9hShZ5dGG9wJPtxmN/S1tY4Fpy6JbkjwwOBQi4CoXNq7dX4xmNnDupbCmwgSI6aMR0oD1OFkd6FxlLReAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T16:41:35.113399Z"},"content_sha256":"adde93852e82f5eb4c330cdc80209a845d2ca68de6333be4d6e86860e2012574","schema_version":"1.0","event_id":"sha256:adde93852e82f5eb4c330cdc80209a845d2ca68de6333be4d6e86860e2012574"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I2BP5G24VWFBF4WXJ7XT3WGTSD/bundle.json","state_url":"https://pith.science/pith/I2BP5G24VWFBF4WXJ7XT3WGTSD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I2BP5G24VWFBF4WXJ7XT3WGTSD/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":"2026-08-09T16:41:35Z","links":{"resolver":"https://pith.science/pith/I2BP5G24VWFBF4WXJ7XT3WGTSD","bundle":"https://pith.science/pith/I2BP5G24VWFBF4WXJ7XT3WGTSD/bundle.json","state":"https://pith.science/pith/I2BP5G24VWFBF4WXJ7XT3WGTSD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I2BP5G24VWFBF4WXJ7XT3WGTSD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:I2BP5G24VWFBF4WXJ7XT3WGTSD","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":"97a1df658977c7be0788f324bcc4dd060b1ff5e659cb04545d03c876d77a2b17","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-18T14:38:34Z","title_canon_sha256":"089fda96614858cac274b8ef58e56cd8b6b682cbb4ab042c8a54e37e4306a9a6"},"schema_version":"1.0","source":{"id":"1909.08478","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.08478","created_at":"2026-07-05T00:05:31Z"},{"alias_kind":"arxiv_version","alias_value":"1909.08478v1","created_at":"2026-07-05T00:05:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.08478","created_at":"2026-07-05T00:05:31Z"},{"alias_kind":"pith_short_12","alias_value":"I2BP5G24VWFB","created_at":"2026-07-05T00:05:31Z"},{"alias_kind":"pith_short_16","alias_value":"I2BP5G24VWFBF4WX","created_at":"2026-07-05T00:05:31Z"},{"alias_kind":"pith_short_8","alias_value":"I2BP5G24","created_at":"2026-07-05T00:05:31Z"}],"graph_snapshots":[{"event_id":"sha256:adde93852e82f5eb4c330cdc80209a845d2ca68de6333be4d6e86860e2012574","target":"graph","created_at":"2026-07-05T00:05:31Z","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/1909.08478/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fine-tuning pre-trained Neural Machine Translation (NMT) models is the dominant approach for adapting to new languages and domains. However, fine-tuning requires adapting and maintaining a separate model for each target task. We propose a simple yet efficient approach for adaptation in NMT. Our proposed approach consists of injecting tiny task specific adapter layers into a pre-trained model. These lightweight adapters, with just a small fraction of the original model size, adapt the model to multiple individual tasks simultaneously. We evaluate our approach on two tasks: (i) Domain Adaptation","authors_text":"Ankur Bapna, Naveen Arivazhagan, Orhan Firat","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-18T14:38:34Z","title":"Simple, Scalable Adaptation for Neural Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.08478","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":"sha256:65b1793e7423b9b7f9ea95aca0eafce46bfacbfc28a26629bbe31077c3846ffa","target":"record","created_at":"2026-07-05T00:05:31Z","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":"97a1df658977c7be0788f324bcc4dd060b1ff5e659cb04545d03c876d77a2b17","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-18T14:38:34Z","title_canon_sha256":"089fda96614858cac274b8ef58e56cd8b6b682cbb4ab042c8a54e37e4306a9a6"},"schema_version":"1.0","source":{"id":"1909.08478","kind":"arxiv","version":1}},"canonical_sha256":"4682fe9b5cad8a12f2d74fef3dd8d390f5c5944529259bf0355bd9dceca3fcff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4682fe9b5cad8a12f2d74fef3dd8d390f5c5944529259bf0355bd9dceca3fcff","first_computed_at":"2026-07-05T00:05:31.108992Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:05:31.108992Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TsErYhLWUVNuAOtoxJqmqdwJ6glIg1TvNwVypYUbYDxe0preQHgpPMP9iqOD4CAzfm/pfdlQHQiPPoH5wtXaDA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:05:31.109403Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.08478","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:65b1793e7423b9b7f9ea95aca0eafce46bfacbfc28a26629bbe31077c3846ffa","sha256:adde93852e82f5eb4c330cdc80209a845d2ca68de6333be4d6e86860e2012574"],"state_sha256":"817ecd23b1e59fd529894f24f83520cc57370f23d45640b5f36c256b277f6f12"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vhBHSPX+GCXg63pcY2Cgm83aWeX/rmkG/XrzxDinuit/7yEIV6y0z5HF8b179z2y3QiXEqX/XvhhU5PZGWqmDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T16:41:35.117766Z","bundle_sha256":"506629c8e49e926f4e0dfc064893211b499337377444cd57e6e9997a2203e177"}}