{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:45JQGEVUZZKLLHWRSJG3UDN7GC","short_pith_number":"pith:45JQGEVU","canonical_record":{"source":{"id":"1911.02692","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-07T00:54:06Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3399fb5cadab2ae7ddd15e0f42883dd21889978cd9899cc01324e2bd9c95787e","abstract_canon_sha256":"5ff8443b495959a8b90375da3b786e191a6572e106941171e11e3ccc40cab5e2"},"schema_version":"1.0"},"canonical_sha256":"e7530312b4ce54b59ed1924dba0dbf309e2500043312367d5b4448a52b371c1d","source":{"kind":"arxiv","id":"1911.02692","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.02692","created_at":"2026-07-05T02:14:40Z"},{"alias_kind":"arxiv_version","alias_value":"1911.02692v3","created_at":"2026-07-05T02:14:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.02692","created_at":"2026-07-05T02:14:40Z"},{"alias_kind":"pith_short_12","alias_value":"45JQGEVUZZKL","created_at":"2026-07-05T02:14:40Z"},{"alias_kind":"pith_short_16","alias_value":"45JQGEVUZZKLLHWR","created_at":"2026-07-05T02:14:40Z"},{"alias_kind":"pith_short_8","alias_value":"45JQGEVU","created_at":"2026-07-05T02:14:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:45JQGEVUZZKLLHWRSJG3UDN7GC","target":"record","payload":{"canonical_record":{"source":{"id":"1911.02692","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-07T00:54:06Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3399fb5cadab2ae7ddd15e0f42883dd21889978cd9899cc01324e2bd9c95787e","abstract_canon_sha256":"5ff8443b495959a8b90375da3b786e191a6572e106941171e11e3ccc40cab5e2"},"schema_version":"1.0"},"canonical_sha256":"e7530312b4ce54b59ed1924dba0dbf309e2500043312367d5b4448a52b371c1d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:14:40.604204Z","signature_b64":"HKJu9Yi+4YUv4U1Q7BvRhzbot56dVIdkt+/4rD15G17aV8u/EQd9PJePwAuX3nNrzKdrK+TlVWAc4LnmuNI2Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7530312b4ce54b59ed1924dba0dbf309e2500043312367d5b4448a52b371c1d","last_reissued_at":"2026-07-05T02:14:40.603826Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:14:40.603826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1911.02692","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:14:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xZv5KB9QvNrtiHb9s9kSzxMJuCUxeYKypNo6ZAQ41UEORGVW0GsYN28a9W/xT+WGrgLogo5Xh0iIjfxLYBLGDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:31:44.249768Z"},"content_sha256":"0a12a1409694ed4b8e4ed7b838a2e596decf71bd4e07c903e101e0d0955d0717","schema_version":"1.0","event_id":"sha256:0a12a1409694ed4b8e4ed7b838a2e596decf71bd4e07c903e101e0d0955d0717"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:45JQGEVUZZKLLHWRSJG3UDN7GC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-Domain Neural Machine Translation with Word-Level Adaptive Layer-wise Domain Mixing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Chen Liang, Chong Wang, Haoming Jiang, Tuo Zhao","submitted_at":"2019-11-07T00:54:06Z","abstract_excerpt":"Many multi-domain neural machine translation (NMT) models achieve knowledge transfer by enforcing one encoder to learn shared embedding across domains. However, this design lacks adaptation to individual domains. To overcome this limitation, we propose a novel multi-domain NMT model using individual modules for each domain, on which we apply word-level, adaptive and layer-wise domain mixing. We first observe that words in a sentence are often related to multiple domains. Hence, we assume each word has a domain proportion, which indicates its domain preference. Then word representations are obt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.02692","kind":"arxiv","version":3},"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/1911.02692/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":"2026-07-05T02:14:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mPcJQJWpqjdfZxHYzgkGCQPihfSnbZ2NRvbWGGBNx7bGM+sOJrBG+1L94/8L+kUO8/VhdKRXigVX+7uuluhHAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:31:44.306725Z"},"content_sha256":"29aa76c2469c7b782ba5862b5edf63ae0b6c853daca019963d58c25f97de5d4d","schema_version":"1.0","event_id":"sha256:29aa76c2469c7b782ba5862b5edf63ae0b6c853daca019963d58c25f97de5d4d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/45JQGEVUZZKLLHWRSJG3UDN7GC/bundle.json","state_url":"https://pith.science/pith/45JQGEVUZZKLLHWRSJG3UDN7GC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/45JQGEVUZZKLLHWRSJG3UDN7GC/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":"2026-08-03T15:31:44Z","links":{"resolver":"https://pith.science/pith/45JQGEVUZZKLLHWRSJG3UDN7GC","bundle":"https://pith.science/pith/45JQGEVUZZKLLHWRSJG3UDN7GC/bundle.json","state":"https://pith.science/pith/45JQGEVUZZKLLHWRSJG3UDN7GC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/45JQGEVUZZKLLHWRSJG3UDN7GC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:45JQGEVUZZKLLHWRSJG3UDN7GC","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":"5ff8443b495959a8b90375da3b786e191a6572e106941171e11e3ccc40cab5e2","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-07T00:54:06Z","title_canon_sha256":"3399fb5cadab2ae7ddd15e0f42883dd21889978cd9899cc01324e2bd9c95787e"},"schema_version":"1.0","source":{"id":"1911.02692","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.02692","created_at":"2026-07-05T02:14:40Z"},{"alias_kind":"arxiv_version","alias_value":"1911.02692v3","created_at":"2026-07-05T02:14:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.02692","created_at":"2026-07-05T02:14:40Z"},{"alias_kind":"pith_short_12","alias_value":"45JQGEVUZZKL","created_at":"2026-07-05T02:14:40Z"},{"alias_kind":"pith_short_16","alias_value":"45JQGEVUZZKLLHWR","created_at":"2026-07-05T02:14:40Z"},{"alias_kind":"pith_short_8","alias_value":"45JQGEVU","created_at":"2026-07-05T02:14:40Z"}],"graph_snapshots":[{"event_id":"sha256:29aa76c2469c7b782ba5862b5edf63ae0b6c853daca019963d58c25f97de5d4d","target":"graph","created_at":"2026-07-05T02:14:40Z","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/1911.02692/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many multi-domain neural machine translation (NMT) models achieve knowledge transfer by enforcing one encoder to learn shared embedding across domains. However, this design lacks adaptation to individual domains. To overcome this limitation, we propose a novel multi-domain NMT model using individual modules for each domain, on which we apply word-level, adaptive and layer-wise domain mixing. We first observe that words in a sentence are often related to multiple domains. Hence, we assume each word has a domain proportion, which indicates its domain preference. Then word representations are obt","authors_text":"Chen Liang, Chong Wang, Haoming Jiang, Tuo Zhao","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-07T00:54:06Z","title":"Multi-Domain Neural Machine Translation with Word-Level Adaptive Layer-wise Domain Mixing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.02692","kind":"arxiv","version":3},"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":"sha256:0a12a1409694ed4b8e4ed7b838a2e596decf71bd4e07c903e101e0d0955d0717","target":"record","created_at":"2026-07-05T02:14:40Z","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":"5ff8443b495959a8b90375da3b786e191a6572e106941171e11e3ccc40cab5e2","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-07T00:54:06Z","title_canon_sha256":"3399fb5cadab2ae7ddd15e0f42883dd21889978cd9899cc01324e2bd9c95787e"},"schema_version":"1.0","source":{"id":"1911.02692","kind":"arxiv","version":3}},"canonical_sha256":"e7530312b4ce54b59ed1924dba0dbf309e2500043312367d5b4448a52b371c1d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e7530312b4ce54b59ed1924dba0dbf309e2500043312367d5b4448a52b371c1d","first_computed_at":"2026-07-05T02:14:40.603826Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:14:40.603826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HKJu9Yi+4YUv4U1Q7BvRhzbot56dVIdkt+/4rD15G17aV8u/EQd9PJePwAuX3nNrzKdrK+TlVWAc4LnmuNI2Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:14:40.604204Z","signed_message":"canonical_sha256_bytes"},"source_id":"1911.02692","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0a12a1409694ed4b8e4ed7b838a2e596decf71bd4e07c903e101e0d0955d0717","sha256:29aa76c2469c7b782ba5862b5edf63ae0b6c853daca019963d58c25f97de5d4d"],"state_sha256":"1c21dbc9eb9f2efc282cec933097366e56d7626f4129011eb75546ee135224f7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7xkz5Sv1izVO86GpruFTqJODPxvahzOE87//wpD5a2z8i48Oq/0d5mmn94ukIUCBxqbB099oyPx9HCeACzyACw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T15:31:44.314187Z","bundle_sha256":"0eebf1b505ab9311040ea5fade3d10cde702132ff0e73ba11a13a9d810aa7008"}}