{"as_of":"2026-08-16T15:06:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e45de49b6362140cbe89c088247e594f9e99c2c2c6792b6c71b3226e8d1e4d3b","coverage":[{"denominator":26,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":26,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T20:33:13.008044Z","state":"measured"},{"denominator":26,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":26,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2505.13554/citation-record","integrity":"/paper/2505.13554/integrity","json":"/paper/2505.13554/citation-record.json","paper":"/paper/2505.13554"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:33:12.897180Z","title":"online\" 'onlinestring :=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.13554","last_updated":"2025-05-19T06:50:52Z","snapshot_observed_at":"2026-08-15T20:24:32.644052Z","submitted_at":"2025-05-19T06:50:52Z","title":"Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-15T20:33:12.897180Z"},"links":{"citing_paper":"/paper/2505.13554"},"observation_digest":"sha256:2d047b0f4aa457f7017ca113d31536f3e316f16e0dfd5b89a95971f088d4aae0","observation_id":"89d63856-e34d-40af-b381-b64d8a295b73","resolution":{"observed_at":"2026-08-15T20:33:12.897180Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:33:12.902235Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.13554","last_updated":"2025-05-19T06:50:52Z","snapshot_observed_at":"2026-08-15T20:24:32.644052Z","submitted_at":"2025-05-19T06:50:52Z","title":"Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-15T20:33:12.902235Z"},"links":{"citing_paper":"/paper/2505.13554"},"observation_digest":"sha256:d8f3766d984453db9b22375cac5741b6125bc328b62d4125d75ffff6582813fa","observation_id":"ffb5e728-19cf-459d-bfa5-67ae8196edc0","resolution":{"observed_at":"2026-08-15T20:33:12.902235Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1409.0473","last_updated":"2016-05-19T21:53:22Z","snapshot_observed_at":"2026-08-12T12:07:33.202888Z","submitted_at":"2014-09-01T16:33:02Z","title":"Neural Machine Translation by Jointly Learning to Align and Translate","version":7},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1409.0473","snapshot_observed_at":"2026-08-15T20:33:12.906520Z","title":null,"venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.13554","last_updated":"2025-05-19T06:50:52Z","snapshot_observed_at":"2026-08-15T20:24:32.644052Z","submitted_at":"2025-05-19T06:50:52Z","title":"Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-15T20:33:12.906520Z"},"links":{"cited_paper":"/paper/1409.0473","citing_paper":"/paper/2505.13554"},"observation_digest":"sha256:cc997d5adf31ba56b45acf09da059e5f6bb9f371707409eb0f0ca026fd20c388","observation_id":"18d1c06e-45f7-4063-8eca-56d1aa4d7395","resolution":{"observed_at":"2026-08-15T20:33:12.906520Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1911.02116","last_updated":"2020-04-08T01:02:17Z","snapshot_observed_at":"2026-08-16T12:39:33.749100Z","submitted_at":"2019-11-05T22:42:00Z","title":"Unsupervised Cross-lingual Representation Learning at Scale","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1911.02116","snapshot_observed_at":"2026-08-15T20:33:12.912422Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.13554","last_updated":"2025-05-19T06:50:52Z","snapshot_observed_at":"2026-08-15T20:24:32.644052Z","submitted_at":"2025-05-19T06:50:52Z","title":"Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-15T20:33:12.912422Z"},"links":{"cited_paper":"/paper/1911.02116","citing_paper":"/paper/2505.13554"},"observation_digest":"sha256:025260fb9741007ef1553ff12189037b67b3f0c9515aef64f8f6f6b1a975aabd","observation_id":"9c15caf3-2559-40f7-9fa5-21ab6f57dbbd","resolution":{"observed_at":"2026-08-15T20:33:12.912422Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2207.04672","last_updated":"2022-08-25T17:10:53Z","snapshot_observed_at":"2026-07-06T13:29:47.927628Z","submitted_at":"2022-07-11T07:33:36Z","title":"No Language Left Behind: Scaling Human-Centered Machine Translation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2207.04672","snapshot_observed_at":"2026-08-15T20:33:12.916137Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.13554","last_updated":"2025-05-19T06:50:52Z","snapshot_observed_at":"2026-08-15T20:24:32.644052Z","submitted_at":"2025-05-19T06:50:52Z","title":"Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-15T20:33:12.916137Z"},"links":{"cited_paper":"/paper/2207.04672","citing_paper":"/paper/2505.13554"},"observation_digest":"sha256:c466aaf04014c95ffd794d5661211a3fa71f76d3d508f4115d8c38823fd42ec8","observation_id":"c72a1327-105e-4e67-b504-1888494c68fa","resolution":{"observed_at":"2026-08-15T20:33:12.916137Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:33:12.919809Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.13554","last_updated":"2025-05-19T06:50:52Z","snapshot_observed_at":"2026-08-15T20:24:32.644052Z","submitted_at":"2025-05-19T06:50:52Z","title":"Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-15T20:33:12.919809Z"},"links":{"citing_paper":"/paper/2505.13554"},"observation_digest":"sha256:cd10d08fc0d6c537baf899776c58ed789fcd338b3db1bbfd53d1a117ec9573b4","observation_id":"04d00252-cb69-4ac8-9b46-b9fb9148568e","resolution":{"observed_at":"2026-08-15T20:33:12.919809Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.10608","last_updated":"2020-07-20T08:37:22Z","snapshot_observed_at":"2026-08-11T19:00:42.984405Z","submitted_at":"2020-05-21T12:38:06Z","title":"Unsupervised Quality Estimation for Neural Machine Translation","version":2},"cited_work":{"arxiv_id":"2005.10608","doi":null,"metadata_source":"pith","pith_arxiv_id":"2005.10608","snapshot_observed_at":"2026-08-15T20:33:13.235083Z","title":"Unsupervised Quality Estimation for Neural Machine Translation","venue":"cs.CL","work_id":"ccaba4d5-695b-4679-97b3-7bacb46a4c6d","year":2020},"citing_paper":{"arxiv_id":"2505.13554","last_updated":"2025-05-19T06:50:52Z","snapshot_observed_at":"2026-08-15T20:24:32.644052Z","submitted_at":"2025-05-19T06:50:52Z","title":"Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-15T20:33:12.923905Z"},"links":{"cited_paper":"/paper/2005.10608","citing_paper":"/paper/2505.13554"},"observation_digest":"sha256:3202bd4b4ac0e285d044380b73221ae939fb463f8b8d247e2b04dba8679bab7c","observation_id":"88fbdf50-7e02-4865-b528-75704095876d","resolution":{"observed_at":"2026-08-15T20:33:13.239745Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2302.09210","last_updated":"2023-02-18T02:11:36Z","snapshot_observed_at":"2026-08-13T12:42:25.435316Z","submitted_at":"2023-02-18T02:11:36Z","title":"How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.09210","snapshot_observed_at":"2026-08-15T20:33:12.928616Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.13554","last_updated":"2025-05-19T06:50:52Z","snapshot_observed_at":"2026-08-15T20:24:32.644052Z","submitted_at":"2025-05-19T06:50:52Z","title":"Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-15T20:33:12.928616Z"},"links":{"cited_paper":"/paper/2302.09210","citing_paper":"/paper/2505.13554"},"observation_digest":"sha256:efdb6ac0f3179b2c8ecff4710537a7df470b516799ade03e9f3e4cf68b5eed7e","observation_id":"20049e76-c664-4e69-b377-c5810fe0edfa","resolution":{"observed_at":"2026-08-15T20:33:12.928616Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2301.13294","last_updated":"2023-05-09T11:04:43Z","snapshot_observed_at":"2026-08-16T13:07:12.670093Z","submitted_at":"2023-01-30T21:17:15Z","title":"Adaptive Machine Translation with Large Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.13294","snapshot_observed_at":"2026-08-15T20:33:12.933554Z","title":"Kelleher, and Andy Way","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.13554","last_updated":"2025-05-19T06:50:52Z","snapshot_observed_at":"2026-08-15T20:24:32.644052Z","submitted_at":"2025-05-19T06:50:52Z","title":"Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-15T20:33:12.933554Z"},"links":{"cited_paper":"/paper/2301.13294","citing_paper":"/paper/2505.13554"},"observation_digest":"sha256:cd5c72720844ff7209f0c34d9c4e38eefedd2d720f6350dd8d827be7a457335c","observation_id":"299d4070-90db-425d-b6a0-0a13c12a81e0","resolution":{"observed_at":"2026-08-15T20:33:12.933554Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:33:12.938009Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.13554","last_updated":"2025-05-19T06:50:52Z","snapshot_observed_at":"2026-08-15T20:24:32.644052Z","submitted_at":"2025-05-19T06:50:52Z","title":"Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-15T20:33:12.938009Z"},"links":{"citing_paper":"/paper/2505.13554"},"observation_digest":"sha256:7fe1696faf0a980ea7b76775e0255413469b2ebbb1acda51e1e334615f56cc35","observation_id":"3887c801-4da2-4ed3-8430-ef90d67732eb","resolution":{"observed_at":"2026-08-15T20:33:12.938009Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.02155","last_updated":"2022-03-04T07:04:42Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-03-04T07:04:42Z","title":"Training language models to follow instructions with human feedback","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.02155","snapshot_observed_at":"2026-08-15T20:33:12.942049Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.13554","last_updated":"2025-05-19T06:50:52Z","snapshot_observed_at":"2026-08-15T20:24:32.644052Z","submitted_at":"2025-05-19T06:50:52Z","title":"Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-15T20:33:12.942049Z"},"links":{"cited_paper":"/paper/2203.02155","citing_paper":"/paper/2505.13554"},"observation_digest":"sha256:da2250045f7af30a698eb085e2d2585c3499c2f9bd4b8894eb4f3f0cf96378a8","observation_id":"2014b8a1-07bc-42bd-90e4-50facb4859ca","resolution":{"observed_at":"2026-08-15T20:33:12.942049Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:33:12.946796Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.13554","last_updated":"2025-05-19T06:50:52Z","snapshot_observed_at":"2026-08-15T20:24:32.644052Z","submitted_at":"2025-05-19T06:50:52Z","title":"Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-15T20:33:12.946796Z"},"links":{"citing_paper":"/paper/2505.13554"},"observation_digest":"sha256:88a94015f70f56099fdd81838f50f3766bf17fc73397d4375b42a5a275eb6a44","observation_id":"7a025b8b-6126-4c1a-87d2-570eac3d2e0b","resolution":{"observed_at":"2026-08-15T20:33:12.946796Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:33:12.951035Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.13554","last_updated":"2025-05-19T06:50:52Z","snapshot_observed_at":"2026-08-15T20:24:32.644052Z","submitted_at":"2025-05-19T06:50:52Z","title":"Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-15T20:33:12.951035Z"},"links":{"citing_paper":"/paper/2505.13554"},"observation_digest":"sha256:71b39bfd9c1958a41550e35e4248f5c48bd32d2c8ff21f3ed16d58f6c57be3ba","observation_id":"463bdccd-7808-42a8-802c-ca1f67ab23c3","resolution":{"observed_at":"2026-08-15T20:33:12.951035Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2209.06243","last_updated":"2022-09-13T18:05:12Z","snapshot_observed_at":"2026-08-13T14:27:34.089347Z","submitted_at":"2022-09-13T18:05:12Z","title":"CometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Task","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.06243","snapshot_observed_at":"2026-08-15T20:33:12.959769Z","title":"Guerreiro, Chrysoula Zerva, Ana C","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.13554","last_updated":"2025-05-19T06:50:52Z","snapshot_observed_at":"2026-08-15T20:24:32.644052Z","submitted_at":"2025-05-19T06:50:52Z","title":"Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-15T20:33:12.959769Z"},"links":{"cited_paper":"/paper/2209.06243","citing_paper":"/paper/2505.13554"},"observation_digest":"sha256:0e9435e1712123fa18609e4ae203ca4be18c108c6a971dd0c036045bc74a2676","observation_id":"fa44ce71-8cdb-42c7-9612-d3dddd0cce34","resolution":{"observed_at":"2026-08-15T20:33:12.959769Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:33:12.963777Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.13554","last_updated":"2025-05-19T06:50:52Z","snapshot_observed_at":"2026-08-15T20:24:32.644052Z","submitted_at":"2025-05-19T06:50:52Z","title":"Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-15T20:33:12.963777Z"},"links":{"citing_paper":"/paper/2505.13554"},"observation_digest":"sha256:baabe33971d964e614abedb7f5f4aec0ff19a141c23955e01444ffad7e662938","observation_id":"83635262-5e32-4a5e-a03e-8e829a63e766","resolution":{"observed_at":"2026-08-15T20:33:12.963777Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.3390/info14100574","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:33:13.042506Z","title":null,"venue":null,"work_id":"f9933b13-4760-4782-9e01-8be15411e924","year":2023},"citing_paper":{"arxiv_id":"2505.13554","last_updated":"2025-05-19T06:50:52Z","snapshot_observed_at":"2026-08-15T20:24:32.644052Z","submitted_at":"2025-05-19T06:50:52Z","title":"Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-15T20:33:12.967663Z"},"links":{"citing_paper":"/paper/2505.13554"},"observation_digest":"sha256:57d64c4e05fa79c8dfc09fee9c9e3e134965b525f7aada31037d7ff58b1d953b","observation_id":"8f8cec74-55cd-4c8c-a4fa-9657eeaafbce","resolution":{"observed_at":"2026-08-15T20:33:13.047844Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1409.3215","last_updated":"2014-12-14T20:59:51Z","snapshot_observed_at":"2026-08-14T23:19:57.426044Z","submitted_at":"2014-09-10T19:55:35Z","title":"Sequence to Sequence Learning with Neural Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1409.3215","snapshot_observed_at":"2026-08-15T20:33:12.971775Z","title":null,"venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2505.13554","last_updated":"2025-05-19T06:50:52Z","snapshot_observed_at":"2026-08-15T20:24:32.644052Z","submitted_at":"2025-05-19T06:50:52Z","title":"Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-15T20:33:12.971775Z"},"links":{"cited_paper":"/paper/1409.3215","citing_paper":"/paper/2505.13554"},"observation_digest":"sha256:9d35bd75974d26204153344ac2e3aae41069d45dccc3f61019b5c7e5296c8c03","observation_id":"c0aaec66-833b-4253-b551-198244ba8b7f","resolution":{"observed_at":"2026-08-15T20:33:12.971775Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.13971","last_updated":"2023-02-27T17:11:15Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-02-27T17:11:15Z","title":"LLaMA: Open and Efficient Foundation Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.13971","snapshot_observed_at":"2026-08-15T20:33:12.975902Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.13554","last_updated":"2025-05-19T06:50:52Z","snapshot_observed_at":"2026-08-15T20:24:32.644052Z","submitted_at":"2025-05-19T06:50:52Z","title":"Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-15T20:33:12.975902Z"},"links":{"cited_paper":"/paper/2302.13971","citing_paper":"/paper/2505.13554"},"observation_digest":"sha256:c59bfe3e8d6ede6551073183931ae6c1cde8d2aac71fca852ac0e086d4dbdf54","observation_id":"33ed4a23-7f0a-41db-9c0a-dfb15734afb8","resolution":{"observed_at":"2026-08-15T20:33:12.975902Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1706.03762","last_updated":"2023-08-02T00:41:18Z","snapshot_observed_at":"2026-08-16T05:25:19.960199Z","submitted_at":"2017-06-12T17:57:34Z","title":"Attention Is All You Need","version":7},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1706.03762","snapshot_observed_at":"2026-08-15T20:33:12.980099Z","title":"Gomez, Lukasz Kaiser, and Illia Polosukhin","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.13554","last_updated":"2025-05-19T06:50:52Z","snapshot_observed_at":"2026-08-15T20:24:32.644052Z","submitted_at":"2025-05-19T06:50:52Z","title":"Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-15T20:33:12.980099Z"},"links":{"cited_paper":"/paper/1706.03762","citing_paper":"/paper/2505.13554"},"observation_digest":"sha256:7d326adc504bd0c3566a9b9b5c12d5e49a1410be71e73b5b9e99714527314aad","observation_id":"fa1c4411-2731-490e-9eab-8895e7d8c7a6","resolution":{"observed_at":"2026-08-15T20:33:12.980099Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1906.01787","last_updated":"2019-06-05T02:24:12Z","snapshot_observed_at":"2026-08-14T16:20:46.561829Z","submitted_at":"2019-06-05T02:24:12Z","title":"Learning Deep Transformer Models for Machine Translation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1906.01787","snapshot_observed_at":"2026-08-15T20:33:12.984119Z","title":"Wong, and Lidia S","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.13554","last_updated":"2025-05-19T06:50:52Z","snapshot_observed_at":"2026-08-15T20:24:32.644052Z","submitted_at":"2025-05-19T06:50:52Z","title":"Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-15T20:33:12.984119Z"},"links":{"cited_paper":"/paper/1906.01787","citing_paper":"/paper/2505.13554"},"observation_digest":"sha256:5d49f581d2fd218bc1dc30fb140ece3d46919e4630aec2651000238d33869264","observation_id":"88493198-826f-479c-8876-edf891eee8f0","resolution":{"observed_at":"2026-08-15T20:33:12.984119Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.05722","last_updated":"2022-06-16T11:29:37Z","snapshot_observed_at":"2026-08-13T17:54:55.471780Z","submitted_at":"2021-10-12T03:17:03Z","title":"LightSeq2: Accelerated Training for Transformer-based Models on GPUs","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.05722","snapshot_observed_at":"2026-08-15T20:33:12.988266Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.13554","last_updated":"2025-05-19T06:50:52Z","snapshot_observed_at":"2026-08-15T20:24:32.644052Z","submitted_at":"2025-05-19T06:50:52Z","title":"Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-15T20:33:12.988266Z"},"links":{"cited_paper":"/paper/2110.05722","citing_paper":"/paper/2505.13554"},"observation_digest":"sha256:332866ab1c6294e6f9e67c3f5f1375cea64d068b5ec9faad96e97c1f03faf3f2","observation_id":"37a50796-4c88-4cd4-b113-54e43a0d7d89","resolution":{"observed_at":"2026-08-15T20:33:12.988266Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:33:13.303772Z","title":null,"venue":null,"work_id":"28ba1df5-d511-42cb-a420-5112fa00d9d5","year":2021},"citing_paper":{"arxiv_id":"2505.13554","last_updated":"2025-05-19T06:50:52Z","snapshot_observed_at":"2026-08-15T20:24:32.644052Z","submitted_at":"2025-05-19T06:50:52Z","title":"Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-15T20:33:12.992502Z"},"links":{"citing_paper":"/paper/2505.13554"},"observation_digest":"sha256:d2856e232fa05dfaa14f8f54fddb08e6b4559dc17e1d11164b8bb1adebaa39ed","observation_id":"e928ae3e-f9dd-4862-bfde-1513b55a7fc1","resolution":{"observed_at":"2026-08-15T20:33:13.308025Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:33:13.291463Z","title":null,"venue":null,"work_id":"ac7346f4-70c4-48a2-900f-3e42f11963ed","year":2022},"citing_paper":{"arxiv_id":"2505.13554","last_updated":"2025-05-19T06:50:52Z","snapshot_observed_at":"2026-08-15T20:24:32.644052Z","submitted_at":"2025-05-19T06:50:52Z","title":"Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-15T20:33:12.996259Z"},"links":{"citing_paper":"/paper/2505.13554"},"observation_digest":"sha256:f02d38345609249c701ac2db779ebe78edab5e176da70735f60f951f05e372f9","observation_id":"d46da066-31c3-4751-ae83-13c6d2eaf560","resolution":{"observed_at":"2026-08-15T20:33:13.295510Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:33:12.999979Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.13554","last_updated":"2025-05-19T06:50:52Z","snapshot_observed_at":"2026-08-15T20:24:32.644052Z","submitted_at":"2025-05-19T06:50:52Z","title":"Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-15T20:33:12.999979Z"},"links":{"citing_paper":"/paper/2505.13554"},"observation_digest":"sha256:aa307e493d14af3203722ce1cc6204ac1eab34342d1caa5b97edebb13509b4ff","observation_id":"8d5ff02e-d431-4fe5-b542-891a35aba946","resolution":{"observed_at":"2026-08-15T20:33:12.999979Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.02851","last_updated":"2024-05-27T07:52:38Z","snapshot_observed_at":"2026-08-16T14:45:48.444798Z","submitted_at":"2023-11-06T03:41:57Z","title":"Improving Machine Translation with Large Language Models: A Preliminary Study with Cooperative Decoding","version":2},"cited_work":{"arxiv_id":"2311.02851","doi":null,"metadata_source":"pith","pith_arxiv_id":"2311.02851","snapshot_observed_at":"2026-08-15T20:33:13.093710Z","title":"Improving Machine Translation with Large Language Models: A Preliminary Study with Cooperative Decoding","venue":"cs.CL","work_id":"b582d496-99bf-4e45-9540-662ffeb1eb2a","year":2023},"citing_paper":{"arxiv_id":"2505.13554","last_updated":"2025-05-19T06:50:52Z","snapshot_observed_at":"2026-08-15T20:24:32.644052Z","submitted_at":"2025-05-19T06:50:52Z","title":"Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-15T20:33:13.003755Z"},"links":{"cited_paper":"/paper/2311.02851","citing_paper":"/paper/2505.13554"},"observation_digest":"sha256:af16361f804a730252396108dfbfbfb22ebe3a0e528c1e55e1674ad302aea10c","observation_id":"3476cc39-6f01-4f8f-8bfe-df2c305ec10f","resolution":{"observed_at":"2026-08-15T20:33:13.098688Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2301.07069","last_updated":"2023-01-18T11:30:05Z","snapshot_observed_at":"2026-08-13T13:03:00.906503Z","submitted_at":"2023-01-17T18:32:06Z","title":"Prompting Large Language Model for Machine Translation: A Case Study","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.07069","snapshot_observed_at":"2026-08-15T20:33:13.008044Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.13554","last_updated":"2025-05-19T06:50:52Z","snapshot_observed_at":"2026-08-15T20:24:32.644052Z","submitted_at":"2025-05-19T06:50:52Z","title":"Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-15T20:33:13.008044Z"},"links":{"cited_paper":"/paper/2301.07069","citing_paper":"/paper/2505.13554"},"observation_digest":"sha256:ce1742d01eb57c5368103d26502385d2f2c5ae941f5ad86a9ec8e048ddf43430","observation_id":"657d53f0-d419-42a9-b39f-c3edb819b865","resolution":{"observed_at":"2026-08-15T20:33:13.008044Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2505.13554","last_updated":"2025-05-19T06:50:52Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-15T20:24:32.644052Z","submitted_at":"2025-05-19T06:50:52Z","title":"Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation"},"reference_resolution":{"displayed":26,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":23,"verified_exact":3,"verified_fuzzy":0},"total_outbound_references":26},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 26 of 26 outbound references and 0 inbound Pith citation observations for arXiv:2505.13554."}