{"as_of":"2026-08-18T05:37:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b4d921a65cbf8948bdf2aaf6cb11722b77a214ff9cc2d7e0a9951852672ca9ca","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":3,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":3,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T18:11:55.364167Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-13T21:49:52.252152Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2204.02967","last_updated":"2022-09-13T17:00:55Z","snapshot_observed_at":"2026-08-16T17:08:48.467808Z","submitted_at":"2022-04-06T17:59:22Z","title":"Enhanced Direct Speech-to-Speech Translation Using Self-supervised Pre-training and Data Augmentation","version":3},"cited_work":{"arxiv_id":"2204.02967","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2204.02967","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Enhanced direct speech-to-speech translation using self-supervised pre-training and data augmentation","venue":null,"work_id":"60243ba4-c915-4bb7-b8cd-083827396fe9","year":null},"citing_paper":{"arxiv_id":"2210.13438","last_updated":"2022-10-24T17:52:02Z","snapshot_observed_at":"2026-08-15T04:43:16.361751Z","submitted_at":"2022-10-24T17:52:02Z","title":"High Fidelity Neural Audio Compression","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-05-13T21:49:52.184932Z"},"links":{"cited_paper":"/paper/2204.02967","citing_paper":"/paper/2210.13438"},"observation_digest":"sha256:8ce8a817fef03d95c6b86349f9830af807a616010b0c906f85bf004b35527fc0","observation_id":"41b2c46d-4f93-4ff0-a264-5e3a92384a0a","resolution":{"observed_at":"2026-05-13T21:49:52.253847Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2204.02967","last_updated":"2022-09-13T17:00:55Z","snapshot_observed_at":"2026-08-16T17:08:48.467808Z","submitted_at":"2022-04-06T17:59:22Z","title":"Enhanced Direct Speech-to-Speech Translation Using Self-supervised Pre-training and Data Augmentation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.02967","snapshot_observed_at":"2026-08-09T19:16:37.776878Z","title":"Enhanced direct speech-to-speech translation using self-supervised pre-training and data augmentation,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.00377","last_updated":"2025-02-01T09:29:21Z","snapshot_observed_at":"2026-08-16T09:56:33.713959Z","submitted_at":"2025-02-01T09:29:21Z","title":"When End-to-End is Overkill: Rethinking Cascaded Speech-to-Text Translation","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-09T19:16:37.776878Z"},"links":{"cited_paper":"/paper/2204.02967","citing_paper":"/paper/2502.00377"},"observation_digest":"sha256:9e4729ebb77c462814117978f0bcf8ad05928ece43a02b8d4600d201833fe6a7","observation_id":"6c869978-87ae-4c77-b825-c11b644a453c","resolution":{"observed_at":"2026-08-09T19:16:37.776878Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2204.02967","last_updated":"2022-09-13T17:00:55Z","snapshot_observed_at":"2026-08-16T17:08:48.467808Z","submitted_at":"2022-04-06T17:59:22Z","title":"Enhanced Direct Speech-to-Speech Translation Using Self-supervised Pre-training and Data Augmentation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.02967","snapshot_observed_at":"2026-08-15T18:11:55.364167Z","title":"Enhanced direct speech-to- speech translation using self-supervised pre-training and data augmentation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.18897","last_updated":"2025-07-25T02:44:30Z","snapshot_observed_at":"2026-08-17T00:47:18.660035Z","submitted_at":"2025-07-25T02:44:30Z","title":"HH-Codec: High Compression High-fidelity Discrete Neural Codec for Spoken Language Modeling","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T18:11:55.364167Z"},"links":{"cited_paper":"/paper/2204.02967","citing_paper":"/paper/2507.18897"},"observation_digest":"sha256:d6b9132605635b8a65afa963a39722852174249c2e92b3f246952c28fce7664b","observation_id":"37aa6348-e795-4132-9b4d-342faa23e802","resolution":{"observed_at":"2026-08-15T18:11:55.364167Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2204.02967/citation-record","integrity":"/paper/2204.02967/integrity","json":"/paper/2204.02967/citation-record.json","paper":"/paper/2204.02967"},"outbound":[],"paper":{"arxiv_id":"2204.02967","last_updated":"2022-09-13T17:00:55Z","latest_version":3,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-16T17:08:48.467808Z","submitted_at":"2022-04-06T17:59:22Z","title":"Enhanced Direct Speech-to-Speech Translation Using Self-supervised Pre-training and Data Augmentation"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2204.02967."}