{"as_of":"2026-08-15T14:07:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:561922dbe65229aa12ddfc5b0286e1d566a9a52828fe860c02a4e956447c2900","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":"2026-08-15T06:32:42.880941+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":"2026-08-11T21:30:10.964761Z","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":"2026-07-02T00:56:25.008128Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2204.05409","last_updated":"2022-04-11T20:59:51Z","snapshot_observed_at":"2026-08-14T02:24:40.569454Z","submitted_at":"2022-04-11T20:59:51Z","title":"Unified Speech-Text Pre-training for Speech Translation and Recognition","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.05409","snapshot_observed_at":"2026-08-11T21:30:10.964761Z","title":"Unified speech-text pre-training for speech translation and recognition","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.04425","last_updated":"2024-12-05T18:51:10Z","snapshot_observed_at":"2026-08-15T06:55:15.263597Z","submitted_at":"2024-12-05T18:51:10Z","title":"CA-SSLR: Condition-Aware Self-Supervised Learning Representation for Generalized Speech Processing","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-11T21:30:10.964761Z"},"links":{"cited_paper":"/paper/2204.05409","citing_paper":"/paper/2412.04425"},"observation_digest":"sha256:950c174c707edddb79dd80351e8cb23525ef6a61a274493f5208893e223da609","observation_id":"8d438f6b-c4e6-47f8-9af7-8a1956bb0ec1","resolution":{"observed_at":"2026-08-11T21:30:10.964761Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2204.05409","last_updated":"2022-04-11T20:59:51Z","snapshot_observed_at":"2026-08-14T02:24:40.569454Z","submitted_at":"2022-04-11T20:59:51Z","title":"Unified Speech-Text Pre-training for Speech Translation and Recognition","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.05409","snapshot_observed_at":"2026-08-06T21:51:36.079536Z","title":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.23325","last_updated":"2025-07-09T17:40:35Z","snapshot_observed_at":"2026-08-13T18:27:51.812424Z","submitted_at":"2025-06-29T16:51:50Z","title":"XY-Tokenizer: Mitigating the Semantic-Acoustic Conflict in Low-Bitrate Speech Codecs","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T21:51:36.079536Z"},"links":{"cited_paper":"/paper/2204.05409","citing_paper":"/paper/2506.23325"},"observation_digest":"sha256:ac297d9a25652c9cd3b1bea8a936ec64e49aa0c5942a0b6d845a9741c9d4b710","observation_id":"dc09ecda-a6e5-439a-862e-d73db211cc55","resolution":{"observed_at":"2026-08-06T21:51:36.079536Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2204.05409","last_updated":"2022-04-11T20:59:51Z","snapshot_observed_at":"2026-08-14T02:24:40.569454Z","submitted_at":"2022-04-11T20:59:51Z","title":"Unified Speech-Text Pre-training for Speech Translation and Recognition","version":1},"cited_work":{"arxiv_id":"2204.05409","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2204.05409","snapshot_observed_at":"2026-07-02T00:56:25.008128Z","title":"Unified speech-text pre-training for speech translation and recognition","venue":null,"work_id":"b5949b4e-e445-4fc1-8a5a-bffe322bb463","year":2022},"citing_paper":{"arxiv_id":"2606.01802","last_updated":"2026-06-05T13:33:35Z","snapshot_observed_at":"2026-08-06T23:00:35.099926Z","submitted_at":"2026-06-01T07:19:22Z","title":"MOSS-Audio Technical Report","version":3},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-06-28T13:05:29.813707Z"},"links":{"cited_paper":"/paper/2204.05409","citing_paper":"/paper/2606.01802"},"observation_digest":"sha256:a58ec97e66fe24970cd85d51f65ffa61ca6f3dd682c8f39ea40ca272cf66a35a","observation_id":"a3a7cb2a-6403-4ac3-afa6-4eb6e0ac3465","resolution":{"observed_at":"2026-07-02T00:56:25.010703Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2204.05409/citation-record","integrity":"/paper/2204.05409/integrity","json":"/paper/2204.05409/citation-record.json","paper":"/paper/2204.05409"},"outbound":[],"paper":{"arxiv_id":"2204.05409","last_updated":"2022-04-11T20:59:51Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-14T02:24:40.569454Z","submitted_at":"2022-04-11T20:59:51Z","title":"Unified Speech-Text Pre-training for Speech Translation and Recognition"},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2204.05409."}