{"as_of":"2026-08-21T08:17:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e66bc0ddd7532451451dede8cce61055f650e18a89f98dfb1fb1aadb7abf0822","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":2,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":2,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-21T06:32:19.484+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T22:18:01.797969Z","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":"2026-07-03T13:18:12.805168Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2309.08876","last_updated":"2024-01-09T09:02:23Z","snapshot_observed_at":"2026-08-21T02:09:11.896278Z","submitted_at":"2023-09-16T04:57:37Z","title":"Decoder-only Architecture for Speech Recognition with CTC Prompts and Text Data Augmentation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.08876","snapshot_observed_at":"2026-08-10T22:18:01.797969Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.02370","last_updated":"2025-02-07T20:12:12Z","snapshot_observed_at":"2026-08-16T01:05:08.422924Z","submitted_at":"2025-01-04T20:14:16Z","title":"Prepending or Cross-Attention for Speech-to-Text? An Empirical Comparison","version":3},"reference_index":61,"source":"arxiv_source","source_observed_at":"2026-08-10T22:18:01.797969Z"},"links":{"cited_paper":"/paper/2309.08876","citing_paper":"/paper/2501.02370"},"observation_digest":"sha256:932cc5938f436dfe53f3215a76e912cebacde77e2ef791c01ab67ec2ca015555","observation_id":"e53bfefd-adc3-4cb6-9abb-cdd0ff7e0f80","resolution":{"observed_at":"2026-08-10T22:18:01.797969Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.08876","last_updated":"2024-01-09T09:02:23Z","snapshot_observed_at":"2026-08-21T02:09:11.896278Z","submitted_at":"2023-09-16T04:57:37Z","title":"Decoder-only Architecture for Speech Recognition with CTC Prompts and Text Data Augmentation","version":2},"cited_work":{"arxiv_id":"2309.08876","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2309.08876","snapshot_observed_at":"2026-07-03T13:18:12.805168Z","title":"Decoder-only archi- tecture for speech recognition with CTC prompts and text-only training,","venue":null,"work_id":"33d637a1-55a7-459b-accc-af8a052eb832","year":2023},"citing_paper":{"arxiv_id":"2606.12199","last_updated":"2026-06-10T15:19:15Z","snapshot_observed_at":"2026-08-14T07:37:13.185382Z","submitted_at":"2026-06-10T15:19:15Z","title":"Which Speech Representation Better Matches Text-Native Reasoning? A Study of Speech-Text Alignment on Frame Rate and Representation","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-06-27T08:18:23.182355Z"},"links":{"cited_paper":"/paper/2309.08876","citing_paper":"/paper/2606.12199"},"observation_digest":"sha256:d5315fa8aab6f8fd49d9d567298ad3c65052b0a2af5a3a310465156ddc6bba00","observation_id":"5e36fd15-449f-4aea-a0d1-78185b4b78b8","resolution":{"observed_at":"2026-07-03T13:18:12.806735Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2309.08876/citation-record","integrity":"/paper/2309.08876/integrity","json":"/paper/2309.08876/citation-record.json","paper":"/paper/2309.08876"},"outbound":[],"paper":{"arxiv_id":"2309.08876","last_updated":"2024-01-09T09:02:23Z","latest_version":2,"primary_category":"eess.AS","snapshot_observed_at":"2026-08-21T02:09:11.896278Z","submitted_at":"2023-09-16T04:57:37Z","title":"Decoder-only Architecture for Speech Recognition with CTC Prompts and Text 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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 21 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2309.08876."}