{"as_of":"2026-08-21T02:37:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:1d8570a965ba974dc50b562c817e90e847ce775cb06515edde4efc1bb487803a","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":"2026-08-20T06:33:59.587034+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":"2026-08-10T22:18:01.839297Z","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":"2026-07-02T22:47:25.658858Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2310.00230","last_updated":"2023-09-30T02:27:45Z","snapshot_observed_at":"2026-08-16T14:56:19.891641Z","submitted_at":"2023-09-30T02:27:45Z","title":"SLM: Bridge the thin gap between speech and text foundation models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.00230","snapshot_observed_at":"2026-08-10T22:18:01.839297Z","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":67,"source":"arxiv_source","source_observed_at":"2026-08-10T22:18:01.839297Z"},"links":{"cited_paper":"/paper/2310.00230","citing_paper":"/paper/2501.02370"},"observation_digest":"sha256:c074c59838332964719e51f8fcc597468b69795609fb6b9e981aae2baf12b51e","observation_id":"750102ff-069e-4043-b423-4e8dbce94f38","resolution":{"observed_at":"2026-08-10T22:18:01.839297Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.00230","last_updated":"2023-09-30T02:27:45Z","snapshot_observed_at":"2026-08-16T14:56:19.891641Z","submitted_at":"2023-09-30T02:27:45Z","title":"SLM: Bridge the thin gap between speech and text foundation models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.00230","snapshot_observed_at":"2026-08-05T05:51:44.521768Z","title":"Slm: Bridge the thin gap between speech and text foundation models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.04871","last_updated":"2025-09-05T07:36:12Z","snapshot_observed_at":"2026-08-14T15:17:57.852608Z","submitted_at":"2025-09-05T07:36:12Z","title":"Cloning a Conversational Voice AI Agent from Call\\,Recording Datasets for Telesales","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-05T05:51:44.521768Z"},"links":{"cited_paper":"/paper/2310.00230","citing_paper":"/paper/2509.04871"},"observation_digest":"sha256:34e5777edfd58d259e4052cd9cbfdf60d3f691a5e6cb8438b1882d8ac65cb57e","observation_id":"e06371db-ea51-478f-b783-e0a0ba9f3c5d","resolution":{"observed_at":"2026-08-05T05:51:44.521768Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.00230","last_updated":"2023-09-30T02:27:45Z","snapshot_observed_at":"2026-08-16T14:56:19.891641Z","submitted_at":"2023-09-30T02:27:45Z","title":"SLM: Bridge the thin gap between speech and text foundation models","version":1},"cited_work":{"arxiv_id":"2310.00230","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2310.00230","snapshot_observed_at":"2026-07-02T22:47:25.658858Z","title":"Rubenstein, Lukas Zilka, Dian Yu, Zhong Meng, Golan Pundak, Nikhil Siddhartha, Johan Schalkwyk, and Yonghui Wu","venue":null,"work_id":"4d20396c-39d9-4fd1-b51e-45533566b311","year":2023},"citing_paper":{"arxiv_id":"2606.08486","last_updated":"2026-06-07T07:15:34Z","snapshot_observed_at":"2026-08-14T07:00:54.042268Z","submitted_at":"2026-06-07T07:15:34Z","title":"TRADE: Transducer-Augmented Decoder for Speech LLM","version":1},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-06-27T18:40:19.688550Z"},"links":{"cited_paper":"/paper/2310.00230","citing_paper":"/paper/2606.08486"},"observation_digest":"sha256:82bfb495b611e5e11887fb82571d2b747dadfbba25e420132cf98089e6682842","observation_id":"aa2abefd-40e9-4c08-a168-81432cce60b0","resolution":{"observed_at":"2026-07-02T22:47:25.660276Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2310.00230/citation-record","integrity":"/paper/2310.00230/integrity","json":"/paper/2310.00230/citation-record.json","paper":"/paper/2310.00230"},"outbound":[],"paper":{"arxiv_id":"2310.00230","last_updated":"2023-09-30T02:27:45Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-16T14:56:19.891641Z","submitted_at":"2023-09-30T02:27:45Z","title":"SLM: Bridge the thin gap between speech and text foundation models"},"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":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"thesis":"As of 21 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2310.00230."}