{"as_of":"2026-08-20T17:26:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:1e3ac805bbdb73c6b23825bff0d22d4d50e7be41868a2944eeb72072679d2115","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":"2026-08-05T17:56:52.026432Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-07-07T14:53:55.737392Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2307.03183","last_updated":"2023-07-06T17:58:28Z","snapshot_observed_at":"2026-08-16T15:18:09.177606Z","submitted_at":"2023-07-06T17:58:28Z","title":"Whisper-AT: Noise-Robust Automatic Speech Recognizers are Also Strong General Audio Event Taggers","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.03183","snapshot_observed_at":"2026-08-05T17:56:52.026432Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.15418","last_updated":"2025-08-21T10:20:00Z","snapshot_observed_at":"2026-08-14T16:19:43.372797Z","submitted_at":"2025-08-21T10:20:00Z","title":"LLaSO: A Foundational Framework for Reproducible Research in Large Language and Speech Model","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-05T17:56:52.026432Z"},"links":{"cited_paper":"/paper/2307.03183","citing_paper":"/paper/2508.15418"},"observation_digest":"sha256:a6067256e712b3b1c052a089016fc668571f5a1ca70c3871359266184f415cce","observation_id":"1c2aba40-a6ac-49f4-bc82-b47b16aa1f0c","resolution":{"observed_at":"2026-08-05T17:56:52.026432Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.03183","last_updated":"2023-07-06T17:58:28Z","snapshot_observed_at":"2026-08-16T15:18:09.177606Z","submitted_at":"2023-07-06T17:58:28Z","title":"Whisper-AT: Noise-Robust Automatic Speech Recognizers are Also Strong General Audio Event Taggers","version":1},"cited_work":{"arxiv_id":"2307.03183","doi":null,"metadata_source":"pith","pith_arxiv_id":"2307.03183","snapshot_observed_at":"2026-07-07T14:53:55.737392Z","title":"Whisper-AT: Noise-Robust Automatic Speech Recognizers are Also Strong General Audio Event Taggers","venue":"cs.SD","work_id":"82d7ec8e-14d8-4501-9a22-55f62f950f44","year":2023},"citing_paper":{"arxiv_id":"2607.05365","last_updated":"2026-07-06T17:42:59Z","snapshot_observed_at":"2026-08-13T16:59:23.044763Z","submitted_at":"2026-07-06T17:42:59Z","title":"SPEARBench: A Benchmark for Naturalness Evaluation in Streaming Speech-to-Speech Language Models","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-07-07T14:53:07.512543Z"},"links":{"cited_paper":"/paper/2307.03183","citing_paper":"/paper/2607.05365"},"observation_digest":"sha256:3890b4f587bf6b0b1455ab1565df8882a9d41c4838f3d763a9c2cdafcff3a18c","observation_id":"68ee057e-8f93-4c68-8492-a4431557e16e","resolution":{"observed_at":"2026-07-07T14:53:55.739204Z","resolver_source":"local_arxiv","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"}},{"citation":{"cited_paper":{"arxiv_id":"2307.03183","last_updated":"2023-07-06T17:58:28Z","snapshot_observed_at":"2026-08-16T15:18:09.177606Z","submitted_at":"2023-07-06T17:58:28Z","title":"Whisper-AT: Noise-Robust Automatic Speech Recognizers are Also Strong General Audio Event Taggers","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.03183","snapshot_observed_at":"2026-08-01T14:46:35.599874Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.18666","last_updated":"2026-07-21T03:25:34Z","snapshot_observed_at":"2026-08-17T16:58:02.976368Z","submitted_at":"2026-07-21T03:25:34Z","title":"Fusion Embedding: A Unified Embedding Space for Text, Image, Video, and Audio","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-01T14:46:35.599874Z"},"links":{"cited_paper":"/paper/2307.03183","citing_paper":"/paper/2607.18666"},"observation_digest":"sha256:a22bd93077ad0aed289e1f00655af9b9e72e1d65e416c93782ff42f69f000f52","observation_id":"a3493da3-643c-4812-a2c6-07c005deb742","resolution":{"observed_at":"2026-08-01T14:46:35.599874Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2307.03183/citation-record","integrity":"/paper/2307.03183/integrity","json":"/paper/2307.03183/citation-record.json","paper":"/paper/2307.03183"},"outbound":[],"paper":{"arxiv_id":"2307.03183","last_updated":"2023-07-06T17:58:28Z","latest_version":1,"primary_category":"cs.SD","snapshot_observed_at":"2026-08-16T15:18:09.177606Z","submitted_at":"2023-07-06T17:58:28Z","title":"Whisper-AT: Noise-Robust Automatic Speech Recognizers are Also Strong General Audio Event Taggers"},"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 20 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2307.03183."}