{"as_of":"2026-08-04T06:26:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:44881d8eb4a719c76b441482b78c4577a93e7236531e745d306162171b0fec88","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":"2026-08-03T06:30:56.289259+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":"2026-06-30T22:11:44.891731Z","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":"2026-07-10T12:15:01.137692Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2506.05984","last_updated":"2025-06-06T11:05:48Z","snapshot_observed_at":"2026-07-06T21:37:51.892023Z","submitted_at":"2025-06-06T11:05:48Z","title":"Audio-Aware Large Language Models as Judges for Speaking Styles","version":1},"cited_work":{"arxiv_id":"2506.05984","doi":"10.48550/arxiv.2506.05984","metadata_source":"arxiv_reference","pith_arxiv_id":"2506.05984","snapshot_observed_at":"2026-07-10T12:15:01.137692Z","title":"Audio-aware large language models as judges for speaking styles","venue":null,"work_id":"8c842325-baa3-4788-bf79-a6755d9f83fb","year":2025},"citing_paper":{"arxiv_id":"2509.26388","last_updated":"2026-05-01T17:28:37Z","snapshot_observed_at":"2026-07-06T22:31:15.349221Z","submitted_at":"2025-09-30T15:23:39Z","title":"Game-Time: Evaluating Temporal Dynamics in Spoken Language Models","version":4},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-05-18T11:51:43.561210Z"},"links":{"cited_paper":"/paper/2506.05984","citing_paper":"/paper/2509.26388"},"observation_digest":"sha256:0932cea72b73f378b83b33aa2bb67653365490cda7031d034b17dc4f27d7aeb2","observation_id":"e329342d-cbbb-428f-8d72-7cb0cac8f484","resolution":{"observed_at":"2026-05-18T11:52:35.677607Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.05984","last_updated":"2025-06-06T11:05:48Z","snapshot_observed_at":"2026-07-06T21:37:51.892023Z","submitted_at":"2025-06-06T11:05:48Z","title":"Audio-Aware Large Language Models as Judges for Speaking Styles","version":1},"cited_work":{"arxiv_id":"2506.05984","doi":"10.48550/arxiv.2506.05984","metadata_source":"arxiv_reference","pith_arxiv_id":"2506.05984","snapshot_observed_at":"2026-07-10T12:15:01.137692Z","title":"Audio-aware large language models as judges for speaking styles","venue":null,"work_id":"8c842325-baa3-4788-bf79-a6755d9f83fb","year":2025},"citing_paper":{"arxiv_id":"2604.16211","last_updated":"2026-04-21T13:32:36Z","snapshot_observed_at":"2026-08-01T22:51:55.583851Z","submitted_at":"2026-04-17T16:20:55Z","title":"NVBench: A Benchmark for Speech Synthesis with Non-Verbal Vocalizations","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-05-10T07:37:44.393592Z"},"links":{"cited_paper":"/paper/2506.05984","citing_paper":"/paper/2604.16211"},"observation_digest":"sha256:fffb748bfe5437df615bacbaf5c4d6802401ad37b77e44de4a786a382b4babb4","observation_id":"28fd3e27-1afb-49b1-aa3a-c8274b0c770e","resolution":{"observed_at":"2026-05-10T07:47:12.959163Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.05984","last_updated":"2025-06-06T11:05:48Z","snapshot_observed_at":"2026-07-06T21:37:51.892023Z","submitted_at":"2025-06-06T11:05:48Z","title":"Audio-Aware Large Language Models as Judges for Speaking Styles","version":1},"cited_work":{"arxiv_id":"2506.05984","doi":"10.48550/arxiv.2506.05984","metadata_source":"arxiv_reference","pith_arxiv_id":"2506.05984","snapshot_observed_at":"2026-07-10T12:15:01.137692Z","title":"Audio-aware large language models as judges for speaking styles","venue":null,"work_id":"8c842325-baa3-4788-bf79-a6755d9f83fb","year":2025},"citing_paper":{"arxiv_id":"2606.11219","last_updated":"2026-05-11T20:27:40Z","snapshot_observed_at":"2026-08-03T04:36:58.884789Z","submitted_at":"2026-05-11T20:27:40Z","title":"Afrispeech Semantics: Evaluating Audio Semantic Reasoning in Spoken Language Models Across Domains and Accents","version":1},"reference_index":218,"source":"arxiv_source","source_observed_at":"2026-06-30T22:11:44.891731Z"},"links":{"cited_paper":"/paper/2506.05984","citing_paper":"/paper/2606.11219"},"observation_digest":"sha256:edfb939ae87bc837d926a129b655750ed7984340c1aa6e4d2d4849b915812b54","observation_id":"5ef85fb7-9c1b-4e1c-a98a-de4754aa107d","resolution":{"observed_at":"2026-06-30T22:15:05.705501Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2506.05984/citation-record","integrity":"/paper/2506.05984/integrity","json":"/paper/2506.05984/citation-record.json","paper":"/paper/2506.05984"},"outbound":[],"paper":{"arxiv_id":"2506.05984","last_updated":"2025-06-06T11:05:48Z","latest_version":1,"primary_category":"eess.AS","snapshot_observed_at":"2026-07-06T21:37:51.892023Z","submitted_at":"2025-06-06T11:05:48Z","title":"Audio-Aware Large Language Models as Judges for Speaking Styles"},"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":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"thesis":"As of 4 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2506.05984."}