{"as_of":"2026-08-14T15:28:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:11ff04b156fda91ef8a7f3011cb48a8f8275a05f270611c648fdeab517ddc0f7","coverage":[{"denominator":3,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-29T07:44:50.169335Z","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":"2026-08-14T06:32:32.682623+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2605.30472/citation-record","integrity":"/paper/2605.30472/integrity","json":"/paper/2605.30472/citation-record.json","paper":"/paper/2605.30472"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T07:44:50.169335Z","title":"InFindings of the Association for Computational Linguistics: EMNLP 2025, pages 7317–7351, Suzhou, China","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.30472","last_updated":"2026-05-28T18:42:38Z","snapshot_observed_at":"2026-07-06T23:39:43.967889Z","submitted_at":"2026-05-28T18:42:38Z","title":"Your Multimodal Speech Model Says I Have a Face for Radio","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-06-29T07:44:50.169335Z"},"links":{"citing_paper":"/paper/2605.30472"},"observation_digest":"sha256:cc28f2f78f2923fd0414ab3c94de957fb9c392f54f2ab695bc457d1a6452c737","observation_id":"e686ade0-eb3e-4a3a-abe2-d291f86fc4c2","resolution":{"observed_at":"2026-06-29T07:44:50.169335Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.02184","last_updated":"2022-03-13T01:52:28Z","snapshot_observed_at":"2026-08-13T17:03:44.084494Z","submitted_at":"2022-01-05T17:40:45Z","title":"Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction","version":2},"cited_work":{"arxiv_id":"2201.02184","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2201.02184","snapshot_observed_at":"2026-07-04T08:49:41.728084Z","title":"Learning audio-visual speech representa- tion by masked multimodal cluster prediction","venue":null,"work_id":"2e8fb221-cf84-40aa-a1b3-76de79871327","year":2022},"citing_paper":{"arxiv_id":"2605.30472","last_updated":"2026-05-28T18:42:38Z","snapshot_observed_at":"2026-07-06T23:39:43.967889Z","submitted_at":"2026-05-28T18:42:38Z","title":"Your Multimodal Speech Model Says I Have a Face for Radio","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-06-29T07:44:50.169335Z"},"links":{"cited_paper":"/paper/2201.02184","citing_paper":"/paper/2605.30472"},"observation_digest":"sha256:40d5561c324abc561f898776986d0fd355f9013d288de4d4467e7657ade47b03","observation_id":"c1ac8eb4-36f1-4f64-a1c0-65dcd4a3abf9","resolution":{"observed_at":"2026-06-29T07:53:14.062161Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1510.08484","last_updated":"2015-10-28T20:59:04Z","snapshot_observed_at":"2026-07-06T04:34:36.474437Z","submitted_at":"2015-10-28T20:59:04Z","title":"MUSAN: A Music, Speech, and Noise Corpus","version":1},"cited_work":{"arxiv_id":"1510.08484","doi":null,"metadata_source":"pith","pith_arxiv_id":"1510.08484","snapshot_observed_at":"2026-07-10T12:57:07.598373Z","title":"MUSAN: A Music, Speech, and Noise Corpus","venue":"cs.SD","work_id":"7c604702-578b-4f91-9cc6-f8aa7dbe6d26","year":2015},"citing_paper":{"arxiv_id":"2605.30472","last_updated":"2026-05-28T18:42:38Z","snapshot_observed_at":"2026-07-06T23:39:43.967889Z","submitted_at":"2026-05-28T18:42:38Z","title":"Your Multimodal Speech Model Says I Have a Face for Radio","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-06-29T07:44:50.169335Z"},"links":{"cited_paper":"/paper/1510.08484","citing_paper":"/paper/2605.30472"},"observation_digest":"sha256:bbb560cf89c0f8bbcbaede7de52a0053bae8ef0c053b8b2d85c1b4a9b9803532","observation_id":"a9280b75-fec8-4838-89a4-61031563674c","resolution":{"observed_at":"2026-06-29T07:53:14.059929Z","resolver_source":"local_arxiv","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2605.30472","last_updated":"2026-05-28T18:42:38Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T23:39:43.967889Z","submitted_at":"2026-05-28T18:42:38Z","title":"Your Multimodal Speech Model Says I Have a Face for Radio"},"reference_resolution":{"displayed":3,"state_counts":{"malformed_identifier":1,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":1,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":3},"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":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"As of 14 August 2026, this Paper Citation Record lists 3 of 3 outbound references and 0 inbound Pith citation observations for arXiv:2605.30472."}