{"as_of":"2026-08-22T01:52:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:7cffca3b67d13b38d7293bfa8e3df600bd0415318122d5f2b67d7eb8f120941a","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":1,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":1,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-21T06:32:19.484+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-13T16:09:50.207908Z","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":[{"citation":{"cited_paper":{"arxiv_id":"2210.00705","last_updated":"2022-10-25T13:37:08Z","snapshot_observed_at":"2026-08-16T16:27:25.476664Z","submitted_at":"2022-10-03T04:15:36Z","title":"SpeechCLIP: Integrating Speech with Pre-Trained Vision and Language Model","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.00705","snapshot_observed_at":"2026-07-13T16:09:50.207908Z","title":"Speechclip: Integrating speech with pre- trained vision and language model,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.28737","last_updated":"2026-06-20T22:01:30Z","snapshot_observed_at":"2026-08-16T17:58:07.855123Z","submitted_at":"2026-03-30T17:50:07Z","title":"ParaSpeechCLAP: A Dual-Encoder Speech-Text Model for Rich Stylistic Language-Audio Pretraining","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-07-13T16:09:50.207908Z"},"links":{"cited_paper":"/paper/2210.00705","citing_paper":"/paper/2603.28737"},"observation_digest":"sha256:ce1d040a14cf44897032b68aaa70e96a245bb4b50aefb4d0a8fdfe265a52f6b1","observation_id":"72b50dc6-d0e3-4951-960f-9af9bba08bdb","resolution":{"observed_at":"2026-07-13T16:09:50.207908Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2210.00705/citation-record","integrity":"/paper/2210.00705/integrity","json":"/paper/2210.00705/citation-record.json","paper":"/paper/2210.00705"},"outbound":[],"paper":{"arxiv_id":"2210.00705","last_updated":"2022-10-25T13:37:08Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-16T16:27:25.476664Z","submitted_at":"2022-10-03T04:15:36Z","title":"SpeechCLIP: Integrating Speech with Pre-Trained Vision and Language Model"},"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 22 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2210.00705."}