{"as_of":"2026-08-04T08:30:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e7f59132b02c3ec8e9e8056ceea82274258d5526e2ef4845b7b012b72283f104","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":"2026-08-04T06:34:03.388597+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":"2026-05-11T02:14:45.371564Z","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":"2026-05-11T02:14:45.456426Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2212.00500","last_updated":"2022-11-29T13:16:09Z","snapshot_observed_at":"2026-07-06T14:25:36.764202Z","submitted_at":"2022-11-29T13:16:09Z","title":"MMSpeech: Multi-modal Multi-task Encoder-Decoder Pre-training for Speech Recognition","version":1},"cited_work":{"arxiv_id":"2212.00500","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2212.00500","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Mmspeech: Multi-modal multi-task encoder-decoder pre-training for speech recognition","venue":null,"work_id":"012e7c4a-55be-490d-8971-204e512e4348","year":null},"citing_paper":{"arxiv_id":"2407.10759","last_updated":"2024-07-15T14:38:09Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-07-15T14:38:09Z","title":"Qwen2-Audio Technical Report","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-05-11T02:14:45.371564Z"},"links":{"cited_paper":"/paper/2212.00500","citing_paper":"/paper/2407.10759"},"observation_digest":"sha256:5a420c11adba5472861995564a3ea34ba8c4bec14c977373a042e16223f0139a","observation_id":"50dd1283-adf9-424f-b27d-ada02fa3c230","resolution":{"observed_at":"2026-05-11T02:14:45.458737Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2212.00500/citation-record","integrity":"/paper/2212.00500/integrity","json":"/paper/2212.00500/citation-record.json","paper":"/paper/2212.00500"},"outbound":[],"paper":{"arxiv_id":"2212.00500","last_updated":"2022-11-29T13:16:09Z","latest_version":1,"primary_category":"cs.MM","snapshot_observed_at":"2026-07-06T14:25:36.764202Z","submitted_at":"2022-11-29T13:16:09Z","title":"MMSpeech: Multi-modal Multi-task Encoder-Decoder Pre-training for Speech Recognition"},"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":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"thesis":"As of 4 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2212.00500."}