{"as_of":"2026-08-14T11:40:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f0f859c1fa3cd77b6cc2857f2ea3ff20440df3f3b652b2c8a24b7a62a45a552f","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":"2026-08-14T06:32:32.682623+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":"2026-08-12T14:04:00.563204Z","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":"2026-08-12T14:04:03.519898Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1909.03795","last_updated":"2019-09-09T12:24:06Z","snapshot_observed_at":"2026-08-13T17:39:01.483069Z","submitted_at":"2019-09-09T12:24:06Z","title":"Language learning using Speech to Image retrieval","version":1},"cited_work":{"arxiv_id":"1909.03795","doi":null,"metadata_source":"pith","pith_arxiv_id":"1909.03795","snapshot_observed_at":"2026-08-12T14:04:03.519898Z","title":"Language learning using Speech to Image retrieval","venue":"cs.CL","work_id":"6c214b85-6bf1-438d-be7e-98cf40eafb56","year":2019},"citing_paper":{"arxiv_id":"2412.00049","last_updated":"2024-11-24T03:26:34Z","snapshot_observed_at":"2026-08-13T20:27:52.554751Z","submitted_at":"2024-11-24T03:26:34Z","title":"A Survey of Recent Advances and Challenges in Deep Audio-Visual Correlation Learning","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-12T14:04:00.563204Z"},"links":{"cited_paper":"/paper/1909.03795","citing_paper":"/paper/2412.00049"},"observation_digest":"sha256:ef4e65b33b05960a62132e819cffbcb78f16c93c62e00ab9d733d35dd5a4bbdd","observation_id":"a5cf2254-ea8f-4752-9e31-eb0e64482836","resolution":{"observed_at":"2026-08-12T14:04:03.523908Z","resolver_source":"local_arxiv","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"}}],"links":{"evidence":"/evidence","html":"/paper/1909.03795/citation-record","integrity":"/paper/1909.03795/integrity","json":"/paper/1909.03795/citation-record.json","paper":"/paper/1909.03795"},"outbound":[],"paper":{"arxiv_id":"1909.03795","last_updated":"2019-09-09T12:24:06Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-13T17:39:01.483069Z","submitted_at":"2019-09-09T12:24:06Z","title":"Language learning using Speech to Image retrieval"},"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":"2026-08-14T06:32:32.682623+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 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:1909.03795."}