{"as_of":"2026-08-13T17:24:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:68f5283ab7243d2e37031def90b0461466dde386d021ce30c92a12387c96fcfc","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":2,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":2,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-13T06:32:02.005865+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T14:04:00.213629Z","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":"2026-05-20T22:13:46.799678Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1911.12667","last_updated":"2020-10-26T14:02:35Z","snapshot_observed_at":"2026-07-06T08:40:39.015024Z","submitted_at":"2019-11-28T12:17:36Z","title":"Self-Supervised Learning by Cross-Modal Audio-Video Clustering","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1911.12667","snapshot_observed_at":"2026-08-12T14:04:00.213629Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.00049","last_updated":"2024-11-24T03:26:34Z","snapshot_observed_at":"2026-08-13T08:29:44.393581Z","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":7,"source":"pdf_text","source_observed_at":"2026-08-12T14:04:00.213629Z"},"links":{"cited_paper":"/paper/1911.12667","citing_paper":"/paper/2412.00049"},"observation_digest":"sha256:695f46e9254970ed3c6272f550a94138aac8e649ea4ce84577c087ebe6dc30c2","observation_id":"0e8406f2-7cca-4aac-840c-332e34565c4c","resolution":{"observed_at":"2026-08-12T14:04:00.213629Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1911.12667","last_updated":"2020-10-26T14:02:35Z","snapshot_observed_at":"2026-07-06T08:40:39.015024Z","submitted_at":"2019-11-28T12:17:36Z","title":"Self-Supervised Learning by Cross-Modal Audio-Video Clustering","version":3},"cited_work":{"arxiv_id":"1911.12667","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1911.12667","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Self- supervised learning by cross-modal audio-video clustering.ArXiv, abs/1911.12667","venue":null,"work_id":"618836a7-948f-4531-832a-891cd88d6544","year":1911},"citing_paper":{"arxiv_id":"2605.16403","last_updated":"2026-05-13T05:00:19Z","snapshot_observed_at":"2026-07-06T23:27:34.514541Z","submitted_at":"2026-05-13T05:00:19Z","title":"When Vision Speaks for Sound","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-20T22:12:52.160596Z"},"links":{"cited_paper":"/paper/1911.12667","citing_paper":"/paper/2605.16403"},"observation_digest":"sha256:e0c463ca21e06c0cf84e493edef268c2167b7500a5b9b694079e127a1d9dcf62","observation_id":"d1c77142-f1e2-4e79-b3eb-31e8d2e07aee","resolution":{"observed_at":"2026-05-20T22:13:46.806775Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/1911.12667/citation-record","integrity":"/paper/1911.12667/integrity","json":"/paper/1911.12667/citation-record.json","paper":"/paper/1911.12667"},"outbound":[],"paper":{"arxiv_id":"1911.12667","last_updated":"2020-10-26T14:02:35Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T08:40:39.015024Z","submitted_at":"2019-11-28T12:17:36Z","title":"Self-Supervised Learning by Cross-Modal Audio-Video Clustering"},"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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:1911.12667."}