{"as_of":"2026-08-20T22:10:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:eb653fbaa0f105c617ebea0a424278c0cc6657e58aa0b8baf644866f2ab6b208","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":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":"2026-08-20T06:33:59.587034+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-02T00:14:56.926226Z","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":"2026-05-16T09:50:00.769373Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2110.11499","last_updated":"2022-02-15T13:06:57Z","snapshot_observed_at":"2026-08-16T17:47:27.872702Z","submitted_at":"2021-10-21T22:00:13Z","title":"Wav2CLIP: Learning Robust Audio Representations From CLIP","version":2},"cited_work":{"arxiv_id":"2110.11499","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2110.11499","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Xu Xie, Fei Sun, Zhaoyang Liu, Shiwen Wu, Jinyang Gao, Jiandong Zhang, Bolin Ding, and Bin Cui","venue":null,"work_id":"e8489180-cfbb-4c36-8715-18e698e959fe","year":2021},"citing_paper":{"arxiv_id":"2204.00598","last_updated":"2022-05-27T17:52:50Z","snapshot_observed_at":"2026-08-13T04:37:51.649726Z","submitted_at":"2022-04-01T17:43:13Z","title":"Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language","version":2},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-05-16T09:50:00.546571Z"},"links":{"cited_paper":"/paper/2110.11499","citing_paper":"/paper/2204.00598"},"observation_digest":"sha256:3b9992ef848dad94ea1b3c06a6b563613ca0f2a991a702fc4b0a68211a0486e5","observation_id":"66491047-8c62-41a2-993a-f08546bc6e5a","resolution":{"observed_at":"2026-05-16T09:50:00.771567Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.11499","last_updated":"2022-02-15T13:06:57Z","snapshot_observed_at":"2026-08-16T17:47:27.872702Z","submitted_at":"2021-10-21T22:00:13Z","title":"Wav2CLIP: Learning Robust Audio Representations From CLIP","version":2},"cited_work":{"arxiv_id":"2110.11499","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2110.11499","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Xu Xie, Fei Sun, Zhaoyang Liu, Shiwen Wu, Jinyang Gao, Jiandong Zhang, Bolin Ding, and Bin Cui","venue":null,"work_id":"e8489180-cfbb-4c36-8715-18e698e959fe","year":2021},"citing_paper":{"arxiv_id":"2604.16678","last_updated":"2026-04-17T20:21:34Z","snapshot_observed_at":"2026-08-14T12:06:49.782476Z","submitted_at":"2026-04-17T20:21:34Z","title":"UniCon: Unified Framework for Efficient Contrastive Alignment via Kernels","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-10T08:32:36.729122Z"},"links":{"cited_paper":"/paper/2110.11499","citing_paper":"/paper/2604.16678"},"observation_digest":"sha256:8b42f5fda7a0c1bf939dc2e0e2ffb86933c09994ef47cb6d13167e467b270f85","observation_id":"014daf05-65a3-41e5-aa0e-72445b5f1224","resolution":{"observed_at":"2026-05-10T08:32:51.989046Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.11499","last_updated":"2022-02-15T13:06:57Z","snapshot_observed_at":"2026-08-16T17:47:27.872702Z","submitted_at":"2021-10-21T22:00:13Z","title":"Wav2CLIP: Learning Robust Audio Representations From CLIP","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.11499","snapshot_observed_at":"2026-08-02T00:14:56.926226Z","title":"Wav2clip: Learning robust audio representations from clip.arXiv preprint arXiv:2110.11499, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.15094","last_updated":"2026-07-16T15:07:23Z","snapshot_observed_at":"2026-08-20T05:40:40.311381Z","submitted_at":"2026-07-16T15:07:23Z","title":"AlphaWiSE: Adaptive Weight Interpolation for Continual Multimodal Representation Learning","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-02T00:14:56.926226Z"},"links":{"cited_paper":"/paper/2110.11499","citing_paper":"/paper/2607.15094"},"observation_digest":"sha256:a77e8439fe74db11213c805e9cfe39f115981df6943b9b1c8ef7f743b5720276","observation_id":"b1f2c7ae-eaac-49a9-8238-c86604d361e1","resolution":{"observed_at":"2026-08-02T00:14:56.926226Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2110.11499/citation-record","integrity":"/paper/2110.11499/integrity","json":"/paper/2110.11499/citation-record.json","paper":"/paper/2110.11499"},"outbound":[],"paper":{"arxiv_id":"2110.11499","last_updated":"2022-02-15T13:06:57Z","latest_version":2,"primary_category":"cs.SD","snapshot_observed_at":"2026-08-16T17:47:27.872702Z","submitted_at":"2021-10-21T22:00:13Z","title":"Wav2CLIP: Learning Robust Audio Representations From CLIP"},"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":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"thesis":"As of 20 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2110.11499."}