{"as_of":"2026-08-10T14:54:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:289fdba1e9a7be46e7e8bb84d326c833c4e610fa8c95e85c66f2169b544949d5","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":"2026-08-10T06:31:04.303077+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":"2026-08-08T19:15:43.893409Z","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":"2026-05-12T12:40:23.831580Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2212.07525","last_updated":"2023-06-15T15:19:22Z","snapshot_observed_at":"2026-08-10T14:45:22.611226Z","submitted_at":"2022-12-14T22:13:11Z","title":"Efficient Self-supervised Learning with Contextualized Target Representations for Vision, Speech and Language","version":2},"cited_work":{"arxiv_id":"2212.07525","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2212.07525","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Efficient self-supervised learning with contextualized target representations for vision, speech and language","venue":null,"work_id":"ac81813c-f799-4e42-9180-fdedbdabbd57","year":2022},"citing_paper":{"arxiv_id":"2404.08471","last_updated":"2024-02-15T18:59:11Z","snapshot_observed_at":"2026-08-07T02:30:11.447693Z","submitted_at":"2024-02-15T18:59:11Z","title":"Revisiting Feature Prediction for Learning Visual Representations from Video","version":1},"reference_index":222,"source":"arxiv_source","source_observed_at":"2026-05-12T12:40:23.709098Z"},"links":{"cited_paper":"/paper/2212.07525","citing_paper":"/paper/2404.08471"},"observation_digest":"sha256:35d424e5dd36a64f4fd22c9c0bedfd36436e89c99da32a238c25e564ba293c84","observation_id":"4470f0eb-37ac-4c0a-9e19-65e348c7e71f","resolution":{"observed_at":"2026-05-12T12:40:23.833624Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2212.07525","last_updated":"2023-06-15T15:19:22Z","snapshot_observed_at":"2026-08-10T14:45:22.611226Z","submitted_at":"2022-12-14T22:13:11Z","title":"Efficient Self-supervised Learning with Contextualized Target Representations for Vision, Speech and Language","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.07525","snapshot_observed_at":"2026-08-08T19:15:43.893409Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.04351","last_updated":"2026-08-05T01:50:37Z","snapshot_observed_at":"2026-08-08T23:11:30.376300Z","submitted_at":"2026-08-05T01:50:37Z","title":"HyPASE: Hyperbolic Geometry for Parameter-Efficient Speech Emotion Fine-Tuning Framework for Large Audio-Language Models","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-08T19:15:43.893409Z"},"links":{"cited_paper":"/paper/2212.07525","citing_paper":"/paper/2608.04351"},"observation_digest":"sha256:e0931fef00725fa3ff6c440f0571cc87ff98858361010827633d8a712f7335be","observation_id":"ccf72dc3-1cb0-48a4-90b4-35f92071835b","resolution":{"observed_at":"2026-08-08T19:15:43.893409Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2212.07525/citation-record","integrity":"/paper/2212.07525/integrity","json":"/paper/2212.07525/citation-record.json","paper":"/paper/2212.07525"},"outbound":[],"paper":{"arxiv_id":"2212.07525","last_updated":"2023-06-15T15:19:22Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-10T14:45:22.611226Z","submitted_at":"2022-12-14T22:13:11Z","title":"Efficient Self-supervised Learning with Contextualized Target Representations for Vision, Speech and Language"},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2212.07525."}