{"as_of":"2026-08-08T12:06:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:df975aec6b9a3314eeb8e3f41eee43d22f1e3bf571791c250ed685c2a9724613","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":"2026-08-08T06:32:00.761636+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":"2026-08-07T15:16:39.968294Z","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":"2026-08-05T10:58:21.356963Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2501.01426","last_updated":"2025-06-15T21:53:18Z","snapshot_observed_at":"2026-08-07T18:41:52.024477Z","submitted_at":"2025-01-02T18:59:45Z","title":"Unifying Specialized Visual Encoders for Video Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.01426","snapshot_observed_at":"2026-08-07T15:16:39.968294Z","title":"Unifying specialized visual encoders for video language models.arXiv preprint arXiv:2501.01426, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.15755","last_updated":"2025-05-21T17:01:08Z","snapshot_observed_at":"2026-08-07T15:09:58.322707Z","submitted_at":"2025-05-21T17:01:08Z","title":"Exploring The Visual Feature Space for Multimodal Neural Decoding","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T15:16:39.968294Z"},"links":{"cited_paper":"/paper/2501.01426","citing_paper":"/paper/2505.15755"},"observation_digest":"sha256:4ca2440476f52acfb02c10f96a9acab4b64c6fd3e562336418bab82b0256e95b","observation_id":"332b05ac-8d32-4eff-9e6b-8312a4a097bc","resolution":{"observed_at":"2026-08-07T15:16:39.968294Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.01426","last_updated":"2025-06-15T21:53:18Z","snapshot_observed_at":"2026-08-07T18:41:52.024477Z","submitted_at":"2025-01-02T18:59:45Z","title":"Unifying Specialized Visual Encoders for Video Language Models","version":2},"cited_work":{"arxiv_id":"2501.01426","doi":null,"metadata_source":"pith","pith_arxiv_id":"2501.01426","snapshot_observed_at":"2026-08-05T10:58:21.356963Z","title":"Unifying Specialized Visual Encoders for Video Language Models","venue":"cs.CV","work_id":"10d9662b-52ee-4edb-bdd9-1c64b635908e","year":2025},"citing_paper":{"arxiv_id":"2509.03501","last_updated":"2025-09-03T17:33:20Z","snapshot_observed_at":"2026-08-07T14:11:47.550063Z","submitted_at":"2025-09-03T17:33:20Z","title":"Strefer: Empowering Video LLMs with Space-Time Referring and Reasoning via Synthetic Instruction Data","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-05T10:58:15.827629Z"},"links":{"cited_paper":"/paper/2501.01426","citing_paper":"/paper/2509.03501"},"observation_digest":"sha256:8eac6f22a58695ae1c3a02dbf785f69e3b4757b823d316fcfd23f452c485a733","observation_id":"bd4597e5-0732-488b-8a8c-dc1b7b90ad62","resolution":{"observed_at":"2026-08-05T10:58:21.479672Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2501.01426/citation-record","integrity":"/paper/2501.01426/integrity","json":"/paper/2501.01426/citation-record.json","paper":"/paper/2501.01426"},"outbound":[],"paper":{"arxiv_id":"2501.01426","last_updated":"2025-06-15T21:53:18Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-07T18:41:52.024477Z","submitted_at":"2025-01-02T18:59:45Z","title":"Unifying Specialized Visual Encoders for Video Language Models"},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2501.01426."}