{"as_of":"2026-08-09T23:42:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ee3cb3d318168ac00580ff0e0e33be2c54c32fb99931f915c12c3d6e0eb9689a","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":"2026-08-09T06:31:02.800959+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":"2026-08-07T01:06:06.285352Z","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":"2026-07-02T16:47:10.086468Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2310.10591","last_updated":"2023-10-16T17:12:06Z","snapshot_observed_at":"2026-08-07T04:47:37.971137Z","submitted_at":"2023-10-16T17:12:06Z","title":"Interpreting and Controlling Vision Foundation Models via Text Explanations","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.10591","snapshot_observed_at":"2026-08-07T01:06:06.285352Z","title":"Interpreting and controlling vision foundation mod- els via text explanations","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.11976","last_updated":"2025-06-22T00:39:23Z","snapshot_observed_at":"2026-08-09T16:06:21.482138Z","submitted_at":"2025-06-13T17:34:05Z","title":"How Visual Representations Map to Language Feature Space in Multimodal LLMs","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T01:06:06.285352Z"},"links":{"cited_paper":"/paper/2310.10591","citing_paper":"/paper/2506.11976"},"observation_digest":"sha256:0084b9ae65141d31bae1c64fff6f7368d873cef411170bc9019c6dd38a468318","observation_id":"07ce8781-2025-4982-8acf-de1552b550a7","resolution":{"observed_at":"2026-08-07T01:06:06.285352Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.10591","last_updated":"2023-10-16T17:12:06Z","snapshot_observed_at":"2026-08-07T04:47:37.971137Z","submitted_at":"2023-10-16T17:12:06Z","title":"Interpreting and Controlling Vision Foundation Models via Text Explanations","version":1},"cited_work":{"arxiv_id":"2310.10591","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2310.10591","snapshot_observed_at":"2026-07-02T16:47:10.086468Z","title":"Interpreting and controlling vision foundation models via text explanations","venue":null,"work_id":"b0bf7a34-fe8c-4407-98a1-a4eef3a3499c","year":2023},"citing_paper":{"arxiv_id":"2511.18359","last_updated":"2026-04-07T10:36:41Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-11-23T09:12:48Z","title":"TRANSPORTER: Transferring Visual Semantics from VLM Manifolds","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-17T05:59:14.478279Z"},"links":{"cited_paper":"/paper/2310.10591","citing_paper":"/paper/2511.18359"},"observation_digest":"sha256:a5204a823f2d2617731386dde24356b0d2c369fc32fcaae67a83ef4e0b86305f","observation_id":"ba69f30f-791d-403a-85a0-c79a5c5246f5","resolution":{"observed_at":"2026-05-17T06:01:34.733435Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.10591","last_updated":"2023-10-16T17:12:06Z","snapshot_observed_at":"2026-08-07T04:47:37.971137Z","submitted_at":"2023-10-16T17:12:06Z","title":"Interpreting and Controlling Vision Foundation Models via Text Explanations","version":1},"cited_work":{"arxiv_id":"2310.10591","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2310.10591","snapshot_observed_at":"2026-07-02T16:47:10.086468Z","title":"Interpreting and controlling vision foundation models via text explanations","venue":null,"work_id":"b0bf7a34-fe8c-4407-98a1-a4eef3a3499c","year":2023},"citing_paper":{"arxiv_id":"2606.07451","last_updated":"2026-06-05T16:54:40Z","snapshot_observed_at":"2026-07-06T23:47:05.104295Z","submitted_at":"2026-06-05T16:54:40Z","title":"TEVI: Text-Conditioned Editing of Visual Representations via Sparse Autoencoders for Improved Vision-Language Alignment","version":1},"reference_index":104,"source":"arxiv_source","source_observed_at":"2026-06-27T22:22:01.979434Z"},"links":{"cited_paper":"/paper/2310.10591","citing_paper":"/paper/2606.07451"},"observation_digest":"sha256:6298c74722f1582c74280ba6b815dc52b32af39f93b8065f5ec3ff5ddfc20c83","observation_id":"e16be028-036e-4004-accf-63593fd7257a","resolution":{"observed_at":"2026-07-02T16:47:10.087796Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2310.10591/citation-record","integrity":"/paper/2310.10591/integrity","json":"/paper/2310.10591/citation-record.json","paper":"/paper/2310.10591"},"outbound":[],"paper":{"arxiv_id":"2310.10591","last_updated":"2023-10-16T17:12:06Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-07T04:47:37.971137Z","submitted_at":"2023-10-16T17:12:06Z","title":"Interpreting and Controlling Vision Foundation Models via Text Explanations"},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2310.10591."}