{"as_of":"2026-08-21T03:26:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:1392900be236694d71a4178fb0696f95e961ec904b28900ca0b5699d572162e6","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":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-20T06:33:59.587034+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T21:01:38.462143Z","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":"2026-06-29T08:13:15.045689Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2301.13081","last_updated":"2023-02-08T02:29:27Z","snapshot_observed_at":"2026-08-16T15:59:06.907992Z","submitted_at":"2023-01-30T17:21:30Z","title":"STAIR: Learning Sparse Text and Image Representation in Grounded Tokens","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.13081","snapshot_observed_at":"2026-08-11T23:54:23.870158Z","title":"Stair: learning sparse text and image representation in grounded tokens,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.02104","last_updated":"2024-12-03T02:54:31Z","snapshot_observed_at":"2026-08-16T12:56:12.864592Z","submitted_at":"2024-12-03T02:54:31Z","title":"Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey","version":1},"reference_index":148,"source":"pdf_text","source_observed_at":"2026-08-11T23:54:23.870158Z"},"links":{"cited_paper":"/paper/2301.13081","citing_paper":"/paper/2412.02104"},"observation_digest":"sha256:ee6036fb6a26d6047766b11033b599d0b7ff19c55c58b6b552a620cf93500b13","observation_id":"e995b258-cf60-42ab-a7f7-32d1ec033e82","resolution":{"observed_at":"2026-08-11T23:54:23.870158Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2301.13081","last_updated":"2023-02-08T02:29:27Z","snapshot_observed_at":"2026-08-16T15:59:06.907992Z","submitted_at":"2023-01-30T17:21:30Z","title":"STAIR: Learning Sparse Text and Image Representation in Grounded Tokens","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.13081","snapshot_observed_at":"2026-08-10T17:26:35.139053Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.12203","last_updated":"2025-01-21T15:18:55Z","snapshot_observed_at":"2026-08-17T19:14:39.414452Z","submitted_at":"2025-01-21T15:18:55Z","title":"Explainability for Vision Foundation Models: A Survey","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-10T17:26:35.139053Z"},"links":{"cited_paper":"/paper/2301.13081","citing_paper":"/paper/2501.12203"},"observation_digest":"sha256:06f4e2b5935043a5f4ea6b7ab0903047f8fc25dbdabe300ffa0c557376fbfdd7","observation_id":"295232f7-4a71-44e8-8189-1db30573fcef","resolution":{"observed_at":"2026-08-10T17:26:35.139053Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2301.13081","last_updated":"2023-02-08T02:29:27Z","snapshot_observed_at":"2026-08-16T15:59:06.907992Z","submitted_at":"2023-01-30T17:21:30Z","title":"STAIR: Learning Sparse Text and Image Representation in Grounded Tokens","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.13081","snapshot_observed_at":"2026-08-15T21:01:38.462143Z","title":"Stair: Learning sparse text and image representation in grounded tokens","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.11216","last_updated":"2025-05-16T13:12:41Z","snapshot_observed_at":"2026-08-17T06:30:04.839140Z","submitted_at":"2025-05-16T13:12:41Z","title":"GeoMM: On Geodesic Perspective for Multi-modal Learning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T21:01:38.462143Z"},"links":{"cited_paper":"/paper/2301.13081","citing_paper":"/paper/2505.11216"},"observation_digest":"sha256:fccf0a8a80e91bd289851ba252516d3b6c6502cab1e7c0ecd1c0b86250d2110f","observation_id":"274db597-f706-466c-94af-bff1aab1ab82","resolution":{"observed_at":"2026-08-15T21:01:38.462143Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2301.13081","last_updated":"2023-02-08T02:29:27Z","snapshot_observed_at":"2026-08-16T15:59:06.907992Z","submitted_at":"2023-01-30T17:21:30Z","title":"STAIR: Learning Sparse Text and Image Representation in Grounded Tokens","version":2},"cited_work":{"arxiv_id":"2301.13081","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2301.13081","snapshot_observed_at":"2026-06-29T08:13:15.045689Z","title":null,"venue":null,"work_id":"65087f85-91a3-4864-9ab9-37932465e96e","year":2023},"citing_paper":{"arxiv_id":"2605.30027","last_updated":"2026-05-28T14:50:53Z","snapshot_observed_at":"2026-08-06T11:47:39.586448Z","submitted_at":"2026-05-28T14:50:53Z","title":"DocRetriever: A Plug-and-Play Framework for Multimodal Document Retrieval with Comprehensive Benchmark","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-06-29T08:09:41.068000Z"},"links":{"cited_paper":"/paper/2301.13081","citing_paper":"/paper/2605.30027"},"observation_digest":"sha256:535fbb1c05e29c48ce4ed481a438dd0db74041a1a8f4ccc1cf91986e952bf0c5","observation_id":"a4c819ea-c411-4840-b4b8-e2ab995369f5","resolution":{"observed_at":"2026-06-29T08:13:15.047177Z","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"}}],"links":{"evidence":"/evidence","html":"/paper/2301.13081/citation-record","integrity":"/paper/2301.13081/integrity","json":"/paper/2301.13081/citation-record.json","paper":"/paper/2301.13081"},"outbound":[],"paper":{"arxiv_id":"2301.13081","last_updated":"2023-02-08T02:29:27Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-16T15:59:06.907992Z","submitted_at":"2023-01-30T17:21:30Z","title":"STAIR: Learning Sparse Text and Image Representation in Grounded Tokens"},"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 21 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2301.13081."}