{"as_of":"2026-08-15T01:56:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d5347cfb7036022474435e675db8a9f1d5e67f476cf1ad9c2ebb214ccb2ec887","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":"2026-08-14T06:32:32.682623+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":"2026-08-11T12:20:25.563248Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"arxiv_reference","source_observed_at":"2026-08-05T02:28:24.338817Z","state":"measured"}],"external_citation_measurements":[{"count":3,"observed_at":"2026-08-05T02:28:24.338817Z","source":"arxiv_reference"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2203.17247","last_updated":"2022-08-22T22:25:59Z","snapshot_observed_at":"2026-08-13T16:12:47.654785Z","submitted_at":"2022-03-30T05:25:35Z","title":"VL-InterpreT: An Interactive Visualization Tool for Interpreting Vision-Language Transformers","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.17247","snapshot_observed_at":"2026-08-11T12:20:25.563248Z","title":"Vl-interpret: An interactive visualization tool for interpreting vision-language transformers, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.14373","last_updated":"2025-07-29T21:20:14Z","snapshot_observed_at":"2026-08-13T14:45:16.482962Z","submitted_at":"2024-12-18T22:13:21Z","title":"ECG-Byte: A Tokenizer for End-to-End Generative Electrocardiogram Language Modeling","version":3},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-11T12:20:25.563248Z"},"links":{"cited_paper":"/paper/2203.17247","citing_paper":"/paper/2412.14373"},"observation_digest":"sha256:13f09d4b37a6d68c3757a10f801296a1a6221511605740830bd03902649d3851","observation_id":"af14f367-45f6-493f-8ac0-195be67bd773","resolution":{"observed_at":"2026-08-11T12:20:25.563248Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.17247","last_updated":"2022-08-22T22:25:59Z","snapshot_observed_at":"2026-08-13T16:12:47.654785Z","submitted_at":"2022-03-30T05:25:35Z","title":"VL-InterpreT: An Interactive Visualization Tool for Interpreting Vision-Language Transformers","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.17247","snapshot_observed_at":"2026-08-11T12:04:52.031554Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.14672","last_updated":"2025-03-19T12:04:30Z","snapshot_observed_at":"2026-08-14T22:55:37.006938Z","submitted_at":"2024-12-19T09:24:10Z","title":"FiVL: A Framework for Improved Vision-Language Alignment through the Lens of Training, Evaluation and Explainability","version":2},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-11T12:04:52.031554Z"},"links":{"cited_paper":"/paper/2203.17247","citing_paper":"/paper/2412.14672"},"observation_digest":"sha256:510062f5e6fd02083993c30dc28f856866ad727e6e411135964ce994ca16449a","observation_id":"4b785016-af4d-4cdf-a077-8a09aa752174","resolution":{"observed_at":"2026-08-11T12:04:52.031554Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.17247","last_updated":"2022-08-22T22:25:59Z","snapshot_observed_at":"2026-08-13T16:12:47.654785Z","submitted_at":"2022-03-30T05:25:35Z","title":"VL-InterpreT: An Interactive Visualization Tool for Interpreting Vision-Language Transformers","version":3},"cited_work":{"arxiv_id":"2203.17247","doi":"10.48550/arxiv.2203.17247","metadata_source":"arxiv_reference","pith_arxiv_id":"2203.17247","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Aflalo, M","venue":"arXiv (Cornell University)","work_id":"a7d636ea-7cd4-41de-92d6-56a462d868a0","year":2022},"citing_paper":{"arxiv_id":"2508.04427","last_updated":"2026-06-11T09:27:03Z","snapshot_observed_at":"2026-08-09T05:23:29.071990Z","submitted_at":"2025-08-06T13:14:20Z","title":"Decoding the Multimodal Maze: A Systematic Review on the Adoption of Explainability in Multimodal Attention-based Models","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-05-19T00:34:38.247099Z"},"links":{"cited_paper":"/paper/2203.17247","citing_paper":"/paper/2508.04427"},"observation_digest":"sha256:3f5150fecc7ae1c4531d50092fe98e4ba967c1e35bb777ec8e4ca34fbb52c3a0","observation_id":"d22f0c98-cf58-4f17-862e-2bbe03f981ca","resolution":{"observed_at":"2026-05-19T00:36:55.771214Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2203.17247","last_updated":"2022-08-22T22:25:59Z","snapshot_observed_at":"2026-08-13T16:12:47.654785Z","submitted_at":"2022-03-30T05:25:35Z","title":"VL-InterpreT: An Interactive Visualization Tool for Interpreting Vision-Language Transformers","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.17247","snapshot_observed_at":"2026-08-06T00:02:58.737084Z","title":"Aflalo, M","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.04427","last_updated":"2026-06-11T09:27:03Z","snapshot_observed_at":"2026-08-09T05:23:29.071990Z","submitted_at":"2025-08-06T13:14:20Z","title":"Decoding the Multimodal Maze: A Systematic Review on the Adoption of Explainability in Multimodal Attention-based Models","version":2},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-06T00:02:58.737084Z"},"links":{"cited_paper":"/paper/2203.17247","citing_paper":"/paper/2508.04427"},"observation_digest":"sha256:25bc787df5f19a89d37d735c5815a676e1dc1bfa3e76e5982e5884715d9ba160","observation_id":"72bd86c6-d025-474b-b5c2-b25d721d4d65","resolution":{"observed_at":"2026-08-06T00:02:58.737084Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2203.17247/citation-record","integrity":"/paper/2203.17247/integrity","json":"/paper/2203.17247/citation-record.json","paper":"/paper/2203.17247"},"outbound":[],"paper":{"arxiv_id":"2203.17247","last_updated":"2022-08-22T22:25:59Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-13T16:12:47.654785Z","submitted_at":"2022-03-30T05:25:35Z","title":"VL-InterpreT: An Interactive Visualization Tool for Interpreting Vision-Language Transformers"},"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":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2203.17247."}