{"as_of":"2026-08-14T02:26:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ee2c218c71b5bcdafc87a86dd204a55d385a166afbc0d8a7fe372e2d096a2a3d","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":"2026-08-13T06:32:02.005865+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":"2026-08-11T13:03:41.078191Z","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":"2026-05-18T17:56:42.234753Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2111.12085","last_updated":"2022-07-27T17:56:35Z","snapshot_observed_at":"2026-08-13T17:28:52.685349Z","submitted_at":"2021-11-23T18:59:14Z","title":"UniTAB: Unifying Text and Box Outputs for Grounded Vision-Language Modeling","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.12085","snapshot_observed_at":"2026-08-11T13:03:41.078191Z","title":"Crossing the format boundary of text and boxes: Towards unified vision-language modeling,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.13599","last_updated":"2024-12-18T08:31:26Z","snapshot_observed_at":"2026-08-12T00:07:04.086581Z","submitted_at":"2024-12-18T08:31:26Z","title":"Unlocking the Potential of Weakly Labeled Data: A Co-Evolutionary Learning Framework for Abnormality Detection and Report Generation","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-11T13:03:41.078191Z"},"links":{"cited_paper":"/paper/2111.12085","citing_paper":"/paper/2412.13599"},"observation_digest":"sha256:8046e65c0adcdfe72a37815762fd6f86156693ba6741efa1a60470100dff119f","observation_id":"3e4dcd1d-847c-41fb-b75a-d72205561be1","resolution":{"observed_at":"2026-08-11T13:03:41.078191Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2111.12085","last_updated":"2022-07-27T17:56:35Z","snapshot_observed_at":"2026-08-13T17:28:52.685349Z","submitted_at":"2021-11-23T18:59:14Z","title":"UniTAB: Unifying Text and Box Outputs for Grounded Vision-Language Modeling","version":2},"cited_work":{"arxiv_id":"2111.12085","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2111.12085","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"14dfce92-eafc-4b38-9307-1ac28950cc2c","year":2022},"citing_paper":{"arxiv_id":"2509.10026","last_updated":"2026-04-14T03:34:18Z","snapshot_observed_at":"2026-08-10T23:31:25.488694Z","submitted_at":"2025-09-12T07:45:44Z","title":"LaV-CoT: Language-Aware Visual CoT with Multi-Aspect Reward Optimization for Real-World Multilingual VQA","version":4},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-05-18T17:53:08.136677Z"},"links":{"cited_paper":"/paper/2111.12085","citing_paper":"/paper/2509.10026"},"observation_digest":"sha256:fd055b77c6f28294489181a8d8457c66cf4c201ea910ea69792183e06c43e2e9","observation_id":"d2e4e9d1-1a31-47e4-a176-7ed5d30c1c39","resolution":{"observed_at":"2026-05-18T17:56:42.238935Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2111.12085/citation-record","integrity":"/paper/2111.12085/integrity","json":"/paper/2111.12085/citation-record.json","paper":"/paper/2111.12085"},"outbound":[],"paper":{"arxiv_id":"2111.12085","last_updated":"2022-07-27T17:56:35Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-13T17:28:52.685349Z","submitted_at":"2021-11-23T18:59:14Z","title":"UniTAB: Unifying Text and Box Outputs for Grounded Vision-Language Modeling"},"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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 14 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2111.12085."}