{"as_of":"2026-08-14T00:30:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6f3807af46984593bade6231f718dd69545c8f057ff23d2994d1ebb1e6dd6568","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":"2026-08-12T16:56:10.927640Z","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":"2026-08-12T10:30:29.551282Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2105.02626","last_updated":"2021-04-29T00:36:17Z","snapshot_observed_at":"2026-08-13T19:32:15.353702Z","submitted_at":"2021-04-29T00:36:17Z","title":"A First Look: Towards Explainable TextVQA Models via Visual and Textual Explanations","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2105.02626","snapshot_observed_at":"2026-08-12T16:56:10.927640Z","title":"A first look: Towards explainable textvqa models via visual and textual explanations","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.13053","last_updated":"2024-11-20T05:57:00Z","snapshot_observed_at":"2026-08-13T07:40:26.980776Z","submitted_at":"2024-11-20T05:57:00Z","title":"MEGL: Multimodal Explanation-Guided Learning","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-12T16:56:10.927640Z"},"links":{"cited_paper":"/paper/2105.02626","citing_paper":"/paper/2411.13053"},"observation_digest":"sha256:125085f76edddf211aeebe204f980c59b8e5390121019c03bf4349c159a57e97","observation_id":"b20adb0b-4d6c-44ad-aa25-2dea72338326","resolution":{"observed_at":"2026-08-12T16:56:10.927640Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2105.02626","last_updated":"2021-04-29T00:36:17Z","snapshot_observed_at":"2026-08-13T19:32:15.353702Z","submitted_at":"2021-04-29T00:36:17Z","title":"A First Look: Towards Explainable TextVQA Models via Visual and Textual Explanations","version":1},"cited_work":{"arxiv_id":"2105.02626","doi":null,"metadata_source":"pith","pith_arxiv_id":"2105.02626","snapshot_observed_at":"2026-08-12T10:30:29.551282Z","title":"A First Look: Towards Explainable TextVQA Models via Visual and Textual Explanations","venue":"cs.CV","work_id":"85a58999-1496-416b-87d6-15934c0c8907","year":2021},"citing_paper":{"arxiv_id":"2411.19187","last_updated":"2025-02-19T05:44:50Z","snapshot_observed_at":"2026-08-13T12:28:24.594748Z","submitted_at":"2024-11-28T14:47:55Z","title":"Beyond Logit Lens: Contextual Embeddings for Robust Hallucination Detection & Grounding in VLMs","version":2},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-12T10:30:28.949071Z"},"links":{"cited_paper":"/paper/2105.02626","citing_paper":"/paper/2411.19187"},"observation_digest":"sha256:cb2e1d4178817d35c5b7321e48f15a5e4deb42592756c721da670569bb90b915","observation_id":"94578df9-6f54-486e-9d28-a3f1226aa5d8","resolution":{"observed_at":"2026-08-12T10:30:29.563644Z","resolver_source":"local_arxiv","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/2105.02626/citation-record","integrity":"/paper/2105.02626/integrity","json":"/paper/2105.02626/citation-record.json","paper":"/paper/2105.02626"},"outbound":[],"paper":{"arxiv_id":"2105.02626","last_updated":"2021-04-29T00:36:17Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-13T19:32:15.353702Z","submitted_at":"2021-04-29T00:36:17Z","title":"A First Look: Towards Explainable TextVQA Models via Visual and Textual 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":"2026-08-13T06:32:02.005865+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:2105.02626."}