{"as_of":"2026-08-08T09:28:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:dbcf0b518b76d6eaa82fdbf7d9c4a05928b05165744ff91e69b3f9d39fd6d152","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":"2026-08-08T06:32:00.761636+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":"2026-08-06T17:07:53.544005Z","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":"2026-05-17T04:44:02.457882Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2412.00151","last_updated":"2025-07-10T02:48:27Z","snapshot_observed_at":"2026-07-06T19:59:11.046948Z","submitted_at":"2024-11-29T06:17:11Z","title":"DLaVA: Document Language and Vision Assistant for Answer Localization with Enhanced Interpretability and Trustworthiness","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.00151","snapshot_observed_at":"2026-08-06T17:07:53.544005Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.12490","last_updated":"2025-07-15T20:05:25Z","snapshot_observed_at":"2026-08-08T01:49:25.936637Z","submitted_at":"2025-07-15T20:05:25Z","title":"Spatially Grounded Explanations in Vision Language Models for Document Visual Question Answering","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T17:07:53.544005Z"},"links":{"cited_paper":"/paper/2412.00151","citing_paper":"/paper/2507.12490"},"observation_digest":"sha256:745a8aeb1eb6b7fd5aa45bca192bcf787701f6206d620de34651507f72e319fe","observation_id":"b8fcff72-8148-4bbc-8735-301968efb62e","resolution":{"observed_at":"2026-08-06T17:07:53.544005Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.00151","last_updated":"2025-07-10T02:48:27Z","snapshot_observed_at":"2026-07-06T19:59:11.046948Z","submitted_at":"2024-11-29T06:17:11Z","title":"DLaVA: Document Language and Vision Assistant for Answer Localization with Enhanced Interpretability and Trustworthiness","version":2},"cited_work":{"arxiv_id":"2412.00151","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2412.00151","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Dlava: Document lan- guage and vision assistant for answer localization with en- hanced interpretability and trustworthiness","venue":null,"work_id":"75d54572-8376-42bc-8315-e5683b10d06a","year":2024},"citing_paper":{"arxiv_id":"2511.22521","last_updated":"2026-04-16T14:40:49Z","snapshot_observed_at":"2026-07-06T22:37:08.086095Z","submitted_at":"2025-11-27T15:00:58Z","title":"DocVAL: Validated Chain-of-Thought Distillation for Grounded Document VQA","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-17T04:41:55.030673Z"},"links":{"cited_paper":"/paper/2412.00151","citing_paper":"/paper/2511.22521"},"observation_digest":"sha256:902991f3c5d728ef9e65fd0f64cd8cc68bf6498911e0a4e7f1b7e055fa63202c","observation_id":"8e5826c9-dd94-46cc-8d8c-4fe1a8678444","resolution":{"observed_at":"2026-05-17T04:44:02.459977Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.00151","last_updated":"2025-07-10T02:48:27Z","snapshot_observed_at":"2026-07-06T19:59:11.046948Z","submitted_at":"2024-11-29T06:17:11Z","title":"DLaVA: Document Language and Vision Assistant for Answer Localization with Enhanced Interpretability and Trustworthiness","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.00151","snapshot_observed_at":"2026-08-02T01:25:28.323502Z","title":"arXiv preprint arXiv:2412.00151 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14682","last_updated":"2026-07-16T07:43:39Z","snapshot_observed_at":"2026-08-06T12:12:36.114458Z","submitted_at":"2026-07-16T07:43:39Z","title":"Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment","version":1},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-02T01:25:28.323502Z"},"links":{"cited_paper":"/paper/2412.00151","citing_paper":"/paper/2607.14682"},"observation_digest":"sha256:45382084413c97510bbd81fadfed09ace751f347db10b8307251f50fcedfb323","observation_id":"13c8431a-09e6-43fe-bf40-f1ecb82f34a6","resolution":{"observed_at":"2026-08-02T01:25:28.323502Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2412.00151/citation-record","integrity":"/paper/2412.00151/integrity","json":"/paper/2412.00151/citation-record.json","paper":"/paper/2412.00151"},"outbound":[],"paper":{"arxiv_id":"2412.00151","last_updated":"2025-07-10T02:48:27Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T19:59:11.046948Z","submitted_at":"2024-11-29T06:17:11Z","title":"DLaVA: Document Language and Vision Assistant for Answer Localization with Enhanced Interpretability and Trustworthiness"},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2412.00151."}