{"as_of":"2026-08-07T19:11:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:434510b1190efe94ae3f8b498e3501ed4517e1c9d0b27cff036257b81bda67f1","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":"2026-08-07T06:34:17.273281+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":"2026-05-20T06:20:36.235304Z","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":"2026-05-20T06:20:36.499322Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2312.01571","last_updated":"2023-12-04T02:03:23Z","snapshot_observed_at":"2026-08-04T15:17:47.832154Z","submitted_at":"2023-12-04T02:03:23Z","title":"How to Configure Good In-Context Sequence for Visual Question Answering","version":1},"cited_work":{"arxiv_id":"2312.01571","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2312.01571","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2312.01571 , year=","venue":null,"work_id":"f5d533ff-4f4b-4eb0-8a52-fc3d87a74e28","year":2023},"citing_paper":{"arxiv_id":"2408.04840","last_updated":"2024-08-13T08:10:32Z","snapshot_observed_at":"2026-07-06T18:58:39.334273Z","submitted_at":"2024-08-09T03:25:42Z","title":"mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models","version":2},"reference_index":113,"source":"arxiv_source","source_observed_at":"2026-05-20T06:20:36.235304Z"},"links":{"cited_paper":"/paper/2312.01571","citing_paper":"/paper/2408.04840"},"observation_digest":"sha256:76ea5a8420a8dcb858dbcbc6ef87321efeda63fa5f766e44c490e2ea97c4a32b","observation_id":"e66d72d4-c06f-42cb-83c9-5fdd9237b91b","resolution":{"observed_at":"2026-05-20T06:20:36.501279Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.01571","last_updated":"2023-12-04T02:03:23Z","snapshot_observed_at":"2026-08-04T15:17:47.832154Z","submitted_at":"2023-12-04T02:03:23Z","title":"How to Configure Good In-Context Sequence for Visual Question Answering","version":1},"cited_work":{"arxiv_id":"2312.01571","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2312.01571","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2312.01571 , year=","venue":null,"work_id":"f5d533ff-4f4b-4eb0-8a52-fc3d87a74e28","year":2023},"citing_paper":{"arxiv_id":"2604.13403","last_updated":"2026-04-15T02:12:51Z","snapshot_observed_at":"2026-07-06T23:01:23.771347Z","submitted_at":"2026-04-15T02:12:51Z","title":"Why Multimodal In-Context Learning Lags Behind? Unveiling the Inner Mechanisms and Bottlenecks","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-05-10T13:41:37.942145Z"},"links":{"cited_paper":"/paper/2312.01571","citing_paper":"/paper/2604.13403"},"observation_digest":"sha256:f95299f740e0e21b42da69fbd897f462f1b3b2dbf6e5bb533f121941425b98b7","observation_id":"3096baac-c8b2-4062-a132-13b3c9f85d45","resolution":{"observed_at":"2026-05-10T13:45:28.291909Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2312.01571/citation-record","integrity":"/paper/2312.01571/integrity","json":"/paper/2312.01571/citation-record.json","paper":"/paper/2312.01571"},"outbound":[],"paper":{"arxiv_id":"2312.01571","last_updated":"2023-12-04T02:03:23Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-04T15:17:47.832154Z","submitted_at":"2023-12-04T02:03:23Z","title":"How to Configure Good In-Context Sequence for Visual Question Answering"},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2312.01571."}