{"as_of":"2026-08-05T10:53:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:798bc92ce47c2f8ecf1a3e12956a02ecf2b4f2e86e7cb117b7cb95dab5f64376","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":"2026-08-05T06:32:48.257954+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":"2026-05-18T05:36:38.735914Z","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":"2026-05-18T05:40:56.036122Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2311.18021","last_updated":"2024-12-07T15:34:23Z","snapshot_observed_at":"2026-07-06T16:54:37.940527Z","submitted_at":"2023-11-29T19:08:11Z","title":"Can Multimodal Large Language Models Truly Perform Multimodal In-Context Learning?","version":2},"cited_work":{"arxiv_id":"2311.18021","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2311.18021","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Shuo Chen, Zhen Han, Bailan He, Jianzhe Liu, Mark Buckley, Yao Qin, Philip Torr, V olker Tresp, and Jindong Gu","venue":null,"work_id":"6b80443b-a76f-41af-9c05-ee504fc0b5cb","year":2024},"citing_paper":{"arxiv_id":"2510.18117","last_updated":"2026-04-07T16:14:59Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-10-20T21:35:17Z","title":"Online In-Context Distillation for Low-Resource Vision Language Models","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-18T05:36:38.735914Z"},"links":{"cited_paper":"/paper/2311.18021","citing_paper":"/paper/2510.18117"},"observation_digest":"sha256:ea4cc6633e26d01996cad23edde95d4688aabbc4f5d1a7170828c8a6fbb68221","observation_id":"f7798c12-b2f3-499a-afef-f652dc53e1b7","resolution":{"observed_at":"2026-05-18T05:40:56.038621Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.18021","last_updated":"2024-12-07T15:34:23Z","snapshot_observed_at":"2026-07-06T16:54:37.940527Z","submitted_at":"2023-11-29T19:08:11Z","title":"Can Multimodal Large Language Models Truly Perform Multimodal In-Context Learning?","version":2},"cited_work":{"arxiv_id":"2311.18021","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2311.18021","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Shuo Chen, Zhen Han, Bailan He, Jianzhe Liu, Mark Buckley, Yao Qin, Philip Torr, V olker Tresp, and Jindong Gu","venue":null,"work_id":"6b80443b-a76f-41af-9c05-ee504fc0b5cb","year":2024},"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":4,"source":"arxiv_source","source_observed_at":"2026-05-10T13:41:37.942145Z"},"links":{"cited_paper":"/paper/2311.18021","citing_paper":"/paper/2604.13403"},"observation_digest":"sha256:36b6f6ee1863f87733a0584b62b12de7d0537d5eaa05b28bf5bcbd289169248b","observation_id":"488fc930-8120-4fcb-aefc-b2555ab85a12","resolution":{"observed_at":"2026-05-10T13:45:28.206259Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2311.18021/citation-record","integrity":"/paper/2311.18021/integrity","json":"/paper/2311.18021/citation-record.json","paper":"/paper/2311.18021"},"outbound":[],"paper":{"arxiv_id":"2311.18021","last_updated":"2024-12-07T15:34:23Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T16:54:37.940527Z","submitted_at":"2023-11-29T19:08:11Z","title":"Can Multimodal Large Language Models Truly Perform Multimodal In-Context Learning?"},"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":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"thesis":"As of 5 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2311.18021."}