{"as_of":"2026-08-07T10:07:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d66f54e3f1b927bfa6ad35328ccb78406f19e038ccc48e6acefb9df23c124a65","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":"2026-08-07T06:34:17.273281+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":"2026-05-16T21:55:40.808698Z","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":"2026-05-16T21:55:40.963336Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2406.05862","last_updated":"2025-01-13T09:33:47Z","snapshot_observed_at":"2026-08-07T00:28:56.995843Z","submitted_at":"2024-06-09T17:25:47Z","title":"II-Bench: An Image Implication Understanding Benchmark for Multimodal Large Language Models","version":3},"cited_work":{"arxiv_id":"2406.05862","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2406.05862","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Ii-bench: An image implication under- standing benchmark for multimodal large language models","venue":null,"work_id":"fd919e2b-4bc6-43ff-b3ad-577963d4bdf4","year":2024},"citing_paper":{"arxiv_id":"2407.01284","last_updated":"2024-07-01T13:39:08Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-07-01T13:39:08Z","title":"We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-05-16T21:55:40.808698Z"},"links":{"cited_paper":"/paper/2406.05862","citing_paper":"/paper/2407.01284"},"observation_digest":"sha256:eda0a65cefc8cbd9f6c87c36b8cc6d56b487751da77743f59365af9f1c2181a2","observation_id":"77f25bc0-583e-4d16-a488-1f95b423d7f1","resolution":{"observed_at":"2026-05-16T21:55:40.965887Z","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":"2406.05862","last_updated":"2025-01-13T09:33:47Z","snapshot_observed_at":"2026-08-07T00:28:56.995843Z","submitted_at":"2024-06-09T17:25:47Z","title":"II-Bench: An Image Implication Understanding Benchmark for Multimodal Large Language Models","version":3},"cited_work":{"arxiv_id":"2406.05862","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2406.05862","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Ii-bench: An image implication under- standing benchmark for multimodal large language models","venue":null,"work_id":"fd919e2b-4bc6-43ff-b3ad-577963d4bdf4","year":2024},"citing_paper":{"arxiv_id":"2604.27389","last_updated":"2026-05-13T08:16:41Z","snapshot_observed_at":"2026-08-06T03:49:04.127433Z","submitted_at":"2026-04-30T03:59:22Z","title":"COHERENCE: Benchmarking Fine-Grained Image-Text Alignment in Interleaved Multimodal Contexts","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-05-07T09:47:27.891288Z"},"links":{"cited_paper":"/paper/2406.05862","citing_paper":"/paper/2604.27389"},"observation_digest":"sha256:fd7893611da2d5f73786fdbb0f9eca348d36df681579b643bd6c1dcb457c8d2c","observation_id":"0529d0dd-097d-4de7-b7dd-416f7eeb8724","resolution":{"observed_at":"2026-05-12T09:41:26.745432Z","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":"2406.05862","last_updated":"2025-01-13T09:33:47Z","snapshot_observed_at":"2026-08-07T00:28:56.995843Z","submitted_at":"2024-06-09T17:25:47Z","title":"II-Bench: An Image Implication Understanding Benchmark for Multimodal Large Language Models","version":3},"cited_work":{"arxiv_id":"2406.05862","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2406.05862","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Ii-bench: An image implication under- standing benchmark for multimodal large language models","venue":null,"work_id":"fd919e2b-4bc6-43ff-b3ad-577963d4bdf4","year":2024},"citing_paper":{"arxiv_id":"2604.27389","last_updated":"2026-05-13T08:16:41Z","snapshot_observed_at":"2026-08-06T03:49:04.127433Z","submitted_at":"2026-04-30T03:59:22Z","title":"COHERENCE: Benchmarking Fine-Grained Image-Text Alignment in Interleaved Multimodal Contexts","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-05-14T21:15:30.952247Z"},"links":{"cited_paper":"/paper/2406.05862","citing_paper":"/paper/2604.27389"},"observation_digest":"sha256:e5e0906dc66ed66dec1e8133e3fd70de5e1186f38d300b8da7c5209f1df4c423","observation_id":"b71352d4-e37f-4840-9f5a-25457cd0fd57","resolution":{"observed_at":"2026-05-14T21:17:59.301490Z","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/2406.05862/citation-record","integrity":"/paper/2406.05862/integrity","json":"/paper/2406.05862/citation-record.json","paper":"/paper/2406.05862"},"outbound":[],"paper":{"arxiv_id":"2406.05862","last_updated":"2025-01-13T09:33:47Z","latest_version":3,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-07T00:28:56.995843Z","submitted_at":"2024-06-09T17:25:47Z","title":"II-Bench: An Image Implication Understanding Benchmark for Multimodal Large Language Models"},"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 3 inbound Pith citation observations for arXiv:2406.05862."}