{"as_of":"2026-08-21T19:34:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:33cd05fe9732a3c104f11692cac9fd48caf8823a0d76c5023f461ae1c650b316","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":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-21T06:32:19.484+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T21:27:06.336943Z","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":"2026-05-15T05:37:41.501768Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2308.16463","last_updated":"2024-09-17T07:46:07Z","snapshot_observed_at":"2026-08-16T15:04:25.599348Z","submitted_at":"2023-08-31T05:15:27Z","title":"Sparkles: Unlocking Chats Across Multiple Images for Multimodal Instruction-Following Models","version":3},"cited_work":{"arxiv_id":"2308.16463","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2308.16463","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Sparkles: Unlocking chats across multiple images for multimodal instruction-following mod- els","venue":null,"work_id":"478148d3-5176-41b5-b373-11bf99acd759","year":2023},"citing_paper":{"arxiv_id":"2311.16502","last_updated":"2024-06-13T15:02:39Z","snapshot_observed_at":"2026-08-17T13:10:52.611064Z","submitted_at":"2023-11-27T17:33:21Z","title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","version":4},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-05-15T05:37:41.401736Z"},"links":{"cited_paper":"/paper/2308.16463","citing_paper":"/paper/2311.16502"},"observation_digest":"sha256:5beb8c61998ba6bfb04950cc232b3108afb5ad489d9684f0a3206f3592ae264c","observation_id":"a0c933ba-9210-4abe-a2bd-e8e72d43619d","resolution":{"observed_at":"2026-05-15T05:37:41.505507Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.16463","last_updated":"2024-09-17T07:46:07Z","snapshot_observed_at":"2026-08-16T15:04:25.599348Z","submitted_at":"2023-08-31T05:15:27Z","title":"Sparkles: Unlocking Chats Across Multiple Images for Multimodal Instruction-Following Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.16463","snapshot_observed_at":"2026-08-12T14:31:36.996413Z","title":"Sparkles: Unlocking chats across multiple images for multi- modal instruction-following models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.15296","last_updated":"2024-12-08T04:24:31Z","snapshot_observed_at":"2026-08-18T21:58:09.907460Z","submitted_at":"2024-11-22T18:59:54Z","title":"MME-Survey: A Comprehensive Survey on Evaluation of Multimodal LLMs","version":2},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-12T14:31:36.996413Z"},"links":{"cited_paper":"/paper/2308.16463","citing_paper":"/paper/2411.15296"},"observation_digest":"sha256:6fc9b349b1c4d5c5da86af5eae47c567142a3a61bd6d6a8c6a7232e292890360","observation_id":"7f5c4991-0029-49b1-b0d4-903f5fe2fa16","resolution":{"observed_at":"2026-08-12T14:31:36.996413Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.16463","last_updated":"2024-09-17T07:46:07Z","snapshot_observed_at":"2026-08-16T15:04:25.599348Z","submitted_at":"2023-08-31T05:15:27Z","title":"Sparkles: Unlocking Chats Across Multiple Images for Multimodal Instruction-Following Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.16463","snapshot_observed_at":"2026-08-11T14:59:01.882239Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.18619","last_updated":"2024-12-30T03:00:30Z","snapshot_observed_at":"2026-08-21T08:28:48.041857Z","submitted_at":"2024-12-16T05:02:25Z","title":"Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey","version":2},"reference_index":172,"source":"pdf_text","source_observed_at":"2026-08-11T14:59:01.882239Z"},"links":{"cited_paper":"/paper/2308.16463","citing_paper":"/paper/2412.18619"},"observation_digest":"sha256:06ce64e731d50f6e62f6ad418934d2d908b1065219b0f20bfe5771e568e21e2e","observation_id":"bce4011e-7787-4c5f-90f1-ea1b7de4a710","resolution":{"observed_at":"2026-08-11T14:59:01.882239Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.16463","last_updated":"2024-09-17T07:46:07Z","snapshot_observed_at":"2026-08-16T15:04:25.599348Z","submitted_at":"2023-08-31T05:15:27Z","title":"Sparkles: Unlocking Chats Across Multiple Images for Multimodal Instruction-Following Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.16463","snapshot_observed_at":"2026-08-15T21:27:06.336943Z","title":"Sparkles: Unlocking chats across multiple images for multimodal instruction-following models.arXiv preprint arXiv:2308.16463, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.09787","last_updated":"2025-05-14T20:28:04Z","snapshot_observed_at":"2026-08-19T18:43:04.980263Z","submitted_at":"2025-05-14T20:28:04Z","title":"A Multimodal Multi-Agent Framework for Radiology Report Generation","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T21:27:06.336943Z"},"links":{"cited_paper":"/paper/2308.16463","citing_paper":"/paper/2505.09787"},"observation_digest":"sha256:486d92e6824dba984b96d1e2d00b088ec25cf5d179bba19f71e9daac424da0dc","observation_id":"c8bc9744-c23b-4ead-b8ef-791c14e066f3","resolution":{"observed_at":"2026-08-15T21:27:06.336943Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2308.16463/citation-record","integrity":"/paper/2308.16463/integrity","json":"/paper/2308.16463/citation-record.json","paper":"/paper/2308.16463"},"outbound":[],"paper":{"arxiv_id":"2308.16463","last_updated":"2024-09-17T07:46:07Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-16T15:04:25.599348Z","submitted_at":"2023-08-31T05:15:27Z","title":"Sparkles: Unlocking Chats Across Multiple Images for Multimodal Instruction-Following 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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 21 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2308.16463."}