{"as_of":"2026-08-16T22:20:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2240718eb00728f159c368dd3bcfd30125c8be32e7bc43cc890b7f4ff2fad042","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":"2026-08-16T06:30:59.297886+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":"2026-08-16T00:09:18.359522Z","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":"2026-05-11T19:16:09.844730Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2402.16832","last_updated":"2024-07-21T18:11:34Z","snapshot_observed_at":"2026-08-16T14:15:11.514877Z","submitted_at":"2024-02-26T18:56:48Z","title":"Cross-Modal Projection in Multimodal LLMs Doesn't Really Project Visual Attributes to Textual Space","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.16832","snapshot_observed_at":"2026-08-11T12:33:42.018763Z","title":"Mysterious projections: Multimodal llms gain domain- specific visual capabilities without richer cross-modal projections,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.14056","last_updated":"2024-12-18T17:06:21Z","snapshot_observed_at":"2026-08-13T23:42:32.185607Z","submitted_at":"2024-12-18T17:06:21Z","title":"A Review of Multimodal Explainable Artificial Intelligence: Past, Present and Future","version":1},"reference_index":283,"source":"pdf_text","source_observed_at":"2026-08-11T12:33:42.018763Z"},"links":{"cited_paper":"/paper/2402.16832","citing_paper":"/paper/2412.14056"},"observation_digest":"sha256:3559974a7b92e57e0d759f80bb3235fc35b3f0f570758cec4714a2655973ca13","observation_id":"4268f4a2-41f7-4f93-933e-4b5ddb9a16df","resolution":{"observed_at":"2026-08-11T12:33:42.018763Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.16832","last_updated":"2024-07-21T18:11:34Z","snapshot_observed_at":"2026-08-16T14:15:11.514877Z","submitted_at":"2024-02-26T18:56:48Z","title":"Cross-Modal Projection in Multimodal LLMs Doesn't Really Project Visual Attributes to Textual Space","version":2},"cited_work":{"arxiv_id":"2402.16832","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.16832","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Cross-modal pro- jection in multimodal llms doesn’t really project visual at- tributes to textual space.arXiv preprint arXiv:2402.16832","venue":null,"work_id":"b8928fca-feeb-4245-aac4-a8c103710741","year":null},"citing_paper":{"arxiv_id":"2604.22989","last_updated":"2026-04-24T20:03:04Z","snapshot_observed_at":"2026-07-06T23:09:19.041332Z","submitted_at":"2026-04-24T20:03:04Z","title":"CheXmix: Unified Generative Pretraining for Vision Language Models in Medical Imaging","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-05-08T12:22:11.995334Z"},"links":{"cited_paper":"/paper/2402.16832","citing_paper":"/paper/2604.22989"},"observation_digest":"sha256:8ee5ae72fbe221102812847f1c05e72c7d639c4f23cc41a77df264faa94163bc","observation_id":"64460e9b-1445-4076-8b87-93ba772ffef4","resolution":{"observed_at":"2026-05-11T19:16:09.847578Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.16832","last_updated":"2024-07-21T18:11:34Z","snapshot_observed_at":"2026-08-16T14:15:11.514877Z","submitted_at":"2024-02-26T18:56:48Z","title":"Cross-Modal Projection in Multimodal LLMs Doesn't Really Project Visual Attributes to Textual Space","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.16832","snapshot_observed_at":"2026-08-16T00:09:18.359522Z","title":"arXiv preprint arXiv:2402.16832 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.12748","last_updated":"2026-08-13T02:57:21Z","snapshot_observed_at":"2026-08-16T22:10:30.748176Z","submitted_at":"2026-08-13T02:57:21Z","title":"Scaling Representation Diversity: Modulated Attention and Reconstructive Regularization for Visual Grounding","version":1},"reference_index":65,"source":"arxiv_source","source_observed_at":"2026-08-16T00:09:18.359522Z"},"links":{"cited_paper":"/paper/2402.16832","citing_paper":"/paper/2608.12748"},"observation_digest":"sha256:49636ebc453465be5a4ddb552cb2da032b42462b361ce21b3657ea69f8a46979","observation_id":"94bcdb0f-c482-477f-bbbd-02555ecee220","resolution":{"observed_at":"2026-08-16T00:09:18.359522Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2402.16832/citation-record","integrity":"/paper/2402.16832/integrity","json":"/paper/2402.16832/citation-record.json","paper":"/paper/2402.16832"},"outbound":[],"paper":{"arxiv_id":"2402.16832","last_updated":"2024-07-21T18:11:34Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-16T14:15:11.514877Z","submitted_at":"2024-02-26T18:56:48Z","title":"Cross-Modal Projection in Multimodal LLMs Doesn't Really Project Visual Attributes to Textual Space"},"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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2402.16832."}