{"as_of":"2026-08-14T07:18:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:58816f70415be8c7bf8a4ba7b3b363ffbc425a6da1b4c1bd3df14a0094a735c5","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":"2026-08-14T06:32:32.682623+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":"2026-08-12T20:54:07.425517Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-06T18:36:01.793751Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2410.04778","last_updated":"2025-06-27T17:08:56Z","snapshot_observed_at":"2026-08-12T22:29:28.114750Z","submitted_at":"2024-10-07T06:36:55Z","title":"MM-R$^3$: On (In-)Consistency of Vision-Language Models (VLMs)","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.04778","snapshot_observed_at":"2026-08-12T20:54:07.425517Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.09273","last_updated":"2024-11-14T08:22:42Z","snapshot_observed_at":"2026-08-12T22:57:44.060170Z","submitted_at":"2024-11-14T08:22:42Z","title":"Cross-Modal Consistency in Multimodal Large Language Models","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-12T20:54:07.425517Z"},"links":{"cited_paper":"/paper/2410.04778","citing_paper":"/paper/2411.09273"},"observation_digest":"sha256:6dd97ab834382ab55f27a95e9a12d450d464d3386e44394879ff864ba1626da1","observation_id":"faa740de-faa2-4496-b262-29ae9ea5a219","resolution":{"observed_at":"2026-08-12T20:54:07.425517Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.04778","last_updated":"2025-06-27T17:08:56Z","snapshot_observed_at":"2026-08-12T22:29:28.114750Z","submitted_at":"2024-10-07T06:36:55Z","title":"MM-R$^3$: On (In-)Consistency of Vision-Language Models (VLMs)","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.04778","snapshot_observed_at":"2026-08-07T12:36:38.091875Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.24211","last_updated":"2025-05-30T04:51:54Z","snapshot_observed_at":"2026-08-10T05:40:33.964253Z","submitted_at":"2025-05-30T04:51:54Z","title":"Are Any-to-Any Models More Consistent Across Modality Transfers Than Specialists?","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-07T12:36:38.091875Z"},"links":{"cited_paper":"/paper/2410.04778","citing_paper":"/paper/2505.24211"},"observation_digest":"sha256:cb8e53a35b081fddded7e5cc8ac2d13f554e490a0867facb4604b7a412ac5319","observation_id":"4ae63147-8f78-4a3f-b092-4784a1fb23b6","resolution":{"observed_at":"2026-08-07T12:36:38.091875Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.04778","last_updated":"2025-06-27T17:08:56Z","snapshot_observed_at":"2026-08-12T22:29:28.114750Z","submitted_at":"2024-10-07T06:36:55Z","title":"MM-R$^3$: On (In-)Consistency of Vision-Language Models (VLMs)","version":2},"cited_work":{"arxiv_id":"2410.04778","doi":null,"metadata_source":"pith","pith_arxiv_id":"2410.04778","snapshot_observed_at":"2026-08-06T18:36:01.793751Z","title":"MM-R$^3$: On (In-)Consistency of Vision-Language Models (VLMs)","venue":"cs.CV","work_id":"6137019a-5040-48ee-aaa6-4236df789258","year":2024},"citing_paper":{"arxiv_id":"2507.10442","last_updated":"2025-07-10T15:26:41Z","snapshot_observed_at":"2026-08-13T08:39:26.634751Z","submitted_at":"2025-07-10T15:26:41Z","title":"Response Wide Shut? Surprising Observations in Basic Vision Language Model Capabilities","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-06T18:36:01.249092Z"},"links":{"cited_paper":"/paper/2410.04778","citing_paper":"/paper/2507.10442"},"observation_digest":"sha256:56476b00bf3fa8f5cd62072889a357200fcd5196c3620d4a7c6e815e23c46cd8","observation_id":"5c11106e-fb3b-4761-92e4-34662b57b134","resolution":{"observed_at":"2026-08-06T18:36:01.798101Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2410.04778/citation-record","integrity":"/paper/2410.04778/integrity","json":"/paper/2410.04778/citation-record.json","paper":"/paper/2410.04778"},"outbound":[],"paper":{"arxiv_id":"2410.04778","last_updated":"2025-06-27T17:08:56Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-12T22:29:28.114750Z","submitted_at":"2024-10-07T06:36:55Z","title":"MM-R$^3$: On (In-)Consistency of Vision-Language Models (VLMs)"},"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":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"As of 14 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2410.04778."}