{"as_of":"2026-08-15T23:53:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:8ddedea4cd221739045138bda95aba4df490a4a03cc136c30adce6a11f6fe3bc","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":"2026-08-15T06:32:42.880941+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":"2026-08-12T11:06:10.026636Z","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":"2026-05-20T15:03:24.780269Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2109.04448","last_updated":"2021-09-09T17:47:50Z","snapshot_observed_at":"2026-08-15T14:21:07.670390Z","submitted_at":"2021-09-09T17:47:50Z","title":"Vision-and-Language or Vision-for-Language? On Cross-Modal Influence in Multimodal Transformers","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.04448","snapshot_observed_at":"2026-08-12T11:06:10.026636Z","title":"Vision-and-Language or Vision-for-Language? On Cross- Modal Influence in Multimodal Transformers","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.18620","last_updated":"2025-03-25T18:59:50Z","snapshot_observed_at":"2026-08-12T10:57:44.673291Z","submitted_at":"2024-11-27T18:59:26Z","title":"Cross-modal Information Flow in Multimodal Large Language Models","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-12T11:06:10.026636Z"},"links":{"cited_paper":"/paper/2109.04448","citing_paper":"/paper/2411.18620"},"observation_digest":"sha256:1e4d800aac415a3bf9c455fe5b415c49056ee53461c6f954f3dced605835463d","observation_id":"d646a383-9468-4e36-af97-baa081b32688","resolution":{"observed_at":"2026-08-12T11:06:10.026636Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.04448","last_updated":"2021-09-09T17:47:50Z","snapshot_observed_at":"2026-08-15T14:21:07.670390Z","submitted_at":"2021-09-09T17:47:50Z","title":"Vision-and-Language or Vision-for-Language? On Cross-Modal Influence in Multimodal Transformers","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.04448","snapshot_observed_at":"2026-08-11T23:54:23.886081Z","title":"Vision-and- language or vision-for-language? on cross-modal in- fluence in multimodal transformers,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.02104","last_updated":"2024-12-03T02:54:31Z","snapshot_observed_at":"2026-08-13T18:59:32.206758Z","submitted_at":"2024-12-03T02:54:31Z","title":"Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey","version":1},"reference_index":151,"source":"pdf_text","source_observed_at":"2026-08-11T23:54:23.886081Z"},"links":{"cited_paper":"/paper/2109.04448","citing_paper":"/paper/2412.02104"},"observation_digest":"sha256:403e57f459f5ef2bf170553f244f3c765f11f396e27a30ad4f9a97fcf5046c26","observation_id":"168d1ec8-1e15-43a4-9108-42b99c2a9024","resolution":{"observed_at":"2026-08-11T23:54:23.886081Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.04448","last_updated":"2021-09-09T17:47:50Z","snapshot_observed_at":"2026-08-15T14:21:07.670390Z","submitted_at":"2021-09-09T17:47:50Z","title":"Vision-and-Language or Vision-for-Language? On Cross-Modal Influence in Multimodal Transformers","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.04448","snapshot_observed_at":"2026-08-11T12:33:40.452712Z","title":"Vision-and-language or vision- for-language? on cross-modal influence in multimodal transformers,","venue":null,"work_id":null,"year":2021},"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":203,"source":"pdf_text","source_observed_at":"2026-08-11T12:33:40.452712Z"},"links":{"cited_paper":"/paper/2109.04448","citing_paper":"/paper/2412.14056"},"observation_digest":"sha256:4054227ef6bb75f6e0e906ca34e2465c5fc6e539a14664ee01027464717b4730","observation_id":"fa39ec64-9548-49a8-8b08-436f511eb967","resolution":{"observed_at":"2026-08-11T12:33:40.452712Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.04448","last_updated":"2021-09-09T17:47:50Z","snapshot_observed_at":"2026-08-15T14:21:07.670390Z","submitted_at":"2021-09-09T17:47:50Z","title":"Vision-and-Language or Vision-for-Language? On Cross-Modal Influence in Multimodal Transformers","version":1},"cited_work":{"arxiv_id":"2109.04448","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2109.04448","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"& Elliott, D","venue":null,"work_id":"ae371515-bbf6-4085-a65f-c92ca5247524","year":2021},"citing_paper":{"arxiv_id":"2605.17436","last_updated":"2026-05-17T13:11:38Z","snapshot_observed_at":"2026-08-02T02:17:15.999300Z","submitted_at":"2026-05-17T13:11:38Z","title":"Medical Context Distorts Decisions in Clinical Vision Language Models","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-20T14:59:11.496757Z"},"links":{"cited_paper":"/paper/2109.04448","citing_paper":"/paper/2605.17436"},"observation_digest":"sha256:ca77501f4dda08a7986f1dca9732a0f0c4060ff87565dd49795c19eae217cece","observation_id":"251beba0-629c-4e9b-9f7d-5a2103929d7a","resolution":{"observed_at":"2026-05-20T15:03:24.781943Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2109.04448/citation-record","integrity":"/paper/2109.04448/integrity","json":"/paper/2109.04448/citation-record.json","paper":"/paper/2109.04448"},"outbound":[],"paper":{"arxiv_id":"2109.04448","last_updated":"2021-09-09T17:47:50Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-15T14:21:07.670390Z","submitted_at":"2021-09-09T17:47:50Z","title":"Vision-and-Language or Vision-for-Language? On Cross-Modal Influence in Multimodal Transformers"},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2109.04448."}