{"as_of":"2026-08-08T22:37:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:78bd065de764063027a5e6dee67774cf8f881e3e35389cafb15b0d22ef8d15da","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":2,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":2,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T04:09:40.892599Z","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":"2026-06-30T06:24:19.584161Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2306.08889","last_updated":"2024-06-07T05:45:02Z","snapshot_observed_at":"2026-08-02T21:49:10.577943Z","submitted_at":"2023-06-15T06:45:46Z","title":"Dissecting Multimodality in VideoQA Transformer Models by Impairing Modality Fusion","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.08889","snapshot_observed_at":"2026-08-07T04:09:40.892599Z","title":"S., Matyasko, A., Jaiswal, S., Fernando, B., and Tan, C","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.11465","last_updated":"2025-06-13T04:39:58Z","snapshot_observed_at":"2026-08-08T12:08:14.565060Z","submitted_at":"2025-06-13T04:39:58Z","title":"RollingQ: Reviving the Cooperation Dynamics in Multimodal Transformer","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-07T04:09:40.892599Z"},"links":{"cited_paper":"/paper/2306.08889","citing_paper":"/paper/2506.11465"},"observation_digest":"sha256:914e4e3443aac6c214dc824da2e6df7de71059f04f53774d55f455b541b9c8e0","observation_id":"547cea5c-7798-47df-9452-779a9b14c033","resolution":{"observed_at":"2026-08-07T04:09:40.892599Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.08889","last_updated":"2024-06-07T05:45:02Z","snapshot_observed_at":"2026-08-02T21:49:10.577943Z","submitted_at":"2023-06-15T06:45:46Z","title":"Dissecting Multimodality in VideoQA Transformer Models by Impairing Modality Fusion","version":3},"cited_work":{"arxiv_id":"2306.08889","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2306.08889","snapshot_observed_at":"2026-06-30T06:24:19.584161Z","title":"Dissecting multimodality in videoqa transformer models by impairing modality fusion.arXiv preprint arXiv:2306.08889, 2023","venue":null,"work_id":"af6ca6bc-1e89-434e-afe6-bb3ef37b94f1","year":2023},"citing_paper":{"arxiv_id":"2606.29915","last_updated":"2026-06-29T07:51:25Z","snapshot_observed_at":"2026-08-04T10:56:20.672023Z","submitted_at":"2026-06-29T07:51:25Z","title":"H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-06-30T06:16:51.452335Z"},"links":{"cited_paper":"/paper/2306.08889","citing_paper":"/paper/2606.29915"},"observation_digest":"sha256:6c5a55da2a359df6d4c2e76cd09f168779082727f46eecbceca9e7a360a4ae2c","observation_id":"5e974d39-0d41-4161-a197-8def928049a4","resolution":{"observed_at":"2026-06-30T06:24:19.585935Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2306.08889/citation-record","integrity":"/paper/2306.08889/integrity","json":"/paper/2306.08889/citation-record.json","paper":"/paper/2306.08889"},"outbound":[],"paper":{"arxiv_id":"2306.08889","last_updated":"2024-06-07T05:45:02Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-02T21:49:10.577943Z","submitted_at":"2023-06-15T06:45:46Z","title":"Dissecting Multimodality in VideoQA Transformer Models by Impairing Modality Fusion"},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2306.08889."}