{"as_of":"2026-08-08T05:09:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ca55337b322b732fcc490e98251f73c503ac63aa71e1aaf2ee5659ea52d05011","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":"2026-08-07T06:34:17.273281+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":"2026-08-07T11:59:06.205021Z","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":"2026-06-30T22:05:06.148661Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2206.09852","last_updated":"2022-06-20T15:31:13Z","snapshot_observed_at":"2026-08-07T22:31:22.587774Z","submitted_at":"2022-06-20T15:31:13Z","title":"M&M Mix: A Multimodal Multiview Transformer Ensemble","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.09852","snapshot_observed_at":"2026-08-07T11:59:06.205021Z","title":"M&m mix: A multimodal multiview transformer ensemble","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.00827","last_updated":"2025-06-01T04:22:02Z","snapshot_observed_at":"2026-08-07T11:54:56.796885Z","submitted_at":"2025-06-01T04:22:02Z","title":"Improving Keystep Recognition in Ego-Video via Dexterous Focus","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T11:59:06.205021Z"},"links":{"cited_paper":"/paper/2206.09852","citing_paper":"/paper/2506.00827"},"observation_digest":"sha256:a73c1289653c87b950850e40c06abc05e42a42db642403bdd581e20e0c9402e0","observation_id":"adfd9535-5c8b-4070-a0fc-537de4b1c8a5","resolution":{"observed_at":"2026-08-07T11:59:06.205021Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.09852","last_updated":"2022-06-20T15:31:13Z","snapshot_observed_at":"2026-08-07T22:31:22.587774Z","submitted_at":"2022-06-20T15:31:13Z","title":"M&M Mix: A Multimodal Multiview Transformer Ensemble","version":1},"cited_work":{"arxiv_id":"2206.09852","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2206.09852","snapshot_observed_at":"2026-06-30T22:05:06.148661Z","title":"arXiv preprint arXiv:2206.09852 , year=","venue":null,"work_id":"be87a646-fea0-474a-8307-269d1d5605ee","year":null},"citing_paper":{"arxiv_id":"2606.09853","last_updated":"2026-05-12T19:42:19Z","snapshot_observed_at":"2026-08-02T09:39:01.496025Z","submitted_at":"2026-05-12T19:42:19Z","title":"SynIB: Informational Bottleneck for Maximizing Synergy in Multimodal Learning","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-06-30T21:55:53.630732Z"},"links":{"cited_paper":"/paper/2206.09852","citing_paper":"/paper/2606.09853"},"observation_digest":"sha256:d639a9738062c7f8fb198a88ccf0f7e93d1948cf8a1045e0e5cba2247e100b2d","observation_id":"5fb200b2-fd31-45c6-941c-a00b94891884","resolution":{"observed_at":"2026-06-30T22:05:06.150242Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2206.09852/citation-record","integrity":"/paper/2206.09852/integrity","json":"/paper/2206.09852/citation-record.json","paper":"/paper/2206.09852"},"outbound":[],"paper":{"arxiv_id":"2206.09852","last_updated":"2022-06-20T15:31:13Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-07T22:31:22.587774Z","submitted_at":"2022-06-20T15:31:13Z","title":"M&M Mix: A Multimodal Multiview Transformer Ensemble"},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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:2206.09852."}