{"as_of":"2026-08-10T18:59:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:dd3bd507003d48ac625e50b019a25a84b57d994d789be1509314a6ec2f4079bf","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":"2026-08-10T06:31:04.303077+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":"2026-08-06T19:01:55.604664Z","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":"2026-07-03T09:07:48.171808Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2104.11178","last_updated":"2021-12-07T04:01:25Z","snapshot_observed_at":"2026-07-06T11:02:49.722095Z","submitted_at":"2021-04-22T17:07:41Z","title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.11178","snapshot_observed_at":"2026-08-06T19:01:55.604664Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.06652","last_updated":"2025-07-09T08:34:24Z","snapshot_observed_at":"2026-08-09T05:56:03.301144Z","submitted_at":"2025-07-09T08:34:24Z","title":"Federated Learning Inspired Fuzzy Systems: Decentralized Rule Updating for Privacy and Scalable Decision Making","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T19:01:55.604664Z"},"links":{"cited_paper":"/paper/2104.11178","citing_paper":"/paper/2507.06652"},"observation_digest":"sha256:799b2b789043de00eddaffac84914178b81bc4c2bdce5537323ed19ec33b8eb8","observation_id":"58f10a6c-dabf-4c71-a7ef-f73c84dfcbe7","resolution":{"observed_at":"2026-08-06T19:01:55.604664Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.11178","last_updated":"2021-12-07T04:01:25Z","snapshot_observed_at":"2026-07-06T11:02:49.722095Z","submitted_at":"2021-04-22T17:07:41Z","title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","version":3},"cited_work":{"arxiv_id":"2104.11178","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2104.11178","snapshot_observed_at":"2026-07-03T09:07:48.171808Z","title":"Vatt: Transformers for multimodal self-supervised learning from raw video, audio and text.arXiv preprint arXiv:2104.11178, 2021","venue":null,"work_id":"9b283c23-6898-4860-b602-118a5253f19f","year":2021},"citing_paper":{"arxiv_id":"2507.21420","last_updated":"2026-04-28T19:54:45Z","snapshot_observed_at":"2026-08-06T19:44:38.919643Z","submitted_at":"2025-07-29T01:07:09Z","title":"ReGATE: Learning Faster and Better with Fewer Tokens in MLLMs","version":3},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-05-19T03:18:11.993413Z"},"links":{"cited_paper":"/paper/2104.11178","citing_paper":"/paper/2507.21420"},"observation_digest":"sha256:e46f1474a884b7547a90d8fa646a13c24366b82fbdd60c924aac86e0d8401c25","observation_id":"cde02cdd-0274-427c-ad10-2fff5afbfb3c","resolution":{"observed_at":"2026-05-19T03:22:01.096519Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2104.11178","last_updated":"2021-12-07T04:01:25Z","snapshot_observed_at":"2026-07-06T11:02:49.722095Z","submitted_at":"2021-04-22T17:07:41Z","title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","version":3},"cited_work":{"arxiv_id":"2104.11178","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2104.11178","snapshot_observed_at":"2026-07-03T09:07:48.171808Z","title":"Vatt: Transformers for multimodal self-supervised learning from raw video, audio and text.arXiv preprint arXiv:2104.11178, 2021","venue":null,"work_id":"9b283c23-6898-4860-b602-118a5253f19f","year":2021},"citing_paper":{"arxiv_id":"2606.12362","last_updated":"2026-06-10T17:31:34Z","snapshot_observed_at":"2026-08-09T08:33:25.944536Z","submitted_at":"2026-06-10T17:31:34Z","title":"Latent World Recovery for Multimodal Learning with Missing Modalities","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-06-27T10:30:27.174843Z"},"links":{"cited_paper":"/paper/2104.11178","citing_paper":"/paper/2606.12362"},"observation_digest":"sha256:ae4ab04152f1574d8e6691abb65a9de42f7c762d66bb9301cd96ac46f54fc34d","observation_id":"13f3e6b7-70c9-4f31-b4f9-c6c71a5fe01b","resolution":{"observed_at":"2026-07-03T09:07:48.173570Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2104.11178/citation-record","integrity":"/paper/2104.11178/integrity","json":"/paper/2104.11178/citation-record.json","paper":"/paper/2104.11178"},"outbound":[],"paper":{"arxiv_id":"2104.11178","last_updated":"2021-12-07T04:01:25Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T11:02:49.722095Z","submitted_at":"2021-04-22T17:07:41Z","title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text"},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2104.11178."}