{"as_of":"2026-08-11T09:41:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ae4b2f8883ce7567053c9f3e83d84caa9454da0e0c9bd78d7c3d6d79c82669dd","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":"2026-08-11T06:34:44.6726+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":"2026-08-10T21:33:21.102908Z","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":"2026-08-06T19:50:26.429204Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2205.06126","last_updated":"2022-05-12T14:39:21Z","snapshot_observed_at":"2026-07-06T13:09:18.182976Z","submitted_at":"2022-05-12T14:39:21Z","title":"One Model, Multiple Modalities: A Sparsely Activated Approach for Text, Sound, Image, Video and Code","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.06126","snapshot_observed_at":"2026-08-10T21:33:21.102908Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.04575","last_updated":"2025-01-08T15:45:21Z","snapshot_observed_at":"2026-08-10T21:27:03.875743Z","submitted_at":"2025-01-08T15:45:21Z","title":"InfiGUIAgent: A Multimodal Generalist GUI Agent with Native Reasoning and Reflection","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-10T21:33:21.102908Z"},"links":{"cited_paper":"/paper/2205.06126","citing_paper":"/paper/2501.04575"},"observation_digest":"sha256:1f5c4df708568227556f3dd35ff9ae82e986566bdcb5324d44f48ab680ffc9c3","observation_id":"ec985c00-984e-4cc9-83be-003c37b69df8","resolution":{"observed_at":"2026-08-10T21:33:21.102908Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.06126","last_updated":"2022-05-12T14:39:21Z","snapshot_observed_at":"2026-07-06T13:09:18.182976Z","submitted_at":"2022-05-12T14:39:21Z","title":"One Model, Multiple Modalities: A Sparsely Activated Approach for Text, Sound, Image, Video and Code","version":1},"cited_work":{"arxiv_id":"2205.06126","doi":null,"metadata_source":"pith","pith_arxiv_id":"2205.06126","snapshot_observed_at":"2026-08-06T19:50:26.429204Z","title":"One Model, Multiple Modalities: A Sparsely Activated Approach for Text, Sound, Image, Video and Code","venue":"cs.CL","work_id":"a6ffbe8f-5c9e-4dcd-afc2-7f45cf4e9789","year":2022},"citing_paper":{"arxiv_id":"2507.13364","last_updated":"2025-07-06T18:51:22Z","snapshot_observed_at":"2026-08-09T15:11:32.122204Z","submitted_at":"2025-07-06T18:51:22Z","title":"OmniVec2 -- A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T19:50:15.468308Z"},"links":{"cited_paper":"/paper/2205.06126","citing_paper":"/paper/2507.13364"},"observation_digest":"sha256:8e06aae554c5408e814f25cc752028fe3a98a37a5c9c71aa8dfc5fa3243b52a3","observation_id":"56770bc8-7652-4291-a236-385ac86ae989","resolution":{"observed_at":"2026-08-06T19:50:26.526503Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2205.06126/citation-record","integrity":"/paper/2205.06126/integrity","json":"/paper/2205.06126/citation-record.json","paper":"/paper/2205.06126"},"outbound":[],"paper":{"arxiv_id":"2205.06126","last_updated":"2022-05-12T14:39:21Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T13:09:18.182976Z","submitted_at":"2022-05-12T14:39:21Z","title":"One Model, Multiple Modalities: A Sparsely Activated Approach for Text, Sound, Image, Video and Code"},"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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2205.06126."}