{"as_of":"2026-08-08T23:35:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:be497d7b879da8a80ac5ae7b51a22ba2422ae2c0f29d93978f140e575772d8f0","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":"2026-08-08T06:32:00.761636+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":"2026-08-06T15:58:20.441340Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"arxiv_reference","source_observed_at":"2026-08-05T02:28:24.338817Z","state":"measured"}],"external_citation_measurements":[{"count":7,"observed_at":"2026-08-05T02:28:24.338817Z","source":"arxiv_reference"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2209.12152","last_updated":"2023-03-25T13:01:42Z","snapshot_observed_at":"2026-07-06T13:55:56.633104Z","submitted_at":"2022-09-25T05:21:59Z","title":"All are Worth Words: A ViT Backbone for Diffusion Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.12152","snapshot_observed_at":"2026-08-06T15:58:20.441340Z","title":"All are worth words: A vit backbone for diffusion models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.14549","last_updated":"2025-07-19T09:12:13Z","snapshot_observed_at":"2026-08-08T09:43:02.623391Z","submitted_at":"2025-07-19T09:12:13Z","title":"Synthesizing Images on Perceptual Boundaries of ANNs for Uncovering Human Perceptual Variability on Facial Expressions","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T15:58:20.441340Z"},"links":{"cited_paper":"/paper/2209.12152","citing_paper":"/paper/2507.14549"},"observation_digest":"sha256:945a98672e59e2552feb9d0c39866e234c1a7bfeae3e6c89e8cab2574d0ed6f8","observation_id":"b08dfb67-1461-4ca1-9ba1-6f209b6214a5","resolution":{"observed_at":"2026-08-06T15:58:20.441340Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2209.12152","last_updated":"2023-03-25T13:01:42Z","snapshot_observed_at":"2026-07-06T13:55:56.633104Z","submitted_at":"2022-09-25T05:21:59Z","title":"All are Worth Words: A ViT Backbone for Diffusion Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.12152","snapshot_observed_at":"2026-08-06T15:44:53.492073Z","title":"All are worth words: a vit backbone for score-based diffusion models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.15216","last_updated":"2025-07-21T03:36:58Z","snapshot_observed_at":"2026-08-06T15:35:49.818397Z","submitted_at":"2025-07-21T03:36:58Z","title":"Improving Joint Embedding Predictive Architecture with Diffusion Noise","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T15:44:53.492073Z"},"links":{"cited_paper":"/paper/2209.12152","citing_paper":"/paper/2507.15216"},"observation_digest":"sha256:fc86fc100c271067ba5f14b6eaefd10841ec9f2a89c9649dc26c94c5bcce02a2","observation_id":"2064eb82-2671-4e20-8ed9-532491679207","resolution":{"observed_at":"2026-08-06T15:44:53.492073Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2209.12152","last_updated":"2023-03-25T13:01:42Z","snapshot_observed_at":"2026-07-06T13:55:56.633104Z","submitted_at":"2022-09-25T05:21:59Z","title":"All are Worth Words: A ViT Backbone for Diffusion Models","version":4},"cited_work":{"arxiv_id":"2209.12152","doi":"10.48550/arxiv.2209.12152","metadata_source":"arxiv_reference","pith_arxiv_id":"2209.12152","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"All are worth words: A ViT backbone for diffusion models","venue":"arXiv (Cornell University)","work_id":"7ef680c5-947e-4488-a94f-8db02078147f","year":2023},"citing_paper":{"arxiv_id":"2604.18603","last_updated":"2026-04-09T19:32:11Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-04-09T19:32:11Z","title":"Dual Triangle Attention: Effective Bidirectional Attention Without Positional Embeddings","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-05-10T16:50:43.716813Z"},"links":{"cited_paper":"/paper/2209.12152","citing_paper":"/paper/2604.18603"},"observation_digest":"sha256:692ff51fc15525a50d170197a36e957fe41dcb90e37aab75964f6207f8dedcef","observation_id":"134142fa-b14e-48ce-afce-3a180f602e70","resolution":{"observed_at":"2026-05-10T21:20:51.622783Z","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"}},{"citation":{"cited_paper":{"arxiv_id":"2209.12152","last_updated":"2023-03-25T13:01:42Z","snapshot_observed_at":"2026-07-06T13:55:56.633104Z","submitted_at":"2022-09-25T05:21:59Z","title":"All are Worth Words: A ViT Backbone for Diffusion Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.12152","snapshot_observed_at":"2026-08-02T06:22:13.432641Z","title":"InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.12839","last_updated":"2026-07-25T21:10:17Z","snapshot_observed_at":"2026-08-07T08:22:19.273816Z","submitted_at":"2026-07-14T14:56:14Z","title":"HeteroMosaic: Exposing and Exploiting Heterogeneous Execution Opportunities for Energy-Efficient Edge LLM Inference","version":4},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-02T06:22:13.432641Z"},"links":{"cited_paper":"/paper/2209.12152","citing_paper":"/paper/2607.12839"},"observation_digest":"sha256:50caab9c014249e013e4ae710dde98c61140c8c4333b35b6e26a5d45010841f6","observation_id":"4f65ae32-0b8e-48b7-a539-158fab93b72b","resolution":{"observed_at":"2026-08-02T06:22:13.432641Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2209.12152/citation-record","integrity":"/paper/2209.12152/integrity","json":"/paper/2209.12152/citation-record.json","paper":"/paper/2209.12152"},"outbound":[],"paper":{"arxiv_id":"2209.12152","last_updated":"2023-03-25T13:01:42Z","latest_version":4,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T13:55:56.633104Z","submitted_at":"2022-09-25T05:21:59Z","title":"All are Worth Words: A ViT Backbone for Diffusion Models"},"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 4 inbound Pith citation observations for arXiv:2209.12152."}