{"as_of":"2026-08-13T02:44:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:4f4719922ebc0f80d11e833ec8130579d7b14f848908e3c5238e80a47152369a","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":"2026-08-12T06:34:41.77262+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":"2026-08-12T10:10:35.078326Z","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":"2026-08-07T05:47:18.734726Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2410.04081","last_updated":"2025-05-28T19:15:39Z","snapshot_observed_at":"2026-08-12T22:30:13.131686Z","submitted_at":"2024-10-05T08:27:53Z","title":"Epsilon-VAE: Denoising as Visual Decoding","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.04081","snapshot_observed_at":"2026-08-12T10:10:35.078326Z","title":"person is acting like human monkey","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.19527","last_updated":"2025-08-07T08:03:29Z","snapshot_observed_at":"2026-08-12T10:04:01.603806Z","submitted_at":"2024-11-29T07:54:56Z","title":"DisCoRD: Discrete Tokens to Continuous Motion via Rectified Flow Decoding","version":4},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-12T10:10:35.078326Z"},"links":{"cited_paper":"/paper/2410.04081","citing_paper":"/paper/2411.19527"},"observation_digest":"sha256:26e4e10706fe3a312545d2c19eb3bdbe3a709374cbc84ba433656688364744c3","observation_id":"290c47bb-45d4-4b72-8b63-c65c8d444811","resolution":{"observed_at":"2026-08-12T10:10:35.078326Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.04081","last_updated":"2025-05-28T19:15:39Z","snapshot_observed_at":"2026-08-12T22:30:13.131686Z","submitted_at":"2024-10-05T08:27:53Z","title":"Epsilon-VAE: Denoising as Visual Decoding","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.04081","snapshot_observed_at":"2026-08-09T22:56:36.235654Z","title":"-vae: Denoising as visual decoding, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.18593","last_updated":"2025-01-30T18:59:37Z","snapshot_observed_at":"2026-08-10T02:35:35.003821Z","submitted_at":"2025-01-30T18:59:37Z","title":"Diffusion Autoencoders are Scalable Image Tokenizers","version":1},"reference_index":68,"source":"arxiv_source","source_observed_at":"2026-08-09T22:56:36.235654Z"},"links":{"cited_paper":"/paper/2410.04081","citing_paper":"/paper/2501.18593"},"observation_digest":"sha256:0462ff3879556bb9872d258adfb1ee2a88f93e8d99240ea27499a14ab3550a2c","observation_id":"6ece528b-28f1-436c-be1c-fbf0048ec9ce","resolution":{"observed_at":"2026-08-09T22:56:36.235654Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.04081","last_updated":"2025-05-28T19:15:39Z","snapshot_observed_at":"2026-08-12T22:30:13.131686Z","submitted_at":"2024-10-05T08:27:53Z","title":"Epsilon-VAE: Denoising as Visual Decoding","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.04081","snapshot_observed_at":"2026-08-07T12:46:47.729995Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.23660","last_updated":"2025-05-29T17:09:25Z","snapshot_observed_at":"2026-08-12T19:13:20.732949Z","submitted_at":"2025-05-29T17:09:25Z","title":"D-AR: Diffusion via Autoregressive Models","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T12:46:47.729995Z"},"links":{"cited_paper":"/paper/2410.04081","citing_paper":"/paper/2505.23660"},"observation_digest":"sha256:6f8cd0296eb1bfe497c13de6a98a7d7e1843dfec968ba450919f7ec17dba225d","observation_id":"29b6e9f4-6ec3-4d52-8b38-a40df98700e2","resolution":{"observed_at":"2026-08-07T12:46:47.729995Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.04081","last_updated":"2025-05-28T19:15:39Z","snapshot_observed_at":"2026-08-12T22:30:13.131686Z","submitted_at":"2024-10-05T08:27:53Z","title":"Epsilon-VAE: Denoising as Visual Decoding","version":4},"cited_work":{"arxiv_id":"2410.04081","doi":null,"metadata_source":"pith","pith_arxiv_id":"2410.04081","snapshot_observed_at":"2026-08-07T05:47:18.734726Z","title":"Epsilon-VAE: Denoising as Visual Decoding","venue":"cs.CV","work_id":"03d45c83-4fcd-40e2-80bc-fa289c6e3963","year":2024},"citing_paper":{"arxiv_id":"2506.07136","last_updated":"2025-06-08T13:30:11Z","snapshot_observed_at":"2026-08-09T23:29:32.319934Z","submitted_at":"2025-06-08T13:30:11Z","title":"Hi-VAE: Efficient Video Autoencoding with Global and Detailed Motion","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:18.275937Z"},"links":{"cited_paper":"/paper/2410.04081","citing_paper":"/paper/2506.07136"},"observation_digest":"sha256:84b54d6f7025c7307d67ecb3820c6152a7c82d61662d61acee3edbebacb977cc","observation_id":"9b4fcf9e-5213-4de5-9430-42b5dd41d3a1","resolution":{"observed_at":"2026-08-07T05:47:18.823298Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2410.04081/citation-record","integrity":"/paper/2410.04081/integrity","json":"/paper/2410.04081/citation-record.json","paper":"/paper/2410.04081"},"outbound":[],"paper":{"arxiv_id":"2410.04081","last_updated":"2025-05-28T19:15:39Z","latest_version":4,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-12T22:30:13.131686Z","submitted_at":"2024-10-05T08:27:53Z","title":"Epsilon-VAE: Denoising as Visual Decoding"},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2410.04081."}