{"as_of":"2026-08-14T06:38:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:549e18275686c83f7837f7bf95b3fad8d2bf5178225448105aec1fd09c76076a","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":"2026-08-14T06:32:32.682623+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":"2026-08-12T10:31:01.959283Z","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":"2026-08-07T04:44:07.592512Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2303.02153","last_updated":"2023-03-03T18:59:47Z","snapshot_observed_at":"2026-08-13T12:32:28.384053Z","submitted_at":"2023-03-03T18:59:47Z","title":"Unleashing Text-to-Image Diffusion Models for Visual Perception","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.02153","snapshot_observed_at":"2026-08-12T10:31:01.959283Z","title":"Unleashing text-to-image diffusion models for visual perception","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.19189","last_updated":"2025-03-17T12:43:52Z","snapshot_observed_at":"2026-08-12T12:43:00.612672Z","submitted_at":"2024-11-28T14:50:14Z","title":"Video Depth without Video Models","version":2},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-12T10:31:01.959283Z"},"links":{"cited_paper":"/paper/2303.02153","citing_paper":"/paper/2411.19189"},"observation_digest":"sha256:93941430987b4bb76ed6c84f2e4be584ce6ac1dc6ddfce1094d5e4b6adc03049","observation_id":"0a3e5fbf-5e3d-485e-92b1-4bd17bd1b5d4","resolution":{"observed_at":"2026-08-12T10:31:01.959283Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.02153","last_updated":"2023-03-03T18:59:47Z","snapshot_observed_at":"2026-08-13T12:32:28.384053Z","submitted_at":"2023-03-03T18:59:47Z","title":"Unleashing Text-to-Image Diffusion Models for Visual Perception","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.02153","snapshot_observed_at":"2026-08-11T17:28:31.742188Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.09063","last_updated":"2024-12-13T02:41:26Z","snapshot_observed_at":"2026-08-14T01:12:56.241735Z","submitted_at":"2024-12-12T08:46:22Z","title":"An Efficient Framework for Enhancing Discriminative Models via Diffusion Techniques","version":2},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-11T17:28:31.742188Z"},"links":{"cited_paper":"/paper/2303.02153","citing_paper":"/paper/2412.09063"},"observation_digest":"sha256:cc5b0528c0fe194182bd46760f288a42b71fcda009d31d664236a604458e88cf","observation_id":"6159d87c-9ae0-4e2e-a59f-bcd54cc4ee38","resolution":{"observed_at":"2026-08-11T17:28:31.742188Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.02153","last_updated":"2023-03-03T18:59:47Z","snapshot_observed_at":"2026-08-13T12:32:28.384053Z","submitted_at":"2023-03-03T18:59:47Z","title":"Unleashing Text-to-Image Diffusion Models for Visual Perception","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.02153","snapshot_observed_at":"2026-08-11T13:14:47.976666Z","title":"Unleashing text-to-image diffusion models for visual perception.arXiv:2303.02153, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.13389","last_updated":"2025-09-14T11:15:24Z","snapshot_observed_at":"2026-08-14T02:05:57.291421Z","submitted_at":"2024-12-18T00:06:41Z","title":"Marigold-DC: Zero-Shot Monocular Depth Completion with Guided Diffusion","version":2},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-11T13:14:47.976666Z"},"links":{"cited_paper":"/paper/2303.02153","citing_paper":"/paper/2412.13389"},"observation_digest":"sha256:e3d1e4940bf5c3ba5e2be33f63354e826361494c25d6b39934d3588021a5b391","observation_id":"ee830df3-fca5-4262-8319-979a20894047","resolution":{"observed_at":"2026-08-11T13:14:47.976666Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.02153","last_updated":"2023-03-03T18:59:47Z","snapshot_observed_at":"2026-08-13T12:32:28.384053Z","submitted_at":"2023-03-03T18:59:47Z","title":"Unleashing Text-to-Image Diffusion Models for Visual Perception","version":1},"cited_work":{"arxiv_id":"2303.02153","doi":null,"metadata_source":"pith","pith_arxiv_id":"2303.02153","snapshot_observed_at":"2026-08-07T04:44:07.592512Z","title":"Unleashing Text-to-Image Diffusion Models for Visual Perception","venue":"cs.CV","work_id":"3b26e1ec-3331-4965-9b7e-7d42e742946b","year":2023},"citing_paper":{"arxiv_id":"2506.09954","last_updated":"2025-06-11T17:23:41Z","snapshot_observed_at":"2026-08-07T21:45:10.885875Z","submitted_at":"2025-06-11T17:23:41Z","title":"Vision Generalist Model: A Survey","version":1},"reference_index":208,"source":"arxiv_source","source_observed_at":"2026-08-07T04:44:05.736382Z"},"links":{"cited_paper":"/paper/2303.02153","citing_paper":"/paper/2506.09954"},"observation_digest":"sha256:e5d372b7f8cbba4308cf5ec625a394c96e119326950040a114644455dcc39e87","observation_id":"140a3005-03f8-4585-9448-dbf1ded9ba36","resolution":{"observed_at":"2026-08-07T04:44:07.649723Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2303.02153/citation-record","integrity":"/paper/2303.02153/integrity","json":"/paper/2303.02153/citation-record.json","paper":"/paper/2303.02153"},"outbound":[],"paper":{"arxiv_id":"2303.02153","last_updated":"2023-03-03T18:59:47Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-13T12:32:28.384053Z","submitted_at":"2023-03-03T18:59:47Z","title":"Unleashing Text-to-Image Diffusion Models for Visual Perception"},"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":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"As of 14 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2303.02153."}