{"as_of":"2026-08-16T23:04:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:8b4a522b5300a341af25a1e309ec62da44b7cd1cf0e074d19c22485084ecb2ee","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":"2026-08-16T06:30:59.297886+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":"2026-08-15T22:42:48.240412Z","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":"2026-08-12T15:53:32.028523Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2309.04109","last_updated":"2024-10-01T10:30:07Z","snapshot_observed_at":"2026-08-16T15:02:21.597744Z","submitted_at":"2023-09-08T04:10:01Z","title":"From Text to Mask: Localizing Entities Using the Attention of Text-to-Image Diffusion Models","version":2},"cited_work":{"arxiv_id":"2309.04109","doi":null,"metadata_source":"pith","pith_arxiv_id":"2309.04109","snapshot_observed_at":"2026-08-12T15:53:32.028523Z","title":"From Text to Mask: Localizing Entities Using the Attention of Text-to-Image Diffusion Models","venue":"cs.CV","work_id":"6db47440-5bd3-4a74-a2af-14863c4d90c0","year":2023},"citing_paper":{"arxiv_id":"2411.13836","last_updated":"2024-11-21T04:54:30Z","snapshot_observed_at":"2026-08-14T16:27:47.281160Z","submitted_at":"2024-11-21T04:54:30Z","title":"CLIPer: Hierarchically Improving Spatial Representation of CLIP for Open-Vocabulary Semantic Segmentation","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-12T15:53:31.718299Z"},"links":{"cited_paper":"/paper/2309.04109","citing_paper":"/paper/2411.13836"},"observation_digest":"sha256:793c3ed99f9e2626b4c46ef93ef80cdeaa3a4003394726f66fbfd71a281b4d27","observation_id":"5268430a-a04e-4686-bde8-0acc42f79d99","resolution":{"observed_at":"2026-08-12T15:53:32.041705Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.04109","last_updated":"2024-10-01T10:30:07Z","snapshot_observed_at":"2026-08-16T15:02:21.597744Z","submitted_at":"2023-09-08T04:10:01Z","title":"From Text to Mask: Localizing Entities Using the Attention of Text-to-Image Diffusion Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.04109","snapshot_observed_at":"2026-08-15T22:42:48.240412Z","title":"From text to mask: Localizing entities using the attention of text-to-image diffusion models.arXiv preprint arXiv:2309.04109, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.06668","last_updated":"2026-06-26T08:45:47Z","snapshot_observed_at":"2026-08-15T22:34:19.368814Z","submitted_at":"2025-05-10T14:58:44Z","title":"StableMotion: One-Step Motion Estimation with Diffusion Prior","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-15T22:42:48.240412Z"},"links":{"cited_paper":"/paper/2309.04109","citing_paper":"/paper/2505.06668"},"observation_digest":"sha256:e0e50f41ce936c4edf649d3bdbe87efefa93ea35c84659f2562138932919700a","observation_id":"5480e564-64dd-4fc7-b8cb-c561a7697186","resolution":{"observed_at":"2026-08-15T22:42:48.240412Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2309.04109/citation-record","integrity":"/paper/2309.04109/integrity","json":"/paper/2309.04109/citation-record.json","paper":"/paper/2309.04109"},"outbound":[],"paper":{"arxiv_id":"2309.04109","last_updated":"2024-10-01T10:30:07Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-16T15:02:21.597744Z","submitted_at":"2023-09-08T04:10:01Z","title":"From Text to Mask: Localizing Entities Using the Attention of Text-to-Image 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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2309.04109."}