{"as_of":"2026-08-17T17:25:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:86ef0e8454006058aa0aea2acb5ce2b05665ca24dae5e01fb18399df8668f238","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":"2026-08-17T06:30:58.91139+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":"2026-08-11T22:51:11.822595Z","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":"2026-08-10T20:56:40.179251Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2403.07860","last_updated":"2024-03-12T17:50:11Z","snapshot_observed_at":"2026-08-16T14:10:28.721369Z","submitted_at":"2024-03-12T17:50:11Z","title":"Bridging Different Language Models and Generative Vision Models for Text-to-Image Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.07860","snapshot_observed_at":"2026-08-11T22:51:11.822595Z","title":"Bridging different language models and generative vision models for text-to-image generation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.03085","last_updated":"2024-12-04T07:26:44Z","snapshot_observed_at":"2026-08-16T03:54:00.453682Z","submitted_at":"2024-12-04T07:26:44Z","title":"Mimir: Improving Video Diffusion Models for Precise Text Understanding","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-11T22:51:11.822595Z"},"links":{"cited_paper":"/paper/2403.07860","citing_paper":"/paper/2412.03085"},"observation_digest":"sha256:e4d651d4fd19f9777c769505f38e831c9f737030a013c5ffbd5d723b9c7c39c3","observation_id":"560ddeec-0fa3-42e1-8d32-b12b9fe9caf4","resolution":{"observed_at":"2026-08-11T22:51:11.822595Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.07860","last_updated":"2024-03-12T17:50:11Z","snapshot_observed_at":"2026-08-16T14:10:28.721369Z","submitted_at":"2024-03-12T17:50:11Z","title":"Bridging Different Language Models and Generative Vision Models for Text-to-Image Generation","version":1},"cited_work":{"arxiv_id":"2403.07860","doi":null,"metadata_source":"pith","pith_arxiv_id":"2403.07860","snapshot_observed_at":"2026-08-10T20:56:40.179251Z","title":"Bridging Different Language Models and Generative Vision Models for Text-to-Image Generation","venue":"cs.CV","work_id":"e181c78e-0747-4d99-ac8a-52a4f65acf11","year":2024},"citing_paper":{"arxiv_id":"2501.06751","last_updated":"2025-03-02T09:10:13Z","snapshot_observed_at":"2026-08-15T22:44:21.878854Z","submitted_at":"2025-01-12T08:36:38Z","title":"Padding Tone: A Mechanistic Analysis of Padding Tokens in T2I Models","version":2},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-10T20:56:39.855387Z"},"links":{"cited_paper":"/paper/2403.07860","citing_paper":"/paper/2501.06751"},"observation_digest":"sha256:dd0b0410c6f44ffdc7f88f0e14c00f64d8424124f2ffe1b2729d5179739019d1","observation_id":"bcdaec2c-5ff8-4e6a-bd0d-4a0a6c6436d3","resolution":{"observed_at":"2026-08-10T20:56:40.193232Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2403.07860/citation-record","integrity":"/paper/2403.07860/integrity","json":"/paper/2403.07860/citation-record.json","paper":"/paper/2403.07860"},"outbound":[],"paper":{"arxiv_id":"2403.07860","last_updated":"2024-03-12T17:50:11Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-16T14:10:28.721369Z","submitted_at":"2024-03-12T17:50:11Z","title":"Bridging Different Language Models and Generative Vision Models for Text-to-Image Generation"},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2403.07860."}