{"as_of":"2026-08-07T16:39:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2ad1b504d2792ebea9a25b8505457ce4371e39ee26370a926a316aff26760eeb","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":"2026-08-07T06:34:17.273281+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":"2026-08-07T13:33:23.782720Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-19T03:21:08.462430Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2405.08246","last_updated":"2024-05-14T00:22:06Z","snapshot_observed_at":"2026-07-06T18:13:55.543513Z","submitted_at":"2024-05-14T00:22:06Z","title":"Compositional Text-to-Image Generation with Dense Blob Representations","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.08246","snapshot_observed_at":"2026-08-07T13:33:23.782720Z","title":"movie scene with a meerkat, a bunny, a fox, and a frog dancing hula in Hawaii","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.21488","last_updated":"2025-05-27T17:54:24Z","snapshot_observed_at":"2026-08-07T13:24:37.065210Z","submitted_at":"2025-05-27T17:54:24Z","title":"Be Decisive: Noise-Induced Layouts for Multi-Subject Generation","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T13:33:23.782720Z"},"links":{"cited_paper":"/paper/2405.08246","citing_paper":"/paper/2505.21488"},"observation_digest":"sha256:f3a9c54c199240722a0f50e512f20466a56963169e536d1c672e78ccc91091dc","observation_id":"633d58c8-eab2-4d84-be9f-eefb59be8001","resolution":{"observed_at":"2026-08-07T13:33:23.782720Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.08246","last_updated":"2024-05-14T00:22:06Z","snapshot_observed_at":"2026-07-06T18:13:55.543513Z","submitted_at":"2024-05-14T00:22:06Z","title":"Compositional Text-to-Image Generation with Dense Blob Representations","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.08246","snapshot_observed_at":"2026-08-06T19:32:43.604776Z","title":"Compositional text-to-image generation with dense blob representations","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.05259","last_updated":"2025-07-07T17:59:56Z","snapshot_observed_at":"2026-08-06T19:26:21.392797Z","submitted_at":"2025-07-07T17:59:56Z","title":"Beyond Simple Edits: X-Planner for Complex Instruction-Based Image Editing","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T19:32:43.604776Z"},"links":{"cited_paper":"/paper/2405.08246","citing_paper":"/paper/2507.05259"},"observation_digest":"sha256:bc52dbb41bfff9cc6cde5454d4c9c217dbf3f6ceba5cbd800274c1f5a4080a82","observation_id":"cfe16a15-78d0-45ac-ac80-c2025c25e2ed","resolution":{"observed_at":"2026-08-06T19:32:43.604776Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.08246","last_updated":"2024-05-14T00:22:06Z","snapshot_observed_at":"2026-07-06T18:13:55.543513Z","submitted_at":"2024-05-14T00:22:06Z","title":"Compositional Text-to-Image Generation with Dense Blob Representations","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.08246","snapshot_observed_at":"2026-08-06T13:58:05.130972Z","title":"Compositional text-to-image generation with dense blob representations","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.19939","last_updated":"2025-07-26T12:57:02Z","snapshot_observed_at":"2026-08-06T19:10:47.776898Z","submitted_at":"2025-07-26T12:57:02Z","title":"LLMControl: Grounded Control of Text-to-Image Diffusion-based Synthesis with Multimodal LLMs","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-06T13:58:05.130972Z"},"links":{"cited_paper":"/paper/2405.08246","citing_paper":"/paper/2507.19939"},"observation_digest":"sha256:0cb74229aa8e317fb55aea9c4e9b0202c6e05d54ce7798855fc9bd1d5d236616","observation_id":"40174456-e7e8-4dc2-aaae-aec564f43fd0","resolution":{"observed_at":"2026-08-06T13:58:05.130972Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.08246","last_updated":"2024-05-14T00:22:06Z","snapshot_observed_at":"2026-07-06T18:13:55.543513Z","submitted_at":"2024-05-14T00:22:06Z","title":"Compositional Text-to-Image Generation with Dense Blob Representations","version":1},"cited_work":{"arxiv_id":"2405.08246","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2405.08246","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2405.08246 (2024)","venue":null,"work_id":"dd39756d-9b13-4430-9b9b-b1b8aff58937","year":2024},"citing_paper":{"arxiv_id":"2605.15181","last_updated":"2026-05-14T17:58:19Z","snapshot_observed_at":"2026-07-06T23:26:32.979566Z","submitted_at":"2026-05-14T17:58:19Z","title":"From Plans to Pixels: Learning to Plan and Orchestrate for Open-Ended Image Editing","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-05-15T03:20:26.350336Z"},"links":{"cited_paper":"/paper/2405.08246","citing_paper":"/paper/2605.15181"},"observation_digest":"sha256:c7d8862b89f9955eb9c97009d82b04340958fa68dd09f04c2b818708f8075d48","observation_id":"f887800e-1fe3-45ae-a6da-714969f3ce9d","resolution":{"observed_at":"2026-05-15T03:24:56.130598Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2405.08246/citation-record","integrity":"/paper/2405.08246/integrity","json":"/paper/2405.08246/citation-record.json","paper":"/paper/2405.08246"},"outbound":[],"paper":{"arxiv_id":"2405.08246","last_updated":"2024-05-14T00:22:06Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T18:13:55.543513Z","submitted_at":"2024-05-14T00:22:06Z","title":"Compositional Text-to-Image Generation with Dense Blob Representations"},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2405.08246."}