{"as_of":"2026-08-10T04:02:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:42d2c964ad4fa5ed42ef3d43136a9cc5b0ee009d8207f0b0f6d9c075b49f2432","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":"2026-08-09T06:31:02.800959+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":"2026-08-06T20:01:50.856287Z","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":"2026-05-15T20:36:35.322493Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2310.06311","last_updated":"2023-10-10T05:09:05Z","snapshot_observed_at":"2026-08-09T20:27:52.493255Z","submitted_at":"2023-10-10T05:09:05Z","title":"Improving Compositional Text-to-image Generation with Large Vision-Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.06311","snapshot_observed_at":"2026-08-06T20:01:50.856287Z","title":"Improving compositional text-to-image generation with large vision-language models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.04151","last_updated":"2025-07-05T20:16:32Z","snapshot_observed_at":"2026-08-10T03:31:56.202288Z","submitted_at":"2025-07-05T20:16:32Z","title":"Unlocking Compositional Control: Self-Supervision for LVLM-Based Image Generation","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T20:01:50.856287Z"},"links":{"cited_paper":"/paper/2310.06311","citing_paper":"/paper/2507.04151"},"observation_digest":"sha256:7825ad4a7a3b87912539bd4b4279279f16d2e90183ed79e5587c032378df4f71","observation_id":"d773c6ae-7ce0-4acc-90e3-fc520c889a19","resolution":{"observed_at":"2026-08-06T20:01:50.856287Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.06311","last_updated":"2023-10-10T05:09:05Z","snapshot_observed_at":"2026-08-09T20:27:52.493255Z","submitted_at":"2023-10-10T05:09:05Z","title":"Improving Compositional Text-to-image Generation with Large Vision-Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.06311","snapshot_observed_at":"2026-08-06T19:18:49.998240Z","title":"Improving compositional text-to- image generation with large vision-language mod- els,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.06033","last_updated":"2025-07-08T14:35:02Z","snapshot_observed_at":"2026-08-08T00:52:55.228538Z","submitted_at":"2025-07-08T14:35:02Z","title":"TextPixs: Glyph-Conditioned Diffusion with Character-Aware Attention and OCR-Guided Supervision","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T19:18:49.998240Z"},"links":{"cited_paper":"/paper/2310.06311","citing_paper":"/paper/2507.06033"},"observation_digest":"sha256:7699df44e04480b7d9bce65624ff255b050483bc507fa6bf9d5e4c556116e057","observation_id":"c8a68eda-ea4f-4bc6-a8ce-56170b0ecd0c","resolution":{"observed_at":"2026-08-06T19:18:49.998240Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.06311","last_updated":"2023-10-10T05:09:05Z","snapshot_observed_at":"2026-08-09T20:27:52.493255Z","submitted_at":"2023-10-10T05:09:05Z","title":"Improving Compositional Text-to-image Generation with Large Vision-Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.06311","snapshot_observed_at":"2026-08-03T15:25:47.262209Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2512.20666","last_updated":"2026-07-22T05:36:55Z","snapshot_observed_at":"2026-08-03T15:25:42.559505Z","submitted_at":"2025-12-19T06:36:15Z","title":"Dominant vs. Dominated: Concept-Level Generative Collapse in Diffusion Models","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-03T15:25:47.262209Z"},"links":{"cited_paper":"/paper/2310.06311","citing_paper":"/paper/2512.20666"},"observation_digest":"sha256:20be2218dabdcfa797cc71ef5532d58519c37a8da6e921399986a3a4acaa7600","observation_id":"3a110bba-da6a-4fa4-8485-8eefd35e848a","resolution":{"observed_at":"2026-08-03T15:25:47.262209Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.06311","last_updated":"2023-10-10T05:09:05Z","snapshot_observed_at":"2026-08-09T20:27:52.493255Z","submitted_at":"2023-10-10T05:09:05Z","title":"Improving Compositional Text-to-image Generation with Large Vision-Language Models","version":1},"cited_work":{"arxiv_id":"2310.06311","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2310.06311","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Improving compositional text-to- image generation with large vision-language models","venue":null,"work_id":"ea47852c-a5bd-436d-9933-46305c524d90","year":2023},"citing_paper":{"arxiv_id":"2602.19974","last_updated":"2026-05-07T22:11:37Z","snapshot_observed_at":"2026-07-06T22:46:45.213871Z","submitted_at":"2026-02-23T15:39:53Z","title":"RL-RIG: A Generative Spatial Reasoner via Intrinsic Reflection","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-05-15T20:33:09.627731Z"},"links":{"cited_paper":"/paper/2310.06311","citing_paper":"/paper/2602.19974"},"observation_digest":"sha256:708e49b515a115c481793a20600e31cc6f2337b02e3602b29eda1e91404938a0","observation_id":"a7f3ac62-b9a3-41b9-9b02-8a2bac4b11b7","resolution":{"observed_at":"2026-05-15T20:36:35.324071Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2310.06311/citation-record","integrity":"/paper/2310.06311/integrity","json":"/paper/2310.06311/citation-record.json","paper":"/paper/2310.06311"},"outbound":[],"paper":{"arxiv_id":"2310.06311","last_updated":"2023-10-10T05:09:05Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-09T20:27:52.493255Z","submitted_at":"2023-10-10T05:09:05Z","title":"Improving Compositional Text-to-image Generation with Large Vision-Language 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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2310.06311."}