{"as_of":"2026-08-09T09:07:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0ffdd7768bc8f634ef068ec6e33ed4c01945f4642829ca29c19112e526966366","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":3,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":3,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T10:29:04.652919Z","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":"2026-05-12T17:34:27.167581Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2502.20172","last_updated":"2025-02-27T15:08:39Z","snapshot_observed_at":"2026-08-07T17:42:37.911885Z","submitted_at":"2025-02-27T15:08:39Z","title":"Multimodal Representation Alignment for Image Generation: Text-Image Interleaved Control Is Easier Than You Think","version":1},"cited_work":{"arxiv_id":"2502.20172","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.20172","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Multimodal representation alignment for image generation: Text-image interleaved control is easier than you think","venue":null,"work_id":"0e2c2486-ebef-41d7-987d-d39f3f386fb2","year":2025},"citing_paper":{"arxiv_id":"2506.03147","last_updated":"2025-06-18T18:00:05Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-03T17:59:33Z","title":"UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation","version":4},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-12T17:34:26.951644Z"},"links":{"cited_paper":"/paper/2502.20172","citing_paper":"/paper/2506.03147"},"observation_digest":"sha256:eeea05e5b98b8970aef1e2a5b370cc5a12bfae753bd6cff0062fefd0b67ed810","observation_id":"39945a39-ac64-4c70-9272-0ff6a2576505","resolution":{"observed_at":"2026-05-12T17:34:27.171277Z","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"}},{"citation":{"cited_paper":{"arxiv_id":"2502.20172","last_updated":"2025-02-27T15:08:39Z","snapshot_observed_at":"2026-08-07T17:42:37.911885Z","submitted_at":"2025-02-27T15:08:39Z","title":"Multimodal Representation Alignment for Image Generation: Text-Image Interleaved Control Is Easier Than You Think","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.20172","snapshot_observed_at":"2026-08-07T10:29:04.652919Z","title":"Multimodal representation alignment for image generation: Text-image interleaved control is easier than you think","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.05083","last_updated":"2025-06-06T13:18:12Z","snapshot_observed_at":"2026-08-08T13:17:32.037310Z","submitted_at":"2025-06-05T14:30:39Z","title":"SeedEdit 3.0: Fast and High-Quality Generative Image Editing","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T10:29:04.652919Z"},"links":{"cited_paper":"/paper/2502.20172","citing_paper":"/paper/2506.05083"},"observation_digest":"sha256:f5a334fc388f678786cce86434d33b93349c0ca66b143071ebb9f5a16a35d69f","observation_id":"1393c8f4-569d-4aa9-87a7-a465c1b22fa5","resolution":{"observed_at":"2026-08-07T10:29:04.652919Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.20172","last_updated":"2025-02-27T15:08:39Z","snapshot_observed_at":"2026-08-07T17:42:37.911885Z","submitted_at":"2025-02-27T15:08:39Z","title":"Multimodal Representation Alignment for Image Generation: Text-Image Interleaved Control Is Easier Than You Think","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.20172","snapshot_observed_at":"2026-07-13T22:15:10.917455Z","title":"arXiv preprint arXiv:2502.20172 (2025)","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.19036","last_updated":"2026-07-01T03:31:54Z","snapshot_observed_at":"2026-08-07T06:18:25.485509Z","submitted_at":"2026-03-19T15:33:11Z","title":"FUMO: Prior-Modulated Diffusion for Single Image Reflection Removal","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-07-13T22:15:10.917455Z"},"links":{"cited_paper":"/paper/2502.20172","citing_paper":"/paper/2603.19036"},"observation_digest":"sha256:cfc33e9dd15236ac0b80a55e7bfbbf318582ab0212a98103ef4167fa1486f3c3","observation_id":"8f474622-01e9-4d9d-98a5-2465c968fc28","resolution":{"observed_at":"2026-07-13T22:15:10.917455Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2502.20172/citation-record","integrity":"/paper/2502.20172/integrity","json":"/paper/2502.20172/citation-record.json","paper":"/paper/2502.20172"},"outbound":[],"paper":{"arxiv_id":"2502.20172","last_updated":"2025-02-27T15:08:39Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-07T17:42:37.911885Z","submitted_at":"2025-02-27T15:08:39Z","title":"Multimodal Representation Alignment for Image Generation: Text-Image Interleaved Control Is Easier Than You Think"},"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 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2502.20172."}