{"as_of":"2026-08-16T23:03:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:42071d3b73c79c8fa12571686b578757a9680ae47662b5b2dbc72a306e738b10","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":"2026-08-16T06:30:59.297886+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":"2026-08-16T00:00:51.481975Z","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":"2026-05-18T05:15:54.318059Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2409.19967","last_updated":"2024-09-30T05:36:24Z","snapshot_observed_at":"2026-08-16T13:14:16.700372Z","submitted_at":"2024-09-30T05:36:24Z","title":"Magnet: We Never Know How Text-to-Image Diffusion Models Work, Until We Learn How Vision-Language Models Function","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.19967","snapshot_observed_at":"2026-08-11T17:18:42.960273Z","title":"in origami style","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.09169","last_updated":"2024-12-12T10:59:44Z","snapshot_observed_at":"2026-08-16T17:44:20.243935Z","submitted_at":"2024-12-12T10:59:44Z","title":"DECOR:Decomposition and Projection of Text Embeddings for Text-to-Image Customization","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-11T17:18:42.960273Z"},"links":{"cited_paper":"/paper/2409.19967","citing_paper":"/paper/2412.09169"},"observation_digest":"sha256:e5aea46ccee6f539669c38f8358f8602f61ff3b7e214634a4cb65cc3be0ba47f","observation_id":"a656a0b0-e6e6-4f57-abce-c1c705dc8443","resolution":{"observed_at":"2026-08-11T17:18:42.960273Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.19967","last_updated":"2024-09-30T05:36:24Z","snapshot_observed_at":"2026-08-16T13:14:16.700372Z","submitted_at":"2024-09-30T05:36:24Z","title":"Magnet: We Never Know How Text-to-Image Diffusion Models Work, Until We Learn How Vision-Language Models Function","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.19967","snapshot_observed_at":"2026-08-16T00:00:51.481975Z","title":"Magnet: We never know how text-to-image diffusion models work, until we learn how vision-language models function,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.03203","last_updated":"2025-05-06T05:38:13Z","snapshot_observed_at":"2026-08-15T23:54:58.597647Z","submitted_at":"2025-05-06T05:38:13Z","title":"PiCo: Enhancing Text-Image Alignment with Improved Noise Selection and Precise Mask Control in Diffusion Models","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-16T00:00:51.481975Z"},"links":{"cited_paper":"/paper/2409.19967","citing_paper":"/paper/2505.03203"},"observation_digest":"sha256:d6c6e2bf14b344c114f167ba1e2cceb2d6bbafccf661bf001f595bbf97071670","observation_id":"7649b0b8-6060-4a8a-9e0e-1627ee22ff10","resolution":{"observed_at":"2026-08-16T00:00:51.481975Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.19967","last_updated":"2024-09-30T05:36:24Z","snapshot_observed_at":"2026-08-16T13:14:16.700372Z","submitted_at":"2024-09-30T05:36:24Z","title":"Magnet: We Never Know How Text-to-Image Diffusion Models Work, Until We Learn How Vision-Language Models Function","version":1},"cited_work":{"arxiv_id":"2409.19967","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2409.19967","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Magnet: We never know how text-to-image diffusion models work, until we learn how vision- language models function","venue":null,"work_id":"6ad1796b-d7b5-4dff-ab2b-7a2ae91522c2","year":2024},"citing_paper":{"arxiv_id":"2510.20206","last_updated":"2026-05-14T08:53:49Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-10-23T04:45:09Z","title":"RAPO++: Cross-Stage Prompt Optimization for Text-to-Video Generation via Data Alignment and Test-Time Scaling","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-05-18T05:13:42.934115Z"},"links":{"cited_paper":"/paper/2409.19967","citing_paper":"/paper/2510.20206"},"observation_digest":"sha256:374b84e3b0a670560f826a78cf0bf2f8b3f83b270dd820685e2173e73d8420ad","observation_id":"fcc4e5d7-f047-4403-85fa-5ea420373245","resolution":{"observed_at":"2026-05-18T05:15:54.320879Z","resolver_source":"arxiv_id","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"}}],"links":{"evidence":"/evidence","html":"/paper/2409.19967/citation-record","integrity":"/paper/2409.19967/integrity","json":"/paper/2409.19967/citation-record.json","paper":"/paper/2409.19967"},"outbound":[],"paper":{"arxiv_id":"2409.19967","last_updated":"2024-09-30T05:36:24Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-16T13:14:16.700372Z","submitted_at":"2024-09-30T05:36:24Z","title":"Magnet: We Never Know How Text-to-Image Diffusion Models Work, Until We Learn How Vision-Language Models Function"},"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 3 inbound Pith citation observations for arXiv:2409.19967."}