{"as_of":"2026-08-08T18:49:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:621b8c10797184a35fa62676a53d8624291b76a79a3e3167155943382deb90c0","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":"2026-08-08T06:32:00.761636+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":"2026-08-06T15:46:11.210581Z","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":"2026-05-14T21:58:03.356763Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2406.09162","last_updated":"2024-06-13T14:26:43Z","snapshot_observed_at":"2026-07-06T18:30:19.486766Z","submitted_at":"2024-06-13T14:26:43Z","title":"EMMA: Your Text-to-Image Diffusion Model Can Secretly Accept Multi-Modal Prompts","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.09162","snapshot_observed_at":"2026-08-06T15:46:11.210581Z","title":"Emma: Your text-to-image diffusion model can secretly accept multi-modal prompts","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.15037","last_updated":"2025-07-20T16:37:53Z","snapshot_observed_at":"2026-08-06T15:39:55.785393Z","submitted_at":"2025-07-20T16:37:53Z","title":"OmniVTON: Training-Free Universal Virtual Try-On","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T15:46:11.210581Z"},"links":{"cited_paper":"/paper/2406.09162","citing_paper":"/paper/2507.15037"},"observation_digest":"sha256:0e4eed9bdd96c119fb3e1e298ea2c2acb29be0f2d21cd0e1357e1b434992ce2e","observation_id":"29763110-c2d3-4854-9259-58fbe4c70db9","resolution":{"observed_at":"2026-08-06T15:46:11.210581Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.09162","last_updated":"2024-06-13T14:26:43Z","snapshot_observed_at":"2026-07-06T18:30:19.486766Z","submitted_at":"2024-06-13T14:26:43Z","title":"EMMA: Your Text-to-Image Diffusion Model Can Secretly Accept Multi-Modal Prompts","version":1},"cited_work":{"arxiv_id":"2406.09162","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2406.09162","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Emma: Your text-to-image diffusion model can secretly accept multi-modal prompts","venue":null,"work_id":"dfcce9d3-ead8-4172-b238-d755512e4e6d","year":2024},"citing_paper":{"arxiv_id":"2605.10127","last_updated":"2026-05-13T05:54:11Z","snapshot_observed_at":"2026-07-06T23:22:08.560919Z","submitted_at":"2026-05-11T07:40:03Z","title":"Fashion130K: An E-commerce Fashion Dataset for Outfit Generation with Unified Multi-modal Condition","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-12T03:56:43.640874Z"},"links":{"cited_paper":"/paper/2406.09162","citing_paper":"/paper/2605.10127"},"observation_digest":"sha256:68ca4778bd9eaca6254c94ffabdd4ce7c0950f236ddb44e579c7592175973fde","observation_id":"cb0c192d-7e2d-44c8-ab64-02c526388f9e","resolution":{"observed_at":"2026-05-12T06:51:27.864449Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.09162","last_updated":"2024-06-13T14:26:43Z","snapshot_observed_at":"2026-07-06T18:30:19.486766Z","submitted_at":"2024-06-13T14:26:43Z","title":"EMMA: Your Text-to-Image Diffusion Model Can Secretly Accept Multi-Modal Prompts","version":1},"cited_work":{"arxiv_id":"2406.09162","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2406.09162","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Emma: Your text-to-image diffusion model can secretly accept multi-modal prompts","venue":null,"work_id":"dfcce9d3-ead8-4172-b238-d755512e4e6d","year":2024},"citing_paper":{"arxiv_id":"2605.10127","last_updated":"2026-05-13T05:54:11Z","snapshot_observed_at":"2026-07-06T23:22:08.560919Z","submitted_at":"2026-05-11T07:40:03Z","title":"Fashion130K: An E-commerce Fashion Dataset for Outfit Generation with Unified Multi-modal Condition","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-14T21:56:10.499014Z"},"links":{"cited_paper":"/paper/2406.09162","citing_paper":"/paper/2605.10127"},"observation_digest":"sha256:cf6a70359a380c448d73d0726b234c1ea3771c1d0e8af5e48869a74c2e49ea53","observation_id":"da1331c7-faeb-4974-bba4-a959ca14ec52","resolution":{"observed_at":"2026-05-14T21:58:03.360545Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2406.09162/citation-record","integrity":"/paper/2406.09162/integrity","json":"/paper/2406.09162/citation-record.json","paper":"/paper/2406.09162"},"outbound":[],"paper":{"arxiv_id":"2406.09162","last_updated":"2024-06-13T14:26:43Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T18:30:19.486766Z","submitted_at":"2024-06-13T14:26:43Z","title":"EMMA: Your Text-to-Image Diffusion Model Can Secretly Accept Multi-Modal Prompts"},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2406.09162."}