{"as_of":"2026-08-16T20:25:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0b1917540cc52db39f6415d503da84cb9f24e3345a7016e5fcad89acb6891706","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":"2026-08-15T23:46:02.893977Z","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":"2026-07-01T10:15:45.077800Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2306.00964","last_updated":"2023-06-01T17:55:32Z","snapshot_observed_at":"2026-08-16T16:33:14.217028Z","submitted_at":"2023-06-01T17:55:32Z","title":"Cocktail: Mixing Multi-Modality Controls for Text-Conditional Image Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.00964","snapshot_observed_at":"2026-08-15T23:46:02.893977Z","title":"Cocktail: Mixing multi-modality controls for text-conditional image generation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.05501","last_updated":"2025-05-06T19:35:29Z","snapshot_observed_at":"2026-08-16T12:59:54.201377Z","submitted_at":"2025-05-06T19:35:29Z","title":"Preliminary Explorations with GPT-4o(mni) Native Image Generation","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-15T23:46:02.893977Z"},"links":{"cited_paper":"/paper/2306.00964","citing_paper":"/paper/2505.05501"},"observation_digest":"sha256:ee58d1b067ab9e69113fe3933377b6398a73b038c37aefd435648b635a5a72bf","observation_id":"c3b79798-25d7-44b9-b6a9-eb4f08b76709","resolution":{"observed_at":"2026-08-15T23:46:02.893977Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.00964","last_updated":"2023-06-01T17:55:32Z","snapshot_observed_at":"2026-08-16T16:33:14.217028Z","submitted_at":"2023-06-01T17:55:32Z","title":"Cocktail: Mixing Multi-Modality Controls for Text-Conditional Image Generation","version":1},"cited_work":{"arxiv_id":"2306.00964","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2306.00964","snapshot_observed_at":"2026-07-01T10:15:45.077800Z","title":"Cocktail: Mixing multi-modality controls for text-conditional image generation","venue":null,"work_id":"81e10516-fc43-4ae5-a7cc-b3fa75fbcd6c","year":2023},"citing_paper":{"arxiv_id":"2509.19454","last_updated":"2026-04-03T06:49:01Z","snapshot_observed_at":"2026-08-11T00:17:48.700247Z","submitted_at":"2025-09-23T18:11:53Z","title":"ROPA: Synthetic Robot Pose Generation for RGB-D Bimanual Data Augmentation","version":2},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-05-18T14:10:44.161455Z"},"links":{"cited_paper":"/paper/2306.00964","citing_paper":"/paper/2509.19454"},"observation_digest":"sha256:405c5e1def82f40d91d44a23f96f2039393b4f73e6644923c941b5cd3cc116c8","observation_id":"f599f7bd-e5ca-4d20-9839-167fea0466d9","resolution":{"observed_at":"2026-05-18T14:11:27.392171Z","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"}},{"citation":{"cited_paper":{"arxiv_id":"2306.00964","last_updated":"2023-06-01T17:55:32Z","snapshot_observed_at":"2026-08-16T16:33:14.217028Z","submitted_at":"2023-06-01T17:55:32Z","title":"Cocktail: Mixing Multi-Modality Controls for Text-Conditional Image Generation","version":1},"cited_work":{"arxiv_id":"2306.00964","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2306.00964","snapshot_observed_at":"2026-07-01T10:15:45.077800Z","title":"Cocktail: Mixing multi-modality controls for text-conditional image generation","venue":null,"work_id":"81e10516-fc43-4ae5-a7cc-b3fa75fbcd6c","year":2023},"citing_paper":{"arxiv_id":"2606.31924","last_updated":"2026-06-30T16:33:03Z","snapshot_observed_at":"2026-08-01T22:17:51.863711Z","submitted_at":"2026-06-30T16:33:03Z","title":"InstanceControl: Controllable Complex Image Generation without Instance Labeling","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-07-01T05:37:41.030752Z"},"links":{"cited_paper":"/paper/2306.00964","citing_paper":"/paper/2606.31924"},"observation_digest":"sha256:544c16d238318879b46c935f45d622f6d57bb1a8f87fe4bbd1022df9c4285f86","observation_id":"5029b1d2-a617-446f-a5dc-7129e955d396","resolution":{"observed_at":"2026-07-01T10:15:45.079446Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"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/2306.00964/citation-record","integrity":"/paper/2306.00964/integrity","json":"/paper/2306.00964/citation-record.json","paper":"/paper/2306.00964"},"outbound":[],"paper":{"arxiv_id":"2306.00964","last_updated":"2023-06-01T17:55:32Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-16T16:33:14.217028Z","submitted_at":"2023-06-01T17:55:32Z","title":"Cocktail: Mixing Multi-Modality Controls for Text-Conditional Image Generation"},"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:2306.00964."}