{"as_of":"2026-08-09T08:14:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:40efb06f61b36f170c0ed82510c573ee12b4797c59437dc47f417b9c456ee07c","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":"2026-08-08T10:23:04.592103Z","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":"2026-05-16T23:28:40.778208Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2305.13050","last_updated":"2023-05-22T14:02:44Z","snapshot_observed_at":"2026-07-06T15:30:42.173342Z","submitted_at":"2023-05-22T14:02:44Z","title":"AudioToken: Adaptation of Text-Conditioned Diffusion Models for Audio-to-Image Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.13050","snapshot_observed_at":"2026-08-08T10:23:04.592103Z","title":"Audiotoken: Adaptation of text- conditioned diffusion models for audio-to-image genera- tion","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.08134","last_updated":"2025-02-12T05:34:48Z","snapshot_observed_at":"2026-08-09T06:44:46.712800Z","submitted_at":"2025-02-12T05:34:48Z","title":"A Survey on Data Curation for Visual Contrastive Learning: Why Crafting Effective Positive and Negative Pairs Matters","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-08T10:23:04.592103Z"},"links":{"cited_paper":"/paper/2305.13050","citing_paper":"/paper/2502.08134"},"observation_digest":"sha256:9d87c7d3673c6488ee9d19c65135ef68df27c5c6d0d18e90e7d0226af2645b8e","observation_id":"c5185103-8fa3-4d97-9762-bd3100ab15c9","resolution":{"observed_at":"2026-08-08T10:23:04.592103Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.13050","last_updated":"2023-05-22T14:02:44Z","snapshot_observed_at":"2026-07-06T15:30:42.173342Z","submitted_at":"2023-05-22T14:02:44Z","title":"AudioToken: Adaptation of Text-Conditioned Diffusion Models for Audio-to-Image Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.13050","snapshot_observed_at":"2026-08-05T05:01:37.123408Z","title":"AudioToken: Adap- tation of Text-Conditioned Diffusion Models for Audio-to-Image Generation.ArXiv, 2305.13050, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.05786","last_updated":"2025-09-06T17:42:22Z","snapshot_observed_at":"2026-08-08T09:14:25.199933Z","submitted_at":"2025-09-06T17:42:22Z","title":"Effectively obtaining acoustic, visual and textual data from videos","version":1},"reference_index":129,"source":"pdf_text","source_observed_at":"2026-08-05T05:01:37.123408Z"},"links":{"cited_paper":"/paper/2305.13050","citing_paper":"/paper/2509.05786"},"observation_digest":"sha256:2835d397c0efa3781db9bff4c2cff76d67ff82df62a17433ef428ce4b90836df","observation_id":"db14552c-0686-4b68-a9bb-c76e7ff55378","resolution":{"observed_at":"2026-08-05T05:01:37.123408Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.13050","last_updated":"2023-05-22T14:02:44Z","snapshot_observed_at":"2026-07-06T15:30:42.173342Z","submitted_at":"2023-05-22T14:02:44Z","title":"AudioToken: Adaptation of Text-Conditioned Diffusion Models for Audio-to-Image Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.13050","snapshot_observed_at":"2026-08-04T21:25:27.400444Z","title":"AudioToken: Adap- tation of Text-Conditioned Diffusion Models for Audio-to-Image Generation.ArXiv, 2305.13050, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.09717","last_updated":"2025-09-09T18:57:10Z","snapshot_observed_at":"2026-08-08T11:56:25.298917Z","submitted_at":"2025-09-09T18:57:10Z","title":"Testing chatbots on the creation of encoders for audio conditioned image generation","version":1},"reference_index":117,"source":"pdf_text","source_observed_at":"2026-08-04T21:25:27.400444Z"},"links":{"cited_paper":"/paper/2305.13050","citing_paper":"/paper/2509.09717"},"observation_digest":"sha256:928e3f011a17d9b4f61b7df902c019ed16895e0873cab2b8d9c99dbb515d15ae","observation_id":"5c19713f-1f68-4fac-8937-94562320036e","resolution":{"observed_at":"2026-08-04T21:25:27.400444Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.13050","last_updated":"2023-05-22T14:02:44Z","snapshot_observed_at":"2026-07-06T15:30:42.173342Z","submitted_at":"2023-05-22T14:02:44Z","title":"AudioToken: Adaptation of Text-Conditioned Diffusion Models for Audio-to-Image Generation","version":1},"cited_work":{"arxiv_id":"2305.13050","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2305.13050","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"AudioToken: Adaptation of text-conditioned diffusion mod- els for audio-to-image generation","venue":null,"work_id":"e152d225-b8d7-4adf-9f87-c2289b4afbb1","year":2023},"citing_paper":{"arxiv_id":"2512.10571","last_updated":"2026-05-02T11:27:08Z","snapshot_observed_at":"2026-07-31T11:34:00.884185Z","submitted_at":"2025-12-11T11:58:53Z","title":"AVI-Edit: Audio-sync Video Instance Editing with Granularity-Aware Mask Refiner","version":4},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-05-16T23:26:21.855485Z"},"links":{"cited_paper":"/paper/2305.13050","citing_paper":"/paper/2512.10571"},"observation_digest":"sha256:2582a723e9214f85654ca1ffb765e34de7c9bd18926fbaf84246c85816764ed8","observation_id":"48a0a4e2-730f-468b-99be-846552dbec2b","resolution":{"observed_at":"2026-05-16T23:28:40.780299Z","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/2305.13050/citation-record","integrity":"/paper/2305.13050/integrity","json":"/paper/2305.13050/citation-record.json","paper":"/paper/2305.13050"},"outbound":[],"paper":{"arxiv_id":"2305.13050","last_updated":"2023-05-22T14:02:44Z","latest_version":1,"primary_category":"cs.SD","snapshot_observed_at":"2026-07-06T15:30:42.173342Z","submitted_at":"2023-05-22T14:02:44Z","title":"AudioToken: Adaptation of Text-Conditioned Diffusion Models for Audio-to-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":"2026-08-09T06:31:02.800959+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 4 inbound Pith citation observations for arXiv:2305.13050."}