{"as_of":"2026-08-10T08:15:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:be5e88ad1a14f76a1a43f4c62661cf1197e668aa096f13a7ac8f6045b59ad334","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":"2026-08-10T06:31:04.303077+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":"2026-08-09T20:50:17.284979Z","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":"2026-07-04T11:59:50.959114Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2305.12708","last_updated":"2024-04-21T07:17:14Z","snapshot_observed_at":"2026-08-04T00:42:56.058282Z","submitted_at":"2023-05-22T04:37:41Z","title":"ViT-TTS: Visual Text-to-Speech with Scalable Diffusion Transformer","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.12708","snapshot_observed_at":"2026-08-09T20:50:17.284979Z","title":"VIT-TTS: visual text-to-speech with scalable diffusion transformer,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.19258","last_updated":"2025-08-16T21:44:41Z","snapshot_observed_at":"2026-08-09T20:44:21.325715Z","submitted_at":"2025-01-31T16:16:52Z","title":"VisualSpeech: Enhancing Prosody Modeling in TTS Using Video","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-09T20:50:17.284979Z"},"links":{"cited_paper":"/paper/2305.12708","citing_paper":"/paper/2501.19258"},"observation_digest":"sha256:7ca18b7c5ca6327e6f75360235ac05438a03df25f3c571da76c2f29c86c42aca","observation_id":"94ffe127-0a7d-4bff-af9a-4a3d08338dee","resolution":{"observed_at":"2026-08-09T20:50:17.284979Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.12708","last_updated":"2024-04-21T07:17:14Z","snapshot_observed_at":"2026-08-04T00:42:56.058282Z","submitted_at":"2023-05-22T04:37:41Z","title":"ViT-TTS: Visual Text-to-Speech with Scalable Diffusion Transformer","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.12708","snapshot_observed_at":"2026-08-05T17:42:57.228657Z","title":"Vit-tts: Visual text-to-speech with scalable diffusion transformer","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:57.228657Z"},"links":{"cited_paper":"/paper/2305.12708","citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:2e2114214289b605255f97e05b6a0b09522e01998933aa4827661d3bbaade331","observation_id":"3b5b277b-5ef8-4ed6-9797-1bd7b85d147d","resolution":{"observed_at":"2026-08-05T17:42:57.228657Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.12708","last_updated":"2024-04-21T07:17:14Z","snapshot_observed_at":"2026-08-04T00:42:56.058282Z","submitted_at":"2023-05-22T04:37:41Z","title":"ViT-TTS: Visual Text-to-Speech with Scalable Diffusion Transformer","version":2},"cited_work":{"arxiv_id":"2305.12708","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2305.12708","snapshot_observed_at":"2026-07-04T11:59:50.959114Z","title":"Audioldm 2: Learning holistic audio generation with self-supervised pretraining","venue":null,"work_id":"5a9a5ca7-6fba-4396-b5fb-ba69c9191a7c","year":null},"citing_paper":{"arxiv_id":"2606.23080","last_updated":"2026-06-22T09:30:02Z","snapshot_observed_at":"2026-07-06T23:57:53.101659Z","submitted_at":"2026-06-22T09:30:02Z","title":"AudioCALM: Continuous Autoregressive Language Modeling for Universal Audio Generation","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-06-26T07:24:01.244733Z"},"links":{"cited_paper":"/paper/2305.12708","citing_paper":"/paper/2606.23080"},"observation_digest":"sha256:5d093d69b41bc1fe1f16932d5b1c14c4d9eaf277bf6565977a815240048df50b","observation_id":"fa6337f1-9d05-4894-ade0-8e5f4ed94700","resolution":{"observed_at":"2026-07-04T11:59:50.961104Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2305.12708/citation-record","integrity":"/paper/2305.12708/integrity","json":"/paper/2305.12708/citation-record.json","paper":"/paper/2305.12708"},"outbound":[],"paper":{"arxiv_id":"2305.12708","last_updated":"2024-04-21T07:17:14Z","latest_version":2,"primary_category":"eess.AS","snapshot_observed_at":"2026-08-04T00:42:56.058282Z","submitted_at":"2023-05-22T04:37:41Z","title":"ViT-TTS: Visual Text-to-Speech with Scalable Diffusion Transformer"},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2305.12708."}