{"as_of":"2026-08-11T03:20:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:80e4645c5a2a5c3027d229b375f17bb0854042413e1db46bad91b67149a0c508","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":"2026-08-10T04:36:38.317034Z","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":"2026-05-18T18:31:44.709866Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2411.05141","last_updated":"2025-06-06T05:50:30Z","snapshot_observed_at":"2026-08-06T23:57:10.370112Z","submitted_at":"2024-11-07T19:50:28Z","title":"Audiobox TTA-RAG: Improving Zero-Shot and Few-Shot Text-To-Audio with Retrieval-Augmented Generation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.05141","snapshot_observed_at":"2026-08-10T04:36:38.317034Z","title":"Audiobox tta-rag: Improving zero-shot and few-shot text-to-audio with retrieval-augmented generation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.18648","last_updated":"2025-03-21T18:17:47Z","snapshot_observed_at":"2026-08-10T18:54:42.949169Z","submitted_at":"2025-01-29T16:38:57Z","title":"Multimodal Large Language Models for Image, Text, and Speech Data Augmentation: A Survey","version":2},"reference_index":272,"source":"pdf_text","source_observed_at":"2026-08-10T04:36:38.317034Z"},"links":{"cited_paper":"/paper/2411.05141","citing_paper":"/paper/2501.18648"},"observation_digest":"sha256:648ede8588b277f58347d0d3abb742f66c03245c328677b9c0c862e059ff98a3","observation_id":"0095252f-8b07-4fd4-ae63-4540ffcd0b5e","resolution":{"observed_at":"2026-08-10T04:36:38.317034Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.05141","last_updated":"2025-06-06T05:50:30Z","snapshot_observed_at":"2026-08-06T23:57:10.370112Z","submitted_at":"2024-11-07T19:50:28Z","title":"Audiobox TTA-RAG: Improving Zero-Shot and Few-Shot Text-To-Audio with Retrieval-Augmented Generation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.05141","snapshot_observed_at":"2026-08-07T23:35:56.659200Z","title":"Yibin Yan and Weidi Xie","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.08826","last_updated":"2025-06-02T17:15:08Z","snapshot_observed_at":"2026-08-10T06:53:40.258420Z","submitted_at":"2025-02-12T22:33:41Z","title":"Ask in Any Modality: A Comprehensive Survey on Multimodal Retrieval-Augmented Generation","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T23:35:56.659200Z"},"links":{"cited_paper":"/paper/2411.05141","citing_paper":"/paper/2502.08826"},"observation_digest":"sha256:c29079ddcee3f8de4bcdf5ed3d0667535691a30137a5a6acf6d777f5d4f9ff78","observation_id":"8cac02ab-68db-4eae-bbb7-469423258364","resolution":{"observed_at":"2026-08-07T23:35:56.659200Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.05141","last_updated":"2025-06-06T05:50:30Z","snapshot_observed_at":"2026-08-06T23:57:10.370112Z","submitted_at":"2024-11-07T19:50:28Z","title":"Audiobox TTA-RAG: Improving Zero-Shot and Few-Shot Text-To-Audio with Retrieval-Augmented Generation","version":2},"cited_work":{"arxiv_id":"2411.05141","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2411.05141","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Audiobox TTA- RAG: Improving zero-shot and few-shot text-to-audio with retrieval- augmented generation","venue":null,"work_id":"4e113c53-9c3e-4d05-a12b-0d8be0638683","year":2024},"citing_paper":{"arxiv_id":"2509.06027","last_updated":"2026-04-27T10:03:51Z","snapshot_observed_at":"2026-08-10T23:18:57.268702Z","submitted_at":"2025-09-07T12:06:21Z","title":"DreamAudio: Customized Text-to-Audio Generation with Diffusion Models","version":3},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-05-18T18:26:51.583145Z"},"links":{"cited_paper":"/paper/2411.05141","citing_paper":"/paper/2509.06027"},"observation_digest":"sha256:7fff1a64d5131587e9e2640f840bea7734715450003123418e2715464a8a9e07","observation_id":"84c253a3-6161-48a6-9596-a06b6dd60bf5","resolution":{"observed_at":"2026-05-18T18:31:44.712246Z","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/2411.05141/citation-record","integrity":"/paper/2411.05141/integrity","json":"/paper/2411.05141/citation-record.json","paper":"/paper/2411.05141"},"outbound":[],"paper":{"arxiv_id":"2411.05141","last_updated":"2025-06-06T05:50:30Z","latest_version":2,"primary_category":"eess.AS","snapshot_observed_at":"2026-08-06T23:57:10.370112Z","submitted_at":"2024-11-07T19:50:28Z","title":"Audiobox TTA-RAG: Improving Zero-Shot and Few-Shot Text-To-Audio with Retrieval-Augmented 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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2411.05141."}