{"as_of":"2026-08-13T16:45:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d3199b726f40aec6165f99fef8b900c5309f1b426b5736c21e9ccad77ebfb0b0","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":"2026-08-13T06:32:02.005865+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":"2026-08-07T13:21:54.970330Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-06T13:14:38.023477Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2404.09313","last_updated":"2024-05-20T05:50:36Z","snapshot_observed_at":"2026-08-13T00:30:26.548489Z","submitted_at":"2024-04-14T18:00:05Z","title":"Text-to-Song: Towards Controllable Music Generation Incorporating Vocals and Accompaniment","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.09313","snapshot_observed_at":"2026-08-07T13:21:54.970330Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.22053","last_updated":"2025-08-05T07:47:10Z","snapshot_observed_at":"2026-08-10T06:47:29.527434Z","submitted_at":"2025-05-28T07:23:53Z","title":"AudioGenie: A Training-Free Multi-Agent Framework for Diverse Multimodality-to-Multiaudio Generation","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:54.970330Z"},"links":{"cited_paper":"/paper/2404.09313","citing_paper":"/paper/2505.22053"},"observation_digest":"sha256:ea98a9dfce899d931fcd6d80b1994e383770664cb470664ba5bbec974998a2d9","observation_id":"29723086-15d4-47f6-a5e0-d48190012ec4","resolution":{"observed_at":"2026-08-07T13:21:54.970330Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.09313","last_updated":"2024-05-20T05:50:36Z","snapshot_observed_at":"2026-08-13T00:30:26.548489Z","submitted_at":"2024-04-14T18:00:05Z","title":"Text-to-Song: Towards Controllable Music Generation Incorporating Vocals and Accompaniment","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.09313","snapshot_observed_at":"2026-08-06T16:40:49.005488Z","title":"Text-to-song: Towards controllable music generation incorporating vocals and accompaniment,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.12890","last_updated":"2025-07-24T08:15:02Z","snapshot_observed_at":"2026-08-08T03:25:27.344834Z","submitted_at":"2025-07-17T08:18:55Z","title":"DiffRhythm+: Controllable and Flexible Full-Length Song Generation with Preference Optimization","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T16:40:49.005488Z"},"links":{"cited_paper":"/paper/2404.09313","citing_paper":"/paper/2507.12890"},"observation_digest":"sha256:ac0c2861ccf1ecd8fcdf41f79000a74aa1aec4061f0f19d98377703687e769ec","observation_id":"7e9350cf-ea76-40d2-b2f9-fe64ac461676","resolution":{"observed_at":"2026-08-06T16:40:49.005488Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.09313","last_updated":"2024-05-20T05:50:36Z","snapshot_observed_at":"2026-08-13T00:30:26.548489Z","submitted_at":"2024-04-14T18:00:05Z","title":"Text-to-Song: Towards Controllable Music Generation Incorporating Vocals and Accompaniment","version":3},"cited_work":{"arxiv_id":"2404.09313","doi":null,"metadata_source":"pith","pith_arxiv_id":"2404.09313","snapshot_observed_at":"2026-08-06T13:14:38.023477Z","title":"Text-to-Song: Towards Controllable Music Generation Incorporating Vocals and Accompaniment","venue":"eess.AS","work_id":"eb4e83e6-a69b-4e15-ac8e-92772380b09a","year":2024},"citing_paper":{"arxiv_id":"2507.20880","last_updated":"2025-07-28T14:34:02Z","snapshot_observed_at":"2026-08-06T16:37:02.345788Z","submitted_at":"2025-07-28T14:34:02Z","title":"JAM: A Tiny Flow-based Song Generator with Fine-grained Controllability and Aesthetic Alignment","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-06T13:14:37.514538Z"},"links":{"cited_paper":"/paper/2404.09313","citing_paper":"/paper/2507.20880"},"observation_digest":"sha256:2bd0ab2c8e420160c3bd2adc7d2bcb4b7fefd9097e52f339d90943053b2676dd","observation_id":"d68b5b89-3299-43ec-b5b4-2ce023b466c7","resolution":{"observed_at":"2026-08-06T13:14:38.027610Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2404.09313/citation-record","integrity":"/paper/2404.09313/integrity","json":"/paper/2404.09313/citation-record.json","paper":"/paper/2404.09313"},"outbound":[],"paper":{"arxiv_id":"2404.09313","last_updated":"2024-05-20T05:50:36Z","latest_version":3,"primary_category":"eess.AS","snapshot_observed_at":"2026-08-13T00:30:26.548489Z","submitted_at":"2024-04-14T18:00:05Z","title":"Text-to-Song: Towards Controllable Music Generation Incorporating Vocals and Accompaniment"},"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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2404.09313."}