{"as_of":"2026-08-07T08:39:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ba7990eba007e01edaefdd7c212c833b1f2a203fd62c5356392e2078b77b8fc9","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":"2026-08-07T06:34:17.273281+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":"2026-08-06T19:21:03.992535Z","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":"2026-05-11T04:50:56.285704Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2406.07162","last_updated":"2024-06-11T11:12:51Z","snapshot_observed_at":"2026-08-06T08:12:49.540745Z","submitted_at":"2024-06-11T11:12:51Z","title":"EmoBox: Multilingual Multi-corpus Speech Emotion Recognition Toolkit and Benchmark","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.07162","snapshot_observed_at":"2026-08-06T19:21:03.992535Z","title":"Emobox: Multilingual multi-corpus speech emotion recognition toolkit and benchmark,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.05911","last_updated":"2025-07-08T11:57:16Z","snapshot_observed_at":"2026-08-07T07:17:41.212038Z","submitted_at":"2025-07-08T11:57:16Z","title":"Differentiable Reward Optimization for LLM based TTS system","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T19:21:03.992535Z"},"links":{"cited_paper":"/paper/2406.07162","citing_paper":"/paper/2507.05911"},"observation_digest":"sha256:bdd967352d7a64ced106f1cd1a2bfc93300c1822a685ee517c327db89d848798","observation_id":"a913a405-6aa8-4709-99b5-ba60796d5be2","resolution":{"observed_at":"2026-08-06T19:21:03.992535Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.07162","last_updated":"2024-06-11T11:12:51Z","snapshot_observed_at":"2026-08-06T08:12:49.540745Z","submitted_at":"2024-06-11T11:12:51Z","title":"EmoBox: Multilingual Multi-corpus Speech Emotion Recognition Toolkit and Benchmark","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.07162","snapshot_observed_at":"2026-08-06T05:17:06.215755Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.02038","last_updated":"2025-08-14T01:47:28Z","snapshot_observed_at":"2026-08-06T05:17:04.279967Z","submitted_at":"2025-08-04T04:08:22Z","title":"Marco-Voice Technical Report","version":4},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T05:17:06.215755Z"},"links":{"cited_paper":"/paper/2406.07162","citing_paper":"/paper/2508.02038"},"observation_digest":"sha256:827412d7a3d91b6b7d7877f1b933e9c9b4ce0b36a9225e61ed03a643b3a5ba3f","observation_id":"5128c4bc-6773-4381-bdbf-52782b84470e","resolution":{"observed_at":"2026-08-06T05:17:06.215755Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.07162","last_updated":"2024-06-11T11:12:51Z","snapshot_observed_at":"2026-08-06T08:12:49.540745Z","submitted_at":"2024-06-11T11:12:51Z","title":"EmoBox: Multilingual Multi-corpus Speech Emotion Recognition Toolkit and Benchmark","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.07162","snapshot_observed_at":"2026-08-05T17:33:59.835425Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.16188","last_updated":"2025-08-27T19:49:56Z","snapshot_observed_at":"2026-08-07T00:41:10.101975Z","submitted_at":"2025-08-22T08:08:45Z","title":"Seeing is Believing: Emotion-Aware Audio-Visual Language Modeling for Expressive Speech Generation","version":2},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-05T17:33:59.835425Z"},"links":{"cited_paper":"/paper/2406.07162","citing_paper":"/paper/2508.16188"},"observation_digest":"sha256:fa9d812a90e05b37cafc7abc27385d8728a4fc44f2db409f03c0593062816d9c","observation_id":"cb258ebd-d063-4120-b459-a5dddc0c6ee4","resolution":{"observed_at":"2026-08-05T17:33:59.835425Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.07162","last_updated":"2024-06-11T11:12:51Z","snapshot_observed_at":"2026-08-06T08:12:49.540745Z","submitted_at":"2024-06-11T11:12:51Z","title":"EmoBox: Multilingual Multi-corpus Speech Emotion Recognition Toolkit and Benchmark","version":1},"cited_work":{"arxiv_id":"2406.07162","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2406.07162","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2406.07162 , year=","venue":null,"work_id":"071ae116-f3f1-4c3e-9661-fee3b1e9e11b","year":null},"citing_paper":{"arxiv_id":"2605.06765","last_updated":"2026-05-07T17:59:56Z","snapshot_observed_at":"2026-08-02T05:36:23.979419Z","submitted_at":"2026-05-07T17:59:56Z","title":"VITA-QinYu: Expressive Spoken Language Model for Role-Playing and Singing","version":1},"reference_index":64,"source":"arxiv_source","source_observed_at":"2026-05-11T01:03:09.942984Z"},"links":{"cited_paper":"/paper/2406.07162","citing_paper":"/paper/2605.06765"},"observation_digest":"sha256:26555c6a7a73012c937b72598c12fdac046e835234f7856101ac6220d2d7975e","observation_id":"8469d56e-a787-47ba-a552-3ddcd28e3b26","resolution":{"observed_at":"2026-05-11T04:50:56.288746Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2406.07162/citation-record","integrity":"/paper/2406.07162/integrity","json":"/paper/2406.07162/citation-record.json","paper":"/paper/2406.07162"},"outbound":[],"paper":{"arxiv_id":"2406.07162","last_updated":"2024-06-11T11:12:51Z","latest_version":1,"primary_category":"cs.SD","snapshot_observed_at":"2026-08-06T08:12:49.540745Z","submitted_at":"2024-06-11T11:12:51Z","title":"EmoBox: Multilingual Multi-corpus Speech Emotion Recognition Toolkit and Benchmark"},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2406.07162."}