{"as_of":"2026-08-16T06:14:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:636f757876244df924367ba6d72ece12144b66b823ad439bd04a1fa1c17f647f","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":"2026-08-15T06:32:42.880941+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":"2026-08-15T21:20:25.320711Z","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":"2026-08-07T10:17:48.264337Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2204.03040","last_updated":"2022-08-24T14:24:57Z","snapshot_observed_at":"2026-08-13T16:07:23.204833Z","submitted_at":"2022-04-06T18:45:20Z","title":"SOMOS: The Samsung Open MOS Dataset for the Evaluation of Neural Text-to-Speech Synthesis","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.03040","snapshot_observed_at":"2026-08-10T12:30:52.084767Z","title":"Somos: The sam- sung open mos dataset for the evaluation of neural text-to-speech synthesis","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.17202","last_updated":"2025-03-12T02:01:46Z","snapshot_observed_at":"2026-08-14T01:54:19.788458Z","submitted_at":"2025-01-27T22:47:51Z","title":"Audio Large Language Models Can Be Descriptive Speech Quality Evaluators","version":2},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-10T12:30:52.084767Z"},"links":{"cited_paper":"/paper/2204.03040","citing_paper":"/paper/2501.17202"},"observation_digest":"sha256:5db83237d82e191b2c853fc74c67e6acfc82815631f6b5a570969fa04ce5a41b","observation_id":"52791c61-0c25-417a-a2f8-6e053af36743","resolution":{"observed_at":"2026-08-10T12:30:52.084767Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2204.03040","last_updated":"2022-08-24T14:24:57Z","snapshot_observed_at":"2026-08-13T16:07:23.204833Z","submitted_at":"2022-04-06T18:45:20Z","title":"SOMOS: The Samsung Open MOS Dataset for the Evaluation of Neural Text-to-Speech Synthesis","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.03040","snapshot_observed_at":"2026-08-15T21:20:25.320711Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.10596","last_updated":"2025-05-15T10:03:05Z","snapshot_observed_at":"2026-08-15T21:13:35.245828Z","submitted_at":"2025-05-15T10:03:05Z","title":"Inclusivity of AI Speech in Healthcare: A Decade Look Back","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T21:20:25.320711Z"},"links":{"cited_paper":"/paper/2204.03040","citing_paper":"/paper/2505.10596"},"observation_digest":"sha256:8ffd75a8ae56d9a403985583ed34a991b3bf68c3b6c5156749f1657a524dc32c","observation_id":"ae7f5136-cc0c-4e7f-a416-98f00339f303","resolution":{"observed_at":"2026-08-15T21:20:25.320711Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2204.03040","last_updated":"2022-08-24T14:24:57Z","snapshot_observed_at":"2026-08-13T16:07:23.204833Z","submitted_at":"2022-04-06T18:45:20Z","title":"SOMOS: The Samsung Open MOS Dataset for the Evaluation of Neural Text-to-Speech Synthesis","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.03040","snapshot_observed_at":"2026-08-07T11:44:17.773360Z","title":"SOMOS: The samsung open mos dataset for the evaluation of neural text-to-speech synthesis,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.02082","last_updated":"2025-06-02T10:45:40Z","snapshot_observed_at":"2026-08-08T00:25:40.747351Z","submitted_at":"2025-06-02T10:45:40Z","title":"SALF-MOS: Speaker Agnostic Latent Features Downsampled for MOS Prediction","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T11:44:17.773360Z"},"links":{"cited_paper":"/paper/2204.03040","citing_paper":"/paper/2506.02082"},"observation_digest":"sha256:763ccc273521ff0db260f8260f6ba0b86b316b0574b96566e9d331fdb92d8dd1","observation_id":"85f38dec-661a-4107-b374-415b0001405f","resolution":{"observed_at":"2026-08-07T11:44:17.773360Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2204.03040","last_updated":"2022-08-24T14:24:57Z","snapshot_observed_at":"2026-08-13T16:07:23.204833Z","submitted_at":"2022-04-06T18:45:20Z","title":"SOMOS: The Samsung Open MOS Dataset for the Evaluation of Neural Text-to-Speech Synthesis","version":2},"cited_work":{"arxiv_id":"2204.03040","doi":null,"metadata_source":"pith","pith_arxiv_id":"2204.03040","snapshot_observed_at":"2026-08-07T10:17:48.264337Z","title":"SOMOS: The Samsung Open MOS Dataset for the Evaluation of Neural Text-to-Speech Synthesis","venue":"cs.SD","work_id":"98c0bebc-ce8e-4e7e-a8a2-154eb6cb349a","year":2022},"citing_paper":{"arxiv_id":"2506.10019","last_updated":"2025-06-06T11:09:46Z","snapshot_observed_at":"2026-08-14T07:07:49.646647Z","submitted_at":"2025-06-06T11:09:46Z","title":"A Survey of Automatic Evaluation Methods on Text, Visual and Speech Generations","version":1},"reference_index":251,"source":"pdf_text","source_observed_at":"2026-08-07T10:17:47.138454Z"},"links":{"cited_paper":"/paper/2204.03040","citing_paper":"/paper/2506.10019"},"observation_digest":"sha256:6380188ac5df955efc99443602dc87801bfa5c15d86001a0a853314d41af3e1f","observation_id":"0be484ed-559b-4ba8-b77a-60b2039438be","resolution":{"observed_at":"2026-08-07T10:17:48.268410Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2204.03040/citation-record","integrity":"/paper/2204.03040/integrity","json":"/paper/2204.03040/citation-record.json","paper":"/paper/2204.03040"},"outbound":[],"paper":{"arxiv_id":"2204.03040","last_updated":"2022-08-24T14:24:57Z","latest_version":2,"primary_category":"cs.SD","snapshot_observed_at":"2026-08-13T16:07:23.204833Z","submitted_at":"2022-04-06T18:45:20Z","title":"SOMOS: The Samsung Open MOS Dataset for the Evaluation of Neural Text-to-Speech Synthesis"},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2204.03040."}