{"as_of":"2026-08-18T08:16:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:fd4ff24c202e0e454b84d0fc26f6c47c040223eddcd63d4aa5646afe70397c85","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":2,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":2,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T05:24:30.551203Z","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":"2026-05-16T23:28:40.873044Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2104.08189","last_updated":"2021-06-17T19:28:31Z","snapshot_observed_at":"2026-08-16T18:31:03.148300Z","submitted_at":"2021-04-16T15:58:46Z","title":"TalkNet 2: Non-Autoregressive Depth-Wise Separable Convolutional Model for Speech Synthesis with Explicit Pitch and Duration Prediction","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.08189","snapshot_observed_at":"2026-08-07T05:24:30.551203Z","title":"TalkNet 2: Non-autoregressive depth-wise separable convolu- tional model for speech synthesis with explicit pitch and duration prediction,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.08003","last_updated":"2025-06-09T17:59:42Z","snapshot_observed_at":"2026-08-16T14:51:37.417423Z","submitted_at":"2025-06-09T17:59:42Z","title":"Audio-Sync Video Generation with Multi-Stream Temporal Control","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-07T05:24:30.551203Z"},"links":{"cited_paper":"/paper/2104.08189","citing_paper":"/paper/2506.08003"},"observation_digest":"sha256:71013ea76501532c2fff39bc461e9fdfc3abe558f2c03967d688798a8389c249","observation_id":"c24d23f4-aca3-4d3f-a2ef-5d519b718316","resolution":{"observed_at":"2026-08-07T05:24:30.551203Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.08189","last_updated":"2021-06-17T19:28:31Z","snapshot_observed_at":"2026-08-16T18:31:03.148300Z","submitted_at":"2021-04-16T15:58:46Z","title":"TalkNet 2: Non-Autoregressive Depth-Wise Separable Convolutional Model for Speech Synthesis with Explicit Pitch and Duration Prediction","version":3},"cited_work":{"arxiv_id":"2104.08189","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2104.08189","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"TalkNet 2: Non- autoregressive depth-wise separable convolutional model for speech synthesis with explicit pitch and duration prediction","venue":null,"work_id":"69362040-64f0-45f0-bae9-13aae299e792","year":2021},"citing_paper":{"arxiv_id":"2512.10571","last_updated":"2026-05-02T11:27:08Z","snapshot_observed_at":"2026-08-14T01:07:57.560232Z","submitted_at":"2025-12-11T11:58:53Z","title":"AVI-Edit: Audio-sync Video Instance Editing with Granularity-Aware Mask Refiner","version":4},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-16T23:26:21.855485Z"},"links":{"cited_paper":"/paper/2104.08189","citing_paper":"/paper/2512.10571"},"observation_digest":"sha256:cc69dbddca3966f16aa1e4570b9f0bb7ddfd009f335c3427db907f6c4e4f64b9","observation_id":"68973736-eb59-4246-b13b-be55748fc444","resolution":{"observed_at":"2026-05-16T23:28:40.877420Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2104.08189/citation-record","integrity":"/paper/2104.08189/integrity","json":"/paper/2104.08189/citation-record.json","paper":"/paper/2104.08189"},"outbound":[],"paper":{"arxiv_id":"2104.08189","last_updated":"2021-06-17T19:28:31Z","latest_version":3,"primary_category":"eess.AS","snapshot_observed_at":"2026-08-16T18:31:03.148300Z","submitted_at":"2021-04-16T15:58:46Z","title":"TalkNet 2: Non-Autoregressive Depth-Wise Separable Convolutional Model for Speech Synthesis with Explicit Pitch and Duration Prediction"},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2104.08189."}