{"as_of":"2026-08-12T05:47:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:51ec1ce380f7e3ef8b18c0fd56da342fff8ff24a5e6f996a9d05a2ce14eead42","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":"2026-08-11T06:34:44.6726+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":"2026-08-11T15:01:33.795919Z","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":"2026-08-11T04:34:07.992797Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2410.14101","last_updated":"2024-12-23T08:57:37Z","snapshot_observed_at":"2026-08-11T18:43:33.380184Z","submitted_at":"2024-10-18T00:46:18Z","title":"Multi-Source Spatial Knowledge Understanding for Immersive Visual Text-to-Speech","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.14101","snapshot_observed_at":"2026-08-11T15:01:33.795919Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.11409","last_updated":"2025-01-15T01:59:02Z","snapshot_observed_at":"2026-08-12T03:17:17.017036Z","submitted_at":"2024-12-16T03:25:23Z","title":"Multi-modal and Multi-scale Spatial Environment Understanding for Immersive Visual Text-to-Speech","version":3},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-11T15:01:33.795919Z"},"links":{"cited_paper":"/paper/2410.14101","citing_paper":"/paper/2412.11409"},"observation_digest":"sha256:8cb88044149efc4303367ac8cb022fdf5f03462b1a6b32d94073afcf21ef085b","observation_id":"5ff458eb-6d03-4358-9d4f-977c5d726824","resolution":{"observed_at":"2026-08-11T15:01:33.795919Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.14101","last_updated":"2024-12-23T08:57:37Z","snapshot_observed_at":"2026-08-11T18:43:33.380184Z","submitted_at":"2024-10-18T00:46:18Z","title":"Multi-Source Spatial Knowledge Understanding for Immersive Visual Text-to-Speech","version":2},"cited_work":{"arxiv_id":"2410.14101","doi":null,"metadata_source":"pith","pith_arxiv_id":"2410.14101","snapshot_observed_at":"2026-08-11T04:34:07.992797Z","title":"Multi-Source Spatial Knowledge Understanding for Immersive Visual Text-to-Speech","venue":"cs.SD","work_id":"782426f5-7c66-4b5a-ad4a-6fa581aacb39","year":2024},"citing_paper":{"arxiv_id":"2412.18748","last_updated":"2024-12-31T07:27:26Z","snapshot_observed_at":"2026-08-11T04:28:26.087195Z","submitted_at":"2024-12-25T02:41:13Z","title":"Towards Expressive Video Dubbing with Multiscale Multimodal Context Interaction","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-11T04:34:07.902789Z"},"links":{"cited_paper":"/paper/2410.14101","citing_paper":"/paper/2412.18748"},"observation_digest":"sha256:ce3d5b6e93a1e49a713626817b2bb6ff4c49d25806c2d0f34f1e451fdbfd3079","observation_id":"0deab94c-ff93-4883-8c05-0eb527827fc1","resolution":{"observed_at":"2026-08-11T04:34:07.997986Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2410.14101/citation-record","integrity":"/paper/2410.14101/integrity","json":"/paper/2410.14101/citation-record.json","paper":"/paper/2410.14101"},"outbound":[],"paper":{"arxiv_id":"2410.14101","last_updated":"2024-12-23T08:57:37Z","latest_version":2,"primary_category":"cs.SD","snapshot_observed_at":"2026-08-11T18:43:33.380184Z","submitted_at":"2024-10-18T00:46:18Z","title":"Multi-Source Spatial Knowledge Understanding for Immersive Visual Text-to-Speech"},"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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2410.14101."}