{"as_of":"2026-08-21T09:00:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0a5f6a2af4b61797b7ea7d2549d7e678593ea7e493869b7444c2bf35467ae2f8","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":"2026-08-21T06:32:19.484+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":"2026-08-12T21:42:21.566425Z","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":"2026-08-07T11:54:26.730197Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2109.00181","last_updated":"2021-09-01T04:18:19Z","snapshot_observed_at":"2026-08-18T04:02:18.735630Z","submitted_at":"2021-09-01T04:18:19Z","title":"CTAL: Pre-training Cross-modal Transformer for Audio-and-Language Representations","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.00181","snapshot_observed_at":"2026-08-12T21:42:21.566425Z","title":"arXiv preprint arXiv:2109.00181 (2021)","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.08409","last_updated":"2024-11-13T07:55:41Z","snapshot_observed_at":"2026-08-15T22:12:27.219327Z","submitted_at":"2024-11-13T07:55:41Z","title":"DiVR: incorporating context from diverse VR scenes for human trajectory prediction","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-12T21:42:21.566425Z"},"links":{"cited_paper":"/paper/2109.00181","citing_paper":"/paper/2411.08409"},"observation_digest":"sha256:360e0bc12fa83350a2a6250fd0ac7432d6cee57d121e0f523987aadb2816ad39","observation_id":"3dda79c5-c8e7-44e8-9f11-02d23b282cae","resolution":{"observed_at":"2026-08-12T21:42:21.566425Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.00181","last_updated":"2021-09-01T04:18:19Z","snapshot_observed_at":"2026-08-18T04:02:18.735630Z","submitted_at":"2021-09-01T04:18:19Z","title":"CTAL: Pre-training Cross-modal Transformer for Audio-and-Language Representations","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.00181","snapshot_observed_at":"2026-08-10T14:36:19.232892Z","title":"Ctal: Pre-training cross- modal transformer for audio-and-language representations,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.15177","last_updated":"2026-07-03T16:46:09Z","snapshot_observed_at":"2026-08-19T23:01:24.892193Z","submitted_at":"2025-01-25T11:15:06Z","title":"Audio-Language Models for Audio-Centric Tasks: A Systematic Survey","version":3},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-10T14:36:19.232892Z"},"links":{"cited_paper":"/paper/2109.00181","citing_paper":"/paper/2501.15177"},"observation_digest":"sha256:cf3475d652b3b99df6a10abff176e4bae82a96ad578577b91cbcd06539b5f49b","observation_id":"a3f3efb4-5131-4b49-8fdf-e5fe6f7be77c","resolution":{"observed_at":"2026-08-10T14:36:19.232892Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.00181","last_updated":"2021-09-01T04:18:19Z","snapshot_observed_at":"2026-08-18T04:02:18.735630Z","submitted_at":"2021-09-01T04:18:19Z","title":"CTAL: Pre-training Cross-modal Transformer for Audio-and-Language Representations","version":1},"cited_work":{"arxiv_id":"2109.00181","doi":null,"metadata_source":"pith","pith_arxiv_id":"2109.00181","snapshot_observed_at":"2026-08-07T11:54:26.730197Z","title":"CTAL: Pre-training Cross-modal Transformer for Audio-and-Language Representations","venue":"cs.SD","work_id":"31f6bc4f-4bdc-4858-af38-3d3eb0ae28cc","year":2021},"citing_paper":{"arxiv_id":"2506.01111","last_updated":"2025-06-01T18:29:17Z","snapshot_observed_at":"2026-08-17T21:37:37.030375Z","submitted_at":"2025-06-01T18:29:17Z","title":"FusionAudio-1.2M: Towards Fine-grained Audio Captioning with Multimodal Contextual Fusion","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T11:54:24.139798Z"},"links":{"cited_paper":"/paper/2109.00181","citing_paper":"/paper/2506.01111"},"observation_digest":"sha256:e095d06dcf690ee71601f4be72dd0efd8ea997378272acccd115e0e9190bb790","observation_id":"96a26cd4-5438-442b-8501-83c7f5e3ccbf","resolution":{"observed_at":"2026-08-07T11:54:26.810143Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2109.00181/citation-record","integrity":"/paper/2109.00181/integrity","json":"/paper/2109.00181/citation-record.json","paper":"/paper/2109.00181"},"outbound":[],"paper":{"arxiv_id":"2109.00181","last_updated":"2021-09-01T04:18:19Z","latest_version":1,"primary_category":"cs.SD","snapshot_observed_at":"2026-08-18T04:02:18.735630Z","submitted_at":"2021-09-01T04:18:19Z","title":"CTAL: Pre-training Cross-modal Transformer for Audio-and-Language Representations"},"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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 21 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2109.00181."}