{"as_of":"2026-08-12T16:20:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3bdd5210d4b063aef65bf5b25ceca77b61be442c0b23ae34b179a4064d730019","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":"2026-08-12T06:34:41.77262+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":"2026-08-10T14:59:13.293802Z","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":"2026-07-02T16:17:09.108134Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2404.17806","last_updated":"2024-04-27T07:05:48Z","snapshot_observed_at":"2026-07-06T18:06:24.289614Z","submitted_at":"2024-04-27T07:05:48Z","title":"T-CLAP: Temporal-Enhanced Contrastive Language-Audio Pretraining","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.17806","snapshot_observed_at":"2026-08-10T14:59:13.293802Z","title":"T-CLAP: Temporal-enhanced contrastive language-audio pretraining,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.14680","last_updated":"2025-01-27T10:41:29Z","snapshot_observed_at":"2026-08-11T23:42:43.016880Z","submitted_at":"2025-01-24T17:57:47Z","title":"Diffusion based Text-to-Music Generation with Global and Local Text based Conditioning","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-10T14:59:13.293802Z"},"links":{"cited_paper":"/paper/2404.17806","citing_paper":"/paper/2501.14680"},"observation_digest":"sha256:8839bcb12ad6cfc8fe0b39b5d1d960ec14427b893a50b95d071d04556b65503f","observation_id":"3fcc17df-b228-41c0-95d1-6a3e309169d7","resolution":{"observed_at":"2026-08-10T14:59:13.293802Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.17806","last_updated":"2024-04-27T07:05:48Z","snapshot_observed_at":"2026-07-06T18:06:24.289614Z","submitted_at":"2024-04-27T07:05:48Z","title":"T-CLAP: Temporal-Enhanced Contrastive Language-Audio Pretraining","version":1},"cited_work":{"arxiv_id":"2404.17806","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2404.17806","snapshot_observed_at":"2026-07-02T16:17:09.108134Z","title":null,"venue":null,"work_id":"243184fa-810f-4b67-b26f-6d27348afd71","year":2024},"citing_paper":{"arxiv_id":"2606.05812","last_updated":"2026-06-04T07:50:33Z","snapshot_observed_at":"2026-08-02T04:12:05.501062Z","submitted_at":"2026-06-04T07:50:33Z","title":"FORTE: FOL-guided Optimal Refinement for Text-audio rEtrieval","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-06-27T22:52:14.518137Z"},"links":{"cited_paper":"/paper/2404.17806","citing_paper":"/paper/2606.05812"},"observation_digest":"sha256:bc96dfc9a91173108c1b4ed90b85461b1d366203b017e18fb0b791fcb4444604","observation_id":"d2d5cb99-c007-4bea-889b-6b9405265bd0","resolution":{"observed_at":"2026-07-02T16:17:09.109553Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2404.17806/citation-record","integrity":"/paper/2404.17806/integrity","json":"/paper/2404.17806/citation-record.json","paper":"/paper/2404.17806"},"outbound":[],"paper":{"arxiv_id":"2404.17806","last_updated":"2024-04-27T07:05:48Z","latest_version":1,"primary_category":"cs.SD","snapshot_observed_at":"2026-07-06T18:06:24.289614Z","submitted_at":"2024-04-27T07:05:48Z","title":"T-CLAP: Temporal-Enhanced Contrastive Language-Audio Pretraining"},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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:2404.17806."}