{"as_of":"2026-08-21T14:08:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5111690af36549ec6847f44767246fde7d73b6f46f6187ac564e4572565ea9d2","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":"2026-08-21T06:32:19.484+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":"2026-08-10T22:03:38.088084Z","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":"2026-08-04T21:25:27.530032Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2402.06986","last_updated":"2024-09-30T16:15:24Z","snapshot_observed_at":"2026-08-16T14:19:39.640988Z","submitted_at":"2024-02-10T16:34:26Z","title":"Cacophony: An Improved Contrastive Audio-Text Model","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.06986","snapshot_observed_at":"2026-08-10T22:03:38.088084Z","title":"Cacophony: An improved contrastive audio-text model,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.03038","last_updated":"2025-01-07T15:13:41Z","snapshot_observed_at":"2026-08-21T11:23:59.578829Z","submitted_at":"2025-01-06T14:26:00Z","title":"Piano Transcription by Hierarchical Language Modeling with Pretrained Roll-based Encoders","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-10T22:03:38.088084Z"},"links":{"cited_paper":"/paper/2402.06986","citing_paper":"/paper/2501.03038"},"observation_digest":"sha256:612ec06958be02f66f0310b7affdadb6603ed6c3149dc59a5e4c8ae0af4a3df0","observation_id":"d7a87563-d594-4c62-8751-cd66d377eb6e","resolution":{"observed_at":"2026-08-10T22:03:38.088084Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.06986","last_updated":"2024-09-30T16:15:24Z","snapshot_observed_at":"2026-08-16T14:19:39.640988Z","submitted_at":"2024-02-10T16:34:26Z","title":"Cacophony: An Improved Contrastive Audio-Text Model","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.06986","snapshot_observed_at":"2026-08-10T14:36:19.486690Z","title":"Cacophony: An improved contrastive audio-text model,","venue":null,"work_id":null,"year":2024},"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":79,"source":"pdf_text","source_observed_at":"2026-08-10T14:36:19.486690Z"},"links":{"cited_paper":"/paper/2402.06986","citing_paper":"/paper/2501.15177"},"observation_digest":"sha256:f777919308227f1693ff25df19a2f33031b963d574476ec8919ba510126e2b3d","observation_id":"2a3d6981-0b78-432b-80bf-01e144a37c99","resolution":{"observed_at":"2026-08-10T14:36:19.486690Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.06986","last_updated":"2024-09-30T16:15:24Z","snapshot_observed_at":"2026-08-16T14:19:39.640988Z","submitted_at":"2024-02-10T16:34:26Z","title":"Cacophony: An Improved Contrastive Audio-Text Model","version":3},"cited_work":{"arxiv_id":"2402.06986","doi":null,"metadata_source":"pith","pith_arxiv_id":"2402.06986","snapshot_observed_at":"2026-08-04T21:25:27.530032Z","title":"Cacophony: An Improved Contrastive Audio-Text Model","venue":"cs.SD","work_id":"594a233c-f248-45d4-beb8-074e46043b19","year":2024},"citing_paper":{"arxiv_id":"2509.09717","last_updated":"2025-09-09T18:57:10Z","snapshot_observed_at":"2026-08-15T13:12:57.491333Z","submitted_at":"2025-09-09T18:57:10Z","title":"Testing chatbots on the creation of encoders for audio conditioned image generation","version":1},"reference_index":121,"source":"pdf_text","source_observed_at":"2026-08-04T21:25:27.430366Z"},"links":{"cited_paper":"/paper/2402.06986","citing_paper":"/paper/2509.09717"},"observation_digest":"sha256:20ee44fcdd56d41cbd2c69031ed0514a8c7fdc9ef6ddb2e706e4ce86722a0cf2","observation_id":"92cf2ff3-a538-488b-8ee6-a4fc7b06218b","resolution":{"observed_at":"2026-08-04T21:25:27.535905Z","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"}},{"citation":{"cited_paper":{"arxiv_id":"2402.06986","last_updated":"2024-09-30T16:15:24Z","snapshot_observed_at":"2026-08-16T14:19:39.640988Z","submitted_at":"2024-02-10T16:34:26Z","title":"Cacophony: An Improved Contrastive Audio-Text Model","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.06986","snapshot_observed_at":"2026-08-01T14:46:37.580702Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.18666","last_updated":"2026-07-21T03:25:34Z","snapshot_observed_at":"2026-08-17T16:58:02.976368Z","submitted_at":"2026-07-21T03:25:34Z","title":"Fusion Embedding: A Unified Embedding Space for Text, Image, Video, and Audio","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-01T14:46:37.580702Z"},"links":{"cited_paper":"/paper/2402.06986","citing_paper":"/paper/2607.18666"},"observation_digest":"sha256:c035f0d3c44d94545de24cbf74732de673817e80f9a11f32aae79a7ecca9fb45","observation_id":"1c5044bf-9698-4589-9779-b99ceea62a69","resolution":{"observed_at":"2026-08-01T14:46:37.580702Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2402.06986/citation-record","integrity":"/paper/2402.06986/integrity","json":"/paper/2402.06986/citation-record.json","paper":"/paper/2402.06986"},"outbound":[],"paper":{"arxiv_id":"2402.06986","last_updated":"2024-09-30T16:15:24Z","latest_version":3,"primary_category":"cs.SD","snapshot_observed_at":"2026-08-16T14:19:39.640988Z","submitted_at":"2024-02-10T16:34:26Z","title":"Cacophony: An Improved Contrastive Audio-Text Model"},"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 4 inbound Pith citation observations for arXiv:2402.06986."}