{"as_of":"2026-08-24T01:11:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2ce14f2b8088bf3e0ccb11e33f379426405e4fe312e8d7e308a8cb9015fcf3ca","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":"2026-08-23T06:30:58.430688+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":"2026-08-07T13:20:15.968878Z","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":"2026-08-07T13:20:17.952996Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2406.13275","last_updated":"2024-06-25T08:07:36Z","snapshot_observed_at":"2026-08-21T01:51:12.445829Z","submitted_at":"2024-06-19T07:09:46Z","title":"Enhancing Automated Audio Captioning via Large Language Models with Optimized Audio Encoding","version":2},"cited_work":{"arxiv_id":"2406.13275","doi":null,"metadata_source":"pith","pith_arxiv_id":"2406.13275","snapshot_observed_at":"2026-08-07T13:20:17.952996Z","title":"Enhancing Automated Audio Captioning via Large Language Models with Optimized Audio Encoding","venue":"cs.SD","work_id":"bc3bb14c-d932-4282-8466-1f0deef86ac7","year":2024},"citing_paper":{"arxiv_id":"2505.22045","last_updated":"2025-05-28T07:08:17Z","snapshot_observed_at":"2026-08-19T10:12:59.859968Z","submitted_at":"2025-05-28T07:08:17Z","title":"Mitigating Audiovisual Mismatch in Visual-Guide Audio Captioning","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T13:20:15.968878Z"},"links":{"cited_paper":"/paper/2406.13275","citing_paper":"/paper/2505.22045"},"observation_digest":"sha256:da732630bea38c14386d87f99f6c80003b018623bd56d75f684406acd7d5e44e","observation_id":"987c54b5-ee94-4442-89d2-239d455eff1a","resolution":{"observed_at":"2026-08-07T13:20:18.006011Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.13275","last_updated":"2024-06-25T08:07:36Z","snapshot_observed_at":"2026-08-21T01:51:12.445829Z","submitted_at":"2024-06-19T07:09:46Z","title":"Enhancing Automated Audio Captioning via Large Language Models with Optimized Audio Encoding","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.13275","snapshot_observed_at":"2026-07-11T16:20:13.303809Z","title":"Enhancing automated audio captioning via large language models with optimized audio encoding,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.04619","last_updated":"2026-07-06T02:58:47Z","snapshot_observed_at":"2026-08-11T23:49:30.842835Z","submitted_at":"2026-07-06T02:58:47Z","title":"CARD: Cross-component Audio Representation Distillation for Encoder-Free Audio Captioning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-07-11T16:20:13.303809Z"},"links":{"cited_paper":"/paper/2406.13275","citing_paper":"/paper/2607.04619"},"observation_digest":"sha256:92f3d28cb8b47d54f594c96f3eeb4a011ad332bce76d88b0ada4dfd1cb9d1e37","observation_id":"2e0f931e-e155-478c-b1d0-61010534587b","resolution":{"observed_at":"2026-07-11T16:20:13.303809Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.13275","last_updated":"2024-06-25T08:07:36Z","snapshot_observed_at":"2026-08-21T01:51:12.445829Z","submitted_at":"2024-06-19T07:09:46Z","title":"Enhancing Automated Audio Captioning via Large Language Models with Optimized Audio Encoding","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.13275","snapshot_observed_at":"2026-08-01T14:46:36.225816Z","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":20,"source":"arxiv_source","source_observed_at":"2026-08-01T14:46:36.225816Z"},"links":{"cited_paper":"/paper/2406.13275","citing_paper":"/paper/2607.18666"},"observation_digest":"sha256:09cb78013ac6f61e0123eb6139991479bd3ac0de47bfa04923a2cb4b70bf7b32","observation_id":"69113afc-ea52-4ef1-975b-5bf0ac9db095","resolution":{"observed_at":"2026-08-01T14:46:36.225816Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2406.13275/citation-record","integrity":"/paper/2406.13275/integrity","json":"/paper/2406.13275/citation-record.json","paper":"/paper/2406.13275"},"outbound":[],"paper":{"arxiv_id":"2406.13275","last_updated":"2024-06-25T08:07:36Z","latest_version":2,"primary_category":"cs.SD","snapshot_observed_at":"2026-08-21T01:51:12.445829Z","submitted_at":"2024-06-19T07:09:46Z","title":"Enhancing Automated Audio Captioning via Large Language Models with Optimized Audio Encoding"},"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":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"thesis":"As of 24 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2406.13275."}