{"as_of":"2026-08-09T01:59:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:95665c8ade63374af22cbffd64b53bbdcbb43cb4eebbef85fcb282d40167e416","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":"2026-08-08T06:32:00.761636+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":"2026-08-07T15:36:05.263202Z","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":"2026-08-07T14:33:49.645828Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2406.18871","last_updated":"2024-06-27T03:52:35Z","snapshot_observed_at":"2026-08-06T09:14:18.018297Z","submitted_at":"2024-06-27T03:52:35Z","title":"DeSTA: Enhancing Speech Language Models through Descriptive Speech-Text Alignment","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.18871","snapshot_observed_at":"2026-08-07T15:36:05.263202Z","title":"Desta: Enhancing speech language mod- els through descriptive speech-text alignment,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.14518","last_updated":"2025-07-01T02:25:58Z","snapshot_observed_at":"2026-08-08T14:34:56.906762Z","submitted_at":"2025-05-20T15:44:01Z","title":"Teaching Audio-Aware Large Language Models What Does Not Hear: Mitigating Hallucinations through Synthesized Negative Samples","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T15:36:05.263202Z"},"links":{"cited_paper":"/paper/2406.18871","citing_paper":"/paper/2505.14518"},"observation_digest":"sha256:66eda4413f019f521a27d662ffe3ab7a098c76a5d976ee4a5f2e12a3c1b8faf6","observation_id":"c9704f10-ca59-4fde-a91b-0c38e62b6af4","resolution":{"observed_at":"2026-08-07T15:36:05.263202Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.18871","last_updated":"2024-06-27T03:52:35Z","snapshot_observed_at":"2026-08-06T09:14:18.018297Z","submitted_at":"2024-06-27T03:52:35Z","title":"DeSTA: Enhancing Speech Language Models through Descriptive Speech-Text Alignment","version":1},"cited_work":{"arxiv_id":"2406.18871","doi":null,"metadata_source":"pith","pith_arxiv_id":"2406.18871","snapshot_observed_at":"2026-08-07T14:33:49.645828Z","title":"DeSTA: Enhancing Speech Language Models through Descriptive Speech-Text Alignment","venue":"eess.AS","work_id":"3ba005c3-ceea-47b2-aeed-231b61403b39","year":2024},"citing_paper":{"arxiv_id":"2505.18517","last_updated":"2025-05-24T05:28:22Z","snapshot_observed_at":"2026-08-08T15:41:54.286673Z","submitted_at":"2025-05-24T05:28:22Z","title":"LiSTEN: Learning Soft Token Embeddings for Neural Audio LLMs","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T14:33:46.609940Z"},"links":{"cited_paper":"/paper/2406.18871","citing_paper":"/paper/2505.18517"},"observation_digest":"sha256:05af342288993ad3b2d4d3fa4361b989f793bc0fc82311df4220118bbbfac4a6","observation_id":"7b707605-3459-4962-b65d-072eb27a8a39","resolution":{"observed_at":"2026-08-07T14:33:49.704245Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2406.18871/citation-record","integrity":"/paper/2406.18871/integrity","json":"/paper/2406.18871/citation-record.json","paper":"/paper/2406.18871"},"outbound":[],"paper":{"arxiv_id":"2406.18871","last_updated":"2024-06-27T03:52:35Z","latest_version":1,"primary_category":"eess.AS","snapshot_observed_at":"2026-08-06T09:14:18.018297Z","submitted_at":"2024-06-27T03:52:35Z","title":"DeSTA: Enhancing Speech Language Models through Descriptive Speech-Text Alignment"},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2406.18871."}