{"as_of":"2026-08-17T13:44:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c3495e313b636bcdd11959ada48665f605954854947bb049a46c67ad70c176e7","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":"2026-08-17T06:30:58.91139+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":"2026-08-11T19:55:14.938194Z","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":"2026-08-05T10:18:35.658471Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2406.08353","last_updated":"2025-03-23T16:45:04Z","snapshot_observed_at":"2026-08-16T13:43:41.325087Z","submitted_at":"2024-06-12T15:59:25Z","title":"Speech Emotion Recognition with ASR Transcripts: A Comprehensive Study on Word Error Rate and Fusion Techniques","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.08353","snapshot_observed_at":"2026-08-11T19:55:14.938194Z","title":"Speech emotion recognition with asr transcripts: A comprehensive study on word error rate and fusion techniques,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.06259","last_updated":"2024-12-09T07:18:29Z","snapshot_observed_at":"2026-08-16T16:09:27.015113Z","submitted_at":"2024-12-09T07:18:29Z","title":"Leveraging Prompt Learning and Pause Encoding for Alzheimer's Disease Detection","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-11T19:55:14.938194Z"},"links":{"cited_paper":"/paper/2406.08353","citing_paper":"/paper/2412.06259"},"observation_digest":"sha256:be4ff762f52954463c0d0c8f34539500eb1014ab8381cdd4dc02afb2a53f791f","observation_id":"0f4739d3-21c7-4e02-a276-669e1fcf14ea","resolution":{"observed_at":"2026-08-11T19:55:14.938194Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.08353","last_updated":"2025-03-23T16:45:04Z","snapshot_observed_at":"2026-08-16T13:43:41.325087Z","submitted_at":"2024-06-12T15:59:25Z","title":"Speech Emotion Recognition with ASR Transcripts: A Comprehensive Study on Word Error Rate and Fusion Techniques","version":3},"cited_work":{"arxiv_id":"2406.08353","doi":null,"metadata_source":"pith","pith_arxiv_id":"2406.08353","snapshot_observed_at":"2026-08-05T10:18:35.658471Z","title":"Speech Emotion Recognition with ASR Transcripts: A Comprehensive Study on Word Error Rate and Fusion Techniques","venue":"eess.AS","work_id":"b15bee05-2d28-49a6-8ad6-ef15f4e7c503","year":2024},"citing_paper":{"arxiv_id":"2509.04357","last_updated":"2025-09-04T16:18:34Z","snapshot_observed_at":"2026-08-12T02:29:59.457036Z","submitted_at":"2025-09-04T16:18:34Z","title":"PARCO: Phoneme-Augmented Robust Contextual ASR via Contrastive Entity Disambiguation","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-05T10:18:31.395886Z"},"links":{"cited_paper":"/paper/2406.08353","citing_paper":"/paper/2509.04357"},"observation_digest":"sha256:2d7406dad13ee99ddbdfe8dad5f7a44f424ba7d4d6e74e8bd5de11c8cf8ed91e","observation_id":"9c529a58-f17f-49f4-884e-b0ad911e284f","resolution":{"observed_at":"2026-08-05T10:18:35.743208Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2406.08353/citation-record","integrity":"/paper/2406.08353/integrity","json":"/paper/2406.08353/citation-record.json","paper":"/paper/2406.08353"},"outbound":[],"paper":{"arxiv_id":"2406.08353","last_updated":"2025-03-23T16:45:04Z","latest_version":3,"primary_category":"eess.AS","snapshot_observed_at":"2026-08-16T13:43:41.325087Z","submitted_at":"2024-06-12T15:59:25Z","title":"Speech Emotion Recognition with ASR Transcripts: A Comprehensive Study on Word Error Rate and Fusion Techniques"},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2406.08353."}