{"as_of":"2026-08-09T01:18:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d46c4f4b8579f9cefbeed8770f2f5e39e52667a09e22ff89032b8435d91a1d92","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":"2026-07-12T06:14:42.321767Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2409.16920","last_updated":"2025-04-30T13:16:09Z","snapshot_observed_at":"2026-08-08T18:40:06.346575Z","submitted_at":"2024-09-25T13:27:17Z","title":"Cross-Lingual Speech Emotion Recognition: Humans vs. Self-Supervised Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.16920","snapshot_observed_at":"2026-07-12T06:14:42.321767Z","title":"Cross- lingual speech emotion recognition: Humans vs. self-supervised mod- els,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.02904","last_updated":"2026-07-03T03:02:48Z","snapshot_observed_at":"2026-08-08T09:39:08.965602Z","submitted_at":"2026-07-03T03:02:48Z","title":"Speaker-Aware Temporal Aggregation Strategies on Segment Representations for Depression Detection in Dyadic Interaction: A Benchmark Study","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-07-12T06:14:42.321767Z"},"links":{"cited_paper":"/paper/2409.16920","citing_paper":"/paper/2607.02904"},"observation_digest":"sha256:3fd5f549b96d08fc02846a771a0e49ea28b6b6c7a959c3c0edd0cf555bdcb79a","observation_id":"be9de19d-e7db-4d1b-b876-96b7518b54f8","resolution":{"observed_at":"2026-07-12T06:14:42.321767Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.16920","last_updated":"2025-04-30T13:16:09Z","snapshot_observed_at":"2026-08-08T18:40:06.346575Z","submitted_at":"2024-09-25T13:27:17Z","title":"Cross-Lingual Speech Emotion Recognition: Humans vs. Self-Supervised Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.16920","snapshot_observed_at":"2026-07-12T06:06:46.343211Z","title":"Cross- lingual speech emotion recognition: Humans vs. self-supervised mod- els,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.02920","last_updated":"2026-07-03T03:24:38Z","snapshot_observed_at":"2026-08-09T00:13:42.364327Z","submitted_at":"2026-07-03T03:24:38Z","title":"Layer-wise Cross-Lingual Depression Detection from Speech: Analysis with Contrastive Alignment","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-07-12T06:06:46.343211Z"},"links":{"cited_paper":"/paper/2409.16920","citing_paper":"/paper/2607.02920"},"observation_digest":"sha256:2b74f4c5cd99276a8013a2f064a178734781cf977e0d6c1756e3b18d34db41eb","observation_id":"c9a4d282-efc8-4e3a-9c59-61378e3f44b7","resolution":{"observed_at":"2026-07-12T06:06:46.343211Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2409.16920/citation-record","integrity":"/paper/2409.16920/integrity","json":"/paper/2409.16920/citation-record.json","paper":"/paper/2409.16920"},"outbound":[],"paper":{"arxiv_id":"2409.16920","last_updated":"2025-04-30T13:16:09Z","latest_version":2,"primary_category":"eess.AS","snapshot_observed_at":"2026-08-08T18:40:06.346575Z","submitted_at":"2024-09-25T13:27:17Z","title":"Cross-Lingual Speech Emotion Recognition: Humans vs. Self-Supervised Models"},"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:2409.16920."}