{"as_of":"2026-08-10T08:00:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6caf168018e37783eadeff0ec12be57f14ae0bedc27e0c281f3718fac7b3aaaa","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":"2026-08-10T06:31:04.303077+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":"2026-08-09T20:20:58.891002Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-11T07:26:02.600207Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2310.15261","last_updated":"2023-10-23T18:09:31Z","snapshot_observed_at":"2026-07-06T16:37:27.609912Z","submitted_at":"2023-10-23T18:09:31Z","title":"Modality Dropout for Multimodal Device Directed Speech Detection using Verbal and Non-Verbal Features","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.15261","snapshot_observed_at":"2026-08-09T20:20:58.891002Z","title":"Modality dropout for multimodal device directed speech detection using verbal and non-verbal features,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.19377","last_updated":"2025-02-03T17:35:35Z","snapshot_observed_at":"2026-08-09T20:15:32.638699Z","submitted_at":"2025-01-31T18:30:36Z","title":"SELMA: A Speech-Enabled Language Model for Virtual Assistant Interactions","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-09T20:20:58.891002Z"},"links":{"cited_paper":"/paper/2310.15261","citing_paper":"/paper/2501.19377"},"observation_digest":"sha256:92dd03332398bfb3249c3cea1df04407002b0a2f2cc3e83a02d67e5c3b82def0","observation_id":"833d2349-e460-49be-a96e-5d6cfa999c25","resolution":{"observed_at":"2026-08-09T20:20:58.891002Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.15261","last_updated":"2023-10-23T18:09:31Z","snapshot_observed_at":"2026-07-06T16:37:27.609912Z","submitted_at":"2023-10-23T18:09:31Z","title":"Modality Dropout for Multimodal Device Directed Speech Detection using Verbal and Non-Verbal Features","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.15261","snapshot_observed_at":"2026-08-08T11:32:42.774601Z","title":"arXiv preprint arXiv:2310.15261 (2023)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.07905","last_updated":"2025-02-11T19:21:23Z","snapshot_observed_at":"2026-08-09T00:39:02.531369Z","submitted_at":"2025-02-11T19:21:23Z","title":"DeepSeek on a Trip: Inducing Targeted Visual Hallucinations via Representation Vulnerabilities","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-08T11:32:42.774601Z"},"links":{"cited_paper":"/paper/2310.15261","citing_paper":"/paper/2502.07905"},"observation_digest":"sha256:a4c45836d9e8bc6f4aab266a997b79e3457b3a3aa6daa526cc572e77d7626ff6","observation_id":"11a11ee7-a7e6-42bd-9c2e-8dad5082d41d","resolution":{"observed_at":"2026-08-08T11:32:42.774601Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.15261","last_updated":"2023-10-23T18:09:31Z","snapshot_observed_at":"2026-07-06T16:37:27.609912Z","submitted_at":"2023-10-23T18:09:31Z","title":"Modality Dropout for Multimodal Device Directed Speech Detection using Verbal and Non-Verbal Features","version":1},"cited_work":{"arxiv_id":"2310.15261","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2310.15261","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Modality dropout for multimodal device di- rected speech detection using verbal and non- verbal features","venue":null,"work_id":"7ed99e77-84c6-4d5f-b6ce-4a85ac9ef285","year":2023},"citing_paper":{"arxiv_id":"2604.08412","last_updated":"2026-04-09T16:11:15Z","snapshot_observed_at":"2026-08-03T10:23:02.892336Z","submitted_at":"2026-04-09T16:11:15Z","title":"Selective Attention System (SAS): Device-Addressed Speech Detection for Real-Time On-Device Voice AI","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-10T17:11:01.258282Z"},"links":{"cited_paper":"/paper/2310.15261","citing_paper":"/paper/2604.08412"},"observation_digest":"sha256:44f69d9ef68e8e67409e1f725f9c5bc55daa9122370b16b35d482b9ad67da7e2","observation_id":"ca0003c1-f13b-4a49-9868-73806b23acf4","resolution":{"observed_at":"2026-05-11T07:26:02.604901Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2310.15261/citation-record","integrity":"/paper/2310.15261/integrity","json":"/paper/2310.15261/citation-record.json","paper":"/paper/2310.15261"},"outbound":[],"paper":{"arxiv_id":"2310.15261","last_updated":"2023-10-23T18:09:31Z","latest_version":1,"primary_category":"cs.SD","snapshot_observed_at":"2026-07-06T16:37:27.609912Z","submitted_at":"2023-10-23T18:09:31Z","title":"Modality Dropout for Multimodal Device Directed Speech Detection using Verbal and Non-Verbal Features"},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2310.15261."}