{"as_of":"2026-08-15T15:50:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:fdaa3808c7b0e1c8a5616636bb24139917ef2a676b87ded343ca42e88deae2d1","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":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-15T06:32:42.880941+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T14:37:54.757887Z","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":"2026-07-01T10:05:41.160122Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1904.13377","last_updated":"2019-05-03T14:00:16Z","snapshot_observed_at":"2026-08-14T16:39:11.834763Z","submitted_at":"2019-04-30T17:20:32Z","title":"Very Deep Self-Attention Networks for End-to-End Speech Recognition","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1904.13377","snapshot_observed_at":"2026-08-14T10:23:02.157631Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"1908.11365","last_updated":"2019-08-29T17:50:55Z","snapshot_observed_at":"2026-08-14T10:14:57.277338Z","submitted_at":"2019-08-29T17:50:55Z","title":"Improving Deep Transformer with Depth-Scaled Initialization and Merged Attention","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-14T10:23:02.157631Z"},"links":{"cited_paper":"/paper/1904.13377","citing_paper":"/paper/1908.11365"},"observation_digest":"sha256:184b99face8f01e713fddd5e6ff556517376d5260d046554d618cec8978b429f","observation_id":"4dd5d653-295b-4f15-b764-147929974035","resolution":{"observed_at":"2026-08-14T10:23:02.157631Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1904.13377","last_updated":"2019-05-03T14:00:16Z","snapshot_observed_at":"2026-08-14T16:39:11.834763Z","submitted_at":"2019-04-30T17:20:32Z","title":"Very Deep Self-Attention Networks for End-to-End Speech Recognition","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1904.13377","snapshot_observed_at":"2026-08-05T11:39:56.523465Z","title":"https://doi.org/10.48550/arXiv.1904.13377","venue":null,"work_id":null,"year":1904},"citing_paper":{"arxiv_id":"2509.04507","last_updated":"2025-09-02T16:13:29Z","snapshot_observed_at":"2026-08-13T11:54:47.009806Z","submitted_at":"2025-09-02T16:13:29Z","title":"From Silent Signals to Natural Language: A Dual-Stage Transformer-LLM Approach","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-05T11:39:56.523465Z"},"links":{"cited_paper":"/paper/1904.13377","citing_paper":"/paper/2509.04507"},"observation_digest":"sha256:6aab8f31f6c78fff4d555c167a00b15bea6b5897e0c854332bb8c1e16678eeed","observation_id":"6ff11374-f745-4777-9b3b-f29fd2a75b74","resolution":{"observed_at":"2026-08-05T11:39:56.523465Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1904.13377","last_updated":"2019-05-03T14:00:16Z","snapshot_observed_at":"2026-08-14T16:39:11.834763Z","submitted_at":"2019-04-30T17:20:32Z","title":"Very Deep Self-Attention Networks for End-to-End Speech Recognition","version":2},"cited_work":{"arxiv_id":"1904.13377","doi":null,"metadata_source":"pith","pith_arxiv_id":"1904.13377","snapshot_observed_at":"2026-07-01T10:05:41.160122Z","title":"Very Deep Self-Attention Networks for End-to-End Speech Recognition","venue":"cs.CL","work_id":"12226a18-cb1d-4ea9-8467-6e721feddc2b","year":2019},"citing_paper":{"arxiv_id":"2606.31722","last_updated":"2026-06-30T14:23:49Z","snapshot_observed_at":"2026-08-13T02:50:40.933372Z","submitted_at":"2026-06-30T14:23:49Z","title":"Adapting Foundation ASR Models to Dysarthric Speech: A Case Study","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-07-01T05:52:02.121828Z"},"links":{"cited_paper":"/paper/1904.13377","citing_paper":"/paper/2606.31722"},"observation_digest":"sha256:2705c331f74afea7cd43f9c0fb24825405899feca43eed90f0dded201fe2a8c4","observation_id":"5c1a6edb-f924-4127-8618-9872a7f56a7d","resolution":{"observed_at":"2026-07-01T10:05:41.161352Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1904.13377","last_updated":"2019-05-03T14:00:16Z","snapshot_observed_at":"2026-08-14T16:39:11.834763Z","submitted_at":"2019-04-30T17:20:32Z","title":"Very Deep Self-Attention Networks for End-to-End Speech Recognition","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1904.13377","snapshot_observed_at":"2026-08-15T14:37:54.757887Z","title":"Very deep self-attention networks for end-to-end speech recognition,","venue":null,"work_id":null,"year":1904},"citing_paper":{"arxiv_id":"2608.05759","last_updated":"2026-08-06T08:45:33Z","snapshot_observed_at":"2026-08-15T14:32:38.243386Z","submitted_at":"2026-08-06T08:45:33Z","title":"How to Recognize New Words: A Comparison Between Context Biasing Methods and Speech LLMs","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T14:37:54.757887Z"},"links":{"cited_paper":"/paper/1904.13377","citing_paper":"/paper/2608.05759"},"observation_digest":"sha256:98a3a10eeb1a8a548464b2301dbd7ec14fb398b4358559d8da6d69dc88f7ec00","observation_id":"f83f31c8-b898-41b9-9946-fb80c9d7f038","resolution":{"observed_at":"2026-08-15T14:37:54.757887Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/1904.13377/citation-record","integrity":"/paper/1904.13377/integrity","json":"/paper/1904.13377/citation-record.json","paper":"/paper/1904.13377"},"outbound":[],"paper":{"arxiv_id":"1904.13377","last_updated":"2019-05-03T14:00:16Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-14T16:39:11.834763Z","submitted_at":"2019-04-30T17:20:32Z","title":"Very Deep Self-Attention Networks for End-to-End Speech Recognition"},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:1904.13377."}