{"as_of":"2026-08-09T12:49:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3ac58242cb70afb0a100b85c9d0c42e685224d4008e743c9cfb370770564c4e4","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":"2026-08-09T06:31:02.800959+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":"2026-08-07T11:58:41.805991Z","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":"2026-07-03T15:18:32.619358Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2110.10329","last_updated":"2021-10-20T00:59:36Z","snapshot_observed_at":"2026-07-06T11:59:43.025772Z","submitted_at":"2021-10-20T00:59:36Z","title":"SLAM: A Unified Encoder for Speech and Language Modeling via Speech-Text Joint Pre-Training","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.10329","snapshot_observed_at":"2026-08-07T11:58:41.805991Z","title":"Slam: A unified encoder for speech and language modeling via speech-text joint pre-training,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.06343","last_updated":"2025-06-01T09:27:55Z","snapshot_observed_at":"2026-08-09T06:02:47.435740Z","submitted_at":"2025-06-01T09:27:55Z","title":"TESU-LLM: Training Speech-LLMs Without Speech via Unified Encoder Alignment","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T11:58:41.805991Z"},"links":{"cited_paper":"/paper/2110.10329","citing_paper":"/paper/2506.06343"},"observation_digest":"sha256:29e600c553e778b275f097459ab3ba7cecd2ab3252960c93a4984bacd071dbf0","observation_id":"c6c26aea-4ace-4858-abee-3cebbce44cf4","resolution":{"observed_at":"2026-08-07T11:58:41.805991Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.10329","last_updated":"2021-10-20T00:59:36Z","snapshot_observed_at":"2026-07-06T11:59:43.025772Z","submitted_at":"2021-10-20T00:59:36Z","title":"SLAM: A Unified Encoder for Speech and Language Modeling via Speech-Text Joint Pre-Training","version":1},"cited_work":{"arxiv_id":"2110.10329","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2110.10329","snapshot_observed_at":"2026-07-03T15:18:32.619358Z","title":"SLAM: A unified encoder for speech and language modeling via speech-text joint pre-training","venue":null,"work_id":"92401e15-21d2-437c-ac24-312de8895112","year":2021},"citing_paper":{"arxiv_id":"2604.26514","last_updated":"2026-04-29T10:28:00Z","snapshot_observed_at":"2026-08-08T23:20:13.854522Z","submitted_at":"2026-04-29T10:28:00Z","title":"Text-Utilization for Encoder-dominated Speech Recognition Models","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-07T13:37:09.614784Z"},"links":{"cited_paper":"/paper/2110.10329","citing_paper":"/paper/2604.26514"},"observation_digest":"sha256:2bbd400a0d88a1c5199ee515dd9c7cad24710b50b7b6f852a2b41aa69cffcbff","observation_id":"056fd21f-1c73-4e5f-8554-548b3bc90d5b","resolution":{"observed_at":"2026-05-12T08:51:25.145646Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.10329","last_updated":"2021-10-20T00:59:36Z","snapshot_observed_at":"2026-07-06T11:59:43.025772Z","submitted_at":"2021-10-20T00:59:36Z","title":"SLAM: A Unified Encoder for Speech and Language Modeling via Speech-Text Joint Pre-Training","version":1},"cited_work":{"arxiv_id":"2110.10329","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2110.10329","snapshot_observed_at":"2026-07-03T15:18:32.619358Z","title":"SLAM: A unified encoder for speech and language modeling via speech-text joint pre-training","venue":null,"work_id":"92401e15-21d2-437c-ac24-312de8895112","year":2021},"citing_paper":{"arxiv_id":"2607.01733","last_updated":"2026-07-02T05:42:01Z","snapshot_observed_at":"2026-08-06T21:21:57.811880Z","submitted_at":"2026-07-02T05:42:01Z","title":"Rethinking Speech-LLM Integration for ASR: Effective Joint Speech-Text Training by Interleaving","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-07-03T15:17:52.966144Z"},"links":{"cited_paper":"/paper/2110.10329","citing_paper":"/paper/2607.01733"},"observation_digest":"sha256:dd5177e93b3867b2becd1c1c3bd24c3f0c553d3ed471d9a54a1e1534d3a67728","observation_id":"3a4a95b5-2717-4677-8651-6b50b3fe1c73","resolution":{"observed_at":"2026-07-03T15:18:32.621184Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2110.10329/citation-record","integrity":"/paper/2110.10329/integrity","json":"/paper/2110.10329/citation-record.json","paper":"/paper/2110.10329"},"outbound":[],"paper":{"arxiv_id":"2110.10329","last_updated":"2021-10-20T00:59:36Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T11:59:43.025772Z","submitted_at":"2021-10-20T00:59:36Z","title":"SLAM: A Unified Encoder for Speech and Language Modeling via Speech-Text Joint Pre-Training"},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2110.10329."}