{"as_of":"2026-08-10T14:55:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e05739721b327ab3e4d21e24ce4e345576d0270244f682d020b9807b59adcf31","coverage":[{"denominator":3,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-29T06:02:07.932691Z","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":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-03T10:13:57.787394Z","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":"2605.29209","last_updated":"2026-05-28T00:42:45Z","snapshot_observed_at":"2026-08-03T17:19:06.252921Z","submitted_at":"2026-05-28T00:42:45Z","title":"The WER Trap: Shattering the Illusion of Unified Tokens in Speech Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2605.29209","snapshot_observed_at":"2026-08-03T10:13:57.787394Z","title":"arXiv preprint arXiv:2605.29209 (2026)","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.29279","last_updated":"2026-07-31T10:50:14Z","snapshot_observed_at":"2026-08-06T04:02:53.771607Z","submitted_at":"2026-07-31T10:50:14Z","title":"ParaASR: Multi-Token Prediction for Fast and Long-Context LLM-Based Speech Recognition","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-03T10:13:57.787394Z"},"links":{"cited_paper":"/paper/2605.29209","citing_paper":"/paper/2607.29279"},"observation_digest":"sha256:ea86fd4f513a7977152c551c8a93a5bf401d82b8968d671e4375a9458fc09127","observation_id":"92418081-62ad-4080-9924-bd5911203b0b","resolution":{"observed_at":"2026-08-03T10:13:57.787394Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2605.29209/citation-record","integrity":"/paper/2605.29209/integrity","json":"/paper/2605.29209/citation-record.json","paper":"/paper/2605.29209"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2410.19168","last_updated":"2024-10-24T21:20:10Z","snapshot_observed_at":"2026-07-06T19:39:23.839070Z","submitted_at":"2024-10-24T21:20:10Z","title":"MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmark","version":1},"cited_work":{"arxiv_id":"2410.19168","doi":"10.48550/arxiv.2410.19168","metadata_source":"pith","pith_arxiv_id":"2410.19168","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmark","venue":"eess.AS","work_id":"e60f85db-636c-4830-af85-5d31ebc74a1b","year":2024},"citing_paper":{"arxiv_id":"2605.29209","last_updated":"2026-05-28T00:42:45Z","snapshot_observed_at":"2026-08-03T17:19:06.252921Z","submitted_at":"2026-05-28T00:42:45Z","title":"The WER Trap: Shattering the Illusion of Unified Tokens in Speech Language Models","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-06-29T06:02:07.932691Z"},"links":{"cited_paper":"/paper/2410.19168","citing_paper":"/paper/2605.29209"},"observation_digest":"sha256:099162c8dfd792f4df1499680dc51bcf713f3faf7fe549571416c52cb9b7d842","observation_id":"5f8f2a8e-d722-4b33-879c-17de4a9412ca","resolution":{"observed_at":"2026-06-29T06:03:08.411387Z","resolver_source":"local_arxiv","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"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2511.15848","doi":"10.48550/arxiv.2511.15848","metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Step-audio-r1 technical report","venue":"arXiv (Cornell University)","work_id":"80b24600-9960-4df9-97b2-66714cfd73f5","year":2025},"citing_paper":{"arxiv_id":"2605.29209","last_updated":"2026-05-28T00:42:45Z","snapshot_observed_at":"2026-08-03T17:19:06.252921Z","submitted_at":"2026-05-28T00:42:45Z","title":"The WER Trap: Shattering the Illusion of Unified Tokens in Speech Language Models","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-06-29T06:02:07.932691Z"},"links":{"citing_paper":"/paper/2605.29209"},"observation_digest":"sha256:061ce018c282fc36f6c4324c926b5c12794d0cd0a3d83d6202959d714ea44866","observation_id":"540b4a8b-dd47-466f-b4b3-ec4f989f556b","resolution":{"observed_at":"2026-06-29T06:03:08.408192Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"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"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T06:02:07.932691Z","title":"Tokenizer Backbone.Both the encoder and decoder utilize a robust Transformer architecture: • Encoder:32 layers, 20 attention heads, 1280 hidden dimension, and 5120 linear units","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2605.29209","last_updated":"2026-05-28T00:42:45Z","snapshot_observed_at":"2026-08-03T17:19:06.252921Z","submitted_at":"2026-05-28T00:42:45Z","title":"The WER Trap: Shattering the Illusion of Unified Tokens in Speech Language Models","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-06-29T06:02:07.932691Z"},"links":{"citing_paper":"/paper/2605.29209"},"observation_digest":"sha256:b6a22b698521db272c7bdd75c52f809f9725587865db395fb9944f1123738f26","observation_id":"dc72c124-18db-419a-80a7-5dd153362632","resolution":{"observed_at":"2026-06-29T06:02:07.932691Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2605.29209","last_updated":"2026-05-28T00:42:45Z","latest_version":1,"primary_category":"eess.AS","snapshot_observed_at":"2026-08-03T17:19:06.252921Z","submitted_at":"2026-05-28T00:42:45Z","title":"The WER Trap: Shattering the Illusion of Unified Tokens in Speech Language Models"},"reference_resolution":{"displayed":3,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":1,"verified_exact":1,"verified_fuzzy":0},"total_outbound_references":3},"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 3 of 3 outbound references and 1 inbound Pith citation observation for arXiv:2605.29209."}