{"as_of":"2026-08-07T20:23:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0c6eebf580ddadf9cdc9de186d3c7b96e4c0c6818764384191e718e357a1cf5d","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":"2026-08-07T06:34:17.273281+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":"2026-08-07T12:27:29.799802Z","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":"2026-08-06T10:29:56.552302Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2504.04060","last_updated":"2025-04-22T07:59:31Z","snapshot_observed_at":"2026-08-07T16:08:27.561459Z","submitted_at":"2025-04-05T04:57:12Z","title":"VocalNet: Speech LLM with Multi-Token Prediction for Faster and High-Quality Generation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.04060","snapshot_observed_at":"2026-08-07T12:27:29.799802Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.24496","last_updated":"2025-05-30T11:47:29Z","snapshot_observed_at":"2026-08-07T12:18:03.337808Z","submitted_at":"2025-05-30T11:47:29Z","title":"Speech Token Prediction via Compressed-to-fine Language Modeling for Speech Generation","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T12:27:29.799802Z"},"links":{"cited_paper":"/paper/2504.04060","citing_paper":"/paper/2505.24496"},"observation_digest":"sha256:d79de8c7bf108f3e36a3d7998f7f2c61a464a1a9082ca86c69bc5dbeb2a284c6","observation_id":"4072c288-ec98-4003-8ff6-bdcc3fc82fba","resolution":{"observed_at":"2026-08-07T12:27:29.799802Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.04060","last_updated":"2025-04-22T07:59:31Z","snapshot_observed_at":"2026-08-07T16:08:27.561459Z","submitted_at":"2025-04-05T04:57:12Z","title":"VocalNet: Speech LLM with Multi-Token Prediction for Faster and High-Quality Generation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.04060","snapshot_observed_at":"2026-08-06T22:18:59.507675Z","title":"V ocalnet: Speech llm with multi-token prediction for faster and high-quality generation,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.22023","last_updated":"2025-06-27T08:45:21Z","snapshot_observed_at":"2026-08-07T19:17:21.433342Z","submitted_at":"2025-06-27T08:45:21Z","title":"Robust and Efficient Autoregressive Speech Synthesis with Dynamic Chunk-wise Prediction Policy","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T22:18:59.507675Z"},"links":{"cited_paper":"/paper/2504.04060","citing_paper":"/paper/2506.22023"},"observation_digest":"sha256:15b30053a9634fcf4aafc2a76efc21c07e861079432eac07ee56c8c7204b3889","observation_id":"7f734fbc-4e28-473c-b2b5-189bfff8215b","resolution":{"observed_at":"2026-08-06T22:18:59.507675Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.04060","last_updated":"2025-04-22T07:59:31Z","snapshot_observed_at":"2026-08-07T16:08:27.561459Z","submitted_at":"2025-04-05T04:57:12Z","title":"VocalNet: Speech LLM with Multi-Token Prediction for Faster and High-Quality Generation","version":2},"cited_work":{"arxiv_id":"2504.04060","doi":null,"metadata_source":"pith","pith_arxiv_id":"2504.04060","snapshot_observed_at":"2026-08-06T10:29:56.552302Z","title":"VocalNet: Speech LLM with Multi-Token Prediction for Faster and High-Quality Generation","venue":"cs.CL","work_id":"29a0e1a5-fb38-4afb-b440-862964f07d50","year":2025},"citing_paper":{"arxiv_id":"2507.23777","last_updated":"2025-08-06T09:51:03Z","snapshot_observed_at":"2026-08-07T07:56:49.904222Z","submitted_at":"2025-07-31T17:58:30Z","title":"XSpecMesh: Quality-Preserving Auto-Regressive Mesh Generation Acceleration via Multi-Head Speculative Decoding","version":2},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-06T10:29:56.297683Z"},"links":{"cited_paper":"/paper/2504.04060","citing_paper":"/paper/2507.23777"},"observation_digest":"sha256:4ab6c5170216f7e8d12e77e319973a35ba2d83eaedd9f537ffb50f7d546df4af","observation_id":"ede00025-69dd-4317-876d-fc3b252c5435","resolution":{"observed_at":"2026-08-06T10:29:56.559355Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2504.04060/citation-record","integrity":"/paper/2504.04060/integrity","json":"/paper/2504.04060/citation-record.json","paper":"/paper/2504.04060"},"outbound":[],"paper":{"arxiv_id":"2504.04060","last_updated":"2025-04-22T07:59:31Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-07T16:08:27.561459Z","submitted_at":"2025-04-05T04:57:12Z","title":"VocalNet: Speech LLM with Multi-Token Prediction for Faster and High-Quality Generation"},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2504.04060."}