{"as_of":"2026-08-09T18:49:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3b6be49930be6da93ab7f59e52904e7353756936fbd3967aacaddf68a7153d46","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":"2026-08-09T06:31:02.800959+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":"2026-08-08T15:04:29.503731Z","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":"2026-07-01T11:45:47.239641Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2504.10344","last_updated":"2025-04-14T15:51:56Z","snapshot_observed_at":"2026-08-07T16:05:50.273054Z","submitted_at":"2025-04-14T15:51:56Z","title":"ALMTokenizer: A Low-bitrate and Semantic-rich Audio Codec Tokenizer for Audio Language Modeling","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.10344","snapshot_observed_at":"2026-08-08T15:04:29.503731Z","title":"Almtokenizer: A low-bitrate and semantic-rich audio codec tokenizer for audio language modeling,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2502.06604","last_updated":"2025-05-16T03:43:21Z","snapshot_observed_at":"2026-08-09T14:54:34.308877Z","submitted_at":"2025-02-10T16:01:55Z","title":"Do we really have to filter out random noise in pre-training data for language models?","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-08T15:04:29.503731Z"},"links":{"cited_paper":"/paper/2504.10344","citing_paper":"/paper/2502.06604"},"observation_digest":"sha256:dc269a0a36a82ad29dc098c3b093b0e2e92130ed1e191ed6be4498312ac3c1db","observation_id":"5bea82d2-a5dc-4f64-9633-aade6bdb05c6","resolution":{"observed_at":"2026-08-08T15:04:29.503731Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.10344","last_updated":"2025-04-14T15:51:56Z","snapshot_observed_at":"2026-08-07T16:05:50.273054Z","submitted_at":"2025-04-14T15:51:56Z","title":"ALMTokenizer: A Low-bitrate and Semantic-rich Audio Codec Tokenizer for Audio Language Modeling","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.10344","snapshot_observed_at":"2026-08-05T16:46:49.260250Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.17863","last_updated":"2025-08-25T10:16:07Z","snapshot_observed_at":"2026-08-08T02:19:42.525581Z","submitted_at":"2025-08-25T10:16:07Z","title":"Speech Discrete Tokens or Continuous Features? A Comparative Analysis for Spoken Language Understanding in SpeechLLMs","version":1},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-05T16:46:49.260250Z"},"links":{"cited_paper":"/paper/2504.10344","citing_paper":"/paper/2508.17863"},"observation_digest":"sha256:241f02301b99849fadbae41034c37aa140ff89281437a49ff896331c47201e87","observation_id":"edfe98b9-dc87-4e50-9f77-c65c579c2dbf","resolution":{"observed_at":"2026-08-05T16:46:49.260250Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.10344","last_updated":"2025-04-14T15:51:56Z","snapshot_observed_at":"2026-08-07T16:05:50.273054Z","submitted_at":"2025-04-14T15:51:56Z","title":"ALMTokenizer: A Low-bitrate and Semantic-rich Audio Codec Tokenizer for Audio Language Modeling","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.10344","snapshot_observed_at":"2026-08-05T11:41:03.148013Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.02349","last_updated":"2025-09-04T14:25:57Z","snapshot_observed_at":"2026-08-09T00:24:32.254551Z","submitted_at":"2025-09-02T14:15:22Z","title":"AudioCodecBench: A Comprehensive Benchmark for Audio Codec Evaluation","version":2},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-05T11:41:03.148013Z"},"links":{"cited_paper":"/paper/2504.10344","citing_paper":"/paper/2509.02349"},"observation_digest":"sha256:a07c78d727c0353c2081bf797456d62ca0ff976a9c096af3b999fc8dc3c9e744","observation_id":"b8e10872-b9b5-478e-acec-aa350f22d77d","resolution":{"observed_at":"2026-08-05T11:41:03.148013Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.10344","last_updated":"2025-04-14T15:51:56Z","snapshot_observed_at":"2026-08-07T16:05:50.273054Z","submitted_at":"2025-04-14T15:51:56Z","title":"ALMTokenizer: A Low-bitrate and Semantic-rich Audio Codec Tokenizer for Audio Language Modeling","version":1},"cited_work":{"arxiv_id":"2504.10344","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2504.10344","snapshot_observed_at":"2026-07-01T11:45:47.239641Z","title":"arXiv preprint arXiv:2504.10344 , year=","venue":null,"work_id":"40cc0490-131b-43e6-b051-7fa4bffdaf76","year":null},"citing_paper":{"arxiv_id":"2606.31247","last_updated":"2026-06-30T07:24:10Z","snapshot_observed_at":"2026-07-07T00:04:58.486133Z","submitted_at":"2026-06-30T07:24:10Z","title":"FlexiSLM: A Dynamic and Controllable Frame Rate Spoken Language Model","version":1},"reference_index":252,"source":"arxiv_source","source_observed_at":"2026-07-01T03:50:26.873406Z"},"links":{"cited_paper":"/paper/2504.10344","citing_paper":"/paper/2606.31247"},"observation_digest":"sha256:f7aa56657bfc6eb0f28c54bce6ae78cab14970f50472283d2573e8a69c2d0a9f","observation_id":"8052c5cc-8fe5-4a97-a993-19fc3d8498e5","resolution":{"observed_at":"2026-07-01T11:45:47.240918Z","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/2504.10344/citation-record","integrity":"/paper/2504.10344/integrity","json":"/paper/2504.10344/citation-record.json","paper":"/paper/2504.10344"},"outbound":[],"paper":{"arxiv_id":"2504.10344","last_updated":"2025-04-14T15:51:56Z","latest_version":1,"primary_category":"cs.SD","snapshot_observed_at":"2026-08-07T16:05:50.273054Z","submitted_at":"2025-04-14T15:51:56Z","title":"ALMTokenizer: A Low-bitrate and Semantic-rich Audio Codec Tokenizer for Audio Language Modeling"},"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 4 inbound Pith citation observations for arXiv:2504.10344."}