{"as_of":"2026-08-08T22:06:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6b174a9d21f486387e9afaedfd612243ad542be9fe9349a922b33fc5a4d110fc","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":"2026-08-08T06:32:00.761636+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":"2026-08-07T14:49:47.428543Z","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":"2026-07-04T01:29:22.085242Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2204.03067","last_updated":"2022-07-04T16:36:54Z","snapshot_observed_at":"2026-08-05T23:55:15.838693Z","submitted_at":"2022-04-06T20:03:38Z","title":"ByT5 model for massively multilingual grapheme-to-phoneme conversion","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.03067","snapshot_observed_at":"2026-08-07T14:49:47.428543Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.17513","last_updated":"2025-05-23T06:06:37Z","snapshot_observed_at":"2026-08-08T00:52:13.840507Z","submitted_at":"2025-05-23T06:06:37Z","title":"What You Read Isn't What You Hear: Linguistic Sensitivity in Deepfake Speech Detection","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-07T14:49:47.428543Z"},"links":{"cited_paper":"/paper/2204.03067","citing_paper":"/paper/2505.17513"},"observation_digest":"sha256:2fe31ca27436c086416e49bf7a13f8fcf8ae21179ae36c355717fccebc87884a","observation_id":"c497e06a-8009-4f63-a16e-29e8494a4551","resolution":{"observed_at":"2026-08-07T14:49:47.428543Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2204.03067","last_updated":"2022-07-04T16:36:54Z","snapshot_observed_at":"2026-08-05T23:55:15.838693Z","submitted_at":"2022-04-06T20:03:38Z","title":"ByT5 model for massively multilingual grapheme-to-phoneme conversion","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.03067","snapshot_observed_at":"2026-08-07T00:58:18.179144Z","title":"The North Wind and the Sun","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.12311","last_updated":"2026-07-02T10:04:54Z","snapshot_observed_at":"2026-08-08T04:31:19.593177Z","submitted_at":"2025-06-14T02:16:38Z","title":"Phonikud: Overcoming Phonetic Underspecification for Hebrew Text-To-Speech","version":4},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:18.179144Z"},"links":{"cited_paper":"/paper/2204.03067","citing_paper":"/paper/2506.12311"},"observation_digest":"sha256:aeafa80f7d8618f1ddf8ee0ac7b0714f6ff0a1163382fe1b67974d201722da4e","observation_id":"24669fea-f05d-46e3-a985-ac10934b55bb","resolution":{"observed_at":"2026-08-07T00:58:18.179144Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2204.03067","last_updated":"2022-07-04T16:36:54Z","snapshot_observed_at":"2026-08-05T23:55:15.838693Z","submitted_at":"2022-04-06T20:03:38Z","title":"ByT5 model for massively multilingual grapheme-to-phoneme conversion","version":2},"cited_work":{"arxiv_id":"2204.03067","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2204.03067","snapshot_observed_at":"2026-07-04T01:29:22.085242Z","title":"Byt5 model for massively multilingual grapheme-to-phoneme conversion,","venue":null,"work_id":"8b612acd-65d5-46c9-a510-f5efd44a26e2","year":2022},"citing_paper":{"arxiv_id":"2607.01238","last_updated":"2026-05-01T17:46:18Z","snapshot_observed_at":"2026-08-07T08:40:29.704088Z","submitted_at":"2026-05-01T17:46:18Z","title":"SPARCLE: SPeaker-aware Aligned Representations via Contrastive Language Embeddings","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-07-04T01:21:02.597103Z"},"links":{"cited_paper":"/paper/2204.03067","citing_paper":"/paper/2607.01238"},"observation_digest":"sha256:3fc636920cbe1ffd3da9aa70d7c5dae0f28e9887e14b7865c250fd87abac09c5","observation_id":"9ff03490-0720-4192-9179-fdc6a806758c","resolution":{"observed_at":"2026-07-04T01:29:22.086768Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2204.03067","last_updated":"2022-07-04T16:36:54Z","snapshot_observed_at":"2026-08-05T23:55:15.838693Z","submitted_at":"2022-04-06T20:03:38Z","title":"ByT5 model for massively multilingual grapheme-to-phoneme conversion","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.03067","snapshot_observed_at":"2026-07-31T23:18:49.538974Z","title":"URL https://arxiv","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24030","last_updated":"2026-07-27T05:55:50Z","snapshot_observed_at":"2026-08-07T09:50:33.541075Z","submitted_at":"2026-07-27T05:55:50Z","title":"MoLGE: Mixture of Language Group Experts for Efficient Scaling of Massively Multilingual Speech Recognition","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-07-31T23:18:49.538974Z"},"links":{"cited_paper":"/paper/2204.03067","citing_paper":"/paper/2607.24030"},"observation_digest":"sha256:ac83f5b637c2c286859a9a7d6fcc0e2f12a42af8e090a2ab13e7c066e562cb4d","observation_id":"33bdb0ee-20e6-47ea-b1a1-646a1d566f5e","resolution":{"observed_at":"2026-07-31T23:18:49.538974Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2204.03067/citation-record","integrity":"/paper/2204.03067/integrity","json":"/paper/2204.03067/citation-record.json","paper":"/paper/2204.03067"},"outbound":[],"paper":{"arxiv_id":"2204.03067","last_updated":"2022-07-04T16:36:54Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-05T23:55:15.838693Z","submitted_at":"2022-04-06T20:03:38Z","title":"ByT5 model for massively multilingual grapheme-to-phoneme conversion"},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2204.03067."}