{"as_of":"2026-08-18T10:10:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2e79299e5a42acb42080f0c9db991ac23afe643b318ae81e7241c1ee8a335a95","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":"2026-08-18T06:34:40.430872+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":"2026-08-10T15:57:42.507832Z","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":"2026-07-08T07:34:43.100777Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2101.00387","last_updated":"2021-07-12T22:46:37Z","snapshot_observed_at":"2026-08-16T18:54:42.322126Z","submitted_at":"2021-01-02T06:29:12Z","title":"What all do audio transformer models hear? Probing Acoustic Representations for Language Delivery and its Structure","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.00387","snapshot_observed_at":"2026-08-10T15:57:42.507832Z","title":"What all do audio transformer models hear? probing acoustic representations for language delivery and its structure,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.13497","last_updated":"2025-01-23T09:25:31Z","snapshot_observed_at":"2026-08-15T14:24:11.716152Z","submitted_at":"2025-01-23T09:25:31Z","title":"DQ-Data2vec: Decoupling Quantization for Multilingual Speech Recognition","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-10T15:57:42.507832Z"},"links":{"cited_paper":"/paper/2101.00387","citing_paper":"/paper/2501.13497"},"observation_digest":"sha256:1d970af99a392a3c787861bcfa8784e03ee8cb1099664899a537d2ffad32bc99","observation_id":"1d506e3c-8735-4ad5-a59d-a7a2205dbe7b","resolution":{"observed_at":"2026-08-10T15:57:42.507832Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2101.00387","last_updated":"2021-07-12T22:46:37Z","snapshot_observed_at":"2026-08-16T18:54:42.322126Z","submitted_at":"2021-01-02T06:29:12Z","title":"What all do audio transformer models hear? Probing Acoustic Representations for Language Delivery and its Structure","version":2},"cited_work":{"arxiv_id":"2101.00387","doi":null,"metadata_source":"pith","pith_arxiv_id":"2101.00387","snapshot_observed_at":"2026-07-08T07:34:43.100777Z","title":"What all do audio transformer models hear? probing acoustic rep- resentations for language delivery and its structure","venue":"cs.CL","work_id":"2dd54a11-e44d-4b89-913f-ca5c09c31009","year":2021},"citing_paper":{"arxiv_id":"2509.15151","last_updated":"2026-05-21T10:15:02Z","snapshot_observed_at":"2026-08-15T07:50:51.074417Z","submitted_at":"2025-09-18T16:57:08Z","title":"Exploring How Audio Effects Alter Emotion with Foundation Models","version":4},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-22T12:34:31.239629Z"},"links":{"cited_paper":"/paper/2101.00387","citing_paper":"/paper/2509.15151"},"observation_digest":"sha256:240936ce47241382a019f43ebd79a854403c7295c30e70d6430fdcbff795756b","observation_id":"8e3f5882-bee8-4822-b5dd-cddf9f77fc25","resolution":{"observed_at":"2026-05-22T12:34:52.399917Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2101.00387","last_updated":"2021-07-12T22:46:37Z","snapshot_observed_at":"2026-08-16T18:54:42.322126Z","submitted_at":"2021-01-02T06:29:12Z","title":"What all do audio transformer models hear? Probing Acoustic Representations for Language Delivery and its Structure","version":2},"cited_work":{"arxiv_id":"2101.00387","doi":null,"metadata_source":"pith","pith_arxiv_id":"2101.00387","snapshot_observed_at":"2026-07-08T07:34:43.100777Z","title":"What all do audio transformer models hear? probing acoustic rep- resentations for language delivery and its structure","venue":"cs.CL","work_id":"2dd54a11-e44d-4b89-913f-ca5c09c31009","year":2021},"citing_paper":{"arxiv_id":"2607.06392","last_updated":"2026-07-07T15:25:47Z","snapshot_observed_at":"2026-08-17T20:01:50.771212Z","submitted_at":"2026-07-07T15:25:47Z","title":"InsideSSL: Understanding Self-Supervised Speech Representations using a Model-Centric Perspective","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-07-08T07:33:22.898615Z"},"links":{"cited_paper":"/paper/2101.00387","citing_paper":"/paper/2607.06392"},"observation_digest":"sha256:263be581b533d77f9f31f067573943ea40efafa9001ef0e352208e4d0d1ca6ec","observation_id":"36d8a162-c6e8-4401-98cf-c998e26c91d3","resolution":{"observed_at":"2026-07-08T07:34:43.103019Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2101.00387/citation-record","integrity":"/paper/2101.00387/integrity","json":"/paper/2101.00387/citation-record.json","paper":"/paper/2101.00387"},"outbound":[],"paper":{"arxiv_id":"2101.00387","last_updated":"2021-07-12T22:46:37Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-16T18:54:42.322126Z","submitted_at":"2021-01-02T06:29:12Z","title":"What all do audio transformer models hear? Probing Acoustic Representations for Language Delivery and its Structure"},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2101.00387."}