{"as_of":"2026-08-14T10:19:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5e6c92873509d41802f89f61fe8bf8f40b71fc8323a89d0bc01217c877401016","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":"2026-08-14T06:32:32.682623+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":"2026-08-12T12:45:20.140755Z","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":"2026-08-05T13:12:14.954784Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2106.01023","last_updated":"2021-06-02T08:42:33Z","snapshot_observed_at":"2026-08-13T19:12:00.633466Z","submitted_at":"2021-06-02T08:42:33Z","title":"One Teacher is Enough? Pre-trained Language Model Distillation from Multiple Teachers","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.01023","snapshot_observed_at":"2026-08-12T12:45:20.140755Z","title":"One teacher is enough? pre-trained language model distillation from multiple teachers","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.16991","last_updated":"2024-11-25T23:37:48Z","snapshot_observed_at":"2026-08-14T09:19:58.622460Z","submitted_at":"2024-11-25T23:37:48Z","title":"Dynamic Self-Distillation via Previous Mini-batches for Fine-tuning Small Language Models","version":1},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-12T12:45:20.140755Z"},"links":{"cited_paper":"/paper/2106.01023","citing_paper":"/paper/2411.16991"},"observation_digest":"sha256:8144364952a05301113897209545a4980e5bc489c90c365520cdb60c50fb3326","observation_id":"22f5248d-ac3c-449a-8b1f-7997f5b05802","resolution":{"observed_at":"2026-08-12T12:45:20.140755Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.01023","last_updated":"2021-06-02T08:42:33Z","snapshot_observed_at":"2026-08-13T19:12:00.633466Z","submitted_at":"2021-06-02T08:42:33Z","title":"One Teacher is Enough? Pre-trained Language Model Distillation from Multiple Teachers","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.01023","snapshot_observed_at":"2026-08-07T05:44:36.012650Z","title":"One teacher is enough? pre- trained language model distillation from multiple teachers,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.07237","last_updated":"2025-06-11T17:28:22Z","snapshot_observed_at":"2026-08-10T08:31:33.686868Z","submitted_at":"2025-06-08T17:45:46Z","title":"Multi-Distillation from Speech and Music Representation Models","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:36.012650Z"},"links":{"cited_paper":"/paper/2106.01023","citing_paper":"/paper/2506.07237"},"observation_digest":"sha256:881c78e124f1f698970372836540160b55bc99f719ed3685af17a0fc27082eb5","observation_id":"a255aba1-da9b-42b0-b42d-4e76689a877d","resolution":{"observed_at":"2026-08-07T05:44:36.012650Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.01023","last_updated":"2021-06-02T08:42:33Z","snapshot_observed_at":"2026-08-13T19:12:00.633466Z","submitted_at":"2021-06-02T08:42:33Z","title":"One Teacher is Enough? Pre-trained Language Model Distillation from Multiple Teachers","version":1},"cited_work":{"arxiv_id":"2106.01023","doi":null,"metadata_source":"pith","pith_arxiv_id":"2106.01023","snapshot_observed_at":"2026-08-05T13:12:14.954784Z","title":"One Teacher is Enough? Pre-trained Language Model Distillation from Multiple Teachers","venue":"cs.CL","work_id":"f8948d50-2cac-4b55-bd38-5a41cf6698a1","year":2021},"citing_paper":{"arxiv_id":"2509.00914","last_updated":"2025-08-31T15:57:13Z","snapshot_observed_at":"2026-08-13T09:46:11.040599Z","submitted_at":"2025-08-31T15:57:13Z","title":"TinyMusician: On-Device Music Generation with Knowledge Distillation and Mixed Precision Quantization","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:14.589072Z"},"links":{"cited_paper":"/paper/2106.01023","citing_paper":"/paper/2509.00914"},"observation_digest":"sha256:143e3e23bc43907bc29f71279d2e539c096e420443ed080d90e5c52a9347ea1a","observation_id":"d50a9689-5cfd-447e-8fab-41b96dfe43ee","resolution":{"observed_at":"2026-08-05T13:12:14.960588Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2106.01023/citation-record","integrity":"/paper/2106.01023/integrity","json":"/paper/2106.01023/citation-record.json","paper":"/paper/2106.01023"},"outbound":[],"paper":{"arxiv_id":"2106.01023","last_updated":"2021-06-02T08:42:33Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-13T19:12:00.633466Z","submitted_at":"2021-06-02T08:42:33Z","title":"One Teacher is Enough? Pre-trained Language Model Distillation from Multiple Teachers"},"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":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"As of 14 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2106.01023."}