{"as_of":"2026-08-08T01:30:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c1f81eb2dde1680eab7be5cf4d018f691ddd271cdc8650fb56c8208176dec8a7","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":"2026-08-07T06:34:17.273281+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":"2026-08-06T20:46:22.667588Z","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":"2026-05-11T03:40:54.087627Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2311.07052","last_updated":"2025-07-30T16:00:53Z","snapshot_observed_at":"2026-07-06T16:46:22.210429Z","submitted_at":"2023-11-13T03:36:18Z","title":"Towards the Law of Capacity Gap in Distilling Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.07052","snapshot_observed_at":"2026-08-06T20:46:22.667588Z","title":"Towards the law of capacity gap in distilling language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.01887","last_updated":"2025-07-02T16:57:01Z","snapshot_observed_at":"2026-08-08T01:13:17.444788Z","submitted_at":"2025-07-02T16:57:01Z","title":"MiCoTA: Bridging the Learnability Gap with Intermediate CoT and Teacher Assistants","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-06T20:46:22.667588Z"},"links":{"cited_paper":"/paper/2311.07052","citing_paper":"/paper/2507.01887"},"observation_digest":"sha256:a87d8bd03702fb08367ad5fc22a822e518fc4b878cbd61038f9cd434877a104b","observation_id":"86cc947f-b70f-499a-b37b-03d8964ea01b","resolution":{"observed_at":"2026-08-06T20:46:22.667588Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.07052","last_updated":"2025-07-30T16:00:53Z","snapshot_observed_at":"2026-07-06T16:46:22.210429Z","submitted_at":"2023-11-13T03:36:18Z","title":"Towards the Law of Capacity Gap in Distilling Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.07052","snapshot_observed_at":"2026-08-06T17:33:21.728998Z","title":"Towards the law of capacity gap in distilling language models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.14204","last_updated":"2025-07-14T19:09:57Z","snapshot_observed_at":"2026-08-07T13:12:08.750150Z","submitted_at":"2025-07-14T19:09:57Z","title":"LaCache: Ladder-Shaped KV Caching for Efficient Long-Context Modeling of Large Language Models","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T17:33:21.728998Z"},"links":{"cited_paper":"/paper/2311.07052","citing_paper":"/paper/2507.14204"},"observation_digest":"sha256:338b423130a57b2ee260d576ab11a645cc633a3aefd67b3435fdcf3932eea60d","observation_id":"87f807c1-457c-494f-bc19-22a74724ebdf","resolution":{"observed_at":"2026-08-06T17:33:21.728998Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.07052","last_updated":"2025-07-30T16:00:53Z","snapshot_observed_at":"2026-07-06T16:46:22.210429Z","submitted_at":"2023-11-13T03:36:18Z","title":"Towards the Law of Capacity Gap in Distilling Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.07052","snapshot_observed_at":"2026-08-05T12:25:28.503732Z","title":"Towards the law of capacity gap in distilling language models, 2024 a","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.01649","last_updated":"2025-09-01T17:49:14Z","snapshot_observed_at":"2026-08-06T06:09:22.875234Z","submitted_at":"2025-09-01T17:49:14Z","title":"Distilled Pretraining: A modern lens of Data, In-Context Learning and Test-Time Scaling","version":1},"reference_index":67,"source":"arxiv_source","source_observed_at":"2026-08-05T12:25:28.503732Z"},"links":{"cited_paper":"/paper/2311.07052","citing_paper":"/paper/2509.01649"},"observation_digest":"sha256:6d087f3fe7b4a5a0a3fee2018c5aea2a3046cf50f65d23128ee3a3bfbc731fa8","observation_id":"520022cd-cc73-4caa-9412-06279f1c3ca1","resolution":{"observed_at":"2026-08-05T12:25:28.503732Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.07052","last_updated":"2025-07-30T16:00:53Z","snapshot_observed_at":"2026-07-06T16:46:22.210429Z","submitted_at":"2023-11-13T03:36:18Z","title":"Towards the Law of Capacity Gap in Distilling Language Models","version":4},"cited_work":{"arxiv_id":"2311.07052","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2311.07052","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Towards the law of capacity gap in distilling language models","venue":null,"work_id":"e13e780c-f3d5-4494-bdd8-d2418aa77e2f","year":2023},"citing_paper":{"arxiv_id":"2605.07783","last_updated":"2026-05-08T14:21:05Z","snapshot_observed_at":"2026-07-06T23:20:06.574823Z","submitted_at":"2026-05-08T14:21:05Z","title":"Chain-based Distillation for Effective Initialization of Variable-Sized Small Language Models","version":1},"reference_index":110,"source":"arxiv_source","source_observed_at":"2026-05-11T03:31:33.964471Z"},"links":{"cited_paper":"/paper/2311.07052","citing_paper":"/paper/2605.07783"},"observation_digest":"sha256:53dc2b636db990e357495bb3c4af2a6682b1781ef6163d25f2118f30c9bc1c7c","observation_id":"bb62f985-bdf6-45bf-871a-175617111acf","resolution":{"observed_at":"2026-05-11T03:40:54.089255Z","resolver_source":"arxiv_id","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/2311.07052/citation-record","integrity":"/paper/2311.07052/integrity","json":"/paper/2311.07052/citation-record.json","paper":"/paper/2311.07052"},"outbound":[],"paper":{"arxiv_id":"2311.07052","last_updated":"2025-07-30T16:00:53Z","latest_version":4,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T16:46:22.210429Z","submitted_at":"2023-11-13T03:36:18Z","title":"Towards the Law of Capacity Gap in Distilling Language Models"},"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 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2311.07052."}