{"as_of":"2026-08-10T02:32:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:cc9cf4f0d94639216b6cc33d66852c645bbd3f6b99212142024e62fe927ec833","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":"2026-08-09T06:31:02.800959+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":"2026-08-06T17:38:39.821748Z","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":"2026-05-11T22:26:13.229257Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2106.02679","last_updated":"2021-06-04T19:21:49Z","snapshot_observed_at":"2026-08-10T00:14:46.375458Z","submitted_at":"2021-06-04T19:21:49Z","title":"Layered gradient accumulation and modular pipeline parallelism: fast and efficient training of large language models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.02679","snapshot_observed_at":"2026-08-06T17:38:39.821748Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.10392","last_updated":"2025-07-14T15:31:31Z","snapshot_observed_at":"2026-08-08T17:39:46.075064Z","submitted_at":"2025-07-14T15:31:31Z","title":"Zorse: Optimizing LLM Training Efficiency on Heterogeneous GPU Clusters","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T17:38:39.821748Z"},"links":{"cited_paper":"/paper/2106.02679","citing_paper":"/paper/2507.10392"},"observation_digest":"sha256:bc07cc1d0c73489eb824b84983eedda88c01c81a7410d48ae4d7c6f148c9c633","observation_id":"7067a381-fa49-477c-a557-111d07697ab6","resolution":{"observed_at":"2026-08-06T17:38:39.821748Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.02679","last_updated":"2021-06-04T19:21:49Z","snapshot_observed_at":"2026-08-10T00:14:46.375458Z","submitted_at":"2021-06-04T19:21:49Z","title":"Layered gradient accumulation and modular pipeline parallelism: fast and efficient training of large language models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.02679","snapshot_observed_at":"2026-08-05T17:49:20.566377Z","title":"Layered gradient accumulation and modular pipeline parallelism: fast and efficient training of large language models,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.15883","last_updated":"2025-08-25T10:31:36Z","snapshot_observed_at":"2026-08-05T17:49:17.484619Z","submitted_at":"2025-08-21T16:24:24Z","title":"Beyond Imaging: Vision Transformer Digital Twin Surrogates for 3D+T Biological Tissue Dynamics","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-05T17:49:20.566377Z"},"links":{"cited_paper":"/paper/2106.02679","citing_paper":"/paper/2508.15883"},"observation_digest":"sha256:0ba3f4f118f3346e05f000d1aadd65792def286ee881691a9af3678efaf7268b","observation_id":"475ab001-acfd-43f3-877b-ae2d2fb196d6","resolution":{"observed_at":"2026-08-05T17:49:20.566377Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.02679","last_updated":"2021-06-04T19:21:49Z","snapshot_observed_at":"2026-08-10T00:14:46.375458Z","submitted_at":"2021-06-04T19:21:49Z","title":"Layered gradient accumulation and modular pipeline parallelism: fast and efficient training of large language models","version":1},"cited_work":{"arxiv_id":"2106.02679","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2106.02679","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"ba5b0dcc-8f20-492b-9a39-1afa019fd8b0","year":2021},"citing_paper":{"arxiv_id":"2604.24678","last_updated":"2026-04-27T16:38:01Z","snapshot_observed_at":"2026-07-06T23:10:38.548416Z","submitted_at":"2026-04-27T16:38:01Z","title":"Leveraging LLMs for Multi-File DSL Code Generation: An Industrial Case Study","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-08T02:49:14.533263Z"},"links":{"cited_paper":"/paper/2106.02679","citing_paper":"/paper/2604.24678"},"observation_digest":"sha256:0aee5650264409e1c6fe80a1a8ca05782bef4acc00a0c945a14e920a94a34318","observation_id":"3a3c3595-0ed5-496b-91c7-3b195963497d","resolution":{"observed_at":"2026-05-11T22:26:13.231081Z","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/2106.02679/citation-record","integrity":"/paper/2106.02679/integrity","json":"/paper/2106.02679/citation-record.json","paper":"/paper/2106.02679"},"outbound":[],"paper":{"arxiv_id":"2106.02679","last_updated":"2021-06-04T19:21:49Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-10T00:14:46.375458Z","submitted_at":"2021-06-04T19:21:49Z","title":"Layered gradient accumulation and modular pipeline parallelism: fast and efficient training of large 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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2106.02679."}