{"as_of":"2026-08-16T15:57:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:7312693593f5474caa5f1dc585b5bb6a60381672bce03ab35db8a1ca32eb4c2c","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":"2026-08-16T06:30:59.297886+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":"2026-08-12T13:19:49.523451Z","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":"2026-08-13T19:09:43.772777Z","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":"2026-08-12T13:19:49.523451Z","title":"Layered gradient accumulation and mod- ular pipeline parallelism: fast and efficient training of large language models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.16341","last_updated":"2024-11-25T12:37:07Z","snapshot_observed_at":"2026-08-14T03:21:46.636781Z","submitted_at":"2024-11-25T12:37:07Z","title":"From CISC to RISC: language-model guided assembly transpilation","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-12T13:19:49.523451Z"},"links":{"cited_paper":"/paper/2106.02679","citing_paper":"/paper/2411.16341"},"observation_digest":"sha256:75473b187fd06f662e1d0badd7c9881c4d7dfc5f08d64e5c7bf47c0356fed04f","observation_id":"89e3eec5-d1fb-4e4f-8570-3e9efa26aa0f","resolution":{"observed_at":"2026-08-12T13:19:49.523451Z","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":"2026-08-13T19:09:43.772777Z","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":"2026-08-13T23:39:52.572536Z","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":"sha256:78074fe531fc1d1245c6319d9920e28b117811cf6e92c7cee3f1920d34dd06ed","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":"2026-08-13T19:09:43.772777Z","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":"2026-08-14T02:05:05.771247Z","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":"sha256:5072aef160015b83ec87921f2ecfc7dfd5c351cc9d5f8a774ba78a216d1bde3e","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":"2026-08-13T19:09:43.772777Z","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":"2026-08-11T13:32:02.008131Z","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":"sha256:83e7838d085d39b71a30a57db239d8b18f01007d86ddac2cc7abb07ef19d8b3e","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 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-13T19:09:43.772777Z","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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2106.02679."}