{"as_of":"2026-08-10T06:15:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:bd4b980015ef5ec3e43f84fc2d024471058bba0f92d546549b7a7e3c463206ce","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":2,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":2,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T15:19:26.765813Z","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":"2026-05-22T21:15:09.614618Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2108.06084","last_updated":"2022-10-16T08:42:29Z","snapshot_observed_at":"2026-07-06T11:38:02.479171Z","submitted_at":"2021-08-13T06:32:53Z","title":"The Stability-Efficiency Dilemma: Investigating Sequence Length Warmup for Training GPT Models","version":4},"cited_work":{"arxiv_id":"2108.06084","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2108.06084","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"The stability-efficiency dilemma: Investigating sequence length warmup for training gpt models","venue":null,"work_id":"94f0205b-f508-4ff3-b7b1-3e0f6a7851fe","year":2022},"citing_paper":{"arxiv_id":"2504.09844","last_updated":"2026-04-27T14:30:20Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-04-14T03:31:22Z","title":"MegaScale-Data: Scaling Dataloader for Multisource Large Foundation Model Training","version":4},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-05-22T21:12:22.201810Z"},"links":{"cited_paper":"/paper/2108.06084","citing_paper":"/paper/2504.09844"},"observation_digest":"sha256:7c6cb698bf7f02f47486fc9ba29e7b531100a1ba9b0f61c41c596ad22184038b","observation_id":"75d63b07-ed97-4d91-b8e8-87f72239ce93","resolution":{"observed_at":"2026-05-22T21:15:09.617034Z","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"}},{"citation":{"cited_paper":{"arxiv_id":"2108.06084","last_updated":"2022-10-16T08:42:29Z","snapshot_observed_at":"2026-07-06T11:38:02.479171Z","submitted_at":"2021-08-13T06:32:53Z","title":"The Stability-Efficiency Dilemma: Investigating Sequence Length Warmup for Training GPT Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.06084","snapshot_observed_at":"2026-08-07T15:19:26.765813Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.15548","last_updated":"2026-07-28T05:39:01Z","snapshot_observed_at":"2026-08-10T01:36:17.402059Z","submitted_at":"2025-05-21T14:12:30Z","title":"Dense Local Dependencies Induce Attention-Logit Explosion and Training Instability During Long-Sequence Transformer Training","version":2},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-07T15:19:26.765813Z"},"links":{"cited_paper":"/paper/2108.06084","citing_paper":"/paper/2505.15548"},"observation_digest":"sha256:0335df28fd6bd059f70c1b75c1eae2586073cbc20082254d3b78e0e9141c8c15","observation_id":"760a3f7b-41bf-4277-b85a-4857b90daf43","resolution":{"observed_at":"2026-08-07T15:19:26.765813Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2108.06084/citation-record","integrity":"/paper/2108.06084/integrity","json":"/paper/2108.06084/citation-record.json","paper":"/paper/2108.06084"},"outbound":[],"paper":{"arxiv_id":"2108.06084","last_updated":"2022-10-16T08:42:29Z","latest_version":4,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T11:38:02.479171Z","submitted_at":"2021-08-13T06:32:53Z","title":"The Stability-Efficiency Dilemma: Investigating Sequence Length Warmup for Training GPT 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 2 inbound Pith citation observations for arXiv:2108.06084."}