{"as_of":"2026-08-10T17:06:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2edd8498c11ce00647c7d2b142cd4660a1f59f83546269f4b8ba200b6eaa710c","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":"2026-08-10T06:31:04.303077+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":"2026-08-07T15:19:27.943988Z","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":"2026-05-12T07:16:28.922444Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2502.11034","last_updated":"2026-07-19T05:20:00Z","snapshot_observed_at":"2026-08-07T18:15:05.425576Z","submitted_at":"2025-02-16T08:13:23Z","title":"AdaGC: Enhancing LLM Pretraining Stability via Adaptive Gradient Clipping","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.11034","snapshot_observed_at":"2026-08-07T15:19:27.943988Z","title":null,"venue":null,"work_id":null,"year":2025},"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":32,"source":"arxiv_source","source_observed_at":"2026-08-07T15:19:27.943988Z"},"links":{"cited_paper":"/paper/2502.11034","citing_paper":"/paper/2505.15548"},"observation_digest":"sha256:38b51ad32ba74e20814403aa348e9493e0c6ca6f48872ed8465d3c2e9d2f3632","observation_id":"8413a921-310e-4b0b-975d-f730390a50b6","resolution":{"observed_at":"2026-08-07T15:19:27.943988Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.11034","last_updated":"2026-07-19T05:20:00Z","snapshot_observed_at":"2026-08-07T18:15:05.425576Z","submitted_at":"2025-02-16T08:13:23Z","title":"AdaGC: Enhancing LLM Pretraining Stability via Adaptive Gradient Clipping","version":4},"cited_work":{"arxiv_id":"2502.11034","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.11034","snapshot_observed_at":"2026-06-10T02:11:12.038297Z","title":"Adagc: Improving training stability for large language model pretraining.arXiv preprint arXiv:2502.11034","venue":null,"work_id":"a75a4930-a13c-448c-8f8a-d540438de6ed","year":null},"citing_paper":{"arxiv_id":"2605.08809","last_updated":"2026-05-09T08:59:13Z","snapshot_observed_at":"2026-08-02T18:35:09.983848Z","submitted_at":"2026-05-09T08:59:13Z","title":"SimReg: Achieving Higher Performance in the Pretraining via Embedding Similarity Regularization","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-12T03:33:45.192139Z"},"links":{"cited_paper":"/paper/2502.11034","citing_paper":"/paper/2605.08809"},"observation_digest":"sha256:6586e2ac21fcb2ecf1d051e3cd5273a0408a584f29aed0674a6570b1409c916e","observation_id":"808990e5-6e2e-493a-889d-8d20a7c105c5","resolution":{"observed_at":"2026-06-10T02:11:12.038297Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.11034","last_updated":"2026-07-19T05:20:00Z","snapshot_observed_at":"2026-08-07T18:15:05.425576Z","submitted_at":"2025-02-16T08:13:23Z","title":"AdaGC: Enhancing LLM Pretraining Stability via Adaptive Gradient Clipping","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.11034","snapshot_observed_at":"2026-07-11T22:10:49.683444Z","title":"Adagc: Improving training stability for large language model pretraining.arXiv preprint arXiv:2502.11034, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.04033","last_updated":"2026-07-04T21:27:05Z","snapshot_observed_at":"2026-08-07T05:07:10.107694Z","submitted_at":"2026-07-04T21:27:05Z","title":"OmniOpt: Taxonomy, Geometry, and Benchmarking of Modern Optimizers","version":1},"reference_index":109,"source":"pdf_text","source_observed_at":"2026-07-11T22:10:49.683444Z"},"links":{"cited_paper":"/paper/2502.11034","citing_paper":"/paper/2607.04033"},"observation_digest":"sha256:847f7c32c192bca001f3581e84a9546cf92f0761687bdd30b8f2764cef9c658d","observation_id":"ff9d8146-6331-4f96-83c1-b8ed585c9598","resolution":{"observed_at":"2026-07-11T22:10:49.683444Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.11034","last_updated":"2026-07-19T05:20:00Z","snapshot_observed_at":"2026-08-07T18:15:05.425576Z","submitted_at":"2025-02-16T08:13:23Z","title":"AdaGC: Enhancing LLM Pretraining Stability via Adaptive Gradient Clipping","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.11034","snapshot_observed_at":"2026-08-04T15:20:16.207834Z","title":"Adagc: Enhancing llm pretraining stability via adaptive gradient clipping, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.02091","last_updated":"2026-08-03T11:50:06Z","snapshot_observed_at":"2026-08-08T01:20:23.329247Z","submitted_at":"2026-08-03T11:50:06Z","title":"One QK Channel, Many Sources: Guarding Low-Precision Attention Collapse","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-04T15:20:16.207834Z"},"links":{"cited_paper":"/paper/2502.11034","citing_paper":"/paper/2608.02091"},"observation_digest":"sha256:4914820cd5fa9c200e9b981c78f0824db5f0704eb50bab6d54326f6617eaadc9","observation_id":"4b22f652-651d-4634-82f1-136d57ae4494","resolution":{"observed_at":"2026-08-04T15:20:16.207834Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2502.11034/citation-record","integrity":"/paper/2502.11034/integrity","json":"/paper/2502.11034/citation-record.json","paper":"/paper/2502.11034"},"outbound":[],"paper":{"arxiv_id":"2502.11034","last_updated":"2026-07-19T05:20:00Z","latest_version":4,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T18:15:05.425576Z","submitted_at":"2025-02-16T08:13:23Z","title":"AdaGC: Enhancing LLM Pretraining Stability via Adaptive Gradient Clipping"},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2502.11034."}