{"as_of":"2026-08-10T03:52:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:697c807ed263752e89b586bc4c19ee24e4fee8dccab8d50f7be925c6ad876d1e","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":"2026-08-09T06:31:02.800959+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":"2026-08-08T17:01:36.194110Z","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":"2026-06-30T08:24:26.792264Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2408.11029","last_updated":"2024-10-24T17:56:14Z","snapshot_observed_at":"2026-08-06T07:25:53.036005Z","submitted_at":"2024-08-20T17:30:48Z","title":"Scaling Law with Learning Rate Annealing","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.11029","snapshot_observed_at":"2026-08-08T17:01:36.194110Z","title":"Scaling law with learning rate annealing","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.06042","last_updated":"2025-05-26T18:48:37Z","snapshot_observed_at":"2026-08-09T10:18:57.511599Z","submitted_at":"2025-02-09T21:44:27Z","title":"Scaling Laws for Forgetting during Finetuning with Pretraining Data Injection","version":2},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-08T17:01:36.194110Z"},"links":{"cited_paper":"/paper/2408.11029","citing_paper":"/paper/2502.06042"},"observation_digest":"sha256:23cc6c8e9f124222c9bd057c7713afa61c69c856e4145b3c1367f26dffe86082","observation_id":"db0581da-92ba-4af8-90c0-2553e2f59445","resolution":{"observed_at":"2026-08-08T17:01:36.194110Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.11029","last_updated":"2024-10-24T17:56:14Z","snapshot_observed_at":"2026-08-06T07:25:53.036005Z","submitted_at":"2024-08-20T17:30:48Z","title":"Scaling Law with Learning Rate Annealing","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.11029","snapshot_observed_at":"2026-08-07T10:31:20.522740Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.05447","last_updated":"2025-07-14T23:29:38Z","snapshot_observed_at":"2026-08-10T00:22:56.702704Z","submitted_at":"2025-06-05T15:18:35Z","title":"Training Dynamics Underlying Language Model Scaling Laws: Loss Deceleration and Zero-Sum Learning","version":2},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-07T10:31:20.522740Z"},"links":{"cited_paper":"/paper/2408.11029","citing_paper":"/paper/2506.05447"},"observation_digest":"sha256:436881db2fdef81ef8b6740da0adeac4fa314c6e6f013b6ae1f0c49087b917f0","observation_id":"8b1f55d0-2325-4943-aadd-c42eb35e4330","resolution":{"observed_at":"2026-08-07T10:31:20.522740Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.11029","last_updated":"2024-10-24T17:56:14Z","snapshot_observed_at":"2026-08-06T07:25:53.036005Z","submitted_at":"2024-08-20T17:30:48Z","title":"Scaling Law with Learning Rate Annealing","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.11029","snapshot_observed_at":"2026-08-06T20:48:54.159538Z","title":"Scaling law with learning rate annealing","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.02119","last_updated":"2025-07-07T06:13:26Z","snapshot_observed_at":"2026-08-09T03:48:37.458741Z","submitted_at":"2025-07-02T20:03:34Z","title":"Scaling Collapse Reveals Universal Dynamics in Compute-Optimally Trained Neural Networks","version":2},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-06T20:48:54.159538Z"},"links":{"cited_paper":"/paper/2408.11029","citing_paper":"/paper/2507.02119"},"observation_digest":"sha256:41c6256964bce811617cb5278bd842291f8e71af8e765cfd021f9000875e074d","observation_id":"0d53d82b-059b-4a33-be5a-6c88d9f6f97d","resolution":{"observed_at":"2026-08-06T20:48:54.159538Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.11029","last_updated":"2024-10-24T17:56:14Z","snapshot_observed_at":"2026-08-06T07:25:53.036005Z","submitted_at":"2024-08-20T17:30:48Z","title":"Scaling Law with Learning Rate Annealing","version":2},"cited_work":{"arxiv_id":"2408.11029","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2408.11029","snapshot_observed_at":"2026-06-30T08:24:26.792264Z","title":"Scaling law with learning rate annealing.arXiv preprint arXiv:2408.11029, 2024","venue":null,"work_id":"30a83e93-31c0-4306-9016-0862486adbbd","year":2024},"citing_paper":{"arxiv_id":"2606.29158","last_updated":"2026-06-28T02:42:47Z","snapshot_observed_at":"2026-07-31T21:24:10.379144Z","submitted_at":"2026-06-28T02:42:47Z","title":"On the Nonlinearity of Learning Rate Scaling for LLM Training","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-06-30T08:15:20.191222Z"},"links":{"cited_paper":"/paper/2408.11029","citing_paper":"/paper/2606.29158"},"observation_digest":"sha256:ed4dd03e6507fc2793bf76810b3f83a9d98689cf13c8cd26182912da252bf18f","observation_id":"068cd734-0431-4fcc-8a9b-977367f48ca5","resolution":{"observed_at":"2026-06-30T08:24:26.793968Z","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/2408.11029/citation-record","integrity":"/paper/2408.11029/integrity","json":"/paper/2408.11029/citation-record.json","paper":"/paper/2408.11029"},"outbound":[],"paper":{"arxiv_id":"2408.11029","last_updated":"2024-10-24T17:56:14Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-06T07:25:53.036005Z","submitted_at":"2024-08-20T17:30:48Z","title":"Scaling Law with Learning Rate Annealing"},"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 4 inbound Pith citation observations for arXiv:2408.11029."}