{"as_of":"2026-08-23T12:07:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:82b453d151b59dbdba4314dc99541bde0dd29a72e443dabea1df5c7d65540c0c","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":"2026-08-23T06:30:58.430688+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":"2026-08-07T10:42:54.771585Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-07T10:42:54.936992Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2502.15499","last_updated":"2025-02-25T06:54:39Z","snapshot_observed_at":"2026-08-16T12:56:19.531947Z","submitted_at":"2025-02-21T14:49:34Z","title":"Scale-Distribution Decoupling: Enabling Stable and Effective Training of Large Language Models","version":2},"cited_work":{"arxiv_id":"2502.15499","doi":null,"metadata_source":"pith","pith_arxiv_id":"2502.15499","snapshot_observed_at":"2026-08-07T10:42:54.936992Z","title":"Scale-Distribution Decoupling: Enabling Stable and Effective Training of Large Language Models","venue":"cs.CL","work_id":"cf57f275-3475-48af-8c2b-68d79085835d","year":2025},"citing_paper":{"arxiv_id":"2506.04805","last_updated":"2026-05-25T11:37:32Z","snapshot_observed_at":"2026-08-18T14:59:42.545824Z","submitted_at":"2025-06-05T09:31:41Z","title":"Adaptive Preconditioners Trigger Loss Spikes in Adam","version":2},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-07T10:42:54.771585Z"},"links":{"cited_paper":"/paper/2502.15499","citing_paper":"/paper/2506.04805"},"observation_digest":"sha256:f3080449d4e012e93aafce88ae2827f529f230503adbe25412ab8c9fee854c25","observation_id":"c2f39622-7164-437b-9c88-8d37ffa997e0","resolution":{"observed_at":"2026-08-07T10:42:54.942247Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.15499","last_updated":"2025-02-25T06:54:39Z","snapshot_observed_at":"2026-08-16T12:56:19.531947Z","submitted_at":"2025-02-21T14:49:34Z","title":"Scale-Distribution Decoupling: Enabling Stable and Effective Training of Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.15499","snapshot_observed_at":"2026-08-01T08:50:45.475754Z","title":"arXiv preprint arXiv:2502.15499 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.21005","last_updated":"2026-07-23T07:39:03Z","snapshot_observed_at":"2026-08-15T23:27:47.607335Z","submitted_at":"2026-07-23T07:39:03Z","title":"Weight-norm Criticality: A Mechanism for Loss Spikes Induced by the Normalization and Weight Decay","version":1},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-01T08:50:45.475754Z"},"links":{"cited_paper":"/paper/2502.15499","citing_paper":"/paper/2607.21005"},"observation_digest":"sha256:7892137b4f4f3a0587846ab82e8e719cad4a1efcd3cfe906d74fd8f3e860df14","observation_id":"b04247f0-7d18-47ad-8e38-b27b5e78fb73","resolution":{"observed_at":"2026-08-01T08:50:45.475754Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2502.15499/citation-record","integrity":"/paper/2502.15499/integrity","json":"/paper/2502.15499/citation-record.json","paper":"/paper/2502.15499"},"outbound":[],"paper":{"arxiv_id":"2502.15499","last_updated":"2025-02-25T06:54:39Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-16T12:56:19.531947Z","submitted_at":"2025-02-21T14:49:34Z","title":"Scale-Distribution Decoupling: Enabling Stable and Effective 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":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"thesis":"As of 23 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2502.15499."}