{"as_of":"2026-08-16T22:56:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:1e89a0096461d97447c38b10544e009c9586049010d62bbdf6e7088766c4fcff","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":3,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":3,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T19:33:05.307058Z","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":"2026-05-25T06:40:24.954391Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2410.01243","last_updated":"2024-10-15T22:09:24Z","snapshot_observed_at":"2026-08-16T13:13:30.428637Z","submitted_at":"2024-10-02T05:12:13Z","title":"An Information Theory of Compute-Optimal Size Scaling, Emergence, and Plateaus in Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.01243","snapshot_observed_at":"2026-08-15T19:33:05.307058Z","title":"arXiv preprint arXiv:2410.01243 (2024)","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.17345","last_updated":"2025-06-19T15:45:24Z","snapshot_observed_at":"2026-08-15T19:24:52.330586Z","submitted_at":"2025-06-19T15:45:24Z","title":"CLOUD: A Scalable and Physics-Informed Foundation Model for Crystal Representation Learning","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-15T19:33:05.307058Z"},"links":{"cited_paper":"/paper/2410.01243","citing_paper":"/paper/2506.17345"},"observation_digest":"sha256:77f777ba4f16e014e1a2e53d04adb47f5bcd2f2816c1181b3984412c8e2508c7","observation_id":"4ad03e50-f14c-4676-bde9-b494977d04a3","resolution":{"observed_at":"2026-08-15T19:33:05.307058Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.01243","last_updated":"2024-10-15T22:09:24Z","snapshot_observed_at":"2026-08-16T13:13:30.428637Z","submitted_at":"2024-10-02T05:12:13Z","title":"An Information Theory of Compute-Optimal Size Scaling, Emergence, and Plateaus in Language Models","version":2},"cited_work":{"arxiv_id":"2410.01243","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2410.01243","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2410.01243 , year=","venue":null,"work_id":"d810fa99-cb1c-433f-8108-63542b3370c7","year":null},"citing_paper":{"arxiv_id":"2605.17767","last_updated":"2026-05-21T20:45:44Z","snapshot_observed_at":"2026-08-14T07:43:49.289615Z","submitted_at":"2026-05-18T02:37:50Z","title":"Feature Learning in Linear-Width Two-Layer Networks: Two vs. One Step of Gradient Descent","version":1},"reference_index":219,"source":"arxiv_source","source_observed_at":"2026-05-20T01:29:14.555216Z"},"links":{"cited_paper":"/paper/2410.01243","citing_paper":"/paper/2605.17767"},"observation_digest":"sha256:8b17a63e34300fa5f85ccc65770ecd839b98bd3f8e3802305fdec322e8e51d2e","observation_id":"f7d8cc1c-0c02-4cea-b347-2c1ea26ab6c9","resolution":{"observed_at":"2026-05-20T01:32:55.915763Z","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"}},{"citation":{"cited_paper":{"arxiv_id":"2410.01243","last_updated":"2024-10-15T22:09:24Z","snapshot_observed_at":"2026-08-16T13:13:30.428637Z","submitted_at":"2024-10-02T05:12:13Z","title":"An Information Theory of Compute-Optimal Size Scaling, Emergence, and Plateaus in Language Models","version":2},"cited_work":{"arxiv_id":"2410.01243","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2410.01243","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2410.01243 , year=","venue":null,"work_id":"d810fa99-cb1c-433f-8108-63542b3370c7","year":null},"citing_paper":{"arxiv_id":"2605.17767","last_updated":"2026-05-21T20:45:44Z","snapshot_observed_at":"2026-08-14T07:43:49.289615Z","submitted_at":"2026-05-18T02:37:50Z","title":"Feature Learning in Linear-Width Two-Layer Networks: Two vs. One Step of Gradient Descent","version":2},"reference_index":219,"source":"arxiv_source","source_observed_at":"2026-05-25T06:39:16.246591Z"},"links":{"cited_paper":"/paper/2410.01243","citing_paper":"/paper/2605.17767"},"observation_digest":"sha256:6f1afba667c84233aa1680b685c31c69a7d5c652c51be6b8713b046b1611b902","observation_id":"c09ff053-0a39-4998-b0e1-b02f87cba1ab","resolution":{"observed_at":"2026-05-25T06:40:24.957452Z","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/2410.01243/citation-record","integrity":"/paper/2410.01243/integrity","json":"/paper/2410.01243/citation-record.json","paper":"/paper/2410.01243"},"outbound":[],"paper":{"arxiv_id":"2410.01243","last_updated":"2024-10-15T22:09:24Z","latest_version":2,"primary_category":"cs.IT","snapshot_observed_at":"2026-08-16T13:13:30.428637Z","submitted_at":"2024-10-02T05:12:13Z","title":"An Information Theory of Compute-Optimal Size Scaling, Emergence, and Plateaus in 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 3 inbound Pith citation observations for arXiv:2410.01243."}