{"as_of":"2026-08-07T19:33:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e907c07e2f377e0aa50fcef9341d88e5f7cb0e8cd80db8092602fd2007f79ff4","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":"2026-08-07T06:34:17.273281+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":"2026-08-07T15:33:35.873061Z","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":"2026-05-16T02:30:32.237611Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2404.07647","last_updated":"2024-04-11T11:10:36Z","snapshot_observed_at":"2026-07-06T17:58:47.786948Z","submitted_at":"2024-04-11T11:10:36Z","title":"Why do small language models underperform? Studying Language Model Saturation via the Softmax Bottleneck","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.07647","snapshot_observed_at":"2026-08-07T15:33:35.873061Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.14852","last_updated":"2025-05-20T19:31:52Z","snapshot_observed_at":"2026-08-07T15:26:23.422843Z","submitted_at":"2025-05-20T19:31:52Z","title":"EasyMath: A 0-shot Math Benchmark for SLMs","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-07T15:33:35.873061Z"},"links":{"cited_paper":"/paper/2404.07647","citing_paper":"/paper/2505.14852"},"observation_digest":"sha256:6439010b9d3ffeb891df1b67e7a4c0b07018a36f10cdbd7f32d131bbc9bf737d","observation_id":"52cbf95b-fe71-4410-93b3-355dcd598466","resolution":{"observed_at":"2026-08-07T15:33:35.873061Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.07647","last_updated":"2024-04-11T11:10:36Z","snapshot_observed_at":"2026-07-06T17:58:47.786948Z","submitted_at":"2024-04-11T11:10:36Z","title":"Why do small language models underperform? Studying Language Model Saturation via the Softmax Bottleneck","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.07647","snapshot_observed_at":"2026-08-07T10:31:20.382188Z","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":"2026-08-07T10:21:15.691562Z","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":12,"source":"arxiv_source","source_observed_at":"2026-08-07T10:31:20.382188Z"},"links":{"cited_paper":"/paper/2404.07647","citing_paper":"/paper/2506.05447"},"observation_digest":"sha256:b668bff2b73397a6a5b396ac53e9879079144308c6d8a48e43c0bbdb63b34152","observation_id":"2988fb8e-629f-48d4-ace9-b76f3659ff9c","resolution":{"observed_at":"2026-08-07T10:31:20.382188Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.07647","last_updated":"2024-04-11T11:10:36Z","snapshot_observed_at":"2026-07-06T17:58:47.786948Z","submitted_at":"2024-04-11T11:10:36Z","title":"Why do small language models underperform? Studying Language Model Saturation via the Softmax Bottleneck","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.07647","snapshot_observed_at":"2026-08-06T11:59:52.185886Z","title":"Why do small language models underperform? studying language model saturation via the softmax bottleneck.arXiv preprint arXiv:2404.07647,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.22250","last_updated":"2025-07-29T21:56:45Z","snapshot_observed_at":"2026-08-06T11:59:51.689888Z","submitted_at":"2025-07-29T21:56:45Z","title":"Using Scaling Laws for Data Source Utility Estimation in Domain-Specific Pre-Training","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T11:59:52.185886Z"},"links":{"cited_paper":"/paper/2404.07647","citing_paper":"/paper/2507.22250"},"observation_digest":"sha256:b48cfce34d3f34fbea4638cfb593acdb5a36198be137a2a27600257f35ca988a","observation_id":"5827bea8-e2f5-4fc0-ac50-f3017293fa59","resolution":{"observed_at":"2026-08-06T11:59:52.185886Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.07647","last_updated":"2024-04-11T11:10:36Z","snapshot_observed_at":"2026-07-06T17:58:47.786948Z","submitted_at":"2024-04-11T11:10:36Z","title":"Why do small language models underperform? Studying Language Model Saturation via the Softmax Bottleneck","version":1},"cited_work":{"arxiv_id":"2404.07647","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2404.07647","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Why do small language models underperform? studying lan- guage model saturation via the softmax bottleneck.arXiv preprint arXiv:2404.07647","venue":null,"work_id":"38ca0ce4-02fe-4cdf-afa4-1502cd9030e2","year":null},"citing_paper":{"arxiv_id":"2602.09789","last_updated":"2026-05-11T17:16:12Z","snapshot_observed_at":"2026-07-06T22:45:20.365624Z","submitted_at":"2026-02-10T13:49:08Z","title":"When Less is More: The LLM Scaling Paradox in Context Compression","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-16T02:28:37.490958Z"},"links":{"cited_paper":"/paper/2404.07647","citing_paper":"/paper/2602.09789"},"observation_digest":"sha256:14fd0af2e38960663a0f353050b43a3cf3f01dad5ce49195742868a9461b60a7","observation_id":"944e1033-3b30-446b-bc66-2e6868d061fa","resolution":{"observed_at":"2026-05-16T02:30:32.241335Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2404.07647/citation-record","integrity":"/paper/2404.07647/integrity","json":"/paper/2404.07647/citation-record.json","paper":"/paper/2404.07647"},"outbound":[],"paper":{"arxiv_id":"2404.07647","last_updated":"2024-04-11T11:10:36Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T17:58:47.786948Z","submitted_at":"2024-04-11T11:10:36Z","title":"Why do small language models underperform? Studying Language Model Saturation via the Softmax Bottleneck"},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2404.07647."}