{"as_of":"2026-08-09T12:39:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:44c7b0c894e526438a8f7119ed844622a7b3277d75f51d9c7bd302ebaae44bbb","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":"2026-08-09T06:31:02.800959+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":"2026-08-07T12:19:28.566337Z","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":"2026-05-15T00:58:25.685256Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2501.11747","last_updated":"2025-01-23T20:45:47Z","snapshot_observed_at":"2026-07-06T20:23:36.052687Z","submitted_at":"2025-01-20T21:10:22Z","title":"Optimizing Pretraining Data Mixtures with LLM-Estimated Utility","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.11747","snapshot_observed_at":"2026-08-07T12:19:28.566337Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.24871","last_updated":"2025-06-05T05:13:46Z","snapshot_observed_at":"2026-08-09T06:28:01.755194Z","submitted_at":"2025-05-30T17:59:38Z","title":"MoDoMoDo: Multi-Domain Data Mixtures for Multimodal LLM Reinforcement Learning","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T12:19:28.566337Z"},"links":{"cited_paper":"/paper/2501.11747","citing_paper":"/paper/2505.24871"},"observation_digest":"sha256:de57853d5229d7ded13def983cd03ba860866efb547ee74a578d01f6a9e76b16","observation_id":"37c2ea2a-7d24-4ba1-9296-5a561771ff43","resolution":{"observed_at":"2026-08-07T12:19:28.566337Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.11747","last_updated":"2025-01-23T20:45:47Z","snapshot_observed_at":"2026-07-06T20:23:36.052687Z","submitted_at":"2025-01-20T21:10:22Z","title":"Optimizing Pretraining Data Mixtures with LLM-Estimated Utility","version":2},"cited_work":{"arxiv_id":"2501.11747","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2501.11747","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Optimizing pretraining data mixtures with llm-estimated utility","venue":null,"work_id":"5fe46a60-a877-486a-8e0a-d488286739db","year":2025},"citing_paper":{"arxiv_id":"2604.16380","last_updated":"2026-03-25T13:30:40Z","snapshot_observed_at":"2026-08-08T06:45:13.140900Z","submitted_at":"2026-03-25T13:30:40Z","title":"Data Mixing for Large Language Models Pretraining: A Survey and Outlook","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-15T00:56:04.958757Z"},"links":{"cited_paper":"/paper/2501.11747","citing_paper":"/paper/2604.16380"},"observation_digest":"sha256:cf32b77257418230aa18a289d229e0abc3bed644006ea2aa22bf8dd871739cf1","observation_id":"f76c496f-295d-4454-b69f-54f83e03bea8","resolution":{"observed_at":"2026-05-15T00:58:25.686856Z","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/2501.11747/citation-record","integrity":"/paper/2501.11747/integrity","json":"/paper/2501.11747/citation-record.json","paper":"/paper/2501.11747"},"outbound":[],"paper":{"arxiv_id":"2501.11747","last_updated":"2025-01-23T20:45:47Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T20:23:36.052687Z","submitted_at":"2025-01-20T21:10:22Z","title":"Optimizing Pretraining Data Mixtures with LLM-Estimated Utility"},"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 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2501.11747."}