{"as_of":"2026-08-07T18:05:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5a28299a010a536c3637578f2a17a60b949914dbdece38ef3da1ae0c5091f7ba","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":"2026-08-07T06:34:17.273281+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":"2026-08-06T05:37:35.306879Z","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":"2026-05-10T06:56:47.918778Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2504.14194","last_updated":"2025-08-06T15:34:10Z","snapshot_observed_at":"2026-08-07T16:00:57.924743Z","submitted_at":"2025-04-19T06:12:33Z","title":"Meta-rater: A Multi-dimensional Data Selection Method for Pre-training Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.14194","snapshot_observed_at":"2026-08-06T05:37:35.306879Z","title":"Meta-rater: A multi-dimensional data selec- tion method for pre-training language models.arXiv preprint arXiv:2504.14194, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.01453","last_updated":"2025-08-02T18:02:44Z","snapshot_observed_at":"2026-08-07T03:44:19.380268Z","submitted_at":"2025-08-02T18:02:44Z","title":"Kernel-Based Sparse Additive Nonlinear Model Structure Detection through a Linearization Approach","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T05:37:35.306879Z"},"links":{"cited_paper":"/paper/2504.14194","citing_paper":"/paper/2508.01453"},"observation_digest":"sha256:6cacb114349c910547852a39f0ad95398cd91e02476835854fc7412e63eb4e77","observation_id":"9cfe0d69-7090-48e0-bedd-aa22b69ac88b","resolution":{"observed_at":"2026-08-06T05:37:35.306879Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.14194","last_updated":"2025-08-06T15:34:10Z","snapshot_observed_at":"2026-08-07T16:00:57.924743Z","submitted_at":"2025-04-19T06:12:33Z","title":"Meta-rater: A Multi-dimensional Data Selection Method for Pre-training Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.14194","snapshot_observed_at":"2026-08-04T13:24:16.399318Z","title":"12 Xinlin Zhuang, Jiahui Peng, Ren Ma, Yinfan Wang, Tianyi Bai, Xingjian Wei, Jiantao Qiu, Chi Zhang, Ying Qian, and Conghui He","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2510.00866","last_updated":"2026-06-24T09:23:10Z","snapshot_observed_at":"2026-08-07T02:52:46.945895Z","submitted_at":"2025-10-01T13:15:15Z","title":"Removing Noise, not Finding Gold: Quality Filtering for Large-Scale Pretraining","version":4},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-04T13:24:16.399318Z"},"links":{"cited_paper":"/paper/2504.14194","citing_paper":"/paper/2510.00866"},"observation_digest":"sha256:67170c35158841635592662d6e7afc770dabefcd5372b6846307dd8709efc0f0","observation_id":"9496160c-eb4d-48cd-9cfc-274fa04b2015","resolution":{"observed_at":"2026-08-04T13:24:16.399318Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.14194","last_updated":"2025-08-06T15:34:10Z","snapshot_observed_at":"2026-08-07T16:00:57.924743Z","submitted_at":"2025-04-19T06:12:33Z","title":"Meta-rater: A Multi-dimensional Data Selection Method for Pre-training Language Models","version":4},"cited_work":{"arxiv_id":"2504.14194","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2504.14194","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2504.14194 , year=","venue":null,"work_id":"ed23daf1-6523-45d3-a9c9-d46e837be278","year":null},"citing_paper":{"arxiv_id":"2604.17650","last_updated":"2026-04-19T22:45:10Z","snapshot_observed_at":"2026-07-06T23:04:41.564912Z","submitted_at":"2026-04-19T22:45:10Z","title":"Measuring Distribution Shift in User Prompts and Its Effects on LLM Performance","version":1},"reference_index":70,"source":"arxiv_source","source_observed_at":"2026-05-10T05:27:50.049798Z"},"links":{"cited_paper":"/paper/2504.14194","citing_paper":"/paper/2604.17650"},"observation_digest":"sha256:49cd90ca5824b47ef5c9570c10f95ba8e80d35e9b569d6c383e5a5be7995865e","observation_id":"a9b506bd-623f-444b-9b44-7c5822f3486b","resolution":{"observed_at":"2026-05-10T06:56:47.920102Z","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/2504.14194/citation-record","integrity":"/paper/2504.14194/integrity","json":"/paper/2504.14194/citation-record.json","paper":"/paper/2504.14194"},"outbound":[],"paper":{"arxiv_id":"2504.14194","last_updated":"2025-08-06T15:34:10Z","latest_version":4,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-07T16:00:57.924743Z","submitted_at":"2025-04-19T06:12:33Z","title":"Meta-rater: A Multi-dimensional Data Selection Method for Pre-training 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":"2026-08-07T06:34:17.273281+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 3 inbound Pith citation observations for arXiv:2504.14194."}