{"as_of":"2026-08-12T16:18:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:cdbf23fa9df05fb9eb8d4e864a7b05c84af84604dfdc7ae88f99412957206dc3","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":"2026-08-12T06:34:41.77262+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":"2026-08-07T14:33:13.152731Z","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":"2026-05-12T06:31:28.948702Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2407.06654","last_updated":"2024-07-09T08:26:39Z","snapshot_observed_at":"2026-08-08T08:09:16.419779Z","submitted_at":"2024-07-09T08:26:39Z","title":"SoftDedup: an Efficient Data Reweighting Method for Speeding Up Language Model Pre-training","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.06654","snapshot_observed_at":"2026-08-07T14:33:13.152731Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.18458","last_updated":"2025-06-01T16:00:34Z","snapshot_observed_at":"2026-08-07T20:59:19.597449Z","submitted_at":"2025-05-24T01:57:12Z","title":"A Survey of LLM $\\times$ DATA","version":3},"reference_index":167,"source":"pdf_text","source_observed_at":"2026-08-07T14:33:13.152731Z"},"links":{"cited_paper":"/paper/2407.06654","citing_paper":"/paper/2505.18458"},"observation_digest":"sha256:f7c884573ea804b60f5b1fb5ddc257fa5d2c40cdc70b03176b27cd96bf63311d","observation_id":"83629a1f-9d1b-4f2c-aa4d-831a5d328e77","resolution":{"observed_at":"2026-08-07T14:33:13.152731Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.06654","last_updated":"2024-07-09T08:26:39Z","snapshot_observed_at":"2026-08-08T08:09:16.419779Z","submitted_at":"2024-07-09T08:26:39Z","title":"SoftDedup: an Efficient Data Reweighting Method for Speeding Up Language Model Pre-training","version":1},"cited_work":{"arxiv_id":"2407.06654","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2407.06654","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"He et al","venue":null,"work_id":"cddf2c2d-0676-4d49-9b1c-8f9cf672576d","year":2024},"citing_paper":{"arxiv_id":"2605.09990","last_updated":"2026-05-11T05:06:59Z","snapshot_observed_at":"2026-07-06T23:21:59.096464Z","submitted_at":"2026-05-11T05:06:59Z","title":"Merlin: Deterministic Byte-Exact Deduplication for Lossless Context Optimization in Large Language Model Inference","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-12T04:11:02.387702Z"},"links":{"cited_paper":"/paper/2407.06654","citing_paper":"/paper/2605.09990"},"observation_digest":"sha256:4addd44583a793b5e9635eac24d314e8e35f38363410bf5270a0aafad452587c","observation_id":"d8aedb57-aa1a-4d2a-9539-8cfb0a331c71","resolution":{"observed_at":"2026-05-12T06:31:28.952124Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2407.06654/citation-record","integrity":"/paper/2407.06654/integrity","json":"/paper/2407.06654/citation-record.json","paper":"/paper/2407.06654"},"outbound":[],"paper":{"arxiv_id":"2407.06654","last_updated":"2024-07-09T08:26:39Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-08T08:09:16.419779Z","submitted_at":"2024-07-09T08:26:39Z","title":"SoftDedup: an Efficient Data Reweighting Method for Speeding Up Language Model Pre-training"},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2407.06654."}