{"as_of":"2026-08-08T06:13:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:9134022a4abe7b0cbb0155284816b454db0fdf052cf358b52d5cd15d74e8a67e","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":"2026-08-07T04:37:08.755456Z","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":"2026-05-11T17:21:10.885120Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2312.01700","last_updated":"2024-08-02T03:56:35Z","snapshot_observed_at":"2026-07-06T16:56:25.554848Z","submitted_at":"2023-12-04T07:42:16Z","title":"Data Management For Training Large Language Models: A Survey","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.01700","snapshot_observed_at":"2026-08-07T04:37:08.755456Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.10288","last_updated":"2025-06-12T01:53:01Z","snapshot_observed_at":"2026-08-07T04:27:46.870736Z","submitted_at":"2025-06-12T01:53:01Z","title":"ClusterUCB: Efficient Gradient-Based Data Selection for Targeted Fine-Tuning of LLMs","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-07T04:37:08.755456Z"},"links":{"cited_paper":"/paper/2312.01700","citing_paper":"/paper/2506.10288"},"observation_digest":"sha256:c3f1ac6a15b0c087543d4572336b5f926d39b719f8ea6b5dd5f7d7ebde07f795","observation_id":"6849e10f-3a3d-43ad-8d27-7245f7a51d00","resolution":{"observed_at":"2026-08-07T04:37:08.755456Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.01700","last_updated":"2024-08-02T03:56:35Z","snapshot_observed_at":"2026-07-06T16:56:25.554848Z","submitted_at":"2023-12-04T07:42:16Z","title":"Data Management For Training Large Language Models: A Survey","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.01700","snapshot_observed_at":"2026-08-06T18:39:00.075360Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.07817","last_updated":"2025-07-15T11:42:05Z","snapshot_observed_at":"2026-08-06T18:29:19.739745Z","submitted_at":"2025-07-10T14:46:33Z","title":"On the Effect of Instruction Tuning Loss on Generalization","version":2},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-06T18:39:00.075360Z"},"links":{"cited_paper":"/paper/2312.01700","citing_paper":"/paper/2507.07817"},"observation_digest":"sha256:de545f05bde84721238ae185f06b9d876f88d703cba1f4b5fc8622695f3b5028","observation_id":"4ec07e25-2e1b-4c60-a2f5-884e137ba013","resolution":{"observed_at":"2026-08-06T18:39:00.075360Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.01700","last_updated":"2024-08-02T03:56:35Z","snapshot_observed_at":"2026-07-06T16:56:25.554848Z","submitted_at":"2023-12-04T07:42:16Z","title":"Data Management For Training Large Language Models: A Survey","version":3},"cited_work":{"arxiv_id":"2312.01700","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2312.01700","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"5a587292-ca2f-4596-a9ce-44f2aa8dd193","year":2023},"citing_paper":{"arxiv_id":"2605.05267","last_updated":"2026-05-06T09:38:31Z","snapshot_observed_at":"2026-08-04T17:41:12.164736Z","submitted_at":"2026-05-06T09:38:31Z","title":"Bridging Generation and Training: A Systematic Review of Quality Issues in LLMs for Code","version":1},"reference_index":133,"source":"pdf_text","source_observed_at":"2026-05-08T17:37:51.790000Z"},"links":{"cited_paper":"/paper/2312.01700","citing_paper":"/paper/2605.05267"},"observation_digest":"sha256:b1db0e7c543036802816578104bab8366f1fa325734c504fcbb0012619d7cd48","observation_id":"617ab7f9-395b-4326-9744-8a41222275d6","resolution":{"observed_at":"2026-05-11T17:21:10.887228Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"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"}},{"citation":{"cited_paper":{"arxiv_id":"2312.01700","last_updated":"2024-08-02T03:56:35Z","snapshot_observed_at":"2026-07-06T16:56:25.554848Z","submitted_at":"2023-12-04T07:42:16Z","title":"Data Management For Training Large Language Models: A Survey","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.01700","snapshot_observed_at":"2026-07-11T21:50:04.825590Z","title":"Data management for training large language models: A survey","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.04081","last_updated":"2026-07-05T02:23:18Z","snapshot_observed_at":"2026-08-06T17:07:51.204839Z","submitted_at":"2026-07-05T02:23:18Z","title":"A Unified Framework for In-Context Learning with Causal and Masked Language Models","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-07-11T21:50:04.825590Z"},"links":{"cited_paper":"/paper/2312.01700","citing_paper":"/paper/2607.04081"},"observation_digest":"sha256:4379af2a258ffe865ec16610c23cb0e8519a853427d7e630755764d7f8b961dc","observation_id":"e57aaaa5-0220-424c-8969-70e91d770ec3","resolution":{"observed_at":"2026-07-11T21:50:04.825590Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2312.01700/citation-record","integrity":"/paper/2312.01700/integrity","json":"/paper/2312.01700/citation-record.json","paper":"/paper/2312.01700"},"outbound":[],"paper":{"arxiv_id":"2312.01700","last_updated":"2024-08-02T03:56:35Z","latest_version":3,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T16:56:25.554848Z","submitted_at":"2023-12-04T07:42:16Z","title":"Data Management For Training Large Language Models: A Survey"},"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 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2312.01700."}