{"as_of":"2026-08-10T12:36:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0a59395ea1aa38547c1e8815f67a345720aa622af487021ddb1b3be48986cded","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":"2026-08-10T06:31:04.303077+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":"2026-08-07T14:33:13.070132Z","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":"2026-07-04T00:39:17.554218Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2412.15285","last_updated":"2024-12-18T18:41:18Z","snapshot_observed_at":"2026-08-09T06:25:22.863608Z","submitted_at":"2024-12-18T18:41:18Z","title":"Maximize Your Data's Potential: Enhancing LLM Accuracy with Two-Phase Pretraining","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.15285","snapshot_observed_at":"2026-08-07T14:33:13.070132Z","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":139,"source":"pdf_text","source_observed_at":"2026-08-07T14:33:13.070132Z"},"links":{"cited_paper":"/paper/2412.15285","citing_paper":"/paper/2505.18458"},"observation_digest":"sha256:14f20b73729f54a95dfd17d14d343158d8d74f38cf3cc37d0357b11bbf799117","observation_id":"c31f056f-2a0c-4681-b01e-6864e54ecebd","resolution":{"observed_at":"2026-08-07T14:33:13.070132Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.15285","last_updated":"2024-12-18T18:41:18Z","snapshot_observed_at":"2026-08-09T06:25:22.863608Z","submitted_at":"2024-12-18T18:41:18Z","title":"Maximize Your Data's Potential: Enhancing LLM Accuracy with Two-Phase Pretraining","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.15285","snapshot_observed_at":"2026-08-07T12:35:40.495825Z","title":"Maximize your data's potential: Enhancing llm accuracy with two-phase pretraining","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.24844","last_updated":"2025-05-30T17:43:10Z","snapshot_observed_at":"2026-08-09T13:33:17.540834Z","submitted_at":"2025-05-30T17:43:10Z","title":"Chameleon: A Flexible Data-mixing Framework for Language Model Pretraining and Finetuning","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-07T12:35:40.495825Z"},"links":{"cited_paper":"/paper/2412.15285","citing_paper":"/paper/2505.24844"},"observation_digest":"sha256:36603b083e5cd38263434d9f64d4f7a1af45e6a49ef613de671daa03dd7e784e","observation_id":"ed9a85c7-fce3-48df-8edd-4c624c12522a","resolution":{"observed_at":"2026-08-07T12:35:40.495825Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.15285","last_updated":"2024-12-18T18:41:18Z","snapshot_observed_at":"2026-08-09T06:25:22.863608Z","submitted_at":"2024-12-18T18:41:18Z","title":"Maximize Your Data's Potential: Enhancing LLM Accuracy with Two-Phase Pretraining","version":1},"cited_work":{"arxiv_id":"2412.15285","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2412.15285","snapshot_observed_at":"2026-07-04T00:39:17.554218Z","title":"2412.15285 , archivePrefix=","venue":null,"work_id":"673253bd-80b6-455b-aa2a-6691f05385d1","year":null},"citing_paper":{"arxiv_id":"2512.20856","last_updated":"2025-12-24T00:24:05Z","snapshot_observed_at":"2026-08-07T14:13:20.121484Z","submitted_at":"2025-12-24T00:24:05Z","title":"NVIDIA Nemotron 3: Efficient and Open Intelligence","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-05-18T01:40:42.190369Z"},"links":{"cited_paper":"/paper/2412.15285","citing_paper":"/paper/2512.20856"},"observation_digest":"sha256:66bb0a889f252863dbeada903d51347a24be8249d7bafef63f7d0874c78265eb","observation_id":"6fcec0c5-eb1c-4333-bbce-3febb00a897e","resolution":{"observed_at":"2026-05-18T01:40:42.357220Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.15285","last_updated":"2024-12-18T18:41:18Z","snapshot_observed_at":"2026-08-09T06:25:22.863608Z","submitted_at":"2024-12-18T18:41:18Z","title":"Maximize Your Data's Potential: Enhancing LLM Accuracy with Two-Phase Pretraining","version":1},"cited_work":{"arxiv_id":"2412.15285","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2412.15285","snapshot_observed_at":"2026-07-04T00:39:17.554218Z","title":"2412.15285 , archivePrefix=","venue":null,"work_id":"673253bd-80b6-455b-aa2a-6691f05385d1","year":null},"citing_paper":{"arxiv_id":"2606.18663","last_updated":"2026-06-17T04:02:38Z","snapshot_observed_at":"2026-08-01T05:11:38.649391Z","submitted_at":"2026-06-17T04:02:38Z","title":"RegMix-D: Dynamic Data Mixing via Proxy Training Trajectories","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-06-26T21:01:52.850037Z"},"links":{"cited_paper":"/paper/2412.15285","citing_paper":"/paper/2606.18663"},"observation_digest":"sha256:63bee39970696626f2bd4e84392a644740dc08f9085b529194c89daeaf215b38","observation_id":"0e1ab5ef-6b86-46ed-a171-5be072b032b1","resolution":{"observed_at":"2026-07-04T00:39:17.556230Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2412.15285/citation-record","integrity":"/paper/2412.15285/integrity","json":"/paper/2412.15285/citation-record.json","paper":"/paper/2412.15285"},"outbound":[],"paper":{"arxiv_id":"2412.15285","last_updated":"2024-12-18T18:41:18Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-09T06:25:22.863608Z","submitted_at":"2024-12-18T18:41:18Z","title":"Maximize Your Data's Potential: Enhancing LLM Accuracy with Two-Phase Pretraining"},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2412.15285."}