{"as_of":"2026-08-20T23:51:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d261f8eb21b1a1bc1dd9190a19d4277b520969d803a968108d7fbbfce4aedbd4","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":"2026-08-20T06:33:59.587034+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":"2026-08-10T14:14:54.647549Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-07T14:33:14.501284Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2408.15079","last_updated":"2024-08-27T14:08:23Z","snapshot_observed_at":"2026-08-16T13:23:29.783378Z","submitted_at":"2024-08-27T14:08:23Z","title":"BaichuanSEED: Sharing the Potential of ExtensivE Data Collection and Deduplication by Introducing a Competitive Large Language Model Baseline","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.15079","snapshot_observed_at":"2026-08-10T14:14:54.647549Z","title":"Baichuanseed: Sharing the potential of extensive data collection and deduplication by introducing a competitive large language model baseline","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.15558","last_updated":"2025-01-26T15:20:39Z","snapshot_observed_at":"2026-08-14T08:01:00.400549Z","submitted_at":"2025-01-26T15:20:39Z","title":"Ocean-OCR: Towards General OCR Application via a Vision-Language Model","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-10T14:14:54.647549Z"},"links":{"cited_paper":"/paper/2408.15079","citing_paper":"/paper/2501.15558"},"observation_digest":"sha256:c28195268fe0f88b9cc20f2d3564568caa7ca0a54a73480568838ac3c1769236","observation_id":"61f72527-d0e7-49b3-9738-5d220428e41a","resolution":{"observed_at":"2026-08-10T14:14:54.647549Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.15079","last_updated":"2024-08-27T14:08:23Z","snapshot_observed_at":"2026-08-16T13:23:29.783378Z","submitted_at":"2024-08-27T14:08:23Z","title":"BaichuanSEED: Sharing the Potential of ExtensivE Data Collection and Deduplication by Introducing a Competitive Large Language Model Baseline","version":1},"cited_work":{"arxiv_id":"2408.15079","doi":null,"metadata_source":"pith","pith_arxiv_id":"2408.15079","snapshot_observed_at":"2026-08-07T14:33:14.501284Z","title":"BaichuanSEED: Sharing the Potential of ExtensivE Data Collection and Deduplication by Introducing a Competitive Large Language Model Baseline","venue":"cs.CL","work_id":"a16c8ebc-76a3-416a-b5e6-b6883ab3ed88","year":2024},"citing_paper":{"arxiv_id":"2505.18458","last_updated":"2025-06-01T16:00:34Z","snapshot_observed_at":"2026-08-16T16:04:23.826018Z","submitted_at":"2025-05-24T01:57:12Z","title":"A Survey of LLM $\\times$ DATA","version":3},"reference_index":122,"source":"pdf_text","source_observed_at":"2026-08-07T14:33:13.019010Z"},"links":{"cited_paper":"/paper/2408.15079","citing_paper":"/paper/2505.18458"},"observation_digest":"sha256:7dd8db65107be89bb33520dab6a76e8e878073d27575cdd43d88009fc4017259","observation_id":"6f72cb99-de4b-4554-a0e5-ca063bcee65b","resolution":{"observed_at":"2026-08-07T14:33:14.505149Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2408.15079/citation-record","integrity":"/paper/2408.15079/integrity","json":"/paper/2408.15079/citation-record.json","paper":"/paper/2408.15079"},"outbound":[],"paper":{"arxiv_id":"2408.15079","last_updated":"2024-08-27T14:08:23Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-16T13:23:29.783378Z","submitted_at":"2024-08-27T14:08:23Z","title":"BaichuanSEED: Sharing the Potential of ExtensivE Data Collection and Deduplication by Introducing a Competitive Large Language Model Baseline"},"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":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"thesis":"As of 20 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2408.15079."}