{"as_of":"2026-08-02T00:22:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f86a7390a3138e2ac1729510b1c3f707f266c9c997fe3a2efc6cea3eceb189d4","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":1,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":1,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-01T06:32:01.292127+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-01T10:42:42.797506Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2602.22859","last_updated":"2026-05-07T13:23:50Z","snapshot_observed_at":"2026-07-06T22:47:06.893212Z","submitted_at":"2026-02-26T10:53:57Z","title":"From Blind Spots to Gains: Diagnostic-Driven Iterative Training for Large Multimodal Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2602.22859","snapshot_observed_at":"2026-08-01T10:42:42.797506Z","title":"arXiv preprint arXiv:2602.22859 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.20145","last_updated":"2026-07-30T09:30:44Z","snapshot_observed_at":"2026-08-02T00:12:17.736336Z","submitted_at":"2026-07-22T13:49:17Z","title":"SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD","version":2},"reference_index":68,"source":"arxiv_source","source_observed_at":"2026-08-01T10:42:42.797506Z"},"links":{"cited_paper":"/paper/2602.22859","citing_paper":"/paper/2607.20145"},"observation_digest":"sha256:96fead4a6c7f87881540b5f7dc3f5e950787ff6fdd7870d36e73c321199252bf","observation_id":"215f0dd9-9288-46a3-b800-061f4952be67","resolution":{"observed_at":"2026-08-01T10:42:42.797506Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2602.22859/citation-record","integrity":"/paper/2602.22859/integrity","json":"/paper/2602.22859/citation-record.json","paper":"/paper/2602.22859"},"outbound":[],"paper":{"arxiv_id":"2602.22859","last_updated":"2026-05-07T13:23:50Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T22:47:06.893212Z","submitted_at":"2026-02-26T10:53:57Z","title":"From Blind Spots to Gains: Diagnostic-Driven Iterative Training for Large Multimodal 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":"2026-08-01T06:32:01.292127+00:00","source":"crossref"},{"observed_at":"2026-08-01T06:31:58.492377+00:00","source":"retraction_watch"}],"thesis":"As of 2 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2602.22859."}