{"as_of":"2026-08-18T04:57:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2152e2e4925cf92358883e6732798216fa78907b0fb9494acfc3b2c97bf0a877","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":"2026-08-17T06:30:58.91139+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":"2026-08-16T05:01:30.861759Z","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":"2026-08-12T14:58:43.820840Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2410.13733","last_updated":"2024-10-17T16:36:38Z","snapshot_observed_at":"2026-08-16T13:08:20.175225Z","submitted_at":"2024-10-17T16:36:38Z","title":"Improving Multi-modal Large Language Model through Boosting Vision Capabilities","version":1},"cited_work":{"arxiv_id":"2410.13733","doi":null,"metadata_source":"pith","pith_arxiv_id":"2410.13733","snapshot_observed_at":"2026-08-12T14:58:43.820840Z","title":"Improving Multi-modal Large Language Model through Boosting Vision Capabilities","venue":"cs.CV","work_id":"ee85e822-a5fb-4f02-b5d4-bea92b58c51f","year":2024},"citing_paper":{"arxiv_id":"2411.14797","last_updated":"2024-11-22T08:48:30Z","snapshot_observed_at":"2026-08-14T12:55:57.058373Z","submitted_at":"2024-11-22T08:48:30Z","title":"Continual SFT Matches Multimodal RLHF with Negative Supervision","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-12T14:58:43.096094Z"},"links":{"cited_paper":"/paper/2410.13733","citing_paper":"/paper/2411.14797"},"observation_digest":"sha256:3f324f945ca26949ae9e90d161729d8f41a1a1b461c3f37a80dc8d419ad5aa09","observation_id":"9360bab2-3464-492d-95d0-f3c01d58014a","resolution":{"observed_at":"2026-08-12T14:58:43.881132Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.13733","last_updated":"2024-10-17T16:36:38Z","snapshot_observed_at":"2026-08-16T13:08:20.175225Z","submitted_at":"2024-10-17T16:36:38Z","title":"Improving Multi-modal Large Language Model through Boosting Vision Capabilities","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.13733","snapshot_observed_at":"2026-08-16T05:01:30.861759Z","title":"Improving Multi-modal Large Language Model through Boosting Vision Capabilities,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.21614","last_updated":"2025-07-26T14:21:27Z","snapshot_observed_at":"2026-08-17T08:04:00.484680Z","submitted_at":"2025-04-30T13:10:59Z","title":"Mcity Data Engine: Iterative Model Improvement Through Open-Vocabulary Data Selection","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-16T05:01:30.861759Z"},"links":{"cited_paper":"/paper/2410.13733","citing_paper":"/paper/2504.21614"},"observation_digest":"sha256:f62db6ab9e39ca73e6a65c49e9a2d3f5109ebc462b39d959a5f77c098bcfbbe8","observation_id":"8a53a08d-e977-4d6a-9b76-eb4d84efd46a","resolution":{"observed_at":"2026-08-16T05:01:30.861759Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2410.13733/citation-record","integrity":"/paper/2410.13733/integrity","json":"/paper/2410.13733/citation-record.json","paper":"/paper/2410.13733"},"outbound":[],"paper":{"arxiv_id":"2410.13733","last_updated":"2024-10-17T16:36:38Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-16T13:08:20.175225Z","submitted_at":"2024-10-17T16:36:38Z","title":"Improving Multi-modal Large Language Model through Boosting Vision Capabilities"},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2410.13733."}