{"as_of":"2026-08-20T03:40:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:730c86328c15b381d880b2038eac935f4415929224009d8099c9a785a306c873","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":"2026-08-19T06:32:44.657259+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":"2026-08-12T10:24:06.623314Z","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":"2026-08-12T10:24:07.458189Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2009.14558","last_updated":"2020-09-30T10:59:20Z","snapshot_observed_at":"2026-08-16T19:16:55.363242Z","submitted_at":"2020-09-30T10:59:20Z","title":"Learning Object Detection from Captions via Textual Scene Attributes","version":1},"cited_work":{"arxiv_id":"2009.14558","doi":null,"metadata_source":"pith","pith_arxiv_id":"2009.14558","snapshot_observed_at":"2026-08-12T10:24:07.458189Z","title":"Learning Object Detection from Captions via Textual Scene Attributes","venue":"cs.CV","work_id":"91ba64b4-4a4d-4a48-a070-be12b287145a","year":2020},"citing_paper":{"arxiv_id":"2412.00142","last_updated":"2025-06-09T17:01:06Z","snapshot_observed_at":"2026-08-15T06:49:05.052533Z","submitted_at":"2024-11-28T18:55:41Z","title":"Enhancing Few-Shot Vision-Language Classification with Large Multimodal Model Features","version":3},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-12T10:24:06.623314Z"},"links":{"cited_paper":"/paper/2009.14558","citing_paper":"/paper/2412.00142"},"observation_digest":"sha256:05f1322d6b35ab7e424e6d97ef3780e43a85a0200ae72f0afed5a975cf361d9b","observation_id":"5bce9494-9555-495c-83a8-a5e40749a083","resolution":{"observed_at":"2026-08-12T10:24:07.463692Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2009.14558/citation-record","integrity":"/paper/2009.14558/integrity","json":"/paper/2009.14558/citation-record.json","paper":"/paper/2009.14558"},"outbound":[],"paper":{"arxiv_id":"2009.14558","last_updated":"2020-09-30T10:59:20Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-16T19:16:55.363242Z","submitted_at":"2020-09-30T10:59:20Z","title":"Learning Object Detection from Captions via Textual Scene Attributes"},"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":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 20 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2009.14558."}