{"as_of":"2026-08-14T17:27:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3f926fdc0a193ad075e77bf345cb8a6ddd55378e24c17c7328b2e0f99859abec","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":"2026-08-14T06:32:32.682623+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":"2026-07-15T14:07:39.892672Z","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":"2026-05-19T11:13:02.800174Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2409.01133","last_updated":"2024-09-02T10:11:52Z","snapshot_observed_at":"2026-08-12T22:53:10.127791Z","submitted_at":"2024-09-02T10:11:52Z","title":"Large Language Models Can Understanding Depth from Monocular Images","version":1},"cited_work":{"arxiv_id":"2409.01133","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2409.01133","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Large language models can understanding depth from monocular images","venue":null,"work_id":"896d0684-8b98-4480-b087-97e8c5231c53","year":2024},"citing_paper":{"arxiv_id":"2506.09082","last_updated":"2026-05-03T04:37:38Z","snapshot_observed_at":"2026-08-11T14:54:27.718296Z","submitted_at":"2025-06-10T05:43:34Z","title":"AVA-Bench: Atomic Visual Ability Benchmark for Vision Foundation Models","version":5},"reference_index":103,"source":"pdf_text","source_observed_at":"2026-05-19T11:12:41.130806Z"},"links":{"cited_paper":"/paper/2409.01133","citing_paper":"/paper/2506.09082"},"observation_digest":"sha256:48d714e1e322cd393407e005ce8d7f6b21bf53cdc7eadc0f3fa96dbfade50361","observation_id":"714604f2-53d1-4d24-ba05-964988fa3231","resolution":{"observed_at":"2026-05-19T11:13:02.802277Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2409.01133","last_updated":"2024-09-02T10:11:52Z","snapshot_observed_at":"2026-08-12T22:53:10.127791Z","submitted_at":"2024-09-02T10:11:52Z","title":"Large Language Models Can Understanding Depth from Monocular Images","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.01133","snapshot_observed_at":"2026-07-15T14:07:39.892672Z","title":"Large language models can un- derstanding depth from monocular images,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.05962","last_updated":"2026-06-23T00:17:09Z","snapshot_observed_at":"2026-07-15T14:07:39.156464Z","submitted_at":"2026-03-06T06:53:32Z","title":"A novel Framework for Open-Vocabulary Multi-Object Recognition using CLIP","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-07-15T14:07:39.892672Z"},"links":{"cited_paper":"/paper/2409.01133","citing_paper":"/paper/2603.05962"},"observation_digest":"sha256:6b956e76a209e349df907f7c5eb49cb96ed19535f5ce8d70dba16fefcd79c2da","observation_id":"0fa5598e-b729-4188-9b37-d89559577fa9","resolution":{"observed_at":"2026-07-15T14:07:39.892672Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2409.01133/citation-record","integrity":"/paper/2409.01133/integrity","json":"/paper/2409.01133/citation-record.json","paper":"/paper/2409.01133"},"outbound":[],"paper":{"arxiv_id":"2409.01133","last_updated":"2024-09-02T10:11:52Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-12T22:53:10.127791Z","submitted_at":"2024-09-02T10:11:52Z","title":"Large Language Models Can Understanding Depth from Monocular Images"},"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":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"As of 14 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2409.01133."}