{"as_of":"2026-08-09T20:55:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:777336245af3a73cc5bd203c1ddb7bef82bbfd84cb6f639416583c5e0256f24d","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":"2026-08-09T06:31:02.800959+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":"2026-08-04T20:28:21.986990Z","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":"2026-05-11T10:31:03.888372Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2312.17345","last_updated":"2025-01-15T12:46:07Z","snapshot_observed_at":"2026-08-09T03:24:14.032286Z","submitted_at":"2023-12-28T20:26:03Z","title":"3VL: Using Trees to Improve Vision-Language Models' Interpretability","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.17345","snapshot_observed_at":"2026-08-04T20:28:21.986990Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.09732","last_updated":"2025-09-10T13:08:03Z","snapshot_observed_at":"2026-08-09T18:45:49.898879Z","submitted_at":"2025-09-10T13:08:03Z","title":"Decomposing Visual Classification: Assessing Tree-Based Reasoning in VLMs","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-04T20:28:21.986990Z"},"links":{"cited_paper":"/paper/2312.17345","citing_paper":"/paper/2509.09732"},"observation_digest":"sha256:b17685f5178c99322785882d14f9159bc43c10fe0561ad2b6ab93bfdda94ac15","observation_id":"45d68678-604d-4ed8-9009-15a463208fe4","resolution":{"observed_at":"2026-08-04T20:28:21.986990Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.17345","last_updated":"2025-01-15T12:46:07Z","snapshot_observed_at":"2026-08-09T03:24:14.032286Z","submitted_at":"2023-12-28T20:26:03Z","title":"3VL: Using Trees to Improve Vision-Language Models' Interpretability","version":2},"cited_work":{"arxiv_id":"2312.17345","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2312.17345","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"3vl: us- ing trees to teach vision & language models compositional concepts.arXiv preprint arXiv:2312.17345, 2","venue":null,"work_id":"68854198-3ba2-4c8f-90fe-f2b015bd777e","year":2023},"citing_paper":{"arxiv_id":"2604.12335","last_updated":"2026-04-14T06:17:35Z","snapshot_observed_at":"2026-07-06T23:00:32.607699Z","submitted_at":"2026-04-14T06:17:35Z","title":"All in One: A Unified Synthetic Data Pipeline for Multimodal Video Understanding","version":1},"reference_index":100,"source":"pdf_text","source_observed_at":"2026-05-10T15:26:55.369840Z"},"links":{"cited_paper":"/paper/2312.17345","citing_paper":"/paper/2604.12335"},"observation_digest":"sha256:f400cb2a5a2cea1d1e243d8c8a79dc0cb735ac4a5dd3bea7940c79cc46e62bd9","observation_id":"d5dac9c3-cad0-4b04-93a0-86959c08f660","resolution":{"observed_at":"2026-05-11T10:31:03.892950Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2312.17345/citation-record","integrity":"/paper/2312.17345/integrity","json":"/paper/2312.17345/citation-record.json","paper":"/paper/2312.17345"},"outbound":[],"paper":{"arxiv_id":"2312.17345","last_updated":"2025-01-15T12:46:07Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-09T03:24:14.032286Z","submitted_at":"2023-12-28T20:26:03Z","title":"3VL: Using Trees to Improve Vision-Language Models' Interpretability"},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2312.17345."}