{"as_of":"2026-08-22T18:25:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a618c7f751a0a349a332c965f18c4b54d0a038573350553552a8c66b079c9a0e","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":"2026-08-22T06:32:14.747728+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":"2026-08-16T04:54:19.499010Z","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":"2026-08-07T14:45:32.487571Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2405.14612","last_updated":"2024-05-28T11:18:20Z","snapshot_observed_at":"2026-08-16T13:50:10.893128Z","submitted_at":"2024-05-23T14:24:23Z","title":"Explaining Multi-modal Large Language Models by Analyzing their Vision Perception","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.14612","snapshot_observed_at":"2026-08-16T04:54:19.499010Z","title":"Explaining multi-modal large language models by analyzing their vision perception","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.03788","last_updated":"2025-04-30T19:19:21Z","snapshot_observed_at":"2026-08-20T02:18:06.101023Z","submitted_at":"2025-04-30T19:19:21Z","title":"Calibrating Uncertainty Quantification of Multi-Modal LLMs using Grounding","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-16T04:54:19.499010Z"},"links":{"cited_paper":"/paper/2405.14612","citing_paper":"/paper/2505.03788"},"observation_digest":"sha256:6ac0faf20672b20c0f0a46792e605eae749d6d0c62c101d0a7b3af60459b6548","observation_id":"98f50b02-9378-4573-9b5b-31142428528c","resolution":{"observed_at":"2026-08-16T04:54:19.499010Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.14612","last_updated":"2024-05-28T11:18:20Z","snapshot_observed_at":"2026-08-16T13:50:10.893128Z","submitted_at":"2024-05-23T14:24:23Z","title":"Explaining Multi-modal Large Language Models by Analyzing their Vision Perception","version":2},"cited_work":{"arxiv_id":"2405.14612","doi":null,"metadata_source":"pith","pith_arxiv_id":"2405.14612","snapshot_observed_at":"2026-08-07T14:45:32.487571Z","title":"Explaining Multi-modal Large Language Models by Analyzing their Vision Perception","venue":"cs.CV","work_id":"21632da1-a336-4490-bdcb-03a02bddcc70","year":2024},"citing_paper":{"arxiv_id":"2505.17812","last_updated":"2025-05-23T12:29:00Z","snapshot_observed_at":"2026-08-19T10:15:10.249589Z","submitted_at":"2025-05-23T12:29:00Z","title":"Seeing It or Not? Interpretable Vision-aware Latent Steering to Mitigate Object Hallucinations","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T14:45:30.624312Z"},"links":{"cited_paper":"/paper/2405.14612","citing_paper":"/paper/2505.17812"},"observation_digest":"sha256:5f59b37bc0e0a715f182c1a1500b2d20ea86cb5afd2a025be929a8763d310f2c","observation_id":"3519c456-6106-4f20-b0df-74c2d34808f7","resolution":{"observed_at":"2026-08-07T14:45:32.614357Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2405.14612/citation-record","integrity":"/paper/2405.14612/integrity","json":"/paper/2405.14612/citation-record.json","paper":"/paper/2405.14612"},"outbound":[],"paper":{"arxiv_id":"2405.14612","last_updated":"2024-05-28T11:18:20Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-16T13:50:10.893128Z","submitted_at":"2024-05-23T14:24:23Z","title":"Explaining Multi-modal Large Language Models by Analyzing their Vision Perception"},"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":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2405.14612."}