{"as_of":"2026-08-15T18:18:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:46e9d18bd1bb63a75689facf998ff6426ae9567f2eb258fbb53c793f864d79b7","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":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-15T06:32:42.880941+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T14:38:24.510393Z","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":"2026-08-05T06:00:51.350724Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2409.09269","last_updated":"2024-12-12T06:26:09Z","snapshot_observed_at":"2026-08-14T20:13:19.875821Z","submitted_at":"2024-09-14T02:29:36Z","title":"Guiding Vision-Language Model Selection for Visual Question-Answering Across Tasks, Domains, and Knowledge Types","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.09269","snapshot_observed_at":"2026-08-10T14:38:24.510393Z","title":"Sinha, V","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.15144","last_updated":"2025-09-02T09:32:21Z","snapshot_observed_at":"2026-08-14T01:59:28.492817Z","submitted_at":"2025-01-25T09:01:37Z","title":"Exploring Primitive Visual Measurement Understanding and the Role of Output Format in Learning in Vision-Language Models","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-10T14:38:24.510393Z"},"links":{"cited_paper":"/paper/2409.09269","citing_paper":"/paper/2501.15144"},"observation_digest":"sha256:b0348b0062e18bc6032f0c901063ad34342cc160467a5885bc32a9b75eb50e62","observation_id":"e1cdf967-880c-4933-8791-c87a16da6ac7","resolution":{"observed_at":"2026-08-10T14:38:24.510393Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.09269","last_updated":"2024-12-12T06:26:09Z","snapshot_observed_at":"2026-08-14T20:13:19.875821Z","submitted_at":"2024-09-14T02:29:36Z","title":"Guiding Vision-Language Model Selection for Visual Question-Answering Across Tasks, Domains, and Knowledge Types","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.09269","snapshot_observed_at":"2026-08-07T12:42:26.230104Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.24073","last_updated":"2025-08-26T16:42:37Z","snapshot_observed_at":"2026-08-14T14:49:06.501028Z","submitted_at":"2025-05-29T23:32:03Z","title":"mRAG: Elucidating the Design Space of Multi-modal Retrieval-Augmented Generation","version":2},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-07T12:42:26.230104Z"},"links":{"cited_paper":"/paper/2409.09269","citing_paper":"/paper/2505.24073"},"observation_digest":"sha256:9bbc984ccdeb0dc9105051e8338eadab8987744feffac647f2fc8249d52e97cb","observation_id":"972b39de-f9f1-4869-8d3f-f0302f40b985","resolution":{"observed_at":"2026-08-07T12:42:26.230104Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.09269","last_updated":"2024-12-12T06:26:09Z","snapshot_observed_at":"2026-08-14T20:13:19.875821Z","submitted_at":"2024-09-14T02:29:36Z","title":"Guiding Vision-Language Model Selection for Visual Question-Answering Across Tasks, Domains, and Knowledge Types","version":3},"cited_work":{"arxiv_id":"2409.09269","doi":null,"metadata_source":"pith","pith_arxiv_id":"2409.09269","snapshot_observed_at":"2026-08-05T06:00:51.350724Z","title":"Guiding Vision-Language Model Selection for Visual Question-Answering Across Tasks, Domains, and Knowledge Types","venue":"cs.CV","work_id":"4cd32a42-188c-4e8e-9557-93f469ab3399","year":2024},"citing_paper":{"arxiv_id":"2509.04714","last_updated":"2025-09-05T00:02:17Z","snapshot_observed_at":"2026-08-12T10:20:32.657465Z","submitted_at":"2025-09-05T00:02:17Z","title":"ThumbnailTruth: A Multi-Modal LLM Approach for Detecting Misleading YouTube Thumbnails Across Diverse Cultural Settings","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-05T06:00:51.153341Z"},"links":{"cited_paper":"/paper/2409.09269","citing_paper":"/paper/2509.04714"},"observation_digest":"sha256:b551656721fa2efd8206db691f69c9b4f47823a28ea5d607cff78ab436e588b0","observation_id":"78516360-e734-4766-aeda-f61552fbad6b","resolution":{"observed_at":"2026-08-05T06:00:51.355154Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2409.09269","last_updated":"2024-12-12T06:26:09Z","snapshot_observed_at":"2026-08-14T20:13:19.875821Z","submitted_at":"2024-09-14T02:29:36Z","title":"Guiding Vision-Language Model Selection for Visual Question-Answering Across Tasks, Domains, and Knowledge Types","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.09269","snapshot_observed_at":"2026-07-30T14:24:34.414745Z","title":"Sinha, N.; Jain, V .; and Chadha, A","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.23739","last_updated":"2026-07-26T16:25:43Z","snapshot_observed_at":"2026-08-09T01:26:17.776917Z","submitted_at":"2026-07-26T16:25:43Z","title":"Separating Clicks from Baits: Using Large Language Models to Detect Misleading YouTube Thumbnails","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-07-30T14:24:34.414745Z"},"links":{"cited_paper":"/paper/2409.09269","citing_paper":"/paper/2607.23739"},"observation_digest":"sha256:0a119f249e733c5b98f70f25178f3513545b67ceaf3374a7eb2ea86d61993937","observation_id":"4e9bc20e-cc8d-4894-ad95-160116fb95a6","resolution":{"observed_at":"2026-07-30T14:24:34.414745Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2409.09269/citation-record","integrity":"/paper/2409.09269/integrity","json":"/paper/2409.09269/citation-record.json","paper":"/paper/2409.09269"},"outbound":[],"paper":{"arxiv_id":"2409.09269","last_updated":"2024-12-12T06:26:09Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-14T20:13:19.875821Z","submitted_at":"2024-09-14T02:29:36Z","title":"Guiding Vision-Language Model Selection for Visual Question-Answering Across Tasks, Domains, and Knowledge Types"},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2409.09269."}