{"as_of":"2026-08-22T12:05:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3e6ef0a679c229e8d05cffda39508a30aea994f8ae6508b59c529b7e68e81390","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":"2026-08-22T06:32:14.747728+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":"2026-08-15T20:26:58.255579Z","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":"2026-08-10T14:38:24.730733Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2406.14544","last_updated":"2024-06-20T17:54:03Z","snapshot_observed_at":"2026-08-16T13:41:00.258560Z","submitted_at":"2024-06-20T17:54:03Z","title":"Prism: A Framework for Decoupling and Assessing the Capabilities of VLMs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.14544","snapshot_observed_at":"2026-08-12T14:31:37.606322Z","title":"Prism: A framework for decoupling and assessing the capabilities of vlms,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.15296","last_updated":"2024-12-08T04:24:31Z","snapshot_observed_at":"2026-08-18T21:58:09.907460Z","submitted_at":"2024-11-22T18:59:54Z","title":"MME-Survey: A Comprehensive Survey on Evaluation of Multimodal LLMs","version":2},"reference_index":219,"source":"pdf_text","source_observed_at":"2026-08-12T14:31:37.606322Z"},"links":{"cited_paper":"/paper/2406.14544","citing_paper":"/paper/2411.15296"},"observation_digest":"sha256:6edaf8805127d31a8d4d3a7b66bfc12f1567ecba876fb461b064095f2ae786bc","observation_id":"ecfdc766-c689-4f44-8ca1-d2c8c248d4fe","resolution":{"observed_at":"2026-08-12T14:31:37.606322Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.14544","last_updated":"2024-06-20T17:54:03Z","snapshot_observed_at":"2026-08-16T13:41:00.258560Z","submitted_at":"2024-06-20T17:54:03Z","title":"Prism: A Framework for Decoupling and Assessing the Capabilities of VLMs","version":1},"cited_work":{"arxiv_id":"2406.14544","doi":null,"metadata_source":"pith","pith_arxiv_id":"2406.14544","snapshot_observed_at":"2026-08-10T14:38:24.730733Z","title":"Prism: A Framework for Decoupling and Assessing the Capabilities of VLMs","venue":"cs.CV","work_id":"bf926c71-6044-4d03-aee7-209bf6897cb3","year":2024},"citing_paper":{"arxiv_id":"2501.15144","last_updated":"2025-09-02T09:32:21Z","snapshot_observed_at":"2026-08-20T06:02:49.052240Z","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":13,"source":"pdf_text","source_observed_at":"2026-08-10T14:38:24.228150Z"},"links":{"cited_paper":"/paper/2406.14544","citing_paper":"/paper/2501.15144"},"observation_digest":"sha256:d3224ac8cea78b24ff0b64cf0e0d5e0c13cdb2810152aa2900ef536c4aa47035","observation_id":"b1114157-1104-4bb7-a156-a3ff464717d8","resolution":{"observed_at":"2026-08-10T14:38:24.771826Z","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"}},{"citation":{"cited_paper":{"arxiv_id":"2406.14544","last_updated":"2024-06-20T17:54:03Z","snapshot_observed_at":"2026-08-16T13:41:00.258560Z","submitted_at":"2024-06-20T17:54:03Z","title":"Prism: A Framework for Decoupling and Assessing the Capabilities of VLMs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.14544","snapshot_observed_at":"2026-08-15T20:26:58.255579Z","title":"arXiv preprint arXiv:2406.14544 (2024)","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.13031","last_updated":"2025-06-11T15:44:25Z","snapshot_observed_at":"2026-08-17T23:10:01.694062Z","submitted_at":"2025-05-19T12:17:04Z","title":"MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T20:26:58.255579Z"},"links":{"cited_paper":"/paper/2406.14544","citing_paper":"/paper/2505.13031"},"observation_digest":"sha256:d8d1dc72c50962c46439d93e393ef3e1835684ce709fb030182bdab6dd7cbf00","observation_id":"c2050e8c-61c5-498d-b050-32f0d785b733","resolution":{"observed_at":"2026-08-15T20:26:58.255579Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.14544","last_updated":"2024-06-20T17:54:03Z","snapshot_observed_at":"2026-08-16T13:41:00.258560Z","submitted_at":"2024-06-20T17:54:03Z","title":"Prism: A Framework for Decoupling and Assessing the Capabilities of VLMs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.14544","snapshot_observed_at":"2026-08-15T18:30:21.537076Z","title":"Prism: A framework for decoupling and assessing the capabilities of vlms.arXiv preprint arXiv:2406.14544, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.19848","last_updated":"2025-06-24T17:59:55Z","snapshot_observed_at":"2026-08-20T06:25:49.912409Z","submitted_at":"2025-06-24T17:59:55Z","title":"ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-15T18:30:21.537076Z"},"links":{"cited_paper":"/paper/2406.14544","citing_paper":"/paper/2506.19848"},"observation_digest":"sha256:ad9f44fb69a87c1524d53c17171cebda573eb685de99ff23ec04f9fc418b20dc","observation_id":"336d5bca-329a-45bd-a2d9-d90580afc681","resolution":{"observed_at":"2026-08-15T18:30:21.537076Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2406.14544/citation-record","integrity":"/paper/2406.14544/integrity","json":"/paper/2406.14544/citation-record.json","paper":"/paper/2406.14544"},"outbound":[],"paper":{"arxiv_id":"2406.14544","last_updated":"2024-06-20T17:54:03Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-16T13:41:00.258560Z","submitted_at":"2024-06-20T17:54:03Z","title":"Prism: A Framework for Decoupling and Assessing the Capabilities of VLMs"},"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 4 inbound Pith citation observations for arXiv:2406.14544."}