{"as_of":"2026-08-07T09:30:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2e3c95fe71afd26e7a322fc20f17018cfd2dc7d891df0c111fdebcd0457c8d1e","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":3,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":3,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-22T23:49:53.830731Z","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":"2026-05-22T23:52:16.998597Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2401.17981","last_updated":"2024-12-19T11:25:34Z","snapshot_observed_at":"2026-07-06T17:23:10.017122Z","submitted_at":"2024-01-31T16:38:32Z","title":"From Training-Free to Adaptive: Empirical Insights into MLLMs' Understanding of Detection Information","version":3},"cited_work":{"arxiv_id":"2401.17981","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2401.17981","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Enhancing multimodal large language models with vision detection models: An empirical study","venue":null,"work_id":"b81845cb-9fa9-4a7f-aad4-8773b3b97abe","year":2024},"citing_paper":{"arxiv_id":"2404.18930","last_updated":"2025-04-01T18:36:08Z","snapshot_observed_at":"2026-08-06T19:08:14.800394Z","submitted_at":"2024-04-29T17:59:41Z","title":"Hallucination of Multimodal Large Language Models: A Survey","version":2},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-05-11T12:33:32.631346Z"},"links":{"cited_paper":"/paper/2401.17981","citing_paper":"/paper/2404.18930"},"observation_digest":"sha256:90c85c48df3239c6f9a06428a14191b94358d34ee23f63ec529c3e90bbdf891f","observation_id":"c23e0095-0742-4fad-b609-a32aadce42c5","resolution":{"observed_at":"2026-05-11T12:33:33.855906Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.17981","last_updated":"2024-12-19T11:25:34Z","snapshot_observed_at":"2026-07-06T17:23:10.017122Z","submitted_at":"2024-01-31T16:38:32Z","title":"From Training-Free to Adaptive: Empirical Insights into MLLMs' Understanding of Detection Information","version":3},"cited_work":{"arxiv_id":"2401.17981","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2401.17981","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Enhancing multimodal large language models with vision detection models: An empirical study","venue":null,"work_id":"b81845cb-9fa9-4a7f-aad4-8773b3b97abe","year":2024},"citing_paper":{"arxiv_id":"2503.12844","last_updated":"2026-04-30T06:09:00Z","snapshot_observed_at":"2026-07-06T20:53:41.124209Z","submitted_at":"2025-03-17T05:43:40Z","title":"GuideDog: A Real-World Egocentric Multimodal Dataset for Blind and Low-Vision Accessibility-Aware Guidance","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-22T23:49:53.830731Z"},"links":{"cited_paper":"/paper/2401.17981","citing_paper":"/paper/2503.12844"},"observation_digest":"sha256:b53ed5cf9ffe3586a0b4a4937fc1e572f47dcb835362d6dcdcd333b482e07e12","observation_id":"d13d84bd-7232-4e53-b3d6-a2e7017228b7","resolution":{"observed_at":"2026-05-22T23:52:17.001914Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.17981","last_updated":"2024-12-19T11:25:34Z","snapshot_observed_at":"2026-07-06T17:23:10.017122Z","submitted_at":"2024-01-31T16:38:32Z","title":"From Training-Free to Adaptive: Empirical Insights into MLLMs' Understanding of Detection Information","version":3},"cited_work":{"arxiv_id":"2401.17981","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2401.17981","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Enhancing multimodal large language models with vision detection models: An empirical study","venue":null,"work_id":"b81845cb-9fa9-4a7f-aad4-8773b3b97abe","year":2024},"citing_paper":{"arxiv_id":"2605.01359","last_updated":"2026-05-02T10:08:10Z","snapshot_observed_at":"2026-08-02T20:31:00.269826Z","submitted_at":"2026-05-02T10:08:10Z","title":"Structural Ranking of the Cognitive Plausibility of Computational Models of Analogy and Metaphors with the Minimal Cognitive Grid","version":1},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-05-09T14:33:11.033906Z"},"links":{"cited_paper":"/paper/2401.17981","citing_paper":"/paper/2605.01359"},"observation_digest":"sha256:a28b5dbeb2501ca6fa3c18c91fa981f34786b47bbd1b07031742dd2b534fc3a8","observation_id":"d3cf4ee8-985c-4814-ae1a-436893aeb75f","resolution":{"observed_at":"2026-05-11T16:56:06.132399Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2401.17981/citation-record","integrity":"/paper/2401.17981/integrity","json":"/paper/2401.17981/citation-record.json","paper":"/paper/2401.17981"},"outbound":[],"paper":{"arxiv_id":"2401.17981","last_updated":"2024-12-19T11:25:34Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T17:23:10.017122Z","submitted_at":"2024-01-31T16:38:32Z","title":"From Training-Free to Adaptive: Empirical Insights into MLLMs' Understanding of Detection Information"},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2401.17981."}