{"as_of":"2026-08-23T13:28:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a95c887ac5a167f7f34b71c910e8057f90a895f0e47e7c897b01b0dc25340cd0","coverage":[{"denominator":4,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-12T11:14:52.015620Z","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":"2026-08-23T06:30:58.430688+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2606.28862/citation-record","integrity":"/paper/2606.28862/integrity","json":"/paper/2606.28862/citation-record.json","paper":"/paper/2606.28862"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2406.16866","last_updated":"2024-06-24T17:59:58Z","snapshot_observed_at":"2026-08-17T23:37:39.032985Z","submitted_at":"2024-06-24T17:59:58Z","title":"Revisiting Referring Expression Comprehension Evaluation in the Era of Large Multimodal Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.16866","snapshot_observed_at":"2026-07-12T11:14:52.015620Z","title":"Cheng, T.; Song, L.; Ge, Y.; Liu, W.; Wang, X.; and Shan, Y.2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.28862","last_updated":"2026-07-05T22:18:45Z","snapshot_observed_at":"2026-08-18T13:51:03.891802Z","submitted_at":"2026-06-27T11:10:33Z","title":"HKVLM: Faithful Query--Region Binding for Frozen-Detector Visual Grounding","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-07-12T11:14:52.015620Z"},"links":{"cited_paper":"/paper/2406.16866","citing_paper":"/paper/2606.28862"},"observation_digest":"sha256:d4399d0286281517a92a5f98d7e664d0d47f5ab2e3011a68e9ee726c84f43ed9","observation_id":"a2cf8f59-6714-45bc-8395-4bdbb072b083","resolution":{"observed_at":"2026-07-12T11:14:52.015620Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1809.02156","last_updated":"2019-03-29T23:48:52Z","snapshot_observed_at":"2026-08-16T11:34:00.114590Z","submitted_at":"2018-09-06T18:25:18Z","title":"Object Hallucination in Image Captioning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1809.02156","snapshot_observed_at":"2026-07-12T11:14:52.015620Z","title":"Rohrbach, A.; Hendricks, L","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2606.28862","last_updated":"2026-07-05T22:18:45Z","snapshot_observed_at":"2026-08-18T13:51:03.891802Z","submitted_at":"2026-06-27T11:10:33Z","title":"HKVLM: Faithful Query--Region Binding for Frozen-Detector Visual Grounding","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-07-12T11:14:52.015620Z"},"links":{"cited_paper":"/paper/1809.02156","citing_paper":"/paper/2606.28862"},"observation_digest":"sha256:68bf81407f70dd2c1eb55f655fdefd8c632bbd847695da6f38832716fee278c3","observation_id":"259d4117-c0f9-4fda-88f8-bdf868c4f613","resolution":{"observed_at":"2026-07-12T11:14:52.015620Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2508.10104","last_updated":"2025-08-13T18:00:55Z","snapshot_observed_at":"2026-08-18T01:07:23.737664Z","submitted_at":"2025-08-13T18:00:55Z","title":"DINOv3","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2508.10104","snapshot_observed_at":"2026-07-12T11:14:52.015620Z","title":"Wang, P.; Bai, S.; Tan, S.; Wang, S.; Fan, Z.; Bai, J.; Chen, K.; Liu, X.; Wang, J.; Ge, W.; Fan, Y.; Dang, K.; Du, M.; Ren, X.; Men, R.; Liu, D.; Zhou, C.; Zhou, J.; and Lin, J","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.28862","last_updated":"2026-07-05T22:18:45Z","snapshot_observed_at":"2026-08-18T13:51:03.891802Z","submitted_at":"2026-06-27T11:10:33Z","title":"HKVLM: Faithful Query--Region Binding for Frozen-Detector Visual Grounding","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-07-12T11:14:52.015620Z"},"links":{"cited_paper":"/paper/2508.10104","citing_paper":"/paper/2606.28862"},"observation_digest":"sha256:e81b3d0e3e8596a337f673b210dd46f21c153ef2db8bf485e83a0c1a4ff926f3","observation_id":"1b71a4a2-9dfa-4352-8c33-dd56bbf29a47","resolution":{"observed_at":"2026-07-12T11:14:52.015620Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.12191","last_updated":"2024-10-03T15:54:49Z","snapshot_observed_at":"2026-08-06T05:35:29.109022Z","submitted_at":"2024-09-18T17:59:32Z","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.12191","snapshot_observed_at":"2026-07-12T11:14:52.015620Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.28862","last_updated":"2026-07-05T22:18:45Z","snapshot_observed_at":"2026-08-18T13:51:03.891802Z","submitted_at":"2026-06-27T11:10:33Z","title":"HKVLM: Faithful Query--Region Binding for Frozen-Detector Visual Grounding","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-07-12T11:14:52.015620Z"},"links":{"cited_paper":"/paper/2409.12191","citing_paper":"/paper/2606.28862"},"observation_digest":"sha256:db1264a6fb248618829d99435b3459211f765dc66e515c77e7f5a2dd79940143","observation_id":"ac3fc0f9-a43e-4df2-9854-7dcbb289dca9","resolution":{"observed_at":"2026-07-12T11:14:52.015620Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2606.28862","last_updated":"2026-07-05T22:18:45Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-18T13:51:03.891802Z","submitted_at":"2026-06-27T11:10:33Z","title":"HKVLM: Faithful Query--Region Binding for Frozen-Detector Visual Grounding"},"reference_resolution":{"displayed":4,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":4,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":4},"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":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"thesis":"As of 23 August 2026, this Paper Citation Record lists 4 of 4 outbound references and 0 inbound Pith citation observations for arXiv:2606.28862."}