{"as_of":"2026-08-07T23:06:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:24beb336d5ebf479a8a7f0c06e794214340e27d882e20fb1d2618d9052be95ea","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":"2026-08-07T11:31:36.348501Z","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":"2026-08-06T16:50:09.964594Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2501.07783","last_updated":"2025-01-14T01:57:41Z","snapshot_observed_at":"2026-07-06T20:20:42.084970Z","submitted_at":"2025-01-14T01:57:41Z","title":"Parameter-Inverted Image Pyramid Networks for Visual Perception and Multimodal Understanding","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.07783","snapshot_observed_at":"2026-08-07T11:31:36.348501Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.02242","last_updated":"2025-06-17T19:05:02Z","snapshot_observed_at":"2026-08-07T11:25:23.855618Z","submitted_at":"2025-06-02T20:40:56Z","title":"From Street Views to Urban Science: Discovering Road Safety Factors with Multimodal Large Language Models","version":2},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-07T11:31:36.348501Z"},"links":{"cited_paper":"/paper/2501.07783","citing_paper":"/paper/2506.02242"},"observation_digest":"sha256:6e1b4421764995128a1b35fbd49be425aa31050c83c592d405536d6451efbb41","observation_id":"fbd66841-47d1-4c4f-9ab3-d5ed719acaa5","resolution":{"observed_at":"2026-08-07T11:31:36.348501Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.07783","last_updated":"2025-01-14T01:57:41Z","snapshot_observed_at":"2026-07-06T20:20:42.084970Z","submitted_at":"2025-01-14T01:57:41Z","title":"Parameter-Inverted Image Pyramid Networks for Visual Perception and Multimodal Understanding","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.07783","snapshot_observed_at":"2026-08-07T00:48:33.338434Z","title":"Parameter-inverted image pyramid networks for visual perception and multimodal understanding","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.12776","last_updated":"2025-06-15T08:58:09Z","snapshot_observed_at":"2026-08-07T00:40:26.860337Z","submitted_at":"2025-06-15T08:58:09Z","title":"Native Visual Understanding: Resolving Resolution Dilemmas in Vision-Language Models","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-07T00:48:33.338434Z"},"links":{"cited_paper":"/paper/2501.07783","citing_paper":"/paper/2506.12776"},"observation_digest":"sha256:93ebdc515e96bc3232b07171ae31b6780a5ac94fa36c35fa69217922123f9146","observation_id":"3b412e13-b0c9-482f-9f09-a2dae75db265","resolution":{"observed_at":"2026-08-07T00:48:33.338434Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.07783","last_updated":"2025-01-14T01:57:41Z","snapshot_observed_at":"2026-07-06T20:20:42.084970Z","submitted_at":"2025-01-14T01:57:41Z","title":"Parameter-Inverted Image Pyramid Networks for Visual Perception and Multimodal Understanding","version":1},"cited_work":{"arxiv_id":"2501.07783","doi":null,"metadata_source":"pith","pith_arxiv_id":"2501.07783","snapshot_observed_at":"2026-08-06T16:50:09.964594Z","title":"Parameter-Inverted Image Pyramid Networks for Visual Perception and Multimodal Understanding","venue":"cs.CV","work_id":"aaeefb6d-84e6-4a1a-9fdf-f3d93d52d694","year":2025},"citing_paper":{"arxiv_id":"2507.12566","last_updated":"2025-07-16T18:31:23Z","snapshot_observed_at":"2026-08-07T02:53:11.371837Z","submitted_at":"2025-07-16T18:31:23Z","title":"Mono-InternVL-1.5: Towards Cheaper and Faster Monolithic Multimodal Large Language Models","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T16:49:57.683627Z"},"links":{"cited_paper":"/paper/2501.07783","citing_paper":"/paper/2507.12566"},"observation_digest":"sha256:88008221288b63e7777d93f0b7dc3d9a83a536f5c48dd5cf543609b9c978d62c","observation_id":"cc75399e-c724-46e9-8338-dbd706c97401","resolution":{"observed_at":"2026-08-06T16:50:10.051759Z","resolver_source":"local_arxiv","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"}}],"links":{"evidence":"/evidence","html":"/paper/2501.07783/citation-record","integrity":"/paper/2501.07783/integrity","json":"/paper/2501.07783/citation-record.json","paper":"/paper/2501.07783"},"outbound":[],"paper":{"arxiv_id":"2501.07783","last_updated":"2025-01-14T01:57:41Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T20:20:42.084970Z","submitted_at":"2025-01-14T01:57:41Z","title":"Parameter-Inverted Image Pyramid Networks for Visual Perception and Multimodal Understanding"},"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:2501.07783."}