{"as_of":"2026-08-09T16:06:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:aab88004b98b584406e3ec8f48bd7968f5e22d97d46ac7235bb1cf85e8b02ab1","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":2,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":2,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-31T23:06:31.757236Z","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":"2026-05-19T11:17:15.498797Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2408.15876","last_updated":"2024-12-23T08:10:30Z","snapshot_observed_at":"2026-08-09T12:56:22.380671Z","submitted_at":"2024-08-28T15:47:32Z","title":"Unleashing the Temporal-Spatial Reasoning Capacity of GPT for Training-Free Audio and Language Referenced Video Object Segmentation","version":2},"cited_work":{"arxiv_id":"2408.15876","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2408.15876","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Unleashing the temporal-spatial reasoning capacity of gpt for training-free audio and language referenced video object segmentation","venue":null,"work_id":"acdca3ea-4916-4703-94a5-f483d04e7ed9","year":2024},"citing_paper":{"arxiv_id":"2506.01015","last_updated":"2026-05-14T17:12:31Z","snapshot_observed_at":"2026-07-06T21:34:34.091508Z","submitted_at":"2025-06-01T13:57:42Z","title":"AuralSAM2: Enabling SAM2 Hear Through Pyramid Audio-Visual Feature Prompting","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-19T11:14:29.394752Z"},"links":{"cited_paper":"/paper/2408.15876","citing_paper":"/paper/2506.01015"},"observation_digest":"sha256:b0da862c1c01050246b5e34cf13ba727c4149f8c8b82ca372d447cee51f63844","observation_id":"31a87636-c882-40e0-a409-5a1f2e71da41","resolution":{"observed_at":"2026-05-19T11:17:15.500490Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2408.15876","last_updated":"2024-12-23T08:10:30Z","snapshot_observed_at":"2026-08-09T12:56:22.380671Z","submitted_at":"2024-08-28T15:47:32Z","title":"Unleashing the Temporal-Spatial Reasoning Capacity of GPT for Training-Free Audio and Language Referenced Video Object Segmentation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.15876","snapshot_observed_at":"2026-07-31T23:06:31.757236Z","title":"Unleashing the temporal- spatial reasoning capacity of GPT for training-free audio and language referenced video object segmentation,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.24098","last_updated":"2026-07-27T07:39:20Z","snapshot_observed_at":"2026-07-31T23:06:30.484084Z","submitted_at":"2026-07-27T07:39:20Z","title":"ReflexTrack: A Feedback-Driven Agent for Training-Free Referring Video Object Segmentation","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:31.757236Z"},"links":{"cited_paper":"/paper/2408.15876","citing_paper":"/paper/2607.24098"},"observation_digest":"sha256:f95227c609a6c648b7327532f13376924ed5bf3ec58eef111895f58b4874c8cb","observation_id":"66aa3088-8e89-40e1-8f36-f058adb30cf0","resolution":{"observed_at":"2026-07-31T23:06:31.757236Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2408.15876/citation-record","integrity":"/paper/2408.15876/integrity","json":"/paper/2408.15876/citation-record.json","paper":"/paper/2408.15876"},"outbound":[],"paper":{"arxiv_id":"2408.15876","last_updated":"2024-12-23T08:10:30Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-09T12:56:22.380671Z","submitted_at":"2024-08-28T15:47:32Z","title":"Unleashing the Temporal-Spatial Reasoning Capacity of GPT for Training-Free Audio and Language Referenced Video Object Segmentation"},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2408.15876."}