{"as_of":"2026-08-14T09:51:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a58ab6f1dfb0cbb7cd9a67ed5a2cda30fa692b43a0609ed3df80136efc29220c","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":"2026-08-14T06:32:32.682623+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":"2026-08-12T14:09:18.267141Z","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":"2026-08-10T21:31:16.756614Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2411.01756","last_updated":"2024-12-16T12:53:25Z","snapshot_observed_at":"2026-08-12T22:08:40.056053Z","submitted_at":"2024-11-04T02:43:55Z","title":"ChatTracker: Enhancing Visual Tracking Performance via Chatting with Multimodal Large Language Model","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.01756","snapshot_observed_at":"2026-08-12T14:09:18.267141Z","title":"Chat- tracker: Enhancing visual tracking performance via chat- ting with multimodal large language model","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.15600","last_updated":"2024-11-23T16:31:40Z","snapshot_observed_at":"2026-08-14T01:49:02.167455Z","submitted_at":"2024-11-23T16:31:40Z","title":"How Texts Help? A Fine-grained Evaluation to Reveal the Role of Language in Vision-Language Tracking","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-12T14:09:18.267141Z"},"links":{"cited_paper":"/paper/2411.01756","citing_paper":"/paper/2411.15600"},"observation_digest":"sha256:c5b18d3d1f9e35f55306a8e160a3befe2f13bfdcf09eef96e83af5cfe708d464","observation_id":"5ad3aaec-2001-450f-905c-ef1547a5e252","resolution":{"observed_at":"2026-08-12T14:09:18.267141Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.01756","last_updated":"2024-12-16T12:53:25Z","snapshot_observed_at":"2026-08-12T22:08:40.056053Z","submitted_at":"2024-11-04T02:43:55Z","title":"ChatTracker: Enhancing Visual Tracking Performance via Chatting with Multimodal Large Language Model","version":2},"cited_work":{"arxiv_id":"2411.01756","doi":null,"metadata_source":"pith","pith_arxiv_id":"2411.01756","snapshot_observed_at":"2026-08-10T21:31:16.756614Z","title":"ChatTracker: Enhancing Visual Tracking Performance via Chatting with Multimodal Large Language Model","venue":"cs.CV","work_id":"480e6d56-a4f8-4c5e-abd5-14e3980429d8","year":2024},"citing_paper":{"arxiv_id":"2501.04670","last_updated":"2025-07-09T08:04:21Z","snapshot_observed_at":"2026-08-14T03:18:34.834807Z","submitted_at":"2025-01-08T18:30:53Z","title":"Are They the Same? Exploring Visual Correspondence Shortcomings of Multimodal LLMs","version":3},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-10T21:31:16.244193Z"},"links":{"cited_paper":"/paper/2411.01756","citing_paper":"/paper/2501.04670"},"observation_digest":"sha256:d483bf83c710997b669231aa0cb9eefc8b11dee5ff67fa9998baa9d7f232ab62","observation_id":"d508a717-b65a-4bbb-b85a-e51aa83eb981","resolution":{"observed_at":"2026-08-10T21:31:16.760989Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2411.01756/citation-record","integrity":"/paper/2411.01756/integrity","json":"/paper/2411.01756/citation-record.json","paper":"/paper/2411.01756"},"outbound":[],"paper":{"arxiv_id":"2411.01756","last_updated":"2024-12-16T12:53:25Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-12T22:08:40.056053Z","submitted_at":"2024-11-04T02:43:55Z","title":"ChatTracker: Enhancing Visual Tracking Performance via Chatting with Multimodal Large Language Model"},"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":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"As of 14 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2411.01756."}