{"as_of":"2026-08-07T03:28:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:cc5d3debee035091aa4473737253ea93f3f8d06e63f560517ac25d2cb28d08ce","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":"2026-08-06T06:34:29.942622+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":"2026-08-06T17:41:00.759081Z","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":"2026-08-06T17:01:57.806315Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2502.09093","last_updated":"2025-02-13T09:04:28Z","snapshot_observed_at":"2026-07-06T20:35:49.677643Z","submitted_at":"2025-02-13T09:04:28Z","title":"From Visuals to Vocabulary: Establishing Equivalence Between Image and Text Token Through Autoregressive Pre-training in MLLMs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.09093","snapshot_observed_at":"2026-08-06T17:41:00.759081Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.10358","last_updated":"2025-07-14T15:00:00Z","snapshot_observed_at":"2026-08-06T17:30:32.470106Z","submitted_at":"2025-07-14T15:00:00Z","title":"Fine-Grained Zero-Shot Object Detection","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T17:41:00.759081Z"},"links":{"cited_paper":"/paper/2502.09093","citing_paper":"/paper/2507.10358"},"observation_digest":"sha256:ea8f96b1d2298df3e7bec512cbb658c89e01e2569b453ad7a9030a0f9cdf06da","observation_id":"632c63cb-2672-46d3-aba3-c5fc92bcb754","resolution":{"observed_at":"2026-08-06T17:41:00.759081Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.09093","last_updated":"2025-02-13T09:04:28Z","snapshot_observed_at":"2026-07-06T20:35:49.677643Z","submitted_at":"2025-02-13T09:04:28Z","title":"From Visuals to Vocabulary: Establishing Equivalence Between Image and Text Token Through Autoregressive Pre-training in MLLMs","version":1},"cited_work":{"arxiv_id":"2502.09093","doi":null,"metadata_source":"pith","pith_arxiv_id":"2502.09093","snapshot_observed_at":"2026-08-06T17:01:57.806315Z","title":"From Visuals to Vocabulary: Establishing Equivalence Between Image and Text Token Through Autoregressive Pre-training in MLLMs","venue":"cs.CV","work_id":"95d71121-97a0-4093-ad0f-5c4f5fa14313","year":2025},"citing_paper":{"arxiv_id":"2507.12062","last_updated":"2025-07-16T09:18:18Z","snapshot_observed_at":"2026-08-06T16:52:40.556769Z","submitted_at":"2025-07-16T09:18:18Z","title":"MS-DETR: Towards Effective Video Moment Retrieval and Highlight Detection by Joint Motion-Semantic Learning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T17:01:52.483519Z"},"links":{"cited_paper":"/paper/2502.09093","citing_paper":"/paper/2507.12062"},"observation_digest":"sha256:e34216270d3d4f2075161ced9cdd7d4bf18e0d3ae586be924d20fb479d998d5e","observation_id":"555e1e01-2bda-4b0d-a871-6c919cc3702e","resolution":{"observed_at":"2026-08-06T17:01:57.864030Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2502.09093/citation-record","integrity":"/paper/2502.09093/integrity","json":"/paper/2502.09093/citation-record.json","paper":"/paper/2502.09093"},"outbound":[],"paper":{"arxiv_id":"2502.09093","last_updated":"2025-02-13T09:04:28Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T20:35:49.677643Z","submitted_at":"2025-02-13T09:04:28Z","title":"From Visuals to Vocabulary: Establishing Equivalence Between Image and Text Token Through Autoregressive Pre-training in MLLMs"},"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":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2502.09093."}