{"as_of":"2026-08-09T15:44:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:32c4dd668dc20978eefc9426f940f397589ed9e517d2614f9f71b77dd53c5fb6","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":"2026-08-01T11:16:11.595838Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"arxiv_reference","source_observed_at":"2026-08-05T02:28:24.338817Z","state":"measured"}],"external_citation_measurements":[{"count":1,"observed_at":"2026-08-05T02:28:24.338817Z","source":"arxiv_reference"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2404.08755","last_updated":"2024-04-12T18:28:44Z","snapshot_observed_at":"2026-08-04T02:35:48.210622Z","submitted_at":"2024-04-12T18:28:44Z","title":"Training a Vision Language Model as Smartphone Assistant","version":1},"cited_work":{"arxiv_id":"2404.08755","doi":"10.48550/arxiv.2404.08755","metadata_source":"arxiv_reference","pith_arxiv_id":"2404.08755","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":null,"venue":"arXiv (Cornell University)","work_id":"38e07e33-19d0-4599-b26a-218ae6f8bced","year":2024},"citing_paper":{"arxiv_id":"2501.16150","last_updated":"2026-03-27T07:41:10Z","snapshot_observed_at":"2026-08-02T22:37:46.736145Z","submitted_at":"2025-01-27T15:44:02Z","title":"A Comprehensive Survey of Agents for Computer Use: Foundations, Challenges, and Future Directions","version":3},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-05-23T04:59:36.994758Z"},"links":{"cited_paper":"/paper/2404.08755","citing_paper":"/paper/2501.16150"},"observation_digest":"sha256:e436b236a56c99271a93b8493a1de0f8a7cde923b3668e132827f66c4cdf4ce5","observation_id":"697a33a3-ee73-4127-9afc-bd11d0624b55","resolution":{"observed_at":"2026-05-23T05:02:35.306200Z","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":"2404.08755","last_updated":"2024-04-12T18:28:44Z","snapshot_observed_at":"2026-08-04T02:35:48.210622Z","submitted_at":"2024-04-12T18:28:44Z","title":"Training a Vision Language Model as Smartphone Assistant","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.08755","snapshot_observed_at":"2026-08-01T11:16:11.595838Z","title":"Training a vision language model as smartphone assistant,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.19949","last_updated":"2026-07-30T13:38:59Z","snapshot_observed_at":"2026-08-06T18:33:41.738909Z","submitted_at":"2026-07-22T09:25:47Z","title":"SenWorld: A Digital-Twin Simulation for Generating Context-Rich Evaluation Data","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-01T11:16:11.595838Z"},"links":{"cited_paper":"/paper/2404.08755","citing_paper":"/paper/2607.19949"},"observation_digest":"sha256:949a39bbf70293f640a2f0994f47ed6916bee1e70c214cc77f1f253c63258575","observation_id":"5fe55f0f-b8cb-4772-9820-5fa2c5d4dd13","resolution":{"observed_at":"2026-08-01T11:16:11.595838Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2404.08755/citation-record","integrity":"/paper/2404.08755/integrity","json":"/paper/2404.08755/citation-record.json","paper":"/paper/2404.08755"},"outbound":[],"paper":{"arxiv_id":"2404.08755","last_updated":"2024-04-12T18:28:44Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-04T02:35:48.210622Z","submitted_at":"2024-04-12T18:28:44Z","title":"Training a Vision Language Model as Smartphone Assistant"},"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:2404.08755."}