{"as_of":"2026-08-17T19:28:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:02a1e55e394e67413c0a57a866bd31cc668572907b383c2a9d9411752ca8565e","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":"2026-08-17T06:30:58.91139+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":"2026-08-12T16:27:47.796305Z","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":2,"observed_at":"2026-08-05T02:28:24.338817Z","source":"arxiv_reference"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2203.07828","last_updated":"2022-03-15T12:32:28Z","snapshot_observed_at":"2026-08-16T17:14:27.455898Z","submitted_at":"2022-03-15T12:32:28Z","title":"Do BERTs Learn to Use Browser User Interface? Exploring Multi-Step Tasks with Unified Vision-and-Language BERTs","version":1},"cited_work":{"arxiv_id":"2203.07828","doi":"10.48550/arxiv.2203.07828","metadata_source":"arxiv_reference","pith_arxiv_id":"2203.07828","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Do BERTs learn to use browser user interface? Exploring multi-step tasks with unified vision-and-language berts","venue":"arXiv (Cornell University)","work_id":"f4ec2591-3aeb-428d-a6b5-60270ff7b722","year":2022},"citing_paper":{"arxiv_id":"2303.17491","last_updated":"2023-11-16T20:15:14Z","snapshot_observed_at":"2026-08-14T05:01:21.886306Z","submitted_at":"2023-03-30T16:01:52Z","title":"Language Models can Solve Computer Tasks","version":3},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-17T12:17:26.602361Z"},"links":{"cited_paper":"/paper/2203.07828","citing_paper":"/paper/2303.17491"},"observation_digest":"sha256:7192f7866d477fd302060f899ee0878c6a0941139ce7410540c67fca8efbbec2","observation_id":"477f3b94-4004-4d07-8332-b0bf39142dc9","resolution":{"observed_at":"2026-05-17T12:17:26.772916Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2203.07828","last_updated":"2022-03-15T12:32:28Z","snapshot_observed_at":"2026-08-16T17:14:27.455898Z","submitted_at":"2022-03-15T12:32:28Z","title":"Do BERTs Learn to Use Browser User Interface? Exploring Multi-Step Tasks with Unified Vision-and-Language BERTs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.07828","snapshot_observed_at":"2026-08-12T16:27:47.796305Z","title":"Do berts learn to use browser user interface? exploring multi-step tasks with unified vision-and-language berts","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.13451","last_updated":"2024-11-20T16:54:15Z","snapshot_observed_at":"2026-08-17T12:06:09.194935Z","submitted_at":"2024-11-20T16:54:15Z","title":"AdaptAgent: Adapting Multimodal Web Agents with Few-Shot Learning from Human Demonstrations","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-12T16:27:47.796305Z"},"links":{"cited_paper":"/paper/2203.07828","citing_paper":"/paper/2411.13451"},"observation_digest":"sha256:4e91647521cf953cfe3c958aeb3fb570c581e4642febd9341aaa09738a4dfd42","observation_id":"4ae50598-436b-4acf-9b48-44c0a66cce34","resolution":{"observed_at":"2026-08-12T16:27:47.796305Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.07828","last_updated":"2022-03-15T12:32:28Z","snapshot_observed_at":"2026-08-16T17:14:27.455898Z","submitted_at":"2022-03-15T12:32:28Z","title":"Do BERTs Learn to Use Browser User Interface? Exploring Multi-Step Tasks with Unified Vision-and-Language BERTs","version":1},"cited_work":{"arxiv_id":"2203.07828","doi":"10.48550/arxiv.2203.07828","metadata_source":"arxiv_reference","pith_arxiv_id":"2203.07828","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Do BERTs learn to use browser user interface? Exploring multi-step tasks with unified vision-and-language berts","venue":"arXiv (Cornell University)","work_id":"f4ec2591-3aeb-428d-a6b5-60270ff7b722","year":2022},"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":65,"source":"pdf_text","source_observed_at":"2026-05-23T04:59:36.994758Z"},"links":{"cited_paper":"/paper/2203.07828","citing_paper":"/paper/2501.16150"},"observation_digest":"sha256:42c0602d9a54d718c8d41ed02c3fb7ffed5d4fd901ed853721eab0967bc2239e","observation_id":"167b8686-2b81-400b-9b6d-d56a94b13366","resolution":{"observed_at":"2026-05-23T05:02:34.969268Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2203.07828/citation-record","integrity":"/paper/2203.07828/integrity","json":"/paper/2203.07828/citation-record.json","paper":"/paper/2203.07828"},"outbound":[],"paper":{"arxiv_id":"2203.07828","last_updated":"2022-03-15T12:32:28Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-16T17:14:27.455898Z","submitted_at":"2022-03-15T12:32:28Z","title":"Do BERTs Learn to Use Browser User Interface? Exploring Multi-Step Tasks with Unified Vision-and-Language BERTs"},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2203.07828."}