{"as_of":"2026-08-13T13:45:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:61ead2e8e88d4cd9964fab0928368e4a9c0c599553ab5cb80916d1608e23b7d4","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":"2026-08-13T06:32:02.005865+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":"2026-08-04T06:10:35.790766Z","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":"2026-06-29T16:33:38.669600Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2206.08522","last_updated":"2022-08-17T17:18:43Z","snapshot_observed_at":"2026-08-09T12:17:30.206076Z","submitted_at":"2022-06-17T03:07:18Z","title":"VLMbench: A Compositional Benchmark for Vision-and-Language Manipulation","version":2},"cited_work":{"arxiv_id":"2206.08522","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2206.08522","snapshot_observed_at":"2026-06-29T16:33:38.669600Z","title":"VLMbench: A compositional bench- mark for vision-and-language manipulation","venue":null,"work_id":"b3f2b0e4-188c-4643-84ba-ffacfaeb2ca9","year":2022},"citing_paper":{"arxiv_id":"2605.12090","last_updated":"2026-05-12T13:10:52Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-05-12T13:10:52Z","title":"World Action Models: The Next Frontier in Embodied AI","version":1},"reference_index":229,"source":"pdf_text","source_observed_at":"2026-05-13T05:01:16.802019Z"},"links":{"cited_paper":"/paper/2206.08522","citing_paper":"/paper/2605.12090"},"observation_digest":"sha256:67796abe5c8de1fcbdf96eabe3eb451d5a96b692a9b063e746a131fb7c0bb21b","observation_id":"0ba1f0c2-a0fb-44a4-a883-0d2e272ea746","resolution":{"observed_at":"2026-05-13T05:07:17.831978Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.08522","last_updated":"2022-08-17T17:18:43Z","snapshot_observed_at":"2026-08-09T12:17:30.206076Z","submitted_at":"2022-06-17T03:07:18Z","title":"VLMbench: A Compositional Benchmark for Vision-and-Language Manipulation","version":2},"cited_work":{"arxiv_id":"2206.08522","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2206.08522","snapshot_observed_at":"2026-06-29T16:33:38.669600Z","title":"VLMbench: A compositional bench- mark for vision-and-language manipulation","venue":null,"work_id":"b3f2b0e4-188c-4643-84ba-ffacfaeb2ca9","year":2022},"citing_paper":{"arxiv_id":"2605.27759","last_updated":"2026-05-26T23:17:39Z","snapshot_observed_at":"2026-08-12T08:29:29.657428Z","submitted_at":"2026-05-26T23:17:39Z","title":"Colosseum V2: Benchmarking Generalization for Vision Language Action Models","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-06-29T16:32:32.885345Z"},"links":{"cited_paper":"/paper/2206.08522","citing_paper":"/paper/2605.27759"},"observation_digest":"sha256:5eb9cd0a13d40ec6c1b8b05a73e3859445b847610f3eb324164d1a492f619dc5","observation_id":"9018405c-5ecd-4b40-a2ca-d5eb26d4301e","resolution":{"observed_at":"2026-06-29T16:33:38.671017Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.08522","last_updated":"2022-08-17T17:18:43Z","snapshot_observed_at":"2026-08-09T12:17:30.206076Z","submitted_at":"2022-06-17T03:07:18Z","title":"VLMbench: A Compositional Benchmark for Vision-and-Language Manipulation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.08522","snapshot_observed_at":"2026-08-04T06:10:35.790766Z","title":"Vlmbench: A compositional benchmark for vision-and-language manipulation, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.02497","last_updated":"2026-08-03T17:02:04Z","snapshot_observed_at":"2026-08-10T03:03:42.557157Z","submitted_at":"2026-08-03T17:02:04Z","title":"Grounded Semantic Re-Binding for Robust Instruction Generalization in Vision-Language-Action Models","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-04T06:10:35.790766Z"},"links":{"cited_paper":"/paper/2206.08522","citing_paper":"/paper/2608.02497"},"observation_digest":"sha256:b7e5abe575549bf49efc591b42cb162442ac5679618e8d15234d1c47e7104333","observation_id":"82092713-d2e1-4580-bda7-49222faf5f6d","resolution":{"observed_at":"2026-08-04T06:10:35.790766Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2206.08522/citation-record","integrity":"/paper/2206.08522/integrity","json":"/paper/2206.08522/citation-record.json","paper":"/paper/2206.08522"},"outbound":[],"paper":{"arxiv_id":"2206.08522","last_updated":"2022-08-17T17:18:43Z","latest_version":2,"primary_category":"cs.RO","snapshot_observed_at":"2026-08-09T12:17:30.206076Z","submitted_at":"2022-06-17T03:07:18Z","title":"VLMbench: A Compositional Benchmark for Vision-and-Language Manipulation"},"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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2206.08522."}