{"as_of":"2026-08-08T08:46:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3f6611a5f1509edb244c5b498597843591a81983fdcd5d80e796078caa861ffe","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":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T05:21:35.003872Z","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":"2026-05-18T16:21:36.477879Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2106.09141","last_updated":"2021-06-16T21:36:36Z","snapshot_observed_at":"2026-08-04T12:39:52.869889Z","submitted_at":"2021-06-16T21:36:36Z","title":"Probing Image-Language Transformers for Verb Understanding","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.09141","snapshot_observed_at":"2026-08-07T05:21:35.003872Z","title":"Probing image-language transformers for verb understanding.arXiv preprint arXiv:2106.09141, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.08227","last_updated":"2025-06-09T20:53:43Z","snapshot_observed_at":"2026-08-07T05:14:41.333172Z","submitted_at":"2025-06-09T20:53:43Z","title":"A Good CREPE needs more than just Sugar: Investigating Biases in Compositional Vision-Language Benchmarks","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:35.003872Z"},"links":{"cited_paper":"/paper/2106.09141","citing_paper":"/paper/2506.08227"},"observation_digest":"sha256:2a950d46ddce17882ba470ca8c02789292295096fcc7cdd389cfb7fad5fdbd51","observation_id":"177fad96-974e-474e-9b39-9f75b9d9a461","resolution":{"observed_at":"2026-08-07T05:21:35.003872Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.09141","last_updated":"2021-06-16T21:36:36Z","snapshot_observed_at":"2026-08-04T12:39:52.869889Z","submitted_at":"2021-06-16T21:36:36Z","title":"Probing Image-Language Transformers for Verb Understanding","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.09141","snapshot_observed_at":"2026-08-05T11:15:19.644943Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.03025","last_updated":"2025-09-05T07:49:47Z","snapshot_observed_at":"2026-08-07T14:57:32.906442Z","submitted_at":"2025-09-03T05:17:25Z","title":"Unveiling the Response of Large Vision-Language Models to Visually Absent Tokens","version":2},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-05T11:15:19.644943Z"},"links":{"cited_paper":"/paper/2106.09141","citing_paper":"/paper/2509.03025"},"observation_digest":"sha256:79e556f8709fcbe5ef18d1118e80dd73bab860abad0298b5d523c128c79817ba","observation_id":"1782759a-7914-4003-aa50-63b0dcad429e","resolution":{"observed_at":"2026-08-05T11:15:19.644943Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.09141","last_updated":"2021-06-16T21:36:36Z","snapshot_observed_at":"2026-08-04T12:39:52.869889Z","submitted_at":"2021-06-16T21:36:36Z","title":"Probing Image-Language Transformers for Verb Understanding","version":1},"cited_work":{"arxiv_id":"2106.09141","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2106.09141","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Probing Image-Language Transformers for Verb Understanding","venue":null,"work_id":"0b45250b-b647-414d-aff8-29c145e76e50","year":2021},"citing_paper":{"arxiv_id":"2509.14837","last_updated":"2026-04-27T11:07:26Z","snapshot_observed_at":"2026-07-06T22:30:11.897367Z","submitted_at":"2025-09-18T10:58:34Z","title":"V-SEAM: Visual Semantic Editing and Attention Modulating for Causal Interpretability of Vision-Language Models","version":2},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-05-18T16:21:20.463222Z"},"links":{"cited_paper":"/paper/2106.09141","citing_paper":"/paper/2509.14837"},"observation_digest":"sha256:9f2b9f82f5145a3e0942fd2d14d8261d13f7482c0f9282dfdc40f61f44237683","observation_id":"15b44022-7957-458a-960f-75c25060bfaf","resolution":{"observed_at":"2026-05-18T16:21:36.481429Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.09141","last_updated":"2021-06-16T21:36:36Z","snapshot_observed_at":"2026-08-04T12:39:52.869889Z","submitted_at":"2021-06-16T21:36:36Z","title":"Probing Image-Language Transformers for Verb Understanding","version":1},"cited_work":{"arxiv_id":"2106.09141","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2106.09141","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Probing Image-Language Transformers for Verb Understanding","venue":null,"work_id":"0b45250b-b647-414d-aff8-29c145e76e50","year":2021},"citing_paper":{"arxiv_id":"2605.06157","last_updated":"2026-05-06T14:01:47Z","snapshot_observed_at":"2026-07-06T23:18:41.400741Z","submitted_at":"2026-05-06T14:01:47Z","title":"HNC: Leveraging Hard Negative Captions towards Models with Fine-Grained Visual-Linguistic Comprehension Capabilities","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-05-08T16:27:53.957402Z"},"links":{"cited_paper":"/paper/2106.09141","citing_paper":"/paper/2605.06157"},"observation_digest":"sha256:a27ea94446b875817abb260e58908fbc8e02cca26a0ef833e5280cd7e736d484","observation_id":"7b0f3be6-5957-4ccf-8826-e05938a698ef","resolution":{"observed_at":"2026-05-11T18:11:06.639388Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2106.09141/citation-record","integrity":"/paper/2106.09141/integrity","json":"/paper/2106.09141/citation-record.json","paper":"/paper/2106.09141"},"outbound":[],"paper":{"arxiv_id":"2106.09141","last_updated":"2021-06-16T21:36:36Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-04T12:39:52.869889Z","submitted_at":"2021-06-16T21:36:36Z","title":"Probing Image-Language Transformers for Verb Understanding"},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2106.09141."}