{"as_of":"2026-08-22T06:26:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:8f41a713e43921fdf367a61c5df6d798a6ec61621b9eaef71e5562219361a216","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":"2026-08-21T06:32:19.484+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":"2026-08-15T21:01:38.760337Z","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":"2026-05-16T09:38:09.540556Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2001.07966","last_updated":"2020-01-23T08:03:27Z","snapshot_observed_at":"2026-08-19T05:36:36.819006Z","submitted_at":"2020-01-22T11:35:58Z","title":"ImageBERT: Cross-modal Pre-training with Large-scale Weak-supervised Image-Text Data","version":2},"cited_work":{"arxiv_id":"2001.07966","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2001.07966","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Imagebert: Cross-modal pre-training with large- scale weak-supervised image-text data","venue":null,"work_id":"6367ffe4-a985-4269-93f3-889538c25401","year":2001},"citing_paper":{"arxiv_id":"2111.11432","last_updated":"2021-11-22T18:59:55Z","snapshot_observed_at":"2026-07-06T12:11:02.119174Z","submitted_at":"2021-11-22T18:59:55Z","title":"Florence: A New Foundation Model for Computer Vision","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-16T09:38:09.427509Z"},"links":{"cited_paper":"/paper/2001.07966","citing_paper":"/paper/2111.11432"},"observation_digest":"sha256:d37c8d301c5ae73e4279c401ce2755908c971495498a84ee21b5d903c3bb61e8","observation_id":"a244ce7a-635c-43e8-a289-496097e726dc","resolution":{"observed_at":"2026-05-16T09:38:09.543090Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2001.07966","last_updated":"2020-01-23T08:03:27Z","snapshot_observed_at":"2026-08-19T05:36:36.819006Z","submitted_at":"2020-01-22T11:35:58Z","title":"ImageBERT: Cross-modal Pre-training with Large-scale Weak-supervised Image-Text Data","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2001.07966","snapshot_observed_at":"2026-08-11T22:06:00.109020Z","title":"Imagebert: Cross-modal pre-training with large-scale weak-supervised image-text data,","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2412.03871","last_updated":"2025-03-19T02:30:05Z","snapshot_observed_at":"2026-08-21T02:50:34.606441Z","submitted_at":"2024-12-05T04:58:28Z","title":"CLIP-PING: Boosting Lightweight Vision-Language Models with Proximus Intrinsic Neighbors Guidance","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-11T22:06:00.109020Z"},"links":{"cited_paper":"/paper/2001.07966","citing_paper":"/paper/2412.03871"},"observation_digest":"sha256:e24069a119af9921a3588a52f900683d0547aa02b745073671602ecbdcb44775","observation_id":"ca36181f-c706-41ec-8116-a6c34923517b","resolution":{"observed_at":"2026-08-11T22:06:00.109020Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2001.07966","last_updated":"2020-01-23T08:03:27Z","snapshot_observed_at":"2026-08-19T05:36:36.819006Z","submitted_at":"2020-01-22T11:35:58Z","title":"ImageBERT: Cross-modal Pre-training with Large-scale Weak-supervised Image-Text Data","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2001.07966","snapshot_observed_at":"2026-08-11T16:32:24.428017Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.10029","last_updated":"2024-12-13T10:39:31Z","snapshot_observed_at":"2026-08-16T08:47:48.939648Z","submitted_at":"2024-12-13T10:39:31Z","title":"Enhancing Fine-Grained Vision-Language Pretraining with Negative Augmented Samples","version":1},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-11T16:32:24.428017Z"},"links":{"cited_paper":"/paper/2001.07966","citing_paper":"/paper/2412.10029"},"observation_digest":"sha256:05b28d8a5961cdb4ed8e94d6b1158eb242c0d933c6037c2c79890be46fc038b3","observation_id":"e6158d28-b18e-4d1d-a4b9-87edc4598691","resolution":{"observed_at":"2026-08-11T16:32:24.428017Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2001.07966","last_updated":"2020-01-23T08:03:27Z","snapshot_observed_at":"2026-08-19T05:36:36.819006Z","submitted_at":"2020-01-22T11:35:58Z","title":"ImageBERT: Cross-modal Pre-training with Large-scale Weak-supervised Image-Text Data","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2001.07966","snapshot_observed_at":"2026-08-15T21:01:38.760337Z","title":"Imagebert: Cross-modal pre- training with large-scale weak-supervised image-text data","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2505.11216","last_updated":"2025-05-16T13:12:41Z","snapshot_observed_at":"2026-08-17T06:30:04.839140Z","submitted_at":"2025-05-16T13:12:41Z","title":"GeoMM: On Geodesic Perspective for Multi-modal Learning","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-15T21:01:38.760337Z"},"links":{"cited_paper":"/paper/2001.07966","citing_paper":"/paper/2505.11216"},"observation_digest":"sha256:b5bd03609d7bd15f5a3be37bd71d4d28d398b8c0b0b484314c9ad02144b533fc","observation_id":"83ece59c-1713-4f08-9db8-d05488a96e43","resolution":{"observed_at":"2026-08-15T21:01:38.760337Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2001.07966/citation-record","integrity":"/paper/2001.07966/integrity","json":"/paper/2001.07966/citation-record.json","paper":"/paper/2001.07966"},"outbound":[],"paper":{"arxiv_id":"2001.07966","last_updated":"2020-01-23T08:03:27Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-19T05:36:36.819006Z","submitted_at":"2020-01-22T11:35:58Z","title":"ImageBERT: Cross-modal Pre-training with Large-scale Weak-supervised Image-Text Data"},"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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2001.07966."}