{"as_of":"2026-08-08T02:15:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d95549e06d615331062586810528610f85ec4d8d4ab2954fd556d660ffc8ec18","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":"2026-08-07T06:34:17.273281+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":"2026-08-07T15:27:24.445011Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-06T23:50:23.619666Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2112.14757","last_updated":"2022-12-29T16:36:55Z","snapshot_observed_at":"2026-08-06T08:59:22.727151Z","submitted_at":"2021-12-29T18:56:18Z","title":"A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Model","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.14757","snapshot_observed_at":"2026-08-07T15:27:24.445011Z","title":"A simple baseline for zero- shot semantic segmentation with pre-trained vision-language model","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.15123","last_updated":"2025-08-24T14:40:35Z","snapshot_observed_at":"2026-08-07T15:21:06.525176Z","submitted_at":"2025-05-21T05:16:45Z","title":"Seeing the Trees for the Forest: Rethinking Weakly-Supervised Medical Visual Grounding","version":2},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-07T15:27:24.445011Z"},"links":{"cited_paper":"/paper/2112.14757","citing_paper":"/paper/2505.15123"},"observation_digest":"sha256:0c95601eb28310410961f31c27af6419b205c6b48dc07180a40cb287cfb331a1","observation_id":"30f20f27-6e28-4288-9183-b534cf794ff0","resolution":{"observed_at":"2026-08-07T15:27:24.445011Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2112.14757","last_updated":"2022-12-29T16:36:55Z","snapshot_observed_at":"2026-08-06T08:59:22.727151Z","submitted_at":"2021-12-29T18:56:18Z","title":"A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Model","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.14757","snapshot_observed_at":"2026-08-07T04:47:50.731164Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.09643","last_updated":"2025-06-11T11:56:51Z","snapshot_observed_at":"2026-08-07T21:07:57.707999Z","submitted_at":"2025-06-11T11:56:51Z","title":"Using Sign Language Production as Data Augmentation to enhance Sign Language Translation","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-07T04:47:50.731164Z"},"links":{"cited_paper":"/paper/2112.14757","citing_paper":"/paper/2506.09643"},"observation_digest":"sha256:0b223af658fa13822da22ef4f2ef6469b36fca1058320f4c376e0b2c1983dc03","observation_id":"5cae8e16-119c-41ca-bde5-438a2cb4e53d","resolution":{"observed_at":"2026-08-07T04:47:50.731164Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2112.14757","last_updated":"2022-12-29T16:36:55Z","snapshot_observed_at":"2026-08-06T08:59:22.727151Z","submitted_at":"2021-12-29T18:56:18Z","title":"A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Model","version":2},"cited_work":{"arxiv_id":"2112.14757","doi":null,"metadata_source":"pith","pith_arxiv_id":"2112.14757","snapshot_observed_at":"2026-08-06T23:50:23.619666Z","title":"A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Model","venue":"cs.CV","work_id":"ec5226e2-f2be-4f97-b540-beabba9fed52","year":2021},"citing_paper":{"arxiv_id":"2506.16058","last_updated":"2025-06-24T03:11:42Z","snapshot_observed_at":"2026-08-06T23:41:59.563520Z","submitted_at":"2025-06-19T06:32:53Z","title":"Stepping Out of Similar Semantic Space for Open-Vocabulary Segmentation","version":2},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-06T23:50:23.536291Z"},"links":{"cited_paper":"/paper/2112.14757","citing_paper":"/paper/2506.16058"},"observation_digest":"sha256:5412336738263604b200e38180d91cfe52cdb2dcca1b7dbce15610a645991f37","observation_id":"17813763-b4c7-4cc1-a2ea-c59571aa80ca","resolution":{"observed_at":"2026-08-06T23:50:23.626640Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2112.14757/citation-record","integrity":"/paper/2112.14757/integrity","json":"/paper/2112.14757/citation-record.json","paper":"/paper/2112.14757"},"outbound":[],"paper":{"arxiv_id":"2112.14757","last_updated":"2022-12-29T16:36:55Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-06T08:59:22.727151Z","submitted_at":"2021-12-29T18:56:18Z","title":"A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Model"},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2112.14757."}