{"as_of":"2026-08-16T17:24:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:8e19651352fef426dd0c851d1606d3140873871ad2f4579b8c23196f5cc386dd","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":"2026-08-16T06:30:59.297886+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":"2026-08-16T11:52:01.369930Z","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":"2026-08-10T19:39:25.790022Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2204.03647","last_updated":"2022-04-07T17:59:38Z","snapshot_observed_at":"2026-08-16T17:08:29.489023Z","submitted_at":"2022-04-07T17:59:38Z","title":"Adapting CLIP For Phrase Localization Without Further Training","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.03647","snapshot_observed_at":"2026-08-11T04:32:44.321352Z","title":"Adapting clip for phrase localization without further train- ing","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.18806","last_updated":"2024-12-25T07:08:51Z","snapshot_observed_at":"2026-08-13T02:21:53.624772Z","submitted_at":"2024-12-25T07:08:51Z","title":"FOR: Finetuning for Object Level Open Vocabulary Image Retrieval","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-11T04:32:44.321352Z"},"links":{"cited_paper":"/paper/2204.03647","citing_paper":"/paper/2412.18806"},"observation_digest":"sha256:7d0a88179cef8f12e7588081c3796aeb34ad996db307ecb787c611be355612bc","observation_id":"fd915810-0a36-4df9-a6ea-3e382c155e70","resolution":{"observed_at":"2026-08-11T04:32:44.321352Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2204.03647","last_updated":"2022-04-07T17:59:38Z","snapshot_observed_at":"2026-08-16T17:08:29.489023Z","submitted_at":"2022-04-07T17:59:38Z","title":"Adapting CLIP For Phrase Localization Without Further Training","version":1},"cited_work":{"arxiv_id":"2204.03647","doi":null,"metadata_source":"pith","pith_arxiv_id":"2204.03647","snapshot_observed_at":"2026-08-10T19:39:25.790022Z","title":"Adapting CLIP For Phrase Localization Without Further Training","venue":"cs.CV","work_id":"3a7e1525-c796-4d3f-8207-103f880e554d","year":2022},"citing_paper":{"arxiv_id":"2501.09887","last_updated":"2025-01-17T00:18:34Z","snapshot_observed_at":"2026-08-14T18:21:18.338457Z","submitted_at":"2025-01-17T00:18:34Z","title":"FLORA: Formal Language Model Enables Robust Training-free Zero-shot Object Referring Analysis","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-10T19:39:25.573098Z"},"links":{"cited_paper":"/paper/2204.03647","citing_paper":"/paper/2501.09887"},"observation_digest":"sha256:ff4e7135838bd365915da8845ba88d12b11807f873539af79208ffce964c0d07","observation_id":"1a3009a8-a0a1-49ad-9321-2e8240bfd5da","resolution":{"observed_at":"2026-08-10T19:39:25.802853Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2204.03647","last_updated":"2022-04-07T17:59:38Z","snapshot_observed_at":"2026-08-16T17:08:29.489023Z","submitted_at":"2022-04-07T17:59:38Z","title":"Adapting CLIP For Phrase Localization Without Further Training","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.03647","snapshot_observed_at":"2026-08-16T11:52:01.369930Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2504.14467","last_updated":"2025-05-01T14:14:05Z","snapshot_observed_at":"2026-08-16T11:46:07.601859Z","submitted_at":"2025-04-20T02:51:11Z","title":"LGD: Leveraging Generative Descriptions for Zero-Shot Referring Image Segmentation","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-16T11:52:01.369930Z"},"links":{"cited_paper":"/paper/2204.03647","citing_paper":"/paper/2504.14467"},"observation_digest":"sha256:fd1550afdca1932a4fb90ceffbcedac343b27890a10cff97a44fadb0ec8070d9","observation_id":"dae225bf-5da5-4d56-b44a-f7114986a34d","resolution":{"observed_at":"2026-08-16T11:52:01.369930Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2204.03647","last_updated":"2022-04-07T17:59:38Z","snapshot_observed_at":"2026-08-16T17:08:29.489023Z","submitted_at":"2022-04-07T17:59:38Z","title":"Adapting CLIP For Phrase Localization Without Further Training","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.03647","snapshot_observed_at":"2026-08-14T04:25:00.259046Z","title":"Adapting CLIP for phrase localization without further training.arXiv preprint arXiv:2204.03647, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.08929","last_updated":"2026-08-09T21:44:34Z","snapshot_observed_at":"2026-08-16T12:53:57.421919Z","submitted_at":"2026-08-09T21:44:34Z","title":"Zero-shot 2D Grounding with Novel Affordance Types","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-14T04:25:00.259046Z"},"links":{"cited_paper":"/paper/2204.03647","citing_paper":"/paper/2608.08929"},"observation_digest":"sha256:59864d8c4639d211a8ef3cf8db9a2b70b9b8bde3129eabf281c59d263454091c","observation_id":"fb7d6d82-20ea-4c99-aee4-86feb5326e8f","resolution":{"observed_at":"2026-08-14T04:25:00.259046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2204.03647/citation-record","integrity":"/paper/2204.03647/integrity","json":"/paper/2204.03647/citation-record.json","paper":"/paper/2204.03647"},"outbound":[],"paper":{"arxiv_id":"2204.03647","last_updated":"2022-04-07T17:59:38Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-16T17:08:29.489023Z","submitted_at":"2022-04-07T17:59:38Z","title":"Adapting CLIP For Phrase Localization Without Further Training"},"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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2204.03647."}