{"as_of":"2026-08-06T16:24:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:64ddda1f0cd00c1e1875e78ea33e3158b3b6a0a90570ecc493b81ddadaf277e3","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":2,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":2,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-06T06:34:29.942622+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-13T14:22:16.968028Z","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":"2026-05-13T14:22:17.205509Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2204.14095","last_updated":"2022-05-28T08:52:58Z","snapshot_observed_at":"2026-07-06T13:05:07.752560Z","submitted_at":"2022-04-29T13:38:42Z","title":"PyramidCLIP: Hierarchical Feature Alignment for Vision-language Model Pretraining","version":2},"cited_work":{"arxiv_id":"2204.14095","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2204.14095","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Pyramidclip: Hierarchical feature alignment for vision-language model pretraining","venue":null,"work_id":"dc534238-fd44-4074-b739-836666c0436d","year":2022},"citing_paper":{"arxiv_id":"2210.08402","last_updated":"2022-10-16T00:08:18Z","snapshot_observed_at":"2026-07-29T21:51:47.064287Z","submitted_at":"2022-10-16T00:08:18Z","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-05-13T14:22:16.968028Z"},"links":{"cited_paper":"/paper/2204.14095","citing_paper":"/paper/2210.08402"},"observation_digest":"sha256:441f43cb7a9e84ffadddba6e30e2655a8c3b13bf451c19ca69e05cf4dc46f270","observation_id":"b135d550-b885-4e7d-aa7c-41e083e44ffd","resolution":{"observed_at":"2026-05-13T14:22:17.209492Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2204.14095","last_updated":"2022-05-28T08:52:58Z","snapshot_observed_at":"2026-07-06T13:05:07.752560Z","submitted_at":"2022-04-29T13:38:42Z","title":"PyramidCLIP: Hierarchical Feature Alignment for Vision-language Model Pretraining","version":2},"cited_work":{"arxiv_id":"2204.14095","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2204.14095","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Pyramidclip: Hierarchical feature alignment for vision-language model pretraining","venue":null,"work_id":"dc534238-fd44-4074-b739-836666c0436d","year":2022},"citing_paper":{"arxiv_id":"2604.11496","last_updated":"2026-04-16T10:51:43Z","snapshot_observed_at":"2026-08-03T05:45:05.795046Z","submitted_at":"2026-04-13T14:03:18Z","title":"Revisiting Compositionality in Dual-Encoder Vision-Language Models: The Role of Inference","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-10T16:38:00.522094Z"},"links":{"cited_paper":"/paper/2204.14095","citing_paper":"/paper/2604.11496"},"observation_digest":"sha256:5f0b2eedaa108ad15ee22258e489be0e11da7d5a031b0f0080e7ea3956d31902","observation_id":"d59b29e3-6049-4b0b-98cb-b41a6797ae59","resolution":{"observed_at":"2026-05-11T08:26:01.822361Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2204.14095/citation-record","integrity":"/paper/2204.14095/integrity","json":"/paper/2204.14095/citation-record.json","paper":"/paper/2204.14095"},"outbound":[],"paper":{"arxiv_id":"2204.14095","last_updated":"2022-05-28T08:52:58Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T13:05:07.752560Z","submitted_at":"2022-04-29T13:38:42Z","title":"PyramidCLIP: Hierarchical Feature Alignment for Vision-language Model Pretraining"},"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":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"thesis":"As of 6 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2204.14095."}