{"as_of":"2026-08-15T20:12:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:71a46698ac304a4f965623840ec0bda8e66701dd82ecff92b4c1ab775c7e8f8d","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":"2026-08-15T06:32:42.880941+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":"2026-08-05T20:05:43.383403Z","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":"2026-08-05T16:56:33.417358Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2406.02915","last_updated":"2024-06-05T04:08:41Z","snapshot_observed_at":"2026-08-13T15:40:32.691827Z","submitted_at":"2024-06-05T04:08:41Z","title":"Visual-Text Cross Alignment: Refining the Similarity Score in Vision-Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.02915","snapshot_observed_at":"2026-08-05T20:05:43.383403Z","title":"Visual-text cross alignment: Refining the similarity score in vision-language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.11262","last_updated":"2025-08-15T06:57:26Z","snapshot_observed_at":"2026-08-09T23:53:19.565631Z","submitted_at":"2025-08-15T06:57:26Z","title":"Vision-Language Models display a strong gender bias","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-05T20:05:43.383403Z"},"links":{"cited_paper":"/paper/2406.02915","citing_paper":"/paper/2508.11262"},"observation_digest":"sha256:cdc9af832c8a13515ac0f24f18ec0afef6de2e79bbf18689a503b717385a3154","observation_id":"80c7b3f6-a3cb-4206-9d5a-a37d401e6eef","resolution":{"observed_at":"2026-08-05T20:05:43.383403Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.02915","last_updated":"2024-06-05T04:08:41Z","snapshot_observed_at":"2026-08-13T15:40:32.691827Z","submitted_at":"2024-06-05T04:08:41Z","title":"Visual-Text Cross Alignment: Refining the Similarity Score in Vision-Language Models","version":1},"cited_work":{"arxiv_id":"2406.02915","doi":null,"metadata_source":"pith","pith_arxiv_id":"2406.02915","snapshot_observed_at":"2026-08-05T16:56:33.417358Z","title":"Visual-Text Cross Alignment: Refining the Similarity Score in Vision-Language Models","venue":"cs.CV","work_id":"2252ac60-a7d7-4907-9f08-fb428f677531","year":2024},"citing_paper":{"arxiv_id":"2508.17417","last_updated":"2025-08-24T15:45:22Z","snapshot_observed_at":"2026-08-14T21:40:20.124244Z","submitted_at":"2025-08-24T15:45:22Z","title":"Constrained Prompt Enhancement for Improving Zero-Shot Generalization of Vision-Language Models","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-05T16:56:23.425788Z"},"links":{"cited_paper":"/paper/2406.02915","citing_paper":"/paper/2508.17417"},"observation_digest":"sha256:444fbdbcb6c594cdddb29c5c53b13f91fd1d67cf87f3b6144435da153a6648ec","observation_id":"d1dd3986-f640-441f-a1c4-83afc3a06ec3","resolution":{"observed_at":"2026-08-05T16:56:33.495768Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.02915","last_updated":"2024-06-05T04:08:41Z","snapshot_observed_at":"2026-08-13T15:40:32.691827Z","submitted_at":"2024-06-05T04:08:41Z","title":"Visual-Text Cross Alignment: Refining the Similarity Score in Vision-Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.02915","snapshot_observed_at":"2026-08-04T19:24:21.466174Z","title":"Visual- text cross alignment: Refining the similarity score in vision-language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.09311","last_updated":"2025-09-11T09:54:25Z","snapshot_observed_at":"2026-08-09T15:18:42.282208Z","submitted_at":"2025-09-11T09:54:25Z","title":"Image Recognition with Vision and Language Embeddings of VLMs","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-04T19:24:21.466174Z"},"links":{"cited_paper":"/paper/2406.02915","citing_paper":"/paper/2509.09311"},"observation_digest":"sha256:7931ce48e83e7d705a449a73fc9b8023e2680490e58c651426284dfe6727fa98","observation_id":"8ddf585f-62c6-434f-822c-ccb3333993be","resolution":{"observed_at":"2026-08-04T19:24:21.466174Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.02915","last_updated":"2024-06-05T04:08:41Z","snapshot_observed_at":"2026-08-13T15:40:32.691827Z","submitted_at":"2024-06-05T04:08:41Z","title":"Visual-Text Cross Alignment: Refining the Similarity Score in Vision-Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.02915","snapshot_observed_at":"2026-08-02T05:13:01.180439Z","title":"Visual-text cross alignment: Refining the similarity score in vision-language models, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.13437","last_updated":"2026-07-15T04:40:36Z","snapshot_observed_at":"2026-08-06T18:52:13.968653Z","submitted_at":"2026-07-15T04:40:36Z","title":"CLIP-Guided Label-Free Discriminative Region Scoring for Fine-Grained Classification","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-02T05:13:01.180439Z"},"links":{"cited_paper":"/paper/2406.02915","citing_paper":"/paper/2607.13437"},"observation_digest":"sha256:b612fe782bb19a5df086a34251f7db4851594856ab253dd405bcce85595030ac","observation_id":"b60047ca-8d5b-49db-a2e4-515cb62300c6","resolution":{"observed_at":"2026-08-02T05:13:01.180439Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2406.02915/citation-record","integrity":"/paper/2406.02915/integrity","json":"/paper/2406.02915/citation-record.json","paper":"/paper/2406.02915"},"outbound":[],"paper":{"arxiv_id":"2406.02915","last_updated":"2024-06-05T04:08:41Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-13T15:40:32.691827Z","submitted_at":"2024-06-05T04:08:41Z","title":"Visual-Text Cross Alignment: Refining the Similarity Score in Vision-Language Models"},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2406.02915."}