{"as_of":"2026-08-10T12:13:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c57af96004f56d74631ade995bc8129d4cbdad0a5306277c80e2d54e0f7392c3","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":"2026-08-10T06:31:04.303077+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":"2026-08-06T11:20:06.754233Z","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":"2026-08-06T11:20:07.339154Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2503.14953","last_updated":"2025-07-17T13:40:04Z","snapshot_observed_at":"2026-08-07T16:52:55.334035Z","submitted_at":"2025-03-19T07:42:24Z","title":"Aligning Information Capacity Between Vision and Language via Dense-to-Sparse Feature Distillation for Image-Text Matching","version":2},"cited_work":{"arxiv_id":"2503.14953","doi":null,"metadata_source":"pith","pith_arxiv_id":"2503.14953","snapshot_observed_at":"2026-08-06T11:20:07.339154Z","title":"Aligning Information Capacity Between Vision and Language via Dense-to-Sparse Feature Distillation for Image-Text Matching","venue":"cs.CV","work_id":"7a00f7ee-f344-45fd-b1a1-af7c01a9bcd8","year":2025},"citing_paper":{"arxiv_id":"2507.22791","last_updated":"2026-06-11T08:47:41Z","snapshot_observed_at":"2026-08-09T03:11:19.748474Z","submitted_at":"2025-07-30T15:56:36Z","title":"Modality-Aware Feature Matching in Visual and Vision-Language Applications: A Comprehensive Survey","version":2},"reference_index":131,"source":"pdf_text","source_observed_at":"2026-08-06T11:20:06.754233Z"},"links":{"cited_paper":"/paper/2503.14953","citing_paper":"/paper/2507.22791"},"observation_digest":"sha256:c4386c4be66f635b0a731989b245e95b556bfc59c9830bf162f6e7c040b71422","observation_id":"7be0d177-5d8a-404e-b57b-7fcfa95c90c7","resolution":{"observed_at":"2026-08-06T11:20:07.343170Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2503.14953","last_updated":"2025-07-17T13:40:04Z","snapshot_observed_at":"2026-08-07T16:52:55.334035Z","submitted_at":"2025-03-19T07:42:24Z","title":"Aligning Information Capacity Between Vision and Language via Dense-to-Sparse Feature Distillation for Image-Text Matching","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.14953","snapshot_observed_at":"2026-08-04T00:26:34.902867Z","title":"Novel cross- dimensional coarse-fine-grained complementary network for image-text matching.PeerJ Com- puter Science, 11:e2725, 2025a","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2511.01390","last_updated":"2026-07-02T07:36:28Z","snapshot_observed_at":"2026-08-09T19:02:38.432842Z","submitted_at":"2025-11-03T09:41:32Z","title":"SEPS: Semantic-enhanced Patch Slimming Framework for fine-grained cross-modal alignment","version":2},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-04T00:26:34.902867Z"},"links":{"cited_paper":"/paper/2503.14953","citing_paper":"/paper/2511.01390"},"observation_digest":"sha256:a7977f38bb46f34ecbe67acdebbbd00e3a243298356e69933f82498cf6c6249e","observation_id":"2cd20453-59c6-4e10-af28-860e8b47f367","resolution":{"observed_at":"2026-08-04T00:26:34.902867Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2503.14953/citation-record","integrity":"/paper/2503.14953/integrity","json":"/paper/2503.14953/citation-record.json","paper":"/paper/2503.14953"},"outbound":[],"paper":{"arxiv_id":"2503.14953","last_updated":"2025-07-17T13:40:04Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-07T16:52:55.334035Z","submitted_at":"2025-03-19T07:42:24Z","title":"Aligning Information Capacity Between Vision and Language via Dense-to-Sparse Feature Distillation for Image-Text Matching"},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2503.14953."}