{"as_of":"2026-08-10T04:38:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:1130d1fffe848a944a547eb294257bde975b1a48108e6a573031f5805418d922","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":"2026-08-09T06:31:02.800959+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":"2026-08-08T23:05:28.234921Z","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":"2026-05-16T08:17:36.076321Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2303.03032","last_updated":"2023-03-06T11:02:47Z","snapshot_observed_at":"2026-08-05T10:22:16.844750Z","submitted_at":"2023-03-06T11:02:47Z","title":"DeCap: Decoding CLIP Latents for Zero-Shot Captioning via Text-Only Training","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.03032","snapshot_observed_at":"2026-08-08T23:05:28.234921Z","title":"Decap: Decoding CLIP latents for zero-shot captioning via text-only training","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.04263","last_updated":"2025-02-06T17:58:59Z","snapshot_observed_at":"2026-08-08T22:55:49.019671Z","submitted_at":"2025-02-06T17:58:59Z","title":"Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality Inversion","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-08T23:05:28.234921Z"},"links":{"cited_paper":"/paper/2303.03032","citing_paper":"/paper/2502.04263"},"observation_digest":"sha256:edaa5a92e5532675bd6bc17c0102adcbd0cf9f7e923ce0bfa30a0c4a0f10c329","observation_id":"6a1cca45-c804-4898-b714-2d95db06f8fb","resolution":{"observed_at":"2026-08-08T23:05:28.234921Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.03032","last_updated":"2023-03-06T11:02:47Z","snapshot_observed_at":"2026-08-05T10:22:16.844750Z","submitted_at":"2023-03-06T11:02:47Z","title":"DeCap: Decoding CLIP Latents for Zero-Shot Captioning via Text-Only Training","version":1},"cited_work":{"arxiv_id":"2303.03032","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2303.03032","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Decap: Decoding clip latents for zero-shot captioning via text-only training","venue":null,"work_id":"64abda9d-ce75-4a2e-a676-ff60652f9a05","year":2023},"citing_paper":{"arxiv_id":"2602.07026","last_updated":"2026-06-05T02:27:27Z","snapshot_observed_at":"2026-08-08T04:43:15.472097Z","submitted_at":"2026-02-02T13:59:39Z","title":"Modality Gap-Driven Subspace Alignment Training Paradigm For Multimodal Large Language Models","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-16T08:17:29.924860Z"},"links":{"cited_paper":"/paper/2303.03032","citing_paper":"/paper/2602.07026"},"observation_digest":"sha256:ac266ef6b0cf4d901bf4156fe541e57f84375360281986d42c43a11f7dd9b151","observation_id":"595c1f83-64b7-42a6-964d-d3cca0d664e4","resolution":{"observed_at":"2026-05-16T08:17:36.078684Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.03032","last_updated":"2023-03-06T11:02:47Z","snapshot_observed_at":"2026-08-05T10:22:16.844750Z","submitted_at":"2023-03-06T11:02:47Z","title":"DeCap: Decoding CLIP Latents for Zero-Shot Captioning via Text-Only Training","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.03032","snapshot_observed_at":"2026-08-03T05:34:27.725279Z","title":"Decap: Decoding clip latents for zero-shot captioning via text-only training","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2602.07026","last_updated":"2026-06-05T02:27:27Z","snapshot_observed_at":"2026-08-08T04:43:15.472097Z","submitted_at":"2026-02-02T13:59:39Z","title":"Modality Gap-Driven Subspace Alignment Training Paradigm For Multimodal Large Language Models","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-03T05:34:27.725279Z"},"links":{"cited_paper":"/paper/2303.03032","citing_paper":"/paper/2602.07026"},"observation_digest":"sha256:1f5d34d488f77e3430ca0e5f1944f0bdd74e7fdca5c97ca647df7eb4b76f9ea5","observation_id":"bd169e64-7a85-4eca-92d5-393f38332884","resolution":{"observed_at":"2026-08-03T05:34:27.725279Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2303.03032/citation-record","integrity":"/paper/2303.03032/integrity","json":"/paper/2303.03032/citation-record.json","paper":"/paper/2303.03032"},"outbound":[],"paper":{"arxiv_id":"2303.03032","last_updated":"2023-03-06T11:02:47Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-05T10:22:16.844750Z","submitted_at":"2023-03-06T11:02:47Z","title":"DeCap: Decoding CLIP Latents for Zero-Shot Captioning via Text-Only 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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2303.03032."}