{"as_of":"2026-08-09T17:29:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:aaf98d3cfc9c59f8d44132c857bbbcf2e2e8320849125b283ec2b033e56d763c","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":6,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":6,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":6,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":6,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T15:20:29.556944Z","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":"2026-07-04T20:50:12.702996Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2404.04125","last_updated":"2024-10-29T14:00:46Z","snapshot_observed_at":"2026-08-05T05:20:13.901623Z","submitted_at":"2024-04-04T17:58:02Z","title":"No \"Zero-Shot\" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.04125","snapshot_observed_at":"2026-08-07T15:20:29.556944Z","title":"zero-shot","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.15506","last_updated":"2025-05-21T13:26:56Z","snapshot_observed_at":"2026-08-08T03:22:29.275022Z","submitted_at":"2025-05-21T13:26:56Z","title":"Prompt Tuning Vision Language Models with Margin Regularizer for Few-Shot Learning under Distribution Shifts","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T15:20:29.556944Z"},"links":{"cited_paper":"/paper/2404.04125","citing_paper":"/paper/2505.15506"},"observation_digest":"sha256:17375c4a845e977d203be5d188f525b93ec419b8372c6be61d4cd24a905fb1a5","observation_id":"7b7b485b-7b82-4d58-b0f1-385aaa747aaa","resolution":{"observed_at":"2026-08-07T15:20:29.556944Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.04125","last_updated":"2024-10-29T14:00:46Z","snapshot_observed_at":"2026-08-05T05:20:13.901623Z","submitted_at":"2024-04-04T17:58:02Z","title":"No \"Zero-Shot\" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance","version":3},"cited_work":{"arxiv_id":"2404.04125","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2404.04125","snapshot_observed_at":"2026-07-04T20:50:12.702996Z","title":"zero-shot","venue":null,"work_id":"56a87e0c-c919-47c7-931d-6e76a1439445","year":2024},"citing_paper":{"arxiv_id":"2606.01841","last_updated":"2026-06-01T07:52:40Z","snapshot_observed_at":"2026-08-08T09:24:50.134351Z","submitted_at":"2026-06-01T07:52:40Z","title":"The Neuromorphic Supremacy","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-06-28T12:02:13.100759Z"},"links":{"cited_paper":"/paper/2404.04125","citing_paper":"/paper/2606.01841"},"observation_digest":"sha256:9915aec7e2503a775b4470becc22c0458b089514d1f5459a12550074c53349d9","observation_id":"032948fd-752f-4cdf-bded-3d6621f90fbc","resolution":{"observed_at":"2026-07-02T01:26:24.525369Z","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":"2404.04125","last_updated":"2024-10-29T14:00:46Z","snapshot_observed_at":"2026-08-05T05:20:13.901623Z","submitted_at":"2024-04-04T17:58:02Z","title":"No \"Zero-Shot\" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance","version":3},"cited_work":{"arxiv_id":"2404.04125","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2404.04125","snapshot_observed_at":"2026-07-04T20:50:12.702996Z","title":"zero-shot","venue":null,"work_id":"56a87e0c-c919-47c7-931d-6e76a1439445","year":2024},"citing_paper":{"arxiv_id":"2606.23611","last_updated":"2026-06-22T17:11:15Z","snapshot_observed_at":"2026-07-06T23:58:20.975630Z","submitted_at":"2026-06-22T17:11:15Z","title":"Data Selection Through Iterative Self-Filtering for Vision-Language Settings","version":1},"reference_index":174,"source":"arxiv_source","source_observed_at":"2026-06-26T09:22:47.537137Z"},"links":{"cited_paper":"/paper/2404.04125","citing_paper":"/paper/2606.23611"},"observation_digest":"sha256:712bcd7bca0424827e00b5efc1ab009b98af5448b541a6d62e6b566475faec13","observation_id":"a1eed48c-72fc-4932-94e6-cc0b0e5cffd7","resolution":{"observed_at":"2026-07-04T09:49:44.874705Z","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":"2404.04125","last_updated":"2024-10-29T14:00:46Z","snapshot_observed_at":"2026-08-05T05:20:13.901623Z","submitted_at":"2024-04-04T17:58:02Z","title":"No \"Zero-Shot\" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance","version":3},"cited_work":{"arxiv_id":"2404.04125","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2404.04125","snapshot_observed_at":"2026-07-04T20:50:12.702996Z","title":"zero-shot","venue":null,"work_id":"56a87e0c-c919-47c7-931d-6e76a1439445","year":2024},"citing_paper":{"arxiv_id":"2606.26091","last_updated":"2026-06-24T17:59:02Z","snapshot_observed_at":"2026-08-02T03:35:37.854415Z","submitted_at":"2026-06-24T17:59:02Z","title":"On-Policy Self-Distillation with Sampled Demonstrations Reduces Output Diversity","version":1},"reference_index":196,"source":"arxiv_source","source_observed_at":"2026-06-25T19:23:56.452083Z"},"links":{"cited_paper":"/paper/2404.04125","citing_paper":"/paper/2606.26091"},"observation_digest":"sha256:40983f8d3840a4ade8b42f500dffd32785cfdc317a60ba0b8699ec8d1ba7e1d4","observation_id":"e606f04d-7ae2-45dd-94a5-05457fab8c2c","resolution":{"observed_at":"2026-07-04T20:50:12.704654Z","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":"2404.04125","last_updated":"2024-10-29T14:00:46Z","snapshot_observed_at":"2026-08-05T05:20:13.901623Z","submitted_at":"2024-04-04T17:58:02Z","title":"No \"Zero-Shot\" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.04125","snapshot_observed_at":"2026-07-11T10:00:17.827281Z","title":"zero-shot","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.05019","last_updated":"2026-07-07T07:13:34Z","snapshot_observed_at":"2026-08-07T10:28:45.636740Z","submitted_at":"2026-07-06T12:59:45Z","title":"Beyond Modality Fusion: Deep Ensembles for Multimodal Classification","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-07-11T10:00:17.827281Z"},"links":{"cited_paper":"/paper/2404.04125","citing_paper":"/paper/2607.05019"},"observation_digest":"sha256:5d2f638d53df8c368de3651369a0b3afbdfc202bb6fd7be267cdf4dbeab69c11","observation_id":"216f7082-b215-432a-ab17-c795aaf8bd86","resolution":{"observed_at":"2026-07-11T10:00:17.827281Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.04125","last_updated":"2024-10-29T14:00:46Z","snapshot_observed_at":"2026-08-05T05:20:13.901623Z","submitted_at":"2024-04-04T17:58:02Z","title":"No \"Zero-Shot\" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.04125","snapshot_observed_at":"2026-08-02T06:14:03.708540Z","title":"zero-shot","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.13125","last_updated":"2026-07-18T17:28:17Z","snapshot_observed_at":"2026-08-03T17:18:33.842709Z","submitted_at":"2026-07-14T17:52:05Z","title":"Boogu-Image-0.1: Boosting Open Agentic Multimodal Generation via Understanding under a Minimal Budget","version":2},"reference_index":124,"source":"pdf_text","source_observed_at":"2026-08-02T06:14:03.708540Z"},"links":{"cited_paper":"/paper/2404.04125","citing_paper":"/paper/2607.13125"},"observation_digest":"sha256:6824060c922d1e579f83b4deb1430b4a7ad35dacfca32936fba79187f1d353f0","observation_id":"2497c4ef-a011-4adb-82c7-f809d71b28c3","resolution":{"observed_at":"2026-08-02T06:14:03.708540Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2404.04125/citation-record","integrity":"/paper/2404.04125/integrity","json":"/paper/2404.04125/citation-record.json","paper":"/paper/2404.04125"},"outbound":[],"paper":{"arxiv_id":"2404.04125","last_updated":"2024-10-29T14:00:46Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-05T05:20:13.901623Z","submitted_at":"2024-04-04T17:58:02Z","title":"No \"Zero-Shot\" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance"},"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 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 6 inbound Pith citation observations for arXiv:2404.04125."}