{"as_of":"2026-08-08T07:40:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2e7a7ec458a57a8a4427b93ea4035365161f899d3ec2b7392dfeccbcff9db961","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":"2026-08-08T06:32:00.761636+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":"2026-08-07T05:34:56.416946Z","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":"2026-05-18T13:21:23.825432Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2403.02677","last_updated":"2024-03-05T06:05:15Z","snapshot_observed_at":"2026-08-03T18:49:39.598416Z","submitted_at":"2024-03-05T06:05:15Z","title":"Finetuned Multimodal Language Models Are High-Quality Image-Text Data Filters","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.02677","snapshot_observed_at":"2026-08-07T05:34:56.416946Z","title":"Finetuned multimodal language models are high-quality image- text data filters","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.07643","last_updated":"2025-06-09T11:09:10Z","snapshot_observed_at":"2026-08-07T05:26:32.056348Z","submitted_at":"2025-06-09T11:09:10Z","title":"Synthetic Visual Genome","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-07T05:34:56.416946Z"},"links":{"cited_paper":"/paper/2403.02677","citing_paper":"/paper/2506.07643"},"observation_digest":"sha256:c995b24fe9b4b4adb385aa21ad046efb3edfcc84ba3c69130efa32e14ef8e060","observation_id":"9c70c81f-6cc8-4285-b0ae-3ba391976aeb","resolution":{"observed_at":"2026-08-07T05:34:56.416946Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.02677","last_updated":"2024-03-05T06:05:15Z","snapshot_observed_at":"2026-08-03T18:49:39.598416Z","submitted_at":"2024-03-05T06:05:15Z","title":"Finetuned Multimodal Language Models Are High-Quality Image-Text Data Filters","version":1},"cited_work":{"arxiv_id":"2403.02677","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.02677","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Finetuned multimodal language models are high-quality image-text data filters.arXiv preprint arXiv:2403.02677, 2024a","venue":null,"work_id":"487e6704-3115-4b1c-83fa-24087c340287","year":null},"citing_paper":{"arxiv_id":"2510.03247","last_updated":"2026-04-23T06:21:57Z","snapshot_observed_at":"2026-08-06T13:44:26.635110Z","submitted_at":"2025-09-25T23:08:03Z","title":"Towards Multimodal Active Learning: Efficient Learning with Limited Paired Data","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-18T13:20:56.418690Z"},"links":{"cited_paper":"/paper/2403.02677","citing_paper":"/paper/2510.03247"},"observation_digest":"sha256:7d2d3c828e676d015dc6767473459504afedcc7d91650c45f983ae132d137e4d","observation_id":"1171a2a1-2f83-4c3c-8036-a53abc5387ea","resolution":{"observed_at":"2026-05-18T13:21:23.828044Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2403.02677/citation-record","integrity":"/paper/2403.02677/integrity","json":"/paper/2403.02677/citation-record.json","paper":"/paper/2403.02677"},"outbound":[],"paper":{"arxiv_id":"2403.02677","last_updated":"2024-03-05T06:05:15Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-03T18:49:39.598416Z","submitted_at":"2024-03-05T06:05:15Z","title":"Finetuned Multimodal Language Models Are High-Quality Image-Text Data Filters"},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2403.02677."}