{"as_of":"2026-08-07T13:18:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:9508c17800de512fcd31e3741e19bdb7d2bd894cc9b6db48d5324311586c7722","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":"2026-08-07T06:34:17.273281+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":"2026-08-06T21:27:40.680175Z","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":"2026-08-05T10:32:23.899427Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2409.20424","last_updated":"2024-09-30T15:49:54Z","snapshot_observed_at":"2026-07-06T19:24:39.402031Z","submitted_at":"2024-09-30T15:49:54Z","title":"World to Code: Multi-modal Data Generation via Self-Instructed Compositional Captioning and Filtering","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.20424","snapshot_observed_at":"2026-08-06T21:27:40.680175Z","title":"World to code: Multi-modal data generation via self-instructed compositional captioning and filtering.arXiv preprint arXiv:2409.20424, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.24102","last_updated":"2025-06-30T17:51:25Z","snapshot_observed_at":"2026-08-07T09:15:18.123904Z","submitted_at":"2025-06-30T17:51:25Z","title":"DenseWorld-1M: Towards Detailed Dense Grounded Caption in the Real World","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-06T21:27:40.680175Z"},"links":{"cited_paper":"/paper/2409.20424","citing_paper":"/paper/2506.24102"},"observation_digest":"sha256:10ce30759a0ed66fd84289e3f477d9f8dde6240ceb009a4d0a86ab6b41083c33","observation_id":"16724b0e-b87a-4a6e-8d44-48b746bfe395","resolution":{"observed_at":"2026-08-06T21:27:40.680175Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.20424","last_updated":"2024-09-30T15:49:54Z","snapshot_observed_at":"2026-07-06T19:24:39.402031Z","submitted_at":"2024-09-30T15:49:54Z","title":"World to Code: Multi-modal Data Generation via Self-Instructed Compositional Captioning and Filtering","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.20424","snapshot_observed_at":"2026-08-06T20:53:09.193598Z","title":"World to code: Multi-modal data generation via self-instructed compositional captioning and filtering","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.01643","last_updated":"2025-07-02T12:17:23Z","snapshot_observed_at":"2026-08-06T20:44:05.101436Z","submitted_at":"2025-07-02T12:17:23Z","title":"SAILViT: Towards Robust and Generalizable Visual Backbones for MLLMs via Gradual Feature Refinement","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-06T20:53:09.193598Z"},"links":{"cited_paper":"/paper/2409.20424","citing_paper":"/paper/2507.01643"},"observation_digest":"sha256:21331a282c7ee29d5a8238bbcafb869dacad0545623e38587b8cde7e44ddf5f2","observation_id":"68de02d4-03e1-4ab7-b0da-48d7c9ffbfc4","resolution":{"observed_at":"2026-08-06T20:53:09.193598Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.20424","last_updated":"2024-09-30T15:49:54Z","snapshot_observed_at":"2026-07-06T19:24:39.402031Z","submitted_at":"2024-09-30T15:49:54Z","title":"World to Code: Multi-modal Data Generation via Self-Instructed Compositional Captioning and Filtering","version":1},"cited_work":{"arxiv_id":"2409.20424","doi":null,"metadata_source":"pith","pith_arxiv_id":"2409.20424","snapshot_observed_at":"2026-08-05T10:32:23.899427Z","title":"World to Code: Multi-modal Data Generation via Self-Instructed Compositional Captioning and Filtering","venue":"cs.CV","work_id":"a677386d-a2e9-4a5e-b033-f45f2b7115b9","year":2024},"citing_paper":{"arxiv_id":"2608.03885","last_updated":"2026-08-04T16:20:54Z","snapshot_observed_at":"2026-08-07T13:17:49.505385Z","submitted_at":"2026-08-04T16:20:54Z","title":"MuRA: Multi-Rank Adaptation for Efficient and Effective Test-Time Vision-Language Generalization","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-05T10:32:22.740528Z"},"links":{"cited_paper":"/paper/2409.20424","citing_paper":"/paper/2608.03885"},"observation_digest":"sha256:66196860d539cbc3487fea5a0363e2a4f47248d70945725c29505c09043ca93f","observation_id":"c3c0719d-223b-4719-87da-ef7ac10c1df1","resolution":{"observed_at":"2026-08-05T10:32:23.958610Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2409.20424/citation-record","integrity":"/paper/2409.20424/integrity","json":"/paper/2409.20424/citation-record.json","paper":"/paper/2409.20424"},"outbound":[],"paper":{"arxiv_id":"2409.20424","last_updated":"2024-09-30T15:49:54Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T19:24:39.402031Z","submitted_at":"2024-09-30T15:49:54Z","title":"World to Code: Multi-modal Data Generation via Self-Instructed Compositional Captioning and Filtering"},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2409.20424."}