{"as_of":"2026-08-17T13:42:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:380ea392950857d41f5568f4dd3101c3f1d7e4a4f132e1d112982514a03a8167","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":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T17:51:42.884682Z","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":"2026-08-10T21:48:28.426535Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2402.12501","last_updated":"2024-02-19T20:08:48Z","snapshot_observed_at":"2026-08-16T14:17:11.528452Z","submitted_at":"2024-02-19T20:08:48Z","title":"Your Vision-Language Model Itself Is a Strong Filter: Towards High-Quality Instruction Tuning with Data Selection","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.12501","snapshot_observed_at":"2026-08-12T19:40:42.502268Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.10557","last_updated":"2025-06-28T18:24:35Z","snapshot_observed_at":"2026-08-14T17:10:21.064845Z","submitted_at":"2024-11-15T20:09:59Z","title":"MLAN: Language-Based Instruction Tuning Preserves and Transfers Knowledge in Multimodal Language Models","version":3},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-12T19:40:42.502268Z"},"links":{"cited_paper":"/paper/2402.12501","citing_paper":"/paper/2411.10557"},"observation_digest":"sha256:2f58663184c9fc9157937d9f63128c394befa11fb87a64268e4354b000fc0450","observation_id":"0c62c1f4-78b7-4690-b8cd-fab8addf4b22","resolution":{"observed_at":"2026-08-12T19:40:42.502268Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.12501","last_updated":"2024-02-19T20:08:48Z","snapshot_observed_at":"2026-08-16T14:17:11.528452Z","submitted_at":"2024-02-19T20:08:48Z","title":"Your Vision-Language Model Itself Is a Strong Filter: Towards High-Quality Instruction Tuning with Data Selection","version":1},"cited_work":{"arxiv_id":"2402.12501","doi":null,"metadata_source":"pith","pith_arxiv_id":"2402.12501","snapshot_observed_at":"2026-08-10T21:48:28.426535Z","title":"Your Vision-Language Model Itself Is a Strong Filter: Towards High-Quality Instruction Tuning with Data Selection","venue":"cs.CL","work_id":"e2bd35f1-cb45-4291-a3e6-3b5ac4a4405d","year":2024},"citing_paper":{"arxiv_id":"2501.03879","last_updated":"2025-01-07T15:42:32Z","snapshot_observed_at":"2026-08-15T00:27:44.617873Z","submitted_at":"2025-01-07T15:42:32Z","title":"CL3DOR: Contrastive Learning for 3D Large Multimodal Models via Odds Ratio on High-Resolution Point Clouds","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-10T21:48:26.521483Z"},"links":{"cited_paper":"/paper/2402.12501","citing_paper":"/paper/2501.03879"},"observation_digest":"sha256:d441fdd6019785242dc6b5225cf70f7e6fbed89e337e6e5c81fb757c04947328","observation_id":"7df4fa98-be40-457d-ad55-7d4b71e5b948","resolution":{"observed_at":"2026-08-10T21:48:28.523336Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.12501","last_updated":"2024-02-19T20:08:48Z","snapshot_observed_at":"2026-08-16T14:17:11.528452Z","submitted_at":"2024-02-19T20:08:48Z","title":"Your Vision-Language Model Itself Is a Strong Filter: Towards High-Quality Instruction Tuning with Data Selection","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.12501","snapshot_observed_at":"2026-08-15T17:51:42.884682Z","title":"Chen et al","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.20156","last_updated":"2025-07-27T07:20:25Z","snapshot_observed_at":"2026-08-17T04:17:02.488966Z","submitted_at":"2025-07-27T07:20:25Z","title":"Trust the Model: Compact VLMs as In-Context Judges for Image-Text Data Quality","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T17:51:42.884682Z"},"links":{"cited_paper":"/paper/2402.12501","citing_paper":"/paper/2507.20156"},"observation_digest":"sha256:4c1d62674f04f3ad0aa7e50ac399544a2e098807c8a46b0bb76e0c05eeda848d","observation_id":"a5b05a76-f4e4-4ee9-8d8f-eba98670ca9a","resolution":{"observed_at":"2026-08-15T17:51:42.884682Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.12501","last_updated":"2024-02-19T20:08:48Z","snapshot_observed_at":"2026-08-16T14:17:11.528452Z","submitted_at":"2024-02-19T20:08:48Z","title":"Your Vision-Language Model Itself Is a Strong Filter: Towards High-Quality Instruction Tuning with Data Selection","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.12501","snapshot_observed_at":"2026-08-02T19:46:19.465243Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.01195","last_updated":"2026-06-25T08:08:57Z","snapshot_observed_at":"2026-08-13T08:31:14.697791Z","submitted_at":"2026-03-01T17:26:02Z","title":"VisNec: Measuring and Leveraging Visual Necessity for Multimodal Instruction Tuning","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-02T19:46:19.465243Z"},"links":{"cited_paper":"/paper/2402.12501","citing_paper":"/paper/2603.01195"},"observation_digest":"sha256:6bd9f17245157d985cf454fb62655399162dcc2b2eeb25f6eaac04921ed1d241","observation_id":"d26f3b86-692f-457d-9806-d22ebc67a2b6","resolution":{"observed_at":"2026-08-02T19:46:19.465243Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2402.12501/citation-record","integrity":"/paper/2402.12501/integrity","json":"/paper/2402.12501/citation-record.json","paper":"/paper/2402.12501"},"outbound":[],"paper":{"arxiv_id":"2402.12501","last_updated":"2024-02-19T20:08:48Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-16T14:17:11.528452Z","submitted_at":"2024-02-19T20:08:48Z","title":"Your Vision-Language Model Itself Is a Strong Filter: Towards High-Quality Instruction Tuning with Data Selection"},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2402.12501."}