{"as_of":"2026-08-12T14:20:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:8ec6df93f3fe5e915c7983d413e6d8e51c25794f570a9787b62cda4ca92d5179","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":"2026-08-12T06:34:41.77262+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":"2026-08-10T21:48:26.521483Z","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":"2026-08-12T03:14:43.213847Z","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":"2026-08-12T01:26:25.176273Z","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":"sha256:6cf50dd43e2918005375c65eb847b82cfd6db4d67b6b01984920b37fc8e0da75","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 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.12501","last_updated":"2024-02-19T20:08:48Z","snapshot_observed_at":"2026-08-12T03:14:43.213847Z","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":"2026-08-07T03:33:50.802975Z","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":"sha256:8c25fc77b7ae3d3dddcac7ceaedef2b888f3f7e312f447d6ab73b25ba86ac615","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":"2026-08-12T03:14:43.213847Z","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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2402.12501."}