{"as_of":"2026-08-05T02:57:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f1b54d8021a186791348dc76db1d29d0f7e6dd4a1dc2a8a93dcc1b087ee60909","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":"2026-08-04T06:34:03.388597+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":"2026-07-14T01:07:06.861298Z","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":"2026-05-13T20:08:12.735767Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2412.07012","last_updated":"2024-12-29T03:52:23Z","snapshot_observed_at":"2026-08-04T06:34:17.337678Z","submitted_at":"2024-12-09T21:44:02Z","title":"ProVision: Programmatically Scaling Vision-centric Instruction Data for Multimodal Language Models","version":3},"cited_work":{"arxiv_id":"2412.07012","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2412.07012","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"C., Savarese, S., Xiong, C., Chen, Z., Krishna, R., and Xu, R","venue":null,"work_id":"664a346a-7141-4c51-a952-965d68bdaca3","year":2024},"citing_paper":{"arxiv_id":"2604.02794","last_updated":"2026-04-03T07:02:13Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-04-03T07:02:13Z","title":"CharTool: Tool-Integrated Visual Reasoning for Chart Understanding","version":1},"reference_index":63,"source":"arxiv_source","source_observed_at":"2026-05-13T20:07:23.153064Z"},"links":{"cited_paper":"/paper/2412.07012","citing_paper":"/paper/2604.02794"},"observation_digest":"sha256:cd806bfdcbb13394f69e76fe84049273b7a827b9b85a94dfdeb42837ef5b8501","observation_id":"b9a8b95f-5747-422d-9cb3-298b16a5b14c","resolution":{"observed_at":"2026-05-13T20:08:12.741574Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.07012","last_updated":"2024-12-29T03:52:23Z","snapshot_observed_at":"2026-08-04T06:34:17.337678Z","submitted_at":"2024-12-09T21:44:02Z","title":"ProVision: Programmatically Scaling Vision-centric Instruction Data for Multimodal Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.07012","snapshot_observed_at":"2026-07-14T01:07:06.861298Z","title":"Provision: Programmatically scaling vision-centric instruction data for multimodal language models.arXiv preprint arXiv:2412.07012, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.10004","last_updated":"2026-07-10T22:03:01Z","snapshot_observed_at":"2026-08-03T02:26:02.235143Z","submitted_at":"2026-07-10T22:03:01Z","title":"Model Guides You How to Draw: Adaptive Visual Gating for Unified Multimodal Reasoning","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-07-14T01:07:06.861298Z"},"links":{"cited_paper":"/paper/2412.07012","citing_paper":"/paper/2607.10004"},"observation_digest":"sha256:e84680c94257173eaa0054235516a895f9439d84a256483ba6e431581bbb0f44","observation_id":"7054361a-4db7-44df-b67f-bc57e2443442","resolution":{"observed_at":"2026-07-14T01:07:06.861298Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2412.07012/citation-record","integrity":"/paper/2412.07012/integrity","json":"/paper/2412.07012/citation-record.json","paper":"/paper/2412.07012"},"outbound":[],"paper":{"arxiv_id":"2412.07012","last_updated":"2024-12-29T03:52:23Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-04T06:34:17.337678Z","submitted_at":"2024-12-09T21:44:02Z","title":"ProVision: Programmatically Scaling Vision-centric Instruction Data for Multimodal Language Models"},"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":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"thesis":"As of 5 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2412.07012."}