{"as_of":"2026-08-07T10:26:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0a5afd3b84100ec095c4ce3d7ef6f5e50cfa479ff1673266b7808c61d0357e46","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":"2026-08-07T05:45:30.635922Z","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":"2026-05-16T23:09:34.941866Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2402.12058","last_updated":"2024-02-19T11:23:53Z","snapshot_observed_at":"2026-07-06T17:32:10.828230Z","submitted_at":"2024-02-19T11:23:53Z","title":"Scaffolding Coordinates to Promote Vision-Language Coordination in Large Multi-Modal Models","version":1},"cited_work":{"arxiv_id":"2402.12058","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.12058","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Scaffolding coordinates to promote vision-language coordination in large multi-modal models","venue":null,"work_id":"5af2a997-b957-42c1-ac3f-97f5444ca331","year":null},"citing_paper":{"arxiv_id":"2501.07542","last_updated":"2025-01-13T18:23:57Z","snapshot_observed_at":"2026-08-02T11:23:33.987927Z","submitted_at":"2025-01-13T18:23:57Z","title":"Imagine while Reasoning in Space: Multimodal Visualization-of-Thought","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-16T23:09:34.805552Z"},"links":{"cited_paper":"/paper/2402.12058","citing_paper":"/paper/2501.07542"},"observation_digest":"sha256:892a06b81b2bb163ffe9c272720761b6921be0d37c94aa0a080b64204108c402","observation_id":"ed4c3b5b-cc92-4e5e-bca6-a1f460acc455","resolution":{"observed_at":"2026-05-16T23:09:34.945088Z","resolver_source":"arxiv_id","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"}},{"citation":{"cited_paper":{"arxiv_id":"2402.12058","last_updated":"2024-02-19T11:23:53Z","snapshot_observed_at":"2026-07-06T17:32:10.828230Z","submitted_at":"2024-02-19T11:23:53Z","title":"Scaffolding Coordinates to Promote Vision-Language Coordination in Large Multi-Modal Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.12058","snapshot_observed_at":"2026-08-07T05:45:30.635922Z","title":"Scaffolding coordinates to promote vision-language coordination in large multi-modal models.arXiv preprint arXiv:2402.12058, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07235","last_updated":"2025-06-08T17:38:49Z","snapshot_observed_at":"2026-08-07T05:36:25.549695Z","submitted_at":"2025-06-08T17:38:49Z","title":"Multi-Step Visual Reasoning with Visual Tokens Scaling and Verification","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T05:45:30.635922Z"},"links":{"cited_paper":"/paper/2402.12058","citing_paper":"/paper/2506.07235"},"observation_digest":"sha256:5ab4823cfc694138aee26c3141c3f1f02063c785accad2b2d6922bc949f8657d","observation_id":"bf3df506-9ebc-4103-a789-956e840cebd0","resolution":{"observed_at":"2026-08-07T05:45:30.635922Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.12058","last_updated":"2024-02-19T11:23:53Z","snapshot_observed_at":"2026-07-06T17:32:10.828230Z","submitted_at":"2024-02-19T11:23:53Z","title":"Scaffolding Coordinates to Promote Vision-Language Coordination in Large Multi-Modal Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.12058","snapshot_observed_at":"2026-08-01T16:48:36.029064Z","title":"Lei, X., Yang, Z., Chen, X., Li, P., and Liu, Y","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.17884","last_updated":"2026-07-20T12:35:05Z","snapshot_observed_at":"2026-08-07T08:03:33.617792Z","submitted_at":"2026-07-20T12:35:05Z","title":"ST-Veto: Spatio-Temporal Token Veto for Diffusion MLLMs via Taylor Prediction and Visual Grounding","version":1},"reference_index":2000,"source":"pdf_text","source_observed_at":"2026-08-01T16:48:36.029064Z"},"links":{"cited_paper":"/paper/2402.12058","citing_paper":"/paper/2607.17884"},"observation_digest":"sha256:f7183c5f86b36cfa38ffc7eb768fc0cc06c6fdbf0694cb11be99e5101b33353f","observation_id":"1ce699c0-aaf6-4e27-b179-6c0389bbc14c","resolution":{"observed_at":"2026-08-01T16:48:36.029064Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2402.12058/citation-record","integrity":"/paper/2402.12058/integrity","json":"/paper/2402.12058/citation-record.json","paper":"/paper/2402.12058"},"outbound":[],"paper":{"arxiv_id":"2402.12058","last_updated":"2024-02-19T11:23:53Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T17:32:10.828230Z","submitted_at":"2024-02-19T11:23:53Z","title":"Scaffolding Coordinates to Promote Vision-Language Coordination in Large Multi-Modal 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":"2026-08-07T06:34:17.273281+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:2402.12058."}