{"as_of":"2026-08-07T18:23:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a2cb5d8f89ede8b4121e19b2378ef44443bd53867fa125b03c7e4b63af0ce4d4","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":"2026-07-03T21:20:00.041277Z","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":"2026-07-03T21:28:58.415452Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2412.12940","last_updated":"2024-12-17T14:18:50Z","snapshot_observed_at":"2026-07-06T20:08:34.216137Z","submitted_at":"2024-12-17T14:18:50Z","title":"Improving Fine-grained Visual Understanding in VLMs through Text-Only Training","version":1},"cited_work":{"arxiv_id":"2412.12940","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2412.12940","snapshot_observed_at":"2026-07-03T21:28:58.415452Z","title":null,"venue":null,"work_id":"1d788b85-4ab5-45cf-9a25-f1f8cd904ef0","year":2024},"citing_paper":{"arxiv_id":"2604.20665","last_updated":"2026-05-21T08:47:56Z","snapshot_observed_at":"2026-08-06T16:05:08.769769Z","submitted_at":"2026-04-22T15:15:32Z","title":"The Expense of Seeing: Attaining Trustworthy Multimodal Reasoning Within the Monolithic Paradigm","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-09T23:56:02.856878Z"},"links":{"cited_paper":"/paper/2412.12940","citing_paper":"/paper/2604.20665"},"observation_digest":"sha256:957a335278ed1a15bb7ee34bab0ebee653277a08001ea8eafef722d5d3815fe8","observation_id":"f4f61ac8-4882-48ed-8eae-3bf6c8df07b5","resolution":{"observed_at":"2026-05-11T13:51:05.108698Z","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":"2412.12940","last_updated":"2024-12-17T14:18:50Z","snapshot_observed_at":"2026-07-06T20:08:34.216137Z","submitted_at":"2024-12-17T14:18:50Z","title":"Improving Fine-grained Visual Understanding in VLMs through Text-Only Training","version":1},"cited_work":{"arxiv_id":"2412.12940","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2412.12940","snapshot_observed_at":"2026-07-03T21:28:58.415452Z","title":null,"venue":null,"work_id":"1d788b85-4ab5-45cf-9a25-f1f8cd904ef0","year":2024},"citing_paper":{"arxiv_id":"2604.20665","last_updated":"2026-05-21T08:47:56Z","snapshot_observed_at":"2026-08-06T16:05:08.769769Z","submitted_at":"2026-04-22T15:15:32Z","title":"The Expense of Seeing: Attaining Trustworthy Multimodal Reasoning Within the Monolithic Paradigm","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-22T10:35:50.838150Z"},"links":{"cited_paper":"/paper/2412.12940","citing_paper":"/paper/2604.20665"},"observation_digest":"sha256:52921df36541e40002682a8df01613407916f249b8cbe61dd76f397e11912dca","observation_id":"4591128f-01c6-41d4-91b5-7adcbe14be72","resolution":{"observed_at":"2026-05-22T10:36:25.017520Z","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":"2412.12940","last_updated":"2024-12-17T14:18:50Z","snapshot_observed_at":"2026-07-06T20:08:34.216137Z","submitted_at":"2024-12-17T14:18:50Z","title":"Improving Fine-grained Visual Understanding in VLMs through Text-Only Training","version":1},"cited_work":{"arxiv_id":"2412.12940","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2412.12940","snapshot_observed_at":"2026-07-03T21:28:58.415452Z","title":null,"venue":null,"work_id":"1d788b85-4ab5-45cf-9a25-f1f8cd904ef0","year":2024},"citing_paper":{"arxiv_id":"2607.02089","last_updated":"2026-07-01T14:25:43Z","snapshot_observed_at":"2026-08-02T16:57:02.105465Z","submitted_at":"2026-07-01T14:25:43Z","title":"ESC: Emotional Self-Correction for Reliable Vision-Language Models","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-07-03T21:20:00.041277Z"},"links":{"cited_paper":"/paper/2412.12940","citing_paper":"/paper/2607.02089"},"observation_digest":"sha256:6cce4e4c6ddeaea27d3ec732590163a4ca91203a2a29b510fbf2fd4bb8f12483","observation_id":"8786e51c-aef8-47c0-9dcb-f02a802a4832","resolution":{"observed_at":"2026-07-03T21:28:58.416837Z","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"}}],"links":{"evidence":"/evidence","html":"/paper/2412.12940/citation-record","integrity":"/paper/2412.12940/integrity","json":"/paper/2412.12940/citation-record.json","paper":"/paper/2412.12940"},"outbound":[],"paper":{"arxiv_id":"2412.12940","last_updated":"2024-12-17T14:18:50Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T20:08:34.216137Z","submitted_at":"2024-12-17T14:18:50Z","title":"Improving Fine-grained Visual Understanding in VLMs through Text-Only Training"},"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:2412.12940."}