{"as_of":"2026-08-09T18:49:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:91764c491b3f635a526397378ce35876211beddafe8983e5b02ef617011a093a","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":"2026-08-09T06:31:02.800959+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":"2026-08-07T14:52:07.801312Z","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":"2026-05-19T06:52:08.109335Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2411.09691","last_updated":"2024-11-14T18:57:07Z","snapshot_observed_at":"2026-08-05T04:29:40.575401Z","submitted_at":"2024-11-14T18:57:07Z","title":"Advancing Fine-Grained Visual Understanding with Multi-Scale Alignment in Multi-Modal Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.09691","snapshot_observed_at":"2026-08-07T14:52:07.801312Z","title":"Advancing fine-grained visual understanding with multi-scale alignment in multi-modal models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.17316","last_updated":"2025-05-22T22:10:27Z","snapshot_observed_at":"2026-08-08T12:19:36.067436Z","submitted_at":"2025-05-22T22:10:27Z","title":"Analyzing Fine-Grained Alignment and Enhancing Vision Understanding in Multimodal Language Models","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T14:52:07.801312Z"},"links":{"cited_paper":"/paper/2411.09691","citing_paper":"/paper/2505.17316"},"observation_digest":"sha256:9950ca509eec333da2e8b4dd2ace912b63197891570b21dfb0c1189672d608ab","observation_id":"258e03ae-c032-4490-886e-02438a42f2c5","resolution":{"observed_at":"2026-08-07T14:52:07.801312Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.09691","last_updated":"2024-11-14T18:57:07Z","snapshot_observed_at":"2026-08-05T04:29:40.575401Z","submitted_at":"2024-11-14T18:57:07Z","title":"Advancing Fine-Grained Visual Understanding with Multi-Scale Alignment in Multi-Modal Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.09691","snapshot_observed_at":"2026-08-07T14:18:05.180098Z","title":"Advancing fine-grained visual understanding with multi-scale alignment in multi- modal models.ArXiv, abs/2411.09691, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.19474","last_updated":"2025-05-26T03:53:00Z","snapshot_observed_at":"2026-08-09T07:56:47.651999Z","submitted_at":"2025-05-26T03:53:00Z","title":"Causal-LLaVA: Causal Disentanglement for Mitigating Hallucination in Multimodal Large Language Models","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-07T14:18:05.180098Z"},"links":{"cited_paper":"/paper/2411.09691","citing_paper":"/paper/2505.19474"},"observation_digest":"sha256:f37e2ce4226b51a583f72820dc5bf6c8e1edce4e279ef06dabf7a623ca654616","observation_id":"a8223c6f-90d4-4f43-8f1e-5880c854b88c","resolution":{"observed_at":"2026-08-07T14:18:05.180098Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.09691","last_updated":"2024-11-14T18:57:07Z","snapshot_observed_at":"2026-08-05T04:29:40.575401Z","submitted_at":"2024-11-14T18:57:07Z","title":"Advancing Fine-Grained Visual Understanding with Multi-Scale Alignment in Multi-Modal Models","version":1},"cited_work":{"arxiv_id":"2411.09691","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2411.09691","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Advancing fine-grained visual understanding with multi-scale alignment in multi-modal models","venue":null,"work_id":"423d6db7-7c71-4162-b287-f42a44a61886","year":2024},"citing_paper":{"arxiv_id":"2507.00748","last_updated":"2026-04-12T11:20:16Z","snapshot_observed_at":"2026-08-08T09:01:59.914584Z","submitted_at":"2025-07-01T13:48:57Z","title":"Improving the Reasoning of Multi-Image Grounding in MLLMs via Reinforcement Learning","version":3},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-05-19T06:50:02.607136Z"},"links":{"cited_paper":"/paper/2411.09691","citing_paper":"/paper/2507.00748"},"observation_digest":"sha256:be86f00184d738f53dc24c8300e35ff5f763acc150f816af214263386a1bf726","observation_id":"ad4daefd-ba27-4ed8-9d8a-250ab54f31da","resolution":{"observed_at":"2026-05-19T06:52:08.111822Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2411.09691/citation-record","integrity":"/paper/2411.09691/integrity","json":"/paper/2411.09691/citation-record.json","paper":"/paper/2411.09691"},"outbound":[],"paper":{"arxiv_id":"2411.09691","last_updated":"2024-11-14T18:57:07Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-05T04:29:40.575401Z","submitted_at":"2024-11-14T18:57:07Z","title":"Advancing Fine-Grained Visual Understanding with Multi-Scale Alignment in 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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2411.09691."}