{"as_of":"2026-08-08T09:12:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a385f8c41fbad658b685c6391efcbbeb871b4b52125fa17fc33504832e1b8678","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":"2026-08-08T06:32:00.761636+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":"2026-08-07T14:46:34.401485Z","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":"2026-08-07T12:45:52.393487Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2412.03665","last_updated":"2024-12-04T19:01:06Z","snapshot_observed_at":"2026-08-07T14:02:24.188094Z","submitted_at":"2024-12-04T19:01:06Z","title":"Personalizing Multimodal Large Language Models for Image Captioning: An Experimental Analysis","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.03665","snapshot_observed_at":"2026-08-07T14:46:34.401485Z","title":"Personalizing multimodal large language models for image captioning: an experimental analysis","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.17768","last_updated":"2025-07-20T01:08:18Z","snapshot_observed_at":"2026-08-07T22:16:16.984171Z","submitted_at":"2025-05-23T11:41:26Z","title":"R-Genie: Reasoning-Guided Generative Image Editing","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T14:46:34.401485Z"},"links":{"cited_paper":"/paper/2412.03665","citing_paper":"/paper/2505.17768"},"observation_digest":"sha256:d6a7cabf53a7fa8fbff85bee2d5f1e181ae07e10671cfb92b24587b8d0a31f28","observation_id":"cf8fdaf7-4fae-4a8c-bbdb-27597834ea0e","resolution":{"observed_at":"2026-08-07T14:46:34.401485Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.03665","last_updated":"2024-12-04T19:01:06Z","snapshot_observed_at":"2026-08-07T14:02:24.188094Z","submitted_at":"2024-12-04T19:01:06Z","title":"Personalizing Multimodal Large Language Models for Image Captioning: An Experimental Analysis","version":1},"cited_work":{"arxiv_id":"2412.03665","doi":null,"metadata_source":"pith","pith_arxiv_id":"2412.03665","snapshot_observed_at":"2026-08-07T12:45:52.393487Z","title":"Personalizing Multimodal Large Language Models for Image Captioning: An Experimental Analysis","venue":"cs.CV","work_id":"295c9fb1-d9c1-452b-a8d2-b1d46de1401b","year":2024},"citing_paper":{"arxiv_id":"2505.23693","last_updated":"2025-05-29T17:31:13Z","snapshot_observed_at":"2026-08-07T18:41:28.769570Z","submitted_at":"2025-05-29T17:31:13Z","title":"VF-Eval: Evaluating Multimodal LLMs for Generating Feedback on AIGC Videos","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-07T12:45:44.316344Z"},"links":{"cited_paper":"/paper/2412.03665","citing_paper":"/paper/2505.23693"},"observation_digest":"sha256:6d527d7652b37e2c5396660bab5730e6e747b5482c4d46bd3c4123b3c682198f","observation_id":"939add0e-cde7-4d97-a8f7-4d8a88594e64","resolution":{"observed_at":"2026-08-07T12:45:52.476729Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2412.03665/citation-record","integrity":"/paper/2412.03665/integrity","json":"/paper/2412.03665/citation-record.json","paper":"/paper/2412.03665"},"outbound":[],"paper":{"arxiv_id":"2412.03665","last_updated":"2024-12-04T19:01:06Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-07T14:02:24.188094Z","submitted_at":"2024-12-04T19:01:06Z","title":"Personalizing Multimodal Large Language Models for Image Captioning: An Experimental Analysis"},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2412.03665."}