{"as_of":"2026-08-08T09:56:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:bfc79c2a585084e8278a69a0ab35f1706c38814cf7e40d4abec6199c6a7db332","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":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T12:38:43.273602Z","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":"2026-05-23T16:35:42.142836Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2312.00438","last_updated":"2023-12-01T09:10:33Z","snapshot_observed_at":"2026-07-06T16:55:33.394778Z","submitted_at":"2023-12-01T09:10:33Z","title":"Dolphins: Multimodal Language Model for Driving","version":1},"cited_work":{"arxiv_id":"2312.00438","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2312.00438","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Dolphins: Multimodal language model for driving","venue":null,"work_id":"923f8b6e-cecb-40de-b1e5-44dc0164014c","year":2023},"citing_paper":{"arxiv_id":"2411.18275","last_updated":"2026-04-21T10:31:24Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-11-27T12:09:43Z","title":"Visual Adversarial Attack on Vision-Language Models for Autonomous Driving","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-05-23T16:35:24.063578Z"},"links":{"cited_paper":"/paper/2312.00438","citing_paper":"/paper/2411.18275"},"observation_digest":"sha256:5f2e2126c36951d8b7458aa41e74adda4d5c9fdfce18f819c79621a0b426171a","observation_id":"2df64d50-fdae-4ad5-9a76-5bf2c79e2cf9","resolution":{"observed_at":"2026-05-23T16:35:42.147144Z","resolver_source":"arxiv_id","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"}},{"citation":{"cited_paper":{"arxiv_id":"2312.00438","last_updated":"2023-12-01T09:10:33Z","snapshot_observed_at":"2026-07-06T16:55:33.394778Z","submitted_at":"2023-12-01T09:10:33Z","title":"Dolphins: Multimodal Language Model for Driving","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.00438","snapshot_observed_at":"2026-08-07T12:38:43.273602Z","title":"Dolphins: Multimodal language model for driving.arXiv preprint arXiv:2312.00438, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.24139","last_updated":"2025-06-03T17:03:22Z","snapshot_observed_at":"2026-08-07T12:30:28.753243Z","submitted_at":"2025-05-30T02:20:14Z","title":"S4-Driver: Scalable Self-Supervised Driving Multimodal Large Language Modelwith Spatio-Temporal Visual Representation","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T12:38:43.273602Z"},"links":{"cited_paper":"/paper/2312.00438","citing_paper":"/paper/2505.24139"},"observation_digest":"sha256:b78766e53c6090c513b32a863a0f2070320b3c20ed83db9ec650aa8d0e176498","observation_id":"a5409517-a9f0-48ae-a5f2-665bc24bc018","resolution":{"observed_at":"2026-08-07T12:38:43.273602Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.00438","last_updated":"2023-12-01T09:10:33Z","snapshot_observed_at":"2026-07-06T16:55:33.394778Z","submitted_at":"2023-12-01T09:10:33Z","title":"Dolphins: Multimodal Language Model for Driving","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.00438","snapshot_observed_at":"2026-08-07T04:49:28.374098Z","title":"Dolphins: Multimodal language model for driving","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.09557","last_updated":"2025-06-11T09:41:46Z","snapshot_observed_at":"2026-08-07T04:43:14.922978Z","submitted_at":"2025-06-11T09:41:46Z","title":"AD^2-Bench: A Hierarchical CoT Benchmark for MLLM in Autonomous Driving under Adverse Conditions","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T04:49:28.374098Z"},"links":{"cited_paper":"/paper/2312.00438","citing_paper":"/paper/2506.09557"},"observation_digest":"sha256:3f0894e4ca8d1f651a84b25972c05c7e3b4ba6c2dd929b6cd49efe3151e03934","observation_id":"16892d25-c216-4f37-903a-92aefed9ae5b","resolution":{"observed_at":"2026-08-07T04:49:28.374098Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.00438","last_updated":"2023-12-01T09:10:33Z","snapshot_observed_at":"2026-07-06T16:55:33.394778Z","submitted_at":"2023-12-01T09:10:33Z","title":"Dolphins: Multimodal Language Model for Driving","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.00438","snapshot_observed_at":"2026-08-06T21:52:23.026538Z","title":"Dolphins: Multimodal language model for driving","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.23219","last_updated":"2025-06-29T13:04:27Z","snapshot_observed_at":"2026-08-07T21:43:46.877530Z","submitted_at":"2025-06-29T13:04:27Z","title":"UrbanLLaVA: A Multi-modal Large Language Model for Urban Intelligence with Spatial Reasoning and Understanding","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T21:52:23.026538Z"},"links":{"cited_paper":"/paper/2312.00438","citing_paper":"/paper/2506.23219"},"observation_digest":"sha256:dd0ba7a6437fc3b7c38887f3753038856385dd0bdd3887fb01656767c64052f0","observation_id":"6dd443bf-64e6-47c3-be1f-8389e6fb831e","resolution":{"observed_at":"2026-08-06T21:52:23.026538Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2312.00438/citation-record","integrity":"/paper/2312.00438/integrity","json":"/paper/2312.00438/citation-record.json","paper":"/paper/2312.00438"},"outbound":[],"paper":{"arxiv_id":"2312.00438","last_updated":"2023-12-01T09:10:33Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T16:55:33.394778Z","submitted_at":"2023-12-01T09:10:33Z","title":"Dolphins: Multimodal Language Model for Driving"},"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 4 inbound Pith citation observations for arXiv:2312.00438."}