{"as_of":"2026-08-13T13:30:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c48d58285a6e2ea2bf1ee0495181a3324c5c6108fa3a1cb79b400afa75ef3d2a","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":"2026-08-13T06:32:02.005865+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":"2026-08-06T21:52:14.100701Z","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":"2026-08-06T16:42:13.500312Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2401.03201","last_updated":"2024-01-16T16:39:57Z","snapshot_observed_at":"2026-08-13T04:48:04.997400Z","submitted_at":"2024-01-06T12:20:18Z","title":"3DMIT: 3D Multi-modal Instruction Tuning for Scene Understanding","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.03201","snapshot_observed_at":"2026-08-06T21:52:14.100701Z","title":"3dmit: 3d multi-modal instruction tuning for scene understanding","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.23329","last_updated":"2025-06-29T17:02:57Z","snapshot_observed_at":"2026-08-13T08:46:09.773891Z","submitted_at":"2025-06-29T17:02:57Z","title":"IR3D-Bench: Evaluating Vision-Language Model Scene Understanding as Agentic Inverse Rendering","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-06T21:52:14.100701Z"},"links":{"cited_paper":"/paper/2401.03201","citing_paper":"/paper/2506.23329"},"observation_digest":"sha256:3b3f316db9611fb948db9f47d4e3b2259d48aa9d520f1d2c6b9f814bbca7ffff","observation_id":"477b6121-dda0-4230-a3af-7ebb78398485","resolution":{"observed_at":"2026-08-06T21:52:14.100701Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.03201","last_updated":"2024-01-16T16:39:57Z","snapshot_observed_at":"2026-08-13T04:48:04.997400Z","submitted_at":"2024-01-06T12:20:18Z","title":"3DMIT: 3D Multi-modal Instruction Tuning for Scene Understanding","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.03201","snapshot_observed_at":"2026-08-06T18:37:21.293763Z","title":"3dmit: 3d multi-modal instruction tuning for scene understanding.arXiv preprint arXiv:2401.03201, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.07781","last_updated":"2025-07-10T14:01:24Z","snapshot_observed_at":"2026-08-12T08:20:16.277192Z","submitted_at":"2025-07-10T14:01:24Z","title":"SURPRISE3D: A Dataset for Spatial Understanding and Reasoning in Complex 3D Scenes","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T18:37:21.293763Z"},"links":{"cited_paper":"/paper/2401.03201","citing_paper":"/paper/2507.07781"},"observation_digest":"sha256:f526a2522c1a4323582393153ce904a034655241dd42090503eb1ef757f4de63","observation_id":"362f372f-b1d3-4e5f-a3aa-0d1015d2618b","resolution":{"observed_at":"2026-08-06T18:37:21.293763Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.03201","last_updated":"2024-01-16T16:39:57Z","snapshot_observed_at":"2026-08-13T04:48:04.997400Z","submitted_at":"2024-01-06T12:20:18Z","title":"3DMIT: 3D Multi-modal Instruction Tuning for Scene Understanding","version":2},"cited_work":{"arxiv_id":"2401.03201","doi":null,"metadata_source":"pith","pith_arxiv_id":"2401.03201","snapshot_observed_at":"2026-08-06T16:42:13.500312Z","title":"3DMIT: 3D Multi-modal Instruction Tuning for Scene Understanding","venue":"cs.CV","work_id":"a6aebec0-afc2-476e-8339-ea5dafa6b910","year":2024},"citing_paper":{"arxiv_id":"2507.12916","last_updated":"2025-07-17T09:02:04Z","snapshot_observed_at":"2026-08-11T15:45:25.444647Z","submitted_at":"2025-07-17T09:02:04Z","title":"Argus: Leveraging Multiview Images for Improved 3-D Scene Understanding With Large Language Models","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T16:42:13.263453Z"},"links":{"cited_paper":"/paper/2401.03201","citing_paper":"/paper/2507.12916"},"observation_digest":"sha256:a979c55d7e8966b9a84f1ab61aa02e9f65e78294f295c71c38f8d8d299439bc8","observation_id":"d3b3f86e-6d05-4acb-b267-7eb0d3c59729","resolution":{"observed_at":"2026-08-06T16:42:13.504087Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2401.03201/citation-record","integrity":"/paper/2401.03201/integrity","json":"/paper/2401.03201/citation-record.json","paper":"/paper/2401.03201"},"outbound":[],"paper":{"arxiv_id":"2401.03201","last_updated":"2024-01-16T16:39:57Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-13T04:48:04.997400Z","submitted_at":"2024-01-06T12:20:18Z","title":"3DMIT: 3D Multi-modal Instruction Tuning for Scene Understanding"},"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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2401.03201."}