{"as_of":"2026-08-09T19:50:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:bb001ebc02b9e76e53ff74128ebc1a24ba32817d9f3f05077eaa520a2fe5c4c8","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":"2026-08-09T06:31:02.800959+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":"2026-08-07T15:26:50.349909Z","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":"2026-08-06T10:49:47.762270Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2112.01551","last_updated":"2022-07-22T11:49:32Z","snapshot_observed_at":"2026-08-06T22:54:09.744241Z","submitted_at":"2021-12-02T19:00:06Z","title":"D3Net: A Unified Speaker-Listener Architecture for 3D Dense Captioning and Visual Grounding","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.01551","snapshot_observed_at":"2026-08-07T15:26:50.349909Z","title":"D3net: A speaker-listener architecture for semi-supervised dense captioning and visual ground- ing in rgb-d scans","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.15232","last_updated":"2025-05-21T08:05:27Z","snapshot_observed_at":"2026-08-07T15:19:23.911555Z","submitted_at":"2025-05-21T08:05:27Z","title":"DC-Scene: Data-Centric Learning for 3D Scene Understanding","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T15:26:50.349909Z"},"links":{"cited_paper":"/paper/2112.01551","citing_paper":"/paper/2505.15232"},"observation_digest":"sha256:750989f05f502a853b97726d8f20132a1fba0f9027f568244f6bbeeaeac24d06","observation_id":"150b2214-50d8-468f-8c57-f63aedd7638b","resolution":{"observed_at":"2026-08-07T15:26:50.349909Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2112.01551","last_updated":"2022-07-22T11:49:32Z","snapshot_observed_at":"2026-08-06T22:54:09.744241Z","submitted_at":"2021-12-02T19:00:06Z","title":"D3Net: A Unified Speaker-Listener Architecture for 3D Dense Captioning and Visual Grounding","version":2},"cited_work":{"arxiv_id":"2112.01551","doi":null,"metadata_source":"pith","pith_arxiv_id":"2112.01551","snapshot_observed_at":"2026-08-06T10:49:47.762270Z","title":"D3Net: A Unified Speaker-Listener Architecture for 3D Dense Captioning and Visual Grounding","venue":"cs.CV","work_id":"163c30fb-9aea-4b0a-8754-04392f915df0","year":2021},"citing_paper":{"arxiv_id":"2507.23478","last_updated":"2025-07-31T11:59:06Z","snapshot_observed_at":"2026-08-07T03:56:49.161093Z","submitted_at":"2025-07-31T11:59:06Z","title":"3D-R1: Enhancing Reasoning in 3D VLMs for Unified Scene Understanding","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-06T10:49:46.825579Z"},"links":{"cited_paper":"/paper/2112.01551","citing_paper":"/paper/2507.23478"},"observation_digest":"sha256:eca818386edafabd1eb111f1cbc3af05759f38c8820dece5fabc2e172d0dbed0","observation_id":"e5968314-7a6f-480b-b06f-68ac5a67dff0","resolution":{"observed_at":"2026-08-06T10:49:47.767849Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"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/2112.01551/citation-record","integrity":"/paper/2112.01551/integrity","json":"/paper/2112.01551/citation-record.json","paper":"/paper/2112.01551"},"outbound":[],"paper":{"arxiv_id":"2112.01551","last_updated":"2022-07-22T11:49:32Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-06T22:54:09.744241Z","submitted_at":"2021-12-02T19:00:06Z","title":"D3Net: A Unified Speaker-Listener Architecture for 3D Dense Captioning and Visual Grounding"},"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 2 inbound Pith citation observations for arXiv:2112.01551."}