{"as_of":"2026-08-08T20:09:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0acfe15421f538ae9e8b0851600e3d5099d8a4325c0c0f73c60ea9e496c44509","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":"2026-08-07T15:26:51.170268Z","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":"2026-05-10T06:56:47.341538Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2504.09518","last_updated":"2025-04-13T11:10:47Z","snapshot_observed_at":"2026-08-07T16:06:10.395071Z","submitted_at":"2025-04-13T11:10:47Z","title":"3D CoCa: Contrastive Learners are 3D Captioners","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.09518","snapshot_observed_at":"2026-08-07T15:26:51.170268Z","title":"3d coca: Contrastive learners are 3d captioners","venue":null,"work_id":null,"year":2025},"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":17,"source":"pdf_text","source_observed_at":"2026-08-07T15:26:51.170268Z"},"links":{"cited_paper":"/paper/2504.09518","citing_paper":"/paper/2505.15232"},"observation_digest":"sha256:b4510175a1f56a841cccf776213eab3ece32d6282768095f53e1a7c30f2b3557","observation_id":"a3c1de17-0300-4299-9f16-94523ebd6244","resolution":{"observed_at":"2026-08-07T15:26:51.170268Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.09518","last_updated":"2025-04-13T11:10:47Z","snapshot_observed_at":"2026-08-07T16:06:10.395071Z","submitted_at":"2025-04-13T11:10:47Z","title":"3D CoCa: Contrastive Learners are 3D Captioners","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.09518","snapshot_observed_at":"2026-08-06T10:49:46.920771Z","title":null,"venue":null,"work_id":null,"year":2025},"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":29,"source":"arxiv_source","source_observed_at":"2026-08-06T10:49:46.920771Z"},"links":{"cited_paper":"/paper/2504.09518","citing_paper":"/paper/2507.23478"},"observation_digest":"sha256:98b56410e47574cbbe90e6263fe40aa8a16b00fb5f78648d46e9254080643c54","observation_id":"2e63b041-eb52-4526-89e8-00437bd9d758","resolution":{"observed_at":"2026-08-06T10:49:46.920771Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.09518","last_updated":"2025-04-13T11:10:47Z","snapshot_observed_at":"2026-08-07T16:06:10.395071Z","submitted_at":"2025-04-13T11:10:47Z","title":"3D CoCa: Contrastive Learners are 3D Captioners","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.09518","snapshot_observed_at":"2026-08-04T17:31:40.570298Z","title":"3d coca: Contrastive learners are 3d captioners,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.10884","last_updated":"2025-09-13T16:31:03Z","snapshot_observed_at":"2026-08-06T23:06:21.884601Z","submitted_at":"2025-09-13T16:31:03Z","title":"Nav-R1: Reasoning and Navigation in Embodied Scenes","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-04T17:31:40.570298Z"},"links":{"cited_paper":"/paper/2504.09518","citing_paper":"/paper/2509.10884"},"observation_digest":"sha256:757ae43f23aaf2a2331b01ba7508bef4930cee9dec4e63177cf234529f83f118","observation_id":"23ae5b24-bd45-432a-82b0-285805b76064","resolution":{"observed_at":"2026-08-04T17:31:40.570298Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.09518","last_updated":"2025-04-13T11:10:47Z","snapshot_observed_at":"2026-08-07T16:06:10.395071Z","submitted_at":"2025-04-13T11:10:47Z","title":"3D CoCa: Contrastive Learners are 3D Captioners","version":1},"cited_work":{"arxiv_id":"2504.09518","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2504.09518","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2504.09518 (2025)","venue":null,"work_id":"8510b71b-e0ba-4956-8510-d89dbb8c1738","year":2025},"citing_paper":{"arxiv_id":"2604.17472","last_updated":"2026-04-19T14:53:38Z","snapshot_observed_at":"2026-07-06T23:04:32.734175Z","submitted_at":"2026-04-19T14:53:38Z","title":"UniMesh: Unifying 3D Mesh Understanding and Generation","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-10T06:55:42.679323Z"},"links":{"cited_paper":"/paper/2504.09518","citing_paper":"/paper/2604.17472"},"observation_digest":"sha256:f296094dc85712db4f524afc6cb369193cac507995715af0b15e21d4d37c0816","observation_id":"45c10cbc-9ff3-4d91-b4cd-156d1d30446a","resolution":{"observed_at":"2026-05-10T06:56:47.342753Z","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"}}],"links":{"evidence":"/evidence","html":"/paper/2504.09518/citation-record","integrity":"/paper/2504.09518/integrity","json":"/paper/2504.09518/citation-record.json","paper":"/paper/2504.09518"},"outbound":[],"paper":{"arxiv_id":"2504.09518","last_updated":"2025-04-13T11:10:47Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-07T16:06:10.395071Z","submitted_at":"2025-04-13T11:10:47Z","title":"3D CoCa: Contrastive Learners are 3D Captioners"},"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:2504.09518."}