{"as_of":"2026-08-09T15:44:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a00473e35d81ce6e1641e6e426ca3fb75b6e8dfc77a9bbb6d49503a156f82dcb","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":"2026-08-09T06:31:02.800959+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":"2026-08-06T21:11:41.518057Z","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":"2026-05-16T20:38:24.849071Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2407.06084","last_updated":"2024-07-08T16:26:52Z","snapshot_observed_at":"2026-07-06T18:43:09.852565Z","submitted_at":"2024-07-08T16:26:52Z","title":"3D Vision and Language Pretraining with Large-Scale Synthetic Data","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.06084","snapshot_observed_at":"2026-08-06T21:11:41.518057Z","title":"3d vision and language pretraining with large-scale synthetic data.arXiv:2407.06084, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.00886","last_updated":"2025-07-01T15:52:59Z","snapshot_observed_at":"2026-08-08T11:31:10.308352Z","submitted_at":"2025-07-01T15:52:59Z","title":"GaussianVLM: Scene-centric 3D Vision-Language Models using Language-aligned Gaussian Splats for Embodied Reasoning and Beyond","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-06T21:11:41.518057Z"},"links":{"cited_paper":"/paper/2407.06084","citing_paper":"/paper/2507.00886"},"observation_digest":"sha256:11aefe1080a20daee46aefab33e23d12b21ce6189c9cdd0552c90e5d2e98bb06","observation_id":"082210d5-5156-446f-846e-b2e69e8d03a2","resolution":{"observed_at":"2026-08-06T21:11:41.518057Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.06084","last_updated":"2024-07-08T16:26:52Z","snapshot_observed_at":"2026-07-06T18:43:09.852565Z","submitted_at":"2024-07-08T16:26:52Z","title":"3D Vision and Language Pretraining with Large-Scale Synthetic Data","version":1},"cited_work":{"arxiv_id":"2407.06084","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2407.06084","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"3d vision and language pre- training with large-scale synthetic data","venue":null,"work_id":"f6fbb437-6ef7-4f51-a5e9-643fb119f58a","year":2024},"citing_paper":{"arxiv_id":"2512.17817","last_updated":"2026-05-04T21:21:49Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-12-19T17:22:35Z","title":"Chorus: Multi-Teacher Pretraining for Holistic 3D Gaussian Scene Encoding","version":3},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-05-16T20:34:16.666956Z"},"links":{"cited_paper":"/paper/2407.06084","citing_paper":"/paper/2512.17817"},"observation_digest":"sha256:616924e3e192882cc51b207365a81100c4dcb05f6a4e1283c932cc83345d0df6","observation_id":"0f75b524-9531-4b50-afc4-d6cb8250b81d","resolution":{"observed_at":"2026-05-16T20:38:24.850840Z","resolver_source":"arxiv_id","status":"verified_exact"},"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"}},{"citation":{"cited_paper":{"arxiv_id":"2407.06084","last_updated":"2024-07-08T16:26:52Z","snapshot_observed_at":"2026-07-06T18:43:09.852565Z","submitted_at":"2024-07-08T16:26:52Z","title":"3D Vision and Language Pretraining with Large-Scale Synthetic Data","version":1},"cited_work":{"arxiv_id":"2407.06084","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2407.06084","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"3d vision and language pre- training with large-scale synthetic data","venue":null,"work_id":"f6fbb437-6ef7-4f51-a5e9-643fb119f58a","year":2024},"citing_paper":{"arxiv_id":"2604.25276","last_updated":"2026-04-28T06:34:19Z","snapshot_observed_at":"2026-07-06T23:11:11.827339Z","submitted_at":"2026-04-28T06:34:19Z","title":"OmniVTG: A Large-Scale Dataset and Training Paradigm for Open-World Video Temporal Grounding","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-05-07T16:51:43.783133Z"},"links":{"cited_paper":"/paper/2407.06084","citing_paper":"/paper/2604.25276"},"observation_digest":"sha256:60ae49dcc332b7157960b7025b33187582c618249992efe6d5a60efcf70bedff","observation_id":"502f1c00-f54c-4c55-9ba3-b43cbde4626b","resolution":{"observed_at":"2026-05-11T23:31:15.746451Z","resolver_source":"arxiv_id","status":"verified_exact"},"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/2407.06084/citation-record","integrity":"/paper/2407.06084/integrity","json":"/paper/2407.06084/citation-record.json","paper":"/paper/2407.06084"},"outbound":[],"paper":{"arxiv_id":"2407.06084","last_updated":"2024-07-08T16:26:52Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T18:43:09.852565Z","submitted_at":"2024-07-08T16:26:52Z","title":"3D Vision and Language Pretraining with Large-Scale Synthetic Data"},"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 3 inbound Pith citation observations for arXiv:2407.06084."}