{"as_of":"2026-07-29T05:26:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a3db1b50b8150adcf3cd3c0896862f0704a4d2eff08d0b1302cb20fc1c405f34","coverage":[{"denominator":20,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":20,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-24T20:48:51.430219Z","state":"measured"},{"denominator":20,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":20,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-07-28T06:31:03.373048+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/1907.07061/citation-record","integrity":"/paper/1907.07061/integrity","json":"/paper/1907.07061/citation-record.json","paper":"/paper/1907.07061"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"1903.11027","last_updated":"2020-05-05T09:13:24Z","snapshot_observed_at":"2026-07-06T07:41:49.415532Z","submitted_at":"2019-03-26T17:19:56Z","title":"nuScenes: A multimodal dataset for autonomous driving","version":5},"cited_work":{"arxiv_id":"1903.11027","doi":"10.48550/arxiv.1903.11027","metadata_source":"pith","pith_arxiv_id":"1903.11027","snapshot_observed_at":"2026-07-10T06:15:00.866473Z","title":"nuScenes: A multimodal dataset for autonomous driving","venue":"cs.LG","work_id":"a687c611-43a9-4af4-bf00-36a2d9fa85a8","year":2019},"citing_paper":{"arxiv_id":"1907.07061","last_updated":"2019-07-16T15:21:38Z","snapshot_observed_at":"2026-07-06T08:08:05.915923Z","submitted_at":"2019-07-16T15:21:38Z","title":"How much real data do we actually need: Analyzing object detection performance using synthetic and real data","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-24T20:48:51.430219Z"},"links":{"cited_paper":"/paper/1903.11027","citing_paper":"/paper/1907.07061"},"observation_digest":"sha256:106786f41e68d65b80a400b0bec18620482a97924e075b5b3826f4af1b4c6597","observation_id":"8313f1da-b1bf-4dd1-8eae-844d6f4c9db8","resolution":{"observed_at":"2026-05-24T20:49:54.489370Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-28T06:31:03.373048+00:00","source":"crossref"},{"observed_at":"2026-07-28T06:30:57.601408+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1809.06256","last_updated":"2019-01-07T17:01:45Z","snapshot_observed_at":"2026-07-06T07:02:38.518019Z","submitted_at":"2018-09-17T14:44:42Z","title":"Sensor Transfer: Learning Optimal Sensor Effect Image Augmentation for Sim-to-Real Domain Adaptation","version":2},"cited_work":{"arxiv_id":"1809.06256","doi":null,"metadata_source":"pith","pith_arxiv_id":"1809.06256","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Sensor Transfer: Learning Optimal Sensor Effect Image Augmentation for Sim-to-Real Domain Adaptation","venue":"cs.CV","work_id":"0a850e95-79a3-4805-8851-c9a574d0a2e9","year":2018},"citing_paper":{"arxiv_id":"1907.07061","last_updated":"2019-07-16T15:21:38Z","snapshot_observed_at":"2026-07-06T08:08:05.915923Z","submitted_at":"2019-07-16T15:21:38Z","title":"How much real data do we actually need: Analyzing object detection performance using synthetic and real data","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-24T20:48:51.430219Z"},"links":{"cited_paper":"/paper/1809.06256","citing_paper":"/paper/1907.07061"},"observation_digest":"sha256:95baae2b9e55c6020ab60bb40437e07334b0a954e140cdc77fea0d46b1cb736b","observation_id":"4266b223-15bb-4c8b-89be-49173b3180e4","resolution":{"observed_at":"2026-05-24T20:49:54.512900Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-28T06:31:03.373048+00:00","source":"crossref"},{"observed_at":"2026-07-28T06:30:57.601408+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1811.07112","last_updated":"2019-04-10T09:59:47Z","snapshot_observed_at":"2026-07-06T07:15:19.493472Z","submitted_at":"2018-11-17T07:09:13Z","title":"Augmented LiDAR Simulator for Autonomous Driving","version":2},"cited_work":{"arxiv_id":"1811.07112","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1811.07112","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Simulating LiDAR point cloud for autonomous driving using real-world scenes and traffic flows","venue":null,"work_id":"082c4289-956f-4e36-89e4-4ae42e5334b8","year":2018},"citing_paper":{"arxiv_id":"1907.07061","last_updated":"2019-07-16T15:21:38Z","snapshot_observed_at":"2026-07-06T08:08:05.915923Z","submitted_at":"2019-07-16T15:21:38Z","title":"How much real data do we actually need: Analyzing object detection performance using synthetic and real data","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-24T20:48:51.430219Z"},"links":{"cited_paper":"/paper/1811.07112","citing_paper":"/paper/1907.07061"},"observation_digest":"sha256:57d962ff669cc162500d125427d1f573362a3d27419a58627ab0929b76fd2e4a","observation_id":"b329873e-f0a6-4afb-81d3-49477a34c205","resolution":{"observed_at":"2026-05-24T20:49:54.543397Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-28T06:31:03.373048+00:00","source":"crossref"},{"observed_at":"2026-07-28T06:30:57.601408+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1612.02649","last_updated":"2016-12-08T14:11:10Z","snapshot_observed_at":"2026-07-06T05:21:53.110941Z","submitted_at":"2016-12-08T14:11:10Z","title":"FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation","version":1},"cited_work":{"arxiv_id":"1612.02649","doi":null,"metadata_source":"pith","pith_arxiv_id":"1612.02649","snapshot_observed_at":"2026-07-01T21:16:13.733869Z","title":"FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation","venue":"cs.CV","work_id":"b3eeca82-47bf-4b28-80fc-1dbcd1dc2a8f","year":2016},"citing_paper":{"arxiv_id":"1907.07061","last_updated":"2019-07-16T15:21:38Z","snapshot_observed_at":"2026-07-06T08:08:05.915923Z","submitted_at":"2019-07-16T15:21:38Z","title":"How much real data do we actually need: Analyzing object detection performance using synthetic and real data","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-24T20:48:51.430219Z"},"links":{"cited_paper":"/paper/1612.02649","citing_paper":"/paper/1907.07061"},"observation_digest":"sha256:38b881f8f7fbbfaf7276a2e21c932a719075e87bc4f815787c5b220b870a5d1b","observation_id":"be318d2b-c7c3-4a2f-a671-abc79080868e","resolution":{"observed_at":"2026-05-24T20:49:54.468616Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-28T06:31:03.373048+00:00","source":"crossref"},{"observed_at":"2026-07-28T06:30:57.601408+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1711.03213","last_updated":"2017-12-29T05:00:37Z","snapshot_observed_at":"2026-07-06T06:08:32.009246Z","submitted_at":"2017-11-08T23:54:52Z","title":"CyCADA: Cycle-Consistent Adversarial Domain Adaptation","version":3},"cited_work":{"arxiv_id":"1711.03213","doi":null,"metadata_source":"pith","pith_arxiv_id":"1711.03213","snapshot_observed_at":"2026-06-28T22:42:46.979293Z","title":"CyCADA: Cycle-Consistent Adversarial Domain Adaptation","venue":"cs.CV","work_id":"1372a21e-240c-474b-9f12-5016db339dff","year":2017},"citing_paper":{"arxiv_id":"1907.07061","last_updated":"2019-07-16T15:21:38Z","snapshot_observed_at":"2026-07-06T08:08:05.915923Z","submitted_at":"2019-07-16T15:21:38Z","title":"How much real data do we actually need: Analyzing object detection performance using synthetic and real data","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-24T20:48:51.430219Z"},"links":{"cited_paper":"/paper/1711.03213","citing_paper":"/paper/1907.07061"},"observation_digest":"sha256:a53cdfb78307075f004c4bc7cf013b66bf81d426b8f01775f71d5dc57c6840b2","observation_id":"6cffc965-d240-4a06-99e7-799dfed7cd3a","resolution":{"observed_at":"2026-05-24T20:49:54.461919Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-28T06:31:03.373048+00:00","source":"crossref"},{"observed_at":"2026-07-28T06:30:57.601408+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Speed/accuracy trade-offs for modern con- volutional object detectors","venue":null,"work_id":"7c2d0300-5fa0-43f3-a3ef-196e1963e14b","year":2017},"citing_paper":{"arxiv_id":"1907.07061","last_updated":"2019-07-16T15:21:38Z","snapshot_observed_at":"2026-07-06T08:08:05.915923Z","submitted_at":"2019-07-16T15:21:38Z","title":"How much real data do we actually need: Analyzing object detection performance using synthetic and real data","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-24T20:48:51.430219Z"},"links":{"citing_paper":"/paper/1907.07061"},"observation_digest":"sha256:63cb7711384c3a54079f256fd8e6e602fa15b793805a407227689af5793c4089","observation_id":"2fe245a6-4c39-4465-ae2a-f52373c8ab45","resolution":{"observed_at":"2026-05-24T20:49:55.185914Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-28T06:31:03.373048+00:00","source":"crossref"},{"observed_at":"2026-07-28T06:30:57.601408+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1705.10118","last_updated":"2018-06-13T14:01:09Z","snapshot_observed_at":"2026-07-06T05:44:37.068405Z","submitted_at":"2017-05-29T11:11:07Z","title":"Beyond Counting: Comparisons of Density Maps for Crowd Analysis Tasks - Counting, Detection, and Tracking","version":2},"cited_work":{"arxiv_id":"1705.10118","doi":null,"metadata_source":"pith","pith_arxiv_id":"1705.10118","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Beyond Counting: Comparisons of Density Maps for Crowd Analysis Tasks - Counting, Detection, and Tracking","venue":"cs.CV","work_id":"848bc62b-7e28-4d84-9fce-a6aac789a035","year":2017},"citing_paper":{"arxiv_id":"1907.07061","last_updated":"2019-07-16T15:21:38Z","snapshot_observed_at":"2026-07-06T08:08:05.915923Z","submitted_at":"2019-07-16T15:21:38Z","title":"How much real data do we actually need: Analyzing object detection performance using synthetic and real data","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-24T20:48:51.430219Z"},"links":{"cited_paper":"/paper/1705.10118","citing_paper":"/paper/1907.07061"},"observation_digest":"sha256:a7fe2c72a40d78c62e1b2bef41b4f239ca73b5f025dae1fea7c1fa7036b5af8e","observation_id":"6ddcd631-94bd-490e-b5d6-13ed7b8ef69e","resolution":{"observed_at":"2026-05-24T20:49:54.505546Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-28T06:31:03.373048+00:00","source":"crossref"},{"observed_at":"2026-07-28T06:30:57.601408+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Few-shot image recognition by predicting parameters from activations","venue":null,"work_id":"caa81c6c-be5a-45ab-9ebf-eaf06a9e6861","year":2018},"citing_paper":{"arxiv_id":"1907.07061","last_updated":"2019-07-16T15:21:38Z","snapshot_observed_at":"2026-07-06T08:08:05.915923Z","submitted_at":"2019-07-16T15:21:38Z","title":"How much real data do we actually need: Analyzing object detection performance using synthetic and real data","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-24T20:48:51.430219Z"},"links":{"citing_paper":"/paper/1907.07061"},"observation_digest":"sha256:475d8861014cd2251025fd8eab6bed648b8e57526c81d84c44874f39f5971b0b","observation_id":"0fed72cc-348a-4a71-ae40-b9bfff8203bb","resolution":{"observed_at":"2026-05-24T20:49:55.179258Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-28T06:31:03.373048+00:00","source":"crossref"},{"observed_at":"2026-07-28T06:30:57.601408+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"and Frtunikj, J","venue":null,"work_id":"ae7809e2-1f52-4bb2-9482-b1297c74aac8","year":2018},"citing_paper":{"arxiv_id":"1907.07061","last_updated":"2019-07-16T15:21:38Z","snapshot_observed_at":"2026-07-06T08:08:05.915923Z","submitted_at":"2019-07-16T15:21:38Z","title":"How much real data do we actually need: Analyzing object detection performance using synthetic and real data","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-24T20:48:51.430219Z"},"links":{"citing_paper":"/paper/1907.07061"},"observation_digest":"sha256:7ad58f124c50e3849116dd533faa6d3af06301f36657e1327504e431b5d78b0c","observation_id":"2f593fe5-48f3-4565-9cb0-2e1efc30ae6a","resolution":{"observed_at":"2026-05-24T20:49:55.182486Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-28T06:31:03.373048+00:00","source":"crossref"},{"observed_at":"2026-07-28T06:30:57.601408+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1603.05279","last_updated":"2016-08-02T20:59:14Z","snapshot_observed_at":"2026-07-06T04:49:45.483208Z","submitted_at":"2016-03-16T20:56:21Z","title":"XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks","version":4},"cited_work":{"arxiv_id":"1603.05279","doi":"10.48550/arxiv.1603.05279","metadata_source":"pith","pith_arxiv_id":"1603.05279","snapshot_observed_at":"2026-07-10T06:15:00.866473Z","title":"XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks","venue":"cs.CV","work_id":"fb3880e0-5556-49f3-b77b-34d97cda6320","year":2016},"citing_paper":{"arxiv_id":"1907.07061","last_updated":"2019-07-16T15:21:38Z","snapshot_observed_at":"2026-07-06T08:08:05.915923Z","submitted_at":"2019-07-16T15:21:38Z","title":"How much real data do we actually need: Analyzing object detection performance using synthetic and real data","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-24T20:48:51.430219Z"},"links":{"cited_paper":"/paper/1603.05279","citing_paper":"/paper/1907.07061"},"observation_digest":"sha256:6e07ddebcefca4d1f2e065fad8820257d8945466af8974c81c700ab585d7d01b","observation_id":"7a6c5899-d891-40db-954d-23aa1d6cc55c","resolution":{"observed_at":"2026-05-24T20:49:54.498535Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-28T06:31:03.373048+00:00","source":"crossref"},{"observed_at":"2026-07-28T06:30:57.601408+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1711.06969","last_updated":"2018-04-01T21:48:18Z","snapshot_observed_at":"2026-07-06T06:10:11.091045Z","submitted_at":"2017-11-19T05:25:24Z","title":"Learning from Synthetic Data: Addressing Domain Shift for Semantic Segmentation","version":2},"cited_work":{"arxiv_id":"1711.06969","doi":null,"metadata_source":"pith","pith_arxiv_id":"1711.06969","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Learning from Synthetic Data: Addressing Domain Shift for Semantic Segmentation","venue":"cs.CV","work_id":"56c9474b-bca2-4092-8d1f-ce130bca2908","year":2017},"citing_paper":{"arxiv_id":"1907.07061","last_updated":"2019-07-16T15:21:38Z","snapshot_observed_at":"2026-07-06T08:08:05.915923Z","submitted_at":"2019-07-16T15:21:38Z","title":"How much real data do we actually need: Analyzing object detection performance using synthetic and real data","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-24T20:48:51.430219Z"},"links":{"cited_paper":"/paper/1711.06969","citing_paper":"/paper/1907.07061"},"observation_digest":"sha256:0e7e5d9aa2aaaa8fa26c44cc0cc731535a264f1aadb94fae6e0538d23c9fdca2","observation_id":"8bb5ce35-4329-4375-b408-9e30013f7dc2","resolution":{"observed_at":"2026-05-24T20:49:54.536394Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-28T06:31:03.373048+00:00","source":"crossref"},{"observed_at":"2026-07-28T06:30:57.601408+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1803.06199","last_updated":"2018-09-24T09:27:33Z","snapshot_observed_at":"2026-07-06T06:28:38.726350Z","submitted_at":"2018-03-16T12:54:40Z","title":"Complex-YOLO: Real-time 3D Object Detection on Point Clouds","version":2},"cited_work":{"arxiv_id":"1803.06199","doi":null,"metadata_source":"pith","pith_arxiv_id":"1803.06199","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Complex-YOLO: Real-time 3D Object Detection on Point Clouds","venue":"cs.CV","work_id":"3b114b48-bb52-4dd0-9192-e6bb37a54d52","year":2018},"citing_paper":{"arxiv_id":"1907.07061","last_updated":"2019-07-16T15:21:38Z","snapshot_observed_at":"2026-07-06T08:08:05.915923Z","submitted_at":"2019-07-16T15:21:38Z","title":"How much real data do we actually need: Analyzing object detection performance using synthetic and real data","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-24T20:48:51.430219Z"},"links":{"cited_paper":"/paper/1803.06199","citing_paper":"/paper/1907.07061"},"observation_digest":"sha256:e923c9789bb94bc357aba34189874deb6d246a8e9187460e1bfd1a1d03a2697e","observation_id":"8c07504a-d1d2-44d6-92b2-5e4c77f3cf0d","resolution":{"observed_at":"2026-05-24T20:49:54.475074Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-28T06:31:03.373048+00:00","source":"crossref"},{"observed_at":"2026-07-28T06:30:57.601408+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1711.06025","last_updated":"2018-03-27T10:55:50Z","snapshot_observed_at":"2026-07-06T06:09:48.494244Z","submitted_at":"2017-11-16T11:01:51Z","title":"Learning to Compare: Relation Network for Few-Shot Learning","version":2},"cited_work":{"arxiv_id":"1711.06025","doi":null,"metadata_source":"pith","pith_arxiv_id":"1711.06025","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Learning to Compare: Relation Network for Few-Shot Learning","venue":"cs.CV","work_id":"e518ddc6-12b3-4987-b682-1af23e7192f3","year":2017},"citing_paper":{"arxiv_id":"1907.07061","last_updated":"2019-07-16T15:21:38Z","snapshot_observed_at":"2026-07-06T08:08:05.915923Z","submitted_at":"2019-07-16T15:21:38Z","title":"How much real data do we actually need: Analyzing object detection performance using synthetic and real data","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-24T20:48:51.430219Z"},"links":{"cited_paper":"/paper/1711.06025","citing_paper":"/paper/1907.07061"},"observation_digest":"sha256:7b65ee4d88e1004c4851cfa2d1ac2e91c159876949c51059a7918517eebffa30","observation_id":"46e3c302-20da-4009-a023-7e36c31fb896","resolution":{"observed_at":"2026-05-24T20:49:54.563592Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-28T06:31:03.373048+00:00","source":"crossref"},{"observed_at":"2026-07-28T06:30:57.601408+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1801.07829","last_updated":"2019-06-11T06:11:21Z","snapshot_observed_at":"2026-07-06T06:19:58.980832Z","submitted_at":"2018-01-24T01:14:04Z","title":"Dynamic Graph CNN for Learning on Point Clouds","version":2},"cited_work":{"arxiv_id":"1801.07829","doi":null,"metadata_source":"pith","pith_arxiv_id":"1801.07829","snapshot_observed_at":"2026-07-03T02:57:34.527333Z","title":"Dynamic Graph CNN for Learning on Point Clouds","venue":"cs.CV","work_id":"cb96fb07-0623-404e-9782-1907ebe303f3","year":2018},"citing_paper":{"arxiv_id":"1907.07061","last_updated":"2019-07-16T15:21:38Z","snapshot_observed_at":"2026-07-06T08:08:05.915923Z","submitted_at":"2019-07-16T15:21:38Z","title":"How much real data do we actually need: Analyzing object detection performance using synthetic and real data","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-24T20:48:51.430219Z"},"links":{"cited_paper":"/paper/1801.07829","citing_paper":"/paper/1907.07061"},"observation_digest":"sha256:86834fe493a79a710c6df083132b1904769b41b4b046fdde17ad072964bb5a9d","observation_id":"b89f2164-3bef-4628-8407-04276a846f38","resolution":{"observed_at":"2026-05-24T20:49:54.519856Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-28T06:31:03.373048+00:00","source":"crossref"},{"observed_at":"2026-07-28T06:30:57.601408+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1810.08705","last_updated":"2018-10-19T22:30:44Z","snapshot_observed_at":"2026-07-06T07:09:29.571298Z","submitted_at":"2018-10-19T22:30:44Z","title":"Synscapes: A Photorealistic Synthetic Dataset for Street Scene Parsing","version":1},"cited_work":{"arxiv_id":"1810.08705","doi":null,"metadata_source":"pith","pith_arxiv_id":"1810.08705","snapshot_observed_at":"2026-07-04T08:39:42.341129Z","title":"Synscapes: A Photorealistic Synthetic Dataset for Street Scene Parsing","venue":"cs.CV","work_id":"56b3994c-51d3-4b45-b427-514158d7ed22","year":2018},"citing_paper":{"arxiv_id":"1907.07061","last_updated":"2019-07-16T15:21:38Z","snapshot_observed_at":"2026-07-06T08:08:05.915923Z","submitted_at":"2019-07-16T15:21:38Z","title":"How much real data do we actually need: Analyzing object detection performance using synthetic and real data","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-24T20:48:51.430219Z"},"links":{"cited_paper":"/paper/1810.08705","citing_paper":"/paper/1907.07061"},"observation_digest":"sha256:e8c4ab28e59ec7a44a79ac92300a9ce16d54d687cea60846a2326fceac0644e9","observation_id":"fef4cc0a-9e77-4d9f-bd2d-315bce194827","resolution":{"observed_at":"2026-05-24T20:49:54.482333Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-28T06:31:03.373048+00:00","source":"crossref"},{"observed_at":"2026-07-28T06:30:57.601408+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1710.07368","last_updated":"2017-10-19T23:03:33Z","snapshot_observed_at":"2026-07-06T06:05:09.135384Z","submitted_at":"2017-10-19T23:03:33Z","title":"SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloud","version":1},"cited_work":{"arxiv_id":"1710.07368","doi":null,"metadata_source":"pith","pith_arxiv_id":"1710.07368","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloud","venue":"cs.CV","work_id":"1144ecdf-1fce-4464-a05a-14d8da07308f","year":2017},"citing_paper":{"arxiv_id":"1907.07061","last_updated":"2019-07-16T15:21:38Z","snapshot_observed_at":"2026-07-06T08:08:05.915923Z","submitted_at":"2019-07-16T15:21:38Z","title":"How much real data do we actually need: Analyzing object detection performance using synthetic and real data","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-24T20:48:51.430219Z"},"links":{"cited_paper":"/paper/1710.07368","citing_paper":"/paper/1907.07061"},"observation_digest":"sha256:564cd3ddba68bcd7d5b5b9cc24086fd2259ae81a7c72d488063de7a423409615","observation_id":"5f6e554e-133b-4d81-985b-2bdf9e972888","resolution":{"observed_at":"2026-05-24T20:49:54.454179Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-28T06:31:03.373048+00:00","source":"crossref"},{"observed_at":"2026-07-28T06:30:57.601408+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Learning cross-modal deep representations for robust pedestrian detection","venue":null,"work_id":"a9697a3b-cebc-4cac-9274-d4a962f87215","year":2017},"citing_paper":{"arxiv_id":"1907.07061","last_updated":"2019-07-16T15:21:38Z","snapshot_observed_at":"2026-07-06T08:08:05.915923Z","submitted_at":"2019-07-16T15:21:38Z","title":"How much real data do we actually need: Analyzing object detection performance using synthetic and real data","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-24T20:48:51.430219Z"},"links":{"citing_paper":"/paper/1907.07061"},"observation_digest":"sha256:810746c773eacbb9bdc0d52fd78d6c8a9814f4497b674f33e2b3ae9aa2cb85ce","observation_id":"5fd1a89f-2955-4f5c-807f-330bb9426fba","resolution":{"observed_at":"2026-05-24T20:49:55.189664Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-28T06:31:03.373048+00:00","source":"crossref"},{"observed_at":"2026-07-28T06:30:57.601408+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1805.04687","last_updated":"2020-04-08T09:25:06Z","snapshot_observed_at":"2026-07-06T06:38:43.563060Z","submitted_at":"2018-05-12T09:24:21Z","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","version":2},"cited_work":{"arxiv_id":"1805.04687","doi":null,"metadata_source":"pith","pith_arxiv_id":"1805.04687","snapshot_observed_at":"2026-07-08T02:04:26.297434Z","title":"BD D100K: A diverse driving video database with scalable annotation tooling","venue":"cs.CV","work_id":"9086cbbe-1c48-4785-9867-2f59b3807054","year":2018},"citing_paper":{"arxiv_id":"1907.07061","last_updated":"2019-07-16T15:21:38Z","snapshot_observed_at":"2026-07-06T08:08:05.915923Z","submitted_at":"2019-07-16T15:21:38Z","title":"How much real data do we actually need: Analyzing object detection performance using synthetic and real data","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-24T20:48:51.430219Z"},"links":{"cited_paper":"/paper/1805.04687","citing_paper":"/paper/1907.07061"},"observation_digest":"sha256:a6e4a21230f444ab9a2ac5ee192a97817044053e7d5cfc4c8a722ea3e42f9379","observation_id":"fddaeb79-c8e7-471a-944c-7b73f50394c7","resolution":{"observed_at":"2026-05-24T20:49:54.527731Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-28T06:31:03.373048+00:00","source":"crossref"},{"observed_at":"2026-07-28T06:30:57.601408+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1804.08286","last_updated":"2018-04-23T08:44:52Z","snapshot_observed_at":"2026-07-06T06:34:48.086149Z","submitted_at":"2018-04-23T08:44:52Z","title":"Fully Convolutional Adaptation Networks for Semantic Segmentation","version":1},"cited_work":{"arxiv_id":"1804.08286","doi":null,"metadata_source":"pith","pith_arxiv_id":"1804.08286","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Fully Convolutional Adaptation Networks for Semantic Segmentation","venue":"cs.CV","work_id":"a028b60b-f604-4695-9559-dd3f3fabb878","year":2018},"citing_paper":{"arxiv_id":"1907.07061","last_updated":"2019-07-16T15:21:38Z","snapshot_observed_at":"2026-07-06T08:08:05.915923Z","submitted_at":"2019-07-16T15:21:38Z","title":"How much real data do we actually need: Analyzing object detection performance using synthetic and real data","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-05-24T20:48:51.430219Z"},"links":{"cited_paper":"/paper/1804.08286","citing_paper":"/paper/1907.07061"},"observation_digest":"sha256:c95d8da87cb15b33e7e145654d52338e6bc2971f4ad18f7d71f8371b5fc30c63","observation_id":"362e5f2c-4716-48d1-859c-f078333d22d1","resolution":{"observed_at":"2026-05-24T20:49:54.557231Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-28T06:31:03.373048+00:00","source":"crossref"},{"observed_at":"2026-07-28T06:30:57.601408+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1612.01105","last_updated":"2017-04-27T12:15:17Z","snapshot_observed_at":"2026-07-06T05:21:16.403551Z","submitted_at":"2016-12-04T11:46:22Z","title":"Pyramid Scene Parsing Network","version":2},"cited_work":{"arxiv_id":"1612.01105","doi":null,"metadata_source":"pith","pith_arxiv_id":"1612.01105","snapshot_observed_at":"2026-07-01T23:26:22.156561Z","title":"Pyramid Scene Parsing Network","venue":"cs.CV","work_id":"830d901d-b649-43f9-8a1c-ff8422cdb225","year":2016},"citing_paper":{"arxiv_id":"1907.07061","last_updated":"2019-07-16T15:21:38Z","snapshot_observed_at":"2026-07-06T08:08:05.915923Z","submitted_at":"2019-07-16T15:21:38Z","title":"How much real data do we actually need: Analyzing object detection performance using synthetic and real data","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-24T20:48:51.430219Z"},"links":{"cited_paper":"/paper/1612.01105","citing_paper":"/paper/1907.07061"},"observation_digest":"sha256:a8202552775c084b14f4afe315654c0b442e492f16c507b963ade50100389f0f","observation_id":"6fec306a-39b8-4b90-82da-081721eb531f","resolution":{"observed_at":"2026-05-24T20:49:54.550214Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-28T06:31:03.373048+00:00","source":"crossref"},{"observed_at":"2026-07-28T06:30:57.601408+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"1907.07061","last_updated":"2019-07-16T15:21:38Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T08:08:05.915923Z","submitted_at":"2019-07-16T15:21:38Z","title":"How much real data do we actually need: Analyzing object detection performance using synthetic and real data"},"reference_resolution":{"displayed":20,"state_counts":{"malformed_identifier":0,"metadata_mismatch":9,"parse_uncertain":0,"unresolved":0,"verified_exact":7,"verified_fuzzy":4},"total_outbound_references":20},"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":"2026-07-28T06:31:03.373048+00:00","source":"crossref"},{"observed_at":"2026-07-28T06:30:57.601408+00:00","source":"retraction_watch"}],"thesis":"As of 29 July 2026, this Paper Citation Record lists 20 of 20 outbound references and 0 inbound Pith citation observations for arXiv:1907.07061."}