{"as_of":"2026-08-21T20:42:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:eb7fcd8febd464d60d10872a26ea69afe8d1da68e2b4f6d683b8ec2c1e1e0ebb","coverage":[{"denominator":22,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":22,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T12:40:10.210417Z","state":"measured"},{"denominator":22,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":22,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-21T06:32:19.484+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/2504.12264/citation-record","integrity":"/paper/2504.12264/integrity","json":"/paper/2504.12264/citation-record.json","paper":"/paper/2504.12264"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2212.00842","last_updated":"2022-12-15T14:01:12Z","snapshot_observed_at":"2026-08-18T12:01:26.020359Z","submitted_at":"2022-12-01T20:00:00Z","title":"3D-LDM: Neural Implicit 3D Shape Generation with Latent Diffusion Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.00842","snapshot_observed_at":"2026-08-16T12:40:10.128678Z","title":"3d-ldm: Neural implicit 3d shape generation with latent diffusion models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2504.12264","last_updated":"2025-04-16T17:21:55Z","snapshot_observed_at":"2026-08-18T12:01:54.952395Z","submitted_at":"2025-04-16T17:21:55Z","title":"Towards Learning to Complete Anything in Lidar","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-16T12:40:10.128678Z"},"links":{"cited_paper":"/paper/2212.00842","citing_paper":"/paper/2504.12264"},"observation_digest":"sha256:cbc87572fa026cae5a6359c2eb1aa1e4871df47ef5752f260d7bc6d454a7b9e0","observation_id":"55115178-a383-4345-919c-e068772eda8e","resolution":{"observed_at":"2026-08-16T12:40:10.128678Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.00714","last_updated":"2024-10-28T16:37:57Z","snapshot_observed_at":"2026-07-06T18:55:41.459417Z","submitted_at":"2024-08-01T17:00:08Z","title":"SAM 2: Segment Anything in Images and Videos","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.00714","snapshot_observed_at":"2026-08-16T12:40:10.138586Z","title":"Ren, X., Huang, J., Zeng, X., Museth, K., Fidler, S., and Williams, F","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2504.12264","last_updated":"2025-04-16T17:21:55Z","snapshot_observed_at":"2026-08-18T12:01:54.952395Z","submitted_at":"2025-04-16T17:21:55Z","title":"Towards Learning to Complete Anything in Lidar","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-16T12:40:10.138586Z"},"links":{"cited_paper":"/paper/2408.00714","citing_paper":"/paper/2504.12264"},"observation_digest":"sha256:69895a4d8509d4e0c9b5dcc3e9f6b285b800fcb20179fe31a2de54a40f6ad4f9","observation_id":"f3ed1ce3-de67-4604-a25f-2343a74e0cfb","resolution":{"observed_at":"2026-08-16T12:40:10.138586Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T12:40:10.637000Z","title":"However, (1) we assume no access to semantic labels, and (2) performing such registration is error-prone in our setting","venue":null,"work_id":"4f596972-0790-4638-8a8b-fff45a106ff2","year":2019},"citing_paper":{"arxiv_id":"2504.12264","last_updated":"2025-04-16T17:21:55Z","snapshot_observed_at":"2026-08-18T12:01:54.952395Z","submitted_at":"2025-04-16T17:21:55Z","title":"Towards Learning to Complete Anything in Lidar","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-16T12:40:10.147568Z"},"links":{"citing_paper":"/paper/2504.12264"},"observation_digest":"sha256:735eb492f18e22af63b825eff83e293e915888be65f70f67bc22443830f9afcd","observation_id":"5ac3a03b-3a14-4c22-8fb8-4d7116abaa6e","resolution":{"observed_at":"2026-08-16T12:40:10.641444Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T12:40:10.623507Z","title":null,"venue":null,"work_id":"35edb7c1-e177-4662-b279-13278b30302f","year":2024},"citing_paper":{"arxiv_id":"2504.12264","last_updated":"2025-04-16T17:21:55Z","snapshot_observed_at":"2026-08-18T12:01:54.952395Z","submitted_at":"2025-04-16T17:21:55Z","title":"Towards Learning to Complete Anything in Lidar","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-16T12:40:10.152137Z"},"links":{"citing_paper":"/paper/2504.12264"},"observation_digest":"sha256:98888d6e41ee38b90ba601de1122446ad18e4bef71af8538fea2e9d77920596b","observation_id":"7be2419f-d32f-46e6-a41d-ce176dc911ee","resolution":{"observed_at":"2026-08-16T12:40:10.627895Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T12:40:10.609462Z","title":"The output from this operation is a separate CLIP feature vector of dimension 768, for each object in the scene","venue":null,"work_id":"a25419ef-f564-4582-8443-bbad5586ada0","year":2024},"citing_paper":{"arxiv_id":"2504.12264","last_updated":"2025-04-16T17:21:55Z","snapshot_observed_at":"2026-08-18T12:01:54.952395Z","submitted_at":"2025-04-16T17:21:55Z","title":"Towards Learning to Complete Anything in Lidar","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-16T12:40:10.156852Z"},"links":{"citing_paper":"/paper/2504.12264"},"observation_digest":"sha256:0a500e340e133b084b1943d930e82e1c925f8839b22af823417b3ce42a05188f","observation_id":"f9fa06d4-2f75-479a-b3ca-4c732fa3ba84","resolution":{"observed_at":"2026-08-16T12:40:10.614112Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T12:40:10.595855Z","title":null,"venue":null,"work_id":"eb64d5df-1755-466f-8be3-4ec2d2d1b618","year":2024},"citing_paper":{"arxiv_id":"2504.12264","last_updated":"2025-04-16T17:21:55Z","snapshot_observed_at":"2026-08-18T12:01:54.952395Z","submitted_at":"2025-04-16T17:21:55Z","title":"Towards Learning to Complete Anything in Lidar","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-16T12:40:10.161317Z"},"links":{"citing_paper":"/paper/2504.12264"},"observation_digest":"sha256:c73ce98bc27793d0b39dfa0908b099e1fe0144e47fb48c2f10c19c50c6859fa9","observation_id":"b4cb5679-0cb8-4df5-8b95-30609e88a2a6","resolution":{"observed_at":"2026-08-16T12:40:10.600147Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T12:40:10.581736Z","title":"This MLP block consists of layers with dimensions [384, 512, 1024, 768, 768], where the final dimension, 768, is the dimensionality of the CLIP embedding space","venue":null,"work_id":"deb5467b-628c-4efe-8051-2c9521cf16df","year":2024},"citing_paper":{"arxiv_id":"2504.12264","last_updated":"2025-04-16T17:21:55Z","snapshot_observed_at":"2026-08-18T12:01:54.952395Z","submitted_at":"2025-04-16T17:21:55Z","title":"Towards Learning to Complete Anything in Lidar","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-16T12:40:10.166135Z"},"links":{"citing_paper":"/paper/2504.12264"},"observation_digest":"sha256:87d19d7bc489347e0e03f04b7895f9369a1921b97c245c6660d5740ddb914dce","observation_id":"7f75add6-744c-460f-95ae-b2442b54e176","resolution":{"observed_at":"2026-08-16T12:40:10.586652Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T12:40:10.553446Z","title":null,"venue":null,"work_id":"09890ae5-fc8f-484e-88c8-797f4c9ae962","year":2024},"citing_paper":{"arxiv_id":"2504.12264","last_updated":"2025-04-16T17:21:55Z","snapshot_observed_at":"2026-08-18T12:01:54.952395Z","submitted_at":"2025-04-16T17:21:55Z","title":"Towards Learning to Complete Anything in Lidar","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-16T12:40:10.175726Z"},"links":{"citing_paper":"/paper/2504.12264"},"observation_digest":"sha256:85408dbc25373fdc3aae248ac352223f52d65e37c78ad3a0389f6f0b57bf6e66","observation_id":"d53ccae4-2c09-4d2b-b7fb-2d0b67300c10","resolution":{"observed_at":"2026-08-16T12:40:10.557963Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T12:40:10.539970Z","title":null,"venue":null,"work_id":"7bc6d1ce-89bc-4e84-830c-78b682914a1f","year":2019},"citing_paper":{"arxiv_id":"2504.12264","last_updated":"2025-04-16T17:21:55Z","snapshot_observed_at":"2026-08-18T12:01:54.952395Z","submitted_at":"2025-04-16T17:21:55Z","title":"Towards Learning to Complete Anything in Lidar","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-16T12:40:10.179951Z"},"links":{"citing_paper":"/paper/2504.12264"},"observation_digest":"sha256:7b97a19221ffe6160a9bf79a16a4d51794219624f4fc3a276116f7b1b6f92ad9","observation_id":"5ca21b3b-1429-4b42-a45e-9c4380a649ee","resolution":{"observed_at":"2026-08-16T12:40:10.544267Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T12:40:10.493684Z","title":"We train the CAL model using two different sets of data: pseudo-labels w/o CRF refinement, and with CRF refinement","venue":null,"work_id":"af004b6f-df3a-42ca-9da0-4e6e41fc4455","year":2024},"citing_paper":{"arxiv_id":"2504.12264","last_updated":"2025-04-16T17:21:55Z","snapshot_observed_at":"2026-08-18T12:01:54.952395Z","submitted_at":"2025-04-16T17:21:55Z","title":"Towards Learning to Complete Anything in Lidar","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-16T12:40:10.192828Z"},"links":{"citing_paper":"/paper/2504.12264"},"observation_digest":"sha256:6a03323b2d08885dede7754cff7b996ab70c60c854bf9bba0e339b8b1fe5e9f7","observation_id":"d71a1835-4d61-4c28-ad31-dc1313b44d92","resolution":{"observed_at":"2026-08-16T12:40:10.498434Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T12:40:10.465029Z","title":null,"venue":null,"work_id":"d6e9bb14-6740-42d2-b673-c1ed0e875a71","year":2023},"citing_paper":{"arxiv_id":"2504.12264","last_updated":"2025-04-16T17:21:55Z","snapshot_observed_at":"2026-08-18T12:01:54.952395Z","submitted_at":"2025-04-16T17:21:55Z","title":"Towards Learning to Complete Anything in Lidar","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-16T12:40:10.201887Z"},"links":{"citing_paper":"/paper/2504.12264"},"observation_digest":"sha256:21619f2ee46339fb9469780df9f05936491929bfff3a8f23eb961ce1dcda98c3","observation_id":"447b5d92-e287-4a93-9ac6-38426298a1d0","resolution":{"observed_at":"2026-08-16T12:40:10.469558Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T12:40:10.450559Z","title":"vehicle” “car","venue":null,"work_id":"4d8e29d4-3408-45fb-bc9e-0597f5369e24","year":2024},"citing_paper":{"arxiv_id":"2504.12264","last_updated":"2025-04-16T17:21:55Z","snapshot_observed_at":"2026-08-18T12:01:54.952395Z","submitted_at":"2025-04-16T17:21:55Z","title":"Towards Learning to Complete Anything in Lidar","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-16T12:40:10.206090Z"},"links":{"citing_paper":"/paper/2504.12264"},"observation_digest":"sha256:28b2da7a2d78c878b787cf2bd1a56a8882aa2a04c9d86856477cf62c06a4ff34","observation_id":"081f668e-650d-462f-9bad-1836d8517751","resolution":{"observed_at":"2026-08-16T12:40:10.455278Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T12:40:10.434061Z","title":"While baselines struggle with coherent structure and semantic accuracy, CAL produces cleaner and more complete outputs that align closely with the ground truth","venue":null,"work_id":"19afb845-f02f-4e2b-acb3-e86a34e34335","year":2024},"citing_paper":{"arxiv_id":"2504.12264","last_updated":"2025-04-16T17:21:55Z","snapshot_observed_at":"2026-08-18T12:01:54.952395Z","submitted_at":"2025-04-16T17:21:55Z","title":"Towards Learning to Complete Anything in Lidar","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-16T12:40:10.210417Z"},"links":{"citing_paper":"/paper/2504.12264"},"observation_digest":"sha256:6c96f032271c90cccaf7c9c2cefd6a83f1bcb45e4baec64f3c111dc5ef60afe2","observation_id":"5eeaa8bb-8687-4464-9d78-212787398167","resolution":{"observed_at":"2026-08-16T12:40:10.440580Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T12:40:10.651070Z","title":"CRF-based refinement module In our pseudo-labeling engine (as depicted in Fig","venue":null,"work_id":"dfeb0c28-0ded-4a8f-bc3f-f46256b97144","year":2011},"citing_paper":{"arxiv_id":"2504.12264","last_updated":"2025-04-16T17:21:55Z","snapshot_observed_at":"2026-08-18T12:01:54.952395Z","submitted_at":"2025-04-16T17:21:55Z","title":"Towards Learning to Complete Anything in Lidar","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-16T12:40:10.142917Z"},"links":{"citing_paper":"/paper/2504.12264"},"observation_digest":"sha256:e320a50298af752a966800b3cf0067477b2fe05cbb8eb54708184f6f16bb3ba6","observation_id":"013da8c9-6b64-4ae0-bb74-ccefcb04a25b","resolution":{"observed_at":"2026-08-16T12:40:10.656011Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T12:40:10.567574Z","title":null,"venue":null,"work_id":"ac5494e3-850f-4e57-ac64-588d450eb36b","year":2024},"citing_paper":{"arxiv_id":"2504.12264","last_updated":"2025-04-16T17:21:55Z","snapshot_observed_at":"2026-08-18T12:01:54.952395Z","submitted_at":"2025-04-16T17:21:55Z","title":"Towards Learning to Complete Anything in Lidar","version":1},"reference_index":500,"source":"pdf_text","source_observed_at":"2026-08-16T12:40:10.171222Z"},"links":{"citing_paper":"/paper/2504.12264"},"observation_digest":"sha256:ea1b16649e91d5810f70f6e0f3004abe4be218e207f877a47157c954ba49885e","observation_id":"58641145-fafb-4bca-a728-8c2a7c661dea","resolution":{"observed_at":"2026-08-16T12:40:10.572347Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T12:40:10.525131Z","title":"These datasets provide per-voxel semantic labels (SemanticKITTI: 20 classes, 8 are thing; SSCBench-KITTI360: 19 classes, 6 are thing) that we only use during evaluation","venue":null,"work_id":"1eb7a6ec-27a3-43f7-aa38-258704caa7da","year":2024},"citing_paper":{"arxiv_id":"2504.12264","last_updated":"2025-04-16T17:21:55Z","snapshot_observed_at":"2026-08-18T12:01:54.952395Z","submitted_at":"2025-04-16T17:21:55Z","title":"Towards Learning to Complete Anything in Lidar","version":1},"reference_index":2013,"source":"pdf_text","source_observed_at":"2026-08-16T12:40:10.184330Z"},"links":{"citing_paper":"/paper/2504.12264"},"observation_digest":"sha256:c4ff4adf998ce9e463239cae50d070cfdb0cfb2cd402eba787caa5fa31a57d84","observation_id":"a1543e1f-d3d7-412c-b623-e1da775384fe","resolution":{"observed_at":"2026-08-16T12:40:10.529867Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T12:40:10.509150Z","title":"car” can be addressed by “car, jeep, SUV , van","venue":null,"work_id":"7e00f5f0-2fdf-4894-8e5b-f7b9275b46f1","year":2024},"citing_paper":{"arxiv_id":"2504.12264","last_updated":"2025-04-16T17:21:55Z","snapshot_observed_at":"2026-08-18T12:01:54.952395Z","submitted_at":"2025-04-16T17:21:55Z","title":"Towards Learning to Complete Anything in Lidar","version":1},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-16T12:40:10.188501Z"},"links":{"citing_paper":"/paper/2504.12264"},"observation_digest":"sha256:d12ef5f6ae4a06ce7314e17523b8701e00c2aab84549f7056de441e2989e6ff4","observation_id":"a6ef3170-26f1-4e49-aff4-7a593054cbee","resolution":{"observed_at":"2026-08-16T12:40:10.513986Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T12:40:10.479334Z","title":null,"venue":null,"work_id":"4676c5b7-6592-47bd-8eb7-e30e9da33c1b","year":2023},"citing_paper":{"arxiv_id":"2504.12264","last_updated":"2025-04-16T17:21:55Z","snapshot_observed_at":"2026-08-18T12:01:54.952395Z","submitted_at":"2025-04-16T17:21:55Z","title":"Towards Learning to Complete Anything in Lidar","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-16T12:40:10.197447Z"},"links":{"citing_paper":"/paper/2504.12264"},"observation_digest":"sha256:dc2382ccee5349118bf22891b4927622e354e6826773cbed1af271a6245d324d","observation_id":"9c65aa6f-c1e2-4859-a74c-547aa638d8fb","resolution":{"observed_at":"2026-08-16T12:40:10.483684Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T12:40:10.123819Z","title":"Long-tailed 3d detection via 2d late fusion","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2504.12264","last_updated":"2025-04-16T17:21:55Z","snapshot_observed_at":"2026-08-18T12:01:54.952395Z","submitted_at":"2025-04-16T17:21:55Z","title":"Towards Learning to Complete Anything in Lidar","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-16T12:40:10.123819Z"},"links":{"citing_paper":"/paper/2504.12264"},"observation_digest":"sha256:0ebaff13221f627420262a2c9a10bd1d674ee1314b2ca6f8853b57d13e8573bc","observation_id":"767a1bc9-3b9d-4f6c-88af-5018995eb38f","resolution":{"observed_at":"2026-08-16T12:40:10.123819Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.02463","last_updated":"2023-05-03T23:59:13Z","snapshot_observed_at":"2026-08-12T18:09:04.196531Z","submitted_at":"2023-05-03T23:59:13Z","title":"Shap-E: Generating Conditional 3D Implicit Functions","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.02463","snapshot_observed_at":"2026-08-16T12:40:10.113844Z","title":"and Nichol, A","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2504.12264","last_updated":"2025-04-16T17:21:55Z","snapshot_observed_at":"2026-08-18T12:01:54.952395Z","submitted_at":"2025-04-16T17:21:55Z","title":"Towards Learning to Complete Anything in Lidar","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-16T12:40:10.113844Z"},"links":{"cited_paper":"/paper/2305.02463","citing_paper":"/paper/2504.12264"},"observation_digest":"sha256:4da29004090011417664e3515c71c2ff5c10c522558ff70f752287c7bdd4839e","observation_id":"b8c2671c-dd1a-4654-89ea-df6b2aa11817","resolution":{"observed_at":"2026-08-16T12:40:10.113844Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.10115","last_updated":"2024-10-15T14:54:01Z","snapshot_observed_at":"2026-08-20T17:23:02.164886Z","submitted_at":"2024-06-14T15:21:57Z","title":"Shelf-Supervised Cross-Modal Pre-Training for 3D Object Detection","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.10115","snapshot_observed_at":"2026-08-16T12:40:10.118768Z","title":"Shelf- supervised multi-modal pre-training for 3d object detec- tion","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2504.12264","last_updated":"2025-04-16T17:21:55Z","snapshot_observed_at":"2026-08-18T12:01:54.952395Z","submitted_at":"2025-04-16T17:21:55Z","title":"Towards Learning to Complete Anything in Lidar","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-16T12:40:10.118768Z"},"links":{"cited_paper":"/paper/2406.10115","citing_paper":"/paper/2504.12264"},"observation_digest":"sha256:2762ed99eaad4f2d71309ab7e855e0918a0eef2024595fedab7617a21b65c418","observation_id":"9bbbba9a-26e7-4b2d-be91-417582bb5b38","resolution":{"observed_at":"2026-08-16T12:40:10.118768Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1512.03012","last_updated":"2015-12-09T19:42:48Z","snapshot_observed_at":"2026-08-15T22:26:43.274625Z","submitted_at":"2015-12-09T19:42:48Z","title":"ShapeNet: An Information-Rich 3D Model Repository","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1512.03012","snapshot_observed_at":"2026-08-16T12:40:10.108293Z","title":"X., Funkhouser, T., Guibas, L., Hanrahan, P., Huang, Q., Li, Z., Savarese, S., Savva, M., Song, S., Su, H., et al","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2504.12264","last_updated":"2025-04-16T17:21:55Z","snapshot_observed_at":"2026-08-18T12:01:54.952395Z","submitted_at":"2025-04-16T17:21:55Z","title":"Towards Learning to Complete Anything in Lidar","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-16T12:40:10.108293Z"},"links":{"cited_paper":"/paper/1512.03012","citing_paper":"/paper/2504.12264"},"observation_digest":"sha256:74fa472c22c7dafd80d39e3e47bf7534e071f780fa2e7b530b875d706e02f003","observation_id":"fc3bc9ec-2c02-40f3-ab5d-a6524432a408","resolution":{"observed_at":"2026-08-16T12:40:10.108293Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2504.12264","last_updated":"2025-04-16T17:21:55Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-18T12:01:54.952395Z","submitted_at":"2025-04-16T17:21:55Z","title":"Towards Learning to Complete Anything in Lidar"},"reference_resolution":{"displayed":22,"state_counts":{"malformed_identifier":2,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":13,"verified_exact":0,"verified_fuzzy":7},"total_outbound_references":22},"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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 21 August 2026, this Paper Citation Record lists 22 of 22 outbound references and 0 inbound Pith citation observations for arXiv:2504.12264."}