{"as_of":"2026-08-05T23:57:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e7e23e9f64642c2721ebcfb12cabcc23389548a7fce3de6dd2373c1bbfec0d36","coverage":[{"denominator":89,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":89,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T12:47:49.382534Z","state":"measured"},{"denominator":89,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":89,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-05T06:32:48.257954+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/2509.01250/citation-record","integrity":"/paper/2509.01250/integrity","json":"/paper/2509.01250/citation-record.json","paper":"/paper/2509.01250"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T12:47:49.100102Z","title":"Learning representations and generative models for 3d point clouds","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.100102Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:d0bb2175097350ceb30de134816037ab4b20ce022b75af3ab0bc0e69cd206712","observation_id":"66ae0d3d-0613-493b-a8d9-6c721990e1cc","resolution":{"observed_at":"2026-08-05T12:47:49.100102Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T12:47:49.104084Z","title":"Crosspoint: Self-supervised cross-modal contrastive learning for 3d point cloud understanding","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.104084Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:d0dae8202c32c6107021fb901ead9fb9470032e173048142ff6e952a99b85eea","observation_id":"683722f1-285e-4038-8357-189d990a6b67","resolution":{"observed_at":"2026-08-05T12:47:49.104084Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T12:47:49.107632Z","title":"3d seman- tic parsing of large-scale indoor spaces","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.107632Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:ac919db785e7374e9aa33d7d5fd97dcbc0dcf3502225a7fb61dd88bc7f36e117","observation_id":"d1fd6b21-dc7c-4b2c-a8ed-b44e571cb0be","resolution":{"observed_at":"2026-08-05T12:47:49.107632Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.08254","last_updated":"2022-09-03T14:11:33Z","snapshot_observed_at":"2026-07-06T11:19:34.705520Z","submitted_at":"2021-06-15T16:02:37Z","title":"BEiT: BERT Pre-Training of Image Transformers","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.08254","snapshot_observed_at":"2026-08-05T12:47:49.111436Z","title":"Beit: Bert pre-training of image transformers","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.111436Z"},"links":{"cited_paper":"/paper/2106.08254","citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:9e1ffa99de56b9fcaf4fb218ce68fa50630692d7520d2c94d75720c091749fb4","observation_id":"78e41119-18c9-4cb2-af1d-c4961cf63667","resolution":{"observed_at":"2026-08-05T12:47:49.111436Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T12:47:49.116887Z","title":"Emerg- ing properties in self-supervised vision transformers","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.116887Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:e56c7fab281a35bf4569c87f7b428846cd610b3a86e961c02bad4ae193218db0","observation_id":"0120a922-b234-4c63-89bb-cba148c62cdf","resolution":{"observed_at":"2026-08-05T12:47:49.116887Z","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":"2026-08-02T21:55:14.093687Z","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":"2026-08-05T12:47:49.120748Z","title":"Shapenet: An information-rich 3d model repository","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.120748Z"},"links":{"cited_paper":"/paper/1512.03012","citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:374b9159130dffdc6eb6106e42f4fc0e1bc7e41a37b4e21ebec4802c4a3730f1","observation_id":"fd36566b-f114-4bfb-a713-20dd745c2359","resolution":{"observed_at":"2026-08-05T12:47:49.120748Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T12:47:49.124979Z","title":"Pimae: Point cloud and image interactive masked autoencoders for 3d object detection","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.124979Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:1f5c18c7da8a68f8e4061fcc878d9ef2003b149a86c102a631ad58805bd1ca27","observation_id":"c6339b2f-c202-451d-982a-a98b1ec27a34","resolution":{"observed_at":"2026-08-05T12:47:49.124979Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T12:47:49.127983Z","title":"Pointgpt: Auto-regressively generative pre- training from point clouds","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.127983Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:f52a4a109273d16ac100ffa773d0ca8c9d0ce16c68c5c13db1880a80d27f604b","observation_id":"7c476c11-7684-4c0b-9446-c5ee6e21fd2f","resolution":{"observed_at":"2026-08-05T12:47:49.127983Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T12:47:49.131137Z","title":"A simple framework for contrastive learning of visual representations","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.131137Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:a9fc62db70a34d600bbb98dce3f4eeb31a803dc5ee3bf53683b0b22f4021e0d5","observation_id":"17a25566-91ec-4175-b058-f74146aeace3","resolution":{"observed_at":"2026-08-05T12:47:49.131137Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.08320","last_updated":"2023-02-02T07:26:26Z","snapshot_observed_at":"2026-08-04T11:34:39.486392Z","submitted_at":"2022-12-16T07:46:53Z","title":"Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.08320","snapshot_observed_at":"2026-08-05T12:47:49.134477Z","title":"Autoen- coders as cross-modal teachers: Can pretrained 2d image transformers help 3d representation learning? arXiv preprint arXiv:2212.08320, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.134477Z"},"links":{"cited_paper":"/paper/2212.08320","citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:2a6ab97a1207b2a574db52f15cc2dad7ff3904a85070c58b21a81172b7a748ac","observation_id":"0e5602c2-f5ed-4eb0-a700-b6332f490aeb","resolution":{"observed_at":"2026-08-05T12:47:49.134477Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T12:47:49.137935Z","title":"Self-contrastive learning with hard negative sampling for self-supervised point cloud learning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.137935Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:7811083d2a339a5c3070b933c48687d601ab729edbc1381790fc2f00cf3bb769","observation_id":"898a68f0-aa87-4912-a024-7957fade8327","resolution":{"observed_at":"2026-08-05T12:47:49.137935Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T12:47:49.140989Z","title":"A comparative review of hand-eye calibration tech- niques for vision guided robots","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.140989Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:39373bd2c17547ab2ce4e1abc32433435a27f5b0da969203710f7f2290c7b27a","observation_id":"f13b6045-a3c6-4cdd-b1b0-97b0ead96f69","resolution":{"observed_at":"2026-08-05T12:47:49.140989Z","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":"2026-08-05T12:47:50.235713Z","title":"Efficient image pre-training with siamese cropped masked autoencoders","venue":null,"work_id":"059ee848-bb48-4936-9928-4a2c85ee763b","year":2025},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.144535Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:5a401bfa4e387f75958fe2fa7927ad352f24292422247a68c08a1f197c12489e","observation_id":"84fefa2f-8c88-4327-85a4-e263c533a3eb","resolution":{"observed_at":"2026-08-05T12:47:50.239419Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-08-05T12:47:50.225311Z","title":"A point set generation network for 3d object reconstruction from a single image","venue":null,"work_id":"f01dd8df-861f-4f7c-a23d-8e5dc5c8c171","year":2017},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.147621Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:d46ccbebd43f0f13bc25cbecfe32a315f51c01c7dc13fccccfca365228034645","observation_id":"26bf6423-87c5-43e9-bb0d-410521f2fe04","resolution":{"observed_at":"2026-08-05T12:47:50.228815Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-08-05T12:47:50.213253Z","title":"Revisiting point cloud shape classification with a simple and effective baseline","venue":null,"work_id":"3d2610d6-bc1b-4c68-b02a-6f3c64704f78","year":2021},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.150376Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:98930d37cae7d1009a1d14b9b53e98097014f7687f1f46ea2c0cf65b2fcd92b9","observation_id":"a4bd87a9-5d50-4f04-9aa9-fe2cd5f94ba2","resolution":{"observed_at":"2026-08-05T12:47:50.216841Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-08-05T12:47:50.202827Z","title":"Bootstrap your own latent-a new approach to self-supervised learning","venue":null,"work_id":"6578137a-2555-48af-8735-66e70dc0312b","year":2020},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.153483Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:201eb85eca6bb39625dea940b952f53f3d599c088f52b0c04ef23ee6ddcbb1a7","observation_id":"cba94cf4-7f97-4012-8800-fb5e621f1da5","resolution":{"observed_at":"2026-08-05T12:47:50.205954Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-08-05T12:47:50.192180Z","title":"Pct: Point cloud transformer","venue":null,"work_id":"271c4925-c98e-4345-937e-600fcefed06e","year":2021},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.156143Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:e125b5bc0d4e5a4d8cfdbf4426e3aead268038852c4cc8065a919b370f28ce34","observation_id":"43235794-0c65-491d-85bf-2de93da9f69e","resolution":{"observed_at":"2026-08-05T12:47:50.195838Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2302.14007","last_updated":"2023-09-25T17:22:39Z","snapshot_observed_at":"2026-07-06T14:56:23.908982Z","submitted_at":"2023-02-27T17:56:18Z","title":"Joint-MAE: 2D-3D Joint Masked Autoencoders for 3D Point Cloud Pre-training","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.14007","snapshot_observed_at":"2026-08-05T12:47:49.159320Z","title":"Joint-mae: 2d-3d joint masked au- toencoders for 3d point cloud pre-training","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.159320Z"},"links":{"cited_paper":"/paper/2302.14007","citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:7e258b6cd397587c11b414cfd2f0865f5b609ce4a33db16b04b1485dc64fdd6a","observation_id":"b72c5d02-8db7-4219-a092-f0e4ea5d1041","resolution":{"observed_at":"2026-08-05T12:47:49.159320Z","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":"2026-08-05T12:47:50.180122Z","title":"Siamese masked autoencoders","venue":null,"work_id":"06326790-1502-4de4-827d-6532778bc6a1","year":2023},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.162600Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:ede49074d704a238ce8366d0d3accdf0ac7d5d78d005a8ff98f92d607a8a56a6","observation_id":"f45db9c2-4c5f-4aef-9536-14e73b4c4506","resolution":{"observed_at":"2026-08-05T12:47:50.184176Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-08-05T12:47:50.169843Z","title":"Dynamic focus-aware po- sitional queries for semantic segmentation","venue":null,"work_id":"27b97f83-21c0-4ac0-af94-fc8e8986013b","year":2023},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.165653Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:e35967b76f1ad72c1d44cbdfa9beae9bc213030c2668ab4938705a4b3135f8a4","observation_id":"2756ed16-fa1e-4e21-8f17-36b95e9149c6","resolution":{"observed_at":"2026-08-05T12:47:50.173771Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-08-05T12:47:49.168501Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.168501Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:9d6a9dda19db8279dabdb17d66bee298873378e731761efdeadc47964131841b","observation_id":"82b9c782-fce8-41de-8367-995cd5c0b5c3","resolution":{"observed_at":"2026-08-05T12:47:49.168501Z","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":"2026-08-05T12:47:50.153266Z","title":"Momentum contrast for unsupervised visual rep- resentation learning","venue":null,"work_id":"d676a8f9-56fe-4ba8-8452-cd29a0026445","year":2020},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.171111Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:247a4df5a27e9bda0862c80ebd60abd5159b9fb75a402fc27762b0a43610da55","observation_id":"da778ad9-923a-4763-a206-d66860a76f68","resolution":{"observed_at":"2026-08-05T12:47:50.156571Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-08-05T12:47:50.143223Z","title":"Masked autoencoders are scalable vision learners","venue":null,"work_id":"b2aba463-a4ea-4a2a-9ea7-7bee2cad5505","year":2022},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.173839Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:970e8111b7e7e30c717f3fbb9a89bc8e7202cb102082840f0c2d752daaf4c079","observation_id":"7594e3f2-5ce3-4e75-bc68-2fb9efe096d9","resolution":{"observed_at":"2026-08-05T12:47:50.146652Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1503.02531","last_updated":"2015-03-09T15:44:49Z","snapshot_observed_at":"2026-07-06T04:11:24.157003Z","submitted_at":"2015-03-09T15:44:49Z","title":"Distilling the Knowledge in a Neural Network","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1503.02531","snapshot_observed_at":"2026-08-05T12:47:49.176995Z","title":"Distill- ing the knowledge in a neural network","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.176995Z"},"links":{"cited_paper":"/paper/1503.02531","citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:6826a28d8ae892633f38241f6f2b6d2307092ae8114e3604d700c5e8922cce5e","observation_id":"faa462da-d904-4102-b25d-cddc70de5a39","resolution":{"observed_at":"2026-08-05T12:47:49.176995Z","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":"2026-08-05T12:47:50.132942Z","title":"Spatio-temporal self-supervised representation learning for 3d point clouds","venue":null,"work_id":"f060738c-9710-464c-87e8-80b49d557d67","year":null},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.180622Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:b99f05a3cf801edac56d349e5e1aaedad169f18c1c0a604ab66fecdbd0327706","observation_id":"a2330c0c-8782-4636-ab55-c8146e04be9d","resolution":{"observed_at":"2026-08-05T12:47:50.136623Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-08-05T12:47:50.122434Z","title":"Imagenet classification with deep convolutional neural net- works","venue":null,"work_id":"39f9e527-11a7-4d55-aa44-326c65326e23","year":2012},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.183683Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:a1519704b610d6c508485eb4deb6fa74cb7d2440686fca39e16f3396336b0695","observation_id":"6bb74de1-63b4-4793-93be-35526652b32e","resolution":{"observed_at":"2026-08-05T12:47:50.126141Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-08-05T12:47:50.111295Z","title":"Semmae: Semantic-guided mask- ing for learning masked autoencoders","venue":null,"work_id":"d1d06a2b-4770-4600-93b8-14f6fee91650","year":2022},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.187035Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:dd1398f9c5c9e95d35b02dc12c8e34147224b93baa4e1eabff57782d9a3105e7","observation_id":"be563703-c986-447e-a69c-28fe9b148e8b","resolution":{"observed_at":"2026-08-05T12:47:50.114737Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-08-05T12:47:50.099937Z","title":"So-net: Self- organizing network for point cloud analysis","venue":null,"work_id":"55ec2e54-d200-4777-b90b-c6ed5c296707","year":2018},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.190096Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:e9aede7be32e5818fe185dc9c7d9e77c6bfe00ce799fe090e496f8833b42e9aa","observation_id":"e9ec74c0-fed0-4b70-adb0-42489222ec9f","resolution":{"observed_at":"2026-08-05T12:47:50.103674Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.04891","last_updated":"2023-12-08T08:18:12Z","snapshot_observed_at":"2026-07-06T16:58:43.934362Z","submitted_at":"2023-12-08T08:18:12Z","title":"Cross-BERT for Point Cloud Pretraining","version":1},"cited_work":{"arxiv_id":"2312.04891","doi":null,"metadata_source":"pith","pith_arxiv_id":"2312.04891","snapshot_observed_at":"2026-08-05T12:47:49.523023Z","title":"Cross-BERT for Point Cloud Pretraining","venue":"cs.CV","work_id":"403ffd66-a7ad-454b-9bb2-f4175a469b04","year":2023},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.193094Z"},"links":{"cited_paper":"/paper/2312.04891","citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:4f3be8e3e26155a4ae5d5fd83bacf538cff3b91354d702a304fc0b06eb3953a0","observation_id":"c93d2045-868d-420a-baa7-af12ff775354","resolution":{"observed_at":"2026-08-05T12:47:49.526918Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-08-05T12:47:50.089250Z","title":"Pointcnn: Convolution on x-transformed points","venue":null,"work_id":"643b67fe-8fa2-4439-8854-8d58b4b07aaa","year":2018},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.196731Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:54c4d3653e36523186a1e936e373e6a331757665b882a16854f6547a9eb59214","observation_id":"2145ae06-fb4b-4dcd-933d-2809727d111b","resolution":{"observed_at":"2026-08-05T12:47:50.092791Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-08-05T12:47:50.077973Z","title":"Masked dis- crimination for self-supervised learning on point clouds","venue":null,"work_id":"77cc586b-c01b-4650-b225-5506ddbb5d5b","year":2022},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.199291Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:15496be73c553b604a4e5c7edfb63b8174652c25384655190efa6d4b9d33bbbb","observation_id":"19c73ca8-8d03-4c85-83eb-4830c34116d7","resolution":{"observed_at":"2026-08-05T12:47:50.081674Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-08-05T12:47:50.066662Z","title":"Relation-shape convolutional neural network for point cloud analysis","venue":null,"work_id":"c3a4b8e8-a522-4e62-9996-a6be0811a915","year":2019},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.202859Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:aa182c6c695fe74157b54a2a1e81fcee7e211434d9446e08b141feb46d26db76","observation_id":"31eec0ef-4362-4f89-b77b-13d169bd88dc","resolution":{"observed_at":"2026-08-05T12:47:50.070133Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-08-05T12:47:49.205598Z","title":"Swin transformer: Hierarchical vision transformer using shifted windows","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.205598Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:ce8b1e8deda5490cc3784f185ca51efb98756fbc495d1140727081de94b81379","observation_id":"59dbf3a2-6dbd-476a-95c6-8420fd2d593d","resolution":{"observed_at":"2026-08-05T12:47:49.205598Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1608.03983","last_updated":"2017-05-03T16:28:09Z","snapshot_observed_at":"2026-07-06T05:06:55.589962Z","submitted_at":"2016-08-13T13:46:05Z","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1608.03983","snapshot_observed_at":"2026-08-05T12:47:49.208825Z","title":"Sgdr: Stochas- tic gradient descent with warm restarts","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.208825Z"},"links":{"cited_paper":"/paper/1608.03983","citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:92bddc286cbef5c68347b865cac074c02a8b8df8d1ae4e390294ac2c388b7c4a","observation_id":"9631709a-df3f-4608-b0a4-36d2ae59da2b","resolution":{"observed_at":"2026-08-05T12:47:49.208825Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1711.05101","last_updated":"2019-01-04T21:01:49Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2017-11-14T14:24:06Z","title":"Decoupled Weight Decay Regularization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.05101","snapshot_observed_at":"2026-08-05T12:47:49.212353Z","title":"Decoupled weight decay regularization","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.212353Z"},"links":{"cited_paper":"/paper/1711.05101","citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:ed09c1659dc998c894d32432958d21ea43d65da1a5480cb50e4cd5020d5854a2","observation_id":"ed0c2f71-9698-4b6f-9762-110a585432ed","resolution":{"observed_at":"2026-08-05T12:47:49.212353Z","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":"2026-08-05T12:47:50.050474Z","title":"An end-to- end transformer model for 3d object detection","venue":null,"work_id":"bab9f089-c35b-4fa8-9f8c-47f336f05a21","year":2021},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.215216Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:09773d38d7e669fa140490d7c879fc1450876834099e987d1047d3abc6c5f920","observation_id":"9c0f79c8-76ec-42ac-8872-38b5e8b49829","resolution":{"observed_at":"2026-08-05T12:47:50.053702Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1807.03748","last_updated":"2019-01-22T18:47:12Z","snapshot_observed_at":"2026-07-06T06:49:24.960992Z","submitted_at":"2018-07-10T16:52:11Z","title":"Representation Learning with Contrastive Predictive Coding","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1807.03748","snapshot_observed_at":"2026-08-05T12:47:49.217844Z","title":"Repre- sentation learning with contrastive predictive coding","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.217844Z"},"links":{"cited_paper":"/paper/1807.03748","citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:e7dfcdd6572b3e0b9c2936da53f5558a8e9a5eb310939e02b4fe36f87ac85930","observation_id":"49df17f8-d96e-4563-9aff-992b14aa4f26","resolution":{"observed_at":"2026-08-05T12:47:49.217844Z","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":"2026-08-05T12:47:50.039724Z","title":"Unsupervised 3d point cloud representation learning by triangle constrained contrast for autonomous driving","venue":null,"work_id":"18a39bed-097b-41f6-bcd1-c0863db1de88","year":2023},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.221606Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:72bfa4df3a558b470b8554c8e5905c3bae004737d4e1393a81e8ba40eea7968e","observation_id":"efac4d11-f1c4-4a9e-b356-d5907dd193f1","resolution":{"observed_at":"2026-08-05T12:47:50.043208Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-08-05T12:47:50.029131Z","title":"Masked autoencoders for point cloud self-supervised learning","venue":null,"work_id":"8e3ea0da-c283-4f7b-80df-7e0a1f790fd5","year":2022},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.225042Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:0704d2ff50778e7ee85cad0e12f88a6135435e234d2952ce3945f2b89c3e06a8","observation_id":"7a845d17-170c-43d3-aa7f-71c99f31cf68","resolution":{"observed_at":"2026-08-05T12:47:50.032979Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-08-05T12:47:49.227782Z","title":"Pointnet: Deep learning on point sets for 3d classification and segmentation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.227782Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:602000882c34a168693debe6beba8f7f82118fe24fb0fa2c0bc2f4049fdb1d4c","observation_id":"fec18776-c6ad-4d5a-873d-3f43b2141c1c","resolution":{"observed_at":"2026-08-05T12:47:49.227782Z","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":"2026-08-05T12:47:50.011073Z","title":"Pointnet++: Deep hierarchical feature learning on point sets in a metric space","venue":null,"work_id":"24592c74-3eda-4727-b5be-97a4252a5418","year":2017},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.230635Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:e974eb7600012aef154dc10775dfc7350baf38c5160bbb8f4ceb384b2a0b360a","observation_id":"adc6f010-183f-4638-8a16-77fc7d487a4f","resolution":{"observed_at":"2026-08-05T12:47:50.014725Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-08-05T12:47:50.001134Z","title":"Deep hough voting for 3d object detection in point clouds","venue":null,"work_id":"b1a36595-35d3-499d-a4ca-3fd210fbcb07","year":2019},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.233229Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:dfc008b341955afb37c94444590de6bc55427ad6b8f897a216202c2c6d6f3737","observation_id":"55405bfa-c412-4e13-b782-563670ea218a","resolution":{"observed_at":"2026-08-05T12:47:50.004191Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2302.02318","last_updated":"2023-05-22T12:40:49Z","snapshot_observed_at":"2026-07-06T14:48:29.561857Z","submitted_at":"2023-02-05T06:58:35Z","title":"Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining","version":2},"cited_work":{"arxiv_id":"2302.02318","doi":null,"metadata_source":"pith","pith_arxiv_id":"2302.02318","snapshot_observed_at":"2026-08-05T12:47:49.473940Z","title":"Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining","venue":"cs.CV","work_id":"a6b10116-eeab-4b8c-a69c-6b4fff8a13e7","year":2023},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.237481Z"},"links":{"cited_paper":"/paper/2302.02318","citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:fed8a599b7154bc96c58dc67acd273b10372f4147868d11db56eb229f760bf0e","observation_id":"3f4149c6-e49a-4317-bdeb-a3942f517e48","resolution":{"observed_at":"2026-08-05T12:47:49.477455Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-08-05T12:47:49.989326Z","title":"3d object detection for autonomous driving: A survey","venue":null,"work_id":"55d00fc3-954b-42ce-87a5-449561f632a5","year":2022},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.241493Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:4a6a1d5b718c7a5750b379ab2e8adcac7a623e92e1f16bb437688253fc4ba422","observation_id":"15528bbb-25b7-44d7-b8dc-902f1ad940d5","resolution":{"observed_at":"2026-08-05T12:47:49.993034Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-08-05T12:47:49.977445Z","title":"Explore better relative position embeddings from encoding perspective for transformer models","venue":null,"work_id":"6886a2a8-877b-4bd1-97ed-133e452ca32d","year":2021},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.244735Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:3cbab7950d441cd801ad1458d1a770f9fc7419fe2d8bb33690c9c5ef2a945b26","observation_id":"86798c07-17d6-408c-9cd3-9c57f73bb7fb","resolution":{"observed_at":"2026-08-05T12:47:49.980824Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-08-05T12:47:49.967071Z","title":"Exploring the limits of transfer learning with a unified text-to-text transformer","venue":null,"work_id":"8593cb63-03ad-4cc9-be76-e4b606dc0659","year":2020},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.247567Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:0eace07c28a4106b02985f0fa0ba0c184c274119b1fd29498b4c463b3ae07aa6","observation_id":"8cd11169-72ad-42e6-b681-cbbbe34f4315","resolution":{"observed_at":"2026-08-05T12:47:49.970879Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-08-05T12:47:49.957179Z","title":"Info3d: Representation learning on 3d ob- jects using mutual information maximization and contrastive learning","venue":null,"work_id":"31edba11-8e23-4855-9ab2-a5363d5fd403","year":2020},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.250363Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:23a0549a70e58621db77177f689c0ab502bc4064acc89d70542633967380120b","observation_id":"b42cac55-0003-4592-a5ff-290f9fa2ef3b","resolution":{"observed_at":"2026-08-05T12:47:49.960490Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-08-05T12:47:49.946259Z","title":"3d optical machine vision sensors with intelligent data management for robotic swarm navigation improvement","venue":null,"work_id":"af5bafca-90c4-48f2-bb57-326e8626c369","year":2020},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.253437Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:8e7315c8dc09fb81338da237239df5e9fa79fe54c4e1d8daa7057699293daf6b","observation_id":"fb211cfa-fdaa-4e86-8cd5-e65de49ff8d2","resolution":{"observed_at":"2026-08-05T12:47:49.950224Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-08-05T12:47:49.936252Z","title":"Self-supervised few-shot learning on point clouds","venue":null,"work_id":"c8e5b672-4eca-4a90-bda2-7a4898dbe62c","year":2020},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.256187Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:8c440b32461ab00ec09581ca0966e69d84dfd05501393e80cca483eeb6cd0954","observation_id":"ac012760-3c9c-48d8-80ee-cbb505e7a4be","resolution":{"observed_at":"2026-08-05T12:47:49.939352Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1409.1556","last_updated":"2015-04-10T16:25:04Z","snapshot_observed_at":"2026-07-06T03:53:32.549552Z","submitted_at":"2014-09-04T19:48:04Z","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1409.1556","snapshot_observed_at":"2026-08-05T12:47:49.259313Z","title":"Very deep convo- lutional networks for large-scale image recognition","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.259313Z"},"links":{"cited_paper":"/paper/1409.1556","citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:d3989c2836484f8bccd85d59d7010c9f3b9796e9cd52c9feace80ca87784667d","observation_id":"a7df20d5-0a65-4b2e-9a91-f3783e2cce06","resolution":{"observed_at":"2026-08-05T12:47:49.259313Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T12:47:49.263744Z","title":"Roformer: Enhanced transformer with rotary position embedding","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.263744Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:df13000d3bb1b0d8f4ada7b8833414cc3fe445d0705ed6905ab374f098271a55","observation_id":"bcbc0289-f1d3-4cb9-b8f5-f2228c1a2c02","resolution":{"observed_at":"2026-08-05T12:47:49.263744Z","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":"2026-08-05T12:47:49.919188Z","title":"Proxy graph matching with proximal matching networks","venue":null,"work_id":"97642c85-246b-4a4c-9dc7-da591400db37","year":2021},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.267109Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:e04f52db377105d13050f7dcd18bb85175ba523a4dee563ab1d3e3a53c79b55d","observation_id":"f1b1d5ac-88d4-439c-b79f-98511a41937f","resolution":{"observed_at":"2026-08-05T12:47:49.922955Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-08-05T12:47:49.908535Z","title":"Data pruning via moving- one-sample-out","venue":null,"work_id":"5f8cbae7-1277-44aa-b3c6-9397810be208","year":2023},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.269795Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:d4898b4b156aba1a13c750cb421927d071cca1b2543783f0362b30c88157ef92","observation_id":"ed5001b4-2eb0-410c-b362-30b90e27cca3","resolution":{"observed_at":"2026-08-05T12:47:49.911950Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-08-05T12:47:49.897411Z","title":"Semantic diffusion network for semantic segmentation","venue":null,"work_id":"9fbd78ae-321b-4696-bee5-fa08566918ca","year":2023},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.272742Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:b53747f1c5825a093eff5bedcb869fbfff0932913699d43dd7a0cef0cc01eb3a","observation_id":"3d7781ea-7024-4eb1-9023-06d4aece3131","resolution":{"observed_at":"2026-08-05T12:47:49.900850Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-08-05T12:47:49.886432Z","title":"Ensemble quadratic assignment network for graph matching","venue":null,"work_id":"b8c07265-5a18-44e7-afa5-7b2a2e2dbf1f","year":2024},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.275591Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:e832ca7a767c635a64e56baf56ac5e5d84b0cc8bdf5ba16826739542437d2d95","observation_id":"30b902a1-4cee-4acd-bc03-f6fc8cf92196","resolution":{"observed_at":"2026-08-05T12:47:49.890031Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-08-05T12:47:49.876496Z","title":"Saco loss: Sample-wise affinity consistency for vision-language pre-training","venue":null,"work_id":"577c9dd6-d80c-4f23-9566-d397774410cf","year":2024},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.278175Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:30eaf729f03457d97278bcc43d4c84eccf710019eb2eb78ed8775fe8de1134d5","observation_id":"d7cb7884-fdad-44e8-aca6-234d027a7fb3","resolution":{"observed_at":"2026-08-05T12:47:49.879745Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-08-05T12:47:49.867631Z","title":"Data pruning by information maximization","venue":null,"work_id":"d06cdd55-2cba-4571-a9a3-7a5b75603dad","year":2025},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.281445Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:ad67da00f8b0f7a36ed4424bfb2bbaaf3ee6e5c1d2f314cdb7eaafea57c75dd3","observation_id":"14d8a9fa-8900-46f8-8961-4774e9325071","resolution":{"observed_at":"2026-08-05T12:47:49.870660Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-08-05T12:47:49.858535Z","title":"Diff-in: Data influence estimation with differential ap- proximation, 2025","venue":null,"work_id":"2b264cc4-efac-4872-b133-3e26e2d083ee","year":2025},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.284314Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:2bd6f9fcd2e08a24caf904c775c0cf9b15094f5fe6f772c8265a9a46e9a77492","observation_id":"afb518a5-2abc-4db5-9286-b7fd531bdde1","resolution":{"observed_at":"2026-08-05T12:47:49.861596Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-08-05T12:47:49.848839Z","title":"Revisiting point cloud classification: A new benchmark dataset and classification model on real-world data","venue":null,"work_id":"7ad346ef-21bf-4200-94cc-c7ae1d3b87b2","year":2019},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.287276Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:81ea8f9e60b34f9865ed0229a284fc36d78480b6a4d8b1cc0c131f9f13ab8f80","observation_id":"35b7bbb0-24af-4cb2-b85e-4fd84949db58","resolution":{"observed_at":"2026-08-05T12:47:49.852318Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-08-05T12:47:49.839483Z","title":"Attention is all you need","venue":null,"work_id":"1d9cde43-cbb3-4c04-8dcf-1102bf19180d","year":2017},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.290494Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:2f9c5b54fec5c132fa43e1296c8d6b3f684cf1f1cc41f5c63ccbe1302a7a003a","observation_id":"cb609340-1a9e-4652-bd40-fbfd17906020","resolution":{"observed_at":"2026-08-05T12:47:49.842722Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-08-05T12:47:49.829171Z","title":"Unsupervised point cloud pre-training via oc- clusion completion","venue":null,"work_id":"db41b358-34eb-4b68-a712-57fbb10c0aa6","year":null},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.297028Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:268875fe82977721b70260109370661a30a253bdb14f17049ea6e0d4a9fd9693","observation_id":"b664ac3d-eb0b-4922-aa3e-7f4d29dd7424","resolution":{"observed_at":"2026-08-05T12:47:49.832876Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-08-05T12:47:49.819530Z","title":"Dynamic graph cnn for learning on point clouds","venue":null,"work_id":"b0e488f3-4995-4f1b-86c7-4a1c240bdcd3","year":2019},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.300549Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:4bd45ea88584e72b34442b9cffb7d2c48b8b6b85657745f58a30193f66e2996c","observation_id":"f8be0a0d-96ea-45e0-a3f7-7c7ef0775f6b","resolution":{"observed_at":"2026-08-05T12:47:49.822944Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-08-05T12:47:49.809244Z","title":"Take-a-photo: 3d-to-2d generative pre-training of point cloud models","venue":null,"work_id":"8aa309dc-1fd5-48fc-98bd-82fa1501715e","year":null},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.303328Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:b09e1a6cd37f9d3eadce8a9bb69dbd69318d38d80d980ea49a3e9cef51a23c9b","observation_id":"99bed4fa-da7f-4875-a847-47b47b0e6876","resolution":{"observed_at":"2026-08-05T12:47:49.813244Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-08-05T12:47:49.800091Z","title":"Vertical layering of quantized neural networks for heterogeneous inference","venue":null,"work_id":"cf6bade4-0646-4432-bc56-406ce5d78d05","year":2023},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.306244Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:15bbc43363f56021c8887f4726d50c6dfa49c2e7b194a3097639921a2b69b613","observation_id":"8c626494-1fc4-440a-b8ba-2648ce5604e3","resolution":{"observed_at":"2026-08-05T12:47:49.803376Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-08-05T12:47:49.790783Z","title":"Rethinking and improving relative posi- tion encoding for vision transformer","venue":null,"work_id":"a22c03c2-961d-4138-b52b-dd7a63af654c","year":2021},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.309043Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:030d239b94c8502812786a4c6a68d1d827edff8798870c5e58a746a351867594","observation_id":"3bb22e89-44f9-40d6-add4-8759fee6660f","resolution":{"observed_at":"2026-08-05T12:47:49.794307Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-08-05T12:47:49.781598Z","title":"Mixture-of- scores: Robust image-text data quality score via three lines of code","venue":null,"work_id":"fd6ffc41-453a-4875-8bf6-61d11e34d671","year":2025},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.312916Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:4ced1646ce0e4ad95e6b7f10780ab13d1662d555bb7d459d345e45485a4e4eba","observation_id":"a1486870-9bbb-433f-9ce6-fac8021036c5","resolution":{"observed_at":"2026-08-05T12:47:49.784645Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.10035","last_updated":"2024-03-25T16:00:01Z","snapshot_observed_at":"2026-07-06T17:03:02.786273Z","submitted_at":"2023-12-15T18:59:59Z","title":"Point Transformer V3: Simpler, Faster, Stronger","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.10035","snapshot_observed_at":"2026-08-05T12:47:49.316035Z","title":"Point transformer v3: Simpler, faster, stronger","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.316035Z"},"links":{"cited_paper":"/paper/2312.10035","citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:c6ebed991ed90901921359ef26ee05003078c4d1e1ffa8a647fe0b6f0ddbf277","observation_id":"b7ef367f-f922-4f51-beaf-dda04db20d0c","resolution":{"observed_at":"2026-08-05T12:47:49.316035Z","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":"2026-08-05T12:47:49.772719Z","title":"3d shapenets: A deep representation for volumetric shapes","venue":null,"work_id":"fbec7c49-8064-432b-aa0c-41c76e834804","year":1912},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.319066Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:a236f647a113ee9fff465866c13d1413d6eb93659c3ebd8a0dcd3c47f01d6176","observation_id":"206aaf1b-5c44-4d92-92d1-0a812df08ffc","resolution":{"observed_at":"2026-08-05T12:47:49.775785Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-08-05T12:47:49.763680Z","title":"Pointcontrast: Unsupervised pre- training for 3d point cloud understanding","venue":null,"work_id":"bb080c62-5d2f-46e4-8a72-17dc48bcac7e","year":2020},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.321764Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:5da190882fe9340b296088b1d723839684b0582e4693cd8aceba0131cdd513fb","observation_id":"9063b207-b9e1-4a1a-84c1-b3ba51e8bd57","resolution":{"observed_at":"2026-08-05T12:47:49.766815Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-08-05T12:47:49.754180Z","title":"Simmim: A simple framework for masked image modeling","venue":null,"work_id":"fb50ca57-afa2-4e46-ab98-6563d7336994","year":2022},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.325735Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:65ac7642e967aced33d7b2338d3ce68051b8801c64511dd6aaa6059f27a5edf3","observation_id":"860e49f5-0ae2-447f-9e5b-4cf2fc185622","resolution":{"observed_at":"2026-08-05T12:47:49.757319Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-08-05T12:47:49.744513Z","title":"To- wards robustness and generalization of point cloud represen- tation: A geometry coding method and a large-scale object- level dataset","venue":null,"work_id":"b9a5490d-f40d-438b-af07-73d8f3c04dc6","year":null},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.328470Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:c90c494bcea8ebdefd4c36fae6119287adacfa6544cdaf4fc927bd20792fc5db","observation_id":"ba365d78-9476-4a0e-81b4-0bd4e4b8431d","resolution":{"observed_at":"2026-08-05T12:47:49.748125Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-08-05T12:47:49.733249Z","title":"Ulip: Learning a unified representation of language, images, and point clouds for 3d understanding","venue":null,"work_id":"8c17bc67-cb65-40ae-838d-5ec056c22ae6","year":2023},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.331339Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:b0dd5d8a021af87cbfe2f55d63923c35b7b7d19d0e67abc4582083eee70597f1","observation_id":"a0b0d257-6c26-4d47-af3e-518b63fa51fe","resolution":{"observed_at":"2026-08-05T12:47:49.736675Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1906.08237","last_updated":"2020-01-02T12:48:08Z","snapshot_observed_at":"2026-07-31T22:49:43.034741Z","submitted_at":"2019-06-19T17:35:48Z","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1906.08237","snapshot_observed_at":"2026-08-05T12:47:49.334133Z","title":"Xlnet: Generalized autoregressive pre- training for language understanding","venue":null,"work_id":null,"year":1906},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.334133Z"},"links":{"cited_paper":"/paper/1906.08237","citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:f5ce56dc2f7b7cc34bd6a9ba9a340d336d7a43dc749be51781d943fc92c7907b","observation_id":"30543d3e-263c-44c0-872d-45d8494fb173","resolution":{"observed_at":"2026-08-05T12:47:49.334133Z","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":"2026-08-05T12:47:49.722601Z","title":"A scalable active framework for region annotation in 3d shape collections.ACM Transactions on Graphics (ToG), 35(6):1–12, 2016","venue":null,"work_id":"940aec8e-9ff5-4d79-a5eb-db56d5188cb4","year":2016},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.337762Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:c41d151e352cc5b4633c1832e9e5c8a7d32c153c29c5efb8034a6344d978c542","observation_id":"1ee533b4-80b9-4798-b7fd-38757e6993b6","resolution":{"observed_at":"2026-08-05T12:47:49.726566Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-08-05T12:47:49.712617Z","title":"Point-bert: Pre-training 3d point cloud transformers with masked point modeling","venue":null,"work_id":"dfd04d98-ffd8-4e54-a186-20b3ebabc42b","year":2022},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.340718Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:da863a72c2f27a15142b3037b082b1d4481aa6f554d3d2fc00cd396367db301c","observation_id":"6a2ee9cf-6e62-4c22-b3ff-b885e6f883aa","resolution":{"observed_at":"2026-08-05T12:47:49.716338Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.10726","last_updated":"2023-12-17T14:17:05Z","snapshot_observed_at":"2026-07-06T17:04:13.625458Z","submitted_at":"2023-12-17T14:17:05Z","title":"Towards Compact 3D Representations via Point Feature Enhancement Masked Autoencoders","version":1},"cited_work":{"arxiv_id":"2312.10726","doi":null,"metadata_source":"pith","pith_arxiv_id":"2312.10726","snapshot_observed_at":"2026-08-05T12:47:49.425992Z","title":"Towards Compact 3D Representations via Point Feature Enhancement Masked Autoencoders","venue":"cs.CV","work_id":"53df6232-79e8-4b86-886a-9997592e42f2","year":2023},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.343900Z"},"links":{"cited_paper":"/paper/2312.10726","citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:ecd6f1735d1def856d58bd8e4ac4b671f66f264a4047d49f6a8a190334a02bb8","observation_id":"2595c51c-a99b-4e3d-bf4b-73029dff76cc","resolution":{"observed_at":"2026-08-05T12:47:49.431681Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-08-05T12:47:49.702557Z","title":"Point-m2ae: multi-scale masked autoencoders for hierarchical point cloud pre-training","venue":null,"work_id":"ea2238a1-192d-4267-8fbf-22a7c9fde585","year":2022},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.346697Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:084f4c45074c3f4c56fb6461df9a4856c7eca195512f186aa33ac32ca7866d63","observation_id":"9b8ec74b-7409-487e-978e-d11e8de860d5","resolution":{"observed_at":"2026-08-05T12:47:49.705795Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-08-05T12:47:49.692369Z","title":"Learning 3d representations from 2d pre-trained models via image-to-point masked autoencoders","venue":null,"work_id":"358e0885-c688-46e6-ab3b-cff6b6eca8a9","year":2023},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.349968Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:6efc95ec8c16c5307727dba9f03fd4b1c642a3a8fede6d979093d7c3560cdcb3","observation_id":"4524e096-a038-4d51-9e8a-92dfc4976691","resolution":{"observed_at":"2026-08-05T12:47:49.695648Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-08-05T12:47:49.682237Z","title":"Cr2pq: Continuous relative rotary positional query for dense visual representa- tion learning","venue":null,"work_id":"ec343de8-fe13-4a85-94dc-59ac4b36d1c2","year":null},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.352659Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:9cc1617a9e0eec46f8bd648fa4b87a7ab2177f7f470e91a47ffcd903a8f7615c","observation_id":"4154174c-8c55-49e1-8348-bd6aa751cbd3","resolution":{"observed_at":"2026-08-05T12:47:49.685433Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-08-05T12:47:49.671846Z","title":"The diversified ensemble neural network","venue":null,"work_id":"9c97669e-ff09-4f2e-9e14-300a0a122fb2","year":2020},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.355363Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:cb6eb9dbb854d4212cac3afab4a2a15515713afd24b210d9f46f2ab78beeb0d6","observation_id":"5e88c715-7a99-4c79-9b56-368cce011014","resolution":{"observed_at":"2026-08-05T12:47:49.675392Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-08-05T12:47:49.662063Z","title":"Zero-cl: Instance and feature decorrelation 16 for negative-free symmetric contrastive learning","venue":null,"work_id":"c5f48b6d-2268-4af4-a80c-88caf087e23b","year":2021},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.358272Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:25b3735a14109fa19bf22f01f82d182ae7665ae2c0f1f79138ec08e793dd3d5e","observation_id":"e0051746-8912-4623-bb44-bb6c841ea018","resolution":{"observed_at":"2026-08-05T12:47:49.665538Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-08-05T12:47:49.652106Z","title":"M-mix: Generating hard negatives via multi-sample mixing for con- trastive learning","venue":null,"work_id":"74a09bff-8acd-47d8-9227-dc70afaf146f","year":2022},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.360991Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:d0728236030a13bed4de59c31f130d861d204db6db59ed118bc709b7d785ed56","observation_id":"bca25c0d-202c-44df-b182-bcc97dc0baaf","resolution":{"observed_at":"2026-08-05T12:47:49.655379Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-08-05T12:47:49.641609Z","title":"Patch-level contrastive learning via positional query for visual pre-training","venue":null,"work_id":"8125a3b6-8249-467b-b983-7d177a6a199d","year":2023},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.364378Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:4e8bdc8e601aa2e4e5817c58ab75e21c951573e2c4b5309cde973efb792978a1","observation_id":"6c1a9e24-a097-441a-9d89-b8c579005fcc","resolution":{"observed_at":"2026-08-05T12:47:49.645507Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-08-05T12:47:49.630012Z","title":"Con- textual image masking modeling via synergized contrasting without view augmentation for faster and better visual pre- training","venue":null,"work_id":"679af6e9-7143-4338-ba04-ac19fcad520a","year":2023},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.367335Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:5953ed1824f4c6164bf20be3ccc8c488e3de0a5e1e7341c8368fb5ceb2ad67ea","observation_id":"9912eb8b-14cc-47b4-83b9-926b643677b5","resolution":{"observed_at":"2026-08-05T12:47:49.633263Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-08-05T12:47:49.619836Z","title":"Continuous-multiple image outpaint- ing in one-step via positional query and a diffusion-based approach","venue":null,"work_id":"532afcb4-a0be-4ea2-a090-28327ccd0939","year":2024},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.369989Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:d116d122b2c88e84f754056842e6880e8e372816df59dd6abdde364f082ba59c","observation_id":"e7040a5a-e971-40e9-b0b5-f49571ef5cf6","resolution":{"observed_at":"2026-08-05T12:47:49.623343Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-08-05T12:47:49.609679Z","title":"Pcp- mae: Learning to predict centers for point masked autoen- coders","venue":null,"work_id":"c5478a83-892d-47b8-811b-9dba8b0064c1","year":2024},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.372506Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:c25187e127558f8f2fd2f479a560a298e014de2ba82acae63b4641a77fcb28db","observation_id":"e23a0e07-4f84-4e6e-bfa6-141807de5f1f","resolution":{"observed_at":"2026-08-05T12:47:49.612833Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-08-05T12:47:49.599331Z","title":"Point cloud pre-training with diffusion models","venue":null,"work_id":"f159f8a1-d336-4465-bc8c-9739171afbc8","year":2024},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.375963Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:a1b954d8a9d6738f6fd825c2732c9f96155c6e2c5bb4a2cf797cfe45247849a8","observation_id":"f99f8211-f240-429d-a4a8-5f1c18ae884b","resolution":{"observed_at":"2026-08-05T12:47:49.603169Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2111.07832","last_updated":"2022-01-27T09:20:49Z","snapshot_observed_at":"2026-07-06T12:08:39.149450Z","submitted_at":"2021-11-15T15:18:05Z","title":"iBOT: Image BERT Pre-Training with Online Tokenizer","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.07832","snapshot_observed_at":"2026-08-05T12:47:49.379487Z","title":"ibot: Image bert pre-training with online tokenizer","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.379487Z"},"links":{"cited_paper":"/paper/2111.07832","citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:43a52d6e0ff62056b1a1341af4f9663772625e753eb4be25a20ae88e0648aaa7","observation_id":"e8b11c97-ea03-4233-86cd-b52c8e97b06f","resolution":{"observed_at":"2026-08-05T12:47:49.379487Z","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":"2026-08-05T12:47:49.588566Z","title":"V oxelnet: End-to-end learning for point cloud based 3d object detection","venue":null,"work_id":"cb4a2f25-6e48-40b7-bdc9-0bbb4e6d272a","year":2018},"citing_paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-05T12:47:49.382534Z"},"links":{"citing_paper":"/paper/2509.01250"},"observation_digest":"sha256:5d280a428e4dfd22a1d87947fa9121b627f9260b9159c00b76291ac71eb9430c","observation_id":"595700ee-69d9-457e-ad22-0393f621f740","resolution":{"observed_at":"2026-08-05T12:47:49.591852Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2509.01250","last_updated":"2025-09-01T08:42:17Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-05T12:47:48.308760Z","submitted_at":"2025-09-01T08:42:17Z","title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views"},"reference_resolution":{"displayed":89,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":25,"verified_exact":3,"verified_fuzzy":61},"total_outbound_references":89},"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":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"thesis":"As of 5 August 2026, this Paper Citation Record lists 89 of 89 outbound references and 0 inbound Pith citation observations for arXiv:2509.01250."}