{"as_of":"2026-08-20T02:40:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:21dc6863d3cf48565e42d095372d8c231ece21f06adeee3120c048a66cb0964e","coverage":[{"denominator":58,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":58,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-14T20:18:00.660828Z","state":"measured"},{"denominator":58,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":58,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-19T06:32:44.657259+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/2603.21511/citation-record","integrity":"/paper/2603.21511/integrity","json":"/paper/2603.21511/citation-record.json","paper":"/paper/2603.21511"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T20:18:00.660828Z","title":"Mvtec ad–a comprehensive real-world dataset for unsupervised anomaly detection","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:fbd8bf6aa195c73b8a61730559b39bbb51448fef22ee3b432d65e81d4440ee44","observation_id":"cf686681-4f8a-4b93-bfe4-874987b4895b","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","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":"2026-07-14T20:18:00.660828Z","title":"Comple- mentary pseudo multimodal feature for point cloud anomaly detection.Pattern Recognition, 156:110761, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:c7d07c3962afaf8ae3b6fdcc71a979eb243bd4870fdd0abbca094060fbbf8168","observation_id":"909684b9-7ceb-4cfa-85b0-effb9041d587","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","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":"2026-07-14T20:18:00.660828Z","title":"Adaclip: Adapting clip with hybrid learnable prompts for zero-shot anomaly de- tection","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:4fd26293a25b524547f8f63780b5df67b2bb92ea67a13e4568b7f6ff445de496","observation_id":"ec0c91dd-b51e-458c-b22c-e0ac4438353e","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","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":"2026-07-14T20:18:00.660828Z","title":"Personalizing vision- language models with hybrid prompts for zero-shot anomaly detection.IEEE Transactions on Cybernetics, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:a5abf3e65683e15eab3e41e045d306eeb043b5ca34c793db76a9e9973ae7f128","observation_id":"0a70c526-e37b-4055-8a80-3231df00d48a","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1512.03012","last_updated":"2015-12-09T19:42:48Z","snapshot_observed_at":"2026-08-15T22:26:43.274625Z","submitted_at":"2015-12-09T19:42:48Z","title":"ShapeNet: An Information-Rich 3D Model Repository","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1512.03012","snapshot_observed_at":"2026-07-14T20:18:00.660828Z","title":"Shapenet: An information-rich 3d model repository.arXiv preprint arXiv:1512.03012, 2015","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"cited_paper":"/paper/1512.03012","citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:1d300776d3c81ffd0e21bf3b27226c82d3dc18d493f3433b13a50d49b4540ec1","observation_id":"a6d47eae-2415-40ec-bf9a-312be01d03e7","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","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":"2026-07-14T20:18:00.660828Z","title":"Dis- tilled large language model-driven dynamic sparse expert ac- tivation mechanism.Applied Soft Computing, page 114037,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:144e643c7c720e6ad9fda111dea7eb4505db9a8c05a4eafc4aa31530fccf4213","observation_id":"3d55558e-c465-4755-aa18-3b607e2e0f99","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","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":"2026-07-14T20:18:00.660828Z","title":"Easynet: An easy net- work for 3d industrial anomaly detection","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:fdb216ec140b5fc4af93d769f261aa3e2573d35f100a8e069eec7cd39a227d29","observation_id":"b16ad88f-2334-4bed-85e2-ed91d97d5faa","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","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":"2026-07-14T20:18:00.660828Z","title":"Toward zero-shot point cloud anomaly de- tection: A multiview projection framework.IEEE Transac- tions on Systems, Man, and Cybernetics: Systems, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:9d164813b5ef328c8705516b5ec641226fe981403445fe5be8a4c2230360ed9d","observation_id":"7f2eb9c7-221d-4b47-bc33-e9faf836d6ef","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","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":"2026-07-14T20:18:00.660828Z","title":"Shape-guided dual-memory learning for 3d anomaly detection","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:00844a3b7ee20ca520d45fb3cb0c9133693f726f2e086a663da6940fd711d585","observation_id":"875d54a8-8da0-429c-be6f-e4b553f61119","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","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":"2026-07-14T20:18:00.660828Z","title":"3d scanning method for robotized inspection of industrial sealed parts","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:bbd92a72a3c8b535e6a8f8adf6c337cd3d891182af1e41fe8cab89af1c356435","observation_id":"ee4b5da7-3b1a-409b-a372-02e9334bd192","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","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":"2026-07-14T20:18:00.660828Z","title":"Bert: Pre-training of deep bidirectional trans- formers for language understanding","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:32379694cda4fa1bd2c1e3157a3ff12729da8a245be7da020b4835041c0c2108","observation_id":"0aee7024-dd3a-40a8-932d-481768a053a7","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","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":"2026-07-14T20:18:00.660828Z","title":"3d octave and 2d vanilla mixed convolutional neural network for hyperspectral image classification with limited samples.Remote Sensing, 13(21):4407, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:9b9187620a3e4cf2770ce7bf2222e541b9354782d3d3417e57251ef2444668e9","observation_id":"12e2a56d-5913-4db2-b332-a88dc4fd3def","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","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":"2026-07-14T20:18:00.660828Z","title":"A comprehensive performance evaluation of 3d local feature descriptors.Inter- national Journal of Computer Vision, 116(1):66–89, 2016","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:380a231c6b29b3827e9c9d5d573dbd33dae19903194f8af3ab1507a54ec03068","observation_id":"e6715ca1-36cd-483e-afb8-2cab7710273c","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","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":"2026-07-14T20:18:00.660828Z","title":"Deep learning for 3d point clouds: A survey.IEEE transactions on pattern analysis and machine intelligence, 43(12):4338–4364, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:89bdff27f6653d3224dbf8ce394d78a6735bb398075e87816ed5efbb6465fe96","observation_id":"413f7e75-4689-45bc-9257-2ddcf3444ca1","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","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":"2026-07-14T20:18:00.660828Z","title":"Back to the feature: clas- sical 3d features are (almost) all you need for 3d anomaly detection","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:aca04a26c86c17f47405e58116ad2899149940d236117002510c0a53938b94ac","observation_id":"e0c56bcd-1b5f-4c70-87ee-7129c53b7454","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","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":"2026-07-14T20:18:00.660828Z","title":"Research on product surface quality in- spection technology based on 3d point cloud.Advances in Mechanical Engineering, 15(3):16878132231159523, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:29a1de53b94b7554c9f11ab8b6b4f49fbd6b937fe710a095908c012d332f174f","observation_id":"2110e2b6-68ff-4157-92ee-40e4ff29a8bf","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","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":"2026-07-14T20:18:00.660828Z","title":"Winclip: Zero- /few-shot anomaly classification and segmentation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:6b931d1ab8123d2bd3ec7f28c4b7d8e570f3f421ed375414a72f959c88e468f5","observation_id":"ab33111a-31ad-4e19-88ba-a256588cc94b","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","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":"2026-07-14T20:18:00.660828Z","title":"Using spin images for efficient object recognition in cluttered 3d scenes.IEEE Transactions on pattern analysis and machine intelligence, 21(5):433–449, 2002","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:b631744bd2f4271f6730d5d3827bd2849365a39c5a01cfb46caeac56523076aa","observation_id":"068b2a46-220c-49b5-8ddb-8f099a777517","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","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":"2026-07-14T20:18:00.660828Z","title":"3dffl: privacy- preserving federated few-shot learning for 3d point clouds in autonomous vehicles.Scientific Reports, 14(1):19589, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:aa9c5b5c42b021335b3e017aae3554223145a341547a51c40b1c9f2ebed0ebe6","observation_id":"34aa7bd9-b403-4a0f-b983-dc917ef64771","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2509.10282","last_updated":"2025-09-12T14:21:54Z","snapshot_observed_at":"2026-08-16T15:17:20.306593Z","submitted_at":"2025-09-12T14:21:54Z","title":"MCL-AD: Multimodal Collaboration Learning for Zero-Shot 3D Anomaly Detection","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2509.10282","snapshot_observed_at":"2026-07-14T20:18:00.660828Z","title":"Mcl-ad: Multimodal collaboration learn- ing for zero-shot 3d anomaly detection.arXiv preprint arXiv:2509.10282, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"cited_paper":"/paper/2509.10282","citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:12089c4eb69eceb65b809f6e2bef221de7ff1f6b9dd60d289ffc44fc14a63075","observation_id":"4d9ff513-1d48-4726-b082-38d16a9bb025","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","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":"2026-07-14T20:18:00.660828Z","title":"Towards scalable 3d anomaly detection and localization: A benchmark via 3d anomaly synthesis and a self-supervised learning network","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:08d57c67e7f56b16b5db91b461b374f12245b459cf02845e8cdd373e2764b9c0","observation_id":"4fb3b928-2fbe-404f-b3c7-8b87f1206477","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","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":"2026-07-14T20:18:00.660828Z","title":"Multi-sensor object anomaly detection: Unifying appearance, geometry, and internal properties","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:1132161ed0313238bec00a42a656b7f05f6c49b56724768c6243b2e8174c4761","observation_id":"9de10be0-2558-4ffa-a857-dab37e72142a","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","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":"2026-07-14T20:18:00.660828Z","title":"Real3d- ad: A dataset of point cloud anomaly detection.Advances in Neural Information Processing Systems, 36:30402–30415,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:2b61816a83dc4b221304363f46f7df7e0bc64dcbe998f72de372cf16ed998846","observation_id":"d9d2f3d7-255d-4c6a-8344-ff9986e249f6","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","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":"2026-07-14T20:18:00.660828Z","title":"Openshape: Scaling up 3d shape representation towards open-world understanding.Advances in neural information processing systems, 36:44860–44879, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:e7daee4c43c1b359de923e71df6357f24750a54b3b1d54bc07917937ffa9954b","observation_id":"517d3d8d-59c4-425c-ab0d-e20aeb09cc8d","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","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":"2026-07-14T20:18:00.660828Z","title":"Data-driven many-objective crowd worker selection for mobile crowdsourcing in indus- trial iot.IEEE Transactions on Industrial Informatics, 19(1): 531–540, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:e76978d2eb45774d657325b3cb43f84f320caf992a413cda5e7c5b103bb9737f","observation_id":"66c4987f-1643-4335-9dfd-a41a3a00377b","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","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":"2026-07-14T20:18:00.660828Z","title":"One-for-all few- shot anomaly detection via instance-induced prompt learn- ing","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:701cce64d4cd03c4247c1752b107fba83164cef2ecab6709546a7323c9793055","observation_id":"81c55119-773d-4622-8556-a32eff4959cc","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","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":"2026-07-14T20:18:00.660828Z","title":"Aa-clip: Enhancing zero-shot anomaly detection via anomaly-aware clip","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:f4291909bfe1683523934c8b7b9d10b3ded501eb073dbc7b9920f78519686db7","observation_id":"bc2acd62-71c7-46bf-ab73-6f6235d95472","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","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":"2026-07-14T20:18:00.660828Z","title":"Beyond single-modal boundary: Cross-modal anomaly detection through visual prototype and harmoniza- tion","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:46ced25e96d48ce0a07e41353529806a894d7e372563f390a2bbb80d4dfd783d","observation_id":"fe7b5869-c30f-446e-8d46-a6858f2983ee","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","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":"2026-07-14T20:18:00.660828Z","title":"Delving into out-of-distribution detection with vision-language representations","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:c9a863c67984fb475632e8ee1d24d2a2ddb5d890d2bc0805192d19bebc8a64bc","observation_id":"fa297450-a4b7-4ec7-ab79-482e8b21fa3b","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","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":"2026-07-14T20:18:00.660828Z","title":"Pointnet: Deep learning on point sets for 3d classification and segmentation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:255d7d26b7cdf4709b55c26ac6e1aba3f742f8e91567a0f2c30e62d3429f4cbd","observation_id":"9a39ad22-fab7-4cf7-a552-fd7c9f2e6e29","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","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":"2026-07-14T20:18:00.660828Z","title":"Pointnet++: Deep hierarchical feature learning on point sets in a metric space.Advances in neural information processing systems, 30, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:f5b03ab6c2b9cdb376b60098ab82407a6678c3a54df46e176aa2861387f15244","observation_id":"2125f10b-f34c-4e33-bc82-dd974ff15e67","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","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":"2026-07-14T20:18:00.660828Z","title":"Bayesian prompt flow learning for zero-shot anomaly detec- tion","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:d410a527838e8710ebabb4de74904bdcfc280adf8aff4dfdeca0acbf3cef75e6","observation_id":"e1e494b8-72e9-4eb8-abd6-3159e0445ecd","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","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":"2026-07-14T20:18:00.660828Z","title":"Learning transferable visual models from natural language supervi- sion","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:94e42106b3c15d6a6879239561bce851307ea9aa7523da78574ad2f316259af8","observation_id":"7f8ba2e6-34d3-413d-888f-78cdaa6cb83d","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","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":"2026-07-14T20:18:00.660828Z","title":"Towards to- tal recall in industrial anomaly detection","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:e817e4dcd3643c86c41c7fdca7cde6c9cb96e26b465ca9af69396af608cda12d","observation_id":"2de2dd21-c663-44d3-ac3f-324190ca7c31","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","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":"2026-07-14T20:18:00.660828Z","title":"Fast point feature histograms (fpfh) for 3d registration","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:63609773730bf31a44b400212510a88797e5c4bdbe203d2f3071e6389a9bb614","observation_id":"4fbf8e3a-c852-4709-aa9b-1ca02bf5641b","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","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":"2026-07-14T20:18:00.660828Z","title":"Shot: Unique signatures of histograms for surface and tex- ture description.Computer vision and image understanding, 125:251–264, 2014","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:f53b197d8f469da74f1df3167c53cb924ce8a38a96c711bdd3e68afb4c04da4a","observation_id":"a1141ae0-d2bb-4dc1-8ee6-e55a57b761f4","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","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":"2026-07-14T20:18:00.660828Z","title":"Attention is all you need.Advances in neural information processing systems, 30, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:e843487b4e73afd800a05e000be1a6f884ecb215a9230d6ca799503bf7b47c39","observation_id":"b418099e-9dcb-4fa2-9cb6-1a47ecbc7391","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","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":"2026-07-14T20:18:00.660828Z","title":"Exploiting point- language models with dual-prompts for 3d anomaly detec- tion.Expert Systems with Applications, page 129758, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:2aee11bb1a764f244e10f71fb0417031b9e8cbd14a49bbda55c0c8633443b836","observation_id":"0b14dfcd-5e65-45fe-8ed4-6d29864813d8","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","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":"2026-07-14T20:18:00.660828Z","title":"Toward ac- curate anomaly detection in industrial internet of things us- ing hierarchical federated learning.IEEE Internet of Things Journal, 9(10):7110–7119, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:4c886afeb2a9590c1bc6132c61afa6b5d4cb4d2af32c01b147392413f0b79b0b","observation_id":"de073976-c2bc-4282-b5be-d94855cafe35","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","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":"2026-07-14T20:18:00.660828Z","title":"Dynamic graph cnn for learning on point clouds.ACM Transactions on Graphics (tog), 38(5):1–12, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:01c85af5db9636e783c9dc98fa936e2f41cc6f39a0287ecaf4ba23d81097f2fa","observation_id":"a184a7e2-deb1-4846-8f98-9db4b420582f","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","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":"2026-07-14T20:18:00.660828Z","title":"Multimodal industrial anomaly detection via hybrid fusion","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:b2543d911dda7961a808755d812df92bbbd62cda2ca88a384c4954d8f26812b3","observation_id":"a9d254ee-b9c4-4e09-9d43-e3a8db003be5","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","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":"2026-07-14T20:18:00.660828Z","title":"Multi- space crowd sensing task allocation: A dynamic co- optimization framework with fairness-aware reinforcement learning.IEEE Transactions on Mobile Computing, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:124aa43c36b09ae30e6118643ab60fdc4e50db182c75d04970a3fd2ee0f84f3e","observation_id":"19c4a496-96f1-40f2-bb3f-b9a1786cf797","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","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":"2026-07-14T20:18:00.660828Z","title":"Towards zero-shot 3d anomaly localization","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:8c89e569beb4b6c6cce4fa289c09ce3b56aa39526099983d80c3c3c574e566c0","observation_id":"130b6ae0-b3aa-4350-80d8-e3069722bf55","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","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":"2026-07-14T20:18:00.660828Z","title":"Towards zero-shot anomaly detection and reasoning with multimodal large language models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:efc79af95f540a1f04db813280a80969b878e167b2a61f56a785a43d766cd3a0","observation_id":"b214b605-51c6-4459-9fc9-62b65a334f74","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","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":"2026-07-14T20:18:00.660828Z","title":"Ulip: Learning a unified representation of language, images, and point clouds for 3d understanding","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:9309e42092561a47c1445fac96140bcbd16c53021fe604de309ce868c23cb9c3","observation_id":"fdb4e8a6-0ad1-4feb-9a6f-7ca6678e61cd","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","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":"2026-07-14T20:18:00.660828Z","title":"Ulip-2: Towards scalable multimodal pre-training for 3d understanding","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:a1ff2b32adaf4a34d67aeb6d877c408881c6de0cc151b1c0fdaa8b7b935dbe80","observation_id":"6a4eac6b-52bd-41b1-8bfa-263a45590094","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","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":"2026-07-14T20:18:00.660828Z","title":"Po3ad: Predicting point offsets toward bet- ter 3d point cloud anomaly detection","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:0da2ad3bd2e8eaa765cc2039ac91624bfea0bf39a5ce6eb4f7dd4ec0ad565731","observation_id":"f4278576-dd08-4cf4-aaec-dc6a968b95af","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","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":"2026-07-14T20:18:00.660828Z","title":"A unified model for multi-class anomaly detection.Advances in Neural Information Pro- cessing Systems, 35:4571–4584, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:1bde1cffb18fc481ee19c871397384546cbd3a4c3302801d877ad80a1d0c4cdd","observation_id":"67bff8b4-51c8-4f31-a25e-7e5af2972a52","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","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":"2026-07-14T20:18:00.660828Z","title":"Point-bert: Pre-training 3d point cloud transformers with masked point modeling","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:e94546dd97f69e0c06edf29eb0d48de0801a0a3b5b86ba4f737cefa3509f6664","observation_id":"05c706a0-573e-4229-90ff-fd54367021fc","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","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":"2026-07-14T20:18:00.660828Z","title":"Zero-shot learning in industrial scenarios: New large-scale benchmark, challenges and baseline","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:4da12c08d81731a12b6b56ebeead6d13a94b1142d3354ae3b80be8f92e0f522e","observation_id":"64a66929-2015-490d-8805-31c8965a021c","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","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":"2026-07-14T20:18:00.660828Z","title":"Pointcore: An efficient framework for unsupervised point cloud anomaly detection using joint local-global features","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:404e167368109f1edb069b894db4188ea81b08538c40e83c07599b67fef57512","observation_id":"17f3f115-8d1e-4744-bd06-a47ca814a52a","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","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":"2026-07-14T20:18:00.660828Z","title":"AnomalyCLIP: Object-agnostic prompt learning for zero-shot anomaly detection","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:fc773e2422478f55970ac667c2810eb816a585d28552fa3e6f3c83ac5cfab48d","observation_id":"9cd8e2ab-0de8-4e73-ae2c-8d559e50c7d9","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","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":"2026-07-14T20:18:00.660828Z","title":"Pointad: Comprehending 3d anomalies from points and pixels for zero-shot 3d anomaly detection","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:846220b0adacf7b17ed1d9f0db8d638a4f4afb89894fe5399a4648f2e54f3f46","observation_id":"dbec7800-93cd-40ba-9740-bebac2e8f769","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","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":"2026-07-14T20:18:00.660828Z","title":"A novel ground- based cloud image segmentation method by using deep trans- fer learning.IEEE Geoscience and Remote Sensing Letters, 19:1–5, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:e7a4c25216b61195662f59eba5dc03892e226933bf698a8cc4382f5b9ef0366c","observation_id":"2596106a-8f73-48aa-b863-3ce7320bdea6","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","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":"2026-07-14T20:18:00.660828Z","title":"R3d-ad: Reconstruction via diffu- sion for 3d anomaly detection","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:9dbe1a429912df74079fd715a9cff33697ae513e0321b79c273006d0a5c3cd15","observation_id":"138b7ec0-943f-4931-a679-b0ea2bfb2c90","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","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":"2026-07-14T20:18:00.660828Z","title":"Multi-granularity episodic contrastive learning for few-shot learning.Pattern Recognition, 131:108820, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:86cef87fd2775de02032ee94784012435c9dc03c74d6f79ca8f83fcf960d4bdc","observation_id":"796eabe6-df6a-4e5c-be10-1211f447adfc","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","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":"2026-07-14T20:18:00.660828Z","title":"Real-iad d3: A real-world 2d/pseudo-3d/3d dataset for industrial anomaly detection","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:f7981c699b109338d5faf8e165bcef6beb7af30807ed1520dd71b16f883a3b58","observation_id":"b3ad51e8-cdd5-48be-9d71-a16c747e3f3d","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","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":"2026-07-14T20:18:00.660828Z","title":"Point- clip v2: Prompting clip and gpt for powerful 3d open-world learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","version":3},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-07-14T20:18:00.660828Z"},"links":{"citing_paper":"/paper/2603.21511"},"observation_digest":"sha256:ee1a8702922521e1fe11de1b1d24ed6ab54dada8e16cf9b8c8777a7b43ec5b8f","observation_id":"ee754bc1-8f8d-458f-b36f-07c2618b1166","resolution":{"observed_at":"2026-07-14T20:18:00.660828Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2603.21511","last_updated":"2026-07-12T08:51:47Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-16T15:17:13.501092Z","submitted_at":"2026-03-23T02:59:00Z","title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection"},"reference_resolution":{"displayed":58,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":58,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":58},"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":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 20 August 2026, this Paper Citation Record lists 58 of 58 outbound references and 0 inbound Pith citation observations for arXiv:2603.21511."}