{"as_of":"2026-08-09T22:07:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3932da2db381ff44221488c441dd5d84ed76797c96359f698a81e3bd65746974","coverage":[{"denominator":38,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":38,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-02T11:05:28.776717Z","state":"measured"},{"denominator":38,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":38,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+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/2607.13046/citation-record","integrity":"/paper/2607.13046/integrity","json":"/paper/2607.13046/citation-record.json","paper":"/paper/2607.13046"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T11:05:24.860059Z","title":"Quantum machine learning.Nature, 549(7671):195–202, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.13046","last_updated":"2026-06-17T01:03:26Z","snapshot_observed_at":"2026-08-09T00:22:51.619840Z","submitted_at":"2026-06-17T01:03:26Z","title":"What Your Model Threw Away and Why You'll Want It Back: Masking, Fingerprinting, and Privacy from Discarded Geometry","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-02T11:05:24.860059Z"},"links":{"citing_paper":"/paper/2607.13046"},"observation_digest":"sha256:fe9bc4d0a145d8cdd91f65b3ba5b40dcf9dd08c3548a645a8c6f79cbdcd10ae9","observation_id":"e9f31f08-a145-4f20-82ba-2f57fde1a9d8","resolution":{"observed_at":"2026-08-02T11:05:24.860059Z","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":"2026-08-02T11:05:24.926729Z","title":"Practical secure aggregation for privacy-preserving machine learning","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.13046","last_updated":"2026-06-17T01:03:26Z","snapshot_observed_at":"2026-08-09T00:22:51.619840Z","submitted_at":"2026-06-17T01:03:26Z","title":"What Your Model Threw Away and Why You'll Want It Back: Masking, Fingerprinting, and Privacy from Discarded Geometry","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-02T11:05:24.926729Z"},"links":{"citing_paper":"/paper/2607.13046"},"observation_digest":"sha256:5233a99863f5da2a8d4c375947f9b24dfa701fc6601aedb275598801e1463bcd","observation_id":"c2a2ebe8-73cd-4197-b99e-0d59ac194ff6","resolution":{"observed_at":"2026-08-02T11:05:24.926729Z","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":"2026-08-02T11:05:24.994177Z","title":"Sampling using su (n) gauge equivariant flows.Physical Review D, 103(7):074504, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.13046","last_updated":"2026-06-17T01:03:26Z","snapshot_observed_at":"2026-08-09T00:22:51.619840Z","submitted_at":"2026-06-17T01:03:26Z","title":"What Your Model Threw Away and Why You'll Want It Back: Masking, Fingerprinting, and Privacy from Discarded Geometry","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-02T11:05:24.994177Z"},"links":{"citing_paper":"/paper/2607.13046"},"observation_digest":"sha256:39f86e633adc21b0210d962c6a65fc44b920db43ec473b0c407a04a07cdb9d1c","observation_id":"6a5fcf4d-e3a8-4117-98b4-a338fab7a799","resolution":{"observed_at":"2026-08-02T11:05:24.994177Z","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":"2026-08-02T11:05:25.123071Z","title":"Learning equivariant maps with variational quantum circuits.Physical Review Applied, 23(4):044007, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.13046","last_updated":"2026-06-17T01:03:26Z","snapshot_observed_at":"2026-08-09T00:22:51.619840Z","submitted_at":"2026-06-17T01:03:26Z","title":"What Your Model Threw Away and Why You'll Want It Back: Masking, Fingerprinting, and Privacy from Discarded Geometry","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-02T11:05:25.123071Z"},"links":{"citing_paper":"/paper/2607.13046"},"observation_digest":"sha256:9eeabad881b8ffee040e21661c1cc8be93ac5e19263387ceb8f03887364bbcb3","observation_id":"db90ce56-9534-45ea-8110-eba1fa10d9d6","resolution":{"observed_at":"2026-08-02T11:05:25.123071Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.13478","last_updated":"2021-05-02T16:16:03Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2021-04-27T21:09:51Z","title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.13478","snapshot_observed_at":"2026-08-02T11:05:25.239797Z","title":"Geometric deep learning: Grids, groups, graphs, geodesics, and gauges.arXiv preprint arXiv:2104.13478, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.13046","last_updated":"2026-06-17T01:03:26Z","snapshot_observed_at":"2026-08-09T00:22:51.619840Z","submitted_at":"2026-06-17T01:03:26Z","title":"What Your Model Threw Away and Why You'll Want It Back: Masking, Fingerprinting, and Privacy from Discarded Geometry","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-02T11:05:25.239797Z"},"links":{"cited_paper":"/paper/2104.13478","citing_paper":"/paper/2607.13046"},"observation_digest":"sha256:02d8b8384ce50056a5021b6b34528c8b7e4f3ed502fd7a98e589ad1b75769be2","observation_id":"ff529882-05c2-464a-85b3-262664e10e35","resolution":{"observed_at":"2026-08-02T11:05:25.239797Z","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":"2026-08-02T11:05:25.365756Z","title":"Geometric deep learning: going beyond euclidean data.IEEE Signal Processing Magazine, 34(4):18–42, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.13046","last_updated":"2026-06-17T01:03:26Z","snapshot_observed_at":"2026-08-09T00:22:51.619840Z","submitted_at":"2026-06-17T01:03:26Z","title":"What Your Model Threw Away and Why You'll Want It Back: Masking, Fingerprinting, and Privacy from Discarded Geometry","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-02T11:05:25.365756Z"},"links":{"citing_paper":"/paper/2607.13046"},"observation_digest":"sha256:a5f60f4a672547e29e5ff444b00fffb234b16ebc7727a1636094d39c8ec6c1f0","observation_id":"dd076e63-c78a-4317-a538-18dd28c01dd8","resolution":{"observed_at":"2026-08-02T11:05:25.365756Z","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":"2026-08-02T11:05:25.452668Z","title":"Ipguard: Protecting intellectual property of deep neural networks via fingerprinting the classification boundary","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.13046","last_updated":"2026-06-17T01:03:26Z","snapshot_observed_at":"2026-08-09T00:22:51.619840Z","submitted_at":"2026-06-17T01:03:26Z","title":"What Your Model Threw Away and Why You'll Want It Back: Masking, Fingerprinting, and Privacy from Discarded Geometry","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-02T11:05:25.452668Z"},"links":{"citing_paper":"/paper/2607.13046"},"observation_digest":"sha256:c411799a74b52f799f0c1e7f2af2debbfa18c980cd6ea8640d212100a00f946f","observation_id":"8f5dfb92-c162-4120-a9b6-43a7b4e3e9a7","resolution":{"observed_at":"2026-08-02T11:05:25.452668Z","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":"2026-08-02T11:05:25.596402Z","title":"Variational quan- tum algorithms.Nature Reviews Physics, 3(9):625–644, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.13046","last_updated":"2026-06-17T01:03:26Z","snapshot_observed_at":"2026-08-09T00:22:51.619840Z","submitted_at":"2026-06-17T01:03:26Z","title":"What Your Model Threw Away and Why You'll Want It Back: Masking, Fingerprinting, and Privacy from Discarded Geometry","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-02T11:05:25.596402Z"},"links":{"citing_paper":"/paper/2607.13046"},"observation_digest":"sha256:8adf2da07ae891c7b9b5af038ab702c5262121d3a0d3e72d7632c5c29a1cf297","observation_id":"21f6c747-46d2-487d-bdd0-3430a9349459","resolution":{"observed_at":"2026-08-02T11:05:25.596402Z","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":"2026-08-02T11:05:25.745747Z","title":"Digital image steganog- raphy: Survey and analysis of current methods.Signal processing, 90(3):727–752, 2010","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2607.13046","last_updated":"2026-06-17T01:03:26Z","snapshot_observed_at":"2026-08-09T00:22:51.619840Z","submitted_at":"2026-06-17T01:03:26Z","title":"What Your Model Threw Away and Why You'll Want It Back: Masking, Fingerprinting, and Privacy from Discarded Geometry","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-02T11:05:25.745747Z"},"links":{"citing_paper":"/paper/2607.13046"},"observation_digest":"sha256:e724141a671c36f12297b15e37b1c0e6efef3c1ebed6184ab66df587e92b96d9","observation_id":"f1224535-846a-46ec-a9c9-906397868f0b","resolution":{"observed_at":"2026-08-02T11:05:25.745747Z","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":"2026-08-02T11:05:25.906500Z","title":"Group equivariant convolutional networks","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.13046","last_updated":"2026-06-17T01:03:26Z","snapshot_observed_at":"2026-08-09T00:22:51.619840Z","submitted_at":"2026-06-17T01:03:26Z","title":"What Your Model Threw Away and Why You'll Want It Back: Masking, Fingerprinting, and Privacy from Discarded Geometry","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-02T11:05:25.906500Z"},"links":{"citing_paper":"/paper/2607.13046"},"observation_digest":"sha256:715fe41dd4ec5877b8e9d55027181d8c400e86738cdff67884ced71b531a35b0","observation_id":"e722528f-0db3-4fe5-8e89-7fd5a7eb4624","resolution":{"observed_at":"2026-08-02T11:05:25.906500Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1801.10130","last_updated":"2018-02-25T13:43:49Z","snapshot_observed_at":"2026-07-06T06:20:59.047515Z","submitted_at":"2018-01-30T18:28:30Z","title":"Spherical CNNs","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1801.10130","snapshot_observed_at":"2026-08-02T11:05:26.061702Z","title":"Spherical cnns.arXiv preprint arXiv:1801.10130, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.13046","last_updated":"2026-06-17T01:03:26Z","snapshot_observed_at":"2026-08-09T00:22:51.619840Z","submitted_at":"2026-06-17T01:03:26Z","title":"What Your Model Threw Away and Why You'll Want It Back: Masking, Fingerprinting, and Privacy from Discarded Geometry","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-02T11:05:26.061702Z"},"links":{"cited_paper":"/paper/1801.10130","citing_paper":"/paper/2607.13046"},"observation_digest":"sha256:8babeb28ca1ec165a23ebcf62fae2c989225394a8b712bc34c527959386e9455","observation_id":"c572d949-bb71-4e6c-a88d-8fbcb32444ca","resolution":{"observed_at":"2026-08-02T11:05:26.061702Z","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":"2026-08-02T11:05:26.184283Z","title":"University of Florida, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.13046","last_updated":"2026-06-17T01:03:26Z","snapshot_observed_at":"2026-08-09T00:22:51.619840Z","submitted_at":"2026-06-17T01:03:26Z","title":"What Your Model Threw Away and Why You'll Want It Back: Masking, Fingerprinting, and Privacy from Discarded Geometry","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-02T11:05:26.184283Z"},"links":{"citing_paper":"/paper/2607.13046"},"observation_digest":"sha256:bf831aa90de66d18c6696f3f4bda93c524337156771890a3c3b80c55cac7a20c","observation_id":"cea406e8-de01-4e73-bb3b-d87e630d10e5","resolution":{"observed_at":"2026-08-02T11:05:26.184283Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2007.01263","last_updated":"2020-07-02T17:17:21Z","snapshot_observed_at":"2026-08-08T10:40:46.013623Z","submitted_at":"2020-07-02T17:17:21Z","title":"Outlier Detection through Null Space Analysis of Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2007.01263","snapshot_observed_at":"2026-08-02T11:05:26.290973Z","title":"Outlier detection through null space analysis of neural networks.arXiv preprint arXiv:2007.01263, 2020","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2607.13046","last_updated":"2026-06-17T01:03:26Z","snapshot_observed_at":"2026-08-09T00:22:51.619840Z","submitted_at":"2026-06-17T01:03:26Z","title":"What Your Model Threw Away and Why You'll Want It Back: Masking, Fingerprinting, and Privacy from Discarded Geometry","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-02T11:05:26.290973Z"},"links":{"cited_paper":"/paper/2007.01263","citing_paper":"/paper/2607.13046"},"observation_digest":"sha256:6f019d774aea9ff6d6af9d8d2bd48c33a17177f617876605d27bf7876ac1fe0e","observation_id":"8973c483-cdf8-40c9-901e-79a11f473b6f","resolution":{"observed_at":"2026-08-02T11:05:26.290973Z","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":"2026-08-02T11:05:26.348423Z","title":"Differential privacy: A survey of results","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2607.13046","last_updated":"2026-06-17T01:03:26Z","snapshot_observed_at":"2026-08-09T00:22:51.619840Z","submitted_at":"2026-06-17T01:03:26Z","title":"What Your Model Threw Away and Why You'll Want It Back: Masking, Fingerprinting, and Privacy from Discarded Geometry","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-02T11:05:26.348423Z"},"links":{"citing_paper":"/paper/2607.13046"},"observation_digest":"sha256:1e03eb194ece9b0bfffa1a8269fa0a453c46f665cfb9248b8abb81bda6a42d39","observation_id":"72481f01-7974-474d-bea8-fdae1c3a216c","resolution":{"observed_at":"2026-08-02T11:05:26.348423Z","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":"2026-08-02T11:05:26.424552Z","title":"Calibrating noise to sensi- tivity in private data analysis","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2607.13046","last_updated":"2026-06-17T01:03:26Z","snapshot_observed_at":"2026-08-09T00:22:51.619840Z","submitted_at":"2026-06-17T01:03:26Z","title":"What Your Model Threw Away and Why You'll Want It Back: Masking, Fingerprinting, and Privacy from Discarded Geometry","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-02T11:05:26.424552Z"},"links":{"citing_paper":"/paper/2607.13046"},"observation_digest":"sha256:87a2ebbb3634cef4085682ac5493f5efa8a247087750f9a63d92d663878696ec","observation_id":"29923c79-63c0-4841-ac34-2305aebcae87","resolution":{"observed_at":"2026-08-02T11:05:26.424552Z","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":"2026-08-02T11:05:26.511407Z","title":"Se (3)-transformers: 3d roto- translation equivariant attention networks.Advances in neural information processing systems, 33:1970–1981, 2020","venue":null,"work_id":null,"year":1970},"citing_paper":{"arxiv_id":"2607.13046","last_updated":"2026-06-17T01:03:26Z","snapshot_observed_at":"2026-08-09T00:22:51.619840Z","submitted_at":"2026-06-17T01:03:26Z","title":"What Your Model Threw Away and Why You'll Want It Back: Masking, Fingerprinting, and Privacy from Discarded Geometry","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-02T11:05:26.511407Z"},"links":{"citing_paper":"/paper/2607.13046"},"observation_digest":"sha256:7dd5bb12da307649415cb1e151af33d3517f438ac37e9dc1ab9fbd80d7995b6d","observation_id":"6fe2b997-d190-4e98-a01f-b82fbae11284","resolution":{"observed_at":"2026-08-02T11:05:26.511407Z","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":"2026-08-02T11:05:26.608797Z","title":"Fully homomorphic encryption using ideal lattices","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2607.13046","last_updated":"2026-06-17T01:03:26Z","snapshot_observed_at":"2026-08-09T00:22:51.619840Z","submitted_at":"2026-06-17T01:03:26Z","title":"What Your Model Threw Away and Why You'll Want It Back: Masking, Fingerprinting, and Privacy from Discarded Geometry","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-02T11:05:26.608797Z"},"links":{"citing_paper":"/paper/2607.13046"},"observation_digest":"sha256:fa7c412bddd8562f9929f8ae4b2ea6932cd31f798bc926483924882dc82bb252","observation_id":"1a0bf100-be0e-4939-8cdf-2651d177d3dc","resolution":{"observed_at":"2026-08-02T11:05:26.608797Z","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":"2026-08-02T11:05:26.677973Z","title":"Geometric deep learning and equivariant neural networks","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.13046","last_updated":"2026-06-17T01:03:26Z","snapshot_observed_at":"2026-08-09T00:22:51.619840Z","submitted_at":"2026-06-17T01:03:26Z","title":"What Your Model Threw Away and Why You'll Want It Back: Masking, Fingerprinting, and Privacy from Discarded Geometry","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-02T11:05:26.677973Z"},"links":{"citing_paper":"/paper/2607.13046"},"observation_digest":"sha256:e8eebf144751bb4515e0595728799aec6486426a3530d8ae43271be5e1c8cabb","observation_id":"d16827e0-9294-4377-a51f-f0247cf2307e","resolution":{"observed_at":"2026-08-02T11:05:26.677973Z","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":"2026-08-02T11:05:26.765072Z","title":"Cryptonets: Applying neural networks to encrypted data with high throughput and accuracy","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.13046","last_updated":"2026-06-17T01:03:26Z","snapshot_observed_at":"2026-08-09T00:22:51.619840Z","submitted_at":"2026-06-17T01:03:26Z","title":"What Your Model Threw Away and Why You'll Want It Back: Masking, Fingerprinting, and Privacy from Discarded Geometry","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-02T11:05:26.765072Z"},"links":{"citing_paper":"/paper/2607.13046"},"observation_digest":"sha256:8f4f3cd0062e3846cec159c78c980b5109233e9a0222f5e67de5f04a36806172","observation_id":"1e76b113-0427-4784-9cf1-fd05b7e02296","resolution":{"observed_at":"2026-08-02T11:05:26.765072Z","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":"2026-08-02T11:05:26.813426Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.13046","last_updated":"2026-06-17T01:03:26Z","snapshot_observed_at":"2026-08-09T00:22:51.619840Z","submitted_at":"2026-06-17T01:03:26Z","title":"What Your Model Threw Away and Why You'll Want It Back: Masking, Fingerprinting, and Privacy from Discarded Geometry","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-02T11:05:26.813426Z"},"links":{"citing_paper":"/paper/2607.13046"},"observation_digest":"sha256:4bb0d27a949d2bb3127d5fb4d264f45d0b371ce27bb3a1257ce75d122c4c32d2","observation_id":"e26f9fe8-962d-458b-97b9-5c9bb458dcec","resolution":{"observed_at":"2026-08-02T11:05:26.813426Z","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":"2026-08-02T11:05:26.907632Z","title":"Hall.Lie Groups, Lie Algebras, and Representations: An Elementary Introduction","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.13046","last_updated":"2026-06-17T01:03:26Z","snapshot_observed_at":"2026-08-09T00:22:51.619840Z","submitted_at":"2026-06-17T01:03:26Z","title":"What Your Model Threw Away and Why You'll Want It Back: Masking, Fingerprinting, and Privacy from Discarded Geometry","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-02T11:05:26.907632Z"},"links":{"citing_paper":"/paper/2607.13046"},"observation_digest":"sha256:b4beb63fb9b99a0f31a5d16dcc6a63b3e7546969b3ca170dd875686b595184d6","observation_id":"a93bd72e-9e77-4926-953c-dcacb119336e","resolution":{"observed_at":"2026-08-02T11:05:26.907632Z","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":"2026-08-02T11:05:27.086853Z","title":"Advances and open problems in federated learning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.13046","last_updated":"2026-06-17T01:03:26Z","snapshot_observed_at":"2026-08-09T00:22:51.619840Z","submitted_at":"2026-06-17T01:03:26Z","title":"What Your Model Threw Away and Why You'll Want It Back: Masking, Fingerprinting, and Privacy from Discarded Geometry","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-02T11:05:27.086853Z"},"links":{"citing_paper":"/paper/2607.13046"},"observation_digest":"sha256:a55cb0777d12f203991c8ed8b8624fdba8208f0f6c6913959271c42503b46176","observation_id":"9ee55921-aa1f-44db-9c48-036e4352b52d","resolution":{"observed_at":"2026-08-02T11:05:27.086853Z","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":"2026-08-02T11:05:27.252142Z","title":"Equivariant flow-based sampling for lattice gauge theory.Physical Review Letters, 125(12):121601, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.13046","last_updated":"2026-06-17T01:03:26Z","snapshot_observed_at":"2026-08-09T00:22:51.619840Z","submitted_at":"2026-06-17T01:03:26Z","title":"What Your Model Threw Away and Why You'll Want It Back: Masking, Fingerprinting, and Privacy from Discarded Geometry","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-02T11:05:27.252142Z"},"links":{"citing_paper":"/paper/2607.13046"},"observation_digest":"sha256:1fe18e4b481d3db24df47fe380d7c7a76d4b49dd708f3628fdd2e29ebd0a0040","observation_id":"625418d0-dd2e-42b2-b6d3-0df63959a42d","resolution":{"observed_at":"2026-08-02T11:05:27.252142Z","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":"2026-08-02T11:05:27.372584Z","title":"On the generalization of equivariance and convolution in neural networks to the action of compact groups","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.13046","last_updated":"2026-06-17T01:03:26Z","snapshot_observed_at":"2026-08-09T00:22:51.619840Z","submitted_at":"2026-06-17T01:03:26Z","title":"What Your Model Threw Away and Why You'll Want It Back: Masking, Fingerprinting, and Privacy from Discarded Geometry","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-02T11:05:27.372584Z"},"links":{"citing_paper":"/paper/2607.13046"},"observation_digest":"sha256:e68a3932f6ce997ba3793e74782716f0982a082a99d774cce90c78f763dc2486","observation_id":"04bb7f7a-280a-4ddc-9a52-6eea98af0770","resolution":{"observed_at":"2026-08-02T11:05:27.372584Z","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":"2026-08-02T11:05:27.524754Z","title":"A review of applications in federated learning","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.13046","last_updated":"2026-06-17T01:03:26Z","snapshot_observed_at":"2026-08-09T00:22:51.619840Z","submitted_at":"2026-06-17T01:03:26Z","title":"What Your Model Threw Away and Why You'll Want It Back: Masking, Fingerprinting, and Privacy from Discarded Geometry","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-02T11:05:27.524754Z"},"links":{"citing_paper":"/paper/2607.13046"},"observation_digest":"sha256:c7b71a0f55df00a0d964afb38b2402732eed56e65efd39ef4b5632300f131b8e","observation_id":"4afb6156-c04a-4fd8-8f05-59ecd143b2fb","resolution":{"observed_at":"2026-08-02T11:05:27.524754Z","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":"2026-08-02T11:05:27.646431Z","title":"Null space properties of neural networks with applications to image steganography.Mathematics, 13(21):3394, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.13046","last_updated":"2026-06-17T01:03:26Z","snapshot_observed_at":"2026-08-09T00:22:51.619840Z","submitted_at":"2026-06-17T01:03:26Z","title":"What Your Model Threw Away and Why You'll Want It Back: Masking, Fingerprinting, and Privacy from Discarded Geometry","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-02T11:05:27.646431Z"},"links":{"citing_paper":"/paper/2607.13046"},"observation_digest":"sha256:f7b9c793394aa35f5de568b62549f8479cc39d8c79fed4443a75bae05a9f1262","observation_id":"1d2c02b2-41da-4ea1-b52d-4229e293179a","resolution":{"observed_at":"2026-08-02T11:05:27.646431Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1912.00888","last_updated":"2021-01-20T18:19:24Z","snapshot_observed_at":"2026-07-06T08:41:25.156353Z","submitted_at":"2019-12-02T16:11:56Z","title":"Deep Neural Network Fingerprinting by Conferrable Adversarial Examples","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1912.00888","snapshot_observed_at":"2026-08-02T11:05:27.774368Z","title":"Deep neural network fingerprinting by conferrable adversarial examples.arXiv preprint arXiv:1912.00888, 2019","venue":null,"work_id":null,"year":1912},"citing_paper":{"arxiv_id":"2607.13046","last_updated":"2026-06-17T01:03:26Z","snapshot_observed_at":"2026-08-09T00:22:51.619840Z","submitted_at":"2026-06-17T01:03:26Z","title":"What Your Model Threw Away and Why You'll Want It Back: Masking, Fingerprinting, and Privacy from Discarded Geometry","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-02T11:05:27.774368Z"},"links":{"cited_paper":"/paper/1912.00888","citing_paper":"/paper/2607.13046"},"observation_digest":"sha256:936715d4bfe224d3885ee518ab58fa7bc039e6fc25df3dbfa9e076214c34e268","observation_id":"978fe0bd-1e7b-47c2-88a1-ed8580c8f086","resolution":{"observed_at":"2026-08-02T11:05:27.774368Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2101.05428","last_updated":"2021-01-14T02:44:28Z","snapshot_observed_at":"2026-07-06T10:32:26.581314Z","submitted_at":"2021-01-14T02:44:28Z","title":"Federated Learning: Opportunities and Challenges","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.05428","snapshot_observed_at":"2026-08-02T11:05:27.873595Z","title":"Federated learning: Opportunities and challenges.arXiv preprint arXiv:2101.05428, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.13046","last_updated":"2026-06-17T01:03:26Z","snapshot_observed_at":"2026-08-09T00:22:51.619840Z","submitted_at":"2026-06-17T01:03:26Z","title":"What Your Model Threw Away and Why You'll Want It Back: Masking, Fingerprinting, and Privacy from Discarded Geometry","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-02T11:05:27.873595Z"},"links":{"cited_paper":"/paper/2101.05428","citing_paper":"/paper/2607.13046"},"observation_digest":"sha256:3aabc73c622d84922dd286ea8d0f289e601e9a81d5d00054afe13b24139bc8f0","observation_id":"06bf7f1a-bfe5-41d2-862b-4c0c8bead38f","resolution":{"observed_at":"2026-08-02T11:05:27.873595Z","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":"2026-08-02T11:05:27.980905Z","title":"Communication-efficient learning of deep networks from decentralized data","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.13046","last_updated":"2026-06-17T01:03:26Z","snapshot_observed_at":"2026-08-09T00:22:51.619840Z","submitted_at":"2026-06-17T01:03:26Z","title":"What Your Model Threw Away and Why You'll Want It Back: Masking, Fingerprinting, and Privacy from Discarded Geometry","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-02T11:05:27.980905Z"},"links":{"citing_paper":"/paper/2607.13046"},"observation_digest":"sha256:73e5f35ba5ee44671f29d8fa5471da46b5c1dfc873ce0d534df3467ac6618f8a","observation_id":"9f02c88d-9771-4713-997a-06a81a959b43","resolution":{"observed_at":"2026-08-02T11:05:27.980905Z","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":"2026-08-02T11:05:28.052560Z","title":"An overview of image steganography","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2607.13046","last_updated":"2026-06-17T01:03:26Z","snapshot_observed_at":"2026-08-09T00:22:51.619840Z","submitted_at":"2026-06-17T01:03:26Z","title":"What Your Model Threw Away and Why You'll Want It Back: Masking, Fingerprinting, and Privacy from Discarded Geometry","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-02T11:05:28.052560Z"},"links":{"citing_paper":"/paper/2607.13046"},"observation_digest":"sha256:4036bff162f66cc50c5d9c1d9a1f524c545753272a385014243d16dca6dd12ac","observation_id":"0a96633c-70cb-4ef9-9bf2-e7f102791e9c","resolution":{"observed_at":"2026-08-02T11:05:28.052560Z","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":"2026-08-02T11:05:28.131714Z","title":"Finger- printing deep neural networks globally via universal adversarial perturbations","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.13046","last_updated":"2026-06-17T01:03:26Z","snapshot_observed_at":"2026-08-09T00:22:51.619840Z","submitted_at":"2026-06-17T01:03:26Z","title":"What Your Model Threw Away and Why You'll Want It Back: Masking, Fingerprinting, and Privacy from Discarded Geometry","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-02T11:05:28.131714Z"},"links":{"citing_paper":"/paper/2607.13046"},"observation_digest":"sha256:95767d3e5bbad1f6cb20c2819a3c977995751eff9e151c9834ad73a0357179a3","observation_id":"fd211473-4246-40c3-b807-5e82f4463704","resolution":{"observed_at":"2026-08-02T11:05:28.131714Z","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":"2026-08-02T11:05:28.212647Z","title":"Quantum chemistry structures and properties of 134 kilo molecules.Scientific data, 1(1):1–7, 2014","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2607.13046","last_updated":"2026-06-17T01:03:26Z","snapshot_observed_at":"2026-08-09T00:22:51.619840Z","submitted_at":"2026-06-17T01:03:26Z","title":"What Your Model Threw Away and Why You'll Want It Back: Masking, Fingerprinting, and Privacy from Discarded Geometry","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-02T11:05:28.212647Z"},"links":{"citing_paper":"/paper/2607.13046"},"observation_digest":"sha256:935f483c804bd92c61382e045c78d819baa33f2f3d0201b70480a0ad9d75c9de","observation_id":"55510c37-b54b-4f3e-8922-24e611c17a8d","resolution":{"observed_at":"2026-08-02T11:05:28.212647Z","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":"2026-08-02T11:05:28.263477Z","title":"Protecting artificial intelligence ips: a survey of watermarking and fingerprinting for machine learning.CAAI Transactions on Intelligence Technology, 6(2):180–191, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.13046","last_updated":"2026-06-17T01:03:26Z","snapshot_observed_at":"2026-08-09T00:22:51.619840Z","submitted_at":"2026-06-17T01:03:26Z","title":"What Your Model Threw Away and Why You'll Want It Back: Masking, Fingerprinting, and Privacy from Discarded Geometry","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-02T11:05:28.263477Z"},"links":{"citing_paper":"/paper/2607.13046"},"observation_digest":"sha256:ffe3dc4eabc6ba98b9da4f8f387afdd5c9728a34c7a3bb53856e465c555cc080","observation_id":"656116d5-abcc-49ea-b175-938ef0507113","resolution":{"observed_at":"2026-08-02T11:05:28.263477Z","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":"2026-08-02T11:05:28.336412Z","title":"Enumeration of 166 billion organic small molecules in the chemical universe database gdb-17.Journal of chemical information and modeling, 52(11):2864–2875, 2012","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2607.13046","last_updated":"2026-06-17T01:03:26Z","snapshot_observed_at":"2026-08-09T00:22:51.619840Z","submitted_at":"2026-06-17T01:03:26Z","title":"What Your Model Threw Away and Why You'll Want It Back: Masking, Fingerprinting, and Privacy from Discarded Geometry","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-02T11:05:28.336412Z"},"links":{"citing_paper":"/paper/2607.13046"},"observation_digest":"sha256:1db6239976b601d26866aeca801e2050a027b6350e4564e265e35a4f77be85d8","observation_id":"c83a0863-0859-4313-843a-616f6b846d72","resolution":{"observed_at":"2026-08-02T11:05:28.336412Z","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":"2026-08-02T11:05:28.431993Z","title":"Circuit-centric quantum classifiers.Physical Review A, 101(3):032308, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.13046","last_updated":"2026-06-17T01:03:26Z","snapshot_observed_at":"2026-08-09T00:22:51.619840Z","submitted_at":"2026-06-17T01:03:26Z","title":"What Your Model Threw Away and Why You'll Want It Back: Masking, Fingerprinting, and Privacy from Discarded Geometry","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-02T11:05:28.431993Z"},"links":{"citing_paper":"/paper/2607.13046"},"observation_digest":"sha256:3f9ee5b57365aa189bb32f931ec79647b225ffc0f108062acd3d2f25d01e2376","observation_id":"db3d7d5c-1d26-4edc-9b20-9787f0b48022","resolution":{"observed_at":"2026-08-02T11:05:28.431993Z","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":"2026-08-02T11:05:28.510966Z","title":"Springer, 2012","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2607.13046","last_updated":"2026-06-17T01:03:26Z","snapshot_observed_at":"2026-08-09T00:22:51.619840Z","submitted_at":"2026-06-17T01:03:26Z","title":"What Your Model Threw Away and Why You'll Want It Back: Masking, Fingerprinting, and Privacy from Discarded Geometry","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-02T11:05:28.510966Z"},"links":{"citing_paper":"/paper/2607.13046"},"observation_digest":"sha256:4903119198bc2ea220055763c6404bb7386636c5d745d6c1d0573cb6cf90b5b0","observation_id":"b8f13a29-9108-4c1f-b878-6d6d854a000e","resolution":{"observed_at":"2026-08-02T11:05:28.510966Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1802.08219","last_updated":"2018-05-18T20:09:34Z","snapshot_observed_at":"2026-07-06T06:24:51.822169Z","submitted_at":"2018-02-22T18:17:31Z","title":"Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1802.08219","snapshot_observed_at":"2026-08-02T11:05:28.632636Z","title":"Tensor field networks: Rotation-and translation-equivariant neural networks for 3d point clouds.arXiv preprint arXiv:1802.08219, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.13046","last_updated":"2026-06-17T01:03:26Z","snapshot_observed_at":"2026-08-09T00:22:51.619840Z","submitted_at":"2026-06-17T01:03:26Z","title":"What Your Model Threw Away and Why You'll Want It Back: Masking, Fingerprinting, and Privacy from Discarded Geometry","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-02T11:05:28.632636Z"},"links":{"cited_paper":"/paper/1802.08219","citing_paper":"/paper/2607.13046"},"observation_digest":"sha256:526f3ec483ab30e00577a29a5ab8957bd682f9f022a36612c87d1466826364e1","observation_id":"5250d1a7-ba1d-4550-af87-5476f4f39588","resolution":{"observed_at":"2026-08-02T11:05:28.632636Z","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":"2026-08-02T11:05:28.776717Z","title":"A survey on federated learning: challenges and applications.International journal of machine learning and cybernetics, 14(2):513–535, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.13046","last_updated":"2026-06-17T01:03:26Z","snapshot_observed_at":"2026-08-09T00:22:51.619840Z","submitted_at":"2026-06-17T01:03:26Z","title":"What Your Model Threw Away and Why You'll Want It Back: Masking, Fingerprinting, and Privacy from Discarded Geometry","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-02T11:05:28.776717Z"},"links":{"citing_paper":"/paper/2607.13046"},"observation_digest":"sha256:cf62f4ab998f28e2f40aeb0582fbebe98aeb55530f4bc7e0a1b1dacd0aedd14e","observation_id":"55d67890-9cca-450e-b1e8-456e86fa8fb9","resolution":{"observed_at":"2026-08-02T11:05:28.776717Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.13046","last_updated":"2026-06-17T01:03:26Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T00:22:51.619840Z","submitted_at":"2026-06-17T01:03:26Z","title":"What Your Model Threw Away and Why You'll Want It Back: Masking, Fingerprinting, and Privacy from Discarded Geometry"},"reference_resolution":{"displayed":38,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":38,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":38},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 0 inbound Pith citation observations for arXiv:2607.13046."}