{"as_of":"2026-08-18T16:41:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:96a9fcf05bace99aa404011154c741ba9f595f850f2bf9d933f36b35f57a4e9e","coverage":[{"denominator":56,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":56,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-30T18:56:30.594491Z","state":"measured"},{"denominator":56,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":56,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+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/2607.23658/citation-record","integrity":"/paper/2607.23658/integrity","json":"/paper/2607.23658/citation-record.json","paper":"/paper/2607.23658"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-30T18:56:25.454950Z","title":"Aadc-net: A multimodal deep learning framework for automatic anomaly detection in real-time surveillance,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-07-30T18:56:25.454950Z"},"links":{"citing_paper":"/paper/2607.23658"},"observation_digest":"sha256:22ad0231d108f1b1e2e14fceb6e46af83e2f399ccdcb7036072574e88010dea6","observation_id":"79a4f39f-c944-43dd-8edc-c09cfc45f1b1","resolution":{"observed_at":"2026-07-30T18:56:25.454950Z","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":"2026-07-30T18:56:25.633734Z","title":"Anomaly detection for medical images using heterogeneous auto-encoder,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-07-30T18:56:25.633734Z"},"links":{"citing_paper":"/paper/2607.23658"},"observation_digest":"sha256:ebcc946ec8f0aa91c56d48490a81d22c06132e17f366cdfb3f6ab2fce22498ee","observation_id":"64dd1aba-aae4-4c12-8658-3fe444db4f41","resolution":{"observed_at":"2026-07-30T18:56:25.633734Z","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":"2026-07-30T18:56:25.741089Z","title":"Enhancing unsupervised anomaly detection with score-guided network,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-07-30T18:56:25.741089Z"},"links":{"citing_paper":"/paper/2607.23658"},"observation_digest":"sha256:a59e6664c9d8e3ae293571463db8d2846b64a8d22f306ffc3175bba52fe884af","observation_id":"025642a1-cde0-411a-b5bc-7e45371f61fa","resolution":{"observed_at":"2026-07-30T18:56:25.741089Z","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":"2026-07-30T18:56:25.813412Z","title":"Exploiting structural consistency of chest anatomy for unsupervised anomaly detection in radiography images,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-07-30T18:56:25.813412Z"},"links":{"citing_paper":"/paper/2607.23658"},"observation_digest":"sha256:f98d854e39ef8678eb68d215be74736872fac16ee818708601f46c18a636ed30","observation_id":"b7aaa6b3-6c37-4def-8178-7d77ec0dca7d","resolution":{"observed_at":"2026-07-30T18:56:25.813412Z","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":"2026-07-30T18:56:25.911847Z","title":"Unistad: An unified triple-tower student–teacher model for multi-class anomaly detection and localization,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-07-30T18:56:25.911847Z"},"links":{"citing_paper":"/paper/2607.23658"},"observation_digest":"sha256:7031123d895d26349ebfac91e18145596cf1833985174f8ee00a2521e6f6d579","observation_id":"c0dc1fc6-4896-443e-95f9-56a03a1c2cc4","resolution":{"observed_at":"2026-07-30T18:56:25.911847Z","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":"2026-07-30T18:56:26.005933Z","title":"Boosting global- local feature matching via anomaly synthesis for multi-class point cloud anomaly detection,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-07-30T18:56:26.005933Z"},"links":{"citing_paper":"/paper/2607.23658"},"observation_digest":"sha256:a4b733ee630b984ce10b4766a76e48bed5eea06f225b83f0b7bfdaeb735a7e23","observation_id":"791421fd-0522-4275-b840-50b4afdb7c82","resolution":{"observed_at":"2026-07-30T18:56:26.005933Z","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":"2026-07-30T18:56:26.094496Z","title":"Costfilter- ad: Enhancing anomaly detection through matching cost filtering,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-07-30T18:56:26.094496Z"},"links":{"citing_paper":"/paper/2607.23658"},"observation_digest":"sha256:2f098c88772e5c2f216e3c09db69912a9b4029f9f7f11dd78ef1e70270de13ac","observation_id":"f8ea2681-a15f-4bea-8b47-9c02b00cd708","resolution":{"observed_at":"2026-07-30T18:56:26.094496Z","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":"2026-07-30T18:56:26.186386Z","title":"Revisiting reverse distillation for anomaly detection,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-07-30T18:56:26.186386Z"},"links":{"citing_paper":"/paper/2607.23658"},"observation_digest":"sha256:10b7c64e1b3e2b333fe7bf6725048ccc1f07ef16aab4e2bb5affd7c2711070f0","observation_id":"95d5c992-8978-476e-93d7-b2d7ef9e3c08","resolution":{"observed_at":"2026-07-30T18:56:26.186386Z","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":"2026-07-30T18:56:26.320819Z","title":"A unified anomaly synthesis strategy with gradient ascent for industrial anomaly detection and localization,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-07-30T18:56:26.320819Z"},"links":{"citing_paper":"/paper/2607.23658"},"observation_digest":"sha256:711b4bf97feb730945176c1ab7dd0fa32e6884f4ce591d4fe90a4f38dc1e5384","observation_id":"b894a1d5-cb45-4598-9747-9069defd8949","resolution":{"observed_at":"2026-07-30T18:56:26.320819Z","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":"2026-07-30T18:56:26.412076Z","title":"Unsupervised anomaly segmentation via deep feature reconstruction,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-07-30T18:56:26.412076Z"},"links":{"citing_paper":"/paper/2607.23658"},"observation_digest":"sha256:24c72436f814470f6d7d197c3e6b3610722bad99b0a744be3f86996d60800bb1","observation_id":"25839331-a59e-4b7f-b31a-e1b93b972ade","resolution":{"observed_at":"2026-07-30T18:56:26.412076Z","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":"2026-07-30T18:56:26.503729Z","title":"Towards visually explaining variational autoencoders,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-07-30T18:56:26.503729Z"},"links":{"citing_paper":"/paper/2607.23658"},"observation_digest":"sha256:42ab05d4da87e4b683049d028f059d793a966f7065190c2e566e353c54c0718f","observation_id":"37069cac-0b13-486d-b701-dfdf1140c33f","resolution":{"observed_at":"2026-07-30T18:56:26.503729Z","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":"2026-07-30T18:56:26.606974Z","title":"Divide- and-assemble: Learning block-wise memory for unsupervised anomaly detection,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-07-30T18:56:26.606974Z"},"links":{"citing_paper":"/paper/2607.23658"},"observation_digest":"sha256:ff5a56fe9843a9ad8335c70e0f333289f9e460ec5f198f7ae5d4551b06d33514","observation_id":"be732247-9949-4a8a-b748-c0d134baf767","resolution":{"observed_at":"2026-07-30T18:56:26.606974Z","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":"2026-07-30T18:56:26.707409Z","title":"Memorizing normality to detect anomaly: Memory- augmented deep autoencoder for unsupervised anomaly detection,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-07-30T18:56:26.707409Z"},"links":{"citing_paper":"/paper/2607.23658"},"observation_digest":"sha256:04309191386853b2bd90572f529296ff051641bf8ed6aeeb50589fc1f38de66f","observation_id":"3ecb92b2-c336-4006-a997-844fd538b72f","resolution":{"observed_at":"2026-07-30T18:56:26.707409Z","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":"2026-07-30T18:56:26.812453Z","title":"Omni-frequency channel-selection representations for unsupervised anomaly detection,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-07-30T18:56:26.812453Z"},"links":{"citing_paper":"/paper/2607.23658"},"observation_digest":"sha256:ad6021c60f5f5ab6f07044996a85c5a00ad37458d8ed35131096da84a778f5a0","observation_id":"b45c106e-7780-4e9a-bd23-fd33c2a381c8","resolution":{"observed_at":"2026-07-30T18:56:26.812453Z","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":"2026-07-30T18:56:26.919744Z","title":"Reconstruction by inpainting for visual anomaly detection,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-07-30T18:56:26.919744Z"},"links":{"citing_paper":"/paper/2607.23658"},"observation_digest":"sha256:c9dfcfc68389ae649de94243821e012c54c8f45ef4926528183a322455777cb9","observation_id":"9be01c97-6a11-4fd5-b2a6-87138143c4d5","resolution":{"observed_at":"2026-07-30T18:56:26.919744Z","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":"2026-07-30T18:56:27.024876Z","title":"Unsupervised surface anomaly detection with diffusion probabilistic model,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-07-30T18:56:27.024876Z"},"links":{"citing_paper":"/paper/2607.23658"},"observation_digest":"sha256:cdf36c2eb8b7908e85c2f4a2ca219db464b59f4c982380d188639aab85629b32","observation_id":"50791451-10ac-4edd-ac40-9e0c52b31975","resolution":{"observed_at":"2026-07-30T18:56:27.024876Z","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":"2026-07-30T18:56:27.113481Z","title":"Glad: Towards better reconstruction with global and local adaptive diffusion models for unsupervised anomaly detection,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-07-30T18:56:27.113481Z"},"links":{"citing_paper":"/paper/2607.23658"},"observation_digest":"sha256:9702f3a0f4a59fb34cdf18c3ad1e8e22b7a54fb130968a6cea4f104c5719b48d","observation_id":"476fc681-d57b-4912-94eb-625d18dc62e7","resolution":{"observed_at":"2026-07-30T18:56:27.113481Z","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":"2026-07-30T18:56:27.203875Z","title":"A diffusion-based framework for multi-class anomaly detection,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-07-30T18:56:27.203875Z"},"links":{"citing_paper":"/paper/2607.23658"},"observation_digest":"sha256:dc58f39a8a73df277ab6fbbcb4b9bd6df94d2c0e0cee446ac5793c5ca70364bd","observation_id":"be5f269c-bf3f-4086-bf6c-eacebccbf451","resolution":{"observed_at":"2026-07-30T18:56:27.203875Z","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":"2026-07-30T18:56:27.278786Z","title":"Adtr: Anomaly detection transformer with feature reconstruction,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-07-30T18:56:27.278786Z"},"links":{"citing_paper":"/paper/2607.23658"},"observation_digest":"sha256:05d3c81c575878fb72d2b0fe676191c37f683e50a5d412f99243d8bf73bb8a62","observation_id":"a2a9bbed-0829-4454-ab5e-9bfa67aa99f2","resolution":{"observed_at":"2026-07-30T18:56:27.278786Z","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":"2026-07-30T18:56:27.349818Z","title":"Draem-a discriminatively trained reconstruction embedding for surface anomaly detection,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-07-30T18:56:27.349818Z"},"links":{"citing_paper":"/paper/2607.23658"},"observation_digest":"sha256:2f14683d83a8c574de5e65ed13242d8a5c6d443fff16c3c62877e74a50c6c97b","observation_id":"ea81a7a8-06c1-4ec3-bc90-b86e9d8f00ac","resolution":{"observed_at":"2026-07-30T18:56:27.349818Z","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":"2026-07-30T18:56:27.444185Z","title":"Diffusionad: Norm-guided one-step denoising diffusion for anomaly detection,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-07-30T18:56:27.444185Z"},"links":{"citing_paper":"/paper/2607.23658"},"observation_digest":"sha256:86e9a67416cf85752f0679c78ea17010c5875777a15e994808db59714f273e4b","observation_id":"d1e7155e-a052-4207-9e76-64a1dab3c230","resolution":{"observed_at":"2026-07-30T18:56:27.444185Z","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":"2026-07-30T18:56:27.572064Z","title":"Dsr–a dual subspace re- projection network for surface anomaly detection,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-07-30T18:56:27.572064Z"},"links":{"citing_paper":"/paper/2607.23658"},"observation_digest":"sha256:75c6e33185a6614c9aba44634ca0c8c2a727992e7fa6cd1c3700c10df907a83d","observation_id":"eb938132-e277-49a7-8818-339a947148ea","resolution":{"observed_at":"2026-07-30T18:56:27.572064Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.17900","last_updated":"2024-04-27T13:13:27Z","snapshot_observed_at":"2026-08-16T15:13:43.418892Z","submitted_at":"2024-04-27T13:13:27Z","title":"Unsupervised Anomaly Detection via Masked Diffusion Posterior Sampling","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.17900","snapshot_observed_at":"2026-07-30T18:56:27.615015Z","title":"Unsu- pervised anomaly detection via masked diffusion posterior sampling,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-07-30T18:56:27.615015Z"},"links":{"cited_paper":"/paper/2404.17900","citing_paper":"/paper/2607.23658"},"observation_digest":"sha256:8e62d6fd007b8fe09344432d988fbd4f86ae922128c6e13189d24e4517615172","observation_id":"a9200955-1294-4807-9353-c1fc03b80e0c","resolution":{"observed_at":"2026-07-30T18:56:27.615015Z","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":"2026-07-30T18:56:27.720756Z","title":"Anomaly detection with conditioned denoising diffusion models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-07-30T18:56:27.720756Z"},"links":{"citing_paper":"/paper/2607.23658"},"observation_digest":"sha256:5a22136319fe969d8e40598ea1424f7ceba43be4c9a069980c72b410c0d0ab36","observation_id":"9fe42d8f-cce1-4173-9aa4-276067a4c745","resolution":{"observed_at":"2026-07-30T18:56:27.720756Z","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":"2026-07-30T18:56:27.811362Z","title":"A unified model for multi-class anomaly detection,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-07-30T18:56:27.811362Z"},"links":{"citing_paper":"/paper/2607.23658"},"observation_digest":"sha256:44ecd2ba82e372210cce8d31c43288951e68ac27faa8eee33d061bede73723ce","observation_id":"51e3909c-0a30-448a-9300-50e408ea8224","resolution":{"observed_at":"2026-07-30T18:56:27.811362Z","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":"2026-07-30T18:56:27.909693Z","title":"Destseg: Segmentation guided denoising student-teacher for anomaly detection,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-07-30T18:56:27.909693Z"},"links":{"citing_paper":"/paper/2607.23658"},"observation_digest":"sha256:00fb1f4abfbc5c2e57a6c6e1e80b2d4ccd39aea3152eb9e2a11a97d45f9f2ced","observation_id":"f7842056-9493-443e-afa5-4e265a96c39c","resolution":{"observed_at":"2026-07-30T18:56:27.909693Z","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":"2026-07-30T18:56:27.983378Z","title":"Just noticeable learning for unsupervised anomaly localization and detection,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-07-30T18:56:27.983378Z"},"links":{"citing_paper":"/paper/2607.23658"},"observation_digest":"sha256:d73763dbc7921b446a8bdf41598e22defda4e8f40835aeffd38e003c380c9a3e","observation_id":"35073856-936a-4e50-a331-c861f16b0a52","resolution":{"observed_at":"2026-07-30T18:56:27.983378Z","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":"2026-07-30T18:56:28.144009Z","title":"Learning semantic context from normal samples for unsupervised anomaly detection,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-07-30T18:56:28.144009Z"},"links":{"citing_paper":"/paper/2607.23658"},"observation_digest":"sha256:ea256807b55e66c3879b56e1e40a0aa45455ad8d0f5aab9d1abd231d3704752f","observation_id":"aabc537e-1af6-4a4a-bf3c-1c988679e376","resolution":{"observed_at":"2026-07-30T18:56:28.144009Z","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":"2026-07-30T18:56:28.245327Z","title":"A survey on multimodal large language models for autonomous driving,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-07-30T18:56:28.245327Z"},"links":{"citing_paper":"/paper/2607.23658"},"observation_digest":"sha256:ac494e185b01013626c1c0680126b9640b22b8baf4a002863dbb93f8408b53b2","observation_id":"1d19c5b2-1a1e-4028-8f88-756625d646f3","resolution":{"observed_at":"2026-07-30T18:56:28.245327Z","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":"2026-07-30T18:56:28.365293Z","title":"Spatio-contextual deep network-based multimodal pedestrian detection for autonomous driving,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-07-30T18:56:28.365293Z"},"links":{"citing_paper":"/paper/2607.23658"},"observation_digest":"sha256:2453e69941a3451496feaa05a1431e746c87f44112cbada5432ed60f4080674c","observation_id":"263e7486-0927-46f0-a2a8-955755c2eb76","resolution":{"observed_at":"2026-07-30T18:56:28.365293Z","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":"2026-07-30T18:56:28.429041Z","title":"Unified domain adaptive semantic segmentation,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-07-30T18:56:28.429041Z"},"links":{"citing_paper":"/paper/2607.23658"},"observation_digest":"sha256:c8726602c1a8749e121d88f39ba57a6e731d85d68ab3010ce0f5c3f6bdb08f53","observation_id":"04a1f922-bb23-4eba-bc4c-8db90257b8c0","resolution":{"observed_at":"2026-07-30T18:56:28.429041Z","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":"2026-07-30T18:56:28.491961Z","title":"Multi-granularity con- trastive cross-modal collaborative generation for end-to-end long-term video question answering,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-07-30T18:56:28.491961Z"},"links":{"citing_paper":"/paper/2607.23658"},"observation_digest":"sha256:84610d30ef269d077ed842bd8d35bb4223fae4d971c1e27279f3b132785fe52b","observation_id":"279193ea-6cf8-470a-bf3b-785ff0628682","resolution":{"observed_at":"2026-07-30T18:56:28.491961Z","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":"2026-07-30T18:56:28.642849Z","title":"History aware multimodal transformer for vision-and-language navigation,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-07-30T18:56:28.642849Z"},"links":{"citing_paper":"/paper/2607.23658"},"observation_digest":"sha256:42b73c2c650634cd78b0f52101be41ed8d1ec0205847e3a63bd3ad45ffae3953","observation_id":"2d4664d0-adb2-4d38-8a33-ccd287df1792","resolution":{"observed_at":"2026-07-30T18:56:28.642849Z","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":"2026-07-30T18:56:28.735766Z","title":"Cross-modal map learning for vision and language navigation,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-07-30T18:56:28.735766Z"},"links":{"citing_paper":"/paper/2607.23658"},"observation_digest":"sha256:6f8870080924b1fa338d31c7b33dc4c673886592ae1777054ebeca7d788cdaf2","observation_id":"36e3b8fc-1570-4641-b223-669bed273cda","resolution":{"observed_at":"2026-07-30T18:56:28.735766Z","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":"2026-07-30T18:56:28.807074Z","title":"An overview of deep learning methods for multimodal medical data mining,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-07-30T18:56:28.807074Z"},"links":{"citing_paper":"/paper/2607.23658"},"observation_digest":"sha256:4358d3ecdd5c2b486e3e3c70198bc59668a314b13066411bb8a2b1414b4b5929","observation_id":"8ba99dbb-c8d6-411b-a98e-056f22cefb19","resolution":{"observed_at":"2026-07-30T18:56:28.807074Z","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":"2026-07-30T18:56:28.891441Z","title":"Plug-and-play regula- tors for image-text matching,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-07-30T18:56:28.891441Z"},"links":{"citing_paper":"/paper/2607.23658"},"observation_digest":"sha256:8283b8795aa817c1d89c37d10434eeee94e782b401bab83f1441ec6b1e00ff35","observation_id":"dc6e5525-d6c7-4cd5-b4ea-3dae1705d966","resolution":{"observed_at":"2026-07-30T18:56:28.891441Z","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":"2026-07-30T18:56:28.987046Z","title":"Rfnet: Region-aware fusion network for incomplete multi-modal brain tumor segmentation,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-07-30T18:56:28.987046Z"},"links":{"citing_paper":"/paper/2607.23658"},"observation_digest":"sha256:00f43d9f87849f7eaa1e2296a952af4c89300c255235d996fef08c7961a9a1a8","observation_id":"198ea5bc-6608-4a44-b33e-e00b3294449f","resolution":{"observed_at":"2026-07-30T18:56:28.987046Z","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":"2026-07-30T18:56:29.060584Z","title":"Equivariant multi-modality image fusion,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-07-30T18:56:29.060584Z"},"links":{"citing_paper":"/paper/2607.23658"},"observation_digest":"sha256:85648955f018bcd97a6390d28b19d0892d99b2600263455774bee8e289fd1411","observation_id":"d6bb6700-76b8-44e6-9226-11ca023fe5e6","resolution":{"observed_at":"2026-07-30T18:56:29.060584Z","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":"2026-07-30T18:56:29.103855Z","title":"U-net: Convolutional networks for biomedical image segmentation,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-07-30T18:56:29.103855Z"},"links":{"citing_paper":"/paper/2607.23658"},"observation_digest":"sha256:c0cbbf930b640e3af6f5ef320c60881e57d5a87009fa37704895ec1e2b953bd0","observation_id":"9f968b4c-b0d9-4807-a63c-12abfb5d2a1b","resolution":{"observed_at":"2026-07-30T18:56:29.103855Z","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":"2026-07-30T18:56:29.184897Z","title":"Restormer: Efficient transformer for high-resolution image restoration,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-07-30T18:56:29.184897Z"},"links":{"citing_paper":"/paper/2607.23658"},"observation_digest":"sha256:49f8719d89fa9c53733363617b277534fe0a6c7da5257075d2c00ab7598fcf6a","observation_id":"6b42f882-356e-4603-a4ce-6f8b51589067","resolution":{"observed_at":"2026-07-30T18:56:29.184897Z","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":"2026-07-30T18:56:29.234426Z","title":"Gafusion: Adaptive fusing lidar and camera with multiple guidance for 3d object detection,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-07-30T18:56:29.234426Z"},"links":{"citing_paper":"/paper/2607.23658"},"observation_digest":"sha256:3d9adf2cbc05506fec733bb932ee1603abcafc38d8d1e8549700b14918a117d6","observation_id":"516f219e-15db-40e7-a9e6-29625903f7c3","resolution":{"observed_at":"2026-07-30T18:56:29.234426Z","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":"2026-07-30T18:56:29.408447Z","title":"Event-assisted low-light video object segmentation,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-07-30T18:56:29.408447Z"},"links":{"citing_paper":"/paper/2607.23658"},"observation_digest":"sha256:522c24452ded974fab18ad194a5cf1a60ec2fe1c28f4f8b2c7dee3eca088c375","observation_id":"c26d65a1-8194-4737-9dc0-bb13c800c6b8","resolution":{"observed_at":"2026-07-30T18:56:29.408447Z","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":"2026-07-30T18:56:29.485486Z","title":"Cross-modal implicit relation reasoning and aligning for text-to-image person retrieval,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-07-30T18:56:29.485486Z"},"links":{"citing_paper":"/paper/2607.23658"},"observation_digest":"sha256:28b5b7f6c56b86da338151ea9c6d98388f33237f01d47516b76023c7ff59d91e","observation_id":"a63f6f4b-cd25-4b92-be26-22bf7183a838","resolution":{"observed_at":"2026-07-30T18:56:29.485486Z","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":"2026-07-30T18:56:29.575589Z","title":"See more and know more: Zero-shot point cloud segmentation via multi-modal visual data,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-07-30T18:56:29.575589Z"},"links":{"citing_paper":"/paper/2607.23658"},"observation_digest":"sha256:d1e9bca05a5d03b444433463a2380fd249d3cdaaba5858e38ca84f125d968548","observation_id":"8477a641-4ef5-4fcf-8b7b-3423d1c5fcce","resolution":{"observed_at":"2026-07-30T18:56:29.575589Z","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":"2026-07-30T18:56:29.680808Z","title":"Align before fuse: Vision and language representation learning with momentum distillation,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-07-30T18:56:29.680808Z"},"links":{"citing_paper":"/paper/2607.23658"},"observation_digest":"sha256:fe736346abfd3f0fcb3f70e5d9aff7822a2cae668e550825a59de16194373694","observation_id":"54beb1a3-fbbd-4fdc-8811-e1ebf31efffb","resolution":{"observed_at":"2026-07-30T18:56:29.680808Z","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":"2026-07-30T18:56:29.764765Z","title":"Emerging properties in self-supervised vision transformers,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-07-30T18:56:29.764765Z"},"links":{"citing_paper":"/paper/2607.23658"},"observation_digest":"sha256:6e8498df1afe71e239b05ef5e9d5ea21b4f992f28efa3ee36f6061e177b86827","observation_id":"5803e02f-4954-403a-9d9e-54e0c477841c","resolution":{"observed_at":"2026-07-30T18:56:29.764765Z","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":"2026-07-30T18:56:29.914754Z","title":"Swin transformer: Hierarchical vision transformer using shifted windows,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-07-30T18:56:29.914754Z"},"links":{"citing_paper":"/paper/2607.23658"},"observation_digest":"sha256:7227080aaa766313bab4a7415609f291f3dfb0a38af7edebf789451333c9a57d","observation_id":"d1817295-7759-48d2-a3e8-8496f3c46847","resolution":{"observed_at":"2026-07-30T18:56:29.914754Z","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":"2026-07-30T18:56:29.963248Z","title":"Attention is all you need,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-07-30T18:56:29.963248Z"},"links":{"citing_paper":"/paper/2607.23658"},"observation_digest":"sha256:58c5922aeaa5c410d55cb91ff848df564ce27a51f18859d2698b2f4f14ed0023","observation_id":"3c0b1923-90f7-4fd0-a9b9-e8bf34438350","resolution":{"observed_at":"2026-07-30T18:56:29.963248Z","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":"2026-07-30T18:56:30.050409Z","title":"Wavelet based image fusion techniques—an introduction, review and comparison,","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-07-30T18:56:30.050409Z"},"links":{"citing_paper":"/paper/2607.23658"},"observation_digest":"sha256:9e4b4b1c9d92ec7f6b2a2aa5ea81d0a1dd5bf94bb2392f17f28ce2a368c198aa","observation_id":"1cf30a79-708c-4a06-bc12-977fae695aab","resolution":{"observed_at":"2026-07-30T18:56:30.050409Z","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":"2026-07-30T18:56:30.136344Z","title":"Xnet: Wavelet- based low and high frequency fusion networks for fully-and semi- supervised semantic segmentation of biomedical images,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-07-30T18:56:30.136344Z"},"links":{"citing_paper":"/paper/2607.23658"},"observation_digest":"sha256:3a873cd48f3aa3df47326cc506179862828ad28a49b810c63f7e8646031eac4a","observation_id":"72bb05fc-4478-474a-87a9-876c95a673f0","resolution":{"observed_at":"2026-07-30T18:56:30.136344Z","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":"2026-07-30T18:56:30.229111Z","title":"Simplenet: A simple network for image anomaly detection and localization,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-07-30T18:56:30.229111Z"},"links":{"citing_paper":"/paper/2607.23658"},"observation_digest":"sha256:cd939da69dc20e70b9e677c914469ebbd05ed7cb90bb62da1d8020b00a4992fb","observation_id":"e9e77bb9-c37b-4a5e-b49d-752d1f9ac0ad","resolution":{"observed_at":"2026-07-30T18:56:30.229111Z","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":"2026-07-30T18:56:30.306324Z","title":"Exploring plain vit features for multi-class unsupervised visual anomaly detection,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-07-30T18:56:30.306324Z"},"links":{"citing_paper":"/paper/2607.23658"},"observation_digest":"sha256:4060886a018696125f586f7956f936028c13ea43ad61802ddd0c066313fe7dfe","observation_id":"92f27fa2-d4db-48f7-b266-9cede7b779b3","resolution":{"observed_at":"2026-07-30T18:56:30.306324Z","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":"2026-07-30T18:56:30.399880Z","title":"Anomalydino: Boosting patch-based few-shot anomaly detection with dinov2,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-07-30T18:56:30.399880Z"},"links":{"citing_paper":"/paper/2607.23658"},"observation_digest":"sha256:f7bf1c2f030b3634db2e5f5a521cc4a5307cda9b99f6372496e934bb49cb7a4f","observation_id":"bb5633e5-6331-4218-ad74-ee7745606353","resolution":{"observed_at":"2026-07-30T18:56:30.399880Z","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":"2026-07-30T18:56:30.459379Z","title":"Dinomaly: The less is more philosophy in multi-class unsupervised anomaly detec- tion,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-07-30T18:56:30.459379Z"},"links":{"citing_paper":"/paper/2607.23658"},"observation_digest":"sha256:3067134268636cf74a4fabf8ed352904183bb85bbb3225bda763b240d143f12a","observation_id":"6a277199-a32f-4f14-9388-e937b8dae3cb","resolution":{"observed_at":"2026-07-30T18:56:30.459379Z","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":"2026-07-30T18:56:30.518061Z","title":"On estimation of a probability density function and mode,","venue":null,"work_id":null,"year":1962},"citing_paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-07-30T18:56:30.518061Z"},"links":{"citing_paper":"/paper/2607.23658"},"observation_digest":"sha256:518a5b8f43881cafa768a264002486218274c5911b8e801d70e9dd6b2370f46a","observation_id":"7501e20f-8c0e-4a75-8566-7bd8ec0e5889","resolution":{"observed_at":"2026-07-30T18:56:30.518061Z","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":"2026-07-30T18:56:30.594491Z","title":"Grad-cam: Visual explanations from deep networks via gradient-based localization,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-07-30T18:56:30.594491Z"},"links":{"citing_paper":"/paper/2607.23658"},"observation_digest":"sha256:a1e9bedd5b23f08eda38a174b268bca5ab59130a8aabf5ce7712e4ac6d33b0ee","observation_id":"48f99355-7e36-4016-8cab-70d026f7278b","resolution":{"observed_at":"2026-07-30T18:56:30.594491Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.23658","last_updated":"2026-07-26T13:47:10Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-16T15:13:55.567146Z","submitted_at":"2026-07-26T13:47:10Z","title":"XMatchAD: A Cross-Modal Matching Perspective on Reconstruction-based Anomaly Detection"},"reference_resolution":{"displayed":56,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":56,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":56},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 56 of 56 outbound references and 0 inbound Pith citation observations for arXiv:2607.23658."}