{"as_of":"2026-08-07T23:49:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:9807111bbf8b852cd287d0f2b5d65f972f1d7411ce3385aaaa0f35868f19652f","coverage":[{"denominator":31,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":31,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T22:26:40.829467Z","state":"measured"},{"denominator":31,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":31,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+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/2508.07020/citation-record","integrity":"/paper/2508.07020/integrity","json":"/paper/2508.07020/citation-record.json","paper":"/paper/2508.07020"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2303.08774","last_updated":"2024-03-04T06:01:33Z","snapshot_observed_at":"2026-08-07T07:30:12.213965Z","submitted_at":"2023-03-15T17:15:04Z","title":"GPT-4 Technical Report","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.08774","snapshot_observed_at":"2026-08-05T22:26:40.738840Z","title":"GPT-4 technical report","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.07020","last_updated":"2025-08-09T15:32:22Z","snapshot_observed_at":"2026-08-07T23:09:40.379479Z","submitted_at":"2025-08-09T15:32:22Z","title":"TerraMAE: Learning Spatial-Spectral Representations from Hyperspectral Earth Observation Data via Adaptive Masked Autoencoders","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-05T22:26:40.738840Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2508.07020"},"observation_digest":"sha256:b3097a73cafaf51cb36d97760211eb97ababb25088081a0727bdc1bb233e2dc4","observation_id":"6856a0a3-9925-4b27-856f-48a70440556f","resolution":{"observed_at":"2026-08-05T22:26:40.738840Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.01463","last_updated":"2023-09-26T20:52:46Z","snapshot_observed_at":"2026-08-07T23:09:45.569340Z","submitted_at":"2023-09-26T20:52:46Z","title":"Creating Trustworthy LLMs: Dealing with Hallucinations in Healthcare AI","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.01463","snapshot_observed_at":"2026-08-05T22:26:40.742447Z","title":"Creating trustworthy LLMs: Dealing with hallucinations in healthcare AI","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.07020","last_updated":"2025-08-09T15:32:22Z","snapshot_observed_at":"2026-08-07T23:09:40.379479Z","submitted_at":"2025-08-09T15:32:22Z","title":"TerraMAE: Learning Spatial-Spectral Representations from Hyperspectral Earth Observation Data via Adaptive Masked Autoencoders","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-05T22:26:40.742447Z"},"links":{"cited_paper":"/paper/2311.01463","citing_paper":"/paper/2508.07020"},"observation_digest":"sha256:d51fab37e1292ce7280d980dbc1f31bb1a24ff0d7ec8d1d4107b075ebbfd33d1","observation_id":"041867c6-1d6c-4b4e-80af-ed3416e6a642","resolution":{"observed_at":"2026-08-05T22:26:40.742447Z","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":"2026-08-05T22:26:40.745290Z","title":"Can large language models challenge CNNs in medical image analysis? In IEEE International Conference on Image Processing (ICIP), 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.07020","last_updated":"2025-08-09T15:32:22Z","snapshot_observed_at":"2026-08-07T23:09:40.379479Z","submitted_at":"2025-08-09T15:32:22Z","title":"TerraMAE: Learning Spatial-Spectral Representations from Hyperspectral Earth Observation Data via Adaptive Masked Autoencoders","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-05T22:26:40.745290Z"},"links":{"citing_paper":"/paper/2508.07020"},"observation_digest":"sha256:d3dbdfb72988570cb6790324ec055bba2abf25eb51ac044d9cb8c3e492e8e284","observation_id":"07bb3db2-8014-464a-b326-b05f0a479425","resolution":{"observed_at":"2026-08-05T22:26:40.745290Z","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":"2026-08-05T22:26:40.748226Z","title":"Al-Yasriy","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2508.07020","last_updated":"2025-08-09T15:32:22Z","snapshot_observed_at":"2026-08-07T23:09:40.379479Z","submitted_at":"2025-08-09T15:32:22Z","title":"TerraMAE: Learning Spatial-Spectral Representations from Hyperspectral Earth Observation Data via Adaptive Masked Autoencoders","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-05T22:26:40.748226Z"},"links":{"citing_paper":"/paper/2508.07020"},"observation_digest":"sha256:b0c9def21fe6cb80f20c7bd2343a54bc2f22d030fee1c80f543869df80c55cd6","observation_id":"54e6cc2b-8235-44c6-a76e-5c7bf727f12d","resolution":{"observed_at":"2026-08-05T22:26:40.748226Z","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":"2026-08-05T22:26:40.751170Z","title":"A framework to assess clini- cal safety and hallucination rates of LLMs for medical text summarisation","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.07020","last_updated":"2025-08-09T15:32:22Z","snapshot_observed_at":"2026-08-07T23:09:40.379479Z","submitted_at":"2025-08-09T15:32:22Z","title":"TerraMAE: Learning Spatial-Spectral Representations from Hyperspectral Earth Observation Data via Adaptive Masked Autoencoders","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-05T22:26:40.751170Z"},"links":{"citing_paper":"/paper/2508.07020"},"observation_digest":"sha256:191929e7b8b17138dac1a846c9c2d792fd5e6de23980847fba81fb2859d12d33","observation_id":"dc7f0871-c204-460b-8a2b-2600d45773f5","resolution":{"observed_at":"2026-08-05T22:26:40.751170Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.15040","last_updated":"2025-02-20T20:55:34Z","snapshot_observed_at":"2026-08-07T23:09:29.279302Z","submitted_at":"2025-02-20T20:55:34Z","title":"Reducing Hallucinations of Medical Multimodal Large Language Models with Visual Retrieval-Augmented Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.15040","snapshot_observed_at":"2026-08-05T22:26:40.753852Z","title":"Reducing hallucinations of medical multi- modal large language models with visual retrieval-augmented generation","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.07020","last_updated":"2025-08-09T15:32:22Z","snapshot_observed_at":"2026-08-07T23:09:40.379479Z","submitted_at":"2025-08-09T15:32:22Z","title":"TerraMAE: Learning Spatial-Spectral Representations from Hyperspectral Earth Observation Data via Adaptive Masked Autoencoders","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-05T22:26:40.753852Z"},"links":{"cited_paper":"/paper/2502.15040","citing_paper":"/paper/2508.07020"},"observation_digest":"sha256:78a4e40558980e6e740c2b9c6d15f481c9e688dd36ff1e9b56c207178777e6f9","observation_id":"7dad49f6-0ca2-4643-84ca-8c9a1f8d1e05","resolution":{"observed_at":"2026-08-05T22:26:40.753852Z","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":"2026-08-05T22:26:40.756897Z","title":"Breaking the shield: Vulnerabilities in content moderation for multi- modal language models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.07020","last_updated":"2025-08-09T15:32:22Z","snapshot_observed_at":"2026-08-07T23:09:40.379479Z","submitted_at":"2025-08-09T15:32:22Z","title":"TerraMAE: Learning Spatial-Spectral Representations from Hyperspectral Earth Observation Data via Adaptive Masked Autoencoders","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-05T22:26:40.756897Z"},"links":{"citing_paper":"/paper/2508.07020"},"observation_digest":"sha256:08cd2b426def15972fa9d86f618c1bbe73f76f2c6fa78cc00c0dc8edb624d5d6","observation_id":"7f3a3373-044d-4cc6-9ca0-d03c960bf095","resolution":{"observed_at":"2026-08-05T22:26:40.756897Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.19061","last_updated":"2025-08-20T14:24:25Z","snapshot_observed_at":"2026-08-07T15:58:54.203601Z","submitted_at":"2025-04-27T00:39:12Z","title":"Hallucinations and Key Information Extraction in Medical Texts: A Comprehensive Assessment of Open-Source Large Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.19061","snapshot_observed_at":"2026-08-05T22:26:40.759713Z","title":"Hallucinations and key information extraction in med- ical texts: A comprehensive assessment of open-source large language models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.07020","last_updated":"2025-08-09T15:32:22Z","snapshot_observed_at":"2026-08-07T23:09:40.379479Z","submitted_at":"2025-08-09T15:32:22Z","title":"TerraMAE: Learning Spatial-Spectral Representations from Hyperspectral Earth Observation Data via Adaptive Masked Autoencoders","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-05T22:26:40.759713Z"},"links":{"cited_paper":"/paper/2504.19061","citing_paper":"/paper/2508.07020"},"observation_digest":"sha256:2419719a387e37441f59be751f7203da75dbd584ac309b8ca4e5956dca94680f","observation_id":"bc5692b7-7986-471c-af9f-2d399a6117df","resolution":{"observed_at":"2026-08-05T22:26:40.759713Z","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":"2026-08-05T22:26:40.762467Z","title":"Potential of ChatGPT and GPT-4 for data mining of free-text CT reports on lung cancer","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.07020","last_updated":"2025-08-09T15:32:22Z","snapshot_observed_at":"2026-08-07T23:09:40.379479Z","submitted_at":"2025-08-09T15:32:22Z","title":"TerraMAE: Learning Spatial-Spectral Representations from Hyperspectral Earth Observation Data via Adaptive Masked Autoencoders","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-05T22:26:40.762467Z"},"links":{"citing_paper":"/paper/2508.07020"},"observation_digest":"sha256:00ee4747f2e8a2d43d10d43091fa2db668469342351e8cfff64a7dad4d5476f5","observation_id":"ed5d554b-7f57-45c2-a527-163702b4bb99","resolution":{"observed_at":"2026-08-05T22:26:40.762467Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.02730","last_updated":"2024-07-03T00:59:03Z","snapshot_observed_at":"2026-08-07T23:09:29.141024Z","submitted_at":"2024-07-03T00:59:03Z","title":"MedVH: Towards Systematic Evaluation of Hallucination for Large Vision Language Models in the Medical Context","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.02730","snapshot_observed_at":"2026-08-05T22:26:40.765049Z","title":"Medvh: Towards systematic evaluation of hallucination for large vision language models in the medical context","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.07020","last_updated":"2025-08-09T15:32:22Z","snapshot_observed_at":"2026-08-07T23:09:40.379479Z","submitted_at":"2025-08-09T15:32:22Z","title":"TerraMAE: Learning Spatial-Spectral Representations from Hyperspectral Earth Observation Data via Adaptive Masked Autoencoders","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-05T22:26:40.765049Z"},"links":{"cited_paper":"/paper/2407.02730","citing_paper":"/paper/2508.07020"},"observation_digest":"sha256:b3f1e4727c3751d56d79fb418b5e353185c5e159bed3a96db36209feacc1bfc0","observation_id":"132dd4a7-8acd-489d-ae79-bd02b2a8786b","resolution":{"observed_at":"2026-08-05T22:26:40.765049Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.15264","last_updated":"2025-01-31T03:15:34Z","snapshot_observed_at":"2026-08-07T23:09:26.948517Z","submitted_at":"2024-12-17T02:07:33Z","title":"ReXTrust: A Model for Fine-Grained Hallucination Detection in AI-Generated Radiology Reports","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.15264","snapshot_observed_at":"2026-08-05T22:26:40.767751Z","title":"Rextrust: A model for fine-grained hallucina- tion detection in AI-generated radiology reports","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.07020","last_updated":"2025-08-09T15:32:22Z","snapshot_observed_at":"2026-08-07T23:09:40.379479Z","submitted_at":"2025-08-09T15:32:22Z","title":"TerraMAE: Learning Spatial-Spectral Representations from Hyperspectral Earth Observation Data via Adaptive Masked Autoencoders","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-05T22:26:40.767751Z"},"links":{"cited_paper":"/paper/2412.15264","citing_paper":"/paper/2508.07020"},"observation_digest":"sha256:d35ebf7e4fa45221e93778e3f882ec485890d6331c2d92e1a6d10a41e6ee01fe","observation_id":"9e0df14e-efb7-4a17-a8f1-1ea7867b6703","resolution":{"observed_at":"2026-08-05T22:26:40.767751Z","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":"2026-08-05T22:26:40.770776Z","title":"FactCheXcker: Miti- gating measurement hallucinations in chest X-ray report gen- eration models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.07020","last_updated":"2025-08-09T15:32:22Z","snapshot_observed_at":"2026-08-07T23:09:40.379479Z","submitted_at":"2025-08-09T15:32:22Z","title":"TerraMAE: Learning Spatial-Spectral Representations from Hyperspectral Earth Observation Data via Adaptive Masked Autoencoders","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-05T22:26:40.770776Z"},"links":{"citing_paper":"/paper/2508.07020"},"observation_digest":"sha256:cb73012246f5f5bc8ec1ed3078619a67cc06c035b7d691d513e478090e55fc56","observation_id":"8958df86-8678-4615-90ad-7fe812929d83","resolution":{"observed_at":"2026-08-05T22:26:40.770776Z","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":"2026-08-05T22:26:40.773775Z","title":"DALL-M: Context-aware clinical data augmentation with large language models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.07020","last_updated":"2025-08-09T15:32:22Z","snapshot_observed_at":"2026-08-07T23:09:40.379479Z","submitted_at":"2025-08-09T15:32:22Z","title":"TerraMAE: Learning Spatial-Spectral Representations from Hyperspectral Earth Observation Data via Adaptive Masked Autoencoders","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-05T22:26:40.773775Z"},"links":{"citing_paper":"/paper/2508.07020"},"observation_digest":"sha256:415bb3f1ed0a192ec303f198987cbf59f3a3ccce06e8d8ab444a1933920d9990","observation_id":"8ffec8df-7571-41d2-a039-ba8b6b047736","resolution":{"observed_at":"2026-08-05T22:26:40.773775Z","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":"2026-08-05T22:26:40.776534Z","title":"Evaluation of SVM performance in the detection of lung cancer in marked ct scan dataset","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.07020","last_updated":"2025-08-09T15:32:22Z","snapshot_observed_at":"2026-08-07T23:09:40.379479Z","submitted_at":"2025-08-09T15:32:22Z","title":"TerraMAE: Learning Spatial-Spectral Representations from Hyperspectral Earth Observation Data via Adaptive Masked Autoencoders","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-05T22:26:40.776534Z"},"links":{"citing_paper":"/paper/2508.07020"},"observation_digest":"sha256:1ac7f460d6308324ac85c95cc6fe0169101e63e21ffcc1ac24ff7c9dd51a87aa","observation_id":"4e10332b-4cec-4b12-b2d3-c47d2476c7b9","resolution":{"observed_at":"2026-08-05T22:26:40.776534Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.01075","last_updated":"2025-07-24T02:11:36Z","snapshot_observed_at":"2026-08-07T23:09:25.264669Z","submitted_at":"2025-03-03T00:33:04Z","title":"Tackling Hallucination from Conditional Models for Medical Image Reconstruction with DynamicDPS","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.01075","snapshot_observed_at":"2026-08-05T22:26:40.779364Z","title":"Tackling hallucination from conditional models for medical image reconstruction with dynamicdps","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.07020","last_updated":"2025-08-09T15:32:22Z","snapshot_observed_at":"2026-08-07T23:09:40.379479Z","submitted_at":"2025-08-09T15:32:22Z","title":"TerraMAE: Learning Spatial-Spectral Representations from Hyperspectral Earth Observation Data via Adaptive Masked Autoencoders","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-05T22:26:40.779364Z"},"links":{"cited_paper":"/paper/2503.01075","citing_paper":"/paper/2508.07020"},"observation_digest":"sha256:0fb4531edac9688073d1edc5759449d271fe55570d2a30bbe38f60aaf200ef64","observation_id":"c047cc7c-2da1-4ca4-b7a2-0066f399c1f3","resolution":{"observed_at":"2026-08-05T22:26:40.779364Z","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":"2026-08-05T22:26:40.782185Z","title":"Medical hallucinations in foundation models and their impact on healthcare","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.07020","last_updated":"2025-08-09T15:32:22Z","snapshot_observed_at":"2026-08-07T23:09:40.379479Z","submitted_at":"2025-08-09T15:32:22Z","title":"TerraMAE: Learning Spatial-Spectral Representations from Hyperspectral Earth Observation Data via Adaptive Masked Autoencoders","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-05T22:26:40.782185Z"},"links":{"citing_paper":"/paper/2508.07020"},"observation_digest":"sha256:0934bb02c04a9de79ce1bd4b0f55d054bf047ca76e148650150006eab389238e","observation_id":"5124e28e-58b2-4dcd-8a47-ad25a2f9b67b","resolution":{"observed_at":"2026-08-05T22:26:40.782185Z","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":"2026-08-05T22:26:40.785237Z","title":"Mitigating structural hallucination in LLMs with local diffusion","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.07020","last_updated":"2025-08-09T15:32:22Z","snapshot_observed_at":"2026-08-07T23:09:40.379479Z","submitted_at":"2025-08-09T15:32:22Z","title":"TerraMAE: Learning Spatial-Spectral Representations from Hyperspectral Earth Observation Data via Adaptive Masked Autoencoders","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-05T22:26:40.785237Z"},"links":{"citing_paper":"/paper/2508.07020"},"observation_digest":"sha256:7e71929eab17b00ae79b1b15bb78780274ba9026fea44e1084dfb6a2487d6098","observation_id":"b0c198ee-c064-4058-8cc9-479304a01135","resolution":{"observed_at":"2026-08-05T22:26:40.785237Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.11490","last_updated":"2024-03-18T03:41:09Z","snapshot_observed_at":"2026-08-07T23:09:30.151859Z","submitted_at":"2023-05-19T07:44:39Z","title":"LLM-CXR: Instruction-Finetuned LLM for CXR Image Understanding and Generation","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.11490","snapshot_observed_at":"2026-08-05T22:26:40.788287Z","title":"LLM-CXR: instruction- finetuned LLM for CXR image understanding and generation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.07020","last_updated":"2025-08-09T15:32:22Z","snapshot_observed_at":"2026-08-07T23:09:40.379479Z","submitted_at":"2025-08-09T15:32:22Z","title":"TerraMAE: Learning Spatial-Spectral Representations from Hyperspectral Earth Observation Data via Adaptive Masked Autoencoders","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-05T22:26:40.788287Z"},"links":{"cited_paper":"/paper/2305.11490","citing_paper":"/paper/2508.07020"},"observation_digest":"sha256:8b5ec8b8317c0d92a2ae1b2e71a0ffbc3b71053b950e66a27cba142496da2a36","observation_id":"58d8db1c-e1fd-4c9e-9f28-cd397d6dcac0","resolution":{"observed_at":"2026-08-05T22:26:40.788287Z","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":"2026-08-05T22:26:40.791337Z","title":"Towards a holistic framework for multimodal LLM in 3D brain CT radiology report generation","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.07020","last_updated":"2025-08-09T15:32:22Z","snapshot_observed_at":"2026-08-07T23:09:40.379479Z","submitted_at":"2025-08-09T15:32:22Z","title":"TerraMAE: Learning Spatial-Spectral Representations from Hyperspectral Earth Observation Data via Adaptive Masked Autoencoders","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-05T22:26:40.791337Z"},"links":{"citing_paper":"/paper/2508.07020"},"observation_digest":"sha256:218ff341d5dfecfa5986d9113c87cb0c2da691f6e07ab3336f719c174cd8c73a","observation_id":"fbc80399-b4b3-4d82-974b-1ba64bee1aab","resolution":{"observed_at":"2026-08-05T22:26:40.791337Z","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":"2026-08-05T22:26:40.794261Z","title":"Prompt-guided generation of structured chest X-ray report using a pre-trained LLM","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.07020","last_updated":"2025-08-09T15:32:22Z","snapshot_observed_at":"2026-08-07T23:09:40.379479Z","submitted_at":"2025-08-09T15:32:22Z","title":"TerraMAE: Learning Spatial-Spectral Representations from Hyperspectral Earth Observation Data via Adaptive Masked Autoencoders","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-05T22:26:40.794261Z"},"links":{"citing_paper":"/paper/2508.07020"},"observation_digest":"sha256:8854849ee2f446cf7d3085696f6c946ba5e5805b8f9064f1d16df9988244b414","observation_id":"f42509ce-0b02-44dc-8118-86ac967f31d8","resolution":{"observed_at":"2026-08-05T22:26:40.794261Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.10683","last_updated":"2024-07-15T12:59:03Z","snapshot_observed_at":"2026-08-07T23:09:26.127639Z","submitted_at":"2024-07-15T12:59:03Z","title":"Addressing Image Hallucination in Text-to-Image Generation through Factual Image Retrieval","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.10683","snapshot_observed_at":"2026-08-05T22:26:40.797542Z","title":"Addressing image hal- lucination in text-to-image generation through factual image retrieval","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.07020","last_updated":"2025-08-09T15:32:22Z","snapshot_observed_at":"2026-08-07T23:09:40.379479Z","submitted_at":"2025-08-09T15:32:22Z","title":"TerraMAE: Learning Spatial-Spectral Representations from Hyperspectral Earth Observation Data via Adaptive Masked Autoencoders","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-05T22:26:40.797542Z"},"links":{"cited_paper":"/paper/2407.10683","citing_paper":"/paper/2508.07020"},"observation_digest":"sha256:04106e6e8b0f6ea49126728ddff85d57c8127110d162ea9b0c2bbe5f20b19768","observation_id":"45d012b7-ae69-4ac9-835b-be873d46a7be","resolution":{"observed_at":"2026-08-05T22:26:40.797542Z","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":"2026-08-05T22:26:40.800711Z","title":"Indiana university chest x- ray","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2508.07020","last_updated":"2025-08-09T15:32:22Z","snapshot_observed_at":"2026-08-07T23:09:40.379479Z","submitted_at":"2025-08-09T15:32:22Z","title":"TerraMAE: Learning Spatial-Spectral Representations from Hyperspectral Earth Observation Data via Adaptive Masked Autoencoders","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-05T22:26:40.800711Z"},"links":{"citing_paper":"/paper/2508.07020"},"observation_digest":"sha256:948d47f69531134e835824f5e30e754b62cb8e8487443c58bee0b26017b68b12","observation_id":"ad5f96c1-ab70-4a39-b9ed-9f6300a435c6","resolution":{"observed_at":"2026-08-05T22:26:40.800711Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.15343","last_updated":"2023-10-14T17:04:12Z","snapshot_observed_at":"2026-08-07T02:36:54.737484Z","submitted_at":"2023-07-28T06:43:04Z","title":"Med-HALT: Medical Domain Hallucination Test for Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.15343","snapshot_observed_at":"2026-08-05T22:26:40.803883Z","title":"Med-HALT: Medical domain hallucination test for LLMs","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.07020","last_updated":"2025-08-09T15:32:22Z","snapshot_observed_at":"2026-08-07T23:09:40.379479Z","submitted_at":"2025-08-09T15:32:22Z","title":"TerraMAE: Learning Spatial-Spectral Representations from Hyperspectral Earth Observation Data via Adaptive Masked Autoencoders","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-05T22:26:40.803883Z"},"links":{"cited_paper":"/paper/2307.15343","citing_paper":"/paper/2508.07020"},"observation_digest":"sha256:5b7d89b2ff079c647a5cdf5a979c17c855a2627450c4e21c49811a29f9002a28","observation_id":"b28f2f61-f351-406d-ad89-f2f0183af618","resolution":{"observed_at":"2026-08-05T22:26:40.803883Z","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":"2026-08-05T22:26:40.806977Z","title":"Leveraging large language models to foster equity in health- care","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.07020","last_updated":"2025-08-09T15:32:22Z","snapshot_observed_at":"2026-08-07T23:09:40.379479Z","submitted_at":"2025-08-09T15:32:22Z","title":"TerraMAE: Learning Spatial-Spectral Representations from Hyperspectral Earth Observation Data via Adaptive Masked Autoencoders","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-05T22:26:40.806977Z"},"links":{"citing_paper":"/paper/2508.07020"},"observation_digest":"sha256:a128f2209a22585cbec63a8a4e0f0218df6ff204bf23409f8fc74cfdefb3ceaa","observation_id":"5d1b0511-ac37-4f50-b960-ef756ea44bdc","resolution":{"observed_at":"2026-08-05T22:26:40.806977Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.11805","last_updated":"2025-05-09T21:04:06Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-12-19T02:39:27Z","title":"Gemini: A Family of Highly Capable Multimodal Models","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.11805","snapshot_observed_at":"2026-08-05T22:26:40.810232Z","title":"Gemini: a family of highly capable multimodal models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.07020","last_updated":"2025-08-09T15:32:22Z","snapshot_observed_at":"2026-08-07T23:09:40.379479Z","submitted_at":"2025-08-09T15:32:22Z","title":"TerraMAE: Learning Spatial-Spectral Representations from Hyperspectral Earth Observation Data via Adaptive Masked Autoencoders","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-05T22:26:40.810232Z"},"links":{"cited_paper":"/paper/2312.11805","citing_paper":"/paper/2508.07020"},"observation_digest":"sha256:f9da7093094cd64958ab2e809d5637fc7b86f0ea2451bc88fe6a31023746c620","observation_id":"7fccf8ea-dc5a-4a14-b68e-9b1678dc65ec","resolution":{"observed_at":"2026-08-05T22:26:40.810232Z","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":"2026-08-05T22:26:40.813373Z","title":"Hallucination index: An image quality metric for gener- ative reconstruction models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.07020","last_updated":"2025-08-09T15:32:22Z","snapshot_observed_at":"2026-08-07T23:09:40.379479Z","submitted_at":"2025-08-09T15:32:22Z","title":"TerraMAE: Learning Spatial-Spectral Representations from Hyperspectral Earth Observation Data via Adaptive Masked Autoencoders","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-05T22:26:40.813373Z"},"links":{"citing_paper":"/paper/2508.07020"},"observation_digest":"sha256:29a47c266730b3a5849d85b0707ab7da1386deb331bf5ceebc91c742898cb765","observation_id":"0e1a827a-adea-4f00-840a-4e4afe52e54e","resolution":{"observed_at":"2026-08-05T22:26:40.813373Z","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":"2026-08-05T22:26:40.816606Z","title":"On large visual language models for medical imaging analysis: An empirical study","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.07020","last_updated":"2025-08-09T15:32:22Z","snapshot_observed_at":"2026-08-07T23:09:40.379479Z","submitted_at":"2025-08-09T15:32:22Z","title":"TerraMAE: Learning Spatial-Spectral Representations from Hyperspectral Earth Observation Data via Adaptive Masked Autoencoders","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-05T22:26:40.816606Z"},"links":{"citing_paper":"/paper/2508.07020"},"observation_digest":"sha256:4185e024797c5f733300f6492deb9e53c0b3283bedc2f82676ef0fa24e8557de","observation_id":"071568f0-6a16-46fc-bf6a-bbdba9341b2d","resolution":{"observed_at":"2026-08-05T22:26:40.816606Z","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":"2026-08-05T22:26:40.819700Z","title":"Rodney Long, and George R","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2508.07020","last_updated":"2025-08-09T15:32:22Z","snapshot_observed_at":"2026-08-07T23:09:40.379479Z","submitted_at":"2025-08-09T15:32:22Z","title":"TerraMAE: Learning Spatial-Spectral Representations from Hyperspectral Earth Observation Data via Adaptive Masked Autoencoders","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-05T22:26:40.819700Z"},"links":{"citing_paper":"/paper/2508.07020"},"observation_digest":"sha256:432f1752f30049519b5a70eb5e9cd91fa0a5f2467cadb8ea61d2d67a31eb08d4","observation_id":"900b83b3-9e7e-4f39-a214-8c12e18a2922","resolution":{"observed_at":"2026-08-05T22:26:40.819700Z","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":"2026-08-05T22:26:40.823016Z","title":"Med-hvl: Au- tomatic medical domain hallucination evaluation for large vision-language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.07020","last_updated":"2025-08-09T15:32:22Z","snapshot_observed_at":"2026-08-07T23:09:40.379479Z","submitted_at":"2025-08-09T15:32:22Z","title":"TerraMAE: Learning Spatial-Spectral Representations from Hyperspectral Earth Observation Data via Adaptive Masked Autoencoders","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-05T22:26:40.823016Z"},"links":{"citing_paper":"/paper/2508.07020"},"observation_digest":"sha256:76a33c37d3918ab7cd34a815981c0e224ffed68ff83093be49bcf9fbe1899a34","observation_id":"e2957301-ec11-4dc4-b42e-438cac3c0c06","resolution":{"observed_at":"2026-08-05T22:26:40.823016Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.00299","last_updated":"2024-11-16T04:37:48Z","snapshot_observed_at":"2026-08-07T23:09:28.028516Z","submitted_at":"2024-11-01T01:38:42Z","title":"RadFlag: A Black-Box Hallucination Detection Method for Medical Vision Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.00299","snapshot_observed_at":"2026-08-05T22:26:40.826225Z","title":"Radflag: A black-box hallucination detection method for medical vision language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.07020","last_updated":"2025-08-09T15:32:22Z","snapshot_observed_at":"2026-08-07T23:09:40.379479Z","submitted_at":"2025-08-09T15:32:22Z","title":"TerraMAE: Learning Spatial-Spectral Representations from Hyperspectral Earth Observation Data via Adaptive Masked Autoencoders","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-05T22:26:40.826225Z"},"links":{"cited_paper":"/paper/2411.00299","citing_paper":"/paper/2508.07020"},"observation_digest":"sha256:e3df86758799615360e7c619a5006ba5d5867c974eeffbb10819c7937f9c26ba","observation_id":"84d671a0-3789-48b0-b0d7-78efdf937a6e","resolution":{"observed_at":"2026-08-05T22:26:40.826225Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.18947","last_updated":"2025-03-28T23:37:45Z","snapshot_observed_at":"2026-08-07T23:09:22.936297Z","submitted_at":"2024-12-25T16:51:29Z","title":"MedHallBench: A New Benchmark for Assessing Hallucination in Medical Large Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.18947","snapshot_observed_at":"2026-08-05T22:26:40.829467Z","title":"MedHallBench: A new bench- mark for assessing hallucination in medical large language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.07020","last_updated":"2025-08-09T15:32:22Z","snapshot_observed_at":"2026-08-07T23:09:40.379479Z","submitted_at":"2025-08-09T15:32:22Z","title":"TerraMAE: Learning Spatial-Spectral Representations from Hyperspectral Earth Observation Data via Adaptive Masked Autoencoders","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-05T22:26:40.829467Z"},"links":{"cited_paper":"/paper/2412.18947","citing_paper":"/paper/2508.07020"},"observation_digest":"sha256:6db0dfb13a8c25fec8461eb3160273030cd54f2010121d0a88b8f3c26a327b4b","observation_id":"038607a1-13e2-41aa-a690-ab5f2d7550b7","resolution":{"observed_at":"2026-08-05T22:26:40.829467Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2508.07020","last_updated":"2025-08-09T15:32:22Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-07T23:09:40.379479Z","submitted_at":"2025-08-09T15:32:22Z","title":"TerraMAE: Learning Spatial-Spectral Representations from Hyperspectral Earth Observation Data via Adaptive Masked Autoencoders"},"reference_resolution":{"displayed":31,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":31,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":31},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 31 of 31 outbound references and 0 inbound Pith citation observations for arXiv:2508.07020."}