{"as_of":"2026-08-16T04:44:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:68adde4ac22c3b819c3135856c565a78d84df4b3abd1de6bdf3965b994d95dad","coverage":[{"denominator":51,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":51,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-14T04:32:16.104203Z","state":"measured"},{"denominator":51,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":51,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-15T06:32:42.880941+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/2608.08713/citation-record","integrity":"/paper/2608.08713/integrity","json":"/paper/2608.08713/citation-record.json","paper":"/paper/2608.08713"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:32:18.163535Z","title":"Radiologists’ variation of time to read across different procedure types,","venue":null,"work_id":"d68885cb-e81d-414d-8b1c-0771f8598215","year":2017},"citing_paper":{"arxiv_id":"2608.08713","last_updated":"2026-08-09T13:57:50Z","snapshot_observed_at":"2026-08-14T22:24:17.619964Z","submitted_at":"2026-08-09T13:57:50Z","title":"Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-14T04:32:15.802971Z"},"links":{"citing_paper":"/paper/2608.08713"},"observation_digest":"sha256:3c5e4c159da8445973d8c60349e774a3859f846c825ba87c5430e67fe763ca20","observation_id":"5b50e838-5ab6-4da8-ac50-fa9cd4323436","resolution":{"observed_at":"2026-08-14T04:32:18.170409Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.04449","last_updated":"2024-09-20T17:17:43Z","snapshot_observed_at":"2026-08-12T23:48:25.362189Z","submitted_at":"2024-06-06T19:12:41Z","title":"MAIRA-2: Grounded Radiology Report Generation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.04449","snapshot_observed_at":"2026-08-14T04:32:15.808564Z","title":"Maira-2: Grounded radiology report generation,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.08713","last_updated":"2026-08-09T13:57:50Z","snapshot_observed_at":"2026-08-14T22:24:17.619964Z","submitted_at":"2026-08-09T13:57:50Z","title":"Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-14T04:32:15.808564Z"},"links":{"cited_paper":"/paper/2406.04449","citing_paper":"/paper/2608.08713"},"observation_digest":"sha256:94b234f38d136a343a2b5f8fc0a6da311566a86a8c697cf724fbfec241588981","observation_id":"6c6cdbf4-3ad5-4f1f-8d3e-5f9fe67a749f","resolution":{"observed_at":"2026-08-14T04:32:15.808564Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2601.17151","last_updated":"2026-07-29T22:14:05Z","snapshot_observed_at":"2026-08-10T03:28:27.905833Z","submitted_at":"2026-01-23T20:14:21Z","title":"Scaling medical imaging report generation with multimodal reinforcement learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2601.17151","snapshot_observed_at":"2026-08-14T04:32:15.820464Z","title":"Scaling medical imaging re- port generation with multimodal reinforcement learning,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.08713","last_updated":"2026-08-09T13:57:50Z","snapshot_observed_at":"2026-08-14T22:24:17.619964Z","submitted_at":"2026-08-09T13:57:50Z","title":"Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-14T04:32:15.820464Z"},"links":{"cited_paper":"/paper/2601.17151","citing_paper":"/paper/2608.08713"},"observation_digest":"sha256:cd4dcea98adb1ef07b39ae03770a45d7e9d426f705cc64f5a825cc3d3c5a7f45","observation_id":"9b43c96b-10c7-467b-86af-b2704534502f","resolution":{"observed_at":"2026-08-14T04:32:15.820464Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:32:18.140949Z","title":"Visual instruction tuning,","venue":null,"work_id":"2ea77414-5011-4d5e-b235-f8034cb7ce45","year":2023},"citing_paper":{"arxiv_id":"2608.08713","last_updated":"2026-08-09T13:57:50Z","snapshot_observed_at":"2026-08-14T22:24:17.619964Z","submitted_at":"2026-08-09T13:57:50Z","title":"Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-14T04:32:15.826154Z"},"links":{"citing_paper":"/paper/2608.08713"},"observation_digest":"sha256:44bdb8e66713868e42cc90875afbad2499f0c10702b61f7aea126c509c451607","observation_id":"0da43759-fabd-4a2d-ab16-434891d9d6e5","resolution":{"observed_at":"2026-08-14T04:32:18.146845Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:32:15.832359Z","title":"Compre- hensive language-image pre-training for 3d medical image understanding,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.08713","last_updated":"2026-08-09T13:57:50Z","snapshot_observed_at":"2026-08-14T22:24:17.619964Z","submitted_at":"2026-08-09T13:57:50Z","title":"Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-14T04:32:15.832359Z"},"links":{"citing_paper":"/paper/2608.08713"},"observation_digest":"sha256:8924bc13904cc46ce92ca433a6315d186aafc70397a9b01c5717e84606c30ffa","observation_id":"9fe27d13-250e-4a74-9e7f-d199cd3500b2","resolution":{"observed_at":"2026-08-14T04:32:15.832359Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.00578","last_updated":"2024-03-31T06:55:12Z","snapshot_observed_at":"2026-08-13T19:26:05.889698Z","submitted_at":"2024-03-31T06:55:12Z","title":"M3D: Advancing 3D Medical Image Analysis with Multi-Modal Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.00578","snapshot_observed_at":"2026-08-14T04:32:15.838226Z","title":"M3d: Advancing 3d medical image analysis with multi-modal large language models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.08713","last_updated":"2026-08-09T13:57:50Z","snapshot_observed_at":"2026-08-14T22:24:17.619964Z","submitted_at":"2026-08-09T13:57:50Z","title":"Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-14T04:32:15.838226Z"},"links":{"cited_paper":"/paper/2404.00578","citing_paper":"/paper/2608.08713"},"observation_digest":"sha256:a4626a888c214b074f197d326af2f3bde98b4efbc2e991f341395cfccbb0b8b2","observation_id":"ecc433c6-e8e9-4b99-a967-8151a028bf13","resolution":{"observed_at":"2026-08-14T04:32:15.838226Z","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":"2026-08-14T04:32:15.844845Z","title":"Generalist foundation models from a multimodal dataset for 3D computed tomography,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.08713","last_updated":"2026-08-09T13:57:50Z","snapshot_observed_at":"2026-08-14T22:24:17.619964Z","submitted_at":"2026-08-09T13:57:50Z","title":"Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-14T04:32:15.844845Z"},"links":{"citing_paper":"/paper/2608.08713"},"observation_digest":"sha256:88df49b74bb035cd3d1f703d21f38ccadec1480f3888aaf0ae5080d260f247cd","observation_id":"93207e8d-7e49-4ca3-93ba-e63e64564a35","resolution":{"observed_at":"2026-08-14T04:32:15.844845Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:32:18.063137Z","title":"Merlin: A computed tomography vision-language foundation model and dataset,","venue":null,"work_id":"0b6e4903-b58a-43f8-a340-89e79a1cf718","year":2026},"citing_paper":{"arxiv_id":"2608.08713","last_updated":"2026-08-09T13:57:50Z","snapshot_observed_at":"2026-08-14T22:24:17.619964Z","submitted_at":"2026-08-09T13:57:50Z","title":"Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-14T04:32:15.852936Z"},"links":{"citing_paper":"/paper/2608.08713"},"observation_digest":"sha256:29a695b4ae3b670b8d0b6880ef56b488bffbeab983c8e83df3e1665e41d83360","observation_id":"0e7bf7ae-da18-44ff-bcf5-e9bc19ce2690","resolution":{"observed_at":"2026-08-14T04:32:18.101383Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:32:18.004052Z","title":"Large language model with region- guided referring and grounding for ct report generation,","venue":null,"work_id":"fdb15180-1660-4a0d-bd5c-d6509efe408c","year":2025},"citing_paper":{"arxiv_id":"2608.08713","last_updated":"2026-08-09T13:57:50Z","snapshot_observed_at":"2026-08-14T22:24:17.619964Z","submitted_at":"2026-08-09T13:57:50Z","title":"Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-14T04:32:15.860602Z"},"links":{"citing_paper":"/paper/2608.08713"},"observation_digest":"sha256:113917054a7b2e10d5d3a8055d8c8e4b52235d9366cbb884e9fd6fa3cabcfd8f","observation_id":"3b14066c-2236-4e4e-8694-d0b471766aa6","resolution":{"observed_at":"2026-08-14T04:32:18.009752Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:32:17.976501Z","title":"CT- GRAPH: Hierarchical graph attention network for anatomy-guided ct re- port generation,","venue":null,"work_id":"d1703dec-fd85-49a2-8ee7-d507b0ab19ff","year":2025},"citing_paper":{"arxiv_id":"2608.08713","last_updated":"2026-08-09T13:57:50Z","snapshot_observed_at":"2026-08-14T22:24:17.619964Z","submitted_at":"2026-08-09T13:57:50Z","title":"Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-14T04:32:15.868430Z"},"links":{"citing_paper":"/paper/2608.08713"},"observation_digest":"sha256:d6832b761da1540bface5b137ed6f660de316f5fea75e8cc03435a7cff4630c1","observation_id":"4b134d82-fc31-4d7b-ad88-31f925302ab9","resolution":{"observed_at":"2026-08-14T04:32:17.985323Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2604.05081","last_updated":"2026-05-01T19:02:06Z","snapshot_observed_at":"2026-08-12T16:02:17.136970Z","submitted_at":"2026-04-06T18:35:57Z","title":"MedGemma 1.5 Technical Report","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2604.05081","snapshot_observed_at":"2026-08-14T04:32:15.874083Z","title":"MedGemma 1.5 technical report,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.08713","last_updated":"2026-08-09T13:57:50Z","snapshot_observed_at":"2026-08-14T22:24:17.619964Z","submitted_at":"2026-08-09T13:57:50Z","title":"Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-14T04:32:15.874083Z"},"links":{"cited_paper":"/paper/2604.05081","citing_paper":"/paper/2608.08713"},"observation_digest":"sha256:383f60ad4d328d428a0eb418e2a667a365f69ddf10c6ecc0de8a3a8ada1eab2d","observation_id":"8576a3fe-59b8-4630-91d4-ec6b603187a0","resolution":{"observed_at":"2026-08-14T04:32:15.874083Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:32:17.949766Z","title":"The effect of image resolution on deep learning in radiography,","venue":null,"work_id":"24039408-0a13-4a43-8d48-46cf708a047f","year":2020},"citing_paper":{"arxiv_id":"2608.08713","last_updated":"2026-08-09T13:57:50Z","snapshot_observed_at":"2026-08-14T22:24:17.619964Z","submitted_at":"2026-08-09T13:57:50Z","title":"Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-14T04:32:15.880981Z"},"links":{"citing_paper":"/paper/2608.08713"},"observation_digest":"sha256:cc66fe86d8195480e0a990156985e0c63c4024999632fcedfe2150e5548b95bc","observation_id":"6fe3dd38-0604-4755-bfa2-16cbb2bd19ea","resolution":{"observed_at":"2026-08-14T04:32:17.956082Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:32:17.920691Z","title":"Better tokens for better 3d: Advanc- ing vision-language modeling in 3d medical imaging,","venue":null,"work_id":"1abdd43d-fcee-462d-9aa1-17885f11ad56","year":2026},"citing_paper":{"arxiv_id":"2608.08713","last_updated":"2026-08-09T13:57:50Z","snapshot_observed_at":"2026-08-14T22:24:17.619964Z","submitted_at":"2026-08-09T13:57:50Z","title":"Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-14T04:32:15.886114Z"},"links":{"citing_paper":"/paper/2608.08713"},"observation_digest":"sha256:300e1e10a8358d551a397a1bb91a88326a97826d9864bd83af6228e0787f99d9","observation_id":"09d11c89-eda3-4012-9087-e1fae1bfa30a","resolution":{"observed_at":"2026-08-14T04:32:17.927567Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2606.24570","last_updated":"2026-06-24T15:27:02Z","snapshot_observed_at":"2026-08-12T16:03:05.597749Z","submitted_at":"2026-06-23T13:35:47Z","title":"Jolia: Concept-Level Vision-Language Alignment for 3D CT Contrastive Learning","version":2},"cited_work":{"arxiv_id":"2606.24570","doi":null,"metadata_source":"pith","pith_arxiv_id":"2606.24570","snapshot_observed_at":"2026-08-14T04:32:17.189570Z","title":"Jolia: Concept-Level Vision-Language Alignment for 3D CT Contrastive Learning","venue":"cs.CV","work_id":"20ffd276-2f9e-4b44-b42b-49a1ad721254","year":2026},"citing_paper":{"arxiv_id":"2608.08713","last_updated":"2026-08-09T13:57:50Z","snapshot_observed_at":"2026-08-14T22:24:17.619964Z","submitted_at":"2026-08-09T13:57:50Z","title":"Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-14T04:32:15.891706Z"},"links":{"cited_paper":"/paper/2606.24570","citing_paper":"/paper/2608.08713"},"observation_digest":"sha256:7005e01250370d1699cb0c29cb6bb633dd8354f316d6038889a909c64f957332","observation_id":"92217597-a53a-4444-85e5-6421740a8048","resolution":{"observed_at":"2026-08-14T04:32:17.198321Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:32:17.852823Z","title":"SegVol: Universal and interactive volumetric medical image segmentation,","venue":null,"work_id":"4cef75f7-be5d-482b-aca5-b4fd127fd09f","year":2024},"citing_paper":{"arxiv_id":"2608.08713","last_updated":"2026-08-09T13:57:50Z","snapshot_observed_at":"2026-08-14T22:24:17.619964Z","submitted_at":"2026-08-09T13:57:50Z","title":"Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-14T04:32:15.897465Z"},"links":{"citing_paper":"/paper/2608.08713"},"observation_digest":"sha256:7053536170de24ef845edcead49b605293a68938f705ba7f61a1763d9e81a2d4","observation_id":"9569fe08-2d4b-467c-ba42-9a009c0ef708","resolution":{"observed_at":"2026-08-14T04:32:17.872811Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:32:17.832950Z","title":"Revisiting 2d founda- tion models for scalable 3d medical image classification,","venue":null,"work_id":"5de23c5d-76e2-465f-b598-f691f69330e1","year":2026},"citing_paper":{"arxiv_id":"2608.08713","last_updated":"2026-08-09T13:57:50Z","snapshot_observed_at":"2026-08-14T22:24:17.619964Z","submitted_at":"2026-08-09T13:57:50Z","title":"Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-14T04:32:15.903850Z"},"links":{"citing_paper":"/paper/2608.08713"},"observation_digest":"sha256:9be60aff6f8eaa711f6781a61f577340cf5785c70db92c0fb7be536b615fc9bb","observation_id":"1f53ba16-574c-4d1e-ac99-08867c0b7b44","resolution":{"observed_at":"2026-08-14T04:32:17.839579Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:32:17.811376Z","title":"Towards generalist foundation model for radiology by leveraging web-scale 2d&3d medical data,","venue":null,"work_id":"32eaab5f-0e8c-436d-9ef0-685e30c77d2f","year":2025},"citing_paper":{"arxiv_id":"2608.08713","last_updated":"2026-08-09T13:57:50Z","snapshot_observed_at":"2026-08-14T22:24:17.619964Z","submitted_at":"2026-08-09T13:57:50Z","title":"Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-14T04:32:15.909234Z"},"links":{"citing_paper":"/paper/2608.08713"},"observation_digest":"sha256:dc6954f4e81fa5a5a0875ac53e5dd5e3b78b2b82f56578d2f43646d6b0e60e8a","observation_id":"83807532-a5a6-4ee2-be41-ce08df20fc94","resolution":{"observed_at":"2026-08-14T04:32:17.818758Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:32:17.789174Z","title":"Exploring the design space of 3d mllms for ct report generation,","venue":null,"work_id":"69adc791-aed7-4144-b2e0-d1a216571c7e","year":2025},"citing_paper":{"arxiv_id":"2608.08713","last_updated":"2026-08-09T13:57:50Z","snapshot_observed_at":"2026-08-14T22:24:17.619964Z","submitted_at":"2026-08-09T13:57:50Z","title":"Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-14T04:32:15.920289Z"},"links":{"citing_paper":"/paper/2608.08713"},"observation_digest":"sha256:e67a398f00747c4068999c7c9a2dbedfd6a345220d3b941d6bb6e81b5592020d","observation_id":"911eaef2-1f8f-4050-a74c-b3f8084f3010","resolution":{"observed_at":"2026-08-14T04:32:17.796408Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:32:17.760206Z","title":"Amos: A large-scale abdominal multi-organ benchmark for versatile medical image segmentation,","venue":null,"work_id":"22078591-6b6b-47ea-a2f4-2b2f576b4cc0","year":2022},"citing_paper":{"arxiv_id":"2608.08713","last_updated":"2026-08-09T13:57:50Z","snapshot_observed_at":"2026-08-14T22:24:17.619964Z","submitted_at":"2026-08-09T13:57:50Z","title":"Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-14T04:32:15.927691Z"},"links":{"citing_paper":"/paper/2608.08713"},"observation_digest":"sha256:7b4cb5a4d2cc12c1f323dacc691292959bf8fc062350541e2c0f299c8a875a5e","observation_id":"c17030d1-1a5b-4cd5-9056-3f803c495d97","resolution":{"observed_at":"2026-08-14T04:32:17.767164Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:32:17.738401Z","title":"Primus: Enforcing attention usage for 3d medical image segmentation,","venue":null,"work_id":"fbeaec64-8544-4513-8ebf-d2893e32fd8e","year":2026},"citing_paper":{"arxiv_id":"2608.08713","last_updated":"2026-08-09T13:57:50Z","snapshot_observed_at":"2026-08-14T22:24:17.619964Z","submitted_at":"2026-08-09T13:57:50Z","title":"Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-14T04:32:15.933778Z"},"links":{"citing_paper":"/paper/2608.08713"},"observation_digest":"sha256:6a149a73ab9884137a51f8d352024e721ccbbf0918eee97b6ccbeda568eb2751","observation_id":"6e78ebfd-fd5e-4b9c-80c5-04fec2f76ec7","resolution":{"observed_at":"2026-08-14T04:32:17.745590Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2509.06830","last_updated":"2025-09-08T16:04:12Z","snapshot_observed_at":"2026-08-13T15:40:10.456344Z","submitted_at":"2025-09-08T16:04:12Z","title":"Curia: A Multi-Modal Foundation Model for Radiology","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2509.06830","snapshot_observed_at":"2026-08-14T04:32:15.939958Z","title":"Curia: A multi- modal foundation model for radiology,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.08713","last_updated":"2026-08-09T13:57:50Z","snapshot_observed_at":"2026-08-14T22:24:17.619964Z","submitted_at":"2026-08-09T13:57:50Z","title":"Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-14T04:32:15.939958Z"},"links":{"cited_paper":"/paper/2509.06830","citing_paper":"/paper/2608.08713"},"observation_digest":"sha256:4a07e1966abcef34b44adb33c431dd78c2580a70cd94dfc2c7ce224c0b113421","observation_id":"29145897-4fbc-42ce-8a52-8a5b4916d334","resolution":{"observed_at":"2026-08-14T04:32:15.939958Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.13663","last_updated":"2024-12-19T06:32:26Z","snapshot_observed_at":"2026-08-14T20:02:35.071920Z","submitted_at":"2024-12-18T09:39:44Z","title":"Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.13663","snapshot_observed_at":"2026-08-14T04:32:15.946306Z","title":"Smarter, bet- ter, faster, longer: A modern bidirectional encoder for fast, memory efficient, and long context finetuning and inference,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.08713","last_updated":"2026-08-09T13:57:50Z","snapshot_observed_at":"2026-08-14T22:24:17.619964Z","submitted_at":"2026-08-09T13:57:50Z","title":"Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-14T04:32:15.946306Z"},"links":{"cited_paper":"/paper/2412.13663","citing_paper":"/paper/2608.08713"},"observation_digest":"sha256:410eb3a996ca370d7d0bb020ce4606318a9b2a269c49e984ecd5643c4cf60f8c","observation_id":"8b758449-b0b4-480e-89da-671368d3fb1f","resolution":{"observed_at":"2026-08-14T04:32:15.946306Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2508.10925","last_updated":"2025-08-08T19:24:38Z","snapshot_observed_at":"2026-08-14T02:46:12.121034Z","submitted_at":"2025-08-08T19:24:38Z","title":"gpt-oss-120b & gpt-oss-20b Model Card","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2508.10925","snapshot_observed_at":"2026-08-14T04:32:15.952282Z","title":"gpt-oss-120b & gpt-oss-20b model card,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.08713","last_updated":"2026-08-09T13:57:50Z","snapshot_observed_at":"2026-08-14T22:24:17.619964Z","submitted_at":"2026-08-09T13:57:50Z","title":"Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-14T04:32:15.952282Z"},"links":{"cited_paper":"/paper/2508.10925","citing_paper":"/paper/2608.08713"},"observation_digest":"sha256:534b2eebb75cc21481669720c9acf46dd2432664b0ef1ad4beb3540033c48710","observation_id":"5c53ef90-a8a4-4cfe-ad8f-444480f0006f","resolution":{"observed_at":"2026-08-14T04:32:15.952282Z","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":"2603.15822","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:32:16.773044Z","title":"Beyond the embedding bottleneck: Adaptive retrieval-augmented 3d ct report generation,","venue":null,"work_id":"66a647c4-af4b-4564-8f24-3b69942d5332","year":2026},"citing_paper":{"arxiv_id":"2608.08713","last_updated":"2026-08-09T13:57:50Z","snapshot_observed_at":"2026-08-14T22:24:17.619964Z","submitted_at":"2026-08-09T13:57:50Z","title":"Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-14T04:32:15.957733Z"},"links":{"citing_paper":"/paper/2608.08713"},"observation_digest":"sha256:99a4e68556e3cc75a455f701f3c945ab6bea7bdef111b64b885ff66f951be934","observation_id":"dca9f77b-2fee-4aef-bc26-ab9bd86b3a02","resolution":{"observed_at":"2026-08-14T04:32:16.785767Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2511.21631","last_updated":"2025-11-27T12:16:54Z","snapshot_observed_at":"2026-08-11T14:42:37.584016Z","submitted_at":"2025-11-26T17:59:08Z","title":"Qwen3-VL Technical Report","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2511.21631","snapshot_observed_at":"2026-08-14T04:32:15.962674Z","title":"Qwen3-vl technical report,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.08713","last_updated":"2026-08-09T13:57:50Z","snapshot_observed_at":"2026-08-14T22:24:17.619964Z","submitted_at":"2026-08-09T13:57:50Z","title":"Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-14T04:32:15.962674Z"},"links":{"cited_paper":"/paper/2511.21631","citing_paper":"/paper/2608.08713"},"observation_digest":"sha256:e172c66fd86d554e8f47fbaffe3236169995d855cb1df9ee816b5eae628c7015","observation_id":"9dec57f9-b64b-4acb-93bc-33b09006407a","resolution":{"observed_at":"2026-08-14T04:32:15.962674Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:32:17.716437Z","title":"Tokenpacker: Efficient visual projector for multimodal llm,","venue":null,"work_id":"362fcffa-3252-4042-b604-2f50f06444c0","year":2025},"citing_paper":{"arxiv_id":"2608.08713","last_updated":"2026-08-09T13:57:50Z","snapshot_observed_at":"2026-08-14T22:24:17.619964Z","submitted_at":"2026-08-09T13:57:50Z","title":"Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-14T04:32:15.969203Z"},"links":{"citing_paper":"/paper/2608.08713"},"observation_digest":"sha256:d461b13320217b4a39bcf7164b847b2ca8c885ab5ac9c21e991aaf3a46337c7b","observation_id":"e2241c01-0af7-4560-ae1e-8fd34a2ff195","resolution":{"observed_at":"2026-08-14T04:32:17.723029Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:32:17.700136Z","title":"Flamingo: a visual language model for few-shot learning,","venue":null,"work_id":"90e7455a-d453-4f1c-bb02-26cd6e213d03","year":2022},"citing_paper":{"arxiv_id":"2608.08713","last_updated":"2026-08-09T13:57:50Z","snapshot_observed_at":"2026-08-14T22:24:17.619964Z","submitted_at":"2026-08-09T13:57:50Z","title":"Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-14T04:32:15.974748Z"},"links":{"citing_paper":"/paper/2608.08713"},"observation_digest":"sha256:b587bd00186b2049624bc46b6d919588250f41adeea30e769b3eb0024fe298e1","observation_id":"30dab69a-8dda-4a25-86bc-7276bdd5a42e","resolution":{"observed_at":"2026-08-14T04:32:17.705542Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:32:15.979696Z","title":"Totalsegmentator: robust segmentation of 104 anatomic structures in ct images,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.08713","last_updated":"2026-08-09T13:57:50Z","snapshot_observed_at":"2026-08-14T22:24:17.619964Z","submitted_at":"2026-08-09T13:57:50Z","title":"Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-14T04:32:15.979696Z"},"links":{"citing_paper":"/paper/2608.08713"},"observation_digest":"sha256:e7d115b8a5205cf6490bbea4a99384a48ebb496f006c4da64a2db951070a021f","observation_id":"8d6db3e7-9d23-4133-9e4f-b26e20f4e6f2","resolution":{"observed_at":"2026-08-14T04:32:15.979696Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.09001","last_updated":"2025-02-26T17:04:31Z","snapshot_observed_at":"2026-08-13T23:31:35.648299Z","submitted_at":"2025-01-15T18:30:58Z","title":"Vision Foundation Models for Computed Tomography","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.09001","snapshot_observed_at":"2026-08-14T04:32:15.984772Z","title":"Vision foundation models for computed tomogra- phy,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.08713","last_updated":"2026-08-09T13:57:50Z","snapshot_observed_at":"2026-08-14T22:24:17.619964Z","submitted_at":"2026-08-09T13:57:50Z","title":"Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-14T04:32:15.984772Z"},"links":{"cited_paper":"/paper/2501.09001","citing_paper":"/paper/2608.08713"},"observation_digest":"sha256:ebef24d97023ccf699fee29fffb8bc178cdd8817deabcd7f68d47e950d37311d","observation_id":"3e9a5cfb-2a77-42e3-a6fe-a929313db0af","resolution":{"observed_at":"2026-08-14T04:32:15.984772Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:32:17.672072Z","title":"Masked au- toencoders are scalable vision learners,","venue":null,"work_id":"4e08a29b-d067-45a4-a4c9-eeb181ef24f6","year":2022},"citing_paper":{"arxiv_id":"2608.08713","last_updated":"2026-08-09T13:57:50Z","snapshot_observed_at":"2026-08-14T22:24:17.619964Z","submitted_at":"2026-08-09T13:57:50Z","title":"Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-14T04:32:15.989792Z"},"links":{"citing_paper":"/paper/2608.08713"},"observation_digest":"sha256:dd0291112c2e1a4e2a54ac5c049741c6e34ee3dc9b881d41916092420cb1e1fb","observation_id":"a36ecd49-2e70-45da-a8be-2f047351b638","resolution":{"observed_at":"2026-08-14T04:32:17.677169Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:32:17.654152Z","title":"DINOv2: Learning robust visual features without supervision,","venue":null,"work_id":"7ecece3c-39ee-4276-b1fc-7a9f32a4e295","year":2024},"citing_paper":{"arxiv_id":"2608.08713","last_updated":"2026-08-09T13:57:50Z","snapshot_observed_at":"2026-08-14T22:24:17.619964Z","submitted_at":"2026-08-09T13:57:50Z","title":"Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-14T04:32:15.994294Z"},"links":{"citing_paper":"/paper/2608.08713"},"observation_digest":"sha256:5f51fd7aa1b1c136f2771465acf61d3be5291d555a3ac512933ed02c4ce49619","observation_id":"d5bf0bb4-9310-4ead-a105-f9ab5fc843f1","resolution":{"observed_at":"2026-08-14T04:32:17.659430Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:32:17.634501Z","title":"Learning transferable visual models from natural language supervision,","venue":null,"work_id":"4f9012ee-a92e-445c-bed6-1f402c31e731","year":2021},"citing_paper":{"arxiv_id":"2608.08713","last_updated":"2026-08-09T13:57:50Z","snapshot_observed_at":"2026-08-14T22:24:17.619964Z","submitted_at":"2026-08-09T13:57:50Z","title":"Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-14T04:32:15.998817Z"},"links":{"citing_paper":"/paper/2608.08713"},"observation_digest":"sha256:03da3450495dafcb1ba3b5c83356d59ad5a5fbde71f4e8abb45b128b71b59f8b","observation_id":"dcba1618-2b7c-402d-ae99-a3e4b8dd4b6c","resolution":{"observed_at":"2026-08-14T04:32:17.640793Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:32:16.004793Z","title":"A simple framework for contrastive learning of visual representations,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.08713","last_updated":"2026-08-09T13:57:50Z","snapshot_observed_at":"2026-08-14T22:24:17.619964Z","submitted_at":"2026-08-09T13:57:50Z","title":"Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-14T04:32:16.004793Z"},"links":{"citing_paper":"/paper/2608.08713"},"observation_digest":"sha256:d198ec6b7196906a899fb9118d562610be315b8301509c6547fa383028007abb","observation_id":"a2b7a60e-8898-4080-b079-b4746090e947","resolution":{"observed_at":"2026-08-14T04:32:16.004793Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.09388","last_updated":"2025-05-14T13:41:34Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-14T13:41:34Z","title":"Qwen3 Technical Report","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.09388","snapshot_observed_at":"2026-08-14T04:32:16.010295Z","title":"Qwen3 technical report,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.08713","last_updated":"2026-08-09T13:57:50Z","snapshot_observed_at":"2026-08-14T22:24:17.619964Z","submitted_at":"2026-08-09T13:57:50Z","title":"Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-14T04:32:16.010295Z"},"links":{"cited_paper":"/paper/2505.09388","citing_paper":"/paper/2608.08713"},"observation_digest":"sha256:7730dbda7920f3f5d58bdfd15ef939142e1a60c9ffbe3e956aa681a31077d488","observation_id":"1fa13ad5-786e-4f06-a469-253a7fb95ae2","resolution":{"observed_at":"2026-08-14T04:32:16.010295Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.01743","last_updated":"2025-03-07T09:05:58Z","snapshot_observed_at":"2026-08-15T22:57:45.773661Z","submitted_at":"2025-03-03T17:05:52Z","title":"Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.01743","snapshot_observed_at":"2026-08-14T04:32:16.015813Z","title":"Phi-4-mini technical report: Compact yet powerful multimodal language models via mixture-of- loras,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.08713","last_updated":"2026-08-09T13:57:50Z","snapshot_observed_at":"2026-08-14T22:24:17.619964Z","submitted_at":"2026-08-09T13:57:50Z","title":"Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-14T04:32:16.015813Z"},"links":{"cited_paper":"/paper/2503.01743","citing_paper":"/paper/2608.08713"},"observation_digest":"sha256:e8617280af54e03e27ba02845c7e1cf492c7f7e0f6d1d4ac42db44cdaef9644f","observation_id":"c239c8fc-ba17-407e-ae32-5427d2b3bfe5","resolution":{"observed_at":"2026-08-14T04:32:16.015813Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.19786","last_updated":"2025-03-25T15:52:34Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-03-25T15:52:34Z","title":"Gemma 3 Technical Report","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.19786","snapshot_observed_at":"2026-08-14T04:32:16.021476Z","title":"Gemma 3 technical report,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.08713","last_updated":"2026-08-09T13:57:50Z","snapshot_observed_at":"2026-08-14T22:24:17.619964Z","submitted_at":"2026-08-09T13:57:50Z","title":"Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-14T04:32:16.021476Z"},"links":{"cited_paper":"/paper/2503.19786","citing_paper":"/paper/2608.08713"},"observation_digest":"sha256:93854fde80d8ab7fc7f35e52f41382bb4444c089de647bec86db11a944bbdcb0","observation_id":"3328562c-e077-4aea-bd45-66f5d2c77b23","resolution":{"observed_at":"2026-08-14T04:32:16.021476Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:32:17.600527Z","title":"Reevalmed: Rethinking medical report evaluation by aligning metrics with real-world clinical judgment,","venue":null,"work_id":"742acaed-05b6-4d96-be1f-c7039bdb43e8","year":2025},"citing_paper":{"arxiv_id":"2608.08713","last_updated":"2026-08-09T13:57:50Z","snapshot_observed_at":"2026-08-14T22:24:17.619964Z","submitted_at":"2026-08-09T13:57:50Z","title":"Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-14T04:32:16.027404Z"},"links":{"citing_paper":"/paper/2608.08713"},"observation_digest":"sha256:26cfef4e7d372ad2d790981f7403266caed86699d8b02c856d752d16e1d6a425","observation_id":"5e5e0e82-3f82-41f2-be9e-1adecfd00ff0","resolution":{"observed_at":"2026-08-14T04:32:17.606692Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:32:17.581586Z","title":"Green: Generative radiology report evaluation and error notation,","venue":null,"work_id":"2a946094-2ac5-404a-9698-52acbee51ec6","year":2024},"citing_paper":{"arxiv_id":"2608.08713","last_updated":"2026-08-09T13:57:50Z","snapshot_observed_at":"2026-08-14T22:24:17.619964Z","submitted_at":"2026-08-09T13:57:50Z","title":"Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-14T04:32:16.032818Z"},"links":{"citing_paper":"/paper/2608.08713"},"observation_digest":"sha256:509d4bd7adce10b9f49ce7e97830824dc6a437ca884543dfffff9da2ce4aba79","observation_id":"05c9f676-d590-417d-94df-2f355a827389","resolution":{"observed_at":"2026-08-14T04:32:17.587603Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:32:17.563745Z","title":"Radbert: adapting transformer-based language models to radiology,","venue":null,"work_id":"83a01c47-1bfa-4680-8fc7-b45ed36a7785","year":2022},"citing_paper":{"arxiv_id":"2608.08713","last_updated":"2026-08-09T13:57:50Z","snapshot_observed_at":"2026-08-14T22:24:17.619964Z","submitted_at":"2026-08-09T13:57:50Z","title":"Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-14T04:32:16.038535Z"},"links":{"citing_paper":"/paper/2608.08713"},"observation_digest":"sha256:43b987255cf1ee0dc899876d9e2e4d6a55cd1f5257201e41a0b2318c63e2c16e","observation_id":"ed562441-2dbf-4716-b4b6-973fedf9bb1d","resolution":{"observed_at":"2026-08-14T04:32:17.569418Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:32:17.545690Z","title":"Eval- uating the evaluators: On the reliability of automated label extraction for radiology reports,","venue":null,"work_id":"86838c43-2047-45b0-9b3b-eecfabd0d31a","year":2026},"citing_paper":{"arxiv_id":"2608.08713","last_updated":"2026-08-09T13:57:50Z","snapshot_observed_at":"2026-08-14T22:24:17.619964Z","submitted_at":"2026-08-09T13:57:50Z","title":"Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-14T04:32:16.044052Z"},"links":{"citing_paper":"/paper/2608.08713"},"observation_digest":"sha256:545dbd70c48ff0467f02025cebfd1fec5eddbdd1801aac59dcd8adc2fc9fb6ac","observation_id":"6cb020d1-d7f4-4d45-aaec-439bffd66230","resolution":{"observed_at":"2026-08-14T04:32:17.550995Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:32:16.049619Z","title":"Bleu: a method for automatic evaluation of machine translation,","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2608.08713","last_updated":"2026-08-09T13:57:50Z","snapshot_observed_at":"2026-08-14T22:24:17.619964Z","submitted_at":"2026-08-09T13:57:50Z","title":"Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-14T04:32:16.049619Z"},"links":{"citing_paper":"/paper/2608.08713"},"observation_digest":"sha256:d8a291152f30fc2e23507db1cd7d04694d6b2f0d393232c76a0331c98f88d1d4","observation_id":"226b975d-1fd8-48f0-9837-976b473f9500","resolution":{"observed_at":"2026-08-14T04:32:16.049619Z","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":"2026-08-14T04:32:16.055415Z","title":"Meteor: An automatic metric for mt evaluation with improved correlation with human judgments,","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2608.08713","last_updated":"2026-08-09T13:57:50Z","snapshot_observed_at":"2026-08-14T22:24:17.619964Z","submitted_at":"2026-08-09T13:57:50Z","title":"Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-14T04:32:16.055415Z"},"links":{"citing_paper":"/paper/2608.08713"},"observation_digest":"sha256:095d4fe7c0a28d4467e0ed1a37a8cac7fab357ec4f5d18f208a5fab6351fadfe","observation_id":"cb482829-505d-42a7-8f59-91cf2d321f8d","resolution":{"observed_at":"2026-08-14T04:32:16.055415Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:32:17.500931Z","title":"Rouge: A package for automatic evaluation of summaries,","venue":null,"work_id":"20bede21-6dbe-4ecd-baab-884ac059aa67","year":2004},"citing_paper":{"arxiv_id":"2608.08713","last_updated":"2026-08-09T13:57:50Z","snapshot_observed_at":"2026-08-14T22:24:17.619964Z","submitted_at":"2026-08-09T13:57:50Z","title":"Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-14T04:32:16.061918Z"},"links":{"citing_paper":"/paper/2608.08713"},"observation_digest":"sha256:ba40bd6466dd3b28e59f7a1cc03eafd05f12de9959f5b1196ebb2c3e9a1598b6","observation_id":"2f4433a6-0b28-443b-9eaf-1dd53592d46a","resolution":{"observed_at":"2026-08-14T04:32:17.506127Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1504.00325","last_updated":"2015-04-03T20:21:16Z","snapshot_observed_at":"2026-08-16T01:18:27.067382Z","submitted_at":"2015-04-01T18:13:43Z","title":"Microsoft COCO Captions: Data Collection and Evaluation Server","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1504.00325","snapshot_observed_at":"2026-08-14T04:32:16.067360Z","title":"Microsoft coco captions: Data collection and evaluation server,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2608.08713","last_updated":"2026-08-09T13:57:50Z","snapshot_observed_at":"2026-08-14T22:24:17.619964Z","submitted_at":"2026-08-09T13:57:50Z","title":"Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-14T04:32:16.067360Z"},"links":{"cited_paper":"/paper/1504.00325","citing_paper":"/paper/2608.08713"},"observation_digest":"sha256:79b20f56cbc3f774cbd1c7e79cf5af193d291bd0beec98059f836bb5c5c40a61","observation_id":"c22615ad-9caa-474e-85bd-1b298fff0965","resolution":{"observed_at":"2026-08-14T04:32:16.067360Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:32:17.481018Z","title":"pycocoevalcap: Microsoft coco caption evaluation,","venue":null,"work_id":"9266ccfd-94b7-4cb5-9e88-34103dac5b44","year":2020},"citing_paper":{"arxiv_id":"2608.08713","last_updated":"2026-08-09T13:57:50Z","snapshot_observed_at":"2026-08-14T22:24:17.619964Z","submitted_at":"2026-08-09T13:57:50Z","title":"Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-14T04:32:16.072724Z"},"links":{"citing_paper":"/paper/2608.08713"},"observation_digest":"sha256:d74989a532e5c06d60eb3c08d2c0241cecfab587bd5ace10003d9abba3d08750","observation_id":"ce96ae6d-6b76-461c-9d6d-7aef6cb059f0","resolution":{"observed_at":"2026-08-14T04:32:17.487979Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:32:17.463512Z","title":"LoRA: Low-rank adaptation of large language models,","venue":null,"work_id":"fdf43c99-0d0b-4b10-ab0b-c99d7df14016","year":2022},"citing_paper":{"arxiv_id":"2608.08713","last_updated":"2026-08-09T13:57:50Z","snapshot_observed_at":"2026-08-14T22:24:17.619964Z","submitted_at":"2026-08-09T13:57:50Z","title":"Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-14T04:32:16.078263Z"},"links":{"citing_paper":"/paper/2608.08713"},"observation_digest":"sha256:b6393f77a41277899a900cfa26edd510c4da524ff6f9c79b13c666a84a041c62","observation_id":"bd6498e5-b5b9-43a9-8ac0-44c2942c0a06","resolution":{"observed_at":"2026-08-14T04:32:17.469009Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1711.05101","last_updated":"2019-01-04T21:01:49Z","snapshot_observed_at":"2026-08-14T20:13:52.872565Z","submitted_at":"2017-11-14T14:24:06Z","title":"Decoupled Weight Decay Regularization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.05101","snapshot_observed_at":"2026-08-14T04:32:16.083349Z","title":"Decoupled weight decay regularization,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.08713","last_updated":"2026-08-09T13:57:50Z","snapshot_observed_at":"2026-08-14T22:24:17.619964Z","submitted_at":"2026-08-09T13:57:50Z","title":"Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-14T04:32:16.083349Z"},"links":{"cited_paper":"/paper/1711.05101","citing_paper":"/paper/2608.08713"},"observation_digest":"sha256:dbad46afc5d815450f82de03dfb1a36a27ef759e0e7145cef479f6b8ba1c23b1","observation_id":"ce9fa2bb-0904-48e6-bc6a-726099a89dd2","resolution":{"observed_at":"2026-08-14T04:32:16.083349Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:32:17.446549Z","title":"An openmind for 3d medical vision self- supervised learning,","venue":null,"work_id":"13ae0e4b-a301-4ccc-b77a-09808b6de984","year":2025},"citing_paper":{"arxiv_id":"2608.08713","last_updated":"2026-08-09T13:57:50Z","snapshot_observed_at":"2026-08-14T22:24:17.619964Z","submitted_at":"2026-08-09T13:57:50Z","title":"Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-14T04:32:16.088363Z"},"links":{"citing_paper":"/paper/2608.08713"},"observation_digest":"sha256:84d98e25c3cb694e109cd5558258ff83dcd77b277bdcfa0ed474fdb6b82a0b02","observation_id":"3d636467-6769-4f7c-a277-abb5a4099552","resolution":{"observed_at":"2026-08-14T04:32:17.451474Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:32:16.093383Z","title":"Curriculum-driven 3d ct report generation via language-free visual graft- ing and zone-constrained compression,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.08713","last_updated":"2026-08-09T13:57:50Z","snapshot_observed_at":"2026-08-14T22:24:17.619964Z","submitted_at":"2026-08-09T13:57:50Z","title":"Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-14T04:32:16.093383Z"},"links":{"citing_paper":"/paper/2608.08713"},"observation_digest":"sha256:c64e1e469d730df0e040e9036d02310cd27da45a692ef68dc6b87f6d6cac9a3a","observation_id":"73274b76-32b8-47c7-8301-6126d75b1987","resolution":{"observed_at":"2026-08-14T04:32:16.093383Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:32:17.406046Z","title":"Ct-agent: A multimodal-llm agent for 3d ct radiology question answering,","venue":null,"work_id":"1ceb9ad6-bf59-4e13-ab57-2bee31365f72","year":2026},"citing_paper":{"arxiv_id":"2608.08713","last_updated":"2026-08-09T13:57:50Z","snapshot_observed_at":"2026-08-14T22:24:17.619964Z","submitted_at":"2026-08-09T13:57:50Z","title":"Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-14T04:32:16.098313Z"},"links":{"citing_paper":"/paper/2608.08713"},"observation_digest":"sha256:a7b0f0ce5fca61ccc061aaf82b6075c09cd709274b600009e09c5df689f20002","observation_id":"185b1a1f-5590-4255-a2b0-c22353a682c2","resolution":{"observed_at":"2026-08-14T04:32:17.421883Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:32:16.104203Z","title":"U-vlm: Hi- erarchical vision language modeling for report generation,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.08713","last_updated":"2026-08-09T13:57:50Z","snapshot_observed_at":"2026-08-14T22:24:17.619964Z","submitted_at":"2026-08-09T13:57:50Z","title":"Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-14T04:32:16.104203Z"},"links":{"citing_paper":"/paper/2608.08713"},"observation_digest":"sha256:72c924428cf8d5944874781a9aeed63c7340da71ce8d97b1115c9be668052ab0","observation_id":"81bc408f-dfc1-4ab3-98a2-0ce65b038e44","resolution":{"observed_at":"2026-08-14T04:32:16.104203Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2608.08713","last_updated":"2026-08-09T13:57:50Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-14T22:24:17.619964Z","submitted_at":"2026-08-09T13:57:50Z","title":"Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation"},"reference_resolution":{"displayed":51,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":22,"verified_exact":2,"verified_fuzzy":27},"total_outbound_references":51},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 51 of 51 outbound references and 0 inbound Pith citation observations for arXiv:2608.08713."}